Skip to content

Same agent Smaller bill. The tools and infrastructure to get more work from your AI. Fewer tokens. Less compute. Lower cost.

Docs (#191)

patcher99feb19091521
diff --git a/docs/.DS_Store b/docs/.DS_Store
index 13c2248b..c9d5392d 100644
Binary files a/docs/.DS_Store and b/docs/.DS_Store differ
diff --git a/docs/README.md b/docs/README.md
deleted file mode 100644
index c89c478d..00000000
--- a/docs/README.md
+++ /dev/null
@@ -1,32 +0,0 @@
-# Mintlify Starter Kit
-
-Click on `Use this template` to copy the Mintlify starter kit. The starter kit contains examples including
-
-- Guide pages
-- Navigation
-- Customizations
-- API Reference pages
-- Use of popular components
-
-### Development
-
-Install the [Mintlify CLI](https://www.npmjs.com/package/mintlify) to preview the documentation changes locally. To install, use the following command
-
-```
-npm i -g mintlify
-```
-
-Run the following command at the root of your documentation (where mint.json is)
-
-```
-mintlify dev
-```
-
-### Publishing Changes
-
-Install our Github App to autopropagate changes from youre repo to your deployment. Changes will be deployed to production automatically after pushing to the default branch. Find the link to install on your dashboard.
-
-#### Troubleshooting
-
-- Mintlify dev isn't running - Run `mintlify install` it'll re-install dependencies.
-- Page loads as a 404 - Make sure you are running in a folder with `mint.json`
diff --git a/docs/favicon.png b/docs/favicon.png
index 52424074..122a5b19 100644
Binary files a/docs/favicon.png and b/docs/favicon.png differ
diff --git a/docs/latest/api-reference/endpoint/connections/get.mdx b/docs/latest/api-reference/endpoint/connections/get.mdx
index 6e50f6db..fbc924fc 100644
--- a/docs/latest/api-reference/endpoint/connections/get.mdx
+++ b/docs/latest/api-reference/endpoint/connections/get.mdx
@@ -1,6 +1,4 @@
---
title: 'Get Connection'
openapi: 'GET /api/connections'
----
-
-This functionality was introduced to the Doku Ingester in version `0.1.2`
\ No newline at end of file
+---
\ No newline at end of file
diff --git a/docs/latest/api-reference/introduction.mdx b/docs/latest/api-reference/introduction.mdx
index 278fdf41..fb4d34fb 100644
--- a/docs/latest/api-reference/introduction.mdx
+++ b/docs/latest/api-reference/introduction.mdx
@@ -1,6 +1,6 @@
---
title: 'Introduction'
-description: 'OpenAPI specification for API Endpoints in Doku'
+description: 'OpenAPI specification for API Endpoints in OpenLIT'
---
<CardGroup cols={2}>
<Card
diff --git a/docs/latest/configuration.mdx b/docs/latest/configuration.mdx
index 8b79b933..302ce47e 100644
--- a/docs/latest/configuration.mdx
+++ b/docs/latest/configuration.mdx
@@ -6,9 +6,7 @@ icon: 'sliders'
This guide covers all the available environment variables to fine-tune OpenLIT according to your needs.
-## OpenLIT Client
-
-### Environment Varibales
+## Environment Varibales
<ResponseField name="INIT_DB_HOST" required>
Sets the host address of the ClickHouse server for OpenLIT Client to connect
@@ -64,7 +62,7 @@ This guide covers all the available environment variables to fine-tune OpenLIT a
```
</ResponseField>
-### Sample Environment File (.env)
+## Sample Environment File (.env)
```.env.example .env
INIT_DB_HOST="127.0.0.1"
@@ -75,122 +73,6 @@ INIT_DB_PASSWORD="OPENLIT"
SQLITE_DATABASE_URL="file:/app/client/data/data.db"
```
-## OpenLIT Ingester
-
-### Environment Varibales
-
-<ResponseField name="DOKU_DB_HOST" required>
- Sets the host address of the ClickHouse server for OpenLIT Ingester to connect
-
- **Example**:
- ```yaml
- export DOKU_DB_HOST=127.0.0.1
- ```
-</ResponseField>
-
-<ResponseField name="DOKU_DB_PORT" required>
- Sets the port on which ClickHouse listens
-
- **Example**:
- ```yaml
- export DOKU_DB_PORT=9000
- ```
-</ResponseField>
-
-<ResponseField name="DOKU_DB_NAME" required>
- Sets the name of the database in Clickhouse to be used by OpenLIT
-
- **Example**:
- ```yaml
- export DOKU_DB_NAME=default
- ```
-</ResponseField>
-
-<ResponseField name="DOKU_DB_USER" required>
- Sets the username for authenticating with ClickHouse
-
- **Example**:
- ```yaml
- export DOKU_DB_USER=default
- ```
-</ResponseField>
-
-<ResponseField name="DOKU_DB_PASSWORD" required>
- Sets the password for authenticating with ClickHouse
-
- **Example**:
- ```yaml
- export DOKU_DB_PASSWORD=OPENLIT
- ```
-</ResponseField>
-
-<ResponseField name="DOKU_PRICING_JSON_URL">
- Sets the URL of the json file containing the LLM Pricing data
-
-**Default Value**:
-```shell
-https://raw.githubusercontent.com/dokulabs/ingester/main/assets/pricing.json
-```
-
-**Example**:
-```yaml
-export DOKU_PRICING_JSON_URL=https://raw.githubusercontent.com/dokulabs/ingester/main/assets/pricing.json
- ```
-</ResponseField>
-
-<ResponseField name="DOKU_DB_MAX_IDLE_CONNS">
- Sets the maximum number of concurrent idle database connections.
-
-**Default Value**:
-```shell
-10
-```
-
-**Example**:
-```shell
-export DOKU_DB_MAX_IDLE_CONNS=10
-```
-</ResponseField>
-
-<ResponseField name="DOKU_DB_MAX_OPEN_CONNS">
- Sets the maximum number of concurrent open database connections.
-
-**Default Value**:
-```shell
-20
-```
-
-**Example**:
-```shell
-export DOKU_DB_MAX_OPEN_CONNS=20
-```
-</ResponseField>
-
-<ResponseField name="DOKU_DB_RETENTION_PERIOD">
- Sets the TTL for data in Clickhouse.
-
-**Default Value**:
-```shell
-6 MONTH
-```
-
-**Example**:
-```shell
-export DOKU_DB_RETENTION_PERIOD="6 MONTH"
-```
-</ResponseField>
-
-
-### Sample Environment File (.env)
-
-```.env.example .env
-DOKU_DB_HOST="127.0.0.1"
-DOKU_DB_PORT="9000"
-DOKU_DB_NAME="default"
-DOKU_DB_USER="default"
-DOKU_DB_PASSWORD="OPENLIT"
-```
-
---
<CardGroup cols={2}>
diff --git a/docs/latest/connections/datadog.mdx b/docs/latest/connections/datadog.mdx
index a3d67e73..0f839e44 100644
--- a/docs/latest/connections/datadog.mdx
+++ b/docs/latest/connections/datadog.mdx
@@ -1,877 +1,16 @@
---
title: 'DataDog'
-description: 'LLM Observability with DataDog and Doku'
+description: 'LLM Observability with Grafana Tempo and OpenLIT'
---
-<Frame>
- <img src="https://github.com/dokulabs/doku/blob/main/docs/images/datadog-dashboard-1.jpg?raw=true" />
- <img src="https://github.com/dokulabs/doku/blob/main/docs/images/datadog-dashboard-2.jpg?raw=true" />
-</Frame>
+To send OpenTelemetry data collected by OpenLIt from your LLM Application, You need to set the `otlp_endpoint` and `otlp_headers` arguments according to your needs.
-Doku can automatically send LLM usage data from Doku to DataDog using the [Submit Metrics API](https://docs.datadoghq.com/api/latest/metrics/#submit-metrics) and [Send Logs API](https://docs.datadoghq.com/api/latest/logs/#send-logs)
+```python
+import openlit
-Make the following curl request to Doku to add a connection for DataDog. See more on the [Connections API](/latest/api-reference/endpoint/connections/create)
-
-```shell
-curl --request POST \
- --url https://<YOUR_DOKU_INGESTER_URL>/api/connections \
- --header 'Authorization: <DOKU_API_KEY>' \
- --header 'Content-Type: application/json' \
- --data '{
- "Platform": "datadog",
- "MetricsUrl": "<YOUR_DD_METRICS_URL>",
- "LogsUrl": "<YOUR_DD_LOGS_URL>",
- "ApiKey": "<YOUR_DD_API_KEY>"
-}'
+openlit.init(otlp_endpoint="otlp_backend_endpoint", otlp_headers="otlp_backend_token")
```
-## DataDog Resources
-
-<Accordion title="Dashboard">
- ```json
- {
- "title": "Doku - LLM Monitoring",
- "description": "Dashboard to monitor LLM Applications using Doku",
- "widgets": [
- {
- "id": 2592087041529600,
- "definition": {
- "type": "image",
- "url": "https://github.com/dokulabs/.github/blob/main/profile/assets/favicon.png?raw=true",
- "sizing": "contain",
- "has_background": false,
- "has_border": false,
- "vertical_align": "center",
- "horizontal_align": "center"
- },
- "layout": {
- "x": 0,
- "y": 0,
- "width": 12,
- "height": 1
- }
- },
- {
- "id": 1254363734970878,
- "definition": {
- "title": "Avg Request Duration",
- "title_size": "16",
- "title_align": "left",
- "type": "query_value",
- "requests": [
- {
- "response_format": "scalar",
- "queries": [
- {
- "data_source": "metrics",
- "name": "query1",
- "query": "avg:doku.llm.request.duration{host:doku,$applicationname,$environment}",
- "aggregator": "avg"
- }
- ],
- "conditional_formats": [
- {
- "comparator": "<=",
- "value": 10,
- "palette": "white_on_green"
- },
- {
- "comparator": ">",
- "value": 10,
- "palette": "white_on_red"
- }
- ],
- "formulas": [
- {
- "number_format": {
- "unit": {
- "type": "canonical_unit",
- "unit_name": "second"
- }
- },
- "formula": "query1"
- }
- ]
- }
- ],
- "autoscale": true,
- "precision": 2,
- "timeseries_background": {
- "yaxis": {
- "include_zero": false
- },
- "type": "area"
- }
- },
- "layout": {
- "x": 0,
- "y": 1,
- "width": 3,
- "height": 2
- }
- },
- {
- "id": 5019934425891746,
- "definition": {
- "title": "Avg Total Tokens",
- "title_size": "16",
- "title_align": "left",
- "type": "query_value",
- "requests": [
- {
- "response_format": "scalar",
- "queries": [
- {
- "data_source": "metrics",
- "name": "query1",
- "query": "avg:doku.llm.total.tokens{host:doku,$applicationname,$environment}",
- "aggregator": "avg"
- }
- ],
- "conditional_formats": [
- {
- "comparator": "<=",
- "value": 1000,
- "palette": "white_on_green"
- },
- {
- "comparator": ">",
- "value": 1000,
- "palette": "white_on_red"
- }
- ],
- "formulas": [
- {
- "formula": "query1"
- }
- ]
- }
- ],
- "autoscale": true,
- "precision": 2,
- "timeseries_background": {
- "type": "area"
- }
- },
- "layout": {
- "x": 3,
- "y": 1,
- "width": 3,
- "height": 2
- }
- },
- {
- "id": 1292553433133982,
- "definition": {
- "title": "Avg Cost / Request",
- "title_size": "16",
- "title_align": "left",
- "type": "query_value",
- "requests": [
- {
- "formulas": [
- {
- "formula": "query1",
- "number_format": {
- "unit": {
- "type": "canonical_unit",
- "unit_name": "dollar"
- }
- }
- }
- ],
- "queries": [
- {
- "data_source": "metrics",
- "name": "query1",
- "query": "avg:doku.llm.usage.cost{host:doku,$applicationname,$environment}",
- "aggregator": "max"
- }
- ],
- "response_format": "scalar",
- "conditional_formats": [
- {
- "comparator": ">",
- "value": 0,
- "palette": "custom_bg",
- "custom_bg_color": "#5c7cff"
- }
- ]
- }
- ],
- "autoscale": true,
- "precision": 2,
- "timeseries_background": {
- "yaxis": {
- "include_zero": true
- },
- "type": "area"
- }
- },
- "layout": {
- "x": 6,
- "y": 1,
- "width": 3,
- "height": 2
- }
- },
- {
- "id": 5207596770618026,
- "definition": {
- "title": "Total Cost",
- "title_size": "16",
- "title_align": "left",
- "type": "query_value",
- "requests": [
- {
- "response_format": "scalar",
- "queries": [
- {
- "data_source": "metrics",
- "name": "query1",
- "query": "sum:doku.llm.usage.cost{host:doku,$applicationname,$environment}",
- "aggregator": "avg"
- }
- ],
- "formulas": [
- {
- "number_format": {
- "unit": {
- "type": "canonical_unit",
- "unit_name": "dollar"
- }
- },
- "formula": "query1"
- }
- ]
- }
- ],
- "autoscale": true,
- "precision": 2,
- "timeseries_background": {
- "type": "bars"
- }
- },
- "layout": {
- "x": 9,
- "y": 1,
- "width": 3,
- "height": 2
- }
- },
- {
- "id": 7163232112237060,
- "definition": {
- "title": "Requests",
- "title_size": "16",
- "title_align": "left",
- "show_legend": false,
- "legend_layout": "auto",
- "legend_columns": [
- "avg",
- "min",
- "max",
- "value",
- "sum"
- ],
- "type": "timeseries",
- "requests": [
- {
- "formulas": [
- {
- "formula": "query1"
- }
- ],
- "queries": [
- {
- "data_source": "metrics",
- "name": "query1",
- "query": "count:doku.llm.request.duration{host:doku,$applicationname,$environment}"
- }
- ],
- "response_format": "timeseries",
- "style": {
- "palette": "blue",
- "line_type": "solid",
- "line_width": "normal"
- },
- "display_type": "line"
- }
- ]
- },
- "layout": {
- "x": 0,
- "y": 3,
- "width": 12,
- "height": 3
- }
- },
- {
- "id": 6530509092714956,
- "definition": {
- "title": "Usage cost by Category",
- "title_size": "16",
- "title_align": "left",
- "requests": [
- {
- "response_format": "scalar",
- "formulas": [
- {
- "number_format": {
- "unit": {
- "type": "canonical_unit",
- "unit_name": "dollar"
- }
- },
- "formula": "query1",
- "limit": {
- "count": 500,
- "order": "desc"
- }
- }
- ],
- "queries": [
- {
- "data_source": "metrics",
- "name": "query1",
- "query": "sum:doku.llm.usage.cost{host:doku,$applicationname,$environment} by {generation}",
- "aggregator": "avg"
- }
- ],
- "style": {
- "palette": "datadog16"
- }
- }
- ],
- "type": "sunburst",
- "hide_total": true,
- "legend": {
- "type": "inline"
- }
- },
- "layout": {
- "x": 0,
- "y": 6,
- "width": 3,
- "height": 3
- }
- },
- {
- "id": 8042116329904768,
- "definition": {
- "title": "Usage cost by Platform",
- "title_size": "16",
- "title_align": "left",
- "requests": [
- {
- "response_format": "scalar",
- "formulas": [
- {
- "number_format": {
- "unit": {
- "type": "canonical_unit",
- "unit_name": "dollar"
- }
- },
- "formula": "query1",
- "limit": {
- "count": 500,
- "order": "desc"
- }
- }
- ],
- "queries": [
- {
- "data_source": "metrics",
- "name": "query1",
- "query": "sum:doku.llm.usage.cost{host:doku,$applicationname,$environment} by {platform}",
- "aggregator": "avg"
- }
- ],
- "style": {
- "palette": "datadog16"
- }
- }
- ],
- "type": "sunburst",
- "hide_total": true,
- "legend": {
- "type": "inline"
- }
- },
- "layout": {
- "x": 3,
- "y": 6,
- "width": 3,
- "height": 3
- }
- },
- {
- "id": 6701701162130436,
- "definition": {
- "title": "Usage cost by Application",
- "title_size": "16",
- "title_align": "left",
- "requests": [
- {
- "response_format": "scalar",
- "formulas": [
- {
- "number_format": {
- "unit": {
- "type": "canonical_unit",
- "unit_name": "dollar"
- }
- },
- "formula": "query1",
- "limit": {
- "count": 500,
- "order": "desc"
- }
- }
- ],
- "queries": [
- {
- "data_source": "metrics",
- "name": "query1",
- "query": "sum:doku.llm.usage.cost{host:doku,$applicationname,$environment} by {applicationname}",
- "aggregator": "sum"
- }
- ],
- "style": {
- "palette": "datadog16"
- }
- }
- ],
- "type": "sunburst",
- "hide_total": true,
- "legend": {
- "type": "inline"
- }
- },
- "layout": {
- "x": 6,
- "y": 6,
- "width": 3,
- "height": 3
- }
- },
- {
- "id": 1437027828906050,
- "definition": {
- "title": "Usage cost by Environment",
- "title_size": "16",
- "title_align": "left",
- "requests": [
- {
- "response_format": "scalar",
- "formulas": [
- {
- "number_format": {
- "unit": {
- "type": "canonical_unit",
- "unit_name": "dollar"
- }
- },
- "formula": "query1",
- "limit": {
- "count": 500,
- "order": "desc"
- }
- }
- ],
- "queries": [
- {
- "data_source": "metrics",
- "name": "query1",
- "query": "sum:doku.llm.usage.cost{host:doku,$applicationname,$environment} by {environment}",
- "aggregator": "avg"
- }
- ],
- "style": {
- "palette": "datadog16"
- }
- }
- ],
- "type": "sunburst",
- "hide_total": true,
- "legend": {
- "type": "inline"
- }
- },
- "layout": {
- "x": 9,
- "y": 6,
- "width": 3,
- "height": 3
- }
- },
- {
- "id": 2402383159288882,
- "definition": {
- "title": "Avg Prompt Tokens",
- "title_size": "16",
- "title_align": "left",
- "type": "query_value",
- "requests": [
- {
- "response_format": "scalar",
- "queries": [
- {
- "data_source": "metrics",
- "name": "query1",
- "query": "avg:doku.llm.prompt.tokens{host:doku,$applicationname,$environment}",
- "aggregator": "avg"
- }
- ],
- "conditional_formats": [
- {
- "comparator": "<=",
- "value": 1000,
- "palette": "white_on_green"
- },
- {
- "comparator": ">",
- "value": 1000,
- "palette": "white_on_red"
- }
- ],
- "formulas": [
- {
- "formula": "query1"
- }
- ]
- }
- ],
- "autoscale": true,
- "precision": 2,
- "timeseries_background": {
- "type": "area"
- }
- },
- "layout": {
- "x": 0,
- "y": 9,
- "width": 4,
- "height": 1
- }
- },
- {
- "id": 1887750495626080,
- "definition": {
- "title": "Avg Token Usage",
- "title_size": "16",
- "title_align": "left",
- "show_legend": true,
- "legend_layout": "auto",
- "legend_columns": [
- "avg",
- "min",
- "max",
- "value",
- "sum"
- ],
- "type": "timeseries",
- "requests": [
- {
- "formulas": [
- {
- "formula": "query1"
- },
- {
- "formula": "query2"
- }
- ],
- "queries": [
- {
- "data_source": "metrics",
- "name": "query1",
- "query": "avg:doku.llm.prompt.tokens{host:doku,$applicationname,$environment}"
- },
- {
- "data_source": "metrics",
- "name": "query2",
- "query": "avg:doku.llm.completion.tokens{host:doku,$applicationname,$environment}"
- }
- ],
- "response_format": "timeseries",
- "style": {
- "palette": "dog_classic",
- "line_type": "solid",
- "line_width": "normal"
- },
- "display_type": "line"
- }
- ]
- },
- "layout": {
- "x": 4,
- "y": 9,
- "width": 8,
- "height": 2
- }
- },
- {
- "id": 8227251321537566,
- "definition": {
- "title": "Avg Completion Tokens",
- "title_size": "16",
- "title_align": "left",
- "type": "query_value",
- "requests": [
- {
- "response_format": "scalar",
- "queries": [
- {
- "data_source": "metrics",
- "name": "query1",
- "query": "avg:doku.llm.completion.tokens{host:doku,$applicationname,$environment}",
- "aggregator": "avg"
- }
- ],
- "conditional_formats": [
- {
- "comparator": "<=",
- "value": 1000,
- "palette": "white_on_green"
- },
- {
- "comparator": ">",
- "value": 1000,
- "palette": "white_on_red"
- }
- ],
- "formulas": [
- {
- "formula": "query1"
- }
- ]
- }
- ],
- "autoscale": true,
- "precision": 2,
- "timeseries_background": {
- "type": "area"
- }
- },
- "layout": {
- "x": 0,
- "y": 10,
- "width": 4,
- "height": 1
- }
- },
- {
- "id": 3302397057575330,
- "definition": {
- "title": "Top Models by Usage",
- "title_size": "16",
- "title_align": "left",
- "type": "toplist",
- "requests": [
- {
- "queries": [
- {
- "data_source": "metrics",
- "name": "query1",
- "query": "sum:doku.llm.usage.cost{host:doku,$applicationname,$environment} by {model}",
- "aggregator": "avg"
- }
- ],
- "formulas": [
- {
- "number_format": {
- "unit": {
- "type": "canonical_unit",
- "unit_name": "dollar"
- }
- },
- "formula": "query1",
- "limit": {
- "count": 5,
- "order": "desc"
- }
- }
- ],
- "response_format": "scalar"
- }
- ],
- "style": {
- "display": {
- "type": "stacked",
- "legend": "automatic"
- }
- }
- },
- "layout": {
- "x": 0,
- "y": 11,
- "width": 4,
- "height": 3
- }
- },
- {
- "id": 2328926103668336,
- "definition": {
- "title": "Avg Cost by Models",
- "title_size": "16",
- "title_align": "left",
- "show_legend": true,
- "legend_layout": "horizontal",
- "legend_columns": [
- "avg",
- "min",
- "max",
- "value",
- "sum"
- ],
- "type": "timeseries",
- "requests": [
- {
- "formulas": [
- {
- "number_format": {
- "unit": {
- "type": "canonical_unit",
- "unit_name": "dollar"
- }
- },
- "formula": "query1"
- }
- ],
- "queries": [
- {
- "data_source": "metrics",
- "name": "query1",
- "query": "avg:doku.llm.usage.cost{host:doku,$applicationname,$environment} by {model}"
- }
- ],
- "response_format": "timeseries",
- "style": {
- "palette": "dog_classic",
- "line_type": "solid",
- "line_width": "normal"
- },
- "display_type": "line"
- }
- ]
- },
- "layout": {
- "x": 4,
- "y": 11,
- "width": 8,
- "height": 3
- }
- },
- {
- "id": 6390170780704056,
- "definition": {
- "title": "Prompt",
- "title_size": "16",
- "title_align": "left",
- "requests": [
- {
- "response_format": "event_list",
- "query": {
- "data_source": "logs_stream",
- "query_string": "host:doku type:prompt $applicationname $environment",
- "indexes": [],
- "storage": "hot"
- },
- "columns": [
- {
- "field": "status_line",
- "width": "auto"
- },
- {
- "field": "timestamp",
- "width": "auto"
- },
- {
- "field": "content",
- "width": "compact"
- }
- ]
- }
- ],
- "type": "list_stream"
- },
- "layout": {
- "x": 0,
- "y": 14,
- "width": 6,
- "height": 5
- }
- },
- {
- "id": 8605893614511422,
- "definition": {
- "title": "Response",
- "title_size": "16",
- "title_align": "left",
- "requests": [
- {
- "response_format": "event_list",
- "query": {
- "data_source": "logs_stream",
- "query_string": "host:doku $applicationname type:(response OR image) $environment",
- "indexes": [],
- "storage": "hot"
- },
- "columns": [
- {
- "field": "status_line",
- "width": "auto"
- },
- {
- "field": "timestamp",
- "width": "auto"
- },
- {
- "field": "content",
- "width": "compact"
- }
- ]
- }
- ],
- "type": "list_stream"
- },
- "layout": {
- "x": 6,
- "y": 14,
- "width": 6,
- "height": 5
- }
- }
- ],
- "template_variables": [
- {
- "name": "applicationname",
- "prefix": "applicationname",
- "available_values": [],
- "default": "*"
- },
- {
- "name": "environment",
- "prefix": "environment",
- "available_values": [],
- "default": "*"
- }
- ],
- "layout_type": "ordered",
- "notify_list": [],
- "reflow_type": "fixed"
- }
- ```
-</Accordion>
-
----
+Alternatively, you can configure the OTLP endpoint by setting the `OTEL_EXPORTER_OTLP_ENDPOINT` and the OTLP headers by setting the Appli`OTEL_EXPORTER_OTLP_HEADERS` environmentcation variable as recommended in the OpenTelemetry documentation.
-<CardGroup cols={2}>
-<Card title="Integrations" href="/latest/integrations/introduction" icon='circle-nodes'>
-Integrate your LLM Provider with Doku
-</Card>
-<Card title="API Reference" href="/latest/api-reference/introduction" icon='code'>
-OpenAPI specification for API Endpoints in Doku
-</Card>
-</CardGroup>
\ No newline at end of file
+Refer to the OpenLIT [Python SDK repository](https://github.com/openlit/openlit/tree/main/sdk/python) for more advanced configurations and use cases.
diff --git a/docs/latest/connections/dynatrace.mdx b/docs/latest/connections/dynatrace.mdx
index c232c04a..ef80d65c 100644
--- a/docs/latest/connections/dynatrace.mdx
+++ b/docs/latest/connections/dynatrace.mdx
@@ -1,1773 +1,16 @@
---
title: 'Dynatrace'
-description: 'LLM Observability with Dynatrace and Doku'
+description: 'LLM Observability with Dynatrace and OpenLIT'
---
-<Frame>
- <img src="https://github.com/dokulabs/doku/blob/main/docs/images/dynatrace-dashboard-1.jpg?raw=true" />
- <img src="https://github.com/dokulabs/doku/blob/main/docs/images/dynatrace-dashboard-2.jpg?raw=true" />
- <img src="https://github.com/dokulabs/doku/blob/main/docs/images/dynatrace-dsahboard-3.jpg?raw=true" />
-</Frame>
+To send OpenTelemetry data collected by OpenLIt from your LLM Application, You need to set the `otlp_endpoint` and `otlp_headers` arguments according to your needs.
-Doku can automatically send LLM usage data from Doku to Dynatrace using the [Ingest Metrics API](https://docs.dynatrace.com/docs/dynatrace-api/environment-api/metric-v2/post-ingest-metrics) and [Ingest Logs API](https://docs.dynatrace.com/docs/dynatrace-api/environment-api/log-monitoring-v2/post-ingest-logs)
+```python
+import openlit
-Make the following curl request to Doku to add a connection for Dynatrace. See more on the [Connections API](/latest/api-reference/endpoint/connections/create)
-
-```shell
-curl --request POST \
- --url https://<YOUR_DOKU_INGESTER_URL>/api/connections \
- --header 'Authorization: <DOKU_API_KEY>' \
- --header 'Content-Type: application/json' \
- --data '{
- "Platform": "dynatrace",
- "MetricsUrl": "<YOUR_DYNATRACE_METRICS_URL>",
- "LogsUrl": "<YOUR_DYNATRACE_LOGS_URL>",
- "ApiKey": "<YOUR_DYNATRACE_API_KEY>"
-}'
+openlit.init(otlp_endpoint="otlp_backend_endpoint", otlp_headers="otlp_backend_token")
```
-## Dynatrace Resources
-
-<Accordion title="Dashboard">
- ```json
- {
- "version": 13,
- "variables": [],
- "tiles": {
- "1": {
- "type": "data",
- "title": "",
- "query": "fetch logs\n| filter type == \"prompt\"\n| limit 20",
- "queryConfig": {
- "limit": 20,
- "additionalFilters": {
- "type": [
- {
- "criteria": "equals",
- "expression": "prompt"
- }
- ]
- },
- "version": "4.0.1",
- "datatype": "logs",
- "log.source": [
- {
- "criteria": "contains",
- "expression": ""
- }
- ],
- "content": [
- {
- "criteria": "contains",
- "expression": ""
- }
- ]
- },
- "subType": "dql-builder-logs",
- "visualization": "table",
- "visualizationSettings": {
- "thresholds": [],
- "chartSettings": {
- "gapPolicy": "connect",
- "circleChartSettings": {
- "groupingThresholdType": "relative",
- "groupingThresholdValue": 0,
- "valueType": "relative"
- },
- "categoryOverrides": {},
- "categoricalBarChartSettings": {}
- },
- "singleValue": {
- "showLabel": true,
- "label": "",
- "prefixIcon": "",
- "recordField": "timestamp",
- "autoscale": true,
- "alignment": "center",
- "colorThresholdTarget": "value"
- },
- "table": {
- "rowDensity": "default",
- "enableSparklines": false,
- "hiddenColumns": [
- [
- "event.type"
- ],
- [
- "loglevel"
- ],
- [
- "status"
- ],
- [
- "dt.auth.origin"
- ],
- [
- "custom.attribute"
- ],
- [
- "type"
- ],
- [
- "endpoint"
- ],
- [
- "environment"
- ],
- [
- "generation"
- ],
- [
- "job"
- ],
- [
- "platform"
- ],
- [
- "source"
- ],
- [
- "cost"
- ],
- [
- "application"
- ]
- ],
- "lineWrapIds": [
- [
- "timestamp"
- ],
- [
- "content"
- ],
- [
- "event.type"
- ],
- [
- "loglevel"
- ],
- [
- "status"
- ],
- [
- "application"
- ],
- [
- "cost"
- ],
- [
- "dt.auth.origin"
- ],
- [
- "endpoint"
- ],
- [
- "environment"
- ],
- [
- "generation"
- ],
- [
- "job"
- ],
- [
- "model"
- ],
- [
- "platform"
- ],
- [
- "source"
- ],
- [
- "type"
- ]
- ],
- "columnWidths": {
- "[\"timestamp\"]": 105,
- "[\"application\"]": 113,
- "[\"cost\"]": 75,
- "[\"content\"]": 383
- },
- "colorThresholdTarget": "background",
- "sortBy": {
- "columnId": "[\"timestamp\"]",
- "direction": "descending"
- }
- }
- }
- },
- "2": {
- "type": "data",
- "title": "",
- "query": "fetch logs\n| filter type != \"prompt\"\n| limit 20",
- "queryConfig": {
- "limit": 20,
- "additionalFilters": {
- "type": [
- {
- "criteria": "not-equals",
- "expression": "prompt"
- }
- ]
- },
- "version": "4.0.1",
- "datatype": "logs",
- "log.source": [
- {
- "criteria": "contains",
- "expression": ""
- }
- ],
- "content": [
- {
- "criteria": "contains",
- "expression": ""
- }
- ]
- },
- "subType": "dql-builder-logs",
- "visualization": "table",
- "visualizationSettings": {
- "thresholds": [],
- "chartSettings": {
- "gapPolicy": "connect",
- "circleChartSettings": {
- "groupingThresholdType": "relative",
- "groupingThresholdValue": 0,
- "valueType": "relative"
- },
- "categoryOverrides": {},
- "categoricalBarChartSettings": {}
- },
- "singleValue": {
- "showLabel": true,
- "label": "",
- "prefixIcon": "",
- "recordField": "timestamp",
- "autoscale": true,
- "alignment": "center",
- "colorThresholdTarget": "value"
- },
- "table": {
- "rowDensity": "default",
- "enableSparklines": false,
- "hiddenColumns": [
- [
- "event.type"
- ],
- [
- "loglevel"
- ],
- [
- "status"
- ],
- [
- "dt.auth.origin"
- ],
- [
- "custom.attribute"
- ],
- [
- "type"
- ],
- [
- "endpoint"
- ],
- [
- "environment"
- ],
- [
- "generation"
- ],
- [
- "job"
- ],
- [
- "platform"
- ],
- [
- "source"
- ],
- [
- "cost"
- ],
- [
- "application"
- ]
- ],
- "lineWrapIds": [
- [
- "timestamp"
- ],
- [
- "content"
- ],
- [
- "event.type"
- ],
- [
- "loglevel"
- ],
- [
- "status"
- ],
- [
- "application"
- ],
- [
- "cost"
- ],
- [
- "dt.auth.origin"
- ],
- [
- "endpoint"
- ],
- [
- "environment"
- ],
- [
- "generation"
- ],
- [
- "job"
- ],
- [
- "model"
- ],
- [
- "platform"
- ],
- [
- "source"
- ],
- [
- "type"
- ]
- ],
- "columnWidths": {
- "[\"timestamp\"]": 104,
- "[\"application\"]": 113,
- "[\"cost\"]": 75,
- "[\"content\"]": 413
- },
- "colorThresholdTarget": "background",
- "sortBy": {
- "columnId": "[\"timestamp\"]",
- "direction": "descending"
- }
- }
- }
- },
- "7": {
- "type": "data",
- "title": "",
- "query": "timeseries duration=avg(doku.llm.request.duration, rollup: count)\n| sort arrayAvg(duration) desc\n| limit 20\n| fieldsAdd duration.single_value=arraySum(duration)",
- "davis": {
- "enabled": false,
- "davisVisualization": {
- "isAvailable": true
- }
- },
- "visualization": "singleValue",
- "visualizationSettings": {
- "thresholds": [
- {
- "id": "0",
- "title": "",
- "field": "",
- "rules": [
- {
- "id": "0",
- "label": "",
- "comparator": "≥",
- "color": "#7dc540"
- },
- {
- "id": "1",
- "label": "",
- "comparator": "≥",
- "color": "#f5d30f"
- },
- {
- "id": "2",
- "label": "",
- "comparator": "≥",
- "color": "#dc172a"
- }
- ],
- "isEnabled": true
- }
- ],
- "chartSettings": {
- "gapPolicy": "connect",
- "circleChartSettings": {
- "groupingThresholdType": "relative",
- "groupingThresholdValue": 0,
- "valueType": "relative"
- },
- "categoryOverrides": {},
- "fieldMapping": {
- "timestamp": "timeframe",
- "leftAxisValues": [
- "duration"
- ],
- "leftAxisDimensions": [
- "duration.single_value"
- ],
- "fields": [],
- "values": []
- }
- },
- "singleValue": {
- "showLabel": true,
- "recordField": "duration.single_value",
- "autoscale": true,
- "sparklineSettings": {
- "showTicks": true,
- "variant": "area",
- "record": "duration",
- "visible": true,
- "isVisible": true,
- "color": {
- "Default": "var(--dt-colors-charts-categorical-color-01-default, #134fc9)"
- }
- },
- "trend": {
- "visible": true,
- "relative": true,
- "isVisible": false
- },
- "label": "Total Requests",
- "colorThresholdTarget": "value",
- "alignment": "center"
- },
- "table": {
- "rowDensity": "condensed",
- "enableSparklines": false,
- "hiddenColumns": [],
- "lineWrapIds": [],
- "columnWidths": {}
- }
- }
- },
- "14": {
- "type": "data",
- "title": "",
- "query": "timeseries duration=avg(doku.llm.request.duration)\n| fieldsAdd duration.single_value=arrayAvg(duration)",
- "davis": {
- "enabled": false,
- "davisVisualization": {
- "isAvailable": true
- }
- },
- "visualization": "singleValue",
- "visualizationSettings": {
- "thresholds": [
- {
- "id": "0",
- "title": "",
- "field": "",
- "rules": [
- {
- "id": "0",
- "label": "",
- "comparator": "≥",
- "color": "#7dc540"
- },
- {
- "id": "1",
- "label": "",
- "comparator": "≥",
- "color": "#f5d30f"
- },
- {
- "id": "2",
- "label": "",
- "comparator": "≥",
- "color": "#dc172a"
- }
- ],
- "isEnabled": true
- }
- ],
- "chartSettings": {
- "gapPolicy": "connect",
- "circleChartSettings": {
- "groupingThresholdType": "relative",
- "groupingThresholdValue": 0,
- "valueType": "relative"
- },
- "categoryOverrides": {},
- "fieldMapping": {
- "timestamp": "timeframe",
- "leftAxisValues": [
- "duration"
- ],
- "leftAxisDimensions": [
- "duration.single_value"
- ],
- "fields": [],
- "values": []
- },
- "categoricalBarChartSettings": {}
- },
- "singleValue": {
- "showLabel": true,
- "recordField": "duration.single_value",
- "autoscale": true,
- "sparklineSettings": {
- "showTicks": false,
- "variant": "area",
- "record": "duration",
- "visible": true
- },
- "trend": {
- "visible": true,
- "relative": true,
- "isVisible": false
- },
- "label": "Avg Request Duration"
- },
- "table": {
- "rowDensity": "condensed",
- "enableSparklines": false,
- "hiddenColumns": [],
- "lineWrapIds": [],
- "columnWidths": {}
- },
- "unitsOverrides": [
- {
- "identifier": "duration.single_value",
- "unitCategory": "time",
- "baseUnit": "second",
- "displayUnit": null,
- "decimals": 3,
- "suffix": "",
- "delimiter": false,
- "added": 1707910354866
- }
- ]
- }
- },
- "15": {
- "type": "data",
- "title": "",
- "query": "timeseries duration=avg(doku.llm.total.tokens)\n| fieldsAdd duration.single_value=arrayAvg(duration)",
- "davis": {
- "enabled": false,
- "davisVisualization": {
- "isAvailable": true
- }
- },
- "visualization": "singleValue",
- "visualizationSettings": {
- "thresholds": [
- {
- "id": "0",
- "title": "",
- "field": "",
- "rules": [
- {
- "id": "0",
- "label": "",
- "comparator": "≥",
- "color": "#7dc540"
- },
- {
- "id": "1",
- "label": "",
- "comparator": "≥",
- "color": "#f5d30f"
- },
- {
- "id": "2",
- "label": "",
- "comparator": "≥",
- "color": "#dc172a"
- }
- ],
- "isEnabled": true
- }
- ],
- "chartSettings": {
- "gapPolicy": "connect",
- "circleChartSettings": {
- "groupingThresholdType": "relative",
- "groupingThresholdValue": 0,
- "valueType": "relative"
- },
- "categoryOverrides": {},
- "fieldMapping": {
- "timestamp": "timeframe",
- "leftAxisValues": [
- "duration"
- ],
- "leftAxisDimensions": [
- "duration.single_value"
- ],
- "fields": [],
- "values": []
- },
- "categoricalBarChartSettings": {}
- },
- "singleValue": {
- "showLabel": true,
- "recordField": "duration.single_value",
- "autoscale": true,
- "sparklineSettings": {
- "showTicks": false,
- "variant": "area",
- "record": "duration",
- "visible": true
- },
- "trend": {
- "visible": true,
- "relative": true,
- "isVisible": false
- },
- "label": "Avg Tokens / Request"
- },
- "table": {
- "rowDensity": "condensed",
- "enableSparklines": false,
- "hiddenColumns": [],
- "lineWrapIds": [],
- "columnWidths": {}
- }
- }
- },
- "17": {
- "type": "data",
- "title": "",
- "query": "timeseries cost=sum(doku.llm.usage.cost)\n| sort arraySum(cost) desc\n| limit 20\n| fieldsAdd cost.single_value=arraySum(cost)",
- "davis": {
- "enabled": false,
- "davisVisualization": {
- "isAvailable": true
- }
- },
- "visualization": "singleValue",
- "visualizationSettings": {
- "thresholds": [
- {
- "id": "0",
- "title": "",
- "field": "",
- "rules": [
- {
- "id": "0",
- "label": "",
- "comparator": "≥",
- "color": "#7dc540",
- "value": 0
- },
- {
- "id": "1",
- "label": "",
- "comparator": "≥",
- "color": "#f5d30f",
- "value": 5
- },
- {
- "id": "2",
- "label": "",
- "comparator": "≥",
- "color": "#dc172a",
- "value": 10
- }
- ],
- "isEnabled": true
- }
- ],
- "chartSettings": {
- "gapPolicy": "connect",
- "circleChartSettings": {
- "groupingThresholdType": "relative",
- "groupingThresholdValue": 0,
- "valueType": "relative"
- },
- "categoryOverrides": {},
- "fieldMapping": {
- "timestamp": "timeframe",
- "leftAxisValues": [
- "cost"
- ],
- "leftAxisDimensions": [
- "cost.single_value"
- ],
- "fields": [],
- "values": []
- }
- },
- "singleValue": {
- "showLabel": true,
- "recordField": "cost.single_value",
- "autoscale": true,
- "sparklineSettings": {
- "showTicks": false,
- "variant": "area",
- "record": "cost",
- "visible": true,
- "isVisible": true
- },
- "trend": {
- "visible": true,
- "relative": true,
- "isVisible": false,
- "isRelative": true,
- "isInverseTrend": false
- },
- "colorThresholdTarget": "value",
- "alignment": "center",
- "label": "Total Cost"
- },
- "table": {
- "rowDensity": "condensed",
- "enableSparklines": false,
- "hiddenColumns": [],
- "lineWrapIds": [],
- "columnWidths": {}
- },
- "unitsOverrides": [
- {
- "identifier": "cost.single_value",
- "unitCategory": "currency",
- "baseUnit": "usd",
- "displayUnit": "usd",
- "decimals": 3,
- "suffix": "",
- "delimiter": true,
- "added": 1707910304797
- }
- ]
- }
- },
- "19": {
- "type": "data",
- "title": "",
- "query": "timeseries duration=avg(doku.llm.request.duration, rollup: count)\n| sort arrayAvg(duration) desc\n| limit 20",
- "davis": {
- "enabled": false,
- "davisVisualization": {
- "isAvailable": true
- }
- },
- "visualization": "areaChart",
- "visualizationSettings": {
- "thresholds": [
- {
- "id": "0",
- "title": "",
- "field": "",
- "rules": [
- {
- "id": "0",
- "label": "",
- "comparator": "≥",
- "color": "#7dc540",
- "value": 0
- },
- {
- "id": "1",
- "label": "",
- "comparator": "≥",
- "color": "#f5d30f",
- "value": 5
- },
- {
- "id": "2",
- "label": "",
- "comparator": "≥",
- "color": "#dc172a",
- "value": 10
- }
- ],
- "isEnabled": true
- }
- ],
- "chartSettings": {
- "legend": {
- "hidden": true
- },
- "leftYAxisSettings": {
- "min": "auto",
- "max": "data-max",
- "label": "Requests"
- },
- "categoricalBarChartSettings": {
- "layout": "horizontal"
- },
- "fieldMapping": {
- "timestamp": "timeframe",
- "leftAxisValues": [
- "duration"
- ],
- "leftAxisDimensions": [],
- "fields": [],
- "values": []
- },
- "seriesOverrides": []
- },
- "singleValue": {
- "showLabel": true,
- "label": "",
- "prefixIcon": "",
- "autoscale": true,
- "alignment": "center",
- "colorThresholdTarget": "value"
- },
- "table": {
- "rowDensity": "condensed",
- "enableSparklines": false,
- "hiddenColumns": [],
- "lineWrapIds": [],
- "columnWidths": {}
- },
- "unitsOverrides": []
- }
- },
- "21": {
- "type": "data",
- "title": "Usage Cost by Category",
- "query": "timeseries cost=avg(doku.llm.usage.cost), by: { generation, endpoint, environment, finish_reason, application, model, source, job, platform }\n| fieldsAdd cost=arrayAvg(cost)\n| summarize { cost=avg(cost) } , by: { generation, interval, timeframe }\n| sort cost desc\n| limit 20",
- "davis": {
- "enabled": false,
- "davisVisualization": {
- "isAvailable": true
- }
- },
- "visualization": "pieChart",
- "visualizationSettings": {
- "thresholds": [
- {
- "id": "0",
- "title": "",
- "field": "",
- "rules": [
- {
- "id": "0",
- "label": "",
- "comparator": "≥",
- "color": "#7dc540",
- "value": 0
- },
- {
- "id": "1",
- "label": "",
- "comparator": "≥",
- "color": "#f5d30f",
- "value": 5
- },
- {
- "id": "2",
- "label": "",
- "comparator": "≥",
- "color": "#dc172a",
- "value": 10
- }
- ],
- "isEnabled": true
- }
- ],
- "chartSettings": {
- "gapPolicy": "connect",
- "circleChartSettings": {
- "groupingThresholdType": "absolute",
- "groupingThresholdValue": 0,
- "valueType": "absolute",
- "hideLabels": true,
- "groupingName": null
- },
- "categoryOverrides": {},
- "categoricalBarChartSettings": {
- "categoryAxis": "generation",
- "categoryAxisLabel": "generation",
- "valueAxis": "cost",
- "valueAxisLabel": "cost"
- },
- "legend": {
- "position": "bottom",
- "hidden": false
- }
- },
- "singleValue": {
- "showLabel": true,
- "label": "",
- "prefixIcon": "",
- "recordField": "generation",
- "autoscale": true,
- "alignment": "center",
- "colorThresholdTarget": "value"
- },
- "table": {
- "rowDensity": "condensed",
- "enableSparklines": false,
- "hiddenColumns": [],
- "lineWrapIds": [],
- "columnWidths": {}
- },
- "unitsOverrides": [
- {
- "identifier": "cost",
- "unitCategory": "currency",
- "baseUnit": "usd",
- "displayUnit": "usd",
- "decimals": 4,
- "suffix": "",
- "delimiter": true,
- "added": 1707908592897
- }
- ]
- }
- },
- "22": {
- "type": "data",
- "title": "Usage Cost by Platform",
- "query": "timeseries cost=avg(doku.llm.usage.cost), by: { generation, endpoint, environment, finish_reason, application, model, source, job, platform }\n| fieldsAdd cost=arrayAvg(cost)\n| summarize { cost=avg(cost) } , by: { platform, interval, timeframe }\n| sort cost desc\n| limit 20",
- "davis": {
- "enabled": false,
- "davisVisualization": {
- "isAvailable": true
- }
- },
- "visualization": "pieChart",
- "visualizationSettings": {
- "thresholds": [
- {
- "id": "0",
- "title": "",
- "field": "",
- "rules": [
- {
- "id": "0",
- "label": "",
- "comparator": "≥",
- "color": "#7dc540",
- "value": 0
- },
- {
- "id": "1",
- "label": "",
- "comparator": "≥",
- "color": "#f5d30f",
- "value": 5
- },
- {
- "id": "2",
- "label": "",
- "comparator": "≥",
- "color": "#dc172a",
- "value": 10
- }
- ],
- "isEnabled": true
- }
- ],
- "chartSettings": {
- "gapPolicy": "connect",
- "circleChartSettings": {
- "groupingThresholdType": "absolute",
- "groupingThresholdValue": 0,
- "valueType": "relative",
- "hideLabels": false
- },
- "categoryOverrides": {},
- "categoricalBarChartSettings": {
- "categoryAxis": "platform",
- "categoryAxisLabel": "platform",
- "valueAxis": "cost",
- "valueAxisLabel": "cost"
- },
- "legend": {
- "position": "bottom",
- "hidden": false
- }
- },
- "singleValue": {
- "showLabel": true,
- "label": "",
- "prefixIcon": "",
- "recordField": "generation",
- "autoscale": true,
- "alignment": "center",
- "colorThresholdTarget": "value"
- },
- "table": {
- "rowDensity": "condensed",
- "enableSparklines": false,
- "hiddenColumns": [],
- "lineWrapIds": [],
- "columnWidths": {}
- },
- "unitsOverrides": [
- {
- "identifier": "interval",
- "unitCategory": "time",
- "baseUnit": "nanosecond",
- "displayUnit": "usd",
- "decimals": 4,
- "suffix": "",
- "delimiter": true,
- "added": 1707908592897
- }
- ]
- }
- },
- "23": {
- "type": "data",
- "title": "Usage Cost by Application",
- "query": "timeseries cost=avg(doku.llm.usage.cost), by: { generation, endpoint, environment, finish_reason, application, model, source, job, platform }\n| fieldsAdd cost=arrayAvg(cost)\n| summarize { cost=avg(cost) } , by: { application, interval, timeframe }\n| sort cost desc\n| limit 20",
- "davis": {
- "enabled": false,
- "davisVisualization": {
- "isAvailable": true
- }
- },
- "visualization": "pieChart",
- "visualizationSettings": {
- "thresholds": [
- {
- "id": "0",
- "title": "",
- "field": "",
- "rules": [
- {
- "id": "0",
- "label": "",
- "comparator": "≥",
- "color": "#7dc540",
- "value": 0
- },
- {
- "id": "1",
- "label": "",
- "comparator": "≥",
- "color": "#f5d30f",
- "value": 5
- },
- {
- "id": "2",
- "label": "",
- "comparator": "≥",
- "color": "#dc172a",
- "value": 10
- }
- ],
- "isEnabled": true
- }
- ],
- "chartSettings": {
- "gapPolicy": "connect",
- "circleChartSettings": {
- "groupingThresholdType": "absolute",
- "groupingThresholdValue": 0,
- "valueType": "relative",
- "hideLabels": false
- },
- "categoryOverrides": {},
- "categoricalBarChartSettings": {
- "categoryAxis": "application",
- "categoryAxisLabel": "application",
- "valueAxis": "cost",
- "valueAxisLabel": "cost"
- },
- "legend": {
- "position": "bottom",
- "hidden": false
- }
- },
- "singleValue": {
- "showLabel": true,
- "label": "",
- "prefixIcon": "",
- "recordField": "generation",
- "autoscale": true,
- "alignment": "center",
- "colorThresholdTarget": "value"
- },
- "table": {
- "rowDensity": "condensed",
- "enableSparklines": false,
- "hiddenColumns": [],
- "lineWrapIds": [],
- "columnWidths": {}
- },
- "unitsOverrides": [
- {
- "identifier": "cost",
- "unitCategory": "currency",
- "baseUnit": "usd",
- "displayUnit": "usd",
- "decimals": 4,
- "suffix": "",
- "delimiter": true,
- "added": 1707908592897
- }
- ]
- }
- },
- "24": {
- "type": "data",
- "title": "Usage Cost by Environment",
- "query": "timeseries cost=avg(doku.llm.usage.cost), by: { generation, endpoint, environment, finish_reason, application, model, source, job, platform }\n| fieldsAdd cost=arrayAvg(cost)\n| summarize { cost=avg(cost) } , by: { environment, interval, timeframe }\n| sort cost desc\n| limit 20",
- "davis": {
- "enabled": false,
- "davisVisualization": {
- "isAvailable": true
- }
- },
- "visualization": "pieChart",
- "visualizationSettings": {
- "thresholds": [
- {
- "id": "0",
- "title": "",
- "field": "",
- "rules": [
- {
- "id": "0",
- "label": "",
- "comparator": "≥",
- "color": "#7dc540",
- "value": 0
- },
- {
- "id": "1",
- "label": "",
- "comparator": "≥",
- "color": "#f5d30f",
- "value": 5
- },
- {
- "id": "2",
- "label": "",
- "comparator": "≥",
- "color": "#dc172a",
- "value": 10
- }
- ],
- "isEnabled": true
- }
- ],
- "chartSettings": {
- "gapPolicy": "connect",
- "circleChartSettings": {
- "groupingThresholdType": "absolute",
- "groupingThresholdValue": 0,
- "valueType": "relative",
- "hideLabels": false
- },
- "categoryOverrides": {},
- "categoricalBarChartSettings": {
- "categoryAxis": "environment",
- "categoryAxisLabel": "environment",
- "valueAxis": "cost",
- "valueAxisLabel": "cost"
- },
- "legend": {
- "position": "bottom",
- "hidden": false
- }
- },
- "singleValue": {
- "showLabel": true,
- "label": "",
- "prefixIcon": "",
- "recordField": "generation",
- "autoscale": true,
- "alignment": "center",
- "colorThresholdTarget": "value"
- },
- "table": {
- "rowDensity": "condensed",
- "enableSparklines": false,
- "hiddenColumns": [],
- "lineWrapIds": [],
- "columnWidths": {}
- },
- "unitsOverrides": [
- {
- "identifier": "cost",
- "unitCategory": "currency",
- "baseUnit": "usd",
- "displayUnit": "usd",
- "decimals": 4,
- "suffix": "",
- "delimiter": true,
- "added": 1707908592897
- }
- ]
- }
- },
- "25": {
- "type": "data",
- "title": "",
- "query": "timeseries completionTokens=avg(doku.llm.completion.tokens)\n| sort arrayAvg(completionTokens)\n| append [timeseries promptTokens=avg(doku.llm.prompt.tokens)\n | sort arrayAvg(promptTokens)]",
- "davis": {
- "enabled": false,
- "davisVisualization": {
- "isAvailable": true
- }
- },
- "visualization": "areaChart",
- "visualizationSettings": {
- "thresholds": [
- {
- "id": "0",
- "title": "",
- "field": "",
- "rules": [
- {
- "id": "0",
- "label": "",
- "comparator": "≥",
- "color": "#7dc540",
- "value": 0
- },
- {
- "id": "1",
- "label": "",
- "comparator": "≥",
- "color": "#f5d30f",
- "value": 5
- },
- {
- "id": "2",
- "label": "",
- "comparator": "≥",
- "color": "#dc172a",
- "value": 10
- }
- ],
- "isEnabled": true
- }
- ],
- "chartSettings": {
- "legend": {
- "hidden": false,
- "position": "bottom"
- },
- "leftYAxisSettings": {
- "label": ""
- },
- "categoricalBarChartSettings": {
- "layout": "horizontal"
- },
- "fieldMapping": {
- "timestamp": "timeframe",
- "leftAxisValues": [
- "completionTokens",
- "promptTokens"
- ],
- "leftAxisDimensions": [],
- "fields": [],
- "values": []
- }
- },
- "singleValue": {
- "showLabel": true,
- "label": "",
- "prefixIcon": "",
- "recordField": "error",
- "autoscale": true,
- "alignment": "center",
- "colorThresholdTarget": "value"
- },
- "table": {
- "rowDensity": "condensed",
- "enableSparklines": false,
- "hiddenColumns": [],
- "lineWrapIds": [],
- "columnWidths": {}
- }
- }
- },
- "26": {
- "type": "data",
- "title": "",
- "query": "timeseries duration=avg(doku.llm.prompt.tokens)\n| fieldsAdd duration.single_value=arrayAvg(duration)",
- "davis": {
- "enabled": false,
- "davisVisualization": {
- "isAvailable": true
- }
- },
- "visualization": "singleValue",
- "visualizationSettings": {
- "thresholds": [
- {
- "id": "0",
- "title": "",
- "field": "",
- "rules": [
- {
- "id": "0",
- "label": "",
- "comparator": "≥",
- "color": "#7dc540"
- },
- {
- "id": "1",
- "label": "",
- "comparator": "≥",
- "color": "#f5d30f"
- },
- {
- "id": "2",
- "label": "",
- "comparator": "≥",
- "color": "#dc172a"
- }
- ],
- "isEnabled": true
- }
- ],
- "chartSettings": {
- "gapPolicy": "connect",
- "circleChartSettings": {
- "groupingThresholdType": "relative",
- "groupingThresholdValue": 0,
- "valueType": "relative"
- },
- "categoryOverrides": {},
- "fieldMapping": {
- "timestamp": "timeframe",
- "leftAxisValues": [
- "duration"
- ],
- "leftAxisDimensions": [
- "duration.single_value"
- ],
- "fields": [],
- "values": []
- },
- "categoricalBarChartSettings": {}
- },
- "singleValue": {
- "showLabel": true,
- "recordField": "duration.single_value",
- "autoscale": true,
- "sparklineSettings": {
- "showTicks": false,
- "variant": "area",
- "record": "duration",
- "visible": true
- },
- "trend": {
- "visible": true,
- "relative": true,
- "isVisible": false
- },
- "label": "Avg Prompt Tokens / Request"
- },
- "table": {
- "rowDensity": "condensed",
- "enableSparklines": false,
- "hiddenColumns": [],
- "lineWrapIds": [],
- "columnWidths": {}
- }
- }
- },
- "27": {
- "type": "data",
- "title": "",
- "query": "timeseries duration=avg(doku.llm.completion.tokens)\n| fieldsAdd duration.single_value=arrayAvg(duration)",
- "davis": {
- "enabled": false,
- "davisVisualization": {
- "isAvailable": true
- }
- },
- "visualization": "singleValue",
- "visualizationSettings": {
- "thresholds": [
- {
- "id": "0",
- "title": "",
- "field": "",
- "rules": [
- {
- "id": "0",
- "label": "",
- "comparator": "≥",
- "color": "#7dc540"
- },
- {
- "id": "1",
- "label": "",
- "comparator": "≥",
- "color": "#f5d30f"
- },
- {
- "id": "2",
- "label": "",
- "comparator": "≥",
- "color": "#dc172a"
- }
- ],
- "isEnabled": true
- }
- ],
- "chartSettings": {
- "gapPolicy": "connect",
- "circleChartSettings": {
- "groupingThresholdType": "relative",
- "groupingThresholdValue": 0,
- "valueType": "relative"
- },
- "categoryOverrides": {},
- "fieldMapping": {
- "timestamp": "timeframe",
- "leftAxisValues": [
- "duration"
- ],
- "leftAxisDimensions": [
- "duration.single_value"
- ],
- "fields": [],
- "values": []
- },
- "categoricalBarChartSettings": {}
- },
- "singleValue": {
- "showLabel": true,
- "recordField": "duration.single_value",
- "autoscale": true,
- "sparklineSettings": {
- "showTicks": false,
- "variant": "area",
- "record": "duration",
- "visible": true
- },
- "trend": {
- "visible": true,
- "relative": true,
- "isVisible": false
- },
- "label": "Avg Completion Tokens / Request"
- },
- "table": {
- "rowDensity": "condensed",
- "enableSparklines": false,
- "hiddenColumns": [],
- "lineWrapIds": [],
- "columnWidths": {}
- }
- }
- },
- "28": {
- "type": "data",
- "title": "Top Models by Cost",
- "query": "timeseries cost=sum(doku.llm.usage.cost), by: { generation, endpoint, environment, finish_reason, application, model, source, job, platform }\n| fieldsAdd cost=arrayAvg(cost)\n| summarize { cost=avg(cost) } , by: { model, interval, timeframe }\n| sort cost desc\n| limit 20",
- "davis": {
- "enabled": false,
- "davisVisualization": {
- "isAvailable": true
- }
- },
- "visualization": "categoricalBarChart",
- "visualizationSettings": {
- "thresholds": [
- {
- "id": "0",
- "title": "",
- "field": "",
- "rules": [
- {
- "id": "0",
- "label": "",
- "comparator": "≥",
- "color": "#7dc540",
- "value": 0
- },
- {
- "id": "1",
- "label": "",
- "comparator": "≥",
- "color": "#f5d30f",
- "value": 5
- },
- {
- "id": "2",
- "label": "",
- "comparator": "≥",
- "color": "#dc172a",
- "value": 10
- }
- ],
- "isEnabled": true
- }
- ],
- "chartSettings": {
- "gapPolicy": "connect",
- "circleChartSettings": {
- "groupingThresholdType": "absolute",
- "groupingThresholdValue": 0,
- "valueType": "relative",
- "hideLabels": false
- },
- "categoryOverrides": {},
- "categoricalBarChartSettings": {
- "categoryAxis": "model",
- "categoryAxisLabel": "model",
- "valueAxis": [
- "cost"
- ],
- "valueAxisLabel": "cost",
- "layout": "horizontal",
- "categoryAxisTickLayout": "horizontal",
- "colorPaletteMode": "multi-color"
- },
- "legend": {
- "hidden": true
- }
- },
- "singleValue": {
- "showLabel": true,
- "label": "",
- "prefixIcon": "",
- "recordField": "generation",
- "autoscale": true,
- "alignment": "center",
- "colorThresholdTarget": "value"
- },
- "table": {
- "rowDensity": "condensed",
- "enableSparklines": false,
- "hiddenColumns": [],
- "lineWrapIds": [],
- "columnWidths": {}
- },
- "unitsOverrides": [
- {
- "identifier": "cost",
- "unitCategory": "currency",
- "baseUnit": "usd",
- "displayUnit": null,
- "decimals": 3,
- "suffix": "",
- "delimiter": false,
- "added": 1707910273820
- }
- ]
- }
- },
- "29": {
- "type": "data",
- "title": "Usage Cost by Platform",
- "query": "timeseries cost=avg(doku.llm.usage.cost), by: { generation, endpoint, environment, finish_reason, application, model, source, job, platform }\n| fieldsAdd cost=arrayAvg(cost)\n| summarize { cost=avg(cost) } , by: { model, interval, timeframe }\n| sort cost desc\n| limit 20",
- "davis": {
- "enabled": false,
- "davisVisualization": {
- "isAvailable": true
- }
- },
- "visualization": "areaChart",
- "visualizationSettings": {
- "thresholds": [
- {
- "id": "0",
- "title": "",
- "field": "",
- "rules": [
- {
- "id": "0",
- "label": "",
- "comparator": "≥",
- "color": "#7dc540",
- "value": 0
- },
- {
- "id": "1",
- "label": "",
- "comparator": "≥",
- "color": "#f5d30f",
- "value": 5
- },
- {
- "id": "2",
- "label": "",
- "comparator": "≥",
- "color": "#dc172a",
- "value": 10
- }
- ],
- "isEnabled": true
- }
- ],
- "chartSettings": {
- "gapPolicy": "connect",
- "circleChartSettings": {
- "groupingThresholdType": "absolute",
- "groupingThresholdValue": 0,
- "valueType": "relative",
- "hideLabels": false
- },
- "categoryOverrides": {},
- "categoricalBarChartSettings": {
- "categoryAxis": "model",
- "categoryAxisLabel": "model",
- "valueAxis": "cost",
- "valueAxisLabel": "cost",
- "layout": "horizontal",
- "categoryAxisTickLayout": "horizontal"
- },
- "legend": {
- "hidden": true
- },
- "fieldMapping": {
- "leftAxisValues": [
- "cost"
- ],
- "rightAxisValues": [],
- "leftAxisDimensions": [
- "model"
- ]
- }
- },
- "singleValue": {
- "showLabel": true,
- "label": "",
- "prefixIcon": "",
- "recordField": "generation",
- "autoscale": true,
- "alignment": "center",
- "colorThresholdTarget": "value"
- },
- "table": {
- "rowDensity": "condensed",
- "enableSparklines": false,
- "hiddenColumns": [],
- "lineWrapIds": [],
- "columnWidths": {}
- },
- "unitsOverrides": [
- {
- "identifier": "cost",
- "unitCategory": "currency",
- "baseUnit": "usd",
- "displayUnit": null,
- "decimals": 3,
- "suffix": "",
- "delimiter": false,
- "added": 1707910273820
- }
- ]
- }
- }
- },
- "layouts": {
- "1": {
- "x": 0,
- "y": 24,
- "w": 12,
- "h": 8
- },
- "2": {
- "x": 12,
- "y": 24,
- "w": 12,
- "h": 8
- },
- "7": {
- "x": 0,
- "y": 0,
- "w": 6,
- "h": 3
- },
- "14": {
- "x": 6,
- "y": 0,
- "w": 6,
- "h": 3
- },
- "15": {
- "x": 12,
- "y": 0,
- "w": 6,
- "h": 3
- },
- "17": {
- "x": 18,
- "y": 0,
- "w": 6,
- "h": 3
- },
- "19": {
- "x": 0,
- "y": 3,
- "w": 24,
- "h": 5
- },
- "21": {
- "x": 0,
- "y": 8,
- "w": 6,
- "h": 5
- },
- "22": {
- "x": 6,
- "y": 8,
- "w": 6,
- "h": 5
- },
- "23": {
- "x": 18,
- "y": 8,
- "w": 6,
- "h": 5
- },
- "24": {
- "x": 12,
- "y": 8,
- "w": 6,
- "h": 5
- },
- "25": {
- "x": 7,
- "y": 13,
- "w": 17,
- "h": 6
- },
- "26": {
- "x": 0,
- "y": 13,
- "w": 7,
- "h": 3
- },
- "27": {
- "x": 0,
- "y": 16,
- "w": 7,
- "h": 3
- },
- "28": {
- "x": 0,
- "y": 19,
- "w": 11,
- "h": 5
- },
- "29": {
- "x": 11,
- "y": 19,
- "w": 13,
- "h": 5
- }
- }
- }
- ```
-</Accordion>
-
----
+Alternatively, you can configure the OTLP endpoint by setting the `OTEL_EXPORTER_OTLP_ENDPOINT` and the OTLP headers by setting the Appli`OTEL_EXPORTER_OTLP_HEADERS` environmentcation variable as recommended in the OpenTelemetry documentation.
-<CardGroup cols={2}>
-<Card title="Integrations" href="/latest/integrations/introduction" icon='circle-nodes'>
-Integrate your LLM Provider with Doku
-</Card>
-<Card title="API Reference" href="/latest/api-reference/introduction" icon='code'>
-OpenAPI specification for API Endpoints in Doku
-</Card>
-</CardGroup>
\ No newline at end of file
+Refer to the OpenLIT [Python SDK repository](https://github.com/openlit/openlit/tree/main/sdk/python) for more advanced configurations and use cases.
diff --git a/docs/latest/connections/grafana-tempo.mdx b/docs/latest/connections/grafana-tempo.mdx
new file mode 100644
index 00000000..e738ae62
--- /dev/null
+++ b/docs/latest/connections/grafana-tempo.mdx
@@ -0,0 +1,16 @@
+---
+title: 'Grafana Tempo'
+description: 'LLM Observability with Grafana Tempo and OpenLIT'
+---
+
+To send OpenTelemetry data collected by OpenLIt from your LLM Application, You need to set the `otlp_endpoint` and `otlp_headers` arguments according to your needs.
+
+```python
+import openlit
+
+openlit.init(otlp_endpoint="otlp_backend_endpoint", otlp_headers="otlp_backend_token")
+```
+
+Alternatively, you can configure the OTLP endpoint by setting the `OTEL_EXPORTER_OTLP_ENDPOINT` and the OTLP headers by setting the Appli`OTEL_EXPORTER_OTLP_HEADERS` environmentcation variable as recommended in the OpenTelemetry documentation.
+
+Refer to the OpenLIT [Python SDK repository](https://github.com/openlit/openlit/tree/main/sdk/python) for more advanced configurations and use cases.
diff --git a/docs/latest/connections/grafanacloud.mdx b/docs/latest/connections/grafanacloud.mdx
index 72251ed4..42d9e7d3 100644
--- a/docs/latest/connections/grafanacloud.mdx
+++ b/docs/latest/connections/grafanacloud.mdx
@@ -3,48 +3,18 @@ title: 'Grafana Cloud'
description: 'LLM Observability with Grafana Cloud and OpenLIT'
---
-<Frame>
- <img src="https://github.com/dokulabs/doku/blob/main/docs/images/grafana-dashboard-1.jpg?raw=true" />
- <img src="https://github.com/dokulabs/doku/blob/main/docs/images/grafana-dashboard-2.jpg?raw=true" />
-</Frame>
+To send OpenTelemetry data collected by OpenLIt from your LLM Application, You need to set the `otlp_endpoint` and `otlp_headers` arguments according to your needs.
-You can [send data using OpenTelemetry Protocol (OTLP)](https://grafana.com/docs/grafana-cloud/send-data/otlp/send-data-otlp/) to Grafana Cloud drectly from the OpenLIT SDK.
+```python
+import openlit
-To start sending Traces and Metrics, Follow the below steps
-1. Create an Access Policy token with the metrics:write and traces:write scopes, depending on the data you will be sending.
-2. Open the Cloud Portal, and click Configure on the OpenTelemetry card.
-3. Click on Generate Now in the Password / API Token section. As a result, the Environment Variable section will be populated with environment variables necessary to send data directly to Grafana Cloud.
-
-4. Configure the OpenLIT SDK to use environment variables to push directly to Grafana Cloud
-
-```
-export OTEL_EXPORTER_OTLP_ENDPOINT=<OTLP Endpoint URL>
-export OTEL_EXPORTER_OTLP_HEADERS=Authorization=Basic%20<base64 instanceID:token>
+openlit.init(otlp_endpoint="otlp_backend_endpoint", otlp_headers="otlp_backend_token")
```
-<Tip>
-Make sure to replace the space after `Basic` with `%20`:
+Alternatively, you can configure the OTLP endpoint by setting the `OTEL_EXPORTER_OTLP_ENDPOINT` and the OTLP headers by setting the Appli`OTEL_EXPORTER_OTLP_HEADERS` environmentcation variable as recommended in the OpenTelemetry documentation.
-`OTEL_EXPORTER_OTLP_HEADERS=Authorization=Basic%20<base64 instanceID:token>`
-</Tip>
+Refer to the OpenLIT [Python SDK repository](https://github.com/openlit/openlit/tree/main/sdk/python) for more advanced configurations and use cases.
-You can automatically obtain these values from the Grafana Cloud Portal.
-click on Generate Now in the Password / API Token section. As a result, the Environment Variable section will be populated with environment variables necessary to send data directly to Grafana Cloud.
-
-```shell
-curl --request POST \
- --url https://<YOUR_DOKU_INGESTER_URL>/api/connections \
- --header 'Authorization: <DOKU_API_KEY>' \
- --header 'Content-Type: application/json' \
- --data '{
- "Platform": "grafana",
- "MetricsUrl": "<YOUR_GRAFANA_CLOUD_INFLUX_TELEGRAF_URL>",
- "MetricsUsername": "<YOUR_GRAFANA_CLOUD_PROMETHEUS_USERNAME>",
- "LogsUrl": "<YOUR_GRAFANA_CLOUD_LOGS_URL>",
- "LogsUsername": "<YOUR_GRAFANA_CLOUD_LOGS_USERNAME>",
- "ApiKey": "<YOUR_GRAFANA_CLOUD_API_KEY>"
-}'
-```
## Grafana Resources
@@ -1542,9 +1512,6 @@ curl --request POST \
<CardGroup cols={2}>
<Card title="Integrations" href="/latest/integrations/introduction" icon='circle-nodes'>
-Integrate your LLM Provider with Doku
-</Card>
-<Card title="API Reference" href="/latest/api-reference/introduction" icon='code'>
-OpenAPI specification for API Endpoints in Doku
+Start Monitoringyour LLM Application
</Card>
</CardGroup>
\ No newline at end of file
diff --git a/docs/latest/connections/grafanaoss.mdx b/docs/latest/connections/grafanaoss.mdx
deleted file mode 100644
index 5199d744..00000000
--- a/docs/latest/connections/grafanaoss.mdx
+++ /dev/null
@@ -1,1945 +0,0 @@
----
-title: 'Grafana OSS'
-description: 'LLM Observability with Grafana and Doku'
----
-
-<Frame>
- <img src="https://github.com/dokulabs/doku/blob/main/docs/images/grafana-dashboard-1.jpg?raw=true" />
- <img src="https://github.com/dokulabs/doku/blob/main/docs/images/grafana-dashboard-3.jpg?raw=true" />
-</Frame>
-
-You can add the Doku's backend storage database (`ClickHouse`) as a datasource in Grafana.
-
-## Steps
-
-1. Navigate to your Grafana Instance.
-1. Login with your credentials.
-1. Click on the **Connection** on the left sidebar to open the **Add new connection**.
-1. In the search box, type `ClickHouse` and then click `Install` button on the top right corner.
-1. Click the **Add new data source** button on the top right corner.
-1.In the settings form, fill in the details to connect to your ClickHouse database:
- 1. **Server address**: Provide the host address of your ClickHouse Database (e.g., `127.0.0.1`).
- 1. **Server port**: Provide the port of your ClickHouse Database (e.g., `9000`) and set protocol as `Native`
- 1. **Username**: The username for the ClickHouse database. Default user used by Doku is `default`.
- 1. **Password**: The password for the database. Default password used by Doku is `DOKU`.
- 1. Under **Additional settings**
- - Add **Default database**. Default database used by Doku is `default`.
-1. Optionally customize the **Additional settings**.
-1. Click the **Save & Test** button at the bottom of the page.
-
-Grafana will attempt to connect to the database using the provided settings. If everything is configured correctly, you will see a message indicating the data source is working.
-
-## Grafana Resources
-
-<Accordion title="Dashboard">
- ```json
- {
- "annotations": {
- "list": [
- {
- "builtIn": 1,
- "datasource": {
- "type": "grafana",
- "uid": "-- Grafana --"
- },
- "enable": true,
- "hide": true,
- "iconColor": "rgba(0, 211, 255, 1)",
- "name": "Annotations & Alerts",
- "type": "dashboard"
- }
- ]
- },
- "editable": true,
- "fiscalYearStartMonth": 0,
- "graphTooltip": 0,
- "id": 1,
- "links": [
- {
- "icon": "info",
- "tags": [],
- "targetBlank": true,
- "title": "Doku Documentation",
- "tooltip": "",
- "type": "link",
- "url": "https://grafana.com/docs/grafana/latest/"
- },
- {
- "icon": "info",
- "tags": [],
- "targetBlank": true,
- "title": "Doku Community",
- "tooltip": "",
- "type": "link",
- "url": "https://dokulabs.slack.com/"
- },
- {
- "icon": "info",
- "tags": [],
- "targetBlank": true,
- "title": "Dokulabs GitHub",
- "tooltip": "",
- "type": "link",
- "url": "https://github.com/dokulabs/"
- }
- ],
- "liveNow": false,
- "panels": [
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "gridPos": {
- "h": 4,
- "w": 11,
- "x": 0,
- "y": 0
- },
- "id": 23,
- "options": {
- "code": {
- "language": "plaintext",
- "showLineNumbers": false,
- "showMiniMap": false
- },
- "content": "---\n---\n---\n---\n---\n---",
- "mode": "markdown"
- },
- "pluginVersion": "10.3.3",
- "transparent": true,
- "type": "text"
- },
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "gridPos": {
- "h": 4,
- "w": 2,
- "x": 11,
- "y": 0
- },
- "id": 2,
- "options": {
- "code": {
- "language": "plaintext",
- "showLineNumbers": false,
- "showMiniMap": false
- },
- "content": "![Doku Logo](https://github.com/dokulabs/.github/blob/main/profile/assets/favicon.png?raw=true)",
- "mode": "markdown"
- },
- "pluginVersion": "10.3.3",
- "transparent": true,
- "type": "text"
- },
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "gridPos": {
- "h": 4,
- "w": 11,
- "x": 13,
- "y": 0
- },
- "id": 22,
- "options": {
- "code": {
- "language": "plaintext",
- "showLineNumbers": false,
- "showMiniMap": false
- },
- "content": "---\n---\n---\n---\n---\n---",
- "mode": "markdown"
- },
- "pluginVersion": "10.3.3",
- "transparent": true,
- "type": "text"
- },
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "description": "This panel shows the total number of requests sent to Large Language Models (LLM) Platforms in the selected time interval.",
- "fieldConfig": {
- "defaults": {
- "color": {
- "fixedColor": "yellow",
- "mode": "continuous-BlPu"
- },
- "mappings": [],
- "thresholds": {
- "mode": "absolute",
- "steps": [
- {
- "color": "green",
- "value": null
- },
- {
- "color": "red",
- "value": 80
- }
- ]
- },
- "unitScale": true
- },
- "overrides": []
- },
- "gridPos": {
- "h": 3,
- "w": 6,
- "x": 0,
- "y": 4
- },
- "id": 3,
- "options": {
- "colorMode": "background",
- "graphMode": "area",
- "justifyMode": "auto",
- "orientation": "auto",
- "reduceOptions": {
- "calcs": [
- "lastNotNull"
- ],
- "fields": "",
- "values": false
- },
- "showPercentChange": false,
- "textMode": "auto",
- "wideLayout": true
- },
- "pluginVersion": "10.3.3",
- "targets": [
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "editorMode": "code",
- "editorType": "sql",
- "format": 1,
- "meta": {},
- "pluginVersion": "4.0.3",
- "queryType": "table",
- "rawQuery": true,
- "rawSql": "SELECT count(*) FROM DOKU_LLM_DATA\nWHERE $__timeFilter(time)",
- "refId": "A",
- "sql": {
- "columns": [
- {
- "name": "COUNT",
- "parameters": [
- {
- "name": "environment",
- "type": "functionParameter"
- }
- ],
- "type": "function"
- }
- ],
- "groupBy": [
- {
- "property": {
- "type": "string"
- },
- "type": "groupBy"
- }
- ],
- "limit": 50
- },
- "table": "doku"
- }
- ],
- "title": "Total Requests",
- "transparent": true,
- "type": "stat"
- },
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "description": "This panel shows the average time taken to process each request by the Large Language Models (LLM), offering a snapshot of system performance and efficiency.",
- "fieldConfig": {
- "defaults": {
- "color": {
- "mode": "thresholds"
- },
- "mappings": [],
- "thresholds": {
- "mode": "absolute",
- "steps": [
- {
- "color": "green",
- "value": null
- },
- {
- "color": "red",
- "value": 5
- }
- ]
- },
- "unit": "s",
- "unitScale": true
- },
- "overrides": []
- },
- "gridPos": {
- "h": 3,
- "w": 4,
- "x": 6,
- "y": 4
- },
- "id": 4,
- "options": {
- "colorMode": "background",
- "graphMode": "area",
- "justifyMode": "auto",
- "orientation": "auto",
- "reduceOptions": {
- "calcs": [
- "lastNotNull"
- ],
- "fields": "",
- "values": false
- },
- "showPercentChange": false,
- "textMode": "auto",
- "wideLayout": true
- },
- "pluginVersion": "10.3.3",
- "targets": [
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "editorMode": "code",
- "editorType": "sql",
- "format": 1,
- "meta": {},
- "pluginVersion": "4.0.3",
- "queryType": "table",
- "rawQuery": true,
- "rawSql": "SELECT AVG(requestDuration) FROM DOKU_LLM_DATA\nWHERE $__timeFilter(time)",
- "refId": "A",
- "sql": {
- "columns": [
- {
- "name": "AVG",
- "parameters": [
- {
- "name": "requestduration",
- "type": "functionParameter"
- }
- ],
- "type": "function"
- }
- ],
- "groupBy": [
- {
- "property": {
- "type": "string"
- },
- "type": "groupBy"
- }
- ],
- "limit": 50
- },
- "table": "doku"
- }
- ],
- "title": "Avg Request Duration",
- "transparent": true,
- "type": "stat"
- },
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "description": "This panel shows the average count of Total tokens used per LLM request",
- "fieldConfig": {
- "defaults": {
- "color": {
- "mode": "thresholds"
- },
- "mappings": [],
- "thresholds": {
- "mode": "absolute",
- "steps": [
- {
- "color": "green",
- "value": null
- },
- {
- "color": "red",
- "value": 1000
- }
- ]
- },
- "unit": "none",
- "unitScale": true
- },
- "overrides": []
- },
- "gridPos": {
- "h": 3,
- "w": 4,
- "x": 10,
- "y": 4
- },
- "id": 5,
- "options": {
- "colorMode": "background",
- "graphMode": "area",
- "justifyMode": "auto",
- "orientation": "auto",
- "reduceOptions": {
- "calcs": [
- "lastNotNull"
- ],
- "fields": "",
- "values": false
- },
- "showPercentChange": false,
- "textMode": "auto",
- "wideLayout": true
- },
- "pluginVersion": "10.3.3",
- "targets": [
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "editorMode": "code",
- "editorType": "sql",
- "format": 1,
- "meta": {},
- "pluginVersion": "4.0.3",
- "queryType": "table",
- "rawQuery": true,
- "rawSql": "SELECT AVG(totalTokens) FROM DOKU_LLM_DATA\nWHERE $__timeFilter(time)",
- "refId": "A",
- "sql": {
- "columns": [
- {
- "name": "AVG",
- "parameters": [
- {
- "name": "totaltokens",
- "type": "functionParameter"
- }
- ],
- "type": "function"
- }
- ],
- "groupBy": [
- {
- "property": {
- "type": "string"
- },
- "type": "groupBy"
- }
- ],
- "limit": 50
- },
- "table": "doku"
- }
- ],
- "title": "Avg Tokens per Request",
- "transparent": true,
- "type": "stat"
- },
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "description": "This panel shows the average cost incurred per request to the LLM, helping monitor and optimize budget allocation for LLM usage.",
- "fieldConfig": {
- "defaults": {
- "color": {
- "mode": "thresholds"
- },
- "mappings": [],
- "thresholds": {
- "mode": "absolute",
- "steps": [
- {
- "color": "green",
- "value": null
- },
- {
- "color": "red",
- "value": 5
- }
- ]
- },
- "unit": "currencyUSD",
- "unitScale": true
- },
- "overrides": []
- },
- "gridPos": {
- "h": 3,
- "w": 4,
- "x": 14,
- "y": 4
- },
- "id": 6,
- "options": {
- "colorMode": "background",
- "graphMode": "area",
- "justifyMode": "auto",
- "orientation": "auto",
- "reduceOptions": {
- "calcs": [
- "lastNotNull"
- ],
- "fields": "",
- "values": false
- },
- "showPercentChange": false,
- "textMode": "auto",
- "wideLayout": true
- },
- "pluginVersion": "10.3.3",
- "targets": [
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "editorMode": "code",
- "editorType": "sql",
- "format": 1,
- "meta": {},
- "pluginVersion": "4.0.3",
- "queryType": "table",
- "rawQuery": true,
- "rawSql": "SELECT AVG(usageCost) FROM DOKU_LLM_DATA \nWHERE $__timeFilter(time)",
- "refId": "A",
- "sql": {
- "columns": [
- {
- "name": "AVG",
- "parameters": [
- {
- "name": "usagecost",
- "type": "functionParameter"
- }
- ],
- "type": "function"
- }
- ],
- "groupBy": [
- {
- "property": {
- "type": "string"
- },
- "type": "groupBy"
- }
- ],
- "limit": 50
- },
- "table": "doku"
- }
- ],
- "title": "Avg Cost / Request",
- "transparent": true,
- "type": "stat"
- },
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "description": "This panel shows the total cost on LLM requests over the selected period.",
- "fieldConfig": {
- "defaults": {
- "color": {
- "mode": "continuous-BlPu"
- },
- "mappings": [],
- "thresholds": {
- "mode": "absolute",
- "steps": [
- {
- "color": "green",
- "value": null
- }
- ]
- },
- "unit": "currencyUSD",
- "unitScale": true
- },
- "overrides": []
- },
- "gridPos": {
- "h": 3,
- "w": 6,
- "x": 18,
- "y": 4
- },
- "id": 10,
- "options": {
- "colorMode": "background",
- "graphMode": "area",
- "justifyMode": "auto",
- "orientation": "auto",
- "reduceOptions": {
- "calcs": [
- "lastNotNull"
- ],
- "fields": "",
- "values": false
- },
- "showPercentChange": false,
- "textMode": "auto",
- "wideLayout": true
- },
- "pluginVersion": "10.3.3",
- "targets": [
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "editorMode": "code",
- "editorType": "sql",
- "format": 1,
- "meta": {},
- "pluginVersion": "4.0.3",
- "queryType": "table",
- "rawQuery": true,
- "rawSql": "SELECT SUM(usageCost) FROM DOKU_LLM_DATA\nWHERE $__timeFilter(time)",
- "refId": "A",
- "sql": {
- "columns": [
- {
- "name": "SUM",
- "parameters": [
- {
- "name": "usagecost",
- "type": "functionParameter"
- }
- ],
- "type": "function"
- }
- ],
- "groupBy": [
- {
- "property": {
- "type": "string"
- },
- "type": "groupBy"
- }
- ],
- "limit": 50
- },
- "table": "doku"
- }
- ],
- "title": "Total Cost",
- "transparent": true,
- "type": "stat"
- },
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "description": "This panel shows the count of API requests made to LLMs over the selected time.",
- "fieldConfig": {
- "defaults": {
- "color": {
- "mode": "palette-classic-by-name"
- },
- "custom": {
- "axisBorderShow": false,
- "axisCenteredZero": false,
- "axisColorMode": "series",
- "axisGridShow": true,
- "axisLabel": "",
- "axisPlacement": "auto",
- "barAlignment": 0,
- "drawStyle": "line",
- "fillOpacity": 100,
- "gradientMode": "opacity",
- "hideFrom": {
- "legend": false,
- "tooltip": false,
- "viz": false
- },
- "insertNulls": false,
- "lineInterpolation": "linear",
- "lineStyle": {
- "dash": [
- 10,
- 10
- ],
- "fill": "dash"
- },
- "lineWidth": 2,
- "pointSize": 5,
- "scaleDistribution": {
- "type": "linear"
- },
- "showPoints": "always",
- "spanNulls": false,
- "stacking": {
- "group": "A",
- "mode": "none"
- },
- "thresholdsStyle": {
- "mode": "off"
- }
- },
- "fieldMinMax": false,
- "mappings": [],
- "thresholds": {
- "mode": "absolute",
- "steps": [
- {
- "color": "green",
- "value": null
- }
- ]
- },
- "unit": "none",
- "unitScale": true
- },
- "overrides": []
- },
- "gridPos": {
- "h": 5,
- "w": 24,
- "x": 0,
- "y": 7
- },
- "id": 17,
- "options": {
- "legend": {
- "calcs": [],
- "displayMode": "list",
- "placement": "bottom",
- "showLegend": false
- },
- "tooltip": {
- "mode": "single",
- "sort": "none"
- }
- },
- "pluginVersion": "10.2.3",
- "targets": [
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "editorMode": "code",
- "format": "time_series",
- "rawQuery": true,
- "rawSql": "SELECT\n DATE_TRUNC('day', \"time\") AS \"time\",\n COUNT(endpoint) AS total_requests\nFROM \n DOKU_LLM_DATA\nWHERE\n $__timeFilter(\"time\")\nGROUP BY \n DATE_TRUNC('day', \"time\")\nORDER BY \n \"time\";",
- "refId": "A",
- "sql": {
- "columns": [
- {
- "alias": "\"Prompt Tokens\"",
- "parameters": [
- {
- "name": "prompttokens",
- "type": "functionParameter"
- }
- ],
- "type": "function"
- },
- {
- "alias": "\"time\"",
- "parameters": [
- {
- "name": "\"time\"",
- "type": "functionParameter"
- }
- ],
- "type": "function"
- },
- {
- "alias": "\"Completion Tokens\"",
- "parameters": [
- {
- "name": "completiontokens",
- "type": "functionParameter"
- }
- ],
- "type": "function"
- },
- {
- "alias": "\"Total Tokens\"",
- "parameters": [
- {
- "name": "totaltokens",
- "type": "functionParameter"
- }
- ],
- "type": "function"
- }
- ],
- "groupBy": [
- {
- "property": {
- "type": "string"
- },
- "type": "groupBy"
- }
- ],
- "limit": 50
- },
- "table": "doku"
- }
- ],
- "title": "Total Requests / Day",
- "type": "timeseries"
- },
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "description": "This panel illustrates the distribution of LLM requests across different usage categories: Chat Generations, Embeddings, Image Generations, Audio Generations, and Fine Tuning. It visualizes the relative volume of requests, helping to identify which types of operations are most frequently performed and providing insights into usage patterns by category.\n\n",
- "fieldConfig": {
- "defaults": {
- "color": {
- "mode": "palette-classic"
- },
- "custom": {
- "hideFrom": {
- "legend": false,
- "tooltip": false,
- "viz": false
- }
- },
- "mappings": [],
- "unitScale": true
- },
- "overrides": []
- },
- "gridPos": {
- "h": 9,
- "w": 6,
- "x": 0,
- "y": 12
- },
- "id": 12,
- "options": {
- "displayLabels": [
- "name",
- "percent"
- ],
- "legend": {
- "displayMode": "list",
- "placement": "bottom",
- "showLegend": false,
- "values": []
- },
- "pieType": "pie",
- "reduceOptions": {
- "calcs": [],
- "fields": "/^requests$/",
- "values": true
- },
- "tooltip": {
- "mode": "single",
- "sort": "asc"
- }
- },
- "pluginVersion": "10.2.3",
- "targets": [
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "editorMode": "code",
- "editorType": "sql",
- "format": 1,
- "meta": {},
- "pluginVersion": "4.0.3",
- "queryType": "table",
- "rawQuery": true,
- "rawSql": "SELECT \n category,\n CAST(COUNT(*) AS INTEGER) AS Requests,\n ROUND(100.0 * COUNT(*) / SUM(COUNT(*)) OVER(), 2) AS percentage\n FROM \n (\n SELECT \n CASE\n WHEN endpoint LIKE 'openai.chat%' THEN 'Chat'\n WHEN endpoint LIKE 'openai.completions%' THEN 'Chat'\n WHEN endpoint LIKE 'anthropic.messages%' THEN 'Chat'\n WHEN endpoint LIKE 'cohere.summarize%' THEN 'Chat'\n WHEN endpoint LIKE 'cohere.generate%' THEN 'Chat'\n WHEN endpoint LIKE 'cohere.chat%' THEN 'Chat'\n WHEN endpoint LIKE '%embed%' THEN 'Embeddings'\n WHEN endpoint LIKE 'openai.images%' THEN 'Image'\n WHEN endpoint LIKE 'openai.audio%' THEN 'Audio'\n WHEN endpoint LIKE 'openai.fine_tuning%' THEN 'Fine Tuning'\n END AS category,\n endpoint\n FROM DOKU_LLM_DATA\n WHERE $__timeFilter(time)\n ) AS subquery\n GROUP BY category",
- "refId": "A",
- "sql": {
- "columns": [
- {
- "parameters": [],
- "type": "function"
- }
- ],
- "groupBy": [
- {
- "property": {
- "type": "string"
- },
- "type": "groupBy"
- }
- ],
- "limit": 50
- }
- }
- ],
- "title": "Usage by Category",
- "transparent": true,
- "type": "piechart"
- },
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "description": "Displays the cost breakdown by provider (OpenAI, Cohere, Anthropic) for LLM requests, offering insights into financial deployment across different services.",
- "fieldConfig": {
- "defaults": {
- "color": {
- "mode": "palette-classic"
- },
- "custom": {
- "hideFrom": {
- "legend": false,
- "tooltip": false,
- "viz": false
- }
- },
- "mappings": [],
- "unit": "currencyUSD",
- "unitScale": true
- },
- "overrides": []
- },
- "gridPos": {
- "h": 9,
- "w": 6,
- "x": 6,
- "y": 12
- },
- "id": 16,
- "options": {
- "displayLabels": [
- "name",
- "value"
- ],
- "legend": {
- "displayMode": "list",
- "placement": "bottom",
- "showLegend": false,
- "values": []
- },
- "pieType": "pie",
- "reduceOptions": {
- "calcs": [],
- "fields": "/.*/",
- "values": true
- },
- "tooltip": {
- "mode": "single",
- "sort": "asc"
- }
- },
- "pluginVersion": "10.2.3",
- "targets": [
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "editorMode": "code",
- "editorType": "sql",
- "format": 1,
- "meta": {},
- "pluginVersion": "4.0.3",
- "queryType": "table",
- "rawQuery": true,
- "rawSql": "SELECT\n CASE\n WHEN endpoint LIKE 'openai.%' THEN 'OpenAI'\n WHEN endpoint LIKE 'cohere.%' THEN 'Cohere'\n WHEN endpoint LIKE 'anthropic.%' THEN 'Anthropic'\n END AS provider,\n SUM(usageCost) AS total_cost\nFROM\n DOKU_LLM_DATA\nWHERE $__timeFilter(time)\nGROUP BY\n provider\nORDER BY\n total_cost DESC;",
- "refId": "A",
- "sql": {
- "columns": [
- {
- "parameters": [],
- "type": "function"
- }
- ],
- "groupBy": [
- {
- "property": {
- "type": "string"
- },
- "type": "groupBy"
- }
- ],
- "limit": 50
- }
- }
- ],
- "title": "Usage cost by Provider",
- "transparent": true,
- "type": "piechart"
- },
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "description": "This panel presents a pie chart detailing the distribution of expenses for LLM requests by various applications. It shows how budget allocations are consumed by different applications, enabling a deeper understanding of cost drivers and facilitating cost optimization efforts.",
- "fieldConfig": {
- "defaults": {
- "color": {
- "mode": "palette-classic"
- },
- "custom": {
- "hideFrom": {
- "legend": false,
- "tooltip": false,
- "viz": false
- }
- },
- "mappings": [],
- "unit": "currencyUSD",
- "unitScale": true
- },
- "overrides": []
- },
- "gridPos": {
- "h": 9,
- "w": 6,
- "x": 12,
- "y": 12
- },
- "id": 18,
- "options": {
- "displayLabels": [
- "name",
- "value"
- ],
- "legend": {
- "displayMode": "list",
- "placement": "bottom",
- "showLegend": false
- },
- "pieType": "pie",
- "reduceOptions": {
- "calcs": [
- "uniqueValues"
- ],
- "fields": "",
- "values": true
- },
- "tooltip": {
- "mode": "single",
- "sort": "none"
- }
- },
- "pluginVersion": "10.2.3",
- "targets": [
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "editorMode": "code",
- "editorType": "sql",
- "format": 1,
- "meta": {},
- "pluginVersion": "4.0.3",
- "queryType": "table",
- "rawQuery": true,
- "rawSql": " SELECT\n applicationName,\n sum(usageCost) AS \"usageCost\"\n FROM\n DOKU_LLM_DATA\n WHERE $__timeFilter(time)\n GROUP BY\n applicationName\n ORDER BY\n \"usageCost\" DESC",
- "refId": "A",
- "sql": {
- "columns": [
- {
- "parameters": [],
- "type": "function"
- }
- ],
- "groupBy": [
- {
- "property": {
- "type": "string"
- },
- "type": "groupBy"
- }
- ],
- "limit": 50
- }
- }
- ],
- "title": "Usage cost by Application",
- "transparent": true,
- "type": "piechart"
- },
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "description": "Visualizes the allocation of LLM request expenses across different environments, such as development, staging, and production. This breakdown helps in tracking and managing costs with respect to operational environments.",
- "fieldConfig": {
- "defaults": {
- "color": {
- "mode": "palette-classic"
- },
- "custom": {
- "hideFrom": {
- "legend": false,
- "tooltip": false,
- "viz": false
- }
- },
- "mappings": [],
- "unit": "currencyUSD",
- "unitScale": true
- },
- "overrides": []
- },
- "gridPos": {
- "h": 9,
- "w": 6,
- "x": 18,
- "y": 12
- },
- "id": 19,
- "options": {
- "displayLabels": [
- "name",
- "value"
- ],
- "legend": {
- "displayMode": "list",
- "placement": "bottom",
- "showLegend": false
- },
- "pieType": "pie",
- "reduceOptions": {
- "calcs": [
- "uniqueValues"
- ],
- "fields": "",
- "values": true
- },
- "tooltip": {
- "mode": "single",
- "sort": "none"
- }
- },
- "pluginVersion": "10.2.3",
- "targets": [
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "editorMode": "code",
- "editorType": "sql",
- "format": 1,
- "meta": {},
- "pluginVersion": "4.0.3",
- "queryType": "table",
- "rawQuery": true,
- "rawSql": " SELECT\n environment,\n sum(usageCost) AS \"usageCost\"\n FROM\n DOKU_LLM_DATA\n WHERE $__timeFilter(time)\n GROUP BY\n environment\n ORDER BY\n \"usageCost\" DESC",
- "refId": "A",
- "sql": {
- "columns": [
- {
- "parameters": [],
- "type": "function"
- }
- ],
- "groupBy": [
- {
- "property": {
- "type": "string"
- },
- "type": "groupBy"
- }
- ],
- "limit": 50
- }
- }
- ],
- "title": "Usage cost by Environment",
- "transparent": true,
- "type": "piechart"
- },
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "description": "This panel shows the average count of Prompt tokens used per LLM request",
- "fieldConfig": {
- "defaults": {
- "color": {
- "mode": "continuous-YlBl"
- },
- "mappings": [],
- "thresholds": {
- "mode": "absolute",
- "steps": [
- {
- "color": "green",
- "value": null
- },
- {
- "color": "red",
- "value": 5
- }
- ]
- },
- "unit": "none",
- "unitScale": true
- },
- "overrides": []
- },
- "gridPos": {
- "h": 3,
- "w": 6,
- "x": 0,
- "y": 21
- },
- "id": 9,
- "options": {
- "colorMode": "background",
- "graphMode": "area",
- "justifyMode": "auto",
- "orientation": "auto",
- "reduceOptions": {
- "calcs": [
- "lastNotNull"
- ],
- "fields": "",
- "values": false
- },
- "showPercentChange": false,
- "textMode": "auto",
- "wideLayout": true
- },
- "pluginVersion": "10.3.3",
- "targets": [
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "editorMode": "code",
- "editorType": "sql",
- "format": 1,
- "meta": {},
- "pluginVersion": "4.0.3",
- "queryType": "table",
- "rawQuery": true,
- "rawSql": "SELECT AVG(promptTokens) FROM DOKU_LLM_DATA WHERE \n $__timeFilter(\"time\")",
- "refId": "A",
- "sql": {
- "columns": [
- {
- "name": "AVG",
- "parameters": [
- {
- "name": "prompttokens",
- "type": "functionParameter"
- }
- ],
- "type": "function"
- }
- ],
- "groupBy": [
- {
- "property": {
- "type": "string"
- },
- "type": "groupBy"
- }
- ],
- "limit": 50
- },
- "table": "doku"
- }
- ],
- "title": "Avg Prompt Tokens / Request",
- "type": "stat"
- },
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "description": "Provides a time-series analysis of token consumption for LLM requests, highlighting trends in usage intensity and complexity over time.",
- "fieldConfig": {
- "defaults": {
- "color": {
- "mode": "palette-classic"
- },
- "custom": {
- "axisBorderShow": false,
- "axisCenteredZero": false,
- "axisColorMode": "series",
- "axisGridShow": true,
- "axisLabel": "",
- "axisPlacement": "auto",
- "barAlignment": 0,
- "drawStyle": "line",
- "fillOpacity": 10,
- "gradientMode": "hue",
- "hideFrom": {
- "legend": false,
- "tooltip": false,
- "viz": false
- },
- "insertNulls": 86400000,
- "lineInterpolation": "linear",
- "lineStyle": {
- "fill": "solid"
- },
- "lineWidth": 1,
- "pointSize": 5,
- "scaleDistribution": {
- "type": "linear"
- },
- "showPoints": "never",
- "spanNulls": true,
- "stacking": {
- "group": "A",
- "mode": "none"
- },
- "thresholdsStyle": {
- "mode": "off"
- }
- },
- "fieldMinMax": false,
- "mappings": [],
- "thresholds": {
- "mode": "absolute",
- "steps": [
- {
- "color": "green",
- "value": null
- },
- {
- "color": "red",
- "value": 80
- }
- ]
- },
- "unitScale": true
- },
- "overrides": []
- },
- "gridPos": {
- "h": 6,
- "w": 18,
- "x": 6,
- "y": 21
- },
- "id": 11,
- "options": {
- "legend": {
- "calcs": [],
- "displayMode": "list",
- "placement": "bottom",
- "showLegend": true
- },
- "tooltip": {
- "mode": "single",
- "sort": "none"
- }
- },
- "pluginVersion": "10.2.3",
- "targets": [
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "editorMode": "code",
- "editorType": "sql",
- "format": 1,
- "meta": {},
- "pluginVersion": "4.0.3",
- "queryType": "table",
- "rawQuery": true,
- "rawSql": "SELECT promptTokens AS \"Prompt Tokens\", \"time\" AS \"time\", completionTokens AS \"Completion Tokens\", totalTokens AS \"Total Tokens\" FROM DOKU_LLM_DATA",
- "refId": "A",
- "sql": {
- "columns": [
- {
- "alias": "\"Prompt Tokens\"",
- "parameters": [
- {
- "name": "prompttokens",
- "type": "functionParameter"
- }
- ],
- "type": "function"
- },
- {
- "alias": "\"time\"",
- "parameters": [
- {
- "name": "\"time\"",
- "type": "functionParameter"
- }
- ],
- "type": "function"
- },
- {
- "alias": "\"Completion Tokens\"",
- "parameters": [
- {
- "name": "completiontokens",
- "type": "functionParameter"
- }
- ],
- "type": "function"
- },
- {
- "alias": "\"Total Tokens\"",
- "parameters": [
- {
- "name": "totaltokens",
- "type": "functionParameter"
- }
- ],
- "type": "function"
- }
- ],
- "groupBy": [
- {
- "property": {
- "type": "string"
- },
- "type": "groupBy"
- }
- ],
- "limit": 50
- },
- "table": "doku"
- }
- ],
- "title": "Token usage",
- "type": "timeseries"
- },
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "description": "This panel shows the average count of Completion tokens used per LLM request",
- "fieldConfig": {
- "defaults": {
- "color": {
- "mode": "continuous-YlBl"
- },
- "mappings": [],
- "thresholds": {
- "mode": "absolute",
- "steps": [
- {
- "color": "green",
- "value": null
- },
- {
- "color": "red",
- "value": 5
- }
- ]
- },
- "unit": "none",
- "unitScale": true
- },
- "overrides": []
- },
- "gridPos": {
- "h": 3,
- "w": 6,
- "x": 0,
- "y": 24
- },
- "id": 7,
- "options": {
- "colorMode": "background",
- "graphMode": "area",
- "justifyMode": "auto",
- "orientation": "auto",
- "reduceOptions": {
- "calcs": [
- "lastNotNull"
- ],
- "fields": "",
- "values": false
- },
- "showPercentChange": false,
- "textMode": "auto",
- "wideLayout": true
- },
- "pluginVersion": "10.3.3",
- "targets": [
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "editorMode": "code",
- "editorType": "sql",
- "format": 1,
- "meta": {},
- "pluginVersion": "4.0.3",
- "queryType": "table",
- "rawQuery": true,
- "rawSql": "SELECT AVG(completionTokens) FROM DOKU_LLM_DATA WHERE \n $__timeFilter(\"time\")",
- "refId": "A",
- "sql": {
- "columns": [
- {
- "name": "AVG",
- "parameters": [
- {
- "name": "completiontokens",
- "type": "functionParameter"
- }
- ],
- "type": "function"
- }
- ],
- "groupBy": [
- {
- "property": {
- "type": "string"
- },
- "type": "groupBy"
- }
- ],
- "limit": 50
- },
- "table": "doku"
- }
- ],
- "title": "Avg Completion Tokens / Request",
- "type": "stat"
- },
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "description": "Displays the frequency of model usage over time, identifying the most utilised models and showcasing usage trends across different periods",
- "fieldConfig": {
- "defaults": {
- "color": {
- "fixedColor": "purple",
- "mode": "continuous-YlBl"
- },
- "mappings": [],
- "thresholds": {
- "mode": "absolute",
- "steps": [
- {
- "color": "green",
- "value": null
- },
- {
- "color": "red",
- "value": 80
- }
- ]
- },
- "unit": "none",
- "unitScale": true
- },
- "overrides": []
- },
- "gridPos": {
- "h": 6,
- "w": 12,
- "x": 0,
- "y": 27
- },
- "id": 13,
- "options": {
- "displayMode": "lcd",
- "maxVizHeight": 167,
- "minVizHeight": 10,
- "minVizWidth": 75,
- "namePlacement": "top",
- "orientation": "horizontal",
- "reduceOptions": {
- "calcs": [
- "sum"
- ],
- "fields": "/^total_count$/",
- "values": true
- },
- "showUnfilled": true,
- "sizing": "manual",
- "valueMode": "text"
- },
- "pluginVersion": "10.3.3",
- "targets": [
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "editorMode": "code",
- "editorType": "sql",
- "format": 1,
- "meta": {},
- "pluginVersion": "4.0.3",
- "queryType": "table",
- "rawQuery": true,
- "rawSql": "SELECT \n model,\n total_count,\n percentage_usage\nFROM \n (\n SELECT \n model,\n COUNT(*) AS total_count,\n ROUND(100.0 * COUNT(*) / SUM(COUNT(*)) OVER(), 2) AS percentage_usage\n FROM \n DOKU_LLM_DATA\n WHERE $__timeFilter(time)\n GROUP BY \n model\n ORDER BY \n percentage_usage DESC\n ) sub\nLIMIT 5;",
- "refId": "A",
- "sql": {
- "columns": [
- {
- "parameters": [
- {
- "name": "model",
- "type": "functionParameter"
- }
- ],
- "type": "function"
- }
- ],
- "groupBy": [
- {
- "property": {
- "type": "string"
- },
- "type": "groupBy"
- }
- ],
- "limit": 50
- },
- "table": "doku"
- }
- ],
- "title": "Top models by usage",
- "type": "bargauge"
- },
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "description": "Breaks down token usage across different LLM models, offering insights into which models are driving the highest token consumption.",
- "fieldConfig": {
- "defaults": {
- "color": {
- "mode": "palette-classic"
- },
- "custom": {
- "axisBorderShow": false,
- "axisCenteredZero": false,
- "axisColorMode": "text",
- "axisLabel": "",
- "axisPlacement": "auto",
- "barAlignment": 0,
- "drawStyle": "line",
- "fillOpacity": 0,
- "gradientMode": "none",
- "hideFrom": {
- "legend": false,
- "tooltip": false,
- "viz": false
- },
- "insertNulls": false,
- "lineInterpolation": "linear",
- "lineWidth": 1,
- "pointSize": 5,
- "scaleDistribution": {
- "type": "linear"
- },
- "showPoints": "auto",
- "spanNulls": false,
- "stacking": {
- "group": "A",
- "mode": "none"
- },
- "thresholdsStyle": {
- "mode": "off"
- }
- },
- "mappings": [],
- "thresholds": {
- "mode": "absolute",
- "steps": [
- {
- "color": "green",
- "value": null
- },
- {
- "color": "red",
- "value": 80
- }
- ]
- },
- "unitScale": true
- },
- "overrides": []
- },
- "gridPos": {
- "h": 6,
- "w": 12,
- "x": 12,
- "y": 27
- },
- "id": 14,
- "options": {
- "legend": {
- "calcs": [],
- "displayMode": "list",
- "placement": "bottom",
- "showLegend": true
- },
- "tooltip": {
- "mode": "single",
- "sort": "none"
- }
- },
- "pluginVersion": "10.2.3",
- "targets": [
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "editorMode": "code",
- "editorType": "sql",
- "format": 1,
- "meta": {},
- "pluginVersion": "4.0.3",
- "queryType": "table",
- "rawQuery": true,
- "rawSql": "SELECT \n DATE_TRUNC('day', \"time\") AS \"time\",\n model,\n COUNT(*) AS \"Model:\"\nFROM \n DOKU_LLM_DATA\nWHERE \n $__timeFilter(\"time\")\nGROUP BY \n 1, model\nORDER BY \n \"time\" ASC, model;",
- "refId": "A",
- "sql": {
- "columns": [
- {
- "parameters": [
- {
- "name": "model",
- "type": "functionParameter"
- }
- ],
- "type": "function"
- }
- ],
- "groupBy": [
- {
- "property": {
- "type": "string"
- },
- "type": "groupBy"
- }
- ],
- "limit": 50
- },
- "table": "doku"
- }
- ],
- "title": "Model usage by day",
- "type": "timeseries"
- },
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "description": "Table showing prompts and responses along with their associated costs and token usage.",
- "fieldConfig": {
- "defaults": {
- "color": {
- "mode": "palette-classic-by-name"
- },
- "custom": {
- "align": "center",
- "cellOptions": {
- "mode": "gradient",
- "type": "color-background"
- },
- "filterable": true,
- "inspect": true
- },
- "mappings": [],
- "thresholds": {
- "mode": "absolute",
- "steps": [
- {
- "color": "green",
- "value": null
- },
- {
- "color": "red",
- "value": 80
- }
- ]
- },
- "unit": "currencyUSD",
- "unitScale": true
- },
- "overrides": []
- },
- "gridPos": {
- "h": 8,
- "w": 24,
- "x": 0,
- "y": 33
- },
- "id": 15,
- "options": {
- "cellHeight": "sm",
- "footer": {
- "countRows": false,
- "fields": "",
- "reducer": [
- "sum"
- ],
- "show": false
- },
- "showHeader": true
- },
- "pluginVersion": "10.3.3",
- "targets": [
- {
- "datasource": {
- "type": "grafana-clickhouse-datasource",
- "uid": "${datasource}"
- },
- "editorMode": "code",
- "editorType": "sql",
- "format": 1,
- "meta": {},
- "pluginVersion": "4.0.3",
- "queryType": "table",
- "rawQuery": true,
- "rawSql": "SELECT \"time\", applicationName, model, prompt, response, usageCost FROM DOKU_LLM_DATA WHERE $__timeFilter(time)",
- "refId": "A",
- "sql": {
- "columns": [
- {
- "parameters": [
- {
- "name": "endpoint",
- "type": "functionParameter"
- }
- ],
- "type": "function"
- },
- {
- "parameters": [
- {
- "name": "prompt",
- "type": "functionParameter"
- }
- ],
- "type": "function"
- },
- {
- "parameters": [
- {
- "name": "response",
- "type": "functionParameter"
- }
- ],
- "type": "function"
- },
- {
- "parameters": [
- {
- "name": "totaltokens",
- "type": "functionParameter"
- }
- ],
- "type": "function"
- }
- ],
- "groupBy": [
- {
- "property": {
- "type": "string"
- },
- "type": "groupBy"
- }
- ],
- "limit": 50
- },
- "table": "doku"
- }
- ],
- "title": "User Activity",
- "transparent": true,
- "type": "table"
- }
- ],
- "refresh": "",
- "schemaVersion": 39,
- "tags": [
- "Doku",
- "OpenAI",
- "Cohere",
- "Anthropic"
- ],
- "templating": {
- "list": [
- {
- "current": {
- "selected": false,
- "text": "grafana-clickhouse-datasource",
- "value": "ef07bf93-52b4-4c5d-adda-8a498d388510"
- },
- "hide": 0,
- "includeAll": false,
- "label": "Datasource",
- "multi": false,
- "name": "datasource",
- "options": [],
- "query": "grafana-clickhouse-datasource",
- "queryValue": "",
- "refresh": 1,
- "regex": "",
- "skipUrlSync": false,
- "type": "datasource"
- }
- ]
- },
- "time": {
- "from": "now-7d",
- "to": "now"
- },
- "timepicker": {},
- "timezone": "",
- "title": "Doku - LLM Monitoring",
- "uid": "doku-llm-monitoring",
- "version": 3,
- "weekStart": ""
- }
- ```
-</Accordion>
-
----
-
-<CardGroup cols={2}>
-<Card title="Integrations" href="/latest/integrations/introduction" icon='circle-nodes'>
-Integrate your LLM Provider with Doku
-</Card>
-<Card title="API Reference" href="/latest/api-reference/introduction" icon='code'>
-OpenAPI specification for API Endpoints in Doku
-</Card>
-</CardGroup>
\ No newline at end of file
diff --git a/docs/latest/connections/highlight.mdx b/docs/latest/connections/highlight.mdx
new file mode 100644
index 00000000..f5aa03ec
--- /dev/null
+++ b/docs/latest/connections/highlight.mdx
@@ -0,0 +1,16 @@
+---
+title: 'Highlight.io'
+description: 'LLM Observability with Highlight.io and OpenLIT'
+---
+
+To send OpenTelemetry data collected by OpenLIt from your LLM Application, You need to set the `otlp_endpoint` and `otlp_headers` arguments according to your needs.
+
+````python
+import openlit
+
+openlit.init(otlp_endpoint="otlp_backend_endpoint", otlp_headers="otlp_backend_token")
+```
+
+Alternatively, you can configure the OTLP endpoint by setting the `OTEL_EXPORTER_OTLP_ENDPOINT` and the OTLP headers by setting the Appli`OTEL_EXPORTER_OTLP_HEADERS` environmentcation variable as recommended in the OpenTelemetry documentation.
+
+Refer to the OpenLIT [Python SDK repository](https://github.com/openlit/openlit/tree/main/sdk/python) for more advanced configurations and use cases.
diff --git a/docs/latest/connections/intro.mdx b/docs/latest/connections/intro.mdx
index 36b9d265..22df77b7 100644
--- a/docs/latest/connections/intro.mdx
+++ b/docs/latest/connections/intro.mdx
@@ -3,12 +3,20 @@ title: 'Connect to your existing Observablity Platform'
description: 'Send LLM Monitoring data to your Observablity Platform'
sidebarTitle: 'Introduction'
---
-Doku enhances observability by seamlessly exporting processed LLM data to your observability platform. This assists developers in bringing together all application-related data, including LLM usage metrics, on a unified platform, simplifying the visualization and assessment of the entire application ecosystem.
+OpenLIT enhances observability by seamlessly exporting processed LLM data to your observability platform. This assists developers in bringing together all application-related data, including LLM usage metrics, on a unified platform, simplifying the visualization and assessment of the entire application ecosystem.
-Below is a list of observability platforms that work seamlessly with Doku:
+Below is a list of observability platforms that work seamlessly with OpenLIT:
<CardGroup cols={2}>
- <Card title="Grafana OSS" href="/latest/connections/grafanaoss" icon={<svg role="img" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Grafana</title><path d="M23.02 10.59a8.578 8.578 0 0 0-.862-3.034 8.911 8.911 0 0 0-1.789-2.445c.337-1.342-.413-2.505-.413-2.505-1.292-.08-2.113.4-2.416.62-.052-.02-.102-.044-.154-.064-.22-.089-.446-.172-.677-.247-.231-.073-.47-.14-.711-.197a9.867 9.867 0 0 0-.875-.161C14.557.753 12.94 0 12.94 0c-1.804 1.145-2.147 2.744-2.147 2.744l-.018.093c-.098.029-.2.057-.298.088-.138.042-.275.094-.413.143-.138.055-.275.107-.41.166a8.869 8.869 0 0 0-1.557.87l-.063-.029c-2.497-.955-4.716.195-4.716.195-.203 2.658.996 4.33 1.235 4.636a11.608 11.608 0 0 0-.607 2.635C1.636 12.677.953 15.014.953 15.014c1.926 2.214 4.171 2.351 4.171 2.351.003-.002.006-.002.006-.005.285.509.615.994.986 1.446.156.19.32.371.488.548-.704 2.009.099 3.68.099 3.68 2.144.08 3.553-.937 3.849-1.173a9.784 9.784 0 0 0 3.164.501h.08l.055-.003.107-.002.103-.005.003.002c1.01 1.44 2.788 1.646 2.788 1.646 1.264-1.332 1.337-2.653 1.337-2.94v-.058c0-.02-.003-.039-.003-.06.265-.187.52-.387.758-.6a7.875 7.875 0 0 0 1.415-1.7c1.43.083 2.437-.885 2.437-.885-.236-1.49-1.085-2.216-1.264-2.354l-.018-.013-.016-.013a.217.217 0 0 1-.031-.02c.008-.092.016-.18.02-.27.011-.162.016-.323.016-.48v-.253l-.005-.098-.008-.135a1.891 1.891 0 0 0-.01-.13c-.003-.042-.008-.083-.013-.125l-.016-.124-.018-.122a6.215 6.215 0 0 0-2.032-3.73 6.015 6.015 0 0 0-3.222-1.46 6.292 6.292 0 0 0-.85-.048l-.107.002h-.063l-.044.003-.104.008a4.777 4.777 0 0 0-3.335 1.695c-.332.4-.592.84-.768 1.297a4.594 4.594 0 0 0-.312 1.817l.003.091c.005.055.007.11.013.164a3.615 3.615 0 0 0 .698 1.82 3.53 3.53 0 0 0 1.827 1.282c.33.098.66.14.971.137.039 0 .078 0 .114-.002l.063-.003c.02 0 .041-.003.062-.003.034-.002.065-.007.099-.01.007 0 .018-.003.028-.003l.031-.005.06-.008a1.18 1.18 0 0 0 .112-.02c.036-.008.072-.013.109-.024a2.634 2.634 0 0 0 .914-.415c.028-.02.056-.041.085-.065a.248.248 0 0 0 .039-.35.244.244 0 0 0-.309-.06l-.078.042c-.09.044-.184.083-.283.116a2.476 2.476 0 0 1-.475.096c-.028.003-.054.006-.083.006l-.083.002c-.026 0-.054 0-.08-.002l-.102-.006h-.012l-.024.006c-.016-.003-.031-.003-.044-.006-.031-.002-.06-.007-.091-.01a2.59 2.59 0 0 1-.724-.213 2.557 2.557 0 0 1-.667-.438 2.52 2.52 0 0 1-.805-1.475 2.306 2.306 0 0 1-.029-.444l.006-.122v-.023l.002-.031c.003-.021.003-.04.005-.06a3.163 3.163 0 0 1 1.352-2.29 3.12 3.12 0 0 1 .937-.43 2.946 2.946 0 0 1 .776-.101h.06l.07.002.045.003h.026l.07.005a4.041 4.041 0 0 1 1.635.49 3.94 3.94 0 0 1 1.602 1.662 3.77 3.77 0 0 1 .397 1.414l.005.076.003.075c.002.026.002.05.002.075 0 .024.003.052 0 .07v.065l-.002.073-.008.174a6.195 6.195 0 0 1-.08.639 5.1 5.1 0 0 1-.267.927 5.31 5.31 0 0 1-.624 1.13 5.052 5.052 0 0 1-3.237 2.014 4.82 4.82 0 0 1-.649.066l-.039.003h-.287a6.607 6.607 0 0 1-1.716-.265 6.776 6.776 0 0 1-3.4-2.274 6.75 6.75 0 0 1-.746-1.15 6.616 6.616 0 0 1-.714-2.596l-.005-.083-.002-.02v-.056l-.003-.073v-.096l-.003-.104v-.07l.003-.163c.008-.22.026-.45.054-.678a8.707 8.707 0 0 1 .28-1.355c.128-.444.286-.872.473-1.277a7.04 7.04 0 0 1 1.456-2.1 5.925 5.925 0 0 1 .953-.763c.169-.111.343-.213.524-.306.089-.05.182-.091.273-.135.047-.02.093-.042.138-.062a7.177 7.177 0 0 1 .714-.267l.145-.045c.049-.015.098-.026.148-.041.098-.029.197-.052.296-.076.049-.013.1-.02.15-.033l.15-.032.151-.028.076-.013.075-.01.153-.024c.057-.01.114-.013.171-.023l.169-.021c.036-.003.073-.008.106-.01l.073-.008.036-.003.042-.002c.057-.003.114-.008.171-.01l.086-.006h.023l.037-.003.145-.007a7.999 7.999 0 0 1 1.708.125 7.917 7.917 0 0 1 2.048.68 8.253 8.253 0 0 1 1.672 1.09l.09.077.089.078c.06.052.114.107.171.159.057.052.112.106.166.16.052.055.107.107.159.164a8.671 8.671 0 0 1 1.41 1.978c.012.026.028.052.04.078l.04.078.075.156c.023.051.05.1.07.153l.065.15a8.848 8.848 0 0 1 .45 1.34.19.19 0 0 0 .201.142.186.186 0 0 0 .172-.184c.01-.246.002-.532-.024-.856z"/></svg>}>
+ <Card title="OpenTelemetry Collector" href="/latest/connections/otelcol"
+ icon=
+ {<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 128 128">
+ <path fill="#f5a800" d="M67.648 69.797c-5.246 5.25-5.246 13.758 0 19.008 5.25 5.246 13.758 5.246 19.004 0 5.25-5.25 5.25-13.758 0-19.008-5.246-5.246-13.754-5.246-19.004 0Zm14.207 14.219a6.649 6.649 0 0 1-9.41 0 6.65 6.65 0 0 1 0-9.407 6.649 6.649 0 0 1 9.41 0c2.598 2.586 2.598 6.809 0 9.407ZM86.43 3.672l-8.235 8.234a4.17 4.17 0 0 0 0 5.875l32.149 32.149a4.17 4.17 0 0 0 5.875 0l8.234-8.235c1.61-1.61 1.61-4.261 0-5.87L92.29 3.671a4.159 4.159 0 0 0-5.86 0ZM28.738 108.895a3.763 3.763 0 0 0 0-5.31l-4.183-4.187a3.768 3.768 0 0 0-5.313 0l-8.644 8.649-.016.012-2.371-2.375c-1.313-1.313-3.45-1.313-4.75 0-1.313 1.312-1.313 3.449 0 4.75l14.246 14.242a3.353 3.353 0 0 0 4.746 0c1.3-1.313 1.313-3.45 0-4.746l-2.375-2.375.016-.012Zm0 0"/>
+ <path fill="#425cc7" d="M72.297 27.313 54.004 45.605c-1.625 1.625-1.625 4.301 0 5.926L65.3 62.824c7.984-5.746 19.18-5.035 26.363 2.153l9.148-9.149c1.622-1.625 1.622-4.297 0-5.922L78.22 27.313a4.185 4.185 0 0 0-5.922 0ZM60.55 67.585l-6.672-6.672c-1.563-1.562-4.125-1.562-5.684 0l-23.53 23.54a4.036 4.036 0 0 0 0 5.687l13.331 13.332a4.036 4.036 0 0 0 5.688 0l15.132-15.157c-3.199-6.609-2.625-14.593 1.735-20.73Zm0 0"/>
+ </svg>
+ }>
+ </Card>
+ <Card title="Grafana Tempo" href="/latest/connections/grafana-tempo" icon={<svg role="img" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Grafana</title><path d="M23.02 10.59a8.578 8.578 0 0 0-.862-3.034 8.911 8.911 0 0 0-1.789-2.445c.337-1.342-.413-2.505-.413-2.505-1.292-.08-2.113.4-2.416.62-.052-.02-.102-.044-.154-.064-.22-.089-.446-.172-.677-.247-.231-.073-.47-.14-.711-.197a9.867 9.867 0 0 0-.875-.161C14.557.753 12.94 0 12.94 0c-1.804 1.145-2.147 2.744-2.147 2.744l-.018.093c-.098.029-.2.057-.298.088-.138.042-.275.094-.413.143-.138.055-.275.107-.41.166a8.869 8.869 0 0 0-1.557.87l-.063-.029c-2.497-.955-4.716.195-4.716.195-.203 2.658.996 4.33 1.235 4.636a11.608 11.608 0 0 0-.607 2.635C1.636 12.677.953 15.014.953 15.014c1.926 2.214 4.171 2.351 4.171 2.351.003-.002.006-.002.006-.005.285.509.615.994.986 1.446.156.19.32.371.488.548-.704 2.009.099 3.68.099 3.68 2.144.08 3.553-.937 3.849-1.173a9.784 9.784 0 0 0 3.164.501h.08l.055-.003.107-.002.103-.005.003.002c1.01 1.44 2.788 1.646 2.788 1.646 1.264-1.332 1.337-2.653 1.337-2.94v-.058c0-.02-.003-.039-.003-.06.265-.187.52-.387.758-.6a7.875 7.875 0 0 0 1.415-1.7c1.43.083 2.437-.885 2.437-.885-.236-1.49-1.085-2.216-1.264-2.354l-.018-.013-.016-.013a.217.217 0 0 1-.031-.02c.008-.092.016-.18.02-.27.011-.162.016-.323.016-.48v-.253l-.005-.098-.008-.135a1.891 1.891 0 0 0-.01-.13c-.003-.042-.008-.083-.013-.125l-.016-.124-.018-.122a6.215 6.215 0 0 0-2.032-3.73 6.015 6.015 0 0 0-3.222-1.46 6.292 6.292 0 0 0-.85-.048l-.107.002h-.063l-.044.003-.104.008a4.777 4.777 0 0 0-3.335 1.695c-.332.4-.592.84-.768 1.297a4.594 4.594 0 0 0-.312 1.817l.003.091c.005.055.007.11.013.164a3.615 3.615 0 0 0 .698 1.82 3.53 3.53 0 0 0 1.827 1.282c.33.098.66.14.971.137.039 0 .078 0 .114-.002l.063-.003c.02 0 .041-.003.062-.003.034-.002.065-.007.099-.01.007 0 .018-.003.028-.003l.031-.005.06-.008a1.18 1.18 0 0 0 .112-.02c.036-.008.072-.013.109-.024a2.634 2.634 0 0 0 .914-.415c.028-.02.056-.041.085-.065a.248.248 0 0 0 .039-.35.244.244 0 0 0-.309-.06l-.078.042c-.09.044-.184.083-.283.116a2.476 2.476 0 0 1-.475.096c-.028.003-.054.006-.083.006l-.083.002c-.026 0-.054 0-.08-.002l-.102-.006h-.012l-.024.006c-.016-.003-.031-.003-.044-.006-.031-.002-.06-.007-.091-.01a2.59 2.59 0 0 1-.724-.213 2.557 2.557 0 0 1-.667-.438 2.52 2.52 0 0 1-.805-1.475 2.306 2.306 0 0 1-.029-.444l.006-.122v-.023l.002-.031c.003-.021.003-.04.005-.06a3.163 3.163 0 0 1 1.352-2.29 3.12 3.12 0 0 1 .937-.43 2.946 2.946 0 0 1 .776-.101h.06l.07.002.045.003h.026l.07.005a4.041 4.041 0 0 1 1.635.49 3.94 3.94 0 0 1 1.602 1.662 3.77 3.77 0 0 1 .397 1.414l.005.076.003.075c.002.026.002.05.002.075 0 .024.003.052 0 .07v.065l-.002.073-.008.174a6.195 6.195 0 0 1-.08.639 5.1 5.1 0 0 1-.267.927 5.31 5.31 0 0 1-.624 1.13 5.052 5.052 0 0 1-3.237 2.014 4.82 4.82 0 0 1-.649.066l-.039.003h-.287a6.607 6.607 0 0 1-1.716-.265 6.776 6.776 0 0 1-3.4-2.274 6.75 6.75 0 0 1-.746-1.15 6.616 6.616 0 0 1-.714-2.596l-.005-.083-.002-.02v-.056l-.003-.073v-.096l-.003-.104v-.07l.003-.163c.008-.22.026-.45.054-.678a8.707 8.707 0 0 1 .28-1.355c.128-.444.286-.872.473-1.277a7.04 7.04 0 0 1 1.456-2.1 5.925 5.925 0 0 1 .953-.763c.169-.111.343-.213.524-.306.089-.05.182-.091.273-.135.047-.02.093-.042.138-.062a7.177 7.177 0 0 1 .714-.267l.145-.045c.049-.015.098-.026.148-.041.098-.029.197-.052.296-.076.049-.013.1-.02.15-.033l.15-.032.151-.028.076-.013.075-.01.153-.024c.057-.01.114-.013.171-.023l.169-.021c.036-.003.073-.008.106-.01l.073-.008.036-.003.042-.002c.057-.003.114-.008.171-.01l.086-.006h.023l.037-.003.145-.007a7.999 7.999 0 0 1 1.708.125 7.917 7.917 0 0 1 2.048.68 8.253 8.253 0 0 1 1.672 1.09l.09.077.089.078c.06.052.114.107.171.159.057.052.112.106.166.16.052.055.107.107.159.164a8.671 8.671 0 0 1 1.41 1.978c.012.026.028.052.04.078l.04.078.075.156c.023.051.05.1.07.153l.065.15a8.848 8.848 0 0 1 .45 1.34.19.19 0 0 0 .201.142.186.186 0 0 0 .172-.184c.01-.246.002-.532-.024-.856z"/></svg>}>
</Card>
<Card title="Grafana Cloud" href="/latest/connections/grafanacloud" icon={<svg role="img" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Grafana</title><path d="M23.02 10.59a8.578 8.578 0 0 0-.862-3.034 8.911 8.911 0 0 0-1.789-2.445c.337-1.342-.413-2.505-.413-2.505-1.292-.08-2.113.4-2.416.62-.052-.02-.102-.044-.154-.064-.22-.089-.446-.172-.677-.247-.231-.073-.47-.14-.711-.197a9.867 9.867 0 0 0-.875-.161C14.557.753 12.94 0 12.94 0c-1.804 1.145-2.147 2.744-2.147 2.744l-.018.093c-.098.029-.2.057-.298.088-.138.042-.275.094-.413.143-.138.055-.275.107-.41.166a8.869 8.869 0 0 0-1.557.87l-.063-.029c-2.497-.955-4.716.195-4.716.195-.203 2.658.996 4.33 1.235 4.636a11.608 11.608 0 0 0-.607 2.635C1.636 12.677.953 15.014.953 15.014c1.926 2.214 4.171 2.351 4.171 2.351.003-.002.006-.002.006-.005.285.509.615.994.986 1.446.156.19.32.371.488.548-.704 2.009.099 3.68.099 3.68 2.144.08 3.553-.937 3.849-1.173a9.784 9.784 0 0 0 3.164.501h.08l.055-.003.107-.002.103-.005.003.002c1.01 1.44 2.788 1.646 2.788 1.646 1.264-1.332 1.337-2.653 1.337-2.94v-.058c0-.02-.003-.039-.003-.06.265-.187.52-.387.758-.6a7.875 7.875 0 0 0 1.415-1.7c1.43.083 2.437-.885 2.437-.885-.236-1.49-1.085-2.216-1.264-2.354l-.018-.013-.016-.013a.217.217 0 0 1-.031-.02c.008-.092.016-.18.02-.27.011-.162.016-.323.016-.48v-.253l-.005-.098-.008-.135a1.891 1.891 0 0 0-.01-.13c-.003-.042-.008-.083-.013-.125l-.016-.124-.018-.122a6.215 6.215 0 0 0-2.032-3.73 6.015 6.015 0 0 0-3.222-1.46 6.292 6.292 0 0 0-.85-.048l-.107.002h-.063l-.044.003-.104.008a4.777 4.777 0 0 0-3.335 1.695c-.332.4-.592.84-.768 1.297a4.594 4.594 0 0 0-.312 1.817l.003.091c.005.055.007.11.013.164a3.615 3.615 0 0 0 .698 1.82 3.53 3.53 0 0 0 1.827 1.282c.33.098.66.14.971.137.039 0 .078 0 .114-.002l.063-.003c.02 0 .041-.003.062-.003.034-.002.065-.007.099-.01.007 0 .018-.003.028-.003l.031-.005.06-.008a1.18 1.18 0 0 0 .112-.02c.036-.008.072-.013.109-.024a2.634 2.634 0 0 0 .914-.415c.028-.02.056-.041.085-.065a.248.248 0 0 0 .039-.35.244.244 0 0 0-.309-.06l-.078.042c-.09.044-.184.083-.283.116a2.476 2.476 0 0 1-.475.096c-.028.003-.054.006-.083.006l-.083.002c-.026 0-.054 0-.08-.002l-.102-.006h-.012l-.024.006c-.016-.003-.031-.003-.044-.006-.031-.002-.06-.007-.091-.01a2.59 2.59 0 0 1-.724-.213 2.557 2.557 0 0 1-.667-.438 2.52 2.52 0 0 1-.805-1.475 2.306 2.306 0 0 1-.029-.444l.006-.122v-.023l.002-.031c.003-.021.003-.04.005-.06a3.163 3.163 0 0 1 1.352-2.29 3.12 3.12 0 0 1 .937-.43 2.946 2.946 0 0 1 .776-.101h.06l.07.002.045.003h.026l.07.005a4.041 4.041 0 0 1 1.635.49 3.94 3.94 0 0 1 1.602 1.662 3.77 3.77 0 0 1 .397 1.414l.005.076.003.075c.002.026.002.05.002.075 0 .024.003.052 0 .07v.065l-.002.073-.008.174a6.195 6.195 0 0 1-.08.639 5.1 5.1 0 0 1-.267.927 5.31 5.31 0 0 1-.624 1.13 5.052 5.052 0 0 1-3.237 2.014 4.82 4.82 0 0 1-.649.066l-.039.003h-.287a6.607 6.607 0 0 1-1.716-.265 6.776 6.776 0 0 1-3.4-2.274 6.75 6.75 0 0 1-.746-1.15 6.616 6.616 0 0 1-.714-2.596l-.005-.083-.002-.02v-.056l-.003-.073v-.096l-.003-.104v-.07l.003-.163c.008-.22.026-.45.054-.678a8.707 8.707 0 0 1 .28-1.355c.128-.444.286-.872.473-1.277a7.04 7.04 0 0 1 1.456-2.1 5.925 5.925 0 0 1 .953-.763c.169-.111.343-.213.524-.306.089-.05.182-.091.273-.135.047-.02.093-.042.138-.062a7.177 7.177 0 0 1 .714-.267l.145-.045c.049-.015.098-.026.148-.041.098-.029.197-.052.296-.076.049-.013.1-.02.15-.033l.15-.032.151-.028.076-.013.075-.01.153-.024c.057-.01.114-.013.171-.023l.169-.021c.036-.003.073-.008.106-.01l.073-.008.036-.003.042-.002c.057-.003.114-.008.171-.01l.086-.006h.023l.037-.003.145-.007a7.999 7.999 0 0 1 1.708.125 7.917 7.917 0 0 1 2.048.68 8.253 8.253 0 0 1 1.672 1.09l.09.077.089.078c.06.052.114.107.171.159.057.052.112.106.166.16.052.055.107.107.159.164a8.671 8.671 0 0 1 1.41 1.978c.012.026.028.052.04.078l.04.078.075.156c.023.051.05.1.07.153l.065.15a8.848 8.848 0 0 1 .45 1.34.19.19 0 0 0 .201.142.186.186 0 0 0 .172-.184c.01-.246.002-.532-.024-.856z"/></svg>}>
</Card>
@@ -20,15 +28,39 @@ Below is a list of observability platforms that work seamlessly with Doku:
</Card>
<Card title="Dynatrace" href="/latest/connections/dynatrace" icon={<svg viewBox="0 0 24 24" role="img" xmlns="http://www.w3.org/2000/svg"><title>Dynatrace icon</title><path d="M9.373 0c-.31.006-.93.09-1.521.654C6.98 1.478 2.628 5.61.88 7.27.09 8.024.16 8.865.16 8.934v.377c.067-.292.187-.499.427-.825.496-.616 1.3-.788 1.627-.822a64.233 64.233 0 0 1 .002 0 64.233 64.233 0 0 1 6.527-.549c4.335-.137 7.197.225 7.197.225l6.084-5.793s-3.188-.6-6.82-1.027A93.394 93.394 0 0 0 9.566.006c-.021 0-.09-.008-.193-.006zm13.56 2.508l-6.066 5.79s.222 2.88-.137 7.198c-.189 2.45-.584 4.866-.875 6.494-.052.326-.256 1.114-.925 1.594-.29.198-.491.295-.748.363 1.546-.51 1.091-7.047 1.091-7.047-4.335.137-7.214-.222-7.214-.222L1.975 22.47s3.222.634 6.855 1.045c2.056.24 4.833.429 5.227.463.023 0 .045-.007.068-.012-.013.003-.022.009-.035.012.138 0 .259.015.379.015.085 0 .925.105 1.713-.648 1.748-1.663 6.083-5.81 6.94-6.633.788-.754.72-1.594.72-1.68a81.84 81.84 0 0 0-.207-5.654c-.24-3.65-.701-6.871-.701-6.871zM3.856 8.305C2.125 8.307.348 8.513.16 9.326c.017 1.216.05 3.137.205 5.28.24 3.65.703 6.886.703 6.886l6.082-5.79c-.017.017-.239-2.88.121-7.198H7.27s-1.684-.202-3.415-.2z"/></svg>}>
</Card>
+ <Card title="OpenObserve" href="/latest/connections/openobserve">
+ </Card>
+ <Card title="Jaeger" href="/latest/connections/jaeger"
+ icon={
+ <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 128 128">
+ <path fill="#231f20" d="M38.422 113.68c-1.805.414-7.117 3.289-11.711 4.16-4.59.875-8.563 1.336-9.957 1.851-1.39.512-2.473 1.54.258 2.567 2.738 1.027 15.992 1.387 17.18 0 1.187-1.387-.82-1.988-3.715-1.95-2.063.024-1.813-.69-1.805-.773 0 0 .129-.898 3.3-1.336 3.169-.433 17.18-1.742 16.923-3.234-.258-1.488-8.668-1.695-10.473-1.285Zm-6.406 10.41c-.094-.426-1.375-.52-2.856-.195-1.484.324-2.61.93-2.515 1.359.093.43 1.37.52 2.855.2 1.484-.325 2.605-.934 2.516-1.364Zm-6.164-.004c-.036-.422-1.352-.668-2.942-.543-1.59.129-2.851.574-2.82 1 .035.422 1.351.664 2.941.535 1.594-.121 2.856-.566 2.82-.992Zm-6.043-.664c-.047-.328-.942-.48-2-.336-1.063.14-1.883.527-1.836.86.043.327.941.48 2 .335 1.058-.144 1.879-.527 1.836-.86Zm-3.82-.586c-.04-.262-.9-.36-1.923-.211-1.023.145-1.816.48-1.78.746.038.27.902.367 1.921.219 1.02-.149 1.82-.485 1.777-.754Zm-.852-1.05c-.04-.27-.899-.364-1.922-.216-1.024.149-1.82.485-1.781.75.039.266.902.364 1.921.215 1.024-.144 1.82-.484 1.782-.75Zm-.465-1.157c-.035-.23-.781-.317-1.672-.188-.887.133-1.578.422-1.543.657.031.23.777.312 1.668.183.89-.125 1.582-.418 1.547-.652Zm51.297-5.512c-3.145.156-10.266-.203-11.246 1.442-.98 1.64 2.89 2.257 8.976 1.746 6.09-.516 14.703-1.184 15.067-3.032.359-1.847-1.602-1.492-1.809-2.668-.207-1.183 2.168-1.183 2.633-2.93.465-1.745-3.195-1.542-6.45-1.542-3.25 0-8.663.308-9.183 2.004-.516 1.695 2.477 1.695 4.594 2.105 2.113.414 1.496 1.184 1.496 1.184-.106 1.078-.93 1.539-4.078 1.691Zm-5.684 4.512c0-.492-1.222-.887-2.73-.887s-2.727.395-2.727.887c0 .484 1.219.883 2.727.883 1.508 0 2.73-.399 2.73-.883Zm6.113-.195c0-.45-.816-.809-1.82-.809s-1.82.36-1.82.809c0 .445.816.808 1.82.808s1.82-.363 1.82-.808Zm5.84-.579c0-.363-.894-.656-1.992-.656-1.101 0-1.996.293-1.996.656 0 .364.895.657 1.996.657 1.098 0 1.992-.293 1.992-.657Zm3.832-.73c0-.383-.648-.695-1.453-.695-.8 0-1.453.312-1.453.695 0 .383.652.691 1.453.691.805 0 1.453-.308 1.453-.691Zm3.793-.79c0-.374-.66-.675-1.472-.675-.813 0-1.47.3-1.47.676 0 .371.657.672 1.47.672.812 0 1.472-.301 1.472-.672ZM14.238 98.392c0 .879 1.922 1.707 5.328 2.445-.242-1.762-.093-3.531.133-4.91-3.492.742-5.46 1.582-5.46 2.469Zm100.559-2.266a7.604 7.604 0 0 1-1.953 2.98c-1.54 1.454-2.887 2.325-4.094 2.641 6.66-.933 10.613-2.094 10.613-3.351 0-.81-1.636-1.579-4.566-2.27Zm0 0"/>
+ <path fill="#67cfe3" d="M103.406 94.281c-.422-3.09-1.746-4.476-2.918-5.699-1.086-1.14-2.117-2.215-1.785-4.191.309-1.829 1.766-2.95 4.152-3.243-1.449-9.75-3.574-22.046-6.3-32.535-1.364-5.238-3.516-8.875-6.407-11.297-3.308 1.688-7.28 3.54-11.722 5.457a306.52 306.52 0 0 1-9.676 3.973c-2.531 2.707-5.305 5.379-7.004 6.14-1.207.54-2.285.759-3.219.759-2.02 0-3.386-1.012-4.043-1.91-.77.203-1.382.335-1.797.374-.496.055-1.23.118-2.148.184a2.8 2.8 0 0 1-.46 2.805c-.747.89-1.946 1.34-3.645 1.34-2.442 0-5.918-.926-10.57-2.801-.63-.254-1.259-.5-1.891-.739-.356.004-.711.004-1.067.004h-.004c-4.445 0-7.914-.136-10.636-.359-2.985 6.145-1.688 12.96-.598 18.59 1.047 5.398 4.676 14.996 8.043 23.246 1.137 2.789 2.3 5.57 3.488 8.34 9.11.8 20.793 1.281 33.531 1.281 15.16 0 28.81-.684 38.426-1.777-.703-2.868-1.586-6.86-1.742-7.88ZM28.32 68.011c0-5.8 4.727-10.5 10.555-10.5 5.824 0 10.547 4.7 10.547 10.5 0 2.891-1.176 5.509-3.074 7.41a10.682 10.682 0 0 1-2.137 1.65 10.499 10.499 0 0 1-5.336 1.44c-5.828 0-10.555-4.698-10.555-10.5ZM56.5 90.247c-2.223.66-3.023-1.883-3.262-2.988.016-.008.032-.02.047-.031 1.035-.645 2.238-1.383 3.59-1.899.156.422.402 1.14.55 1.899.247 1.28.223 2.68-.925 3.02Zm3.613-.898c-.554-.207-.972-1.121-1.27-2.121a18.719 18.719 0 0 1-.515-2.344c.258-.059.527-.106.797-.145.133-.02.418-.039 1.016-.039.547 0 1.207.02 1.91.04.199.003.406.011.617.011.059.477.121 1.172.2 2.184.01.105.01.199.01.293.032 2.53-2.187 2.34-2.765 2.12Zm9.496-6.387c-1.078.477-2.656.68-5.293.68-.894 0-1.816-.02-2.629-.04a63.082 63.082 0 0 0-1.925-.038c-.508 0-.88.015-1.102.042-2.488.329-4.543 1.61-6.195 2.641-.48.3-.938.582-1.36.817-.687.374-1.523.574-2.43.574-1.671 0-3.241-.653-4.206-1.746-.797-.907-1.133-2.043-.969-3.282.5-3.714 5.836-5.613 6.441-5.816l.977-.332a1.496 1.496 0 0 1-.074-.29c-.29-1.73 1.98-3.546 5.07-4.058l.414-.058c2.559-.317 4.805.398 5.504 1.691l1.191.008c2.711.023 4.954.387 6.653 1.082 1.715.695 2.761 1.707 2.953 2.848.387 2.293-.746 4.265-3.02 5.277Zm1.954-12.016c-5.825 0-10.547-4.703-10.547-10.504 0-5.8 4.722-10.504 10.547-10.504 5.824 0 10.55 4.704 10.55 10.504 0 5.801-4.722 10.504-10.55 10.504Zm0 0"/>
+ <path fill="#000" d="m85.074 25.055-.082-.137-.101-.133c-.098-.156-.485-.394-.516-.398l-.04-.02-.019-.012-.074-.035h-.008l-.015-.008-.106-.035-.215-.074c-.144-.05-.304-.07-.457-.101-.156-.028-.32-.028-.48-.036a4.047 4.047 0 0 0-.488.04 3.526 3.526 0 0 0-1.657.796 5.275 5.275 0 0 0-1.043 1.22 8.6 8.6 0 0 0-1.03 2.417 9.917 9.917 0 0 0-.313 1.79c-.024.218-.024.39-.028.507-.004.117 0 .18 0 .18l.332-.598c.211-.375.504-.906.864-1.523.367-.61.804-1.31 1.332-1.942.265-.316.558-.61.867-.836.308-.219.625-.375.941-.422.078-.011.16-.023.239-.03.082.01.16 0 .242.019.086.02.168.015.254.043l.203.054.062.032-.008-.008h.012c0 .004.004.008.008.011l.004.004.023.008h-.011c-.004 0-.008 0-.012-.004.012.008.02.02.027.043.043.074.078.23.09.399.016.382-.016.761-.09 1.136-.058.375-.136.739-.226 1.106-.16.695-.32 1.285-.422 1.703-.11.418-.168.66-.168.66s.183-.176.457-.516c.375-.476.715-.98 1.008-1.507a8.36 8.36 0 0 0 .523-1.121c.16-.418.309-.88.356-1.438a2.503 2.503 0 0 0-.118-.96 1.407 1.407 0 0 0-.117-.274Zm0 0"/>
+ <path fill="#000" d="m83.75 25.816-.012-.003.012.011h.004l-.004-.004Zm0 0"/>
+ <path fill="#231f20" d="M19.648 45.129h.145c-.05-.086-.098-.176-.145-.262Zm1.29-4.074c.25.496.546.968.89 1.406.121.16.227.273.3.355.067.082.11.121.11.121s-.043-.226-.12-.609c-.071-.387-.192-.926-.294-1.558a11.31 11.31 0 0 1-.12-1c-.017-.336-.017-.7.054-.961a.731.731 0 0 1 .137-.29.342.342 0 0 1 .148-.081l.047-.012.082-.016c.023-.004-.008.016-.012.016-.004.004-.015.004-.023.004h-.016l.008.004c.02.007.031.007.047.011.078.028.195.094.32.184.262.187.531.48.79.773.257.309.503.621.737.942.473.64.91 1.261 1.293 1.797.313.437.63.875.957 1.3.122.164.254.329.387.489l-.02-.164c-.015-.102-.035-.262-.074-.457a11.835 11.835 0 0 0-.414-1.586 13.412 13.412 0 0 0-.914-2.141 8.953 8.953 0 0 0-.722-1.145 5.303 5.303 0 0 0-1.055-1.097 2.918 2.918 0 0 0-.844-.43c-.094-.02-.183-.039-.277-.05l-.074-.012h-.094c-.067 0-.125.004-.192.007-.054.008-.144.016-.171.024l-.079.02-.078.023-.105.031-.031.012-.059.027a1.773 1.773 0 0 0-.824.707 2.082 2.082 0 0 0-.29.895c-.05.55.06.996.169 1.398.113.367.254.723.425 1.063Zm0 0"/>
+ <path fill="#dfcaa3" d="M25.805 105.574c2.472 0 4.21-1.34 5.437-3.078a362.39 362.39 0 0 1-5.883-14.394c-.593.5-1.273 1.253-2.015 2.39-1.836 2.84-3.352 9.438-1.446 12.926.797 1.45 2.075 2.156 3.907 2.156Zm87.308-16.355c-1.453-3.73-4.535-6.383-7.5-6.446l-.101-.011c-.008 0-.578-.082-1.344-.082-1.613 0-3.594.34-3.867 1.976-.192 1.133.304 1.711 1.36 2.817 1.202 1.261 2.85 2.984 3.347 6.593.566 4.125 1.578 6.223 3.012 6.223.668 0 1.882-.398 3.898-2.3 2.48-2.34 2.242-6.063 1.195-8.77Zm0 0"/>
+ <path fill="#231f20" d="M41.246 71.703a3.32 3.32 0 0 1-3.324 3.313 3.32 3.32 0 0 1-3.328-3.313 3.32 3.32 0 0 1 3.328-3.312 3.297 3.297 0 0 1 2.348.968c.625.621.976 1.465.976 2.344Zm32.215-7.762a3.314 3.314 0 0 1-3.324 3.313 3.318 3.318 0 0 1-3.328-3.313c0-1.828 1.492-3.308 3.328-3.308a3.316 3.316 0 0 1 3.324 3.308Zm0 0"/>
+ <path fill="#648c1a" d="M28.895 34.707c2.597.695 5.53 1.047 8.726 1.047 5.129 0 16.02-.988 31.328-7.633l.344-.152a9.049 9.049 0 0 1 .21-2.512c.337-1.535 1.013-2.84 1.837-3.703-.156-.59-.29-1.02-.383-1.238-1.766-.938-16.324-6.336-23.922-6.336-.762 0-1.422.054-1.969.164-6.73 1.37-16.96 13.023-17.324 14.672-.11.714-.078 2.957.004 5.382Zm-.13 16.543a5.41 5.41 0 0 0-.66-.11 2.822 2.822 0 0 1-2.945-2.304 2.67 2.67 0 0 1-.043-.43 30.14 30.14 0 0 0-2.242 1.39l-1.27.876-.937-1.227a32.58 32.58 0 0 1-2.785-4.418c-2.25 1.059-4.012 2.215-4.442 3.313-.082.207-.046.32.036.441.367.535 2.55 2.172 15.289 2.469Zm26.454-3.59a2.84 2.84 0 0 1 3.468.332c.141-.023.383-.082.735-.242 1.398-.66 6.426-6.008 10.25-10.586.137-.16.285-.305.457-.434-8.734 3.758-20.938 7.864-32.559 7.864-1.867 0-3.64-.106-5.289-.32l.258.746-1.453.554a33.91 33.91 0 0 0-.68.274c1.871.433 4.403 1.289 7.578 2.57 5.809 2.332 8.032 2.422 8.586 2.39a2.85 2.85 0 0 1 2.563-.035 88.955 88.955 0 0 0 3.383-.261c.32-.035.797-.133 1.398-.29a2.802 2.802 0 0 1 1.305-2.562ZM89.05 30.473c-.422 2.511-1.239 5.27-1.774 6.02l-.507.702a118.116 118.116 0 0 0 6.07-3.133c6.035-3.367 6.789-4.84 6.875-5.214.055-.246-.004-.32-.031-.352-.067-.082-.493-.492-2.399-.492-2.082 0-4.996.476-8.039 1.133-.055.449-.121.894-.195 1.336Zm-2.352 6.757-.87-.066a48.844 48.844 0 0 0-3.782-.133c-2.25 0-5.219.137-7.652.711.48.992.335 2.172-.372 3.02a159.513 159.513 0 0 1-2.812 3.277c2.2-.89 4.39-1.805 6.566-2.746a218.13 218.13 0 0 0 8.918-4.063Zm0 0"/>
+ <path fill="#dfcaa3" d="M69.594 29.594c-6.117 2.656-19.52 7.773-31.973 7.773-3.156 0-6.246-.328-9.144-1.11.316.477.617.966.898 1.462 1.078 1.883 1.863 3.746 2.293 4.843 1.508.235 3.473.422 5.902.422 7.153 0 18.336-1.629 33.68-8.504.293-.925.613-1.84.957-2.746-.031 0-.062.008-.094.008-.16 0-.324-.02-.48-.055-.953-.207-1.66-.98-2.04-2.093Zm0 0"/>
+ <path fill="#67cfe3" d="M19.793 45.129a32.127 32.127 0 0 0 2.164 3.344c3.703-2.555 8.55-4.399 8.55-4.399s-.124-.363-.359-.96c-.14-.36-.289-.72-.441-1.075a32.483 32.483 0 0 0-1.39-2.898 23.597 23.597 0 0 0-1.243-2.07c-1.484-2.223-3.37-4.114-5.484-4.114-.664 0-1.356.188-2.059.613-3.879 2.336-1.875 7.684.117 11.297.047.09.098.176.145.262Zm.55-6.535c.028-.278.102-.586.29-.895.191-.316.48-.562.824-.707l.059-.027.027-.012.11-.031.077-.024.079-.02c.027-.007.117-.015.171-.023.067-.003.125-.007.192-.007h.094l.074.011c.09.012.187.032.277.051.344.106.61.266.844.43.45.344.77.715 1.055 1.097.285.376.515.766.722 1.145.367.688.672 1.402.914 2.14.176.52.313 1.051.414 1.59.04.192.059.352.075.454l.02.164s-.15-.176-.388-.489a40.282 40.282 0 0 1-.957-1.3c-.382-.536-.82-1.157-1.293-1.797-.234-.32-.48-.633-.738-.942-.258-.293-.527-.586-.789-.77a1.324 1.324 0 0 0-.32-.187c-.02-.004-.028-.004-.043-.011l-.008-.004h.008c.012 0 .023 0 .027-.004.004 0 .035-.02.012-.016l-.082.02-.047.008a.325.325 0 0 0-.148.082.731.731 0 0 0-.137.289c-.07.261-.07.625-.055.96.024.344.07.684.121.997.102.632.223 1.175.293 1.562.078.383.121.61.121.61s-.043-.04-.11-.122c-.073-.082-.179-.195-.3-.355a8.375 8.375 0 0 1-.89-1.406 6.402 6.402 0 0 1-.422-1.063c-.114-.402-.223-.847-.172-1.398Zm1.247-6.442v.805Zm0 0"/>
+ <path fill="#dfcaa3" d="M73.574 20.637c.164 0 .324.02.485.05 1.187.266 1.988 1.399 2.257 2.977 2.258-3.16 4.73-4.762 7.364-4.762 1.11 0 2.086.262 2.902.766.773-.934 1.535-1.883 2.277-2.844-1.046.188-3.23.473-3.23.473C93.895 14.27 93.23 6.035 93.23 6.035c0 1.422-4.277 4.828-4.277 4.828.192-1.23-.473-2.84-.473-2.84.188 1.61-4.94 5.774-4.94 5.774.378-.758.089-2.082.089-2.082-.285 1.512-2.563 2.082-2.563 2.082 1.422-1.703 4.086-10.692 2.09-11.262-1.996-.566-4.754 5.863-4.754 5.863-.093-1.511-.949-1.511-.949-1.511.383 4.73-3.418 8.515-3.418 8.515-.285-.945-1.808-1.422-1.808-1.422.492 1.055-.067 5.852-.239 7.207.504-.351 1.043-.55 1.586-.55Zm0 0"/>
+ <path fill="#000" d="M71.547 29.844v.004c.043.047.086.086.129.12.015.012.031.02.047.032.03.02.062.043.097.059a.641.641 0 0 0 .16.058.864.864 0 0 0 .266.004c.246-.039.52-.191.797-.445a42.51 42.51 0 0 1 .805-1.774c.257-.527.523-1.05.808-1.566.406-2.14-.144-3.898-.945-4.074a.525.525 0 0 0-.137-.012c-.824 0-2.023 1.426-2.492 3.555-.34 1.543-.184 2.914.219 3.68l.004.003c.07.14.148.262.238.356Zm0 0"/>
+ <path fill="#67cfe3" d="M83.742 25.805h-.012l.008.008.012.003c-.004-.003-.004-.007-.008-.011Zm.035.023-.023-.008-.004-.004v.004l.004.004c.004.004.008.004.012.004Zm0 0"/>
+ <path fill="#67cfe3" d="M83.68 20.512c-4.707 0-8.168 7.054-9.98 11.847a56.69 56.69 0 0 0-.884 2.524c-.14.437-.273.879-.402 1.32.227.043.45.125.66.227 2.742-.817 6.297-1.004 8.973-1.004 2.27 0 3.91.133 3.91.133.715-.996 4.852-15.047-2.277-15.047Zm1.629 5.777a5.063 5.063 0 0 1-.356 1.438 8.36 8.36 0 0 1-.523 1.12 11.785 11.785 0 0 1-1.008 1.508c-.274.34-.457.516-.457.516s.058-.242.168-.66c.101-.418.262-1.008.422-1.703.082-.344.168-.719.226-1.106.074-.375.106-.754.09-1.136-.012-.168-.047-.325-.09-.399-.008-.023-.015-.035-.027-.043h-.004a64.74 64.74 0 0 0-.012-.012l-.062-.03-.203-.055c-.086-.028-.168-.024-.254-.043-.082-.02-.16-.008-.242-.02a5.58 5.58 0 0 1-.239.027c-.316.051-.633.207-.941.426a5.32 5.32 0 0 0-.867.836c-.528.633-.965 1.332-1.328 1.942-.364.617-.657 1.148-.868 1.523l-.332.598s-.004-.063 0-.18c.004-.117.004-.29.028-.508.05-.605.152-1.203.312-1.789.195-.73.5-1.574 1.031-2.422a5.437 5.437 0 0 1 1.043-1.215 3.526 3.526 0 0 1 1.657-.797c.16-.023.324-.035.484-.039.164.008.328.008.484.036.153.03.313.05.457.101l.215.074.106.035.015.008h.008l.074.035.02.012.039.02c.031.004.418.242.516.398l.101.133.082.137a1.2 1.2 0 0 1 .117.273c.121.36.133.676.118.961Zm0 0"/>
+ <path fill="#000" d="M58.527 51.941c.774 0 1.618-.207 2.516-.605 1.879-.844 6.453-5.418 11.664-11.66.277-.332.336-.793.152-1.188a1.114 1.114 0 0 0-1.011-.636 1.117 1.117 0 0 0-.864.398c-2.261 2.719-8.632 10-10.824 11.035l-.031.02a4.78 4.78 0 0 1-1.176.367l-.836.133-.61-.582a1.15 1.15 0 0 0-.773-.301c-.214 0-.422.062-.597.176a1.11 1.11 0 0 0-.344 1.535c.086.133.89 1.308 2.734 1.308Zm-10.629.246c-.18 0-.363.043-.523.126l-.332.171-.367.028c-.09.004-.18.004-.27.004-1.043 0-3.61-.325-9.066-2.52-6.016-2.418-8.403-2.781-9.285-2.781a1.66 1.66 0 0 0-.313.02 1.104 1.104 0 0 0-.902 1.293 1.13 1.13 0 0 0 1.094.917c.023 0 .046 0 .07-.004l.125-.007.121.011c.664.055 2.793.422 8.254 2.614 4.414 1.777 7.754 2.675 9.93 2.675 1.144 0 1.925-.246 2.324-.722a1.114 1.114 0 0 0-.145-1.57 1.083 1.083 0 0 0-.715-.255Zm0 0"/>
+ <path fill="#dfcaa3" d="M63.008 75.36s-.313 3.671-5.508 4.437c-.984.14-1.828.207-2.555.207-2.761 0-3.851-.906-4.492-1.695 0 0-4.976 1.671-5.355 4.515-.285 2.121 1.77 3.211 3.578 3.211.61 0 1.191-.125 1.648-.375 1.809-.992 4.512-3.168 8.125-3.644.328-.04.778-.055 1.313-.055 1.234 0 2.922.082 4.554.082 1.856 0 3.645-.106 4.637-.547 2.23-.992 2.23-2.695 2.09-3.547-.16-.941-2.43-2.543-8.035-2.59Zm0 0"/>
+ <path fill="#231f20" d="m56.957 78.383.184-.031.203-.043c2.703-.551 4.691-2.106 4.71-3.66a1.86 1.86 0 0 0-.222-.903c-.7-1.293-2.945-2.008-5.504-1.691l-.414.058c-3.09.512-5.363 2.328-5.074 4.059.02.101.043.2.078.293.531 1.55 3.129 2.402 6.039 1.918Zm0 0"/>
+ </svg>
+ }>
+ </Card>
+ <Card title="Highlight.io" href="/latest/connections/highlight">
+ </Card>
</CardGroup>
---
<CardGroup cols={2}>
<Card title="Integrations" href="/latest/integrations/introduction" icon='circle-nodes'>
-Integrate your LLM Provider with Doku
-</Card>
-<Card title="API Reference" href="/latest/api-reference/introduction" icon='code'>
-OpenAPI specification for API Endpoints in Doku
+Start Monitoring your LLM Application
</Card>
</CardGroup>
\ No newline at end of file
diff --git a/docs/latest/connections/new-relic.mdx b/docs/latest/connections/new-relic.mdx
index 982b53af..15ea0756 100644
--- a/docs/latest/connections/new-relic.mdx
+++ b/docs/latest/connections/new-relic.mdx
@@ -1,589 +1,16 @@
---
title: 'New Relic'
-description: 'LLM Observability with New Relic and Doku'
+description: 'LLM Observability with Grafana Tempo and OpenLIT'
---
-<Frame>
- <img src="https://github.com/dokulabs/doku/blob/main/docs/images/new-relic-dashboard-1.jpg?raw=true" />
- <img src="https://github.com/dokulabs/doku/blob/main/docs/images/new-relic-dashboard-2.jpg?raw=true" />
- <img src="https://github.com/dokulabs/doku/blob/main/docs/images/new-relic-dashboard-3.jpg?raw=true" />
-</Frame>
+To send OpenTelemetry data collected by OpenLIt from your LLM Application, You need to set the `otlp_endpoint` and `otlp_headers` arguments according to your needs.
-Doku can automatically send LLM usage data from Doku to New Relic using the [Report Metrics HTTP API](https://docs.newrelic.com/docs/data-apis/ingest-apis/metric-api/report-metrics-metric-api/) and [Send Logs API](https://docs.newrelic.com/docs/logs/log-api/introduction-log-api/)
+```python
+import openlit
-Make the following curl request to Doku to add a connection for New Relic. See more on the [Connections API](/latest/api-reference/endpoint/connections/create)
-
-```shell
-curl --request POST \
- --url https://<YOUR_DOKU_INGESTER_URL>/api/connections \
- --header 'Authorization: <DOKU_API_KEY>' \
- --header 'Content-Type: application/json' \
- --data '{
- "Platform": "newrelic",
- "MetricsUrl": "<YOUR_NEWRELIC_METRICS_URL>",
- "LogsUrl": "<YOUR_NEWRELIC_LOGS_URL>",
- "ApiKey": "<YOUR_NEWRELIC_API_KEY>"
-}'
+openlit.init(otlp_endpoint="otlp_backend_endpoint", otlp_headers="otlp_backend_token")
```
-## New Relic Resources
-
-<Accordion title="Dashboard">
- ```json
- {
- "name": "Doku - LLM Monitoring",
- "description": null,
- "permissions": "PUBLIC_READ_WRITE",
- "pages": [
- {
- "name": "Doku - LLM Monitoring",
- "description": null,
- "widgets": [
- {
- "title": "",
- "layout": {
- "column": 1,
- "row": 1,
- "width": 1,
- "height": 1
- },
- "linkedEntityGuids": null,
- "visualization": {
- "id": "viz.markdown"
- },
- "rawConfiguration": {
- "text": "![doku-image](https://github.com/dokulabs/.github/blob/main/profile/assets/favicon.png?raw=true )"
- }
- },
- {
- "title": "",
- "layout": {
- "column": 2,
- "row": 1,
- "width": 2,
- "height": 1
- },
- "linkedEntityGuids": null,
- "visualization": {
- "id": "viz.billboard"
- },
- "rawConfiguration": {
- "facet": {
- "showOtherSeries": false
- },
- "nrqlQueries": [
- {
- "accountIds": [
- 4060909
- ],
- "query": "SELECT COUNT(doku.LLM.Request.Duration) AS 'Total Requests' FROM Metric WHERE job.name='doku'"
- }
- ],
- "platformOptions": {
- "ignoreTimeRange": false
- }
- }
- },
- {
- "title": "Seconds",
- "layout": {
- "column": 4,
- "row": 1,
- "width": 2,
- "height": 1
- },
- "linkedEntityGuids": null,
- "visualization": {
- "id": "viz.billboard"
- },
- "rawConfiguration": {
- "dataFormatters": [],
- "facet": {
- "showOtherSeries": false
- },
- "nrqlQueries": [
- {
- "accountIds": [
- 4060909
- ],
- "query": "SELECT average(doku.LLM.Request.Duration) AS 'Avg Request Duration' FROM Metric"
- }
- ],
- "platformOptions": {
- "ignoreTimeRange": false
- }
- }
- },
- {
- "title": "",
- "layout": {
- "column": 6,
- "row": 1,
- "width": 2,
- "height": 1
- },
- "linkedEntityGuids": null,
- "visualization": {
- "id": "viz.billboard"
- },
- "rawConfiguration": {
- "dataFormatters": [],
- "facet": {
- "showOtherSeries": false
- },
- "nrqlQueries": [
- {
- "accountIds": [
- 4060909
- ],
- "query": "SELECT AVERAGE(doku.LLM.Total.Tokens) AS 'Average Tokens / Request' FROM Metric"
- }
- ],
- "platformOptions": {
- "ignoreTimeRange": false
- }
- }
- },
- {
- "title": "",
- "layout": {
- "column": 8,
- "row": 1,
- "width": 2,
- "height": 1
- },
- "linkedEntityGuids": null,
- "visualization": {
- "id": "viz.billboard"
- },
- "rawConfiguration": {
- "dataFormatters": [],
- "facet": {
- "showOtherSeries": false
- },
- "nrqlQueries": [
- {
- "accountIds": [
- 4060909
- ],
- "query": "SELECT AVERAGE(doku.LLM.Usage.Cost) AS 'Average Cost / Request' FROM Metric"
- }
- ],
- "platformOptions": {
- "ignoreTimeRange": false
- }
- }
- },
- {
- "title": "",
- "layout": {
- "column": 10,
- "row": 1,
- "width": 3,
- "height": 1
- },
- "linkedEntityGuids": null,
- "visualization": {
- "id": "viz.billboard"
- },
- "rawConfiguration": {
- "dataFormatters": [],
- "facet": {
- "showOtherSeries": false
- },
- "nrqlQueries": [
- {
- "accountIds": [
- 4060909
- ],
- "query": "SELECT SUM(doku.LLM.Usage.Cost) AS 'Average Cost / Request' FROM Metric"
- }
- ],
- "platformOptions": {
- "ignoreTimeRange": false
- }
- }
- },
- {
- "title": "Total Request ",
- "layout": {
- "column": 1,
- "row": 2,
- "width": 12,
- "height": 2
- },
- "linkedEntityGuids": null,
- "visualization": {
- "id": "viz.area"
- },
- "rawConfiguration": {
- "facet": {
- "showOtherSeries": false
- },
- "legend": {
- "enabled": false
- },
- "nrqlQueries": [
- {
- "accountIds": [
- 4060909
- ],
- "query": "SELECT count(doku.LLM.Request.Duration) FROM Metric TIMESERIES"
- }
- ],
- "platformOptions": {
- "ignoreTimeRange": false
- }
- }
- },
- {
- "title": "Usage Cost by Category",
- "layout": {
- "column": 1,
- "row": 4,
- "width": 6,
- "height": 3
- },
- "linkedEntityGuids": null,
- "visualization": {
- "id": "viz.pie"
- },
- "rawConfiguration": {
- "facet": {
- "showOtherSeries": true
- },
- "legend": {
- "enabled": true
- },
- "nrqlQueries": [
- {
- "accountIds": [
- 4060909
- ],
- "query": "SELECT SUM(doku.LLM.Usage.Cost AS 'Generation') FROM Metric FACET generation\n"
- }
- ],
- "platformOptions": {
- "ignoreTimeRange": false
- }
- }
- },
- {
- "title": "Usage cost by Platform",
- "layout": {
- "column": 7,
- "row": 4,
- "width": 6,
- "height": 3
- },
- "linkedEntityGuids": null,
- "visualization": {
- "id": "viz.pie"
- },
- "rawConfiguration": {
- "facet": {
- "showOtherSeries": true
- },
- "legend": {
- "enabled": true
- },
- "nrqlQueries": [
- {
- "accountIds": [
- 4060909
- ],
- "query": "SELECT sum(doku.LLM.Usage.Cost AS 'Platform') FROM Metric FACET platform\n"
- }
- ],
- "platformOptions": {
- "ignoreTimeRange": false
- }
- }
- },
- {
- "title": "Usage Cost by Environment",
- "layout": {
- "column": 1,
- "row": 7,
- "width": 6,
- "height": 3
- },
- "linkedEntityGuids": null,
- "visualization": {
- "id": "viz.pie"
- },
- "rawConfiguration": {
- "facet": {
- "showOtherSeries": true
- },
- "legend": {
- "enabled": true
- },
- "nrqlQueries": [
- {
- "accountIds": [
- 4060909
- ],
- "query": "SELECT sum(doku.LLM.Usage.Cost AS 'Environment') FROM Metric FACET environment\n"
- }
- ],
- "platformOptions": {
- "ignoreTimeRange": false
- }
- }
- },
- {
- "title": "Usage Cost by Application",
- "layout": {
- "column": 7,
- "row": 7,
- "width": 6,
- "height": 3
- },
- "linkedEntityGuids": null,
- "visualization": {
- "id": "viz.pie"
- },
- "rawConfiguration": {
- "facet": {
- "showOtherSeries": true
- },
- "legend": {
- "enabled": true
- },
- "nrqlQueries": [
- {
- "accountIds": [
- 4060909
- ],
- "query": "SELECT SUM(doku.LLM.Usage.Cost AS 'Applications') FROM Metric FACET applicationName\n"
- }
- ],
- "platformOptions": {
- "ignoreTimeRange": false
- }
- }
- },
- {
- "title": "Average Tokens ",
- "layout": {
- "column": 1,
- "row": 10,
- "width": 12,
- "height": 3
- },
- "linkedEntityGuids": null,
- "visualization": {
- "id": "viz.stacked-bar"
- },
- "rawConfiguration": {
- "facet": {
- "showOtherSeries": false
- },
- "legend": {
- "enabled": true
- },
- "nrqlQueries": [
- {
- "accountIds": [
- 4060909
- ],
- "query": "SELECT average(doku.LLM.Prompt.Tokens), average(doku.LLM.Completion.Tokens) FROM Metric TIMESERIES"
- }
- ],
- "platformOptions": {
- "ignoreTimeRange": false
- },
- "units": {
- "unit": "COUNT"
- }
- }
- },
- {
- "title": "",
- "layout": {
- "column": 1,
- "row": 13,
- "width": 6,
- "height": 1
- },
- "linkedEntityGuids": null,
- "visualization": {
- "id": "viz.billboard"
- },
- "rawConfiguration": {
- "dataFormatters": [],
- "facet": {
- "showOtherSeries": false
- },
- "nrqlQueries": [
- {
- "accountIds": [
- 4060909
- ],
- "query": "SELECT AVERAGE(doku.LLM.Prompt.Tokens) AS 'Average Prompt Tokens / Request' FROM Metric"
- }
- ],
- "platformOptions": {
- "ignoreTimeRange": false
- }
- }
- },
- {
- "title": "",
- "layout": {
- "column": 7,
- "row": 13,
- "width": 6,
- "height": 1
- },
- "linkedEntityGuids": null,
- "visualization": {
- "id": "viz.billboard"
- },
- "rawConfiguration": {
- "dataFormatters": [],
- "facet": {
- "showOtherSeries": false
- },
- "nrqlQueries": [
- {
- "accountIds": [
- 4060909
- ],
- "query": "SELECT AVERAGE(doku.LLM.Completion.Tokens) AS 'Average Completion Tokens / Request' FROM Metric"
- }
- ],
- "platformOptions": {
- "ignoreTimeRange": false
- }
- }
- },
- {
- "title": "Top Models by Usage",
- "layout": {
- "column": 1,
- "row": 14,
- "width": 4,
- "height": 3
- },
- "linkedEntityGuids": null,
- "visualization": {
- "id": "viz.bar"
- },
- "rawConfiguration": {
- "facet": {
- "showOtherSeries": false
- },
- "nrqlQueries": [
- {
- "accountIds": [
- 4060909
- ],
- "query": "SELECT COUNT(doku.LLM.Request.Duration AS 'Generation') FROM Metric FACET model\n"
- }
- ],
- "platformOptions": {
- "ignoreTimeRange": false
- }
- }
- },
- {
- "title": "Average Cost / Model",
- "layout": {
- "column": 5,
- "row": 14,
- "width": 8,
- "height": 3
- },
- "linkedEntityGuids": null,
- "visualization": {
- "id": "viz.area"
- },
- "rawConfiguration": {
- "facet": {
- "showOtherSeries": false
- },
- "legend": {
- "enabled": true
- },
- "nrqlQueries": [
- {
- "accountIds": [
- 4060909
- ],
- "query": "SELECT AVERAGE(doku.LLM.Usage.Cost AS 'Generation') FROM Metric FACET model TIMESERIES\n"
- }
- ],
- "platformOptions": {
- "ignoreTimeRange": false
- },
- "units": {
- "unit": "APDEX"
- }
- }
- },
- {
- "title": "Prompts",
- "layout": {
- "column": 1,
- "row": 17,
- "width": 6,
- "height": 3
- },
- "linkedEntityGuids": null,
- "visualization": {
- "id": "logger.log-table-widget"
- },
- "rawConfiguration": {
- "nrqlQueries": [
- {
- "accountIds": [
- 4060909
- ],
- "query": "SELECT timestamp, message FROM Log WHERE job.name='doku' AND type='prompt'"
- }
- ]
- }
- },
- {
- "title": "Response's",
- "layout": {
- "column": 7,
- "row": 17,
- "width": 6,
- "height": 3
- },
- "linkedEntityGuids": null,
- "visualization": {
- "id": "logger.log-table-widget"
- },
- "rawConfiguration": {
- "nrqlQueries": [
- {
- "accountIds": [
- 4060909
- ],
- "query": "SELECT timestamp, message FROM Log WHERE job.name='doku' AND type='response' OR type='image'"
- }
- ]
- }
- }
- ]
- }
- ],
- "variables": []
- }
- ```
-</Accordion>
-
----
+Alternatively, you can configure the OTLP endpoint by setting the `OTEL_EXPORTER_OTLP_ENDPOINT` and the OTLP headers by setting the Appli`OTEL_EXPORTER_OTLP_HEADERS` environmentcation variable as recommended in the OpenTelemetry documentation.
-<CardGroup cols={2}>
-<Card title="Integrations" href="/latest/integrations/introduction" icon='circle-nodes'>
-Integrate your LLM Provider with Doku
-</Card>
-<Card title="API Reference" href="/latest/api-reference/introduction" icon='code'>
-OpenAPI specification for API Endpoints in Doku
-</Card>
-</CardGroup>
\ No newline at end of file
+Refer to the OpenLIT [Python SDK repository](https://github.com/openlit/openlit/tree/main/sdk/python) for more advanced configurations and use cases.
diff --git a/docs/latest/connections/openobserve.mdx b/docs/latest/connections/openobserve.mdx
new file mode 100644
index 00000000..87a29d01
--- /dev/null
+++ b/docs/latest/connections/openobserve.mdx
@@ -0,0 +1,16 @@
+---
+title: 'OpenObserve'
+description: 'LLM Observability with OpenObserve and OpenLIT'
+---
+
+To send OpenTelemetry data collected by OpenLIt from your LLM Application, You need to set the `otlp_endpoint` and `otlp_headers` arguments according to your needs.
+
+````python
+import openlit
+
+openlit.init(otlp_endpoint="otlp_backend_endpoint", otlp_headers="otlp_backend_token")
+```
+
+Alternatively, you can configure the OTLP endpoint by setting the `OTEL_EXPORTER_OTLP_ENDPOINT` and the OTLP headers by setting the Appli`OTEL_EXPORTER_OTLP_HEADERS` environmentcation variable as recommended in the OpenTelemetry documentation.
+
+Refer to the OpenLIT [Python SDK repository](https://github.com/openlit/openlit/tree/main/sdk/python) for more advanced configurations and use cases.
diff --git a/docs/latest/connections/otelcol.mdx b/docs/latest/connections/otelcol.mdx
new file mode 100644
index 00000000..f86f9a33
--- /dev/null
+++ b/docs/latest/connections/otelcol.mdx
@@ -0,0 +1,16 @@
+---
+title: 'OpenTelemetry Collector'
+description: 'LLM Observability with OpenTelemetry Collector and OpenLIT'
+---
+
+To send OpenTelemetry data collected by OpenLIt from your LLM Application, You need to set the `otlp_endpoint` and `otlp_headers` arguments according to your needs.
+
+```python
+import openlit
+
+openlit.init(otlp_endpoint="http://127.0.0.1:4318")
+```
+
+Alternatively, you can configure the OTLP endpoint by setting the `OTEL_EXPORTER_OTLP_ENDPOINT` and the OTLP headers by setting the `OTEL_EXPORTER_OTLP_HEADERS`(Optional) environment variable as recommended in the OpenTelemetry documentation.
+
+Refer to the OpenLIT [Python SDK repository](https://github.com/openlit/openlit/tree/main/sdk/python) for more advanced configurations and use cases.
diff --git a/docs/latest/connections/signoz.mdx b/docs/latest/connections/signoz.mdx
index a10a1b7f..50ee5760 100644
--- a/docs/latest/connections/signoz.mdx
+++ b/docs/latest/connections/signoz.mdx
@@ -1,1480 +1,16 @@
---
title: 'SigNoz'
-description: 'LLM Observability with SigNoz and Doku'
+description: 'LLM Observability with SigNoz and OpenLIT'
---
-<Frame>
- <img src="https://github.com/dokulabs/doku/blob/main/docs/images/signoz-dashboard-1.jpg?raw=true" />
- <img src="https://github.com/dokulabs/doku/blob/main/docs/images/signoz-dashboard-2.jpg?raw=true" />
-</Frame>
+To send OpenTelemetry data collected by OpenLIt from your LLM Application, You need to set the `otlp_endpoint` and `otlp_headers` arguments according to your needs.
-Doku can automatically send LLM usage data from Doku to SigNoz using the [HTTP Logs API](https://signoz.io/docs/userguide/send-logs-http/)
+```python
+import openlit
-Make the following curl request to Doku to add a connection for SigNoz. See more on the [Connections API](/latest/api-reference/endpoint/connections/create)
-
-```shell
-curl --request POST \
- --url https://<YOUR_DOKU_INGESTER_URL>/api/connections \
- --header 'Authorization: <DOKU_API_KEY>' \
- --header 'Content-Type: application/json' \
- --data '{
- "Platform": "signoz",
- "LogsUrl": "<YOUR_SIGNOZ_LOGS_URL>",
- "ApiKey": "<YOUR_SIGNOZ_API_KEY>"
-}'
+openlit.init(otlp_endpoint="otlp_backend_endpoint", otlp_headers="otlp_backend_token")
```
-## SigNoz Resources
-
-<Accordion title="Dashboard">
- ```json
- {
- "description": "This dashboard tracks costs, tokens, & model usage for LLM Applications via Doku for enhanced performance and evaluation.",
- "layout": [
- {
- "h": 3,
- "i": "4d33e5a0-2e34-4626-9dff-f795cd8e62ee",
- "moved": false,
- "static": false,
- "w": 9,
- "x": 0,
- "y": 5
- },
- {
- "h": 3,
- "i": "5705486f-dfab-4428-96ce-97d5ccfc0620",
- "moved": false,
- "static": false,
- "w": 6,
- "x": 6,
- "y": 17
- },
- {
- "h": 3,
- "i": "532306fd-bc68-4e3e-a76f-313b92d22f0e",
- "moved": false,
- "static": false,
- "w": 3,
- "x": 9,
- "y": 14
- },
- {
- "h": 3,
- "i": "60e26de7-3b68-4348-b31b-bb7275a26a45",
- "moved": false,
- "static": false,
- "w": 12,
- "x": 0,
- "y": 2
- },
- {
- "h": 2,
- "i": "443e85bf-9863-4002-abd4-0407fa12e92d",
- "moved": false,
- "static": false,
- "w": 3,
- "x": 2,
- "y": 0
- },
- {
- "h": 3,
- "i": "84dc9645-8c6c-4b9a-9558-2386b6eb4d10",
- "moved": false,
- "static": false,
- "w": 6,
- "x": 0,
- "y": 17
- },
- {
- "h": 2,
- "i": "99d0eee5-9e91-4496-a7ee-70508cbbca6b",
- "moved": false,
- "static": false,
- "w": 3,
- "x": 5,
- "y": 0
- },
- {
- "h": 2,
- "i": "a0f453e8-0b6f-45bb-910c-6171a50919a9",
- "moved": false,
- "static": false,
- "w": 2,
- "x": 0,
- "y": 0
- },
- {
- "h": 2,
- "i": "4f778a79-54cd-4a99-a5b0-3d06647c1fb9",
- "moved": false,
- "static": false,
- "w": 4,
- "x": 8,
- "y": 0
- },
- {
- "h": 3,
- "i": "1128a154-ed4f-4189-b1ca-d52f28a78d28",
- "moved": false,
- "static": false,
- "w": 3,
- "x": 9,
- "y": 11
- },
- {
- "h": 3,
- "i": "0c3a8c8a-5116-47f2-9dfe-242440ee65df",
- "moved": false,
- "static": false,
- "w": 3,
- "x": 9,
- "y": 8
- },
- {
- "h": 3,
- "i": "ec9a5671-4a0c-4172-a383-82f37ab682f7",
- "moved": false,
- "static": false,
- "w": 3,
- "x": 9,
- "y": 5
- },
- {
- "h": 3,
- "i": "af5f5471-e523-49e5-8de3-17a8c43fd115",
- "moved": false,
- "static": false,
- "w": 9,
- "x": 0,
- "y": 8
- },
- {
- "h": 3,
- "i": "4f33601c-9707-4b52-8194-e6671c52666e",
- "moved": false,
- "static": false,
- "w": 9,
- "x": 0,
- "y": 11
- },
- {
- "h": 3,
- "i": "11cba8dc-b2de-4eb6-a546-8a3cbe43cba2",
- "moved": false,
- "static": false,
- "w": 9,
- "x": 0,
- "y": 14
- }
- ],
- "name": "",
- "tags": [
- "Doku",
- "OpenAI",
- "Cohere",
- "Anthropic"
- ],
- "title": "Doku - LLM Monitoring",
- "variables": {},
- "widgets": [
- {
- "description": "",
- "fillSpans": false,
- "id": "a0f453e8-0b6f-45bb-910c-6171a50919a9",
- "isStacked": false,
- "nullZeroValues": "zero",
- "opacity": "1",
- "panelTypes": "value",
- "query": {
- "builder": {
- "queryData": [
- {
- "aggregateAttribute": {
- "dataType": "",
- "id": "------false",
- "isColumn": false,
- "isJSON": false,
- "key": "",
- "type": ""
- },
- "aggregateOperator": "count",
- "dataSource": "logs",
- "disabled": false,
- "expression": "A",
- "filters": {
- "items": [
- {
- "id": "9a3b0db1",
- "key": {
- "dataType": "string",
- "id": "job--string--resource--false",
- "isColumn": false,
- "isJSON": false,
- "key": "job",
- "type": "resource"
- },
- "op": "=",
- "value": "doku"
- }
- ],
- "op": "AND"
- },
- "groupBy": [],
- "having": [],
- "legend": "",
- "limit": null,
- "orderBy": [],
- "queryName": "A",
- "reduceTo": "sum",
- "stepInterval": 60
- }
- ],
- "queryFormulas": []
- },
- "clickhouse_sql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "id": "984ba011-8db8-45aa-a4e2-8668569236bb",
- "promql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "queryType": "builder"
- },
- "softMax": null,
- "softMin": null,
- "thresholds": [],
- "timePreferance": "GLOBAL_TIME",
- "title": "Total Requests",
- "yAxisUnit": "none"
- },
- {
- "description": "",
- "fillSpans": false,
- "id": "99d0eee5-9e91-4496-a7ee-70508cbbca6b",
- "isStacked": false,
- "nullZeroValues": "zero",
- "opacity": "1",
- "panelTypes": "value",
- "query": {
- "builder": {
- "queryData": [
- {
- "aggregateAttribute": {
- "dataType": "float64",
- "id": "totalTokens--float64--tag--false",
- "isColumn": false,
- "isJSON": false,
- "key": "totalTokens",
- "type": "tag"
- },
- "aggregateOperator": "avg",
- "dataSource": "logs",
- "disabled": false,
- "expression": "A",
- "filters": {
- "items": [],
- "op": "AND"
- },
- "groupBy": [],
- "having": [],
- "legend": "",
- "limit": null,
- "orderBy": [],
- "queryName": "A",
- "reduceTo": "last",
- "stepInterval": 60
- }
- ],
- "queryFormulas": []
- },
- "clickhouse_sql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "id": "ebc81d59-4638-46a7-b111-adb28ccf64ac",
- "promql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "queryType": "builder"
- },
- "softMax": null,
- "softMin": null,
- "thresholds": [],
- "timePreferance": "GLOBAL_TIME",
- "title": "Avg Tokens / Request",
- "yAxisUnit": "none"
- },
- {
- "description": "",
- "fillSpans": false,
- "id": "84dc9645-8c6c-4b9a-9558-2386b6eb4d10",
- "isStacked": false,
- "nullZeroValues": "zero",
- "opacity": "1",
- "panelTypes": "table",
- "query": {
- "builder": {
- "queryData": [
- {
- "aggregateAttribute": {
- "dataType": "float64",
- "id": "requestDuration--float64--tag--false",
- "isColumn": false,
- "isJSON": false,
- "key": "requestDuration",
- "type": "tag"
- },
- "aggregateOperator": "count",
- "dataSource": "logs",
- "disabled": false,
- "expression": "A",
- "filters": {
- "items": [
- {
- "id": "eb4d013a",
- "key": {
- "dataType": "string",
- "id": "job--string--resource--false",
- "isColumn": false,
- "isJSON": false,
- "key": "job",
- "type": "resource"
- },
- "op": "=",
- "value": "doku"
- }
- ],
- "op": "AND"
- },
- "groupBy": [
- {
- "dataType": "string",
- "id": "model--string--tag--false",
- "isColumn": false,
- "isJSON": false,
- "key": "model",
- "type": "tag"
- }
- ],
- "having": [],
- "legend": "Count",
- "limit": null,
- "orderBy": [
- {
- "columnName": "timestamp",
- "order": "desc"
- }
- ],
- "queryName": "A",
- "reduceTo": "sum",
- "stepInterval": 60
- }
- ],
- "queryFormulas": []
- },
- "clickhouse_sql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "id": "2e7436ea-db19-4790-aeef-e905849ed401",
- "promql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "queryType": "builder"
- },
- "softMax": null,
- "softMin": null,
- "thresholds": [],
- "timePreferance": "GLOBAL_TIME",
- "title": "Model Usage",
- "yAxisUnit": "none"
- },
- {
- "description": "",
- "fillSpans": false,
- "id": "4f778a79-54cd-4a99-a5b0-3d06647c1fb9",
- "isStacked": false,
- "nullZeroValues": "zero",
- "opacity": "1",
- "panelTypes": "value",
- "query": {
- "builder": {
- "queryData": [
- {
- "aggregateAttribute": {
- "dataType": "float64",
- "id": "usageCost--float64--tag--false",
- "isColumn": false,
- "isJSON": false,
- "key": "usageCost",
- "type": "tag"
- },
- "aggregateOperator": "avg",
- "dataSource": "logs",
- "disabled": false,
- "expression": "A",
- "filters": {
- "items": [
- {
- "id": "6ce37ed5",
- "key": {
- "dataType": "string",
- "id": "job--string--resource--false",
- "isColumn": false,
- "isJSON": false,
- "key": "job",
- "type": "resource"
- },
- "op": "=",
- "value": "doku"
- }
- ],
- "op": "AND"
- },
- "groupBy": [],
- "having": [],
- "legend": "",
- "limit": null,
- "orderBy": [],
- "queryName": "A",
- "reduceTo": "last",
- "stepInterval": 60
- }
- ],
- "queryFormulas": []
- },
- "clickhouse_sql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "id": "6d5d2593-1ae7-481f-88be-ba762b9196a0",
- "promql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "queryType": "builder"
- },
- "softMax": null,
- "softMin": null,
- "thresholds": [],
- "timePreferance": "GLOBAL_TIME",
- "title": "Avg Cost / Request",
- "yAxisUnit": "none"
- },
- {
- "description": "",
- "fillSpans": false,
- "id": "443e85bf-9863-4002-abd4-0407fa12e92d",
- "isStacked": false,
- "nullZeroValues": "zero",
- "opacity": "1",
- "panelTypes": "value",
- "query": {
- "builder": {
- "queryData": [
- {
- "aggregateAttribute": {
- "dataType": "float64",
- "id": "requestDuration--float64--tag--false",
- "isColumn": false,
- "isJSON": false,
- "key": "requestDuration",
- "type": "tag"
- },
- "aggregateOperator": "avg",
- "dataSource": "logs",
- "disabled": false,
- "expression": "A",
- "filters": {
- "items": [
- {
- "id": "65e9c28f",
- "key": {
- "dataType": "string",
- "id": "job--string--resource--false",
- "isColumn": false,
- "isJSON": false,
- "key": "job",
- "type": "resource"
- },
- "op": "=",
- "value": "doku"
- }
- ],
- "op": "AND"
- },
- "groupBy": [],
- "having": [],
- "legend": "",
- "limit": null,
- "orderBy": [],
- "queryName": "A",
- "reduceTo": "last",
- "stepInterval": 60
- }
- ],
- "queryFormulas": []
- },
- "clickhouse_sql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "id": "38484c36-2230-45a7-9f0d-4211c9d00975",
- "promql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "queryType": "builder"
- },
- "softMax": null,
- "softMin": null,
- "thresholds": [],
- "timePreferance": "GLOBAL_TIME",
- "title": "Avg Request Duration",
- "yAxisUnit": "none"
- },
- {
- "description": "",
- "fillSpans": false,
- "id": "60e26de7-3b68-4348-b31b-bb7275a26a45",
- "isStacked": false,
- "nullZeroValues": "zero",
- "opacity": "1",
- "panelTypes": "graph",
- "query": {
- "builder": {
- "queryData": [
- {
- "aggregateAttribute": {
- "dataType": "float64",
- "id": "requestDuration--float64--tag--false",
- "isColumn": false,
- "isJSON": false,
- "key": "requestDuration",
- "type": "tag"
- },
- "aggregateOperator": "count",
- "dataSource": "logs",
- "disabled": false,
- "expression": "A",
- "filters": {
- "items": [
- {
- "id": "f28b0509",
- "key": {
- "dataType": "string",
- "id": "job--string--resource--false",
- "isColumn": false,
- "isJSON": false,
- "key": "job",
- "type": "resource"
- },
- "op": "=",
- "value": "doku"
- }
- ],
- "op": "AND"
- },
- "groupBy": [],
- "having": [],
- "legend": "Count",
- "limit": null,
- "orderBy": [],
- "queryName": "A",
- "reduceTo": "sum",
- "stepInterval": 60
- }
- ],
- "queryFormulas": []
- },
- "clickhouse_sql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "id": "c6d1c906-6116-4559-a1eb-33b53d0abfcd",
- "promql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "queryType": "builder"
- },
- "softMax": null,
- "softMin": null,
- "thresholds": [],
- "timePreferance": "GLOBAL_TIME",
- "title": "Requests overtime",
- "yAxisUnit": "none"
- },
- {
- "description": "",
- "fillSpans": false,
- "id": "532306fd-bc68-4e3e-a76f-313b92d22f0e",
- "isStacked": false,
- "nullZeroValues": "zero",
- "opacity": "1",
- "panelTypes": "table",
- "query": {
- "builder": {
- "queryData": [
- {
- "aggregateAttribute": {
- "dataType": "float64",
- "id": "requestDuration--float64--tag--false",
- "isColumn": false,
- "isJSON": false,
- "key": "requestDuration",
- "type": "tag"
- },
- "aggregateOperator": "count",
- "dataSource": "logs",
- "disabled": false,
- "expression": "A",
- "filters": {
- "items": [
- {
- "id": "78e35563",
- "key": {
- "dataType": "string",
- "id": "job--string--resource--false",
- "isColumn": false,
- "isJSON": false,
- "key": "job",
- "type": "resource"
- },
- "op": "=",
- "value": "doku"
- }
- ],
- "op": "AND"
- },
- "groupBy": [
- {
- "dataType": "string",
- "id": "applicationName--string--tag--false",
- "isColumn": false,
- "isJSON": false,
- "key": "applicationName",
- "type": "tag"
- }
- ],
- "having": [],
- "legend": "",
- "limit": null,
- "orderBy": [],
- "queryName": "A",
- "reduceTo": "sum",
- "stepInterval": 60
- }
- ],
- "queryFormulas": []
- },
- "clickhouse_sql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "id": "24b9c833-d9ef-40de-b10c-1dbfbd7ef7c5",
- "promql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "queryType": "builder"
- },
- "softMax": null,
- "softMin": null,
- "thresholds": [],
- "timePreferance": "GLOBAL_TIME",
- "title": "Usage by Application",
- "yAxisUnit": "none"
- },
- {
- "description": "",
- "fillSpans": false,
- "id": "1128a154-ed4f-4189-b1ca-d52f28a78d28",
- "isStacked": false,
- "nullZeroValues": "zero",
- "opacity": "1",
- "panelTypes": "table",
- "query": {
- "builder": {
- "queryData": [
- {
- "aggregateAttribute": {
- "dataType": "float64",
- "id": "requestDuration--float64--tag--false",
- "isColumn": false,
- "isJSON": false,
- "key": "requestDuration",
- "type": "tag"
- },
- "aggregateOperator": "count",
- "dataSource": "logs",
- "disabled": false,
- "expression": "A",
- "filters": {
- "items": [
- {
- "id": "c79b6091",
- "key": {
- "dataType": "string",
- "id": "job--string--resource--false",
- "isColumn": false,
- "isJSON": false,
- "key": "job",
- "type": "resource"
- },
- "op": "=",
- "value": "doku"
- }
- ],
- "op": "AND"
- },
- "groupBy": [
- {
- "dataType": "string",
- "id": "environment--string--resource--false",
- "isColumn": false,
- "isJSON": false,
- "key": "environment",
- "type": "resource"
- }
- ],
- "having": [],
- "legend": "",
- "limit": null,
- "orderBy": [],
- "queryName": "A",
- "reduceTo": "sum",
- "stepInterval": 60
- }
- ],
- "queryFormulas": []
- },
- "clickhouse_sql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "id": "790116c6-535c-4e08-9fa2-0a158eb7b796",
- "promql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "queryType": "builder"
- },
- "softMax": null,
- "softMin": null,
- "thresholds": [],
- "timePreferance": "GLOBAL_TIME",
- "title": "Usage by Environment",
- "yAxisUnit": "none"
- },
- {
- "description": "",
- "fillSpans": false,
- "id": "0c3a8c8a-5116-47f2-9dfe-242440ee65df",
- "isStacked": false,
- "nullZeroValues": "zero",
- "opacity": "1",
- "panelTypes": "table",
- "query": {
- "builder": {
- "queryData": [
- {
- "aggregateAttribute": {
- "dataType": "float64",
- "id": "requestDuration--float64--tag--false",
- "isColumn": false,
- "isJSON": false,
- "key": "requestDuration",
- "type": "tag"
- },
- "aggregateOperator": "count",
- "dataSource": "logs",
- "disabled": false,
- "expression": "A",
- "filters": {
- "items": [
- {
- "id": "b575368c",
- "key": {
- "dataType": "string",
- "id": "applicationName--string--tag--false",
- "isColumn": false,
- "isJSON": false,
- "key": "applicationName",
- "type": "tag"
- },
- "op": "exists",
- "value": ""
- }
- ],
- "op": "AND"
- },
- "groupBy": [
- {
- "dataType": "string",
- "id": "platform--string--tag--false",
- "isColumn": false,
- "isJSON": false,
- "key": "platform",
- "type": "tag"
- }
- ],
- "having": [],
- "legend": "",
- "limit": null,
- "orderBy": [],
- "queryName": "A",
- "reduceTo": "sum",
- "stepInterval": 60
- }
- ],
- "queryFormulas": []
- },
- "clickhouse_sql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "id": "d59f9848-99b6-4d7b-9c3f-ab4752623cff",
- "promql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "queryType": "builder"
- },
- "softMax": null,
- "softMin": null,
- "thresholds": [],
- "timePreferance": "GLOBAL_TIME",
- "title": "Usage by Platform",
- "yAxisUnit": "none"
- },
- {
- "description": "",
- "fillSpans": false,
- "id": "ec9a5671-4a0c-4172-a383-82f37ab682f7",
- "isStacked": false,
- "nullZeroValues": "zero",
- "opacity": "1",
- "panelTypes": "table",
- "query": {
- "builder": {
- "queryData": [
- {
- "aggregateAttribute": {
- "dataType": "float64",
- "id": "requestDuration--float64--tag--false",
- "isColumn": false,
- "isJSON": false,
- "key": "requestDuration",
- "type": "tag"
- },
- "aggregateOperator": "count",
- "dataSource": "logs",
- "disabled": false,
- "expression": "A",
- "filters": {
- "items": [
- {
- "id": "5a2b96e0",
- "key": {
- "dataType": "string",
- "id": "job--string--resource--false",
- "isColumn": false,
- "isJSON": false,
- "key": "job",
- "type": "resource"
- },
- "op": "=",
- "value": "doku"
- }
- ],
- "op": "AND"
- },
- "groupBy": [
- {
- "dataType": "string",
- "id": "generation--string--tag--false",
- "isColumn": false,
- "isJSON": false,
- "key": "generation",
- "type": "tag"
- }
- ],
- "having": [],
- "legend": "",
- "limit": null,
- "orderBy": [
- {
- "columnName": "#SIGNOZ_VALUE",
- "order": "desc"
- }
- ],
- "queryName": "A",
- "reduceTo": "sum",
- "stepInterval": 60
- }
- ],
- "queryFormulas": []
- },
- "clickhouse_sql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "id": "db77fe7d-8982-4f4a-ab90-b139151ae121",
- "promql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "queryType": "builder"
- },
- "softMax": null,
- "softMin": null,
- "thresholds": [],
- "timePreferance": "GLOBAL_TIME",
- "title": "Usage by Category",
- "yAxisUnit": "none"
- },
- {
- "description": "",
- "fillSpans": false,
- "id": "5705486f-dfab-4428-96ce-97d5ccfc0620",
- "isStacked": false,
- "nullZeroValues": "zero",
- "opacity": "1",
- "panelTypes": "graph",
- "query": {
- "builder": {
- "queryData": [
- {
- "aggregateAttribute": {
- "dataType": "float64",
- "id": "usageCost--float64--tag--false",
- "isColumn": false,
- "isJSON": false,
- "key": "usageCost",
- "type": "tag"
- },
- "aggregateOperator": "avg",
- "dataSource": "logs",
- "disabled": false,
- "expression": "A",
- "filters": {
- "items": [
- {
- "id": "67d33dbc",
- "key": {
- "dataType": "string",
- "id": "job--string--resource--false",
- "isColumn": false,
- "isJSON": false,
- "key": "job",
- "type": "resource"
- },
- "op": "=",
- "value": "doku"
- }
- ],
- "op": "AND"
- },
- "groupBy": [
- {
- "dataType": "string",
- "id": "model--string--tag--false",
- "isColumn": false,
- "isJSON": false,
- "key": "model",
- "type": "tag"
- }
- ],
- "having": [],
- "legend": "{{model}}",
- "limit": null,
- "orderBy": [],
- "queryName": "A",
- "reduceTo": "sum",
- "stepInterval": 60
- }
- ],
- "queryFormulas": []
- },
- "clickhouse_sql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "id": "9d51906e-c800-4063-b355-333f882cfa74",
- "promql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "queryType": "builder"
- },
- "softMax": null,
- "softMin": null,
- "thresholds": [],
- "timePreferance": "GLOBAL_TIME",
- "title": "Avg Cost by Model",
- "yAxisUnit": "none"
- },
- {
- "description": "",
- "fillSpans": false,
- "id": "4d33e5a0-2e34-4626-9dff-f795cd8e62ee",
- "isStacked": false,
- "nullZeroValues": "zero",
- "opacity": "1",
- "panelTypes": "graph",
- "query": {
- "builder": {
- "queryData": [
- {
- "aggregateAttribute": {
- "dataType": "float64",
- "id": "usageCost--float64--tag--false",
- "isColumn": false,
- "isJSON": false,
- "key": "usageCost",
- "type": "tag"
- },
- "aggregateOperator": "avg",
- "dataSource": "logs",
- "disabled": false,
- "expression": "A",
- "filters": {
- "items": [
- {
- "id": "b906c8d2",
- "key": {
- "dataType": "string",
- "id": "job--string--resource--false",
- "isColumn": false,
- "isJSON": false,
- "key": "job",
- "type": "resource"
- },
- "op": "=",
- "value": "doku"
- }
- ],
- "op": "AND"
- },
- "groupBy": [
- {
- "dataType": "string",
- "id": "generation--string--tag--false",
- "isColumn": false,
- "isJSON": false,
- "key": "generation",
- "type": "tag"
- }
- ],
- "having": [],
- "legend": "{{generation}}",
- "limit": null,
- "orderBy": [],
- "queryName": "A",
- "reduceTo": "sum",
- "stepInterval": 60
- }
- ],
- "queryFormulas": []
- },
- "clickhouse_sql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "id": "a6678a16-3579-4037-8644-aa29c102dc41",
- "promql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "queryType": "builder"
- },
- "softMax": null,
- "softMin": null,
- "thresholds": [],
- "timePreferance": "GLOBAL_TIME",
- "title": "Avg Cost by Category",
- "yAxisUnit": "none"
- },
- {
- "description": "",
- "fillSpans": false,
- "id": "af5f5471-e523-49e5-8de3-17a8c43fd115",
- "isStacked": false,
- "nullZeroValues": "zero",
- "opacity": "1",
- "panelTypes": "graph",
- "query": {
- "builder": {
- "queryData": [
- {
- "aggregateAttribute": {
- "dataType": "float64",
- "id": "usageCost--float64--tag--false",
- "isColumn": false,
- "isJSON": false,
- "key": "usageCost",
- "type": "tag"
- },
- "aggregateOperator": "avg",
- "dataSource": "logs",
- "disabled": false,
- "expression": "A",
- "filters": {
- "items": [
- {
- "id": "11c2ee90",
- "key": {
- "dataType": "string",
- "id": "job--string--resource--false",
- "isColumn": false,
- "isJSON": false,
- "key": "job",
- "type": "resource"
- },
- "op": "=",
- "value": "doku"
- }
- ],
- "op": "AND"
- },
- "groupBy": [
- {
- "dataType": "string",
- "id": "platform--string--tag--false",
- "isColumn": false,
- "isJSON": false,
- "key": "platform",
- "type": "tag"
- }
- ],
- "having": [],
- "legend": "{{platform}}",
- "limit": null,
- "orderBy": [],
- "queryName": "A",
- "reduceTo": "sum",
- "stepInterval": 60
- }
- ],
- "queryFormulas": []
- },
- "clickhouse_sql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "id": "490a0010-6497-4caf-a19f-06532673278c",
- "promql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "queryType": "builder"
- },
- "softMax": null,
- "softMin": null,
- "thresholds": [],
- "timePreferance": "GLOBAL_TIME",
- "title": "Avg Cost by Platform",
- "yAxisUnit": "none"
- },
- {
- "description": "",
- "fillSpans": false,
- "id": "4f33601c-9707-4b52-8194-e6671c52666e",
- "isStacked": false,
- "nullZeroValues": "zero",
- "opacity": "1",
- "panelTypes": "graph",
- "query": {
- "builder": {
- "queryData": [
- {
- "aggregateAttribute": {
- "dataType": "float64",
- "id": "usageCost--float64--tag--false",
- "isColumn": false,
- "isJSON": false,
- "key": "usageCost",
- "type": "tag"
- },
- "aggregateOperator": "avg",
- "dataSource": "logs",
- "disabled": false,
- "expression": "A",
- "filters": {
- "items": [
- {
- "id": "e2a969e5",
- "key": {
- "dataType": "string",
- "id": "job--string--resource--false",
- "isColumn": false,
- "isJSON": false,
- "key": "job",
- "type": "resource"
- },
- "op": "=",
- "value": "doku"
- }
- ],
- "op": "AND"
- },
- "groupBy": [
- {
- "dataType": "string",
- "id": "environment--string--resource--false",
- "isColumn": false,
- "isJSON": false,
- "key": "environment",
- "type": "resource"
- }
- ],
- "having": [],
- "legend": "{{environment}}",
- "limit": null,
- "orderBy": [],
- "queryName": "A",
- "reduceTo": "sum",
- "stepInterval": 60
- }
- ],
- "queryFormulas": []
- },
- "clickhouse_sql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "id": "8bb7bebd-1472-4f1b-8ab8-9c649581bac0",
- "promql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "queryType": "builder"
- },
- "softMax": null,
- "softMin": null,
- "thresholds": [],
- "timePreferance": "GLOBAL_TIME",
- "title": "Avg Cost by Environment",
- "yAxisUnit": "none"
- },
- {
- "description": "",
- "fillSpans": false,
- "id": "11cba8dc-b2de-4eb6-a546-8a3cbe43cba2",
- "isStacked": false,
- "nullZeroValues": "zero",
- "opacity": "1",
- "panelTypes": "graph",
- "query": {
- "builder": {
- "queryData": [
- {
- "aggregateAttribute": {
- "dataType": "float64",
- "id": "usageCost--float64--tag--false",
- "isColumn": false,
- "isJSON": false,
- "key": "usageCost",
- "type": "tag"
- },
- "aggregateOperator": "avg",
- "dataSource": "logs",
- "disabled": false,
- "expression": "A",
- "filters": {
- "items": [
- {
- "id": "e2a969e5",
- "key": {
- "dataType": "string",
- "id": "job--string--resource--false",
- "isColumn": false,
- "isJSON": false,
- "key": "job",
- "type": "resource"
- },
- "op": "=",
- "value": "doku"
- }
- ],
- "op": "AND"
- },
- "groupBy": [
- {
- "dataType": "string",
- "id": "applicationName--string--tag--false",
- "isColumn": false,
- "isJSON": false,
- "key": "applicationName",
- "type": "tag"
- }
- ],
- "having": [],
- "legend": "{{applicationName}}",
- "limit": null,
- "orderBy": [],
- "queryName": "A",
- "reduceTo": "sum",
- "stepInterval": 60
- }
- ],
- "queryFormulas": []
- },
- "clickhouse_sql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "id": "9c3b02ce-4ff7-4992-a323-0e492f85cb5b",
- "promql": [
- {
- "disabled": false,
- "legend": "",
- "name": "A",
- "query": ""
- }
- ],
- "queryType": "builder"
- },
- "softMax": null,
- "softMin": null,
- "thresholds": [],
- "timePreferance": "GLOBAL_TIME",
- "title": "Avg Cost by Application",
- "yAxisUnit": "none"
- }
- ]
- }
- ```
-</Accordion>
-
----
+Alternatively, you can configure the OTLP endpoint by setting the `OTEL_EXPORTER_OTLP_ENDPOINT` and the OTLP headers by setting the Appli`OTEL_EXPORTER_OTLP_HEADERS` environmentcation variable as recommended in the OpenTelemetry documentation.
-<CardGroup cols={2}>
-<Card title="Integrations" href="/latest/integrations/introduction" icon='circle-nodes'>
-Integrate your LLM Provider with Doku
-</Card>
-<Card title="API Reference" href="/latest/api-reference/introduction" icon='code'>
-OpenAPI specification for API Endpoints in Doku
-</Card>
-</CardGroup>
\ No newline at end of file
+Refer to the OpenLIT [Python SDK repository](https://github.com/openlit/openlit/tree/main/sdk/python) for more advanced configurations and use cases.
diff --git a/docs/latest/installation.mdx b/docs/latest/installation.mdx
index 97570625..9671d24d 100644
--- a/docs/latest/installation.mdx
+++ b/docs/latest/installation.mdx
@@ -27,17 +27,17 @@ OpenLIT flexibly adapts to your preferred environment. Select a deployment metho
## Kubernetes
-Deploy OpenLIT on your Kubernetes cluster using the [OpenLIT Helm chart](https://github.com/dokulabs/helm/tree/main/charts/doku) for a reliable and scalable solution.
+Deploy OpenLIT on your Kubernetes cluster using the [OpenLIT Helm chart](https://github.com/openlit/helm/tree/main/charts/openlit) for a reliable and scalable solution.
<Steps>
<Step title="Helm Repo Setup">
```shell shell
- helm repo add dokulabs https://dokulabs.github.io/helm/
+ helm repo add openlit https://openlit.github.io/helm/
helm repo update
```
</Step>
<Step title="Installing the Helm Chart">
```shell shell
- helm install doku dokulabs/doku --version="0.1.3"
+ helm install openlit openlit/openlit --version="1.0.0"
```
</Step>
</Steps>
@@ -46,63 +46,13 @@ Deploy OpenLIT on your Kubernetes cluster using the [OpenLIT Helm chart](https:/
For a quick and straightforward setup, Docker Compose can be used to deploy OpenLIT.
<Steps>
- <Step title="Create `docker-compose.yml`">
- ```yaml
- version: '3.8'
-
- services:
- clickhouse:
- image: clickhouse/clickhouse-server:24.2.2
- container_name: clickhouse
- environment:
- CLICKHOUSE_PASSWORD: ${DOKU_DB_PASSWORD:-OPENLIT}
- CLICKHOUSE_USER: ${DOKU_DB_USER:-default}
- volumes:
- - clickhouse-data:/var/lib/clickhouse
- ports:
- - "9000:9000"
- - "8123:8123"
- restart: always
-
- doku-ingester:
- image: ghcr.io/dokulabs/doku-ingester:0.1.3
- container_name: doku-ingester
- environment:
- DOKU_DB_HOST: clickhouse
- DOKU_DB_PORT: 9000
- DOKU_DB_NAME: ${DOKU_DB_NAME:-default}
- DOKU_DB_USER: ${DOKU_DB_USER:-default}
- DOKU_DB_PASSWORD: ${DOKU_DB_PASSWORD:-OPENLIT}
- ports:
- - "9044:9044"
- depends_on:
- - clickhouse
- restart: always
-
- doku-client:
- image: ghcr.io/dokulabs/doku-client:0.1.3
- container_name: doku-client
- environment:
- INIT_DB_HOST: clickhouse
- INIT_DB_PORT: 8123
- INIT_DB_DATABASE: ${DOKU_DB_NAME:-default}
- INIT_DB_USERNAME: ${DOKU_DB_USER:-default}
- INIT_DB_PASSWORD: ${DOKU_DB_PASSWORD:-DOKU}
- SQLITE_DATABASE_URL: file:/app/client/data/data.db
- ports:
- - "3000:3000"
- depends_on:
- - clickhouse
- volumes:
- - doku-client-data:/app/client/data
- restart: always
-
- volumes:
- clickhouse-data:
- doku-client-data:
+ <Step title="Git Clone OpenLIT Repository">
+ ```shell
+ git clone [email protected]:openlit/openlit.git
```
</Step>
<Step title="Start Docker Compose">
+ From the root directory of the OpenLIT Repo, Run the below command
```shell
docker-compose up -d
```
diff --git a/docs/latest/integrations/anthropic.mdx b/docs/latest/integrations/anthropic.mdx
new file mode 100644
index 00000000..e6aba9a1
--- /dev/null
+++ b/docs/latest/integrations/anthropic.mdx
@@ -0,0 +1,48 @@
+---
+title: 'Monitor Anthropic using OpenTelemetry'
+sidebarTitle: 'Anthropic'
+---
+
+OpenLIT SDKs provide OpenTelemetry Auto-Instrumentation for monitoring LLM Application using Anthropic which includes performance, token and cost usage and user interactions.
+
+The integration is compatible with
+- Anthropic Python SDK client `>= 0.21.0`
+
+## Get Started
+
+<Steps>
+ <Step title="Install the OpenLIT Python SDK using pip">
+ ```shell
+ pip install openlit
+ ```
+ </Step>
+ <Step title="Add the following two lines to your application code:">
+ Integrating the OpenLIT into LLM applications is straightforward. Start monitoring for your LLM Application with just **one line of code**:
+
+ ```python
+ import openlit
+
+ openlit.init(otlp_endpoint="otlp_backend_endpoint", otlp_headers="otlp_backend_token")
+ ```
+
+ Alternatively, you can configure the OTLP endpoint by setting the `OTEL_EXPORTER_OTLP_ENDPOINT` and the OTLP headers by setting the Appli`OTEL_EXPORTER_OTLP_HEADERS` environmentcation variable as recommended in the OpenTelemetry documentation.
+
+ If your aim is primarily to test or develop without sending telemetry data to an external backend, you can initialize OpenLIT without any parameters. This approach directs all telemetry output to your console, enabling quick diagnostics and local debugging:
+
+ ```python
+ import openlit
+
+ openlit.init()
+ ```
+
+ Refer to the OpenLIT [Python SDK repository](https://github.com/openlit/openlit/tree/main/sdk/python) for more advanced configurations and use cases.
+ </Step>
+</Steps>
+
+---
+
+<CardGroup cols={2}>
+<Card title="Connections" href="/latest/connections/intro" icon='link'>
+Connect to your existing Observablity Platform
+</Card>
+</CardGroup>
\ No newline at end of file
diff --git a/docs/latest/integrations/anthropic/examples/messages.mdx b/docs/latest/integrations/anthropic/examples/messages.mdx
deleted file mode 100644
index 1bf4d688..00000000
--- a/docs/latest/integrations/anthropic/examples/messages.mdx
+++ /dev/null
@@ -1,148 +0,0 @@
----
-title: 'Messages'
-description: 'Monitor Anthropic `messages` API usage for cost, performance & user interactions'
----
-
-<Tabs>
- <Tab title="Python">
-
- ### Synchronous Usage
- <CodeGroup>
- ```python default
- from anthropic import Anthropic
- import dokumetry
-
- client = Anthropic(
- api_key="YOUR_ANTHROPIC_API_KEY",
- )
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all Anthropic calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- message = client.messages.create(
- messages=[{ "role": "user", "content": "Hello, Explain LLM Monitoring in one sentence"}],
- model="claude-3-opus-20240229",
- max_tokens=1024
- )
- print(message.content)
- ```
- ```python streaming
- from anthropic import Anthropic
- import dokumetry
-
- client = Anthropic(
- api_key="YOUR_ANTHROPIC_API_KEY",
- )
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all Anthropic calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- stream = client.messages.create(
- messages=[{"role": "user", "content": "Hello, Explain LLM Monitoring in one sentence"}],
- max_tokens=1024,
- model="claude-3-opus-20240229",
- stream=True,
- )
- for event in stream:
- print(event.type)
- ```
- </CodeGroup>
-
- ### Asynchronous usage
- <CodeGroup>
- ```python default
- import asyncio
- from anthropic import AsyncAnthropic
- import dokumetry
-
- client = AsyncAnthropic(
- api_key="YOUR_ANTHROPIC_API_KEY",
- )
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all Anthropic calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- async def main() -> None:
- message = await client.messages.create(
- messages=[{"role": "user","content": "Hello, How to monitor LLM Applications?"}],
- model="claude-3-opus-20240229",
- )
- print(message.content)
-
- asyncio.run(main())
- ```
-
- ```python streaming
- import asyncio
- from anthropic import AsyncAnthropic
- import dokumetry
-
- client = AsyncAnthropic(
- api_key="YOUR_ANTHROPIC_API_KEY",
- )
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all Anthropic calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- async def main() -> None:
- stream = await client.messages.create(
- messages=[{"role": "user","content": "What metrics to monitor for my LLM Applications?"}],
- model="claude-3-opus-20240229",
- stream=True,
- )
- async for event in stream:
- print(event.type)
-
- asyncio.run(main())
- ```
- </CodeGroup>
- </Tab>
- <Tab title="Javascript">
- <CodeGroup>
- ```javascript default
- import Anthropic from '@anthropic-ai/sdk';
- import DokuMetry from 'dokumetry';
-
- const anthropic = new Anthropic({
- apiKey: 'my_api_key',
- });
-
- // Pass the above `anthropic` object along with your Doku Ingester URL and API key and this will make sure that all Anthropic calls are automatically tracked.
- DokuMetry.init({llm: anthropic, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- async function main() {
- const message = await anthropic.messages.create({
- messages: [{ role: 'user', content: 'How to monitor my LLM Applications?' }],
- model: 'claude-3-opus-20240229',
- });
-
- console.log(message.content);
- }
-
- main();
- ```
-
- ```javascript streaming
- import Anthropic from '@anthropic-ai/sdk';
- import DokuMetry from 'dokumetry';
-
- const anthropic = new Anthropic({
- apiKey: 'my_api_key',
- });
-
- // Pass the above `anthropic` object along with your Doku Ingester URL and API key and this will make sure that all Anthropic calls are automatically tracked.
- DokuMetry.init({llm: anthropic, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- const stream = await anthropic.messages.create({
- messages: [{ role: 'user', content: 'How to setup LLM Obserability?' }],
- model: 'claude-3-opus-20240229',
- stream: true,
- });
- for await (const messageStreamEvent of stream) {
- console.log(messageStreamEvent.type);
- }
- ```
- </CodeGroup>
- </Tab>
-</Tabs>
-
diff --git a/docs/latest/integrations/anthropic/introduction.mdx b/docs/latest/integrations/anthropic/introduction.mdx
deleted file mode 100644
index 894c52ca..00000000
--- a/docs/latest/integrations/anthropic/introduction.mdx
+++ /dev/null
@@ -1,93 +0,0 @@
----
-title: 'Anthropic Integration'
-sidebarTitle: 'Get Started'
----
-
-DokuMetry SDKs (`dokumetry`) empowers you to effortlessly track and monitor Anthropic usage data and metrics from your Python/NodeJS code.
-
-## Get Started
-
-The integration is compatible with
-- Anthropic Python SDK client `>=0.19.0`
-- Anthropic JS/TS SDK client `>=0.9.0`
-
-<Tabs>
- <Tab title="Python">
- ```shell
- pip install dokumetry==0.1.1
- ```
-
- ```python
- from anthropic import Anthropic
- import dokumetry
-
- anthropic = Anthropic(
- api_key="anthropic_api_key",
- )
-
- dokumetry.init(llm = anthropic, doku_url = "YOUR_DOKU_INGESTER_URL", api_key = "YOUR_DOKU_TOKEN")
- ```
- </Tab>
- <Tab title="Javascript">
- ```shell
- npm install [email protected]
- ```
-
- ```javascript
- import Anthropic from '@anthropic-ai/sdk';
- import DokuMetry from 'dokumetry';
-
- const anthropic = new Anthropic({
- apiKey: 'anthropic_api_key',
- });
-
- DokuMetry.init({llm: anthropic, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
- ```
- </Tab>
-</Tabs>
-
-## Supported Endpoints
-
-The following Anthropic Endpoints are supported for monitoring with DokuMetry
-
-- [messages](/latest/integrations/anthropic/examples/messages)
-
-## Parameters
-<Tabs>
- <Tab title="Python">
- | Parameter | Description | Required |
- |-------------------|-----------------------------------------------------------|---------------|
- | llm | Anthropic Object to track | Yes |
- | doku_url | URL of your Doku Ingester | Yes |
- | api_key | Your Doku API key | Yes |
- | environment | Custom environment tag to include in your metrics | Optional |
- | application_name | Custom application name tag for your metrics | Optional |
- | skip_resp | Skip response from the Doku Ingester for faster execution | Optional |
- </Tab>
- <Tab title="NodeJS">
- | Parameter | Description | Required |
- |-------------------|-----------------------------------------------------------|---------------|
- | llm | Anthropic Object to track | Yes |
- | dokuUrl | URL of your Doku Ingester | Yes |
- | apiKey | Your Doku API key | Yes |
- | environment | Custom environment tag to include in your metrics | Optional |
- | applicationName | Custom application name tag for your metrics | Optional |
- | skipResp | Skip response from the Doku Ingester for faster execution | Optional |
- </Tab>
-</Tabs>
-
-## Advanced Usage
-When using DokuMetry in Production environments, It is recommened to set Skip response parameter to `true` for faster porcessing.
-
-To filter your LLM Usage according application or the environment, set the Application name and Environment paramaters with the actual values.
-
----
-
-<CardGroup cols={2}>
-<Card title="Connections" href="/latest/connections/intro" icon='link'>
-Connect to your existing Observablity Platform
-</Card>
-<Card title="API Reference" href="/latest/api-reference/introduction" icon='code'>
-OpenAPI specification for API Endpoints in Doku
-</Card>
-</CardGroup>
\ No newline at end of file
diff --git a/docs/latest/integrations/azure-openai.mdx b/docs/latest/integrations/azure-openai.mdx
new file mode 100644
index 00000000..f6deed04
--- /dev/null
+++ b/docs/latest/integrations/azure-openai.mdx
@@ -0,0 +1,48 @@
+---
+title: 'Monitor Azure OpenAI using OpenTelemetry'
+sidebarTitle: 'Azure OpenAI'
+---
+
+OpenLIT SDKs provide OpenTelemetry Auto-Instrumentation for monitoring LLM Application using Azure OpenAI which includes performance, token and cost usage and user interactions.
+
+The integration is compatible with
+- OpenAI Python SDK client `>=1.13.0`
+
+## Get Started
+
+<Steps>
+ <Step title="Install the OpenLIT Python SDK using pip">
+ ```shell
+ pip install openlit
+ ```
+ </Step>
+ <Step title="Add the following two lines to your application code:">
+ Integrating the OpenLIT into LLM applications is straightforward. Start monitoring for your LLM Application with just **one line of code**:
+
+ ```python
+ import openlit
+
+ openlit.init(otlp_endpoint="otlp_backend_endpoint", otlp_headers="otlp_backend_token")
+ ```
+
+ Alternatively, you can configure the OTLP endpoint by setting the `OTEL_EXPORTER_OTLP_ENDPOINT` and the OTLP headers by setting the Appli`OTEL_EXPORTER_OTLP_HEADERS` environmentcation variable as recommended in the OpenTelemetry documentation.
+
+ If your aim is primarily to test or develop without sending telemetry data to an external backend, you can initialize OpenLIT without any parameters. This approach directs all telemetry output to your console, enabling quick diagnostics and local debugging:
+
+ ```python
+ import openlit
+
+ openlit.init()
+ ```
+
+ Refer to the OpenLIT [Python SDK repository](https://github.com/openlit/openlit/tree/main/sdk/python) for more advanced configurations and use cases.
+ </Step>
+</Steps>
+
+---
+
+<CardGroup cols={2}>
+<Card title="Connections" href="/latest/connections/intro" icon='link'>
+Connect to your existing Observablity Platform
+</Card>
+</CardGroup>
\ No newline at end of file
diff --git a/docs/latest/integrations/azure-openai/examples/chat.mdx b/docs/latest/integrations/azure-openai/examples/chat.mdx
deleted file mode 100644
index 8edbec85..00000000
--- a/docs/latest/integrations/azure-openai/examples/chat.mdx
+++ /dev/null
@@ -1,437 +0,0 @@
----
-title: 'Chat Completions'
-description: 'Monitor Azure OpenAI `chat.completions` API usage for cost, performance & user interactions'
----
-
-<Tabs>
- <Tab title="Python">
-
- ### Synchronous Usage
- <CodeGroup>
- ```python Default
- from openai import AzureOpenAI
- import dokumetry
-
- client = AzureOpenAI(
- api_key = "YOUR_AZURE_OPENAI_API_KEY",
- api_version = "2024-02-01",
- azure_endpoint = "YOUR_AZURE_OPENAI_API_ENDPOINT"
- )
-
- azure_model_deployment = "YOUR_AZURE_OPENAI_DEPLOYMENT"
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- completion = client.chat.completions.create(
- model=azure_model_deployment,
- messages=[
- {"role": "system", "content": "You are a expert at monitoring LLM Applications"},
- {"role": "user", "content": "Hello! How do I monitor my OpenAI based LLM Applications?"}
- ]
- )
-
- print(completion.choices[0].message)
- ```
-
- ```python Streaming
- from openai import AzureOpenAI
- import dokumetry
-
- client = AzureOpenAI(
- api_key = "YOUR_AZURE_OPENAI_API_KEY",
- api_version = "2024-02-01",
- azure_endpoint = "YOUR_AZURE_OPENAI_API_ENDPOINT"
- )
-
- azure_model_deployment = "YOUR_AZURE_OPENAI_DEPLOYMENT"
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- completion = client.chat.completions.create(
- model=azure_model_deployment,
- messages=[
- {"role": "system", "content": "You are a expert at monitoring LLM Applications"},
- {"role": "user", "content": "Hello! How do I monitor my OpenAI based LLM Applications?"}
- ],
- stream=True
- )
-
- for chunk in completion:
- print(chunk.choices[0].delta)
- ```
-
- ```python Functions
- from openai import AzureOpenAI
- import dokumetry
-
- client = AzureOpenAI(
- api_key = "YOUR_AZURE_OPENAI_API_KEY",
- api_version = "2024-02-01",
- azure_endpoint = "YOUR_AZURE_OPENAI_API_ENDPOINT"
- )
-
- azure_model_deployment = "YOUR_AZURE_OPENAI_DEPLOYMENT"
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- tools = [
- {
- "type": "function",
- "function": {
- "name": "get_current_weather",
- "description": "Get the current weather in a given location",
- "parameters": {
- "type": "object",
- "properties": {
- "location": {
- "type": "string",
- "description": "The city and state, e.g. San Francisco, CA",
- },
- "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
- },
- "required": ["location"],
- },
- }
- }
- ]
- messages = [{"role": "user", "content": "What's the weather like in Boston today?"}]
- completion = client.chat.completions.create(
- model=azure_model_deployment,
- messages=messages,
- tools=tools,
- tool_choice="auto"
- )
-
- print(completion)
- ```
-
- ```python LogProbs
- from openai import AzureOpenAI
- import dokumetry
-
- client = AzureOpenAI(
- api_key = "YOUR_AZURE_OPENAI_API_KEY",
- api_version = "2024-02-01",
- azure_endpoint = "YOUR_AZURE_OPENAI_API_ENDPOINT"
- )
-
- azure_model_deployment = "YOUR_AZURE_OPENAI_DEPLOYMENT"
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- completion = client.chat.completions.create(
- model=azure_model_deployment,
- messages=[
- {"role": "system", "content": "You are a expert at monitoring LLM Applications"},
- {"role": "user", "content": "Hello! How do I monitor my OpenAI based LLM Applications?"}
- ],
- logprobs=True,
- top_logprobs=2
- )
-
- print(completion.choices[0].message)
- print(completion.choices[0].logprobs)
- ```
- </CodeGroup>
-
- ### Asynchronous Usage
-
- <CodeGroup>
- ```python Default
- import asyncio
- from openai import AsyncAzureOpenAI
- import dokumetry
-
- client = AsyncAzureOpenAI(
- api_key = "YOUR_AZURE_OPENAI_API_KEY",
- api_version = "2024-02-01",
- azure_endpoint = "YOUR_AZURE_OPENAI_API_ENDPOINT"
- )
-
- azure_model_deployment = "YOUR_AZURE_OPENAI_DEPLOYMENT"
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- async def main() -> None:
- chat_completion = await client.chat.completions.create(
- messages=[
- {"role": "system", "content": "You are a expert at monitoring LLM Applications"},
- {"role": "user", "content": "Hello! How do I monitor my OpenAI based LLM Applications?"}
- ],
- model=azure_model_deployment,
- )
-
- asyncio.run(main())
- ```
-
- ```python Streaming
- import asyncio
- from openai import AsyncAzureOpenAI
- import dokumetry
-
- client = AsyncAzureOpenAI(
- api_key = "YOUR_AZURE_OPENAI_API_KEY",
- api_version = "2024-02-01",
- azure_endpoint = "YOUR_AZURE_OPENAI_API_ENDPOINT"
- )
-
- azure_model_deployment = "YOUR_AZURE_OPENAI_DEPLOYMENT"
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- async def main():
- stream = await client.chat.completions.create(
- model=azure_model_deployment,
- messages=[
- {"role": "system", "content": "You are a expert at monitoring LLM Applications"},
- {"role": "user", "content": "Hello! How do I monitor my OpenAI based LLM Applications?"}
- ],
- stream=True,
- )
- async for chunk in stream:
- print(chunk.choices[0].delta.content or "", end="")
-
-
- asyncio.run(main())
- ```
-
- ```python Functions
- import asyncio
- from openai import AsyncAzureOpenAI
- import dokumetry
-
- client = AsyncAzureOpenAI(
- api_key = "YOUR_AZURE_OPENAI_API_KEY",
- api_version = "2024-02-01",
- azure_endpoint = "YOUR_AZURE_OPENAI_API_ENDPOINT"
- )
-
- azure_model_deployment = "YOUR_AZURE_OPENAI_DEPLOYMENT"
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- tools = [
- {
- "type": "function",
- "function": {
- "name": "get_current_weather",
- "description": "Get the current weather in a given location",
- "parameters": {
- "type": "object",
- "properties": {
- "location": {
- "type": "string",
- "description": "The city and state, e.g. San Francisco, CA",
- },
- "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
- },
- "required": ["location"],
- },
- }
- }
- ]
- messages = [{"role": "user", "content": "What's the weather like in Boston today?"}]
-
- async def main() -> None:
- completion = await client.chat.completions.create(
- model=azure_model_deployment,
- messages=messages,
- tools=tools,
- tool_choice="auto"
- )
-
- asyncio.run(main())
- ```
-
- ```python LogProbs
- import asyncio
- from openai import AsyncAzureOpenAI
- import dokumetry
-
- client = AsyncAzureOpenAI(
- api_key = "YOUR_AZURE_OPENAI_API_KEY",
- api_version = "2024-02-01",
- azure_endpoint = "YOUR_AZURE_OPENAI_API_ENDPOINT"
- )
-
- azure_model_deployment = "YOUR_AZURE_OPENAI_DEPLOYMENT"
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- async def main() -> None:
- completion = await client.chat.completions.create(
- model=azure_model_deployment,
- messages=[
- {"role": "system", "content": "You are a expert at monitoring LLM Applications"},
- {"role": "user", "content": "Hello! How do I monitor my OpenAI based LLM Applications?"}
- ],
- logprobs=True,
- top_logprobs=2
- )
-
- asyncio.run(main())
- ```
- </CodeGroup>
- </Tab>
- <Tab title="NodeJS">
- <CodeGroup>
- ```javascript Default
- import OpenAI from "openai";
- import DokuMetry from 'dokumetry';
-
- const client = new OpenAI({
- apiKey: "YOUR_AZURE_OPENAI_API_KEY",
- baseURL: `https://YOUR_AZURE_OPENAI_RESOURCE.openai.azure.com/openai/deployments/YOUR_AZURE_OPENAI_DEPLOYMENT`,
- defaultQuery: { 'api-version': "2024-02-01" },
- defaultHeaders: { 'api-key': "YOUR_AZURE_OPENAI_API_KEY" },
- });
-
- const azureModelDeployment = 'YOUR_AZURE_OPENAI_DEPLOYMENT';
-
- // Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- DokuMetry.init({llm: client, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- async function main() {
- const completion = await client.chat.completions.create({
- messages: [
- {"role": "system", "content": "You are a expert at monitoring LLM Applications"},
- {"role": "user", "content": "Hello! How do I monitor my OpenAI based LLM Applications?"}
- ],
- model: azureModelDeployment,
- });
-
- console.log(completion.choices[0]);
- }
-
- main();
- ```
-
- ```javascript Streaming
- import OpenAI from "openai";
- import DokuMetry from 'dokumetry';
-
- const client = new OpenAI({
- apiKey: "YOUR_AZURE_OPENAI_API_KEY",
- baseURL: `https://YOUR_AZURE_OPENAI_RESOURCE.openai.azure.com/openai/deployments/YOUR_AZURE_OPENAI_DEPLOYMENT`,
- defaultQuery: { 'api-version': "2024-02-01" },
- defaultHeaders: { 'api-key': "YOUR_AZURE_OPENAI_API_KEY" },
- });
-
- const azureModelDeployment = 'YOUR_AZURE_OPENAI_DEPLOYMENT';
-
- // Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- DokuMetry.init({llm: client, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- async function main() {
- const completion = await client.chat.completions.create({
- model: azureModelDeployment,
- messages: [
- {"role": "system", "content": "You are a expert at monitoring LLM Applications"},
- {"role": "user", "content": "Hello! How do I monitor my OpenAI based LLM Applications?"}
- ],
- stream: true,
- });
-
- for await (const chunk of completion) {
- console.log(chunk.choices[0].delta.content);
- }
- }
-
- main();
- ```
-
- ```javascript Functions
- import OpenAI from "openai";
- import DokuMetry from 'dokumetry';
-
- const client = new OpenAI({
- apiKey: "YOUR_AZURE_OPENAI_API_KEY",
- baseURL: `https://YOUR_AZURE_OPENAI_RESOURCE.openai.azure.com/openai/deployments/YOUR_AZURE_OPENAI_DEPLOYMENT`,
- defaultQuery: { 'api-version': "2024-02-01" },
- defaultHeaders: { 'api-key': "YOUR_AZURE_OPENAI_API_KEY" },
- });
-
- const azureModelDeployment = 'YOUR_AZURE_OPENAI_DEPLOYMENT';
-
- // Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- DokuMetry.init({llm: client, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- async function main() {
- const messages = [{"role": "user", "content": "What's the weather like in Boston today?"}];
- const tools = [
- {
- "type": "function",
- "function": {
- "name": "get_current_weather",
- "description": "Get the current weather in a given location",
- "parameters": {
- "type": "object",
- "properties": {
- "location": {
- "type": "string",
- "description": "The city and state, e.g. San Francisco, CA",
- },
- "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
- },
- "required": ["location"],
- },
- }
- }
- ];
-
- const response = await client.chat.completions.create({
- model: azureModelDeployment,
- messages: messages,
- tools: tools,
- tool_choice: "auto",
- });
-
- console.log(response);
- }
-
- main();
- ```
-
- ```javascript LogProbs
- import OpenAI from "openai";
- import DokuMetry from 'dokumetry';
-
- const client = new OpenAI({
- apiKey: "YOUR_AZURE_OPENAI_API_KEY",
- baseURL: `https://YOUR_AZURE_OPENAI_RESOURCE.openai.azure.com/openai/deployments/YOUR_AZURE_OPENAI_DEPLOYMENT`,
- defaultQuery: { 'api-version': "2024-02-01" },
- defaultHeaders: { 'api-key': "YOUR_AZURE_OPENAI_API_KEY" },
- });
-
- const azureModelDeployment = 'YOUR_AZURE_OPENAI_DEPLOYMENT';
-
- // Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- DokuMetry.init({llm: client, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- async function main() {
- const completion = await client.chat.completions.create({
- messages: [
- {"role": "system", "content": "You are a expert at monitoring LLM Applications"},
- {"role": "user", "content": "Hello! How do I monitor my Azure OpenAI based LLM Applications?"}
- ],
- model: azureModelDeployment,
- logprobs: true,
- top_logprobs: 2,
- });
-
- console.log(completion.choices[0]);
- }
-
- main();
- ```
- </CodeGroup>
- </Tab>
-</Tabs>
\ No newline at end of file
diff --git a/docs/latest/integrations/azure-openai/examples/completions.mdx b/docs/latest/integrations/azure-openai/examples/completions.mdx
deleted file mode 100644
index 313a3a23..00000000
--- a/docs/latest/integrations/azure-openai/examples/completions.mdx
+++ /dev/null
@@ -1,118 +0,0 @@
----
-title: 'Completions'
-description: 'Monitor Azure OpenAI `completions` API usage for cost, performance & user interactions'
----
-
-<Tabs>
- <Tab title="Python">
- <CodeGroup>
- ```python No Streaming
- from openai import AzureOpenAI
- import dokumetry
-
- client = AzureOpenAI(
- api_key = "YOUR_AZURE_OPENAI_API_KEY",
- api_version = "2024-02-01",
- azure_endpoint = "YOUR_AZURE_OPENAI_API_ENDPOINT"
- )
-
- azure_model_deployment = "YOUR_AZURE_OPENAI_DEPLOYMENT"
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- response = client.completions.create(
- model=azure_model_deployment,
- prompt="What is LLM Observablity?",
- )
-
- print(respomse.choices[0].text)
- ```
-
- ```python Streaming
- from openai import AzureOpenAI
- import dokumetry
-
- client = AzureOpenAI(
- api_key = "YOUR_AZURE_OPENAI_API_KEY",
- api_version = "2024-02-01",
- azure_endpoint = "YOUR_AZURE_OPENAI_API_ENDPOINT"
- )
-
- azure_model_deployment = "YOUR_AZURE_OPENAI_DEPLOYMENT"
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- response = client.completions.create(
- model=azure_model_deployment,
- prompt="How to monitor LLM Applications?",
- stream=True
- )
-
- for chunk in respomse:
- print(chunk.choices[0].text)
- ```
- </CodeGroup>
- </Tab>
- <Tab title="NodeJS">
- <CodeGroup>
- ```javascript No Streaming
- import OpenAI from "openai";
- import DokuMetry from 'dokumetry';
-
- const client = new OpenAI({
- apiKey: "YOUR_AZURE_OPENAI_API_KEY",
- baseURL: `https://YOUR_AZURE_OPENAI_RESOURCE.openai.azure.com/openai/deployments/YOUR_AZURE_OPENAI_DEPLOYMENT`,
- defaultQuery: { 'api-version': "2024-02-01" },
- defaultHeaders: { 'api-key': "YOUR_AZURE_OPENAI_API_KEY" },
- });
-
- const azureModelDeployment = 'YOUR_AZURE_OPENAI_DEPLOYMENT';
-
- // Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- DokuMetry.init({llm: client, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- async function main() {
- const response = await client.completions.create({
- model: azureModelDeployment,
- prompt: "How to monitor LLM Applications?",
- });
-
- console.log(response);
- }
- main();
- ```
-
- ```javascript Streaming
- import OpenAI from "openai";
- import DokuMetry from 'dokumetry';
-
- const client = new OpenAI({
- apiKey: "YOUR_AZURE_OPENAI_API_KEY",
- baseURL: `https://YOUR_AZURE_OPENAI_RESOURCE.openai.azure.com/openai/deployments/YOUR_AZURE_OPENAI_DEPLOYMENT`,
- defaultQuery: { 'api-version': "2024-02-01" },
- defaultHeaders: { 'api-key': "YOUR_AZURE_OPENAI_API_KEY" },
- });
-
- const azureModelDeployment = 'YOUR_AZURE_OPENAI_DEPLOYMENT';
-
- // Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- DokuMetry.init({llm: client, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- async function main() {
- const response = await client.completions.create({
- model: azureModelDeployment,
- prompt: "How to monitor LLM Applications?",
- stream: true,
- });
-
- for await (const chunk of response) {
- console.log(chunk.choices[0].text)
- }
- }
- main();
- ```
- </CodeGroup>
- </Tab>
-</Tabs>
\ No newline at end of file
diff --git a/docs/latest/integrations/azure-openai/examples/embeddings.mdx b/docs/latest/integrations/azure-openai/examples/embeddings.mdx
deleted file mode 100644
index c218f846..00000000
--- a/docs/latest/integrations/azure-openai/examples/embeddings.mdx
+++ /dev/null
@@ -1,61 +0,0 @@
----
-title: 'Embeddings'
-description: 'Monitor OpenAI Embeddings API usage'
----
-
-## Create Embeddings
-<Tabs>
- <Tab title="Python">
- ```python
- from openai import AzureOpenAI
- import dokumetry
-
- client = AzureOpenAI(
- api_key = "YOUR_AZURE_OPENAI_API_KEY",
- api_version = "2024-02-01",
- azure_endpoint = "YOUR_AZURE_OPENAI_API_ENDPOINT"
- )
-
- azure_model_deployment = "YOUR_AZURE_OPENAI_DEPLOYMENT"
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- client.embeddings.create(
- model=azure_model_deployment,
- input="LLM monitoring",
- encoding_format="float"
- )
- ```
- </Tab>
- <Tab title="javascript">
- ```javascript
- import OpenAI from "openai";
- import DokuMetry from 'dokumetry';
-
- const client = new OpenAI({
- apiKey: "YOUR_AZURE_OPENAI_API_KEY",
- baseURL: `https://YOUR_AZURE_OPENAI_RESOURCE.openai.azure.com/openai/deployments/YOUR_AZURE_OPENAI_DEPLOYMENT`,
- defaultQuery: { 'api-version': "2024-02-01" },
- defaultHeaders: { 'api-key': "YOUR_AZURE_OPENAI_API_KEY" },
- });
-
- const azureModelDeployment = 'YOUR_AZURE_OPENAI_DEPLOYMENT';
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- async function main() {
- const embedding = await client.embeddings.create({
- model: azureModelDeployment,
- input: "The quick brown fox jumped over the lazy dog",
- encoding_format: "float",
- });
-
- console.log(embedding);
- }
-
- main();
- ```
- </Tab>
-</Tabs>
\ No newline at end of file
diff --git a/docs/latest/integrations/azure-openai/examples/image.mdx b/docs/latest/integrations/azure-openai/examples/image.mdx
deleted file mode 100644
index 36074dd7..00000000
--- a/docs/latest/integrations/azure-openai/examples/image.mdx
+++ /dev/null
@@ -1,60 +0,0 @@
----
-title: 'Image'
-description: 'Monitor Azure OpenAI `image` API usage for cost, performance & user interactions'
----
-
-## Create Image
-
-<Tabs>
- <Tab title="Python">
- ```python
- from openai import AzureOpenAI
- import dokumetry
-
- client = AzureOpenAI(
- api_key = "YOUR_AZURE_OPENAI_API_KEY",
- api_version = "2024-02-01",
- azure_endpoint = "YOUR_AZURE_OPENAI_API_ENDPOINT"
- )
-
- azure_model_deployment = "YOUR_AZURE_OPENAI_DEPLOYMENT"
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- image = client.images.generate(
- model=azure_model_deployment,
- prompt="Create a dashboard for LLM Observability data",
- n=1,
- size="1024x1024"
- )
-
- print(image.data)
- ```
- </Tab>
- <Tab title="Javascript">
- ```javascript
- import OpenAI from "openai";
- import DokuMetry from 'dokumetry';
-
- const client = new OpenAI({
- apiKey: "YOUR_AZURE_OPENAI_API_KEY",
- baseURL: `https://YOUR_AZURE_OPENAI_RESOURCE.openai.azure.com/openai/deployments/YOUR_AZURE_OPENAI_DEPLOYMENT`,
- defaultQuery: { 'api-version': "2024-02-01" },
- defaultHeaders: { 'api-key': "YOUR_AZURE_OPENAI_API_KEY" },
- });
-
- const azureModelDeployment = 'YOUR_AZURE_OPENAI_DEPLOYMENT';
-
- async function main() {
- const image = await client.images.generate({
- model: azureModelDeployment,
- prompt: "Create a dashboard for LLM Observability data"
- });
-
- console.log(image.data);
- }
- main();
- ```
- </Tab>
-</Tabs>
\ No newline at end of file
diff --git a/docs/latest/integrations/azure-openai/introduction.mdx b/docs/latest/integrations/azure-openai/introduction.mdx
deleted file mode 100644
index d6aa989e..00000000
--- a/docs/latest/integrations/azure-openai/introduction.mdx
+++ /dev/null
@@ -1,102 +0,0 @@
----
-title: 'Azure OpenAI Integration'
-sidebarTitle: 'Get Started'
----
-
-DokuMetry SDKs (`dokumetry`) empowers you to effortlessly track and monitor Azure OpenAI usage data and metrics from your Python/NodeJS code.
-
-## Get Started
-
-The integration is compatible with
-- OpenAI Python SDK client `>=1.13.0`
-- OpenAI JS/TS SDK client `>=4.28.0`
-
-<Tabs>
- <Tab title="Python">
- ```shell
- pip install dokumetry==0.1.1
- ```
-
- ```python
- from openai import AzureOpenAI
- import dokumetry
-
- client = AzureOpenAI(
- api_key = "YOUR_AZURE_OPENAI_API_KEY",
- api_version = "2024-02-01",
- azure_endpoint = "YOUR_AZURE_OPENAI_API_ENDPOINT"
- )
-
- dokumetry.init(llm = client, doku_url = "YOUR_DOKU_INGESTER_URL", api_key = "YOUR_DOKU_TOKEN")
- ```
- </Tab>
- <Tab title="Javascript">
- ```shell
- npm install [email protected]
- ```
-
- ```javascript
- import OpenAI from "openai";
- import DokuMetry from 'dokumetry';
-
- const client = new OpenAI({
- apiKey: "YOUR_AZURE_OPENAI_API_KEY",
- baseURL: `https://YOUR_AZURE_OPENAI_RESOURCE.openai.azure.com/openai/deployments/YOUR_AZURE_OPENAI_DEPLOYMENT`,
- defaultQuery: { 'api-version': "2024-02-01" },
- defaultHeaders: { 'api-key': "YOUR_AZURE_OPENAI_API_KEY" },
- });
-
- DokuMetry.init({llm: client, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
- ```
- </Tab>
-</Tabs>
-
-## Supported Endpoints
-
-The following Azure OpenAI Endpoints are supported for monitoring with DokuMetry
-
-- [Chat completions](/latest/integrations/azure-openai/examples/chat)
-- [Image Create](/latest/integrations/azure-openai/examples/image#create-image)
-- [Embeddings](/latest/integrations/azure-openai/examples/embeddings)
-- [Completions](/latest/integrations/azure-openai/examples/completions)
-
-## Parameters
-
-<Tabs>
- <Tab title="Python">
- | Parameter | Description | Required |
- |-------------------|-----------------------------------------------------------|---------------|
- | llm | Azure OpenAI Object to track | Yes |
- | doku_url | URL of your Doku Ingester | Yes |
- | api_key | Your Doku API key | Yes |
- | environment | Custom environment tag to include in your metrics | Optional |
- | application_name | Custom application name tag for your metrics | Optional |
- | skip_resp | Skip response from the Doku Ingester for faster execution | Optional |
- </Tab>
- <Tab title="NodeJS">
- | Parameter | Description | Required |
- |-------------------|-----------------------------------------------------------|---------------|
- | llm | Azure OpenAI Object to track | Yes |
- | dokuUrl | URL of your Doku Ingester | Yes |
- | apiKey | Your Doku API key | Yes |
- | environment | Custom environment tag to include in your metrics | Optional |
- | applicationName | Custom application name tag for your metrics | Optional |
- | skipResp | Skip response from the Doku Ingester for faster execution | Optional |
- </Tab>
-</Tabs>
-
-## Advanced Usage
-When using DokuMetry in Production environments, It is recommened to set Skip response parameter to `true` for faster porcessing.
-
-To filter your LLM Usage according application or the environment, set the Application name and Environment paramaters with the actual values.
-
----
-
-<CardGroup cols={2}>
-<Card title="Connections" href="/latest/connections/intro" icon='link'>
-Connect to your existing Observablity Platform
-</Card>
-<Card title="API Reference" href="/latest/api-reference/introduction" icon='code'>
-OpenAPI specification for API Endpoints in Doku
-</Card>
-</CardGroup>
\ No newline at end of file
diff --git a/docs/latest/integrations/chromadb.mdx b/docs/latest/integrations/chromadb.mdx
new file mode 100644
index 00000000..0718e873
--- /dev/null
+++ b/docs/latest/integrations/chromadb.mdx
@@ -0,0 +1,48 @@
+---
+title: 'Monitor ChromaDB using OpenTelemetry'
+sidebarTitle: 'ChromaDB'
+---
+
+OpenLIT SDKs provide OpenTelemetry Auto-Instrumentation for monitoring LLM Application using ChromaDB which includes performance, Operation stats and more.
+
+The integration is compatible with
+- PineCone Python SDK client `>= 0.4.0`
+
+## Get Started
+
+<Steps>
+ <Step title="Install the OpenLIT Python SDK using pip">
+ ```shell
+ pip install openlit
+ ```
+ </Step>
+ <Step title="Add the following two lines to your application code:">
+ Integrating the OpenLIT into LLM applications is straightforward. Start monitoring for your LLM Application with just **one line of code**:
+
+ ```python
+ import openlit
+
+ openlit.init(otlp_endpoint="otlp_backend_endpoint", otlp_headers="otlp_backend_token")
+ ```
+
+ Alternatively, you can configure the OTLP endpoint by setting the `OTEL_EXPORTER_OTLP_ENDPOINT` and the OTLP headers by setting the Appli`OTEL_EXPORTER_OTLP_HEADERS` environmentcation variable as recommended in the OpenTelemetry documentation.
+
+ If your aim is primarily to test or develop without sending telemetry data to an external backend, you can initialize OpenLIT without any parameters. This approach directs all telemetry output to your console, enabling quick diagnostics and local debugging:
+
+ ```python
+ import openlit
+
+ openlit.init()
+ ```
+
+ Refer to the OpenLIT [Python SDK repository](https://github.com/openlit/openlit/tree/main/sdk/python) for more advanced configurations and use cases.
+ </Step>
+</Steps>
+
+---
+
+<CardGroup cols={2}>
+<Card title="Connections" href="/latest/connections/intro" icon='link'>
+Connect to your existing Observablity Platform
+</Card>
+</CardGroup>
\ No newline at end of file
diff --git a/docs/latest/integrations/cohere.mdx b/docs/latest/integrations/cohere.mdx
new file mode 100644
index 00000000..b7501568
--- /dev/null
+++ b/docs/latest/integrations/cohere.mdx
@@ -0,0 +1,48 @@
+---
+title: 'Monitor Cohere using OpenTelemetry'
+sidebarTitle: 'Cohere'
+---
+
+OpenLIT SDKs provide OpenTelemetry Auto-Instrumentation for monitoring LLM Application using Cohere which includes performance, token and cost usage and user interactions.
+
+The integration is compatible with
+- Cohere Python SDK client `>= 5.3.0`
+
+## Get Started
+
+<Steps>
+ <Step title="Install the OpenLIT Python SDK using pip">
+ ```shell
+ pip install openlit
+ ```
+ </Step>
+ <Step title="Add the following two lines to your application code:">
+ Integrating the OpenLIT into LLM applications is straightforward. Start monitoring for your LLM Application with just **one line of code**:
+
+ ```python
+ import openlit
+
+ openlit.init(otlp_endpoint="otlp_backend_endpoint", otlp_headers="otlp_backend_token")
+ ```
+
+ Alternatively, you can configure the OTLP endpoint by setting the `OTEL_EXPORTER_OTLP_ENDPOINT` and the OTLP headers by setting the Appli`OTEL_EXPORTER_OTLP_HEADERS` environmentcation variable as recommended in the OpenTelemetry documentation.
+
+ If your aim is primarily to test or develop without sending telemetry data to an external backend, you can initialize OpenLIT without any parameters. This approach directs all telemetry output to your console, enabling quick diagnostics and local debugging:
+
+ ```python
+ import openlit
+
+ openlit.init()
+ ```
+
+ Refer to the OpenLIT [Python SDK repository](https://github.com/openlit/openlit/tree/main/sdk/python) for more advanced configurations and use cases.
+ </Step>
+</Steps>
+
+---
+
+<CardGroup cols={2}>
+<Card title="Connections" href="/latest/connections/intro" icon='link'>
+Connect to your existing Observablity Platform
+</Card>
+</CardGroup>
\ No newline at end of file
diff --git a/docs/latest/integrations/cohere/examples/cochat.mdx b/docs/latest/integrations/cohere/examples/cochat.mdx
deleted file mode 100644
index 84718404..00000000
--- a/docs/latest/integrations/cohere/examples/cochat.mdx
+++ /dev/null
@@ -1,106 +0,0 @@
----
-title: 'Chat'
-description: 'Monitor Cohere `chat` API usage for cost, performance & user interactions'
----
-
-<Tabs>
- <Tab title="Python">
- <CodeGroup>
- ```python No Streaming
- import cohere
- import dokumetry
-
- co = cohere.Client("YOUR_COHERE_API_KEY")
-
- # Pass the above `co` object along with your Doku Ingester URL and API key and this will make sure that all Cohere calls are automatically tracked.
- dokumetry.init(llm=co, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- response = co.chat(
- chat_history=[
- {"role": "USER", "message": "What is LLM Observability?"},
- {"role": "CHATBOT", "message": "The best tool to monitor LLM Applications is Doku!"}
- ],
- message="How to monitor LLM Applications?",
- )
- print(response.text)
- ```
-
- ```python Streaming
- import cohere
- import dokumetry
-
- co = cohere.Client("YOUR_COHERE_API_KEY")
-
- # Pass the above `co` object along with your Doku Ingester URL and API key and this will make sure that all Cohere calls are automatically tracked.
- dokumetry.init(llm=co, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- response = co.chat_steam(
- chat_history=[
- {"role": "USER", "message": "What is LLM Observability?"},
- {"role": "CHATBOT", "message": "The best tool to monitor LLM Applications is Doku!"}
- ],
- message="How to monitor LLM Applications?",
- )
- for text in response:
- if text.event_type === "text-generation":
- print(text)
- ```
- </CodeGroup>
- </Tab>
- <Tab title="Javascript">
- <CodeGroup>
- ```javascript No Streaming
- import { CohereClient } from "cohere-ai";
- import DokuMetry from 'dokumetry';
-
- const cohere = new CohereClient({
- token: "YOUR_COHERE_API_KEY",
- });
-
- (async () => {
- // Pass the above `cohere` object along with your Doku Ingester URL and API key and this will make sure that all Cohere calls are automatically tracked.
- DokuMetry.init({llm: cohere, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- const response = await cohere.chat({
- chatHistory: [
- {"role": "USER", "message": "What is LLM Observability?"},
- {"role": "CHATBOT", "message": "The best tool to monitor LLM Applications is Doku!"}
- ],
- message: "How to monitor LLM Applications?",
- model: 'command',
- });
-
- console.log(response.text)
- })();
- ```
-
- ```javascript Streaming
- import { CohereClient } from "cohere-ai";
- import DokuMetry from 'dokumetry';
-
- const cohere = new CohereClient({
- token: "YOUR_COHERE_API_KEY",
- });
-
- (async () => {
- // Pass the above `cohere` object along with your Doku Ingester URL and API key and this will make sure that all Cohere calls are automatically tracked.
- DokuMetry.init({llm: cohere, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- const response = await cohere.chatStream({
- chatHistory: [
- {"role": "USER", "message": "What is LLM Observability?"},
- {"role": "CHATBOT", "message": "The best tool to monitor LLM Applications is Doku!"}
- ],
- message: "How to monitor LLM Applications?",
- model: 'command',
- });
- for await (const message of response) {
- if (message.eventType === "text-generation") {
- console.log(message);
- }
- }
- })();
- ```
- </CodeGroup>
- </Tab>
-</Tabs>
\ No newline at end of file
diff --git a/docs/latest/integrations/cohere/examples/embed.mdx b/docs/latest/integrations/cohere/examples/embed.mdx
deleted file mode 100644
index 57a3835a..00000000
--- a/docs/latest/integrations/cohere/examples/embed.mdx
+++ /dev/null
@@ -1,47 +0,0 @@
----
-title: 'Embed'
-description: 'Monitor Cohere Embed API usage'
----
-
-<Tabs>
- <Tab title="Python">
- ```python
- import cohere
- import dokumetry
-
- co = cohere.Client("YOUR_COHERE_API_KEY")
-
- # Pass the above `co` object along with your Doku Ingester URL and API key and this will make sure that all Cohere calls are automatically tracked.
- dokumetry.init(llm=co, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- response = co.embed(
- texts=['LLM', 'Monitoring', 'Observability'],
- model='embed-english-v3.0',
- input_type='classification'
- )
- print(response)
- ```
- </Tab>
- <Tab title="Javascript">
- ```javascript
- import { CohereClient } from "cohere-ai";
- import DokuMetry from 'dokumetry';
-
- const cohere = new CohereClient({
- token: "YOUR_COHERE_API_KEY",
- });
-
- (async () => {
- // Pass the above `cohere` object along with your Doku Ingester URL and API key and this will make sure that all Cohere calls are automatically tracked.
- DokuMetry.init({llm: cohere, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- const embed = await cohere.embed({
- texts: ['LLM', 'Monitoring', 'Observability'],
- model: "embed-english-v3.0",
- inputType: "classification",
- });
- console.log(embed);
- })();
- ```
- </Tab>
-</Tabs>
\ No newline at end of file
diff --git a/docs/latest/integrations/cohere/examples/generate.mdx b/docs/latest/integrations/cohere/examples/generate.mdx
deleted file mode 100644
index 012c50d0..00000000
--- a/docs/latest/integrations/cohere/examples/generate.mdx
+++ /dev/null
@@ -1,44 +0,0 @@
----
-title: 'Generate'
-description: 'Monitor Cohere `generate` API usage for cost, performance & user interactions'
----
-
-<Tabs>
- <Tab title="Python">
- ```python
- import cohere
- import dokumetry
-
- co = cohere.Client("YOUR_COHERE_API_KEY")
-
- # Pass the above `co` object along with your Doku Ingester URL and API key and this will make sure that all Cohere calls are automatically tracked.
- dokumetry.init(llm=co, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- response = co.generate(
- prompt='How to monitor my LLM Applications?',
- )
- print(response)
- ```
- </Tab>
- <Tab title="Javascript">
- ```javascript
- import { CohereClient } from "cohere-ai";
- import DokuMetry from 'dokumetry';
-
- const cohere = new CohereClient({
- token: "YOUR_COHERE_API_KEY",
- });
-
- (async () => {
- // Pass the above `cohere` object along with your Doku Ingester URL and API key and this will make sure that all Cohere calls are automatically tracked.
- DokuMetry.init({llm: cohere, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- const generate = await cohere.generate({
- prompt: "What is LLM Monitoring?",
- });
-
- console.log(generate);
- })();
- ```
- </Tab>
-</Tabs>
\ No newline at end of file
diff --git a/docs/latest/integrations/cohere/examples/summarize.mdx b/docs/latest/integrations/cohere/examples/summarize.mdx
deleted file mode 100644
index 3715c67b..00000000
--- a/docs/latest/integrations/cohere/examples/summarize.mdx
+++ /dev/null
@@ -1,86 +0,0 @@
----
-title: 'Summarize'
-description: 'Monitor Cohere `summarize` API usage for cost, performance & user interactions'
----
-
-<Tabs>
- <Tab title="Python">
- ```python
- import cohere
- import dokumetry
-
- co = cohere.Client("YOUR_COHERE_API_KEY")
-
- # Pass the above `co` object along with your Doku Ingester URL and API key and this will make sure that all Cohere calls are automatically tracked.
- dokumetry.init(llm=co, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- text=(
- "Ice cream is a sweetened frozen food typically eaten as a snack or dessert. "
- "It may be made from milk or cream and is flavoured with a sweetener, "
- "either sugar or an alternative, and a spice, such as cocoa or vanilla, "
- "or with fruit such as strawberries or peaches. "
- "It can also be made by whisking a flavored cream base and liquid nitrogen together. "
- "Food coloring is sometimes added, in addition to stabilizers. "
- "The mixture is cooled below the freezing point of water and stirred to incorporate air spaces "
- "and to prevent detectable ice crystals from forming. The result is a smooth, "
- "semi-solid foam that is solid at very low temperatures (below 2 °C or 35 °F). "
- "It becomes more malleable as its temperature increases.\n\n"
- "The meaning of the name \"ice cream\" varies from one country to another. "
- "In some countries, such as the United States, \"ice cream\" applies only to a specific variety, "
- "and most governments regulate the commercial use of the various terms according to the "
- "relative quantities of the main ingredients, notably the amount of cream. "
- "Products that do not meet the criteria to be called ice cream are sometimes labelled "
- "\"frozen dairy dessert\" instead. In other countries, such as Italy and Argentina, "
- "one word is used fo\r all variants. Analogues made from dairy alternatives, "
- "such as goat's or sheep's milk, or milk substitutes "
- "(e.g., soy, cashew, coconut, almond milk or tofu), are available for those who are "
- "lactose intolerant, allergic to dairy protein or vegan."
- )
-
- response = co.summarize(
- text=text,
- )
- print(response)
- ```
- </Tab>
- <Tab title="Javascript">
- ```javascript
- import { CohereClient } from "cohere-ai";
- import DokuMetry from 'dokumetry';
-
- const cohere = new CohereClient({
- token: "YOUR_COHERE_API_KEY",
- });
-
- (async () => {
- // Pass the above `cohere` object along with your Doku Ingester URL and API key and this will make sure that all Cohere calls are automatically tracked.
- DokuMetry.init({llm: cohere, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- const summarize = await cohere.summarize({
- text: "Ice cream is a sweetened frozen food typically eaten as a snack or dessert. "
- + "It may be made from milk or cream and is flavoured with a sweetener, "
- + "either sugar or an alternative, and a spice, such as cocoa or vanilla, "
- + "or with fruit such as strawberries or peaches. "
- + "It can also be made by whisking a flavored cream base and liquid nitrogen together. "
- + "Food coloring is sometimes added, in addition to stabilizers. "
- + "The mixture is cooled below the freezing point of water and stirred to incorporate air spaces "
- + "and to prevent detectable ice crystals from forming. The result is a smooth, "
- + "semi-solid foam that is solid at very low temperatures (below 2 °C or 35 °F). "
- + "It becomes more malleable as its temperature increases.\n\n"
- + "The meaning of the name \"ice cream\" varies from one country to another. "
- + "In some countries, such as the United States, \"ice cream\" applies only to a specific variety, "
- + "and most governments regulate the commercial use of the various terms according to the "
- + "relative quantities of the main ingredients, notably the amount of cream. "
- + "Products that do not meet the criteria to be called ice cream are sometimes labelled "
- + "\"frozen dairy dessert\" instead. In other countries, such as Italy and Argentina, "
- + "one word is used fo\r all variants. Analogues made from dairy alternatives, "
- + "such as goat's or sheep's milk, or milk substitutes "
- + "(e.g., soy, cashew, coconut, almond milk or tofu), are available for those who are "
- + "lactose intolerant, allergic to dairy protein or vegan.",
- });
-
- console.log(summarize);
- })();
- ```
- </Tab>
-</Tabs>
\ No newline at end of file
diff --git a/docs/latest/integrations/cohere/introduction.mdx b/docs/latest/integrations/cohere/introduction.mdx
deleted file mode 100644
index ddcd8494..00000000
--- a/docs/latest/integrations/cohere/introduction.mdx
+++ /dev/null
@@ -1,94 +0,0 @@
----
-title: 'Cohere integration'
-sidebarTitle: 'Get Started'
----
-
-DokuMetry SDKs (`dokumetry`) empowers you to effortlessly track and monitor Cohere usage data and metrics from your Python/NodeJS code.
-
-## Get Started
-
-The integration is compatible with
-- Cohere Python SDK client `>=5.0.0`
-- Cohere JS/TS SDK client `>=7.6.0`
-
-<Tabs>
- <Tab title="Python">
- ```shell
- pip install dokumetry==0.1.1
- ```
-
- ```python
- import cohere
- import dokumetry
-
- co = cohere.Client('YOUR_API_KEY')
-
- dokumetry.init(llm = co, doku_url = "YOUR_DOKU_INGESTER_URL", api_key = "YOUR_DOKU_TOKEN")
- ```
- </Tab>
- <Tab title="Javascript">
- ```shell
- npm install [email protected]
- ```
-
- ```javascript
- import { CohereClient } from "cohere-ai";
- import DokuMetry from 'dokumetry';
-
- const co = new CohereClient({
- token: "YOUR_COHERE_API_KEY",
- });
-
- DokuMetry.init({llm: co, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
- ```
- </Tab>
-</Tabs>
-
-## Supported Endpoints
-The following Cohere Endpoints are supported for monitoring with DokuMetry
-
-- [Chat](/latest/integrations/cohere/examples/cochat)
-- [Generate](/latest/integrations/cohere/examples/generate)
-- [Summarize](/latest/integrations/cohere/examples/summarize)
-- [Embed](/latest/integrations/cohere/examples/embed)
-
-## Parameters
-
-<Tabs>
- <Tab title="Python">
- | Parameter | Description | Required |
- |-------------------|-----------------------------------------------------------|---------------|
- | llm | Cohere Object to track | Yes |
- | doku_url | URL of your Doku Ingester | Yes |
- | api_key | Your Doku API key | Yes |
- | environment | Custom environment tag to include in your metrics | Optional |
- | application_name | Custom application name tag for your metrics | Optional |
- | skip_resp | Skip response from the Doku Ingester for faster execution | Optional |
- </Tab>
- <Tab title="NodeJS">
- | Parameter | Description | Required |
- |-------------------|-----------------------------------------------------------|---------------|
- | llm | Cohere Object to track | Yes |
- | dokuUrl | URL of your Doku Ingester | Yes |
- | apiKey | Your Doku API key | Yes |
- | environment | Custom environment tag to include in your metrics | Optional |
- | applicationName | Custom application name tag for your metrics | Optional |
- | skipResp | Skip response from the Doku Ingester for faster execution | Optional |
- </Tab>
-</Tabs>
-
-## Advanced Usage
-When using DokuMetry in Production environments, It is recommened to set Skip response parameter to `true` for faster porcessing.
-
-To filter your LLM Usage according application or the environment, set the Application name and Environment paramaters with the actual values.
-
----
-
-<CardGroup cols={2}>
-<Card title="Connections" href="/latest/connections/intro" icon='link'>
-Connect to your existing Observablity Platform
-</Card>
-<Card title="API Reference" href="/latest/api-reference/introduction" icon='code'>
-OpenAPI specification for API Endpoints in Doku
-</Card>
-</CardGroup>
\ No newline at end of file
diff --git a/docs/latest/integrations/huggingface.mdx b/docs/latest/integrations/huggingface.mdx
new file mode 100644
index 00000000..a1437f63
--- /dev/null
+++ b/docs/latest/integrations/huggingface.mdx
@@ -0,0 +1,48 @@
+---
+title: 'Monitor HuggingFace using OpenTelemetry'
+sidebarTitle: 'HuggingFace'
+---
+
+OpenLIT SDKs provide OpenTelemetry Auto-Instrumentation for monitoring LLM Application using HuggingFace which includes performance, token usage and user interactions.
+
+The integration is compatible with
+- HuggingFace Trasnformers Python SDK client `>= 4.39.3`
+
+## Get Started
+
+<Steps>
+ <Step title="Install the OpenLIT Python SDK using pip">
+ ```shell
+ pip install openlit
+ ```
+ </Step>
+ <Step title="Add the following two lines to your application code:">
+ Integrating the OpenLIT into LLM applications is straightforward. Start monitoring for your LLM Application with just **one line of code**:
+
+ ```python
+ import openlit
+
+ openlit.init(otlp_endpoint="otlp_backend_endpoint", otlp_headers="otlp_backend_token")
+ ```
+
+ Alternatively, you can configure the OTLP endpoint by setting the `OTEL_EXPORTER_OTLP_ENDPOINT` and the OTLP headers by setting the Appli`OTEL_EXPORTER_OTLP_HEADERS` environmentcation variable as recommended in the OpenTelemetry documentation.
+
+ If your aim is primarily to test or develop without sending telemetry data to an external backend, you can initialize OpenLIT without any parameters. This approach directs all telemetry output to your console, enabling quick diagnostics and local debugging:
+
+ ```python
+ import openlit
+
+ openlit.init()
+ ```
+
+ Refer to the OpenLIT [Python SDK repository](https://github.com/openlit/openlit/tree/main/sdk/python) for more advanced configurations and use cases.
+ </Step>
+</Steps>
+
+---
+
+<CardGroup cols={2}>
+<Card title="Connections" href="/latest/connections/intro" icon='link'>
+Connect to your existing Observablity Platform
+</Card>
+</CardGroup>
\ No newline at end of file
diff --git a/docs/latest/integrations/introduction.mdx b/docs/latest/integrations/introduction.mdx
index b0b77042..3eb93b75 100644
--- a/docs/latest/integrations/introduction.mdx
+++ b/docs/latest/integrations/introduction.mdx
@@ -1,15 +1,16 @@
---
-sidebarTitle: 'Introduction'
-title: 'Monitor your LLM Applications'
-description: 'Monitor LLM Costs, Tokens and Performance along with User Interactions'
+sidebarTitle: 'Overview'
+title: 'Monitor your GenAI and LLM Applications'
+description: 'Monitor LLM Costs, Tokens and Performance along with User Interactions with OpenTelemetry'
---
-Start integrating and monitoring your applications with Doku effortlessly. Choose from a range of providers to **start tracking LLM performance, usage, and costs** without hassle.
+Start integrating and monitoring your applications with OpenLIT effortlessly. Choose from a range of Integrations to **start tracking LLM performance, usage, and costs** without hassle.
+### LLMs
<CardGroup cols={2}>
<Card
title="OpenAI"
- href="/latest/integrations/openai/introduction"
+ href="/latest/integrations/openai"
icon={
<svg role="img" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg">
<title>OpenAI</title>
@@ -21,7 +22,7 @@ Start integrating and monitoring your applications with Doku effortlessly. Choos
</Card>
<Card
title="Cohere"
- href="/latest/integrations/cohere/introduction"
+ href="/latest/integrations/cohere"
icon={
<svg role="image" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 80 80">
<g>
@@ -46,7 +47,7 @@ Start integrating and monitoring your applications with Doku effortlessly. Choos
</Card>
<Card
title="Anthropic"
- href="/latest/integrations/anthropic/introduction"
+ href="/latest/integrations/anthropic"
icon={
<svg viewBox="0 0 255 255" xmlns="http://www.w3.org/2000/svg">
<path d="M147.486878,0 C147.486878,0 217.568251,175.780074 217.568251,175.780074 C217.568251,175.780074 256,175.780074 256,175.780074 C256,175.780074 185.918621,0 185.918621,0 C185.918621,0 147.486878,0 147.486878,0 C147.486878,0 147.486878,0 147.486878,0 Z"></path>
@@ -58,40 +59,126 @@ Start integrating and monitoring your applications with Doku effortlessly. Choos
</Card>
<Card
title="Azure OpenAI"
- href="/latest/integrations/azure-openai/introduction"
+ href="/latest/integrations/azure-openai"
icon={
- <svg viewBox="0 0 525 525" xmlns="http://www.w3.org/2000/svg"><g>
- <path d="M52.091 10.225h40.684L50.541 135.361a6.5 6.5 0 01-6.146 4.412H12.732c-3.553 0-6.477-2.923-6.477-6.476 0-.704.115-1.403.34-2.07L45.944 14.638a6.501 6.501 0 016.147-4.415v.002z" transform="translate(2.076 1.626) scale(3.37462)"/><path d="M377.371 319.374H159.644c-5.527 0-10.076 4.549-10.076 10.077 0 2.794 1.164 5.466 3.206 7.37l139.901 130.577a21.986 21.986 0 0015.004 5.91H430.96l-53.589-153.934z"/><path d="M52.091 10.225a6.447 6.447 0 00-6.161 4.498L6.644 131.12a6.457 6.457 0 00-.38 2.185c0 3.548 2.92 6.468 6.469 6.468H45.23a6.95 6.95 0 005.328-4.531l7.834-23.089 27.985 26.102a6.622 6.622 0 004.165 1.518h36.395l-15.962-45.615-46.533.011 28.48-83.944H52.091z" transform="translate(2.076 1.626) scale(3.37462)"/><path d="M104.055 14.631a6.492 6.492 0 00-6.138-4.406H52.575a6.493 6.493 0 016.138 4.406l39.35 116.594c.225.668.34 1.367.34 2.072 0 3.554-2.924 6.478-6.478 6.478h45.344c3.553-.001 6.476-2.925 6.476-6.478 0-.705-.115-1.404-.34-2.072l-39.35-116.594z" transform="translate(2.076 1.626) scale(3.37462)"/></g><defs><linearGradient id="prefix___Linear1" x1="0" y1="0" x2="1" y2="0" gradientUnits="userSpaceOnUse" gradientTransform="rotate(108.701 26.35 33.911) scale(131.7791)"><stop offset="0"/><stop offset="1"/></linearGradient><linearGradient id="prefix___Linear2" x1="0" y1="0" x2="1" y2="0" gradientUnits="userSpaceOnUse" gradientTransform="rotate(161.318 33.644 45.587) scale(10.31703)"><stop offset="0"/><stop offset=".07"/><stop offset=".32"/><stop offset=".62"/><stop offset="1"/></linearGradient><linearGradient id="prefix___Linear3" x1="0" y1="0" x2="1" y2="0" gradientUnits="userSpaceOnUse" gradientTransform="rotate(69.426 25.69 62.036) scale(131.9816)"><stop offset="0"/><stop offset="1"/></linearGradient></defs>
- </svg>
+ <svg viewBox="0 0 512 512" xmlns="http://www.w3.org/2000/svg" fill-rule="evenodd" clip-rule="evenodd" stroke-linejoin="round" stroke-miterlimit="2"><g fill-rule="nonzero"><path d="M52.091 10.225h40.684L50.541 135.361a6.5 6.5 0 01-6.146 4.412H12.732c-3.553 0-6.477-2.923-6.477-6.476 0-.704.115-1.403.34-2.07L45.944 14.638a6.501 6.501 0 016.147-4.415v.002z" fill="url(#prefix___Linear1)" transform="translate(2.076 1.626) scale(3.37462)"/><path d="M377.371 319.374H159.644c-5.527 0-10.076 4.549-10.076 10.077 0 2.794 1.164 5.466 3.206 7.37l139.901 130.577a21.986 21.986 0 0015.004 5.91H430.96l-53.589-153.934z" fill="#0078d4"/><path d="M52.091 10.225a6.447 6.447 0 00-6.161 4.498L6.644 131.12a6.457 6.457 0 00-.38 2.185c0 3.548 2.92 6.468 6.469 6.468H45.23a6.95 6.95 0 005.328-4.531l7.834-23.089 27.985 26.102a6.622 6.622 0 004.165 1.518h36.395l-15.962-45.615-46.533.011 28.48-83.944H52.091z" fill="url(#prefix___Linear2)" transform="translate(2.076 1.626) scale(3.37462)"/><path d="M104.055 14.631a6.492 6.492 0 00-6.138-4.406H52.575a6.493 6.493 0 016.138 4.406l39.35 116.594c.225.668.34 1.367.34 2.072 0 3.554-2.924 6.478-6.478 6.478h45.344c3.553-.001 6.476-2.925 6.476-6.478 0-.705-.115-1.404-.34-2.072l-39.35-116.594z" fill="url(#prefix___Linear3)" transform="translate(2.076 1.626) scale(3.37462)"/></g><defs><linearGradient id="prefix___Linear1" x1="0" y1="0" x2="1" y2="0" gradientUnits="userSpaceOnUse" gradientTransform="rotate(108.701 26.35 33.911) scale(131.7791)"><stop offset="0" stop-color="#114a8b"/><stop offset="1" stop-color="#0669bc"/></linearGradient><linearGradient id="prefix___Linear2" x1="0" y1="0" x2="1" y2="0" gradientUnits="userSpaceOnUse" gradientTransform="rotate(161.318 33.644 45.587) scale(10.31703)"><stop offset="0" stop-opacity=".3"/><stop offset=".07" stop-opacity=".2"/><stop offset=".32" stop-opacity=".1"/><stop offset=".62" stop-opacity=".05"/><stop offset="1" stop-opacity="0"/></linearGradient><linearGradient id="prefix___Linear3" x1="0" y1="0" x2="1" y2="0" gradientUnits="userSpaceOnUse" gradientTransform="rotate(69.426 25.69 62.036) scale(131.9816)"><stop offset="0" stop-color="#3ccbf4"/><stop offset="1" stop-color="#2892df"/></linearGradient></defs></svg>
}
iconType="duotone"
>
</Card>
<Card
title="Mistral"
- href="/latest/integrations/mistral/introduction"
+ href="/latest/integrations/mistral"
+ icon={
+ <svg viewBox="0 0 256 233" version="1.1" xmlns="http://www.w3.org/2000/svg" preserveAspectRatio="xMidYMid">
+ <title>Mistral AI</title>
+ <g>
+ <rect fill="#000000" x="186.181818" y="0" width="46.5454545" height="46.5454545"></rect>
+ <rect fill="#F7D046" x="209.454545" y="0" width="46.5454545" height="46.5454545"></rect>
+ <rect fill="#000000" x="0" y="0" width="46.5454545" height="46.5454545"></rect>
+ <rect fill="#000000" x="0" y="46.5454545" width="46.5454545" height="46.5454545"></rect>
+ <rect fill="#000000" x="0" y="93.0909091" width="46.5454545" height="46.5454545"></rect>
+ <rect fill="#000000" x="0" y="139.636364" width="46.5454545" height="46.5454545"></rect>
+ <rect fill="#000000" x="0" y="186.181818" width="46.5454545" height="46.5454545"></rect>
+ <rect fill="#F7D046" x="23.2727273" y="0" width="46.5454545" height="46.5454545"></rect>
+ <rect fill="#F2A73B" x="209.454545" y="46.5454545" width="46.5454545" height="46.5454545"></rect>
+ <rect fill="#F2A73B" x="23.2727273" y="46.5454545" width="46.5454545" height="46.5454545"></rect>
+ <rect fill="#000000" x="139.636364" y="46.5454545" width="46.5454545" height="46.5454545"></rect>
+ <rect fill="#F2A73B" x="162.909091" y="46.5454545" width="46.5454545" height="46.5454545"></rect>
+ <rect fill="#F2A73B" x="69.8181818" y="46.5454545" width="46.5454545" height="46.5454545"></rect>
+ <rect fill="#EE792F" x="116.363636" y="93.0909091" width="46.5454545" height="46.5454545"></rect>
+ <rect fill="#EE792F" x="162.909091" y="93.0909091" width="46.5454545" height="46.5454545"></rect>
+ <rect fill="#EE792F" x="69.8181818" y="93.0909091" width="46.5454545" height="46.5454545"></rect>
+ <rect fill="#000000" x="93.0909091" y="139.636364" width="46.5454545" height="46.5454545"></rect>
+ <rect fill="#EB5829" x="116.363636" y="139.636364" width="46.5454545" height="46.5454545"></rect>
+ <rect fill="#EE792F" x="209.454545" y="93.0909091" width="46.5454545" height="46.5454545"></rect>
+ <rect fill="#EE792F" x="23.2727273" y="93.0909091" width="46.5454545" height="46.5454545"></rect>
+ <rect fill="#000000" x="186.181818" y="139.636364" width="46.5454545" height="46.5454545"></rect>
+ <rect fill="#EB5829" x="209.454545" y="139.636364" width="46.5454545" height="46.5454545"></rect>
+ <rect fill="#000000" x="186.181818" y="186.181818" width="46.5454545" height="46.5454545"></rect>
+ <rect fill="#EB5829" x="23.2727273" y="139.636364" width="46.5454545" height="46.5454545"></rect>
+ <rect fill="#EA3326" x="209.454545" y="186.181818" width="46.5454545" height="46.5454545"></rect>
+ <rect fill="#EA3326" x="23.2727273" y="186.181818" width="46.5454545" height="46.5454545"></rect>
+ </g>
+ </svg>
+
+ }
+ iconType="duotone"
+ >
+ </Card>
+ <Card
+ title="HuggingFace"
+ href="/latest/integrations/huggingface"
+ icon={
+ <svg viewBox="0 0 226 266" fill="none" xmlns="http://www.w3.org/2000/svg">
+ <path d="M230.721 172.7C230.183 170.673 229.313 168.75 228.146 167.008C228.396 166.091 228.587 165.159 228.714 164.217C229.543 158.241 227.471 152.77 223.567 148.537C221.452 146.225 219.185 144.698 216.784 143.761C218.36 137.018 219.157 130.117 219.161 123.193C219.161 120.03 218.982 116.932 218.682 113.88C218.526 112.356 218.337 110.836 218.115 109.32C217.428 104.847 216.408 100.431 215.064 96.11C214.183 93.2707 213.164 90.476 212.01 87.736C210.281 83.6782 208.262 79.75 205.969 75.982C204.465 73.475 202.827 71.0508 201.062 68.72C200.197 67.543 199.296 66.3938 198.358 65.274C195.58 61.898 192.561 58.7277 189.325 55.788C188.25 54.7997 187.145 53.8453 186.01 52.926C184.893 51.9943 183.751 51.0927 182.586 50.222C180.241 48.4766 177.818 46.8392 175.324 45.315C161.543 36.945 145.382 32.145 128.109 32.145C77.817 32.145 37.057 72.907 37.057 123.196C37.055 130.208 37.867 137.196 39.477 144.02C37.317 144.958 35.247 146.42 33.327 148.535C29.424 152.766 27.351 158.217 28.18 164.193C28.306 165.142 28.495 166.082 28.747 167.006C27.5811 168.749 26.7117 170.673 26.174 172.7C24.974 177.261 25.369 181.374 26.894 184.978C25.236 189.688 25.65 194.704 27.809 199.065C29.379 202.25 31.626 204.714 34.396 206.916C37.689 209.534 41.811 211.758 46.783 213.892C52.715 216.422 59.956 218.799 63.249 219.671C71.755 221.873 79.911 223.269 88.177 223.337C99.954 223.446 110.096 220.677 117.357 213.59C120.924 214.027 124.515 214.246 128.109 214.244C131.906 214.236 135.699 213.997 139.467 213.529C146.711 220.661 156.892 223.455 168.712 223.343C176.977 223.277 185.133 221.881 193.617 219.676C196.932 218.804 204.17 216.427 210.105 213.897C215.077 211.76 219.199 209.536 222.514 206.922C225.263 204.719 227.508 202.256 229.079 199.071C231.26 194.709 231.652 189.693 230.017 184.983C231.527 181.379 231.92 177.257 230.721 172.7ZM222.281 184.673C223.952 187.844 224.059 191.427 222.585 194.764C220.349 199.821 214.795 203.805 204.008 208.082C197.3 210.742 191.158 212.443 191.104 212.458C182.232 214.759 174.208 215.928 167.262 215.928C155.76 215.928 147.201 212.754 141.773 206.486C132.594 208.05 123.222 208.103 114.026 206.644C108.591 212.808 100.081 215.928 88.676 215.928C81.729 215.928 73.706 214.759 64.833 212.458C64.779 212.443 58.639 210.742 51.929 208.082C41.143 203.805 35.587 199.824 33.352 194.764C31.878 191.427 31.985 187.844 33.656 184.673C33.81 184.378 33.976 184.091 34.153 183.813C33.1516 182.309 32.4799 180.61 32.182 178.827C31.8842 177.045 31.967 175.22 32.425 173.472C33.089 170.949 34.46 168.851 36.322 167.344C35.425 165.87 34.8365 164.23 34.592 162.522C34.056 158.808 35.289 155.1 38.062 152.076C40.222 149.723 43.275 148.428 46.655 148.428H46.745C44.1965 140.259 42.9044 131.75 42.913 123.193C42.913 76.522 80.749 38.683 127.427 38.683C174.104 38.683 211.94 76.518 211.94 123.193C211.947 131.773 210.646 140.304 208.081 148.492C208.489 148.452 208.889 148.432 209.282 148.431C212.662 148.431 215.716 149.726 217.874 152.079C220.647 155.1 221.881 158.811 221.344 162.525C221.1 164.233 220.511 165.873 219.615 167.347C221.477 168.854 222.849 170.952 223.512 173.475C223.97 175.223 224.053 177.048 223.755 178.831C223.458 180.613 222.786 182.312 221.784 183.816C221.961 184.091 222.129 184.378 222.281 184.673Z" fill="white"/>
+ <path d="M221.784 183.816C222.786 182.312 223.458 180.613 223.756 178.831C224.053 177.048 223.97 175.223 223.512 173.475C222.848 170.952 221.476 168.854 219.615 167.347C220.512 165.873 221.1 164.233 221.344 162.525C221.881 158.811 220.648 155.103 217.874 152.079C215.716 149.726 212.662 148.431 209.282 148.431C208.889 148.431 208.489 148.452 208.081 148.492C210.643 140.304 211.942 131.774 211.933 123.195C211.933 76.5231 174.097 38.6851 127.424 38.6851C80.75 38.6851 42.9099 76.5191 42.9099 123.195C42.9015 131.752 44.1936 140.261 46.742 148.43H46.6519C43.2719 148.43 40.219 149.724 38.06 152.077C35.287 155.098 34.0529 158.81 34.5899 162.523C34.8346 164.231 35.4231 165.872 36.3199 167.346C34.4579 168.852 33.086 170.95 32.422 173.473C31.9642 175.222 31.8817 177.047 32.1799 178.83C32.4781 180.612 33.1501 182.312 34.1519 183.816C33.9739 184.094 33.8099 184.381 33.6549 184.676C31.9849 187.847 31.877 191.43 33.352 194.767C35.588 199.824 41.1419 203.808 51.9289 208.085C58.6359 210.745 64.779 212.446 64.833 212.461C73.705 214.762 81.729 215.931 88.675 215.931C100.081 215.931 108.591 212.811 114.026 206.647C123.222 208.106 132.594 208.052 141.773 206.489C147.201 212.757 155.76 215.931 167.262 215.931C174.208 215.931 182.232 214.762 191.103 212.461C191.158 212.446 197.298 210.745 204.008 208.085C214.795 203.808 220.35 199.824 222.585 194.767C224.059 191.43 223.952 187.847 222.281 184.676C222.129 184.379 221.961 184.091 221.784 183.816ZM110.137 196.997C109.669 197.815 109.168 198.614 108.635 199.391C107.23 201.448 105.382 203.02 103.237 204.188C99.1369 206.424 93.947 207.205 88.675 207.205C80.346 207.205 71.808 205.256 67.023 204.015C66.787 203.954 37.689 195.735 41.373 188.739C41.993 187.562 43.0129 187.092 44.2979 187.092C49.4849 187.092 58.9299 194.816 62.9889 194.816C63.8959 194.816 64.5359 194.43 64.7969 193.488C66.5269 187.284 38.5039 184.676 40.8639 175.692C41.2799 174.102 42.41 173.456 43.998 173.456C50.856 173.455 66.248 185.516 69.467 185.516C69.714 185.516 69.8909 185.443 69.9869 185.291C70.0009 185.268 70.015 185.246 70.028 185.222C71.539 182.727 70.6719 180.913 60.3209 174.573L59.3269 173.968C47.9359 167.074 39.9409 162.925 44.4879 157.975C45.0109 157.404 45.7529 157.151 46.6539 157.151C47.7219 157.151 49.0149 157.508 50.4389 158.108C56.4549 160.645 64.793 167.564 68.276 170.581C68.8239 171.057 69.3683 171.538 69.9089 172.022C69.9089 172.022 74.319 176.608 76.985 176.608C77.599 176.608 78.1199 176.366 78.4729 175.768C80.364 172.58 60.9099 157.838 59.8129 151.755C59.0689 147.634 60.3349 145.546 62.6749 145.546C63.7879 145.546 65.1459 146.02 66.6449 146.971C71.2949 149.922 80.2729 165.35 83.5599 171.352C84.6619 173.363 86.5429 174.213 88.2379 174.213C91.6009 174.213 94.2299 170.87 88.5459 166.622C80.0029 160.23 83.001 149.782 87.078 149.139C87.252 149.111 87.4279 149.097 87.6029 149.097C91.3109 149.097 92.9459 155.486 92.9459 155.486C92.9459 155.486 97.7399 167.524 105.975 175.753C113.447 183.222 114.491 189.351 110.137 196.997ZM136.766 198.407L136.339 198.458L135.611 198.541C135.228 198.581 134.844 198.619 134.459 198.654L134.084 198.688L133.741 198.717L133.255 198.756L132.718 198.795L132.182 198.83L132.063 198.838C131.923 198.846 131.783 198.855 131.641 198.862L131.462 198.872C131.296 198.881 131.13 198.889 130.962 198.896L130.381 198.921L129.854 198.939L129.502 198.949H129.323C129.213 198.949 129.104 198.955 128.994 198.956H128.82C128.71 198.956 128.601 198.956 128.491 198.961L128.043 198.967H127.418C126.927 198.967 126.437 198.962 125.949 198.952L125.553 198.943C125.44 198.943 125.327 198.938 125.216 198.934L124.796 198.922L124.275 198.902L123.805 198.881L123.684 198.876L123.237 198.853C123.112 198.846 122.989 198.84 122.865 198.831L122.576 198.814C122.213 198.791 121.85 198.766 121.487 198.738L121.107 198.707C120.947 198.695 120.787 198.68 120.628 198.666C120.441 198.65 120.254 198.632 120.067 198.614C119.754 198.585 119.441 198.553 119.128 198.519H119.113C123.683 188.324 121.372 178.802 112.137 169.575C106.08 163.526 102.051 154.594 101.215 152.633C99.5229 146.828 95.045 140.375 87.608 140.375C86.979 140.375 86.351 140.425 85.73 140.523C82.472 141.036 79.624 142.911 77.592 145.733C75.396 143.002 73.262 140.831 71.332 139.605C68.422 137.76 65.5179 136.824 62.6889 136.824C59.1579 136.824 56.0019 138.274 53.8019 140.904L53.7459 140.971C53.7039 140.798 53.6639 140.625 53.6229 140.451L53.6179 140.428C53.1992 138.638 52.8477 136.833 52.5639 135.016C52.5639 135.004 52.5639 134.992 52.5579 134.98C52.5359 134.843 52.5159 134.705 52.4949 134.568C52.4334 134.162 52.3757 133.755 52.3219 133.348C52.2979 133.163 52.2719 132.978 52.2489 132.793L52.1809 132.238C52.1589 132.053 52.1409 131.885 52.1209 131.709L52.115 131.665C52.0351 130.945 51.9651 130.225 51.9049 129.503L51.8829 129.226L51.8479 128.754C51.8379 128.625 51.8279 128.495 51.8209 128.365C51.8209 128.334 51.8159 128.304 51.8149 128.275C51.7895 127.913 51.7678 127.55 51.7499 127.187C51.7399 126.998 51.7299 126.81 51.7219 126.62L51.7019 126.124L51.6969 125.974L51.6809 125.517L51.6709 125.128C51.6709 124.973 51.6629 124.818 51.6609 124.663C51.6579 124.508 51.6539 124.338 51.6529 124.174C51.6509 124.01 51.6529 123.848 51.6479 123.685C51.6439 123.521 51.6479 123.358 51.6479 123.195C51.6479 81.3421 85.5789 47.4111 127.436 47.4111C169.292 47.4111 203.222 81.3411 203.222 123.195V124.174C203.222 124.337 203.217 124.501 203.214 124.663C203.214 124.798 203.208 124.931 203.204 125.068C203.204 125.188 203.199 125.309 203.195 125.425C203.195 125.578 203.186 125.731 203.181 125.884V125.896L203.16 126.427C203.153 126.582 203.147 126.738 203.139 126.893L203.134 127.003L203.107 127.499C203.048 128.562 202.967 129.623 202.866 130.683V130.696C202.849 130.87 202.832 131.044 202.813 131.218L202.768 131.629L202.679 132.433L202.628 132.84L202.565 133.319C202.542 133.493 202.519 133.668 202.493 133.841C202.467 134.036 202.438 134.23 202.409 134.424L202.34 134.883L202.258 135.403C202.23 135.576 202.2 135.748 202.168 135.92C202.135 136.093 202.109 136.265 202.079 136.437C202.019 136.781 201.956 137.125 201.89 137.468C201.789 137.981 201.686 138.493 201.58 139.005L201.47 139.512C201.434 139.681 201.395 139.851 201.357 140.02C199.224 137.947 196.399 136.818 193.284 136.818C190.457 136.818 187.55 137.753 184.641 139.598C182.711 140.824 180.578 142.996 178.381 145.726C176.346 142.904 173.498 141.029 170.242 140.516C169.621 140.418 168.993 140.368 168.364 140.368C160.925 140.368 156.45 146.821 154.757 152.626C153.917 154.587 149.887 163.519 143.825 169.577C134.596 178.775 132.268 188.254 136.766 198.407ZM215.007 177.998L214.977 178.087C214.901 178.288 214.813 178.484 214.714 178.674C214.639 178.814 214.558 178.95 214.47 179.082C214.303 179.331 214.12 179.569 213.921 179.793C213.875 179.845 213.831 179.897 213.779 179.948C213.707 180.025 213.634 180.101 213.559 180.175C212.213 181.509 210.161 182.679 207.841 183.752C207.578 183.871 207.311 183.99 207.042 184.11L206.774 184.229C206.595 184.308 206.416 184.386 206.228 184.463C206.049 184.541 205.863 184.619 205.677 184.695L205.119 184.925C203.814 185.462 202.477 185.974 201.173 186.479L200.615 186.696L200.064 186.912C199.697 187.055 199.335 187.198 198.979 187.341L198.448 187.555L197.926 187.768L197.67 187.876C197.499 187.947 197.332 188.018 197.165 188.089C193.328 189.736 190.567 191.411 191.147 193.489C191.163 193.548 191.181 193.604 191.201 193.659C191.253 193.813 191.324 193.958 191.413 194.095C191.465 194.176 191.525 194.253 191.592 194.323C192.274 195.032 193.515 194.92 195.08 194.357C195.3 194.276 195.519 194.192 195.736 194.104L195.872 194.048C196.23 193.896 196.609 193.726 196.996 193.542C197.093 193.496 197.191 193.452 197.289 193.401C199.203 192.465 201.372 191.205 203.524 190.058C204.385 189.593 205.258 189.152 206.142 188.733C208.18 187.774 210.096 187.094 211.636 187.094C212.359 187.094 212.997 187.242 213.529 187.582L213.618 187.641C213.952 187.876 214.232 188.178 214.441 188.528C214.482 188.595 214.522 188.666 214.561 188.739C215.322 190.184 214.685 191.68 213.194 193.147C211.763 194.556 209.537 195.937 207.007 197.215C206.819 197.31 206.631 197.405 206.44 197.498C198.91 201.196 189.049 203.981 188.912 204.016C186.284 204.697 182.526 205.591 178.292 206.26L177.666 206.358L177.563 206.373C177.089 206.445 176.614 206.512 176.138 206.574C175.655 206.639 175.167 206.698 174.676 206.753L174.586 206.763C172.806 206.968 171.019 207.104 169.228 207.169H169.202C168.554 207.192 167.907 207.204 167.259 207.204H166.512C165.524 207.191 164.538 207.146 163.553 207.07C163.53 207.07 163.505 207.07 163.482 207.064C163.129 207.037 162.777 207.004 162.425 206.965C162.06 206.926 161.696 206.882 161.333 206.833C161.094 206.801 160.856 206.765 160.618 206.726C160.376 206.687 160.134 206.647 159.893 206.605L159.564 206.543L159.539 206.538C159.192 206.472 158.847 206.399 158.503 206.319C158.303 206.274 158.104 206.23 157.907 206.176L157.788 206.146C157.69 206.122 157.595 206.096 157.498 206.07L157.445 206.056L157.137 205.966C157.025 205.935 156.913 205.901 156.801 205.868L156.762 205.857L156.471 205.768C156.361 205.734 156.251 205.698 156.142 205.662L155.874 205.573L155.677 205.504C155.487 205.437 155.298 205.368 155.111 205.296L154.933 205.226L154.786 205.168C154.502 205.054 154.22 204.935 153.941 204.81L153.756 204.72L153.725 204.706C153.659 204.675 153.594 204.644 153.528 204.617C153.399 204.555 153.271 204.491 153.144 204.426L153.105 204.407L152.921 204.31C152.594 204.139 152.274 203.957 151.96 203.764L151.788 203.658C151.702 203.605 151.616 203.55 151.532 203.494L151.308 203.346L151.067 203.18L150.923 203.077C150.771 202.969 150.622 202.857 150.476 202.742L150.243 202.563C150.15 202.488 150.058 202.412 149.967 202.335C149.89 202.272 149.815 202.206 149.74 202.14L149.734 202.135C149.653 202.064 149.574 201.993 149.495 201.92C149.417 201.849 149.339 201.777 149.263 201.704L149.254 201.695C149.174 201.619 149.096 201.542 149.019 201.463C148.942 201.385 148.863 201.307 148.788 201.227C148.713 201.148 148.636 201.067 148.562 200.984C148.488 200.902 148.42 200.827 148.35 200.746L148.327 200.719C148.259 200.641 148.192 200.562 148.126 200.481C147.983 200.31 147.844 200.135 147.71 199.956C147.575 199.776 147.443 199.592 147.314 199.405L147.191 199.221C147.027 198.981 146.867 198.739 146.712 198.493C146.596 198.316 146.483 198.138 146.373 197.957C146.302 197.844 146.234 197.73 146.166 197.618L146.138 197.572C146.073 197.462 146.009 197.354 145.947 197.245C145.911 197.186 145.877 197.127 145.845 197.066C145.812 197.004 145.774 196.941 145.739 196.878L145.682 196.779L145.647 196.715C145.58 196.595 145.514 196.474 145.45 196.352C145.42 196.298 145.391 196.244 145.36 196.192L145.271 196.019L145.181 195.848C144.956 195.398 144.743 194.942 144.543 194.48L144.472 194.311C144.426 194.198 144.383 194.086 144.337 193.975C144.315 193.921 144.293 193.868 144.274 193.814C144.167 193.537 144.067 193.257 143.975 192.975C143.942 192.874 143.91 192.775 143.88 192.675C143.808 192.448 143.743 192.219 143.685 191.988C143.614 191.719 143.551 191.448 143.498 191.175C143.487 191.12 143.476 191.065 143.467 191.012C143.415 190.745 143.373 190.476 143.34 190.206C143.332 190.153 143.326 190.1 143.32 190.047L143.303 189.885C143.281 189.673 143.264 189.46 143.254 189.247C143.254 189.193 143.249 189.139 143.247 189.087C143.242 188.981 143.24 188.875 143.239 188.769C143.183 184.496 145.345 180.388 149.968 175.767C158.203 167.54 162.997 155.501 162.997 155.501C162.997 155.501 163.126 154.996 163.394 154.269C163.431 154.168 163.47 154.064 163.514 153.955C163.67 153.548 163.846 153.148 164.041 152.758L164.08 152.683C164.246 152.351 164.428 152.027 164.624 151.712C164.67 151.639 164.714 151.567 164.765 151.494C164.912 151.277 165.067 151.065 165.23 150.86C165.319 150.749 165.416 150.639 165.513 150.532C165.552 150.49 165.59 150.448 165.631 150.408C166.108 149.915 166.653 149.513 167.27 149.299L167.348 149.273C167.4 149.256 167.452 149.24 167.505 149.225C167.566 149.209 167.627 149.195 167.69 149.182L167.719 149.176C167.849 149.15 167.981 149.133 168.114 149.124H168.125C168.194 149.124 168.264 149.117 168.335 149.117C168.424 149.117 168.507 149.117 168.594 149.126C168.684 149.134 168.773 149.144 168.863 149.158C169.605 149.276 170.311 149.718 170.919 150.4C171.15 150.66 171.358 150.94 171.54 151.236C171.66 151.428 171.773 151.631 171.88 151.845C171.923 151.934 171.964 152.016 172.004 152.104C172.108 152.33 172.202 152.56 172.284 152.795C172.479 153.345 172.626 153.911 172.723 154.487C172.807 154.992 172.857 155.502 172.873 156.013C172.881 156.286 172.881 156.563 172.873 156.842C172.819 158.14 172.553 159.421 172.086 160.634C172.044 160.745 171.997 160.857 171.952 160.969C171.86 161.195 171.759 161.417 171.65 161.634C171.569 161.799 171.484 161.965 171.392 162.13C171.332 162.24 171.269 162.35 171.206 162.46C171.045 162.734 170.871 163.006 170.684 163.277L170.571 163.439C170.129 164.055 169.637 164.633 169.099 165.167C168.569 165.698 168.001 166.189 167.4 166.637C166.798 167.083 166.233 167.577 165.711 168.114C164.208 169.691 163.858 171.083 164.196 172.138C164.25 172.304 164.321 172.465 164.407 172.617C164.508 172.791 164.628 172.951 164.764 173.097L164.817 173.152L164.871 173.206C164.925 173.258 164.982 173.309 165.043 173.359L165.103 173.407C165.248 173.519 165.402 173.619 165.563 173.707C165.61 173.732 165.652 173.757 165.705 173.781C165.879 173.866 166.058 173.939 166.242 173.998C166.293 174.015 166.344 174.03 166.396 174.046L166.461 174.063L166.551 174.087L166.628 174.106L166.712 174.124L166.795 174.141L166.874 174.154C166.932 174.164 166.992 174.174 167.052 174.181L167.109 174.19L167.213 174.2L167.277 174.207L167.382 174.214H167.444L167.554 174.22H167.9L167.999 174.214L168.113 174.207L168.252 174.194L168.382 174.179C168.412 174.179 168.442 174.171 168.472 174.165C168.872 174.107 169.264 174.001 169.639 173.849L169.798 173.782C169.887 173.743 169.977 173.702 170.059 173.658C170.235 173.57 170.406 173.47 170.57 173.361C170.799 173.211 171.015 173.043 171.217 172.858C171.265 172.815 171.312 172.769 171.358 172.725C171.381 172.703 171.403 172.682 171.425 172.658C171.469 172.613 171.514 172.569 171.558 172.52C171.878 172.168 172.155 171.78 172.383 171.363C174.34 167.804 176.391 164.298 178.534 160.849L178.828 160.378L179.125 159.907C179.273 159.668 179.423 159.433 179.572 159.199L179.722 158.965C180.22 158.185 180.726 157.41 181.241 156.641L181.546 156.185C182.158 155.278 182.768 154.396 183.373 153.558L183.674 153.143C184.332 152.236 185.017 151.348 185.728 150.482L186.01 150.144C186.057 150.088 186.1 150.032 186.151 149.978C186.244 149.868 186.337 149.761 186.428 149.657C186.474 149.604 186.517 149.552 186.566 149.5L186.834 149.198L186.968 149.051C187.103 148.906 187.235 148.767 187.365 148.634C187.455 148.544 187.538 148.455 187.624 148.371C188.131 147.853 188.69 147.388 189.293 146.985L189.433 146.895C189.567 146.805 189.706 146.721 189.848 146.645C192.212 145.303 194.169 145.204 195.296 146.331C195.978 147.013 196.356 148.144 196.335 149.718C196.335 149.787 196.335 149.857 196.33 149.929V150.006C196.33 150.078 196.324 150.15 196.318 150.223C196.318 150.313 196.308 150.402 196.299 150.492C196.29 150.581 196.285 150.649 196.276 150.729C196.276 150.751 196.272 150.774 196.268 150.798C196.262 150.867 196.253 150.938 196.243 151.009C196.243 151.03 196.243 151.052 196.235 151.074C196.224 151.169 196.21 151.263 196.194 151.357C196.183 151.447 196.168 151.531 196.152 151.619L196.126 151.768C196.1 151.91 196.067 152.05 196.026 152.188C195.948 152.447 195.854 152.7 195.743 152.946C195.588 153.284 195.417 153.613 195.229 153.933C195.125 154.111 195.018 154.286 194.907 154.459C194.793 154.638 194.673 154.819 194.549 155.002C194.233 155.454 193.905 155.897 193.564 156.33L193.408 156.527C192.852 157.22 192.278 157.899 191.686 158.562L191.499 158.772C191.247 159.053 190.991 159.336 190.729 159.62L190.532 159.834C190.401 159.977 190.264 160.12 190.132 160.264C190.001 160.407 189.864 160.552 189.726 160.697L189.315 161.13L188.898 161.566L188.478 162.002C188.196 162.294 187.913 162.586 187.628 162.878C183.573 167.037 179.301 171.182 177.855 173.766C177.758 173.934 177.671 174.108 177.593 174.285C177.387 174.755 177.301 175.157 177.36 175.482C177.379 175.589 177.416 175.691 177.471 175.785C177.552 175.926 177.651 176.056 177.766 176.172C177.819 176.224 177.875 176.272 177.934 176.316C178.232 176.528 178.591 176.637 178.957 176.627H179.071L179.188 176.618L179.305 176.605L179.402 176.591C179.415 176.589 179.429 176.587 179.442 176.583L179.531 176.566L179.554 176.561L179.653 176.54L179.688 176.531C179.723 176.522 179.757 176.513 179.792 176.503C179.827 176.493 179.875 176.48 179.917 176.466C180.093 176.413 180.265 176.35 180.434 176.278C180.523 176.242 180.61 176.203 180.696 176.161C180.741 176.141 180.786 176.12 180.828 176.098L180.962 176.032C181.282 175.866 181.594 175.685 181.898 175.491L182.031 175.401C182.076 175.373 182.121 175.344 182.164 175.312L182.297 175.223L182.368 175.174L182.56 175.039C182.739 174.916 182.906 174.789 183.075 174.66L183.09 174.648L183.359 174.44C183.726 174.15 184.074 173.858 184.39 173.583L184.6 173.399L184.619 173.381L184.729 173.284C184.987 173.052 185.217 172.836 185.408 172.658L185.487 172.581C185.556 172.516 185.619 172.455 185.676 172.403L185.788 172.292L185.828 172.253L185.839 172.242L185.956 172.125L186.03 172.048L186.039 172.041L186.074 172.009L186.118 171.969L186.132 171.956L186.169 171.922L186.373 171.743L186.487 171.641C186.548 171.588 186.607 171.534 186.666 171.479L186.802 171.358C186.827 171.338 186.851 171.316 186.876 171.294L187.019 171.169L187.229 170.984L187.341 170.887C187.776 170.509 188.305 170.052 188.913 169.537L189.162 169.326L189.573 168.981L189.994 168.63C190.544 168.173 191.136 167.688 191.762 167.185L192.173 166.855C192.523 166.576 192.882 166.292 193.246 166.006C193.393 165.891 193.542 165.776 193.694 165.662C194.066 165.373 194.44 165.086 194.817 164.803C195.675 164.155 196.56 163.506 197.456 162.874L197.84 162.606C198.109 162.421 198.377 162.235 198.645 162.054L198.888 161.89C199.367 161.565 199.853 161.248 200.343 160.939L200.586 160.786L200.827 160.636C201.069 160.486 201.309 160.339 201.548 160.196L201.787 160.053L202.265 159.775L202.734 159.506L202.829 159.454L203.2 159.25C203.355 159.166 203.509 159.085 203.663 159.006L203.892 158.888L204.115 158.776C204.193 158.739 204.27 158.7 204.346 158.663C204.848 158.415 205.36 158.187 205.88 157.979C206.021 157.919 206.161 157.865 206.3 157.818L206.71 157.674C206.833 157.633 206.953 157.594 207.068 157.559L207.108 157.547C207.17 157.527 207.232 157.509 207.293 157.493L207.311 157.488C207.439 157.451 207.566 157.419 207.691 157.389H207.7C208.054 157.304 208.414 157.243 208.777 157.206C208.944 157.189 209.111 157.18 209.279 157.181H209.363C209.475 157.181 209.583 157.188 209.69 157.199C209.739 157.199 209.788 157.209 209.836 157.215H209.856C209.904 157.221 209.952 157.228 210 157.239C210.047 157.248 210.095 157.256 210.141 157.267H210.156C210.203 157.277 210.245 157.289 210.294 157.303C210.548 157.374 210.79 157.484 211.012 157.628C211.121 157.699 211.223 157.779 211.317 157.868L211.344 157.894C211.362 157.91 211.379 157.927 211.395 157.944L211.444 157.997C211.846 158.418 212.178 158.901 212.428 159.427L212.466 159.517C212.551 159.717 212.618 159.924 212.666 160.135C212.808 160.781 212.753 161.455 212.508 162.07C212.415 162.318 212.302 162.557 212.169 162.785C211.858 163.309 211.489 163.796 211.07 164.237L210.981 164.332C210.848 164.472 210.71 164.612 210.565 164.752C210.501 164.815 210.434 164.877 210.367 164.94L210.162 165.129L210.055 165.224C209.797 165.454 209.532 165.677 209.263 165.893C209.1 166.025 208.936 166.154 208.77 166.281C208.184 166.729 207.587 167.161 206.979 167.578C206.612 167.83 206.242 168.077 205.869 168.321C204.95 168.924 204.021 169.512 203.083 170.084C201.115 171.294 198.934 172.588 196.609 173.995L196.007 174.36C195.348 174.762 194.726 175.146 194.14 175.512L193.845 175.697L193.287 176.055C192.917 176.292 192.548 176.531 192.179 176.77L191.882 176.966C191.737 177.06 191.593 177.156 191.449 177.252L191.308 177.342L190.876 177.633L190.647 177.79L190.379 177.976L190.13 178.149C189.713 178.444 189.325 178.725 188.968 178.992L188.834 179.094C188.624 179.253 188.416 179.415 188.211 179.58C187.902 179.829 187.62 180.067 187.367 180.296L187.243 180.409C187.172 180.474 187.102 180.539 187.035 180.603C186.989 180.648 186.946 180.693 186.898 180.736L186.834 180.8C186.691 180.944 186.551 181.091 186.416 181.242L186.35 181.318C186.203 181.488 186.075 181.651 185.963 181.81L185.913 181.881C185.825 182.009 185.744 182.141 185.671 182.277C185.652 182.311 185.635 182.345 185.618 182.379L185.569 182.481L185.536 182.555L185.515 182.605L185.498 182.65L185.475 182.711C185.413 182.88 185.37 183.056 185.345 183.234L185.337 183.296L185.331 183.354V183.669C185.331 183.695 185.331 183.721 185.338 183.749L185.343 183.797C185.343 183.823 185.349 183.848 185.353 183.876C185.357 183.902 185.364 183.949 185.372 183.986V183.991C185.379 184.026 185.386 184.06 185.395 184.095C185.404 184.13 185.413 184.17 185.424 184.206C185.443 184.277 185.467 184.347 185.492 184.417C185.508 184.459 185.523 184.5 185.54 184.541C185.54 184.549 185.546 184.558 185.55 184.566L185.586 184.647L185.636 184.758C185.69 184.873 185.749 184.985 185.813 185.094L185.879 185.208L185.947 185.322C185.959 185.341 185.973 185.359 185.988 185.376L186.01 185.399L186.035 185.422L186.061 185.442C186.099 185.469 186.14 185.49 186.183 185.505C186.206 185.513 186.23 185.519 186.254 185.525C186.831 185.655 188.017 185.178 189.593 184.346C189.682 184.298 189.78 184.248 189.875 184.196L190.355 183.934L190.589 183.804C190.756 183.715 190.926 183.614 191.1 183.515L191.417 183.336C193.5 182.137 195.988 180.597 198.56 179.093C198.801 178.952 199.043 178.811 199.285 178.672L199.771 178.361C200.335 178.038 200.902 177.719 201.471 177.404C202.188 177.01 202.91 176.626 203.639 176.254L204.115 176.013C204.431 175.857 204.744 175.705 205.053 175.557C205.651 175.273 206.256 175.003 206.868 174.748L207.203 174.612L207.243 174.596C209.018 173.893 210.627 173.459 211.929 173.459C212.21 173.456 212.492 173.48 212.769 173.528H212.778C212.867 173.544 212.948 173.562 213.031 173.582H213.046C213.259 173.636 213.466 173.713 213.662 173.812C213.937 173.954 214.184 174.143 214.393 174.371C214.489 174.477 214.574 174.592 214.649 174.714C214.789 174.929 214.899 175.162 214.978 175.406C215.01 175.501 215.038 175.594 215.067 175.693C215.278 176.45 215.257 177.253 215.007 177.998Z" fill="#FF9D00"/>
+ <path fill-rule="evenodd" clip-rule="evenodd" d="M203.21 123.685V123.194C203.21 81.34 169.292 47.411 127.435 47.411C85.5791 47.411 51.648 81.342 51.648 123.194V123.358C51.646 123.467 51.645 123.576 51.648 123.685C51.6529 123.848 51.6546 124.011 51.653 124.174L51.6581 124.534L51.661 124.663C51.661 124.723 51.6631 124.782 51.6651 124.842C51.6681 124.937 51.67 125.033 51.67 125.128L51.681 125.517L51.697 125.974L51.702 126.124L51.722 126.597V126.62C51.73 126.805 51.7401 126.989 51.7491 127.173L51.75 127.187C51.76 127.375 51.7701 127.564 51.7821 127.753C51.7921 127.927 51.802 128.101 51.815 128.275L51.8171 128.306C51.8258 128.455 51.8358 128.605 51.847 128.754L51.85 128.794L51.883 129.226L51.8861 129.254C51.8921 129.338 51.898 129.422 51.906 129.503C51.9658 130.224 52.0355 130.945 52.1151 131.664L52.12 131.709L52.181 132.238L52.2491 132.793L52.299 133.17L52.322 133.347C52.3753 133.755 52.433 134.162 52.495 134.568L52.4991 134.595L52.558 134.979C52.8435 136.808 53.1971 138.626 53.618 140.429L53.6231 140.451L53.655 140.586L53.746 140.971L53.802 140.904C56.002 138.274 59.158 136.824 62.689 136.824C65.519 136.824 68.4221 137.76 71.3321 139.605C73.2621 140.831 75.3961 143.002 77.5921 145.733C79.6241 142.911 82.4721 141.035 85.7301 140.523C86.3513 140.425 86.9792 140.376 87.6081 140.375C95.0441 140.375 99.523 146.828 101.215 152.633C102.051 154.594 106.08 163.526 112.156 169.568C121.392 178.795 123.703 188.316 119.132 198.511H119.148C119.459 198.546 119.772 198.578 120.087 198.607C120.274 198.625 120.46 198.643 120.648 198.659L120.714 198.665L121.127 198.7L121.507 198.73C121.869 198.758 122.232 198.784 122.596 198.807L122.885 198.824L123.114 198.838L123.256 198.846L123.703 198.869L123.825 198.874L124.294 198.895L124.816 198.915L125.235 198.927L125.305 198.929C125.394 198.933 125.483 198.936 125.572 198.936L125.668 198.939C126.258 198.953 126.847 198.96 127.437 198.959H128.063L128.51 198.954C128.62 198.949 128.729 198.949 128.84 198.949H129.014L129.165 198.945C129.224 198.943 129.283 198.941 129.343 198.941H129.522L129.873 198.932L130.401 198.914L130.982 198.888C131.15 198.882 131.316 198.873 131.482 198.865L131.661 198.854L131.927 198.84L132.083 198.831L132.201 198.823L132.738 198.788L133.274 198.749L133.761 198.71L134.103 198.681L134.479 198.647C135.107 198.591 135.733 198.525 136.359 198.45L136.786 198.399C132.287 188.247 134.616 178.767 143.813 169.577C149.876 163.519 153.905 154.587 154.745 152.625C156.438 146.821 160.914 140.368 168.352 140.368C168.981 140.368 169.61 140.418 170.231 140.516C173.486 141.028 176.334 142.904 178.369 145.726C180.566 142.996 182.699 140.823 184.63 139.597C187.539 137.753 190.445 136.817 193.272 136.817C196.388 136.817 199.212 137.947 201.345 140.02C201.384 139.851 201.422 139.682 201.459 139.512L201.568 139.006C201.607 138.821 201.646 138.636 201.683 138.451C201.749 138.124 201.815 137.797 201.878 137.467C201.944 137.125 202.007 136.781 202.067 136.437L202.098 136.251C202.117 136.141 202.135 136.031 202.156 135.92C202.19 135.748 202.218 135.576 202.246 135.402L202.257 135.336L202.328 134.883L202.398 134.424V134.42C202.449 134.081 202.497 133.742 202.542 133.403L202.553 133.319L202.616 132.841L202.667 132.433L202.757 131.629L202.792 131.306L202.801 131.218C202.82 131.044 202.838 130.87 202.854 130.696V130.682C202.867 130.544 202.881 130.405 202.893 130.266C202.964 129.478 203.024 128.686 203.072 127.891C203.081 127.761 203.088 127.63 203.096 127.499V127.493L203.122 127.002L203.128 126.892C203.144 126.56 203.158 126.228 203.169 125.896V125.884L203.174 125.754C203.179 125.645 203.183 125.535 203.183 125.425L203.185 125.381C203.189 125.278 203.193 125.172 203.193 125.067L203.196 124.977C203.199 124.872 203.202 124.768 203.202 124.663L203.204 124.574C203.207 124.441 203.21 124.307 203.21 124.174V123.685ZM108.638 199.391C114.64 190.59 114.214 183.984 105.98 175.754C97.7441 167.523 92.951 155.487 92.951 155.487C92.951 155.487 91.1621 148.496 87.0821 149.138C83.0021 149.78 80.0091 160.227 88.5521 166.622C97.0941 173.017 86.8521 177.353 83.5641 171.352C80.2761 165.35 71.299 149.923 66.645 146.972C61.991 144.021 58.718 145.675 59.815 151.757C60.36 154.776 65.4281 159.929 70.1631 164.743C74.9671 169.627 79.428 174.163 78.474 175.768C76.581 178.955 69.9141 172.023 69.9141 172.023C69.9141 172.023 49.038 153.025 44.494 157.976C40.304 162.539 46.765 166.418 56.7211 172.397C57.5671 172.905 58.4391 173.429 59.3321 173.969C70.7231 180.865 71.609 182.684 69.992 185.293C69.395 186.257 65.582 183.968 60.892 181.153C52.897 176.352 42.3551 170.023 40.8661 175.688C39.5781 180.591 47.334 183.595 54.368 186.32C60.228 188.59 65.5881 190.666 64.7991 193.484C63.9821 196.406 59.5531 193.969 54.7121 191.305C49.2771 188.314 43.3221 185.038 41.3731 188.735C37.6901 195.725 66.7831 203.954 67.0231 204.015C76.4231 206.453 100.295 211.619 108.638 199.391ZM147.303 199.391C141.301 190.59 141.727 183.984 149.962 175.754C158.197 167.523 162.99 155.487 162.99 155.487C162.99 155.487 164.779 148.496 168.859 149.138C172.939 149.78 175.932 160.227 167.39 166.622C158.847 173.017 169.089 177.353 172.377 171.352C175.666 165.35 184.637 149.923 189.291 146.972C193.945 144.021 197.22 145.675 196.122 151.757C195.578 154.776 190.509 159.929 185.774 164.744C180.97 169.628 176.509 174.163 177.462 175.768C179.355 178.955 186.027 172.019 186.027 172.019C186.027 172.019 206.902 153.022 211.448 157.973C215.637 162.535 209.176 166.415 199.219 172.394C198.348 172.917 197.478 173.441 196.609 173.966C185.218 180.862 184.332 182.681 185.948 185.289C186.546 186.254 190.359 183.964 195.048 181.149C203.044 176.349 213.586 170.019 215.075 175.685C216.364 180.588 208.607 183.592 201.573 186.317C195.713 188.587 190.353 190.663 191.141 193.481C191.957 196.402 196.385 193.965 201.225 191.301C206.66 188.31 212.616 185.032 214.564 188.732C218.248 195.726 189.15 203.947 188.915 204.007C179.515 206.453 155.643 211.619 147.303 199.391Z" fill="#FFD21E"/>
+ <path fill-rule="evenodd" clip-rule="evenodd" d="M152.047 102.567C153.229 102.985 154.108 104.257 154.944 105.468C156.074 107.104 157.126 108.627 158.74 107.769C160.644 106.756 162.205 105.202 163.225 103.302C164.246 101.402 164.681 99.2427 164.475 97.096C164.321 95.4908 163.813 93.9398 162.987 92.5548C162.161 91.1697 161.038 89.985 159.7 89.0862C158.361 88.1874 156.839 87.5968 155.245 87.3569C153.65 87.117 152.022 87.2339 150.478 87.699C148.934 88.1639 147.513 88.9653 146.316 90.0455C145.119 91.1257 144.176 92.4578 143.556 93.946C142.936 95.4342 142.653 97.0415 142.728 98.652C142.804 100.263 143.235 101.836 143.992 103.26C144.74 104.667 146.4 104.003 148.152 103.302C149.525 102.753 150.956 102.181 152.047 102.567ZM100.672 102.567C99.49 102.985 98.611 104.258 97.775 105.468C96.645 107.105 95.592 108.627 93.979 107.769C91.5845 106.501 89.7482 104.386 88.8278 101.838C87.9075 99.2895 87.9692 96.4896 89.0008 93.9841C90.0324 91.4786 91.9601 89.4471 94.408 88.2855C96.856 87.1239 99.6488 86.9156 102.242 87.701C104.307 88.3228 106.141 89.5427 107.513 91.2065C108.885 92.8704 109.732 94.9035 109.949 97.049C110.165 99.1945 109.74 101.356 108.728 103.26C107.979 104.667 106.319 104.003 104.567 103.303C103.193 102.753 101.764 102.181 100.672 102.567ZM144.099 149.318C152.242 142.903 155.233 132.429 155.233 125.977C155.233 120.877 151.802 122.482 146.309 125.202L145.999 125.355C140.957 127.852 134.245 131.177 126.877 131.177C119.508 131.177 112.796 127.852 107.755 125.354C102.084 122.545 98.527 120.783 98.527 125.978C98.527 132.634 101.709 143.563 110.443 149.912C111.596 147.573 113.219 145.497 115.211 143.813C117.202 142.129 119.52 140.874 122.018 140.126C122.89 139.866 123.788 141.367 124.707 142.904C125.594 144.386 126.501 145.902 127.423 145.902C128.406 145.902 129.371 144.408 130.314 142.95C131.299 141.425 132.26 139.94 133.189 140.237C137.864 141.738 141.775 144.993 144.099 149.318Z" fill="#32343D"/>
+ <path d="M144.097 149.317C139.856 152.659 134.219 154.9 126.878 154.9C119.981 154.9 114.587 152.922 110.443 149.911C111.596 147.572 113.219 145.495 115.211 143.812C117.202 142.128 119.52 140.873 122.018 140.125C123.73 139.614 125.545 145.901 127.423 145.901C129.433 145.901 131.37 139.655 133.189 140.236C137.863 141.738 141.773 144.993 144.097 149.317Z" fill="#FF323D"/>
+ <path fill-rule="evenodd" clip-rule="evenodd" d="M81.2 111.64C80.2312 112.288 79.1173 112.687 77.9572 112.801C76.7971 112.916 75.6267 112.742 74.55 112.295C73.6893 111.94 72.9072 111.418 72.2488 110.759C71.5903 110.101 71.0684 109.319 70.713 108.458C70.267 107.381 70.0935 106.211 70.2082 105.051C70.3228 103.891 70.7219 102.777 71.37 101.808C72.1488 100.642 73.2558 99.7333 74.5512 99.1967C75.8466 98.6601 77.272 98.5197 78.6471 98.7935C80.0223 99.0672 81.2853 99.7427 82.2764 100.734C83.2675 101.726 83.9422 102.99 84.215 104.365C84.4883 105.74 84.3477 107.165 83.8113 108.46C83.2748 109.755 82.3654 110.861 81.2 111.64ZM182.613 111.64C181.644 112.288 180.53 112.687 179.37 112.801C178.209 112.916 177.039 112.742 175.962 112.295C175.101 111.939 174.319 111.418 173.661 110.759C173.003 110.101 172.481 109.319 172.125 108.458C171.68 107.381 171.507 106.211 171.621 105.051C171.736 103.891 172.135 102.777 172.782 101.808C173.364 100.936 174.133 100.205 175.032 99.6658C175.931 99.1269 176.938 98.7942 177.981 98.6917C179.025 98.5891 180.078 98.7193 181.064 99.0728C182.051 99.4264 182.947 99.9944 183.688 100.736C184.68 101.727 185.355 102.99 185.628 104.365C185.902 105.74 185.761 107.165 185.224 108.46C184.687 109.755 183.779 110.861 182.613 111.64Z" fill="#FFAD03"/>
+ </svg>
+ }
+ iconType="duotone"
+ >
+ </Card>
+</CardGroup>
+
+### VectorDBs
+<CardGroup cols={2}>
+ <Card
+ title="ChromaDB"
+ href="/latest/integrations/chromadb"
+ icon={
+ <svg viewBox="0 0 256 296" version="1.1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" preserveAspectRatio="xMidYMid">
+ <title>Chroma</title>
+ <g>
+ <ellipse fill="#FFDE2D" cx="170.666795" cy="81.9198362" rx="85.3332053" ry="81.9198362"></ellipse>
+ <ellipse fill="#327EFF" cx="85.3332053" cy="81.9198362" rx="85.3332053" ry="81.9198362"></ellipse>
+ <path d="M170.666795,81.9199642 C170.666795,127.163394 132.461431,163.83916 85.3330773,163.83916 L85.3330773,81.9199642 L170.666795,81.9199642 Z M85.3332053,81.9198362 C85.3332053,36.6767906 123.538185,8.95998209e-05 170.666795,8.95998209e-05 L170.666795,81.9198362 L85.3332053,81.9198362 Z" fill="#FF6446"></path>
+ </g>
+ </svg>
+ }
+ iconType="duotone"
+ >
+ </Card>
+ <Card
+ title="Pinecone"
+ href="/latest/integrations/pinecone"
+ icon={
+ <svg viewBox="0 0 256 288" version="1.1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" preserveAspectRatio="xMidYMid">
+ <title>Pinecone</title>
+ <g>
+ <path d="M108.633615,254.43629 C117.713862,254.43629 125.074857,261.797284 125.074857,270.877532 C125.074857,279.957779 117.713862,287.318774 108.633615,287.318774 C99.5533677,287.318774 92.1923728,279.957779 92.1923728,270.877532 C92.1923728,261.797284 99.5533677,254.43629 108.633615,254.43629 Z M199.849665,224.438339 L216.09705,229.252379 L203.199913,272.780219 C202.072982,276.58361 198.458049,279.095992 194.500389,278.826397 L190.516677,278.552973 L190.419263,278.633409 L149.02918,275.728903 L150.180842,258.822508 L177.989056,260.709686 L159.783784,234.447622 L173.709616,224.792379 L191.938895,251.08702 L199.849665,224.438339 Z M23.0126771,194.347476 L39.9158866,195.544979 L37.935897,223.348728 L64.1501315,205.120082 L73.8271476,219.030793 L47.578736,237.278394 L74.3707554,245.173037 L69.5818063,261.427835 L25.8485266,248.543243 C22.0304448,247.418369 19.5101155,243.787479 19.7913963,239.817092 L23.0126771,194.347476 Z M132.151306,170.671396 L162.658679,207.503468 L148.909247,218.891886 L130.753266,196.972134 L124.866941,230.673893 L107.280249,227.599613 L113.172232,193.845272 L88.7296311,208.256891 L79.6674587,192.874434 L120.745504,168.674377 C124.522104,166.449492 129.355297,167.295726 132.151306,170.671396 Z M217.504528,145.960198 L232.744017,137.668804 L254.94482,178.473633 C256.889641,182.048192 256.088221,186.494171 253.017682,189.164674 L249.876622,191.878375 L217.826246,219.77131 L206.441034,206.680621 L227.988588,187.934494 L195.893546,182.152609 L198.972402,165.078949 L231.044844,170.857793 L217.504528,145.960198 Z M37.7821805,103.299272 L49.2622123,116.306888 L28.0106317,135.050179 L60.1668233,140.664193 L57.1863573,157.755303 L24.9947229,152.136967 L38.822104,177.134576 L23.6411026,185.532577 L1.08439616,144.756992 C-0.885025494,141.196884 -0.115545265,136.746375 2.93488097,134.054184 L37.7821805,103.299272 Z M146.476311,89.8796828 L176.88045,126.612847 L163.1271,137.996532 L144.975445,116.067101 L139.08912,149.778947 L121.502428,146.704666 L127.374238,113.081452 L103.025237,127.354817 L93.9976317,111.952048 L131.398812,90.0233663 L131.435631,89.880899 L131.600545,89.9023265 L135.085833,87.870141 C138.861877,85.6569913 143.68556,86.5079996 146.476311,89.8796828 Z M185.655786,71.8143168 L192.305535,55.7902703 L235.318239,73.6399229 C239.072486,75.1978811 241.2415,79.1537636 240.536356,83.1568091 L239.820231,87.1385839 L232.47517,128.919545 L215.389188,125.909819 L220.312646,97.9413879 L191.776157,113.7129 L183.390302,98.5251862 L211.981072,82.7408038 L185.655786,71.8143168 Z M103.71696,40.2373824 L104.456513,57.5706533 L76.0432671,58.785006 L97.4730368,83.2749086 L84.4165529,94.6993319 L62.9507932,70.1728358 L57.949673,98.1737132 L40.8716575,95.1191088 L49.0561498,49.3603563 C49.771444,45.3612115 53.1664633,42.3942036 57.2253811,42.2210231 L61.246149,42.0411642 L61.3363168,41.9758 L103.71696,40.2373824 Z M161.838155,3.27194826 L192.104824,40.2369789 L178.291207,51.5474574 L160.327329,29.6043227 L154.268381,63.2715157 L136.697231,60.1096121 L142.766468,26.3665075 L118.24002,40.7062765 L109.232678,25.2916494 L150.427675,1.21987397 C154.218286,-0.995121237 159.056796,-0.124957814 161.838155,3.27194826 Z" fill="#201D1E"></path>
+ </g>
+ </svg>
+ }
+ iconType="duotone"
+ >
+ </Card>
+</CardGroup>
+
+### Frameworks
+<CardGroup cols={2}>
+ <Card
+ title="LangChain"
+ description="🦜️🔗"
+ href="/latest/integrations/langchain"
icon={
- <svg version="1.1" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 355 355">
- <path d="M0 0 C27.39 0 54.78 0 83 0 C83 17.82 83 35.64 83 54 C100.82 54 118.64 54 137 54 C137 71.82 137 89.64 137 108 C145.58 108 154.16 108 163 108 C163 90.18 163 72.36 163 54 C180.82 54 198.64 54 217 54 C217 36.18 217 18.36 217 0 C244.39 0 271.78 0 300 0 C300 90.09 300 180.18 300 273 C272.61 273 245.22 273 217 273 C217 237.36 217 201.72 217 165 C208.75 165 200.5 165 192 165 C192 182.82 192 200.64 192 219 C164.28 219 136.56 219 108 219 C108 201.18 108 183.36 108 165 C99.75 165 91.5 165 83 165 C83 200.64 83 236.28 83 273 C55.61 273 28.22 273 0 273 C0 182.91 0 92.82 0 0 Z "/>
- <path d="M0 0 C27.39 0 54.78 0 83 0 C83 35.97 83 71.94 83 109 C37.79 109 -7.42 109 -54 109 C-54 90.85 -54 72.7 -54 54 C-36.18 54 -18.36 54 0 54 C0 36.18 0 18.36 0 0 Z "/>
- <path d="M0 0 C18.48 0 36.96 0 56 0 C56 17.82 56 35.64 56 54 C73.82 54 91.64 54 110 54 C110 72.15 110 90.3 110 109 C73.7 109 37.4 109 0 109 C0 73.03 0 37.06 0 0 Z "/>
- <path d="M0 0 C8.91 0 17.82 0 27 0 C27 90.09 27 180.18 27 273 C18.09 273 9.18 273 0 273 C0 182.91 0 92.82 0 0 Z " transform="translate(0,0)"/>
- <path d="M0 0 C9.57 0 19.14 0 29 0 C29 17.82 29 35.64 29 54 C46.82 54 64.64 54 83 54 C83 72.15 83 90.3 83 109 C55.61 109 28.22 109 0 109 C0 73.03 0 37.06 0 0 Z "/>
- <path d="M0 0 C1.01154144 -0.00311188 2.02308289 -0.00622375 3.0652771 -0.00942993 C4.7290892 -0.00645401 4.7290892 -0.00645401 6.42651367 -0.00341797 C7.57181549 -0.00473724 8.71711731 -0.00605652 9.89712524 -0.00741577 C13.62960487 -0.0093378 17.3620104 -0.00299456 21.09448242 0.00439453 C22.34907257 0.00528076 23.60366272 0.00616699 24.89627075 0.00708008 C42.72160294 0.02199104 60.47499934 0.28646042 78.28198242 1.12939453 C78.28198242 19.27939453 78.28198242 37.42939453 78.28198242 56.12939453 C50.56198242 56.12939453 22.84198242 56.12939453 -5.71801758 56.12939453 C-5.73864258 47.07501953 -5.75926758 38.02064453 -5.78051758 28.69189453 C-5.79417358 24.39847046 -5.79417358 24.39847046 -5.80810547 20.01831055 C-5.8110244 17.76497444 -5.81357301 15.5116378 -5.81567383 13.25830078 C-5.82078979 12.07586792 -5.82590576 10.89343506 -5.83117676 9.6751709 C-5.83129761 8.55864136 -5.83141846 7.44211182 -5.83154297 6.29174805 C-5.83376358 5.31689957 -5.83598419 4.34205109 -5.83827209 3.33766174 C-5.61659259 -0.73310076 -3.57396693 0.00319344 0 0 Z "/>
- <path d="M0 0 C0.33 0 0.66 0 1 0 C1 35.97 1 71.94 1 109 C19.15 109 37.3 109 56 109 C56 127.15 56 145.3 56 164 C37.52 164 19.04 164 0 164 C0 109.88 0 55.76 0 0 Z "/>
- <path d="M0 0 C9.24 0 18.48 0 28 0 C28 35.97 28 71.94 28 109 C18.76 109 9.52 109 0 109 C0 73.03 0 37.06 0 0 Z " transform="translate(217,164)"/>
- <path d="M0 0 C18.15 0 36.3 0 55 0 C55.020625 8.889375 55.04125 17.77875 55.0625 26.9375 C55.071604 29.74757568 55.08070801 32.55765137 55.09008789 35.45288086 C55.09300683 37.66520134 55.09555544 39.87752235 55.09765625 42.08984375 C55.10277222 43.25068481 55.10788818 44.41152588 55.11315918 45.60754395 C55.11334045 47.25188416 55.11334045 47.25188416 55.11352539 48.92944336 C55.115746 49.88652695 55.11796661 50.84361053 55.12025452 51.82969666 C55 54 55 54 54 55 C52.31198015 55.09353163 50.62004793 55.11744791 48.92944336 55.11352539 C47.83321655 55.11340454 46.73698975 55.11328369 45.60754395 55.11315918 C44.44670288 55.10804321 43.28586182 55.10292725 42.08984375 55.09765625 C41.02930786 55.09664917 39.96877197 55.09564209 38.87609863 55.09460449 C34.89655483 55.08935387 30.91702638 55.07539276 26.9375 55.0625 C18.048125 55.041875 9.15875 55.02125 0 55 C0 36.85 0 18.7 0 0 Z "/>
- <path d="M0 0 C7.33845237 -0.02590394 14.6768925 -0.04309155 22.01538086 -0.05493164 C24.49845825 -0.05988087 26.98153287 -0.0666419 29.46459961 -0.07543945 C47.00774093 -0.13592078 64.47120007 0.2552166 82 1 C82 18.82 82 36.64 82 55 C64.18 55 46.36 55 28 55 C28 37.18 28 19.36 28 1 C18.76 1 9.52 1 0 1 C0 0.67 0 0.34 0 0 Z "/>
- <path d="M0 0 C18.15 0 36.3 0 55 0 C55 17.82 55 35.64 55 54 C36.85 54 18.7 54 0 54 C0 36.18 0 18.36 0 0 Z "/>
- <path d="M0 0 C17.82 0 35.64 0 54 0 C54 18.15 54 36.3 54 55 C36.18 55 18.36 55 0 55 C0 36.85 0 18.7 0 0 Z "/>
- <path d="M0 0 C9.24 0 18.48 0 28 0 C28 18.15 28 36.3 28 55 C18.76 55 9.52 55 0 55 C0 36.85 0 18.7 0 0 Z "/>
- <path d="M0 0 C9.24 0 18.48 0 28 0 C28 18.15 28 36.3 28 55 C18.76 55 9.52 55 0 55 C0 36.85 0 18.7 0 0 Z "/>
- <path d="M0 0 C9.24 0 18.48 0 28 0 C28 17.82 28 35.64 28 54 C18.76 54 9.52 54 0 54 C0 36.18 0 18.36 0 0 Z "/>
+ <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 216 218">
+ <image href="data:image/png;base64,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" x="25" y="75" width="100" height="100" />
+ <image href="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAKAAAACgCAYAAACLz2ctAAAABGdBTUEAALGPC/xhBQAAACBjSFJNAAB6JgAAgIQAAPoAAACA6AAAdTAAAOpgAAA6mAAAF3CculE8AAAAB3RJTUUH5wIVEg0CnpAdKAAAAAZiS0dEAP8A/wD/oL2nkwAAc0FJREFUeNrsnXecJGd1rp/KVZ3D9ISetBM2J0UkJCQhCQSIKCGCyCZjwNm+NvdejLEvjmCDCQZjYxwwwWSQEAJllKXNYXLOPZ1D5bp/1OwqgU0QQtLu0a8l7U7PTPVXb53vnPOd874Cp+1pYd+64RZ5pVCWm5YlyLJMeyrmSQIOEDxZr/mqFz9vmxCcvndPGfv+TbdHE/FY/p6DIwOm4/e0pZO9M0uFrlrDTIqCGGualu56viSKQhDRVFsQqIuSUBvq6VwtVeuzgWvNX3TOjmnTcmeAypPhMwk33Pyj03f2SWqqhN6wvO3j86tn1RrWudNL6ztqLXvItN2s7fqa7fhIsowoigiCgChKiIIABHhBAAEEQYDjOCiyhCaLnqZK5agmTXZmYkfiEeX+zb25e+Oaehho/UoA+L3v33T6Tj+JLJ1OqlMLa+csFGqXj8wuX7JeMc+smU7GDwRUVUFVVTRVRZZlZElGlCREEQRBBAQEQSAAAgLwA4IgwPMDPN/D9Txsy8FxXRzHQQg8YppUyUSVBwfzqZu62hI3ZhKx+wHvCQPgd244DcAng82vFXtNJ7hyfL7wstnl8rMath9TNZ2IrmMYOpqmIksKkiwjSRKiJIX/FSVEUQQh9IIQer0gCPCDgMAP8AMfz/PwPA/f9/A9H9fzcB2XlmlhmhaubRJR/Ep/e/zms7d2fykd065/IrZp4bobfnD67v8KLZlO77jr4Phr7jky8/JK090mSiqJeJRIJIKmaSiKiqpoqJqKooQvWZYRJRlJemj7BREECIKHAOj5Pr7nn/R+nufiei6e6+K6Lq7r4Lounufi2A7NlkmjXkfwTLqSyp1DnbHP7xjs+jJQ/qUB8NvXfe80Cn4Ftt5whisN5y0/Ojj52mLd6Y3F4yRiMQzDQNc0NCOCoRvouoGm6aiahqqqyIqCLEkIG55PFEUCQQjjPQi9XgC+7+P5Ab7n4Xo+nuttgM7DcRxc18Z2HFzHxnGsjb9zcBwH0zSpVmt4Zo2etPyj87Z3f3wgn/0y4D/uALz1tttOo+EJNFkzUrc+MPLmB0cW31lueZvj8QTpVAojEiFiGESjsY1X6AV1Q0fVZVRFQZYlJFlElATC3VYIvR4Q+OAF4Hs+vh/Gfb4f4HsBrhfgeT6eG+B6Pq7j4TghEG3bxrIt7JMvE8e2cRwbs2VSKZfxzXKwuVP/6sVnDP4lcP/j6wGvv+E0Kp4ga7nC82/dN/FH40vViyPROOlUklg0RjQaJ5FIkkwmSCTjxOIG0YiGrstoqogiC0gSiEKIOX/D07legOv6uI4fejfHO+npQiD6oTcMgEDARyRAIAhEPF/ACwQcF2zHw7ZdLMvCskws08S0TGzLxLEtms0GxfU14kJ94cJd+b+++OwdnwDcxwWARw4fPI2MX7KVG1bX7fvGf++2A1PvEpSo0daWJRmPE4slSKXTZDNpMtkE6VSERFTG0EU0CRSZDU/3EOBMx8e0NpKHpoXZbGI1mlitJo5p4toWnuMQeB5+4CMAgigiiDKiLCOpGqKsIio6oqKBpIGk4gUKri9iOR6W7WKaJq2WiWm2sC0Ty2xRKq1jVlY4oz/2H1u60/8XmPqFAfjFr3ztNEJ+iRZPZ5/zjVsP/tn0Wuu8trY20qk08XiCTDpDrr2N9o4U7RmDTEwiqoImgRyW8vAJsL2ApuPTaDlU6y1q5SrVUon6+jqtSgm7WsGq17CbDZxWE8+28V0H3/NOlmUESUSQFSRVRdZ05EgEJRpFi8ZRo3GUSAzZiCOqcZANPEHF8SUsOwR6q9WiZbYwzRb1WpXiyjwpsbLv6kvPfA9w5y8EwO9+78bTKPkl2NbNA+pXb7znd350eP5/+XIk1dneTiKZJJPO0t7RTnc+Q3d7hFxMJKaAKoC08b1eAKbrUzUdirUWxfUypdVVKstL1FdXaKyvYZaKmJUyVqOO0zJxbDPMaF0PL/AJgiAEIAGiIGyUbWRkWUHWNZQTIEwk0FJp9GQKPZlBT2RQo2kkI4EvR3ADGdMJwgy50aTVatFs1imsLGDYawsvvWjHbwH/9XMD8Jvfuf40Wh7vWM8LNh2bLnzo3pGVaxPpDLlsjmQyRa6jnb6edvq7E3QlJVIKqGEBZSODhZbnU2m5rBWrrCytUFiYozw3S3VpgcbaKs1SkWa1itlqYjkOlufi+AEu4AngCyL+xs9DCAEoBCAEIBMgBwGyKKCKEpokoWkaajSGnkigZbMYmQzRtnYimRx6vA0pkkbQ4rgomLZHrdGi0WjSbDVZXZqH2kLl6kt2/Q7wzz9XUuYHwmnEPK5prnLht2/d97FiSzqrs6uHdCZDJpMl39PFcH+WgXaNNg20MJ8IM9gALD+gYrosr5dZmltgZWqS9alJaksL1JaXqZVLNBoNWo5Ny/exBQFXkvBkhUCSCEQRQRTCExEhBB9BcLITIfAD8H3wfQTfR/J9ZNdFtW30eg2jsIaxtIQej6NnskQ6csRyHUTbOomkO1BjbahqDF2OYKgyVUVCkftYXZKSX7vl0N9ffekuCfjHn9kDfv20B3zcrNJyX3/DveN/0fL1fEdnB+lUhvaODgYGOtnSm6Q3IRALKychKAJwA6jZLqvlOvOz8yyOjrI2MUZ5dprK8hLVcoV6q0XT97BEAVuSCRQZZBlh4zREkgREUUAUBISHfjp+EB7JBUEIQJ+HyjOBH2bJgusjei6K56F7HlFBxFBVIokEkVwbRkcH8Y4uEu15jFQnajxLIEdoWh6VeotqvcHa8gJ2capx1cW73gn8+8/0vIqncfML2/nn7BU/942b3nfH4YX/o8ezWm9HJ5l0lnxvnq1D7Wzp1MmpIJ+ERrjdWl5AodZibn6R+dFRlkeOU5yepLiwQKVUpNpq0fQDLFnG03VQFWRFQVEkFFlEEgUkIawJCkGwUZDeqP8FnKwHBoFPQLgNiwIgCQSSjB8EeHKAH8iYno/petQdF8O2iBUKxGs1jPV1WoUCzVKBeMc6iVyeWDZP0kiiSjqKJCAL3SwHbvSbt+z76JteevE68FN7NeG22+84jaBfwNpzbalv3br/z249vPDuVKaD9lyOtrYc/Zu62TGUZTgrEX9YlBMArg9Vy2VxrcjM6BgLR46wOjZKcW6WUmGNarNBPQgwZRlfVRFVBUVV0BQJVRaRJQFZkpBkCVEMPaEgiCcbEnzfx/U9PM/HdT1s28a2w1MP13XD8oxwYssWCASRIGDj5MQHz0VxXCKuS1wUiesGRluWSGcH8a5u0vleku296Ik27ECmXDMpVWoszk8j1RemXnrZ2S8Dfqr6nmyardMo+jktGk/1/ut1d330gbHCVfnuPtracrR3dDA83M3uTUn6YqA87P0nYr1CrcXM7Dwzhw+zfPQwa1NTrC8tUiyXqbsepiLjqiqirmFoMroioSkSmqqgajqaEUGWFQKEjQ6XFq7rgu/huW7YCYNA4Hmosoyux/D8EGCWbdNshnU927KA4KHmBkFElEV8ScWRJCqOhOk6WI06ScfGbTSx63WsRg2r2SCb7yeW7aAtriISgaCXmfH6wO33Hfn4e9/y6pcBxf/RA66uLJ9G0s9h//HN72+fXGn841TBubAr301bNkdnvottm/Ps7ovQqT4U650orTQdn+VimcmRMWYP7mf52HEKszMUC2tUTJOGIGBpKoKmoWkKhiZjaDIRI0IkFkfVI7iei9lq0ahV8BwbQRCamqqU/IA1z3VqEUN3PM8VavWWLityyvfcXKvVStm2LYuyimZEUfUoHhIt06Reb2A2m/i+hyJJyKqMIIhhmOCD73nIjkPUdUgJIvFIDL29jWh3nnRPH+19AySzeTxRZb1qslooMTd+hAt35j8K/Nb/6AG/c8PNp9H0M9rQli3n/OjIwudcObmrt7efbFuO7t48u7Z2sbNTJS09tN2eAF/FdJlbXGHy0CHmDx5gZWyU1fl5ypUyVd+jJSsEuo6iKxiaQkSTicdjJNNtyKpOvVZlZWkOIfCauqYfGujvvV9TjX2dXV3jF1x40fzi8nLp5htvsDKZpG/ZNitrJfmqq682RFHsuPfuO/uDwN8xNztz7tLC/DPWF1f7BEklnm5Dz6RpRWPUajWa9TqO66KqSthxIwoIgoQnCtREEddx8Bo1EksuvusQOGHRO3BdMh15cnEVwY/h9m7i7oNH3vXaFz/7duCr/60HvPXW080IP4uJqnH5v1x376dLljKUz3eTzebo39TDnq05tuVkojwSfE4A63WTyclppvbvZ+nwIVYmJlhbXqbcbNAQBExNQ9A1dE0mqiskYlHSuXY0PUKpuE69vI6hq/sHBoau37Zz1/fxhQeB6s967bFEXPA9d3BqYvzZBw/sv3p8Yuw5no8aTWWRtRhN06FWKWO1mqiqjKqqCKK4kdD44HrojkPa90loGkY2g9HVRbavn+7BIdLteWxfYrXcYHpqCsUqHP31X3v1FcDCTwTg3Oz0aVT9lHbvwZGXfOXmw5+ypXi+t6ePtlw7A0O9nLE5w3BKRHsY+ALA8mC1XGX8+CizB/azeOQIy1NTFFZXqTg2TVnG1TXkjVgvEdFoa+8kmWmjWi1TXF0imUjcvH3Hrs93deWvB1Yfr88iSaJy6OCB58zOTr9j9PixlwSiIiSyXQSiQr3eoFGvIhKgaSqCKG148uAkCFOeS1LV0bNpIl2d5DYN0DM0TLqtg6YDS+tVRo8e5Fl7h/4G+P2fCMAvfPHLp5H103g+LXbNV28/9klBz+R6untoy7UzvLmXs4ZTbIoJJ4/RToCv5QYsrhUZPXSYuX0Psjw6wvLMDOvFEjXPo6kq+LqGqqvEdJl0OkVndx9BILC8MI0iBveffc75H9995ln/BTR+WZ+rVqlKhdWlV37329/4w/GJyT2Jti6MeBbbdqlWSviujaqpSJIUesINEGqOTdrzSWk6WjZNNN9F19AQPUPDxFNpqk2XiZlFKsvTlWuvfsEVwL0/FoAPPHD/aXT9D3ZwbO5V37l74pNqvD3Tne+mvaOTLVt6OHMoQa/+0InGCQA2HJ/ZxRXGDhxgbt9+lkePszw3T7FaoQ5Ymkaga2i6TCKi09WVJ9ORp1RYoVZaXe/Od39i75nnfAp4wjLEVDI1cNMPvvf+22695U2CFiPRlgdBplpex7FNNFVF3NiOvSAAx8VwHDJ+QNwIQZjo6Sa/eTObhgZR9SjLpQYjx4+zqSP5pZe88AWv5cfMmsgd7R2nEfbf2HduvvOV339w7lNGsiOdz/fQ0dnJtm09nLUpRpf6yPf6QNV0mZ6dZ3zfPhYOHGBpbIzlxUVKjXqY5eoaoq4R0WTSiRj9g8OoRpTFmQkU0b/5Oc99/vuBO2zbekI/5+raytTb3vXet6YSiYnvfOc7/3dtaUbNdvSSzuY24sIGqhqOAAS+gC9LWEDVcZBME6FUoSbLrKoqsYhOT18vbXGZWlcns3OTL52emb4YeEzGK9xxx+2nUfYTbLnUvPo/f3jwH/VkV6Y730NHvosd23o4a1OEdvmRxWUfKLdsJiammXjwQRYOHmRpfJyV5SXKrRYNWcbRNCRdJaJJdHbk6B/ahmmaLEwcM7u7Oj9y7oUX/zW/xPmLn9aKhbV3/se//cuHq6YbyXRuwojEqJWLWGYDRQ6bFN2N4zzJcUk4NilBIhKPonXk6BwaYMuOrWRzbazXbI4cOU5/vu0LV131stfzqLZ+YX29cBppP8aOjEy84JNfveNfxGh7e09PL135PDu393BWv0FWetTJRgDFhsnE2DgT9z/A0pEjLE6Ms7K8QsW2aCoyrqYj6woxQ6Gnp5fegc2sLs7RKK2OX/isi/+IX6Cl6Zdhsiy/81Of+OjHTDSlLT9ANBqjUlzDMpvIsowPuJ4PvofmeKRcl4QsoyUTRPMdDOzYyuatQ4iqzuTsMqvLC+VXv/KVzwEeeAQAjx07ehptjzI7kJ754X/93pcsKdm7qX+Azu48u3Z0c3av8ZganxtAodZg9NgIUw88wOKRIyxOTrFWWKNqOyeTDVmVSUQ1BoaGac/3MzN+FCVwbt575jm/xU95bPVEW728/v7/+M///JPASNPRvQlDNyiuLuK5NoIkh1N3vo/o+RiOQ9r1iRo6ajZF26Y+tu7eRndvnnLD5siRY+zYtvUvgT98BNAPHzrdkv9wM1LtO79y84F/MqXUBvi62b2jm7P6dNLio2p8fsBqpcbY0eMnwbc0Nc3qeoGa59HSNjJdVSaZiLJ563aSmXYmju5noL/7ny6+9LnvezxLK4+3nXvueR+qVMrbvvL1b167rhp09w2Rbc+zvrqA73tIggCCQCAK2JJE0/NRLRuxWqeyssZKJkk2HSNhRGjLJJmZnnzx86988Uce/pnl7Tt2nkbdCUB5Xtdnv3HHP9b96PbBgQE68nl2bs//WPDZPqwUK4weOcrMvn0sHjnK4vQUq+vr1H0fU1U3wCeRSSfZvmsvsqpxfP9dbl8+//9e/bo3/xmP02DPL8sWFhfdV7z2je87evTw2UfG57eUojG6ewZIpNoor6+Eo8iCQICAJ0lYcoDpukimiVmpUFhaodiRoadXoS0VY3x9fdvc7MxFPOx0RJ6bnTmNPOCiiy6K/sVnv/qxxbr0zMHBYTo6u9ixLc+ZfcZJ8PEwz7dSqjBy+AjT99/P0rHjLExPUygVqfk+pqYR6CqaKtPelmHbnrNwXYfpo/vK5z/jvD8C/uH73/3mU2Vppt/45nf82Z998AOfKxWWpWQ6S6qtA6tVp9Wsb5RmRPB9HEnE9ARUx0NqmtTXS6wsrdLWliQR1dE1WVxdXrriEQBcXV46jT7g89+46Y8Pz9au2TS4jfbOLrZs6ebMvght0mO33cVCkdEjR5nbt5+lY8eYnwrBVw+Ch8CnyXS259ix92zq1QorMyPzz3nu834D+PpTbW2ufOnVX7rt5huv/dYNN72guLZMOpsj255ncW4SP/CRBAFfINyKZQnbcVFsG6tep7haoFJup72jjXQ8Qrm4euFzX/CyHLAGIJ973gWnPPgOjM2+9fs3Hf7dnk3bac93MzSc58yBKB2P6qVyAlhaLzFy8DDzB/azeOw4c9PTrJdKG+BTCXQVQ1PId3exdddZFAsrVJamRt781ne8DXhK1rzuvP1W+/wLL/77u++99/JKaU2tlkvk2juJFNeo18phX2EggCjiS+B4Pq7rIzZNqutl1lfXyWbiJOIR1ovlzWsry3uBHwDIa6d6O5Yefeb194x8qK1rQOzs7qV/IM8Zgwm61Yc8XxCEdGcrxTIjhw4zd2A/y8dGWJieoVgqP8bzdfd0s3332ayvLrIydfTg+edf+IYDDz5w4Km8TM969mU/PPecs2+5/oe3X1EsrJLr7CaT66DVrOH5fpiMEOAL4IgCrusjOy5mrcH66jrNnhyGbiAKnloqFc45CcBS6dStA555znm5D332G3/ryqncQO8muvu62DuUoj/y8IGhkGVqrVzh+OGjzB88yOrYOPMz06wVi9R8L/R8moquyfT09rJlxxnh9tQq33vuec98kxf4x57qa3XrzT+wn3XJ5V++4857rqhXi7QadVLZdopry9RrlbDVHwFBkvB9cDwbxfEQTItqqUq1UqPd0InoGsXCypm7zzpfAAK5u2/glAXg1394zweKpnLe8PYhOns62TmUYTghILPBMkXIMrVerTN6bGSjdX6MhekQfPWHgU/TZPLd3WzddRZLM+NIXvWOy5935ZuAiafNA3v2uT8YHtw0s39kpr9aKdHR2UUilaFRrxEQhANRQgCSiCcKeJ6PaDs0q3XKxQptbUkMTaLZqG7O5dpTQEnO5dpPSfAdHp1+1e2H5t7eN7Sbjnw3WwZzbGuT0DhBbxYCsFRvMDoywuyhw6yNjbE4Nc3qWoGG64alFlVFVxXy+S627DyTxZkxtKB52wuvfvUbgemn05qNj4/M7Ni1+84Dx8b7a5USrueTSGVYW17AcR0QhQ0qEIFAkvC9gMB1sRotKqUqlmmiKQrVeqNvaXGhFyjJS4sLpxz40m25Td+6bf8H07leuau3j4GBDnZ0qSQexa9XbbWYmJhi9vBRCuMTLE5Os1JYo+G5WIqCp6koqkRHZwdbdp3F2tIsklu/8yWvuPZpB74TNjC4+c6ooV3batRotZrEEmk0I4Jbq4Y0IAEgCviigE9A4INrOdQrDZqNFqqu4XtWslhY6QUOysXCyikFvksuvUz4hy9d976Ko27ZsWmQ7t4OdvRGyMkPAS8IApqWxfTsHDNHj1GcmmJlZoaV1VXqto0pK7iaiqxI5HJZtuw6k1JhCbdeeODKF7/sjbVabfpp+/BmsodybdnWSqVltJp10qkUkWiMZqMWxoAiCIgEgogvCOH8sePQajRpNFroEY3A92TTbA3AKTgV9+CRsRfce2TuDX1bzqSjO8/mviQ9RjhXG1La+pi2zezCItPHRyhOTrA6PcPy8jJ1s4UpSjiqgqBIpNJJNu84k0a1zNLY4SMXXfqcN85MTY8/ndfvpVddM5lta1taLEwOthoNEET0SAxBlAiCMBtWFBH8AN9xwuF3z8NsmTQaLVLpOAI+nmNvApA9xz5lwHfx5c9P/O3nv/m+aLpTy/f2MdCfYSgtom5wKQeBj+04LK2uMjEySmFiksLcAstLS5TrdUxRwFEVUGTisQjDW3dhWyaN1em5N775bW8Gjjzd13BpeamQSCTnRSEYtG0LLwBNNxA3Yj6EkB5ElPxw3hgB3w9wLIdWo4XtuIiCQKNW7gKQG7XyKQPAW+498Ibp1caF2/fuJt/bweYOnQQ+gQ++7+E4NoVShcmJSdanZyjPz7M0P0epUsEKAmxFJVAVDEOlf2grqmawMPpA+bWvf+Ov8xNazp9utrC4YMUSqTVFlvA8B98PUFQNSZIJfB9BFBAlEcmXcEURXwjJlzzHxTRDKmABqFVKifbuQVk2YulTAnzb95yd/8xXf/jebEc3nT15BrrjtGsBwgb4LMukUq0xPTPN2swstcUFVubnKa4XaToutiLjKTKKItPTP0i2Pc/MkXv8iy581vtmJie+cwpFMb4gyjVFUcAP2VhFUUKURARvg59mg7taFDcmo4MA3/WwLAfbcQgA0zL1UnFdlkvF9VNi1e47NPKGUtPbsnvHAD09bfQlJNTAxw88zFaTWqPJ/NIySzOz1BcXWV9YZG1tnYZlYUsi7kbcl8nl6OodYHHyMM84+4yPWmbzU6daFUHTdVuSJGRxY1wTEEVpg5lLQBREZEXGF4WTxOmC52NZDpblEAQ+nutKptUSZNN6+ichV7zw6vynvnj9mzO5Ljq7u+hvN0iKPoEXYDYb1Ot1VotlFmfnqC4uUV5aZnlphWq9jgU4ikwgScRjMfqGtlFcnqU9ZXz/9W951wdOxRrq3/39xzeEcsRQdyQIEMQN5n4BJElERQi3YAgTEgI8LyRHBw9BkAJJlJAlUXraL9ih0emXF+v25j07+ujuStIRERD9AMtsUKtWKdcaLC8uUV5ZobG2xurSMuVKBdvzcBQl3HpVmXzfIGLg41ZXZy+99nW/c89dd1RPRQB6vq8rsoyqyAiBj+eFbY2iFDJ2KYqM4LgIYkiWBCE9nOv5OG4IQNlQnGgs7snRWPxpvVgvfOnLYx/5py9dG09l6OjqoDutYeBjWybVSplqo8FaocDa8hKt9XXKK6sU14uYloUjiniyhCCJtHV0km5rZ23qsHf5ZZe/f2V56cipCL5krlv0AyGhqCqGrociOb6PKImIvoQoCUiiiLSRfPiCgM9GmcsPFZoIHGK60WzL5Vy5LZd7Wi/YvsPHL1laq5w7vGuYjlyctC7gOw6NWoVavU6xXGV5cYnGeoFGYY3CWoF6o4kDuLKEJ0lEolE6ezZRWZ1j25bB/7zk8uf/G6eozS8sGrVGs03VNHTDQJYEBMFHEkUCSUaWQJFlZM8LGVoDH4GAYENewvU8Atcllc0Va+WCL9fKT+9umKWl+ksFWZE7OtvpTOloQUCzXqVaqVBvtlhbK1AuFLArNcpr65TLFWzXwRUFPFlGlCXaOroRAh/Brs0++/LX/uni/Kx/qgKwK9/bZtlOj2EYaEYUSQxJL2VZAUFAEgMUWUZy3ZNsrSeaef0AbMdF8D2MSGweQDYisaftYg1uO6P7zi9+8/Jspp1MOk5Sk3CtFtVSkXqjSalcYX11BadepVkqUSqVabVauIAryXiSSCweJ9PWTqO4wEUXXPjR40cPjXIK20qpNtA0W53JVAYjEgdRPMldKDgg4yOLIgIC4gbqQsJ0kUAU8HwfCYglUlMAciyRetou1tGxqWdV642BHUMZ0nENVYBGtUKlUqVl26ytFaiXy3j1BuX1ItVqNRT1E8IhG1GWybZ34Vgt2tKJ+y+57Ip/5hS3ux44uMu2PT3R2YkejRF4Dq6mEokYCKaI7LuosoS7UfvjBEf1BhOr57poumJFItFZADkSiT5tF2t1dvYSEUFIJePEDRXPblFcL9BoNqnWGxQKBexGE6dapVKuYLZMXAI8SSaQBIxojHgyjVVZC57xgis+8eADD5RPdQDOL5fOVzWDWDqHqkeQvBaCp2O7DkEQoHgiiuDjeCEjf8jUL4AsEgjguC6anixksrk5ADmTfXomIW3tXcmv3XjnM6IRnYiho8sijWqZcrmEZbmsFUK9DckyaVSrNOoNXNcLn1JJBEkimWnDtW16ujruv+iSi79+qoOvUCh23/TAV56ZyuYwkhkUMcAQBBTBwwvAth1kB6QNSVjf98LuIgEESQQx9IB6NDYdiSWWQg8YSzw9a3/HRvrLlfKW9vZOdE1BxKW8XqBeb9CybAprazitFkGrRa1SwzTNUNhZDDU3FF0nGk+BZ/k7dp75yR/+4AeVUx2Aue5Nl5RqrYGtW7ehRZPERJuYoqNIIo4fUK3UUfARXQfPCYWxgyDAl8SwJigI+L5HKpMbven6rzUA5Juuf3ppxQ3sPC/StJyh2+/d92bbNOPRiI6mCJiNKsX1dZqtFuvFMrVaFcN1MBtNGo1myB4P+JJIIIlE40kMTaNVa3n3j61u37Vt+HJZEg8DK6ci+J5zwZni5792/dVaNCmk2/PohkZaU4jIYY7baJmoioyGgl9v4FgWvufhA54ghsVpAQQCsu2d+078XDnb3vmUXxw52Z0t1prnTcyuXnL/zQfOW6taO2ur023d0QBVkRB8l/L6Guvr6zRNi7X1Io5povsezXqDVqtF4HmwIf4syTLRWAJJCKjYojIzXf2DkeVDvxE3lMnh3vb7NnWlbh7u7biDp9G8x/8Y+y2tnDU6s/Kczp5BjEQaQzLJpuIEroNpu4iiiCIKyEFA03Zw7VAw0RdCKjckiSDwiMbizXg8/eDJexePPzW7YZpCRFkulC9cLlZfOPHggcsrDXeX6QaKompoWgxdlVAkBxFwrRbrxSrFcolmy6Zaq6F6Lq5t02q0cB0XPwjwxTD203SdaCyG47oIRpJsPINt23ql5e248/DcjnuPzb+xLTkx05mO3Dycz371nF1DPwSe1ofq9xwceaMtGslc9yYUTSWteaQTcWq1GpIkEXg+qigi+j5Ws4Xj2OE4qwCBLIEsE3gOqUz2+MDmrSdPkeSBzVufUgtxZHQ6tVZpXHlocuw1U8uVS51AjOh6hHg6TWckgmFEAZ+F9aOIgQ+Bh202KRWLlMo1GqaF1WqhiwKOZdEyW3juBkXLRrBsRAx0Tadh2rhIaIGHoUpEdA2EKI4XUG7Z/avV6ptG56uvOzZXvG2oM/4f7Un960Dp6Qa+bVs37903Ov/qzp4hoqk0htikIxVH1zWazSaiKOB7HqoghH1/zRau7WzEfxK+LCPJEkLg0NM/9KM7brr+ZDVBvuOmp4ZWXLpna3JkeuUVo4vlX1ssmRdIikEy00k8FiMSiWAYEaKRCKlMCqdVZvWQG7b9eA71apVisUS13qBl2uA4oEhYpoVl2aGy+EadSlYkjEgUSZZpuTa2LyBaFooiIxNq72qyiBaPEAgilu3Jo0uNy0YXypd1p7S3PuuMTZ/e3Nf5JcB8ugDwpnsO/pYtRto6ujehSJDRIZdN4bsuoiThun5IVhn4NBtNWo0GrueFCp6yDIqCJPhEoxGvb2D4h48In/oGhp/UHz7b2SeNziy//Dt3HX3PQtG+SIvE6cp3kEgkiMZiJBIJUukY2aRBOqbQkYmwMNXgbtckUMCxbcrlMpVqjXqziWO7qIFHIPjYlo3juAhBEHo/WUDWFDRNDzM2QUHXIxiagqrIKFJ41CTghxkzIqomEdETWB4sNVvP/NqPJp+5aWTh2nO3df8NG9P/T2XLpBNX7J9YeVV+cHcoYCg26WlPkYgnqJRCISTLsggcB8F2qFdqtJotfM/D3WjmUBUZCY9ce/ux/oHhHz0CgP1PYgAem1w477rv3vX7o4vVqyUtJvT0dpNMJEmkkmSzaXK5GJ1pnbaYRFwJ0PCIabDuNPAcG0+UsEwTz/Oo1RuYZpiZaZKA5wbYth1KWwU+giAgihKqqqLpGgEigiQTUQQMVURXRVRFQpUFJCEA3yPwA2zPwnRdLEHCSEZoOQHjhdbzFu+avPDyM/s/OdiV+shTNXPePNCf+NR/3fh+OZoz2jryqIJLR0ygK9eGKIC30V5lmSbYNna9QaNaw7HtjePMcPvVNBlZcNiyfc937rrth49oPpDvuu2HT74icv/2xP7Rhffsn1j7zYYrt+c6e8lmsqTSadrbs3R3xOlu02kzBGKijxj4BBvCfJ7r02yZeL6L70PLNMG0abRaJw/CESQ8P8BxXALf50TPmigKaKqCoqj4CEiCjy55IQgNmWjEIGIYSFIoCOg5Nr5jY5stTNum5dg0FBUjHaNmerHv3Df3B92JuWddce7wH/IUJCa67o77f2e+5F24eecwuqGRlBoMdLYTMQzMZp0ggFbLxG42wWxRK5ap1xu4no8ririKjKQqqIJPKpmo7tx7zmNqfvLOvec8udL9Qu38b91x9M/mivbliWQbm9vbSWcytHe2saknTV+bRk6HiBS2eXu+j+v5+F7Y8OjbFs1mM8zAvPDpdLwAy3JwXQ9ZCIelbccJBf6CIFQsFwQkWUTXZCRJxg1A9CxUNFTJR1cE0nGd9lyGWCxGIMq0HJ9a06JRqWLWykTqVSKmRc2xUQ2Dpp5hqd664Nt3T371zE2JPwE+8VQB34XPOPOyr9/5w99uy28lkU6jCy0GO6J0tmURCCVhHc+nUa9j1+qY5SqVUpmWGR5nOpJEoMjouoqEw9CW7d9PZXMPPgaAqSfJUdz03IJw+4PH3z261Hhfw9O6evsGyWbbaO/M0d/bxmCnQXdUIiL64Pl4rh8eePs+nuvSarWoVquUKxUW5ucRBXBdj1YrBKDjbMiUEuBL4fC563uE4V8AgogsS+iaGo4Y+i6e3SBwJAJHwrMFRD9KXJfI5xJEojF8UaZh+6zVbdYKNUpr68ilNZRakWargRrYqIk4VVPL3XS48PErz9vU9+JLzv4ToPlkBl/DdLr//ks/+LAS60x05LtRJY98HAa7O1AUBce28YKAWrNBtVzGrlYpr61TKVdwXAdHFHFlBVFRMBSReNRwhrfu/OdDD97zWJ2QQw/e86v/xEYmv39i+QP3jJXflm7rYqijg1x7O7197WzuTdCfkknKAYLn4XtBSI4dBLiuS6MRNhUsLC6yML/A0uIiy4UCkijhOTaWZeP4wUYnrk8gBBCI4c/wfNiQNhUEkOWwrUiSJdyGQ7NWRRM2VL19l4oqU01GyaWTqPEYmiqRjqh0pKOs51LMt+dYWmynsraCVFxGrhWQrBKSnqCudvK9Bxf/oFSudZ21ufO3gSflNNhFFz9L+bd//dZfL9fFM7buGEDXVdJqix393aRisXDQnADLdsKJwVKJ+to6xUIBs9XEIcCWFXxFJmqoKNj09u+4MZPr/LGxnpzJ/WpPQuqOcM6Xf/Dgx9ZN5Zm9fZvJtefozHeyebCNLZ0GHXqAHPj4Xqg6GWx4vXqzyfLyMrOzs8xMTzM/N8/6WoFyuYQvCmiGFpYCbBsvEDbA5uMLIXAD28EP/BPlP0RAFgVUOZyR8b1QuE/wXEQhjPdEAhZVCV1VUGSJbDaLLkvEJIFYXCIVTZBMRphNJClE0oiFBVhfIGiUEMQ4UirH3VPF15cqo9EXX7z3nWywhD6Z7PP/dcMfPTBRvLZ3YDuxWIyo2GJHX4ae9od2Ss8PWC+XKa2uYa6tU1pZpVKuYLkutiThKjKyphJRRaIR2d579vkfL6ws/VgGBLmw8quj6G0I0Vd9796Jv2qJ8b6BgR5y7R309XeyfSDNYEYiIYSMBSc0ynzfx7IsVlZXGZ+YYGZikqX5OYqFAqVSiUqtTqVeR9ENcu3ZsLslcPARCYKNFnEBPM8LmyU3ko8T/5alMNP1RAHPcaiur+E06sgixOMBnuvhuw6yCLIkIokibW05JElCBtoUgWhOI2qoTEcjLOtRBC1KsDpLUF6HwEVKZxkrFa/+wT3Hg9e++OK381OIOj9hpx2Hxl5/y8H597V1DZHOtKGLNlvyEbb3d6NIUhhjBwHVZpPlhSWqS8uUFpdYX1uj1WphCwKOLIMiE4toSL7J1u3P+NbOPWfe+BOPUXfuOfNX86R965b/Nbq88n+lSFt0sKeXjs4Ohoc62NkXp9sANfDx/BMEkWGiUSqXmZycYmJkhKXZGYqr4QDReqVMud6gYds4rk9MVkOw+OHcry8EG/OrQdhwEIgbXzshLQiiEA5VK7KIuJHlVmsVKhtz00EgEI8HVDyPSc/DcRw8z0MAcu05JCNCEAREBZ+BuISuxFAUGUlVERWdQJohKC4RWOskU20cXCq8PHHzfc3f+LVr3vFkOMZ78MjoFdffO/GRSKZXy3V0okkevVmRvZt7iepayIJKgO26LC6vUJhfoLa0zNrSMpVKBdP3Q8YwVUHXNQzZJxWPl5/93Bf9dXG98BPVAOTiE6yUlEpn49++48AHD8w2fivX2Ue+u4d8dyfbh9vZ1qmRUwLwA7wNrxcEAaZls7C0zOixY8yOjrK+vMT62iorhXXWKjXqtk0gSkRjKTK5HJqmYTbKYXczAohSCLMgwMPHFQKkDTAGCCGt2IYnlEUBUQSRAEWVaZp1CmtL4XFdTw+pdIZ6rcHE5AymZePYNr7v0dWVRzcMfER0IaA3KiD3GIhSWyh3KigEokKwvghWkUSmnbsmll+f/fr3loD/9asE36b+3rO/eOOD/yBG2tvyXT0YskRn0uOc7ZvIJeLhSVHg4xOwViwzPzlFbWGB9YUliuvrtBwbS5JwFAVRVUhEVXDrXHTpi/9h5OiB/5ayRB45+sRRF2/d+4z8v113198enK29smfTFjo7u+jrz7NzOMPWrExsY8v1NoDnBwHVep2JiUnGjhxhZXqK4tISSysrzK+XqJgWgSyTaGunoytPW1sHiqqyurxMqbAEgR+OBJ7cZMOf6bjeSXlVhIe+JgQgCyJIAqIooqkqUsxAUWSajRKLCz4BAplcJ64Hs3NLNJtNTMsk8D26e/swIhGCQED1Ia8HBF0aARkCBAJBwBckvMICql0iSHVy/b1Tv/eqi7dMAJ/5VYCvUKvv+sxXb/6XINI50Nffj6EptMUcnrG9j/72tpN0dSBQaTSZmpyiMDXN+uwcK0tL1BoNTARsRQFVJh7VUAKb3v7+A5c/70V/9z/9fvny573oCfmg3/rBHVu/eOMDn55a9y/pH9xCvqubTYN5dg8mGEqIqJyI94KNQNdnpbDO6PHjTB09yvrsLGtLi8wsr7JcqWGLIsm2dnr6+sl1dCEIApXSOvNTY5QKK/iBj6ppYelF8ELaCIINUIphPENwcmILwHfDBkpNBlUWCRCpNUza0hqJlIHv2ayvzIMo0ZHvRRBEVgplbOf4BjGPRE9vL7oRwRcCVES6DfA7dTwvfXLb94F6YQHdrxOke8QbH5j8f7/24mceAu56IsG3VChvPTA196+B3r6ru7uPiK6RMmzO2trN5p7Okw8sgkDLdpidnWd5bJzS7ByLc/OUK2Vavo+lqviqQsTQiGsSkm/bL3jJNX989PCB//EESD56+JfvAdVk51m3HZr/nKtk9gwODtOVzzM81MWegTg9Bsgbhc1gY0t0XIfZxSWOHjjA4ugoxblZ5uYWmCmsU7RsjESSrZsG6enfhKqqlAsrLM3NUCsXCDybwG7Ssn3YoIuQfJGTe2wQ4LpeeHoihG3iJ77oez6e56HKArqmYhgRir7vzC2tKulknJ58OxFdxqwsU1JVcl39RFSNcq3GwWOjKIqMoih05fPoukEggIZATxScLh3XTeO5Hp4fxqTN0goxQ6diJ9u+fct9f/O2V135Ip6gbpr9x8a23LRv8t/XLP3M7p4+YpEISc3mzC1d7BrsRRZDWjUEcLyA+aUVpo8fZ31ykuWZWdYLBZq2jakouKqCpqukohqB0+DCy5/7mZFjh38qJR555NjhX+oHPeei5z/7s9+66zOe1r55YNMAXT15tm7uYk+PQacabn0hH3MY8zVNi+nZWY4fOMDyyAhrs7NMzc0zV6pgyQr5gUGGt2wjk81RKxeZGTlOpbCM79oIno3nuXR394xabuDNLq5u1wwDQZQRxWAjmQA38JGFje13g0BHCAJ8z8exXBQxBKAgiLzoRS/6ajbbduxb3/7Wa8enF7a0t6XJd3Zg19corWu0dW0iElepNSscG58kEomgaSrtHV3IioIgCOhAT0yg1WFgW2kc18P1wpZ1u1kmlUgzXWpecONtd/0e8L9/6WXXSHTb3ceX/m2poZzT3d1HPBIhoTmcubWDM7f0o8vSSdIhLxBYXi8ycfQYq6OjrE7PsLq0TM00ackyrqYiaSrJmI7otejo7Lj/RVe9+k9/2muRX3TVq395T9nRsRd/4iu3fspWMt1DQ0Pke/Ps2NLB7rwWSp5ubEfBBnlNtdlkbGyc0f0HKIyPsTg9w+TCIou1OkoyyY7tO9m8ZRu+77E0M8bawjSu1cC1WjiuSzrbfjSbbf/Pl1398n9bW1u77C/++m/+WZJlJHlD3DcQTsaWLiAJbMRl4e7sOy5Wy0LAJxZRUQ0Dz/Ozq6urH3zVq179+bHR0dccOnjwzcdHJ4f7+vsR1AKldZ22/ACirFCqVpmYmSWZTKIZBul0FkEQkBCIiwF9aZGmFcU0nTCLdl1qgY/ot/CSOe4fmX3PG174zOuBO35Z9+S2B47smhov/uu6Y5yZ7+4jEYuSUB12D7dz9vYBoqoSJh0bu9Fapcr48eMsHzvG6sQkSwsLVBp1WqKIpSqImhLKcEk+MSNafvHLX/O7I8cO/9QCjL80D1gyxWu+8aORT0qxztzmTQP09HWzc0s7OzsUkhvhmM9DIjDFapWR4yNMHzrE6tgoM5OTTC6uUHRdUt3d7DzjbPLdvZQLK8xPHKVRKeC7Do1Gg2QyPTcwtOWzfQOD/wLMjo2Pce455xxIJ+LVastMhO1VwUbBL8yw3Y1YE0EMacQ26HlbLQvXcYgbUbry3ezfv//S3/jN37wSuK6/v//Pd+7c8dWx0dHfvP3229+aaNpqh6ChGVHSHX14ksRaqcbM/DyJRAJDN4hEYwRCgBgIpGXoycrUWzEsy8Z23fDoqrpCSlFYbSQTd9x/6H//1jve+DLgcZdMv/fQsbP3TRU/H+i5nV35HhLRKHHFZffmNs7bNUh8A3wn1qXcaDI+Os78ocOsjI2zODNLqVKhCViqgqCpRCM6CUPGaZa58PnXfGBhduq2n+Wa5IXZqccdfG6k41U/PLD4ST3ZnenvH6CnP8+erTl2tMlEBTayqnA79PyAtVKJo4cOh1II42NMTU0zubJKQxTp3bqdPWedSyQaZWl6jOWZUTy7iWO1sCw72Lpt179f/YpXfxh4RDA7PDw81tfddfy+A0eeEYsnECUp/IXhbz6ZDAQi+IIIgQ9eQKtp0WqaGJkE2UyWMST5tltuftu73/tbNwDe7t17R6943pXv7mjvvPWWW2/5s5mJ0c2+IKMacRJtHbhNWFxZpz23SiKZRFE1RE0jAJQA2nWotGk0Gglapo3tOPieg+o1yOVyjC6OX3HXPfdeBXzx8bwnohq59D++/+BnPK19uKurm0Q0QlL12L0lx/m7h0jq2iM8X6VpMjo6zvT+/SwfH2HhhCSZ52FqGugaEUMjHdVwrSrPvOjSz1z+vBd//Ge9Lvny5734cQXfjXfc/6rv3T/zqWRuU7qvv5++TT3s2ZJle1bCOHn72WgGCFhaK3D84CHmDh1keXycyckpZtbW8aJRtu/Zy9bde8HzmTzyAOXVeXzXolIpk87mRi55zrP+H/Bv+/bd/5jr2Lfv/trOnTvuuuv+fc/wPBdFUU6KqQQBeEGASIAgiviiuFHrCrCbNvVai3gbZFJx2vN9HD1y5AXHjh56DnDDiZ+/c/fOL0ci+tE777zzE7OToxdLio4ei2PEMjStEstr67Tl2onF48iyjCjLBEBUCOiKC5SzOo16DNsOm2J9E+KSRyWSFm+/9+BvvO1113wXqD0e9+T2+w5e81+3PfBRR0rle7q7iUV0UprHnq2dnLd7kNSjwFezHCamppnct4/lo8c2BLhDDWRTC2VoDUMlHTdwzSqDQ8O3vOp1b3kf4P3MABQfR37AOx88dM2N++c/lWzflO7vH6B/oJu9W7JsS4toJ8AXoi9UnVxZ4ci+/SwcOszK2BhjU9PMlcrI6TRnPON8hrbtpFpaY+bYflqVAq5j0mia7Nx91ld27z3z/cDx/+56skNDNyVjX3uP2TKliGGEma4fekE/AJcAWRRxJRHPhcDz8WyHWqVOu+uSikfo7OqmuLqo3XbLTX/wR+//09sf3sly4cWXHt5zxpnXfvmLX/zkvQf3vTQaizOwdQ+ikWS9XKdYLpPJZNA3SLwlIeRLScvQmZapVKM0Wyam49DyPQRCLzg1eeSZx0dHXwb8wixcx+cKv37T/rkPBWo22dvVRVRXSRsBZ2zPc86OAVK6+ijw2UxOzTK570GWjx5jYWKSlbVV6q6LqSr4mhY2KMQNRK9FMp0+/twrX/brx44e+rmaK+RjRw89LuDz5MiLvn778U8Z6b70pk2DbBro4YwtGbakBNSTB15hxmt5HnNLKxzbt4+FQ4dZGB1lcnqapVqdaD7P7vOeSU//EGsL08yNHcQzazSbNRzHb1z07Of8+UuvuuZvfpoYSQz8u4YG+o8fOj65U8hkQh0zz0YQCM+E/fCaRFHEEQQ0P+QzqVeb1KsNork4bW1Zcvl+Dh05ftn3rvvWu4APP+rXLL7y1a9+m2X+qzJ2ZP+ViVSWfP8Qpuuxul6ko7OTWCyOqqhIG6Q9mgC5iMBaWqNajdIyLRzHxXV94lGRNSPJffuPvunX3/K6r/BzzpZUKmX5375z2/+54/Di/4ml81J7e46YppCJwRk7ejhn2yYSqhyyF4RleOq2y9TMHGP338/c/gMsjE+wsrpCxbZpqSqerqJtgE/yLHRdX33He3//XcDPrYUnp9OZXxh8ghq9+GNfuunTaqq7bWBwiE0D3ZyxJX0SfDzM+5mux+zCYgi+g4eYHxllcm6WlUaTVN8mznzWxbS1dzE3fpTlqaMErkm1WiGeSE8+78qX/D7wtfvvvfunvbS1855x3nUHDh3d6TouUd3A97yTjJ4hcSIgCjiSiOt4yK6L3WhRXq8QSbeRzaZp78rTatT53vXX/9Eb3/TWu4FHzDV4Pmuve8Nr3/mJT/7D144dvP+cbEcX0WiCUqVBqVIlk85ieC6SLIUk3gHExYBcQmQ9YdCoG5iWjR34SBJkc+2MzR276L777rvk4dv+Tx/vGbkfHZr60F3HC29NtvXQlm0jqonk4gJn7ernjC19xBTxYSqXULMcJqdnGb3vPhYOHGB+bJzl5SWqtk1LUfB07ST4NNEl8P36C1/6ivdOTYzf8otgR56a+MV0VRwtsff7909+FqMjPzi4mb6BbvZuzbI5+RD4AggFYDyf6YUFRh7cx+Khg8wdP8749CxF2yE3vIUzLriYZDrN1NH9rM2OgG9RrdWIJzN3ve6Nb/11YP/PfPy3efM3vvGNr/96o16LZtraCAhoNuonHh18wkq/I4nYrofieriWTaVUIVmvEW/L097RQbPRZHluKvuFL/z7x9/+jnddxWOluObe8+5ff/eHP/qJb0+OHG7fe+6F2L5DYb1IV2cnEcNAUcLpO0EQ0ASBjBGQTqlUKjq6aYYUtkJAIplifkpWjo9PX/OzAlCNpXY9MHrso1MF57JcR55MOk1Uga6Mwtm7B9k10EVEEvH84OS9qZkOE1MzjN53P4sHD7AwNs7KyjIV26KlaPiGhm6oJGMGuhyA77lXvuSaPzDN5pd/Ueclm+bP35zbt3lH/xduuP+fbDmzefPgZno3dbN3c4YtSeFkzHfS83k+0/MLHLv/ARYPHGRuZITJ2TmKjkPn9h2cccElaJrG2MH7KC9NgedQLpfZsmPPV5550aW/U28053+ea9y+bdt955x99g+v/8EtL/HcXmLxJI7tYFsmoiCEg9NAIEpYoofuefiWTatWp1wooSezZNJp6u11HMdlaWn2jO985zufuuyyy97wmH4+Ub73FVe/+INf+K/v/n3f4BahvaOdaq1JpVYnEU+i+T6yJG20wAbEJcjEJAoxg3rdxLRdPB8ieoxYMs3x6cUrfu+db+gHZn6qZOOBw1ddd9foX5YseXNXdy/JeJy4EtDdEeWcPUNs621HE8METAA8BCotm4mJKcbuvZfFQ4dYGJ9gdXWFsm3TVDUCXUMzwkJzRBXwbItnXHjJ/10rFB4XdQB5rfDzdcO8+trXJz/6he9+ohokzh4a3kpPX57dmzNsfXjCsZHtWq7P7OIyIw/uZ/HgQWaPHWNibo6y59Oz5wx2n3choiAweuAe6oVZfM+hXK7yrIuf87HnvfAl/+cXyQbXSxXn5de84p9uue22K0uldXko147neZQKq2E7lSBsTPCHcvOW56HYDm6jRXW9RDRTJtrRQ66jK2R8CgLuefDA85uW849Xv+yl7wIe0VD5hjf+2mcf2HfwyvGjB65s73w+ths+SLlcBxE/PO0RhfDoTxchZUAsrqBXNFqmhWUHeIJGIpVm+uhU37GRsUuBf/lvvZ4Rid/24Ojv3j+2+vuSlox0d7cTMzQSqs+m3gzn7B5iqDONTIDngyAIeAiUmxZj4xNM3P8A8wf2szQxycrqKlXXoalpYbarqyRjGlFNwrEaDG/d8YFiYeUvHq/E9ecSK3zbu39X+OL3fvT/Jgr+Czdv2xoWmTe3sT0roT8KfLbnMb+8yui+DfAdP87k3BwVz6d3z5nsvfBiHMtk7PB9mOUVPMfEsmx/0+DmD1747Ms/WG80gl/0Qz7zWZd8/1kXnH/zjbfe+dze/kHa2juwrBb1cikEIAKBGOCIIk1JRPU8pJaFWalSKayhJTPEE0kCvyv0XUHA0ZGJl7pf+1bi/HPPevfDg/DZuXnrZS958V986nNfuLi0vhbTO7NUq/VwWCcaDSnzNo6mZSCuQCIqEzE0Gg0F1/fxA41YLEkgaRw4OvrfAnD37j3n/ddN+/5kcqX1vFgyRzadJqLKpHUYGuzg7N1D9GViiBt1TwFwAyjWm4yNjjFx730sHTnC4tQUK2tr1DyXpqaBoWEYGqmohqGIOGaDfE/vnzbrtT95PMt2crP+szuX626+6713HFl69+DWM+ju7WHbcI4d7TKRR4HP8QOWCkWOHzzI3IEDzB47xtTMLBXfp++Ms9h1/kWYrRbTh+7Fqq/h2C1sx29cdsUL/wj4+0P7Hh/1q0P77jVffe1rP3b7HXc9e3FuRtnT0UVHVy+2ZWK1zFDf1g8lRi1Joum5yJaFWG9QLayjJ1ZJ98ZIprPgh0Q8CAKHjo5cWq61vvqC5178h8C3Tvy+lVL19j27dnx1ZmLsjV35TlpWOKnnJFP46gnG0BAMEVEgYQjohoKqqliOC76CZsSIJZKMzyyf987Xv6wTWH74Z5pfLWYOjM6/43Pfuec3KpbQ2ZbrIBGLE1UE2hIS27b1s3drH51xHWGjzIIgYPsCa9U6Y8eOM3X//SweOczS9AxrxXWqvv+wInPo+QxZwLYadHZ1/6nn+e9/vA8tZM/72fi2X/3m917+8a/e9sF8/1byvb0MD7Wzs1MhITw85gtwA1gtlTl+8DBz+w8wd/QY09Mz1IKAvjPOCcHXrDNx8G68ZhHbbGJadvGVr33zbz0e9a9H2+Ztu7536bMv/tZ1N9788p5Ng3T3DWGaLVYWZrBtO8wGBQFHkmhKPqrnITdb2OUqpeVllGiceHsPyXQ7AiDJMooss7CwsP1fv/zt/7zwvLM+tbmv62PALMD55579uf/42nWvajaaeiShUa83sF037HXkoSdVEQLimkAkIqNqKrJl47sBkmqQTiaZm1oeXC2U9pwA4NDAJvWBoxMvu/GeY78xs9a4MBJL0dWVJqqrxBWfjlycXTuH2DnURVqVwfdP9iLaPqwUy4wdPsL0A/ezdOQoi7MzrFcq1ABL1xF0jUhEJRXVUUQP17EZ3LzlA8Cf8EswORL76Sl6r33jO/s+9V83/52W6E72bhpgYKCDXScaCx4GPi+AYi18ymb3H2Dx6DFmZ2aoeh7dZ57NjmdcSKtRY/LQPXitIlarQSCIq1e+5Jpfr9eqX/1lfNBvfvPr7pve/PY/37//wLOPHdqXzeY66OkbxGo1WV9dDhthBQhEAUuRqQcBsu0g1uq0iuuUo1EUPUo0myOVySFLIpquo6oqc7OzkRtuuut3D3d3XfHMs3Z8ur+748uNZuPWwb6u766vr708m+yj0WzibLRinWjwDBCQCIjIENHDiTxFlnF8H0nRSCQTOK6vLBfKO8/es/2Ofcenr/z+V3745kOTK88XZF1oy3USi0aIKAJJHXp629m5Y5At3VniUqjVGz5Y0HIDFtcKjB88xNwDD7Bw/BjL8wsUa1XqgoCl60hGOM+SimkIvo3n+u7es897P/Dnv6zmCDmRavup3njNK6+Vv3DdHR+qeNFd24e20NPXwc6+KJ3qQ9tu2L4D1abJxPgkM/sPsnzsOHMzM5Rtm45de9h+7oWYrSaTB+/GN0uYzTqSpCy9+g1vfQfw7V9mG9LswvwD17zimr/76N9/4k9Hjx3mnGdeQu/AFlzHprReCEcABB9PEmlJErLrIjVbCKUqNWUZWdMQFRUjniKRAkWpEjGG0XSNuekplpeWdn/thvLH29tSb961ZdO/qLI0V61VPc9HsiwL27bDvseHuUABAV2CiCagahKyLON7HiIysUiEdDzKTXfv/7UfHZ1/yeRS+RIvkIVMOkMsFsVQJWKKTyYVo3+wj+1b++jPRDGEgA3s4QVhgXluYZnx/ftY2L+fpdFRlhYXKbdaNEQRR9eQDZ3YxrYbuBYEfuM5z3/RHwIf/2XeEzn3UwrV3H9k4i2HZquv3bL7PLp6O9nWn6AvwsZ02UPllqbjMj03z9SG55ufmqTYqJPdtpPtz7wYy2wxdfhe/FYJ22oiK+rSa9/0jrcATwhN19WvePXHHrj/gctvu/u+Z2dzHQzvOINNw9vxvMNUy0XsDXQ4skQ9CBBdF6FaRZBEqpqKqOoIooweixMTQVUaqMOD6EaE2YlRqnWTpeW1s+aXS2epolffvWNYDPyQNsSyHYKNfzZqMWEWK4ChgqqGAPRcB1mQkQydTNLgwWMzu4OYSDqbJapr6KpMRAmI6yLtnR0MbBlguL+NroiMSrjlAjiBQLlpMjU1w/T+fSwePBBmumurVCyTphwWmFVDIx5RSURUHLMBQVB4+ave8NvAv/+y74ccjyX/xzftOvOcXX/3n99/f0fvZvI9PQz1pxlKiY8sNAcBlh+wuFpg8tBhFg8fZWF8nLVyifjAMFvPvxg/EJg8fD9evYDrtAhg7XVveufbnyjwARw4cLD6nt/87d+fnv2t7+y7786OSCxJz6ZhfN9jeuI4pUIB1/cJJAk7gBobIKzUECSJiiQjiBKJjh5i8RiaDqLYYniwj0g0wujxYwilCnYgUG/ZsXKlim1bOK6MZVsEwQZ5vBhsaKmBBGiygKqKyHJ4Ni0iIqkaMUMnEVGRk1GSURVN9ImokE6n6Ozvp38wT38uQpsmogQPdZVbfsByscL06ChzB/azfPQoy7OzrK0XqHgupqoS6Dq6oRLfeNmtOul0Zvo5V770PcB3n4j7IYsnmjV/gp19zrnK577+ww9YYiK/eXCY3r4sW3KPTjrC1H6tXGPi6HEWjxxleXKCwtoaWkeerRdcgqzpjB+4G6++iu9amJZTuuoVr3lnobD6hGvtFgqr97/jnb/+R3/yJx/4xwfvuU2SVZ2O/KYwQfB9KuVySHQkiVjIVIMALAtK5Y0hJiFUiKSHeDyGSoDsmGzqbscwNEZGxllaWkLCodVsYJomyXgE2/NOzryc8FIQ7iKqBIosIkmh1q6EgCJLxKMqhgxSYJFURSKxONnOPJ293fR2p8knJJIyyH4Yv3qBQM1yWVxeZfrIURYO7mdtYpzluTkKtRqNIDiZbEQjGglDJaLJmM0qsqQeeuW1b3orT6D4tpxJ/vcUvQeOT756bKl+1ea9F9LV3c7mrgjtysPjvoAgEKiaNtOTM8wdPsLy+ARry0uQTDJw3oXoiTSTRx7AKi0g4eK4Xutl17zmN4OAXxlDuu24n7v6qpcNf/m/vv6+B+++lb3nPZuu7n5EYGb8OJVKGVwXTwiHdn0gsCyCQpHgZCIRINJNPBZFDAJwLTozCSJ7thOPRTh+fIxatUqr2QQyG4NQ4dYrPOwBFgFFDJBlkGQJSRSQgnBGOaIr6JKHZERp7x0mnWujoytDZ1YjFxGIi6EH9QDL8SnUW8xPzzJ36ACrx4+xNjXF6soKJdOkIYu4mo5saER1lURURZMEqqUCW7fv/EFP/+B7jhw7NPJE3gf5yLGf3A1z0aXP6frmN2//w2x+UMz39jDQk6A3Fn7gk62dgUDL81lcXmP22DFWxsdZm5vFArrPPo9MzyZmxg5TW51GF31KpXLw3Be89H/XKqVfueDfH7zv/R+URKH73//zS288JMkQXEhHvhdRFJmbGqVcKmI7Lk4Qtt6UEPAdG79YDHVyPQ88D6E7T8QwQto3xyKiiGwZ6COqKczNz9NsNkLCxhMAPBEHPoyZQRYJASiF4JSEAEUCQ5VQBQ89laFnaIB0UqY9GRaaIxuK5C1PoNqyWF5ZZXF8nOWjRyhMjLO2MM96qUTV8za2XBXN0IjpKvGIihg4NOpNzrvgon953guv+l/A6hN9D+QLL7r0J37x7gMj7yiY4o69ezaTz6cZSEs8umjjBrBerTM9Ns7SyCiF2VnqrSaZHXtoH97B8vwMxblRIpJHrVZj5+6z/2pxfv5veRLYX/3Zn1hvf/d7fnt5aTl24y13vNzzPLafcR7dvb30SSLyzCSV0jot08RxBBxBoESA6zokymUC/0RA55Pp6EDRQkYG17bw/ID2bAoBH8+1cRwH1w/wBSGcUw542CYMIsJJ4T9RAFEMkAXQVRlNCohFoKtDJ6F6xJVwzsR0Ahq2zXqpysrMLKujx1kfH2N9bpbieoFyq0VdEHAMHVEPvV7UUIkZCo7VxLJt+6xzn/nnr3/zuz4E2L+KeyC3d/x4ciLHdbY+OHrr27p6d9KR72SgQ6dNeWTJxQ+gbrnMzy+xMDLK2swM1WKBSFc3PWecS61aYXHiIBHJpVarsHPP2V9512/+3p/w5LLSa9/41nc5biDcescdV7uOTaN+Bt19/XT2bULTVWrlMo1mM2TakiSqjo3judj1Kt6Sf5KsMppJI0kSnmtjWxvsq56Da4cADGCjG4aTbVDCw7ZhUQgQhCBUHcdHEj0UWUCTAnTJJm6IiJ5H0/IoWSbVSo3i0jKF6QnKU5OU5+cora5QqtWobVBlBLqGegJ4uoqmCLTqVSLR+Pxlz33h/wb+9bpv/+pEoOSf9Mv9aPs7WoGe3zkwRHdnnO6YgPLoOMoPWCmWmRufYG1mhvLKEoGukz/jGXiizOzIvah+C9tuEE+kH3jRVa/87bnZ2SednEE0Hlt746+9+e2xqN664Ye3vHbEtqiWi/T0byKZ6UBVNYxajUazjtmyMC0L27GpuB6OaeKsreL5HqbZQo/FQADbtjBNi3q9RiIr4bleSBEiPJwW6eEWPKw26CHhoQgeghCgyQKuZVGpNjGrNZqVGtW1VaoL89TmZ6ktLVAuFKjUatRdh6Yk4RoGsq5ibIAvqsmIeNSrNTLZ9jtffPWrfvuJTDZ+IgA7urofW3bZs2frX3zmq9d2D51Fe2cbfVmFhPjI93gBVFsOS4vLrMzMUl5axLZMsjt2Y7R3Mj12FLexhiG6CJKy/srX/tpvFlZXFnjy2vq7f+v339HdN7Dy+c9//ndmRg7SqJbItneRTMaIpVIY0QiW2aLRaGCbYWG5Zdt4roNdrdD0XIxEHElWcH0P07KoVmooRjxs/pTCOWGEh+bkH4nBkLkB30MMXGRcfMFHkQWKK6uM3vcgzbUVWoVVmqsrNNfWqJWLVJsN6q5HSxRxdR1RC4EX0WQimoKuSthWi6ZpBuddcPEnd+ze+2ePPlv+lQFQeOyjyC137XudLRqd3f2byHfE6DA4yaVygk/Kcn0K5SpLcwuUlhapF9fQ23JkhnZQWFuhtDRBUhWoVxu86KprP7i6vPQjnuS2urzUyHd1/u41V189e8utt7x/ZW4806xXWU+kSCWTJBMxdCOKpum4jk3LNGk2mniuS9P3sZpNmp6HtDGA5PkhkaPr2ASApKgIooB4AoEP33E2yJjwfYTAQQxspMBFDDwkWaQ8Mcbk8gpWtUyzWqFZr9O0bVq+jylJeLqOoCrouoqhKURUCU2VEfGpV0pEY4mx8y695M+Af50YffJIHsuPvpjLrnhB/oYvX/+qjp6dtHdmySclosKjYj8/oG45rKyuU1hYpLq2jI9AbvNOXFFiefo4EcmjWauw64xzvvryV732Uzy17KMXXPSDQ//82X/8y4NHjp1jm03qlRKrmk4qmSCVSmIYOrGYiqpomLaD49jhaYfnI/oegiiGNCOeh+s4CJKMqBqIovAIVsIT6+oDnhcQeC6CayMGFiI2bIwPVBbmqLdc7MDH9DxsUcCRFQJdR1IVDE1BVxUMTUJTJGQRms06ruMGQ8Nb/2Pz1u0f4heY3filAdAwjEeely4uv6Bms3lz/wDtbVHatIe8n7CxUI4fUKq3WF1eo1pYwaxViXZ0YXR0Mzc/idcsoksuejI9/6rXvvn/zs/NOk8xADI4tOWmd77rPVd9/4br/+AHP/zh25vVluZqEeq1KqsrqySSCeLxOIauhxQcoowke3he2HDgbXBXm6YJgY+sRVA0DXkjCREeXcj3AzzXJ/AcAtdEwELAwvddAs+lZLawbR80jUBVERQZRVVRVRldldCVEHiSKGC26tRNm+6e3gd37D7jw7n2zv98mP94cgEwlcme/MOFF10k//MXv/myeLqDXGc7HQmFqPioMDkIaDkehVKNUmGNZmUdQRJJ9g3RtJqUl2eIqgJWs8lzr3zZh++/50fHeOra/J49u39j+85dN9xy8w//YP+Bgxf7voDje6wsN1ldWcWI6EQiUXRNR5TCUyXP83E9F9uyMJsNVFVFicRRVA1ZCMkwhUeFNI4XUgd7tkXgtBDFFmDj2haO42ApGr6ubMhIyKgbgFMkEVUWEQWwrSaVZotsNjO7bfvefz7nvAv+EVh8Mi+wbBiRk3+YW1jaOb9WvrBv9y6ymRhtWti1+/BygecH1EyHYrlGs1rGbjYw0jmURIbV+XGUwMR3W2wa2vqjy573ws/y9LDvDm/efMcdt972+nvuveutM7Nze8NVkWnWG1TLFSRJRlUUJFkMW+6DANuxkQWIxhNosTSapqA8yvsBeAQhk7/t4llNArsBcgs/MLFtG8t20A0N1TBQZRFFFFFkEXmj5cpqNbDMFolkev5Zz77wyxdffOk/A0eeCgsrt7U91I41PjXzbCeQ0+35btoSKjEpJG08sWIBYHs+5aZFrVrDalQJgFhHHttpYVZWiChge7hXvvjlHx4/fqTO08cqFz7rgo8PDA19bWzk+CsPHDxw7czs7DNMy0HRJPwAHMfCNH0Qwrqe59pkUgniqTb0eApdEUNWrofZiRb5luNhmya+1cC36uA3cTwT0zQxLRtDkzE0GVkMAyHfsag3TEAgmUofftYll31t75nnfBk4YlpPHZk6+cTFbtu2TbrxzvsuiSWzZNrSpCMiysbI4smtIgDTDag0LMxGHddqYSSS6MkU62vzqFi4VpMt23fddN4FF32Xp6ctAn/3/e9d96+LC4tXPPDAfa+Ympq6uFyptNlOAIocCh8GAqbvEI/HSbR1ocUSGLKAIgRhKeZkSAOO59OyXOxmE6dVQ7QbiKKJZZm0WiaW7SLg41hNTM9BFiV0I7I6MLT1jt17z/ymqmo3Akvzc3NPucWUT1x0V3d3z9p65ezs8DCpVJSE8lDy8VCwHNDwfGqtUJ6KwCeSziKKPl6ziCaBL+I/8+LL/+mO226yeRpbJKIXhzcPfrGnr/9L64XVvVMTE5cuLC4+e25u5uxGo9HdaDYRNYm2zjyJ9n4isSgxGaRH1V/8IKDlBTSaNna9itsoo9g1fNHGbLVotkzK1RoEvpNKZefach3359o7b+3syt+eTCaPbOSFT1mTo7EYAGMT03sbptOztaODZFTBeFjp5cSSOUFA3fExrVAjTdE0tGgcu1EOvZ9n09XTv79/cPMNnDoWwLb9F1x08f7DBw99zLLMoZHjR/aW1osXHDp27K1t+U2xWC5PPKIQkTjp/U6YCzRtj2atgVUvYzXKyF4dW/CoNZpUalUGN2/7dt/g9k/v2LnrIDD3dFo8OZdrB2BqfvEMJEVMZTIkdBFFCB5ZqwrCo7e65eFYocaaFo2jaQp+tY6hCDQCly3b93zzRzd/v8KpaR4w2t+THx3asmN5aqX49lz/VqLpNhK6gC48Frq251NtWDQqFVqVdaxqkajSwhIDqrUGtuMFu8898zPAdxdmxp92CyYvzIzTPbBFGJ+c3hmNJ0gkY0QVIexvE4VHbBimH9CwPDzbRZJlIrEYktfEw0YUfPRIrLZpeNsNnOK2a9du4cMf/9SvK9FMJNe7lUQySlrnZAISPGz7bToepUqDRqlAq7SGWy/jRwOafkClVkNS9OWhrTtGn65rJQ9t3YGmR+LVSnUg1jlELKphiI88KTp5/OaD7QZ4gRASL0oe1MuoMviuSybXeTCVaTt0qgPw2Mj4BSNT8y8a2n428Vw36bhMUnpILuLEmjp+QLnlUC6WaKyv0iytIZp1XFWmYXnU6nW6eocOJJPpyactAJPJNKVypatlWz25eCJM9QUesf0KG7Uq0wfHDQARSdGQMAGbQJbwfY/u3oF7H7zrluapDL5nP/eF4lev+8F7ZD0Z6xrYQSKbpj0aUrI9JqFzPNZLdSprq9QLS5jlAgYmLUulbjtYpkX/4JbbDj54t/u0BeDBB+/GDLS8bdvp6Mao34+bEnEDsNwA1yWUPlA1BMdHEnx8EQRJItvete9U9373HzjyvCPjc1cNbd1DorOPXFqjTRUQH72eXkC5abO6WqC6ukhtZRGrUkKNyVRNaDQbKJpR7+4buOnpvF5yd98Ac0urna7r6bquo8kC4gkJ00dF15YHrgeIMpKs4vnuhtaugK5HGqpujJ/K4Nuza0/8rz77n++LxDNaZ/82UrkM3UmRiPDIcMYPAhqOz8p6hcL8PNWlOZrrqwRWC0s3cExoNpr0DQzdqxvR/U9rAOpGlKWl5XwQBGi6iiKJPCoBPlkucPxQ6C8QFBAkTkw/+76PokdWu3v7509lAF53+73vmV0qP2vX3rNJdvWRb9Np14THxNO2G7Beb7G8sERpYYbK0gJWuYikQN3xQqpgz2Vo685vjR0/ZD2tATh2/BCyLOUEAmRZROIh6ohHPrXgeeAHAoEgh1IHnocqyOGIoSCuLszPl09V8MWS2fNvue/I73Xle2nr3UKuI01/8iFi9pPr6AfUbY+llXVWZ6apLM3SXF3BabVwFSPUNbYtMpns/N6zzv/W033d5L1nnc93v/e9tAAnSbRPdO0+3EKZUwHfF/AQCXxwXB9fkBBEGVkRKqtLC/apCL7Ln3NF6s//8Ut/JYhapndoG6muPJvatZMzNA9/iE03YKVUZWFqmvW5KWqLC5jlIp4UdpkrAXhWk+27Lvn6nbfeMPW0B+Cdt95Ao14zBMLpLiH48W1jfhAWo32EDb1d8HwBR5DxEdCNSCuVzrqnIgC/euOd718pNi/asX03qfwgfV0J+mLCY5I5zw8oNU3mZudZmRilPDtNY3UZ27KwYwYgIns20Wi8svecZ/7bqbB28t5znsn0t78r+V44wcWGomPw48ZmNgqC4TRiyDWnijJuICLJUqBqanCqgW+95b/51gf2v3dw0yCZ3s10ducYysnExccmHnXbZWFxhYWREdanJ6kvLWDVa5iyhC3JxGQR16yx85xLvjG0efv9pwQAhzZvR5ZvcD3XwbMtPN/HfxSMhJOvUGfD831cT8DyBBQkJFHFtm21WFiTeIofjv8stnnXmRf/+79/9y86cx1yR99WsvluNnfpdCg8suF0Y+tdXi8zMzrG6vgo5blZmuUipufRMjQUWUbGRY8Y1fOeddknx0aOnhIPszw2cpRkIlF3LAvLbOG63oZI8SMzYWljYFoQwkA61FuTMH0JXdJwzVY8mUorgHMqLJyRzG77hy99/1OKYuS6B7aSzPcz3BenP/7IrTcgbOIoVBtMj02wdPwoxZkpGmsrtFomDV3DkxWSuoJrljnj0uf++3133XrvqfIQy/fddSsB6rpjm5jNeshhd5Jl6SEMSoKALIUgDIKQYd0LRCxfRkRDkuTsjh27YjxMSejpavNLS53fuO3gp0072LFt+xaS+SE29WXYkpGIPAp8XgCVls3MzCyzR46wOjFBdWmBVqNOQxQxVZW4riH6FolMdv6FL33lR0+lEEZ+4UtfyXevu27Fcx3q1Qot0wwB+CgXKAkgSwKiKIS8JoKMIMrYXoAiRvDdtc7FhbkufgX8Ik+kxRPJ9Ddv2//JxbXGxVuGt5DMD9PX386OToXUj5mdblgus/MLzBw8xOroCKX5WerVCrUgoKWpKLpKwpDxzAoXXPySj91+yw9GTykA3n7LD9i0qX8BAq9WXpeajUZYXlFCT3eifU0RQJcFJFl8KDKUZBzbxtFieLafqlXLgzxKtfLpZGedfW700//1/Y/NLNeu2jI0SLJnM/n+PDt7dDofVXIJANMJFQKmDh1h8egRCtNT1AtrNByHpq6DrpGK6XhWnZ7+wdsvveLKT59qSZx86RVX8sB99y4pstyslYrxWrWKs8Fj93AGJxkwFNAUEUkQCAQRQVLx/QaWoOMGmmi2WnuBrz8dF+ry515hfOa/vv+Rg2PLrxseGCDTs5XOvh529Ufp0R+ZdABYXsBiocjE4cMsHDrE6uQkldUV6o5NTVHxdI1kVEcTPURNqT3/xS9//8jRw9VTDoAjRw9z1tnnLHzpi19YLRZW46XiGi3LJqarBPJDe4q0AUBdC1k8w44YAyEoYnkigp5ldmHh/Msue65MeHL3tLHe7i79s1/74YfvPDD19i2DA2R6tpDr7WPXQJxNUU4mHSfAZ/sBq6UyE0ePMX/oEMujo6wvzlNrNanJMo6uEYlopCIqZr3IRZde8XdHDu675VSsocpHDu6jvaNrLR6LTy8sLQ2V1lZoNJtk4pGQUFsSTpZhIpJA1BBRVTncm2UNWZZoOg6inqFYK57tOvY24PDTZYHy+Xzkn75x84d/dGDynZsHNpHp3hyCbyjJcOKRYowE4ZO3Vq4yeuQYs/v3s3T8OKvzc9QaDeqSiKVraIZGW9zAblboGxi+5QUvuebDnKImv+Al1wBYvX39x0fHxi4vLC9RKRfpzKbxFBlFDEJKMcAQIW5IGIYSkmnLGoqmEVRNfCNF2ZLbxsbHnv90AeCu3XuSn/vmLX9739HZX9uyqZ9Mz2ayvf3sGk6xNS08QhWKANwgoFBrMD4yGoLv2DFWZmao1qrURIGWrqMYGpmEgehbGLH4yrWvf8vvVUrrlVMWgJVSqDO8ddu2/ddf/11WlhZYXVmir6ebiCrjSyLSCTZ3IKULxKIKmqJgijKSFkMRapi+j6O3MzW3/PK3vOl1/wA8pWeCF5aWc//23Tv/fmy++KotA5tId4fg2zOcZltGfGSTQRDgB1BqtBgbGWH6wVBpfHl6mlKlTA1obehwpOIGEQVqlbr/4qve8r6JsdEHOIVNnhgLs/72ru598Xi8UlhdSS7OzVHbso24rqPJEqIYDhOKQFKFVEKhENGpN2R8LYauq7RaVYRojqnlpXNHR0ZeAHzlqboo1ZbTf9vB6U+MzZdeuGVggFT3MG29feweSrM9+2jwsQG+JmMjY0w/uJ/FI0eYn5ykUFynBjR1DdHQSMYMEhGFWmmdiy993seWFub/mVPc5KWFsIVv71nnHu/s7DoyNTt7wdL8LKury2SSiZBpSRJPjhNGRcjGRJbjGpWKTsNqIusxtGaBRhDH1Dqk2+7e9+63vfHV3+UpWJT+5vdv3XnP0fnP1q3g/G3Dw8Q7B8j19rFnOMXWR3m+E5RqxUaT0eMjTD64j8XDh5mfmGB1vbBR69MQDZ1ETCcV02jWSmzdsfv61/za2z7AaUN+za+97cT/N/bs3nv7ocNHLlian2NmaoLufBeGKqMpMqIUjqkrQFYXyKY1KuUIrVaDQE8QMSq06mXkeDvHl49ecudd97weeErVtXL5nmfdcXju044j7BgeGCLaMUBnXw+7h5JsST0U853cdoFSo8HI0ZFQCObwEebGx1hZK5wU/hMjOvGYTjpmYDWrqJpx6LkveMl7Dx/YXzkNP5APH9h/8g979uy58etf/9pvry4vqzMTEwwPbyZuGGiyhKTrGzq3kJShI61QLEep1+vUnBZyJEWktYztmbixXm6469D/+rWXP/cmYOypsBDTK+VXfuLLN31ElfXuzZs3Ecltoqs/z+7BBMMJ4REayBCOKJRqdY4fG2HqgX0sHz/K7Ng4S2sFar6HuRHzxaM6mZiOa9aJRGKLr3nDW9/uuc7EaehtANBzH+odOPPsc+4Z3rz5wUNHj50/PzfH5MQ42XQ6ZGRSFNQNURsV6IhAIatRrcQxWy1MJY4eqaGVy7hqlpV6cuDWew78xVtec9VrCFUOnrT29//+rd87Mr3+x/FINNbXP4TR3kdvf57dAzEGopzkxj4JPj9grVJl5OhRZvYfYOXYcabHJ1hcWwvJwXUdKaITj6ik46H2mmU7lVe9/jXvaTSbd5+G3cMA2Gg+FKbdcftt9bPOOvObD+zbf/7Kygqjx46Tz3dhaCqaoiBHYw95QRG60zKVXAyz2cJ2TIJIhqjZwmkW0RId3Dsxe7X6pW/8b+D9T8YPv2PbcPaeY3N/vG9s5b09He10dA9g5HrZNNDJnv4Ivfpj+XFc32e1WObY4SPMHTzI8sgIs+MTLBbWqfk+9gnPF1FJxXQE38GyLfslV73qd8vF4tdPQ+5RACwXi4/4i0svvfxr3/nudb9ZWF3tnJ2ZYWx0lFQyiSpLqIqKpmmhXi7QaUC1XaPZSGJaJmXXRopmibkreFaNWrST247N/dE1F21dBj75ZPrgXd35vV+64Z4Pr1XMy4f7e0m29xPv6GVosJ1d3Rp5NSy+n/B6AuD4PkurBY4dPMz84UOsjo0xPTHJUiHMdl1DR4noxA2NRFRFwqfRagXPvvx5/6dWr/zTabj9GADW6o+MhW++6fujFz7z/G/855e/+s719XVGjo2QzWbRZBlNlpEzWeSNhCQC9CVE6p1RTDON6zhUXQ/Fc4i6q/iBTzXSKX/r7om/fukFm70nS1JSs4PXf/47d3/Asv3BrUNDRNp6SXZ0s3Uwy84uhTbpsd9jui6zC8uMHDrE8rFjrIyNMT01zWKxREMQ8DQNJaqTiGgkDAVJDKjXauzYfeYfr66s/PVpqP0EAK6urDzmL1/0kpf98/dv/MG164VCUjcMjh09RjwaDelgVZVEInmyLJOWYLBNxrKTuI6L57nUfA/V84hW1ghkjbKXjnztR2Mf3dOtp8/Ztfkv+RXxFbuC3Hfvsdk/ODS+8s5MMiENDfdjZLrJ5bvYPpRmW5v0GOX3AGg5LjNzcxzfd4CV48dZmZxkemaW5XKFhiDg6zr6xrYbjyhIgk+tWqOvb+CDtXL5T0/D7CebdNbuHdim+YjX4QP7F7fv3DV43wMPnq3pERzbQVZkDN1AkSSMiIGiqCfPiA0JFF3CFhQcB1zXxw1CMm7RriEJPo0gIs+u1p+Da3b1dab3C4JQFQSBJ+JVbrniwnr9Vbftn/r47HLlJX3dXWJHzwDRXB+9m7rZuzk83Yj9GPDVmi3GJic5/uA+Vo4dZXF8nImpGZaqVRqiBIaOEdVJRjXihoIQeNRrNbq6Nn3Q94M/9v2A06+f/JId58ePcLzy1df+/a233fbS9cJau6KojIyOYeg6kigiyxL57h50LayMyUBeBz+vQ9DGCSWWOqF8aLRWQApaVKMJ7pxovH2xdOzsc7e0/z+egNatZLrtoruOzL53ZrF8TTqRELYMD6OlukjkuhjYlGVHT4QenUe20W8UmEu1OqOjY0wfOUJhbIyFiUmmFxdZbbSwpFBQOhIJgRfVFTzXwjRNBgY2fwD4k9P+7afYgnVd+bFf+Od/+PihK5///H/4x899/v31eIKF+SXUDa8HAZIk0dWVR1W1kwXqHgOEHh1RakOSRCRBJBCEUCGoto5oNlBjKjNl7+z5u2e/vHdT+su7hzo/Ddz2uLp1SZRqpnfR7GrlDTfu2381iMn+nm7i2U60VAe5jg62DKTZ2i4/It47ERc4nsdqscjo8RHmjx1lfWKSuckpphaXKFo2tqKgGBpRQyNuqET0UInItmxv79nPeD/wodPQ+ikBmMxmf+IXr3r5NR+/7/77X3zg6MiZsqIwNzsfZoZBgBAECAh0dHahaQ8DoQ5Kt4amtKEoCoqiUpZVGpIK9SJis4Ia9ak7hnz/ZPU1R+cqLx7Ox793xnD+y5LIbfwCLf3pdHpoYn71ouPTK1ctFWrPCQQhkkunSWfbURPtJLLt9PZm2dITY1NCODm/ETzM9ZmOw9ziEqNHjrI8OkpxeoaZqSmmV9aoei6eqqIaOrGoSkxXMFSJVrOB5/nNy6648n3AR0/D6qc34RMf+8h/+4Zt23dc+du//TtfRYvq6UyWZDJJX283W4YH2b51C5uHhujsyqNp+iM8SdGF6bLHzGKD1eUixWKRer2K2SjjNCv4VgPb8aiZHnXTRZEI0nH1yOae7F3pmHZ3vi11rLszN33voePV3s42c+PwAYBSrakGnmdsH+zN3XNodKjScnc1W855i4XqeU3T6dNUNWSnT2RQYhkiqRztnW0M9SYZyim0K5xkqwoeFvNVGw2mpmcYP3KU9ckJ1qZnmJ6dY369RC3wQQ17+eIRjaguoykSjXoFzwuK11z7ht8BPn8aUj8jAP/j3//1f3zT0sLCX37i05/5g7aOHqLxGIlEkq6udjYPbmLHtm1sGR6iK9+NEYk+Ypy9CSw2AmZWLRaXqxQLJWrVCvVGFbtZxzWreFYTz3Vo2T5Ny6VlO4iiQExXa5omL6uysJyOR4qWZTZt2/bj8bhqO168Um9lfT/IW7abc11flSWJWCxCIh5HjyZRIimMRIZsW4be7hSDnQbdUR7D1UIQ4HgehWKRsbFxpo8eozw7w9rcPNPzCyxWa7QQEDQNIxJuuVFNQpVFqtUKuqbPXf2q174X+OZpOP0cW7CmKv/jm97ytrd/6MCBA2fffve9l0tyHwC+72PbLs2WSavVwrQserp7iCeSiKJ4sk44EBVI9erkUioLa1HW1pKUihVq9SrNRhLbbOLZDVS7Rdy28D0Xx/OwbDdutqx4Kwg2r5caCIKIKAqslYtIknDyaDCbiqHpBooeQdZjKEaCaCJJOpsi35Ggv92gOy48orzy8Ey30WoxNz/P+PFRlicnqCwssDQ/z/TiCoVmC1uSkHWNiKERN2QMVUYWA4rFNRKptiPv/o3ffRtw12ko/Zwe8K47fzoRy3q1svPP//zPvzG3vDbc1hHGfUY0SiqVpLe7i+1bNrN961YG+vtJZ7MoyiOa1bGBsgsrNZ+losn6eoNyuU6j3qDVamKaLRzbxHMsAs8m8FwC3w25ak4cSQgCoiQhijKirCDJGpKqI2sGuhEjkYiRycbpbIvSldboiAokxEcODIU/KsB2XArrRSYnJ5gdG6e8sEBpcZHZuXlmC0Wqjksgyyi6RtRQiRsKuiJC4FEqFunu7b/1/Auf/S6ehAKATykAfu6ffno1rcHBgSt+93d+5wuVlpPNtXcgqyq6HiESi9CRa2Pb5iF2bd/GwKZ+2ts7iMbiJ73hCXOAmgfFVkCh5lKqWFRqJvV6i1bLxDQtHCdUG/c8D9/3Tp6FiYKEKMnIcijUp+sakahBImGQSRrkkhptUZGUFm61jyGlD8DzXcrVGnNz80yNj7E6M0NtZYW15RXmlpZZrtRpESAooeZuzFCIaDKaLOK6No16gy07dn3hsue+4PeApdMQ+gUBeP311/1M31BYXbn2w3/7d59pWk4s29aOrKqomoamG6SSCTb1drNj2xaGBwfpzneRyWTRIxFE4ZFADAhbZBou1OyAmulTb3k0TBfTcrEdL5xP9jwCQoE/URZRZQldlTF0mZghkTBkErpATAGdxzYPnAS+61Kr1VlcXmZqYpKl2RnqqytUC2ssLa4wv16kZDl4ooiiKUQ0lageij1rkkizWafZavp7z3rGX7zs5a/+M6B1Gj6PAwDvvfe+n/mbRo4ffdtf/c3f/J1pe5FMWxuqqiIrWugRDYP2tgzDA/1s3TzMpv4+2ttypFJpjIiBKP54iHgb3tH2QyZWxwfP5yRRkiCAJIKy8VLFsOwj/zfX6Qc+ju1QqdVYXVlhemaWhZlZKqsrtMolioUCi6sF1upNWn6AIMtomkxUV4lqCqosIAlQrZbRNH31wosv/7/AZ07D5nEE4Ec/8jc/X80t2/aWv/3bv/tItdFMZNraUTUVRVYRFQVZUYhGInR25Bga2MTQpn56u7tpa8uSSCaJRCKoqvYY1aDHw4IgwHUcmq0WlWqVlZVV5hcWWF6Yp7y6SqNcol4uUyiWWanUqDtu6PVkOVQa1xR0NZRA9V2HUqlId0/fg69709t++/EumJ82EG6+6Yc/9zfPTk+/8hOf+MTfrVVqXelMFl3XkGUVSVYQJRlRUYhGDNpzWfp7uunv7aE730Uu10YiniAWjaLp+obMqYwgiD/zNYRxoo/jOJimSaPRYH29yMrqKotLS6ytrFAvljDrVVr1GqVyhUKtQc20cREQ5VB3V1dlIqocMj+IAmargWVZ7Dnjn M9ffOlz/hiYOQ2XXwIAv/czxoCPqeNI4sUf/shHPn7o6PHd6UwbkWgURZZDEMoKgighShK6rpNOJejsyNHd1UlHLkeuLUsqmSIWixIxjFDYWVVRJBlJlhBEEQibGsIUNsDzfDzPw3U9bNui2TJpNhpUqjXWi0UKawXW1taolIo0alXsZitkomo2qbUs6pYdNkqIIcODJksY6ob4sxxmudVqhYgRXbrksuf++fNf+JJPcApxHj7hABwb+8VHNg4fPDB8ww3f+9APb771FUgyiWQKRZFRlA1PKEoIooQgSUiyjKFrJOJxMukUmUyaTDpFOpEgGo0SiUQwdB1VVcKSiyCeLJ143v9v7/xe4yqiOP6dMzN7793dNEnzc0Osm6aNSVptWhVsFRFBKBbxyRfRv0DwySef/BcqFaUWVBAtRsQUak3xwWAVNFWKWel2U5OsTatbND/2Z+6vGR/m7ibga9Ikdgfuj6eZgfvhnDtnznxPCM/3sVZzUa3VUKlUUCyVsLpaRLG4amoYVytwazX4rin2XK2uoep58AKFQAOMGDgnSG6giwmCJQhCMNQqZfiBj/TA0KVnnzv5FoCfmohsMYCfj2/O8d2jY2P2+Phnr395YeKNv+7+3ZXc0wrbdiAEh+ACnAswbqwaYwRGBOIcQgjYtgXbthG3HTiOeZdSQggOTjySBTalCzzPh+u6jct3XfiehzDwEQYBAt9H4PvwwhB+ECJQRm6YMQZikc6hYAY+ziElQYc+yuUS2vd2LDz2+PHTT5x4+izuA53DHQHgle+ubGqHi4v5ExcmJt689mvmlOuHSLS0IBaT4MTBBQcnASIy8UEiUw6HGMAIjKGx42Fy+cicQTEZENBaQSsNaAVoDaUUtFJQyoRrQh3lmUXahuv3SMqGGAQRLEmwpFETdtdqkLFYdfTQkU9OnnrhNP5Huja7AsCpqW83vVNiZP18dfqVy5cnX5vL54+GmmA7ceOSicCJwDkHRSlbIAMbAyIdmvWK4mxD8rSOVNK1jt51XYN5Xc+1nkgKpaEiUInBgBfjsGICTAUIQh9CSj/V98DFR8aOvQPgmyYO2wDgmTNvb1nnPV3dqcxvMy9PT199dSF/64gbhLAsB9KyGi6xDmTdKrK69QM1xDHB2H+S+OvgGV2WyBqGCkqFUMoAScQagev6AiP0PSSTyVJf/4OTqb7+D3r7+iaxIdOm2e4xgOfOvb/lg7S1tvbmstkXZzIzL/0+v/Dk8krRJiHBpTT/hg13aXY8jFGM/hVZtApu2EINrdahUxssHcAgOENMclhSQHIGBgWoAEII7O3ovD56+OGvh0cOfxGG+nts09mUZtsA4PlPz9+zwdLpffaNbPapTCbzfG4290yhUBhdKZYsjQg2HsUCo7BL3dXW5c82SqczxsCZWdEKziAEQRADMR09gUQiHiYSybmB/Qd+ODj00GQYqikAd5qffQcBePa9d7dl4Hgy2VEpFY8tLS0dn529+WjhbuFQuVxOlcuVeM1di7bsGIh4wzVTVMG9HhdkUCAwMKbgOA6SiUTViTuFtvaO6z09vde6u3t/HBw8+AuAxean3qEAXrr41bZPwnVd3tHVmbqZu3Hg9u3FgWRLcv/83Hz/Wq3Suby83FoqV50gCKSGJiJSUkqvbU9Ltb29fcV24v+k0wOLxWJxobc3NT88OjKXz//xJ+6TeiW7HkANDAPI7sTJffzRhyKXy1r5W3dEtVIhz/dYLBbTiURSDab3+UPDI25zAbG7278auQ9lP0ENBAAAACV0RVh0ZGF0ZTpjcmVhdGUAMjAyMy0wMi0yMVQxODoxMjozMCswMDowMLf89hAAAAAldEVYdGRhdGU6bW9kaWZ5ADIwMjMtMDItMjFUMTg6MTI6MzArMDA6MDDGoU6sAAAAAElFTkSuQmCC" x="125" y="75" width="100" height="100" />
</svg>
}
iconType="duotone"
>
</Card>
+ <Card
+ title="LiteLLM"
+ href="/latest/integrations/liellm"
+ iconType="duotone"
+ >
+ </Card>
</CardGroup>
---
diff --git a/docs/latest/integrations/langchain.mdx b/docs/latest/integrations/langchain.mdx
new file mode 100644
index 00000000..a06b5c7a
--- /dev/null
+++ b/docs/latest/integrations/langchain.mdx
@@ -0,0 +1,48 @@
+---
+title: 'Monitor LangChain using OpenTelemetry'
+sidebarTitle: 'LangChain'
+---
+
+OpenLIT SDKs provide OpenTelemetry Auto-Instrumentation for monitoring LLM Application using LangChain which includes performance and operation stats.
+
+The integration is compatible with
+- LangChain Python SDK client `>= 0.1.1`
+
+## Get Started
+
+<Steps>
+ <Step title="Install the OpenLIT Python SDK using pip">
+ ```shell
+ pip install openlit
+ ```
+ </Step>
+ <Step title="Add the following two lines to your application code:">
+ Integrating the OpenLIT into LLM applications is straightforward. Start monitoring for your LLM Application with just **one line of code**:
+
+ ```python
+ import openlit
+
+ openlit.init(otlp_endpoint="otlp_backend_endpoint", otlp_headers="otlp_backend_token")
+ ```
+
+ Alternatively, you can configure the OTLP endpoint by setting the `OTEL_EXPORTER_OTLP_ENDPOINT` and the OTLP headers by setting the Appli`OTEL_EXPORTER_OTLP_HEADERS` environmentcation variable as recommended in the OpenTelemetry documentation.
+
+ If your aim is primarily to test or develop without sending telemetry data to an external backend, you can initialize OpenLIT without any parameters. This approach directs all telemetry output to your console, enabling quick diagnostics and local debugging:
+
+ ```python
+ import openlit
+
+ openlit.init()
+ ```
+
+ Refer to the OpenLIT [Python SDK repository](https://github.com/openlit/openlit/tree/main/sdk/python) for more advanced configurations and use cases.
+ </Step>
+</Steps>
+
+---
+
+<CardGroup cols={2}>
+<Card title="Connections" href="/latest/connections/intro" icon='link'>
+Connect to your existing Observablity Platform
+</Card>
+</CardGroup>
\ No newline at end of file
diff --git a/docs/latest/integrations/litellm.mdx b/docs/latest/integrations/litellm.mdx
new file mode 100644
index 00000000..71588b9b
--- /dev/null
+++ b/docs/latest/integrations/litellm.mdx
@@ -0,0 +1,45 @@
+---
+title: 'Monitor LiteLLM using OpenTelemetry'
+sidebarTitle: 'LiteLLM'
+---
+
+OpenLIT SDKs provide OpenTelemetry Auto-Instrumentation for monitoring LLM Application using LiteLLM which includes performance and operation stats.
+
+## Get Started
+
+<Steps>
+ <Step title="Install the OpenLIT Python SDK using pip">
+ ```shell
+ pip install openlit
+ ```
+ </Step>
+ <Step title="Add the following two lines to your application code:">
+ Integrating the OpenLIT into LLM applications is straightforward. Start monitoring for your LLM Application with just **one line of code**:
+
+ ```python
+ import openlit
+
+ openlit.init(otlp_endpoint="otlp_backend_endpoint", otlp_headers="otlp_backend_token")
+ ```
+
+ Alternatively, you can configure the OTLP endpoint by setting the `OTEL_EXPORTER_OTLP_ENDPOINT` and the OTLP headers by setting the Appli`OTEL_EXPORTER_OTLP_HEADERS` environmentcation variable as recommended in the OpenTelemetry documentation.
+
+ If your aim is primarily to test or develop without sending telemetry data to an external backend, you can initialize OpenLIT without any parameters. This approach directs all telemetry output to your console, enabling quick diagnostics and local debugging:
+
+ ```python
+ import openlit
+
+ openlit.init()
+ ```
+
+ Refer to the OpenLIT [Python SDK repository](https://github.com/openlit/openlit/tree/main/sdk/python) for more advanced configurations and use cases.
+ </Step>
+</Steps>
+
+---
+
+<CardGroup cols={2}>
+<Card title="Connections" href="/latest/connections/intro" icon='link'>
+Connect to your existing Observablity Platform
+</Card>
+</CardGroup>
\ No newline at end of file
diff --git a/docs/latest/integrations/mistral.mdx b/docs/latest/integrations/mistral.mdx
new file mode 100644
index 00000000..98527634
--- /dev/null
+++ b/docs/latest/integrations/mistral.mdx
@@ -0,0 +1,48 @@
+---
+title: 'Monitor Mistral using OpenTelemetry'
+sidebarTitle: 'Mistral'
+---
+
+OpenLIT SDKs provide OpenTelemetry Auto-Instrumentation for monitoring LLM Application using Mistral which includes performance, token and cost usage and user interactions.
+
+The integration is compatible with
+- Mistral Python SDK client `>= 0.1.0`
+
+## Get Started
+
+<Steps>
+ <Step title="Install the OpenLIT Python SDK using pip">
+ ```shell
+ pip install openlit
+ ```
+ </Step>
+ <Step title="Add the following two lines to your application code:">
+ Integrating the OpenLIT into LLM applications is straightforward. Start monitoring for your LLM Application with just **one line of code**:
+
+ ```python
+ import openlit
+
+ openlit.init(otlp_endpoint="otlp_backend_endpoint", otlp_headers="otlp_backend_token")
+ ```
+
+ Alternatively, you can configure the OTLP endpoint by setting the `OTEL_EXPORTER_OTLP_ENDPOINT` and the OTLP headers by setting the Appli`OTEL_EXPORTER_OTLP_HEADERS` environmentcation variable as recommended in the OpenTelemetry documentation.
+
+ If your aim is primarily to test or develop without sending telemetry data to an external backend, you can initialize OpenLIT without any parameters. This approach directs all telemetry output to your console, enabling quick diagnostics and local debugging:
+
+ ```python
+ import openlit
+
+ openlit.init()
+ ```
+
+ Refer to the OpenLIT [Python SDK repository](https://github.com/openlit/openlit/tree/main/sdk/python) for more advanced configurations and use cases.
+ </Step>
+</Steps>
+
+---
+
+<CardGroup cols={2}>
+<Card title="Connections" href="/latest/connections/intro" icon='link'>
+Connect to your existing Observablity Platform
+</Card>
+</CardGroup>
\ No newline at end of file
diff --git a/docs/latest/integrations/mistral/examples/embedding.mdx b/docs/latest/integrations/mistral/examples/embedding.mdx
deleted file mode 100644
index a9a3dc71..00000000
--- a/docs/latest/integrations/mistral/examples/embedding.mdx
+++ /dev/null
@@ -1,79 +0,0 @@
----
-title: 'Embedding'
-description: 'Monitor Mistral Embedding API Usage'
----
-
-<Tabs>
- <Tab title="Python">
-
- ### Synchronous Usage
-
- ```python default
- from mistralai.client import MistralClient
- import dokumetry
-
- mistral = MistralClient(
- api_key="YOUR_MISTRAL_API_KEY"
- )
-
- # Pass the above `mistral` object along with your Doku Ingester URL and API key and this will make sure that all Anthropic calls are automatically tracked.
- dokumetry.init(llm=mistral, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- response = mistral.embeddings(
- model="mistral-embed",
- input=["Monitor LLM Applications"]
- )
- print(response)
- ```
-
- ### Asynchronous usage
- ```python default
- import asyncio
- from mistralai.client import AsyncMistralClient
- import dokumetry
-
- mistral = AsyncMistralClient(
- api_key="YOUR_MISTRAL_API_KEY"
- )
-
- # Pass the above `mistral` object along with your Doku Ingester URL and API key and this will make sure that all Anthropic calls are automatically tracked.
- dokumetry.init(llm=mistral, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- async def main() -> None:
- mistral.embeddings(
- model="mistral-embed",
- input=["Monitor LLM Applications"]
- )
-
- print(response)
-
- asyncio.run(main())
- ```
- </Tab>
- <Tab title="Javascript">
-
- ```javascript default
- import MistralClient from '@mistralai/mistralai';
- import DokuMetry from 'dokumetry';
-
- const mistral = new MistralClient("YOUR_MISTRAL_API_KEY");
-
- // Pass the above `mistral` object along with your Doku Ingester URL and API key and this will make sure that all Anthropic calls are automatically tracked.
- DokuMetry.init({llm: mistral, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- async function main() {
- const input = [];
- for (let i = 0; i < 1; i++) {
- input.push('LLM Monitoring');
- }
- const embeddingsBatchResponse = await mistral.embeddings({
- model: 'mistral-embed',
- input: input,
- });
- }
-
- main();
- ```
- </Tab>
-</Tabs>
-
diff --git a/docs/latest/integrations/mistral/examples/mistral-chat.mdx b/docs/latest/integrations/mistral/examples/mistral-chat.mdx
deleted file mode 100644
index cde33eaf..00000000
--- a/docs/latest/integrations/mistral/examples/mistral-chat.mdx
+++ /dev/null
@@ -1,142 +0,0 @@
----
-title: 'Chat'
-description: 'Monitor Mistral `chat` API usage for cost, performance & user interactions'
----
-
-<Tabs>
- <Tab title="Python">
-
- ### Synchronous Usage
- <CodeGroup>
- ```python default
- from mistralai.client import MistralClient
- import dokumetry
-
- mistral = MistralClient(
- api_key="YOUR_MISTRAL_API_KEY"
- )
-
- # Pass the above `mistral` object along with your Doku Ingester URL and API key and this will make sure that all Anthropic calls are automatically tracked.
- dokumetry.init(llm=mistral, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- response = mistral.chat(
- model="mistral-small-latest",
- messages=[ChatMessage(role="user", content="Guide to Monitor my LLM Applications")],
- )
- print(response)
- ```
-
- ```python streaming
- from mistralai.client import MistralClient
- import dokumetry
-
- mistral = MistralClient(
- api_key="YOUR_MISTRAL_API_KEY"
- )
-
- # Pass the above `mistral` object along with your Doku Ingester URL and API key and this will make sure that all Anthropic calls are automatically tracked.
- dokumetry.init(llm=mistral, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- response = mistral.chat_stream(
- model="mistral-small-latest",
- messages=[ChatMessage(role="user", content="Guide to Monitor my LLM Applications")],
- )
- for chunk in response:
- print(chunk)
- ```
- </CodeGroup>
-
- ### Asynchronous usage
- <CodeGroup>
- ```python default
- import asyncio
- from mistralai.client import AsyncMistralClient
- import dokumetry
-
- mistral = AsyncMistralClient(
- api_key="YOUR_MISTRAL_API_KEY"
- )
-
- # Pass the above `mistral` object along with your Doku Ingester URL and API key and this will make sure that all Anthropic calls are automatically tracked.
- dokumetry.init(llm=mistral, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- async def main() -> None:
- response = mistral.chat(
- model="mistral-small-latest",
- messages=[ChatMessage(role="user", content="Guide to Monitor my LLM Applications")],
- )
- print(message)
-
- asyncio.run(main())
- ```
-
- ```python streaming
- import asyncio
- from mistralai.client import AsyncMistralClient
- import dokumetry
-
- mistral = AsyncMistralClient(
- api_key="YOUR_MISTRAL_API_KEY"
- )
-
- # Pass the above `mistral` object along with your Doku Ingester URL and API key and this will make sure that all Anthropic calls are automatically tracked.
- dokumetry.init(llm=mistral, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- async def main() -> None:
- response = mistral.chat_stream(
- model="mistral-small-latest",
- messages=[ChatMessage(role="user", content="Guide to Monitor my LLM Applications")],
- )
- for chunk in response:
- print(chunk)
-
- asyncio.run(main())
- ```
- </CodeGroup>
- </Tab>
- <Tab title="Javascript">
- <CodeGroup>
-
- ```javascript default
- import MistralClient from '@mistralai/mistralai';
- import DokuMetry from 'dokumetry';
-
- const mistral = new MistralClient("YOUR_MISTRAL_API_KEY");
-
- // Pass the above `mistral` object along with your Doku Ingester URL and API key and this will make sure that all Anthropic calls are automatically tracked.
- DokuMetry.init({llm: mistral, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- async function main() {
- const response = await mistral.chat({
- model: 'mistral-small-latest',
- messages: [{role: 'user', content: 'What is LLM Observability?'}],
- });
-
- console.log(response);
- }
-
- main();
- ```
-
- ```javascript streaming
- import MistralClient from '@mistralai/mistralai';
- import DokuMetry from 'dokumetry';
-
- const mistral = new MistralClient("YOUR_MISTRAL_API_KEY");
-
- // Pass the above `mistral` object along with your Doku Ingester URL and API key and this will make sure that all Anthropic calls are automatically tracked.
- DokuMetry.init({llm: mistral, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- const response = await mistral.chatStream({
- model: 'mistral-small-latest',
- messages: [{role: 'user', content: 'What is LLM Observability?'}],
- });
-
- for await (const message of response) {
- console.log(message)
- }
- ```
- </CodeGroup>
- </Tab>
-</Tabs>
-
diff --git a/docs/latest/integrations/mistral/introduction.mdx b/docs/latest/integrations/mistral/introduction.mdx
deleted file mode 100644
index 7f772eb5..00000000
--- a/docs/latest/integrations/mistral/introduction.mdx
+++ /dev/null
@@ -1,92 +0,0 @@
----
-title: 'Mistral Integration'
-sidebarTitle: 'Get Started'
----
-
-DokuMetry SDKs (`dokumetry`) empowers you to effortlessly track and monitor Mistral usage data and metrics from your Python/NodeJS code.
-
-## Get Started
-
-The integration is compatible with
-- Mistral Python SDK client `>=0.1.0`
-- Mistral JS/TS SDK client `>=0.1.0`
-
-<Tabs>
- <Tab title="Python">
- ```shell
- pip install dokumetry==0.1.1
- ```
-
- ```python
- from mistralai.client import MistralClient
- import dokumetry
-
- mistral = MistralClient(
- api_key="YOUR_MISTRAL_API_KEY"
- )
-
- dokumetry.init(llm = Mistral, doku_url = "YOUR_DOKU_INGESTER_URL", api_key = "YOUR_DOKU_TOKEN")
- ```
- </Tab>
- <Tab title="Javascript">
- ```shell
- npm install [email protected]
- ```
-
- ```javascript
- import MistralClient from '@mistralai/mistralai';
- import DokuMetry from 'dokumetry';
-
- const mistral = new MistralClient("YOUR_MISTRAL_API_KEY");
-
- DokuMetry.init({llm: mistral, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
- ```
- </Tab>
-</Tabs>
-
-## Supported Endpoints
-
-The following Mistral Endpoints are supported for monitoring with DokuMetry
-
-- [chat](/latest/integrations/mistral/examples/mistral-chat)
-- [embedding](/latest/integrations/mistral/examples/embedding)
-
-## Parameters
-<Tabs>
- <Tab title="Python">
- | Parameter | Description | Required |
- |-------------------|-----------------------------------------------------------|---------------|
- | llm | Mistral Object to track | Yes |
- | doku_url | URL of your Doku Ingester | Yes |
- | api_key | Your Doku API key | Yes |
- | environment | Custom environment tag to include in your metrics | Optional |
- | application_name | Custom application name tag for your metrics | Optional |
- | skip_resp | Skip response from the Doku Ingester for faster execution | Optional |
- </Tab>
- <Tab title="NodeJS">
- | Parameter | Description | Required |
- |-------------------|-----------------------------------------------------------|---------------|
- | llm | Mistral Object to track | Yes |
- | dokuUrl | URL of your Doku Ingester | Yes |
- | apiKey | Your Doku API key | Yes |
- | environment | Custom environment tag to include in your metrics | Optional |
- | applicationName | Custom application name tag for your metrics | Optional |
- | skipResp | Skip response from the Doku Ingester for faster execution | Optional |
- </Tab>
-</Tabs>
-
-## Advanced Usage
-When using DokuMetry in Production environments, It is recommened to set Skip response parameter to `true` for faster porcessing.
-
-To filter your LLM Usage according application or the environment, set the Application name and Environment paramaters with the actual values.
-
----
-
-<CardGroup cols={2}>
-<Card title="Connections" href="/latest/connections/intro" icon='link'>
-Connect to your existing Observablity Platform
-</Card>
-<Card title="API Reference" href="/latest/api-reference/introduction" icon='code'>
-OpenAPI specification for API Endpoints in Doku
-</Card>
-</CardGroup>
\ No newline at end of file
diff --git a/docs/latest/integrations/openai.mdx b/docs/latest/integrations/openai.mdx
new file mode 100644
index 00000000..11e0239b
--- /dev/null
+++ b/docs/latest/integrations/openai.mdx
@@ -0,0 +1,48 @@
+---
+title: 'Monitor OpenAI using OpenTelemetry'
+sidebarTitle: 'OpenAI'
+---
+
+OpenLIT SDKs provide OpenTelemetry Auto-Instrumentation for monitoring LLM Application using OpenAI which includes performance, token and cost usage and user interactions.
+
+The integration is compatible with
+- OpenAI Python SDK client `>=1.13.0`
+
+## Get Started
+
+<Steps>
+ <Step title="Install the OpenLIT Python SDK using pip">
+ ```shell
+ pip install openlit
+ ```
+ </Step>
+ <Step title="Add the following two lines to your application code:">
+ Integrating the OpenLIT into LLM applications is straightforward. Start monitoring for your LLM Application with just **one line of code**:
+
+ ```python
+ import openlit
+
+ openlit.init(otlp_endpoint="otlp_backend_endpoint", otlp_headers="otlp_backend_token")
+ ```
+
+ Alternatively, you can configure the OTLP endpoint by setting the `OTEL_EXPORTER_OTLP_ENDPOINT` and the OTLP headers by setting the Appli`OTEL_EXPORTER_OTLP_HEADERS` environmentcation variable as recommended in the OpenTelemetry documentation.
+
+ If your aim is primarily to test or develop without sending telemetry data to an external backend, you can initialize OpenLIT without any parameters. This approach directs all telemetry output to your console, enabling quick diagnostics and local debugging:
+
+ ```python
+ import openlit
+
+ openlit.init()
+ ```
+
+ Refer to the OpenLIT [Python SDK repository](https://github.com/openlit/openlit/tree/main/sdk/python) for more advanced configurations and use cases.
+ </Step>
+</Steps>
+
+---
+
+<CardGroup cols={2}>
+<Card title="Connections" href="/latest/connections/intro" icon='link'>
+Connect to your existing Observablity Platform
+</Card>
+</CardGroup>
\ No newline at end of file
diff --git a/docs/latest/integrations/openai/examples/audio.mdx b/docs/latest/integrations/openai/examples/audio.mdx
deleted file mode 100644
index 7a1108c2..00000000
--- a/docs/latest/integrations/openai/examples/audio.mdx
+++ /dev/null
@@ -1,58 +0,0 @@
----
-title: 'Audio'
-description: 'Monitor OpenAI Audio API usage'
----
-
-## Create Speech
-
-<Tabs>
- <Tab title="Python">
- ```python
- from pathlib import Path
- from openai import OpenAI
- import dokumetry
-
- client = OpenAI(
- api_key = "YOUR_OPENAI_API_KEY"
- )
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- speech_file_path = Path(__file__).parent / "speech.mp3"
- response = client.audio.speech.create(
- model= "tts-1",
- voice= "alloy",
- input= "The quick brown fox jumped over the lazy dog."
- )
- response.stream_to_file(speech_file_path)
- ```
- </Tab>
- <Tab title="NodeJS">
- ```javascript
- import fs from "fs";
- import path from "path";
- import OpenAI from "openai";
- import DokuMetry from 'dokumetry';
-
- const openai = new OpenAI();
-
- // Pass the above `openai` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- const speechFile = path.resolve("./speech.mp3");
-
- async function main() {
- const mp3 = await openai.audio.speech.create({
- model: "tts-1",
- voice: "alloy",
- input: "Today is a wonderful day to build something people love!",
- });
- console.log(speechFile);
- const buffer = Buffer.from(await mp3.arrayBuffer());
- await fs.promises.writeFile(speechFile, buffer);
- }
- main();
- ```
- </Tab>
-</Tabs>
\ No newline at end of file
diff --git a/docs/latest/integrations/openai/examples/chatCompletions.mdx b/docs/latest/integrations/openai/examples/chatCompletions.mdx
deleted file mode 100644
index f4770f05..00000000
--- a/docs/latest/integrations/openai/examples/chatCompletions.mdx
+++ /dev/null
@@ -1,472 +0,0 @@
----
-title: 'Chat Completions'
-description: 'Monitor OpenAI `chat.completions` API usage for cost, performance & user interactions'
----
-
-<Tabs>
- <Tab title="Python">
-
- ### Synchronous Usage
- <CodeGroup>
- ```python Default
- from openai import OpenAI
- import dokumetry
-
- client = OpenAI(
- api_key = "YOUR_OPENAI_API_KEY"
- )
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- completion = client.chat.completions.create(
- model="gpt-3.5-turbo",
- messages=[
- {"role": "system", "content": "You are a expert at monitoring LLM Applications"},
- {"role": "user", "content": "Hello! How do I monitor my OpenAI based LLM Applications?"}
- ]
- )
-
- print(completion.choices[0].message)
- ```
-
- ```python Image Input
- from openai import OpenAI
- import dokumetry
-
- client = OpenAI(
- api_key = "YOUR_OPENAI_API_KEY"
- )
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- response = client.chat.completions.create(
- model="gpt-4-vision-preview",
- messages=[
- {
- "role": "user",
- "content": [
- {"type": "text", "text": "What’s in this image?"},
- {
- "type": "image_url",
- "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
- },
- ],
- }
- ],
- max_tokens=300,
- )
-
- print(response.choices[0])
- ```
-
- ```python Streaming
- from openai import OpenAI
- import dokumetry
-
- client = OpenAI(
- api_key = "YOUR_OPENAI_API_KEY"
- )
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- completion = client.chat.completions.create(
- model="gpt-3.5-turbo",
- messages=[
- {"role": "system", "content": "You are a expert at monitoring LLM Applications"},
- {"role": "user", "content": "Hello! How do I monitor my OpenAI based LLM Applications?"}
- ],
- stream=True
- )
-
- for chunk in completion:
- print(chunk.choices[0].delta)
- ```
-
- ```python Functions
- from openai import OpenAI
- import dokumetry
-
- client = OpenAI(
- api_key = "YOUR_OPENAI_API_KEY"
- )
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- tools = [
- {
- "type": "function",
- "function": {
- "name": "get_current_weather",
- "description": "Get the current weather in a given location",
- "parameters": {
- "type": "object",
- "properties": {
- "location": {
- "type": "string",
- "description": "The city and state, e.g. San Francisco, CA",
- },
- "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
- },
- "required": ["location"],
- },
- }
- }
- ]
- messages = [{"role": "user", "content": "What's the weather like in Boston today?"}]
- completion = client.chat.completions.create(
- model="gpt-3.5-turbo",
- messages=messages,
- tools=tools,
- tool_choice="auto"
- )
-
- print(completion)
- ```
-
- ```python LogProbs
- from openai import OpenAI
- import dokumetry
-
- client = OpenAI(
- api_key = "YOUR_OPENAI_API_KEY"
- )
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- completion = client.chat.completions.create(
- model="gpt-3.5-turbo",
- messages=[
- {"role": "system", "content": "You are a expert at monitoring LLM Applications"},
- {"role": "user", "content": "Hello! How do I monitor my OpenAI based LLM Applications?"}
- ],
- logprobs=True,
- top_logprobs=2
- )
-
- print(completion.choices[0].message)
- print(completion.choices[0].logprobs)
- ```
- </CodeGroup>
-
- ### Asynchronous Usage
-
- <CodeGroup>
- ```python Default
- import asyncio
- from openai import AsyncOpenAI
- import dokumetry
-
- client = AsyncOpenAI(
- api_key = "YOUR_OPENAI_API_KEY"
- )
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- async def main() -> None:
- chat_completion = await client.chat.completions.create(
- messages=[
- {"role": "system", "content": "You are a expert at monitoring LLM Applications"},
- {"role": "user", "content": "Hello! How do I monitor my OpenAI based LLM Applications?"}
- ],
- model="gpt-3.5-turbo",
- )
-
- asyncio.run(main())
- ```
-
- ```python Image Input
- import asyncio
- from openai import AsyncOpenAI
- import dokumetry
-
- client = AsyncOpenAI(
- api_key = "YOUR_OPENAI_API_KEY"
- )
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- async def main() -> None:
- response = await client.chat.completions.create(
- model="gpt-4-vision-preview",
- messages=[
- {
- "role": "user",
- "content": [
- {"type": "text", "text": "What’s in this image?"},
- {
- "type": "image_url",
- "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
- },
- ],
- }
- ],
- max_tokens=300,
- )
-
- asyncio.run(main())
- ```
-
- ```python Streaming
- import asyncio
- from openai import AsyncOpenAI
- import dokumetry
-
- client = AsyncOpenAI(
- api_key = "YOUR_OPENAI_API_KEY"
- )
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- async def main():
- stream = await client.chat.completions.create(
- model="gpt-4",
- messages=[
- {"role": "system", "content": "You are a expert at monitoring LLM Applications"},
- {"role": "user", "content": "Hello! How do I monitor my OpenAI based LLM Applications?"}
- ],
- stream=True,
- )
- async for chunk in stream:
- print(chunk.choices[0].delta.content or "", end="")
-
-
- asyncio.run(main())
- ```
-
- ```python Functions
- import asyncio
- from openai import AsyncOpenAI
- import dokumetry
-
- client = AsyncOpenAI(
- api_key = "YOUR_OPENAI_API_KEY"
- )
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- tools = [
- {
- "type": "function",
- "function": {
- "name": "get_current_weather",
- "description": "Get the current weather in a given location",
- "parameters": {
- "type": "object",
- "properties": {
- "location": {
- "type": "string",
- "description": "The city and state, e.g. San Francisco, CA",
- },
- "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
- },
- "required": ["location"],
- },
- }
- }
- ]
- messages = [{"role": "user", "content": "What's the weather like in Boston today?"}]
-
- async def main() -> None:
- completion = await client.chat.completions.create(
- model="gpt-3.5-turbo",
- messages=messages,
- tools=tools,
- tool_choice="auto"
- )
-
- asyncio.run(main())
- ```
-
- ```python LogProbs
- import asyncio
- from openai import AsyncOpenAI
- import dokumetry
-
- client = AsyncOpenAI(
- api_key = "YOUR_OPENAI_API_KEY"
- )
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- async def main() -> None:
- completion = await client.chat.completions.create(
- model="gpt-3.5-turbo",
- messages=[
- {"role": "system", "content": "You are a expert at monitoring LLM Applications"},
- {"role": "user", "content": "Hello! How do I monitor my OpenAI based LLM Applications?"}
- ],
- logprobs=True,
- top_logprobs=2
- )
-
- asyncio.run(main())
- ```
- </CodeGroup>
- </Tab>
- <Tab title="NodeJS">
- <CodeGroup>
- ```javascript Default
- import OpenAI from "openai";
- import DokuMetry from 'dokumetry';
-
- const openai = new OpenAI();
-
- // Pass the above `openai` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- async function main() {
- const completion = await openai.chat.completions.create({
- messages: [
- {"role": "system", "content": "You are a expert at monitoring LLM Applications"},
- {"role": "user", "content": "Hello! How do I monitor my OpenAI based LLM Applications?"}
- ],
- model: "gpt-3.5-turbo",
- });
-
- console.log(completion.choices[0]);
- }
-
- main();
- ```
-
- ```javascript Image Input
- import OpenAI from "openai";
- import DokuMetry from 'dokumetry';
-
- const openai = new OpenAI();
-
- // Pass the above `openai` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- async function main() {
- const response = await openai.chat.completions.create({
- model: "gpt-4-vision-preview",
- messages: [
- {
- role: "user",
- content: [
- { type: "text", text: "What’s in this image?" },
- {
- type: "image_url",
- image_url:
- "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
- },
- ],
- },
- ],
- });
- console.log(response.choices[0]);
- }
- main();
- ```
-
- ```javascript Streaming
- import OpenAI from "openai";
- import DokuMetry from 'dokumetry';
-
- const openai = new OpenAI();
-
- // Pass the above `openai` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- async function main() {
- const completion = await openai.chat.completions.create({
- model: "gpt-3.5-turbo",
- messages: [
- {"role": "system", "content": "You are a expert at monitoring LLM Applications"},
- {"role": "user", "content": "Hello! How do I monitor my OpenAI based LLM Applications?"}
- ],
- stream: true,
- });
-
- for await (const chunk of completion) {
- console.log(chunk.choices[0].delta.content);
- }
- }
-
- main();
- ```
-
- ```javascript Functions
- import OpenAI from "openai";
- import DokuMetry from 'dokumetry';
-
- const openai = new OpenAI();
-
- // Pass the above `openai` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- async function main() {
- const messages = [{"role": "user", "content": "What's the weather like in Boston today?"}];
- const tools = [
- {
- "type": "function",
- "function": {
- "name": "get_current_weather",
- "description": "Get the current weather in a given location",
- "parameters": {
- "type": "object",
- "properties": {
- "location": {
- "type": "string",
- "description": "The city and state, e.g. San Francisco, CA",
- },
- "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
- },
- "required": ["location"],
- },
- }
- }
- ];
-
- const response = await openai.chat.completions.create({
- model: "gpt-3.5-turbo",
- messages: messages,
- tools: tools,
- tool_choice: "auto",
- });
-
- console.log(response);
- }
-
- main();
- ```
-
- ```javascript LogProbs
- import OpenAI from "openai";
- import DokuMetry from 'dokumetry';
-
- const openai = new OpenAI();
-
- // Pass the above `openai` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- async function main() {
- const completion = await openai.chat.completions.create({
- messages: [
- {"role": "system", "content": "You are a expert at monitoring LLM Applications"},
- {"role": "user", "content": "Hello! How do I monitor my OpenAI based LLM Applications?"}
- ],
- model: "gpt-3.5-turbo",
- logprobs: true,
- top_logprobs: 2,
- });
-
- console.log(completion.choices[0]);
- }
-
- main();
- ```
- </CodeGroup>
- </Tab>
-</Tabs>
\ No newline at end of file
diff --git a/docs/latest/integrations/openai/examples/completions.mdx b/docs/latest/integrations/openai/examples/completions.mdx
deleted file mode 100644
index 07a00c0d..00000000
--- a/docs/latest/integrations/openai/examples/completions.mdx
+++ /dev/null
@@ -1,96 +0,0 @@
----
-title: 'Completions'
-description: 'Monitor OpenAI `completions` API usage for cost, performance & user interactions'
----
-
-<Tabs>
- <Tab title="Python">
- <CodeGroup>
- ```python No Streaming
- from openai import OpenAI
- import dokumetry
-
- client = OpenAI(
- api_key = "YOUR_OPENAI_API_KEY"
- )
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- response = client.completions.create(
- model="gpt-3.5-turbo-instruct",
- prompt="What is LLM Observablity?",
- )
-
- print(respomse.choices[0].text)
- ```
-
- ```python Streaming
- from openai import OpenAI
- import dokumetry
-
- client = OpenAI(
- api_key = "YOUR_OPENAI_API_KEY"
- )
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- response = client.completions.create(
- model="gpt-3.5-turbo-instruct",
- prompt="How to monitor LLM Applications?",
- stream=True
- )
-
- for chunk in respomse:
- print(chunk.choices[0].text)
- ```
- </CodeGroup>
- </Tab>
- <Tab title="NodeJS">
- <CodeGroup>
- ```javascript No Streaming
- import OpenAI from "openai";
- import DokuMetry from 'dokumetry';
-
- const openai = new OpenAI();
-
- // Pass the above `openai` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- async function main() {
- const response = await openai.completions.create({
- model: "gpt-3.5-turbo-instruct",
- prompt: "How to monitor LLM Applications?",
- });
-
- console.log(response);
- }
- main();
- ```
-
- ```javascript Streaming
- import OpenAI from "openai";
- import DokuMetry from 'dokumetry';
-
- const openai = new OpenAI();
-
- // Pass the above `openai` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- async function main() {
- const response = await openai.completions.create({
- model: "gpt-3.5-turbo-instruct",
- prompt: "How to monitor LLM Applications?",
- stream: true,
- });
-
- for await (const chunk of response) {
- console.log(chunk.choices[0].text)
- }
- }
- main();
- ```
- </CodeGroup>
- </Tab>
-</Tabs>
\ No newline at end of file
diff --git a/docs/latest/integrations/openai/examples/embeddings.mdx b/docs/latest/integrations/openai/examples/embeddings.mdx
deleted file mode 100644
index c72bf9a9..00000000
--- a/docs/latest/integrations/openai/examples/embeddings.mdx
+++ /dev/null
@@ -1,50 +0,0 @@
----
-title: 'Embeddings'
-description: 'Monitor OpenAI Embeddings API usage'
----
-
-## Create Embeddings
-<Tabs>
- <Tab title="Python">
- ```python
- from openai import OpenAI
- import dokumetry
-
- client = OpenAI(
- api_key = "YOUR_OPENAI_API_KEY"
- )
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- client.embeddings.create(
- model="text-embedding-ada-002",
- input="The food was delicious and the waiter...",
- encoding_format="float"
- )
- ```
- </Tab>
- <Tab title="javascript">
- ```javascript
- import OpenAI from "openai";
- import DokuMetry from 'dokumetry';
-
- const openai = new OpenAI();
-
- // Pass the above `openai` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- async function main() {
- const embedding = await openai.embeddings.create({
- model: "text-embedding-ada-002",
- input: "The quick brown fox jumped over the lazy dog",
- encoding_format: "float",
- });
-
- console.log(embedding);
- }
-
- main();
- ```
- </Tab>
-</Tabs>
\ No newline at end of file
diff --git a/docs/latest/integrations/openai/examples/fine-tuning.mdx b/docs/latest/integrations/openai/examples/fine-tuning.mdx
deleted file mode 100644
index 4be10b0e..00000000
--- a/docs/latest/integrations/openai/examples/fine-tuning.mdx
+++ /dev/null
@@ -1,47 +0,0 @@
----
-title: 'Fine Tuning'
-description: 'Monitor OpenAI Fine Tuning API usage'
----
-
-## Create Fine Tuning Job
-<Tabs>
- <Tab title="Python">
- ```python
- from openai import OpenAI
- import dokumetry
-
- client = OpenAI(
- api_key = "YOUR_OPENAI_API_KEY"
- )
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- client.fine_tuning.jobs.create(
- training_file="file-abc123",
- model="gpt-3.5-turbo"
- )
- ```
- </Tab>
- <Tab title="javascript">
- ```javascript
- import OpenAI from "openai";
- import DokuMetry from 'dokumetry';
-
- const openai = new OpenAI();
-
- // Pass the above `openai` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- async function main() {
- const fineTune = await openai.fineTuning.jobs.create({
- training_file: "file-abc123"
- });
-
- console.log(fineTune);
- }
-
- main();
- ```
- </Tab>
-</Tabs>
\ No newline at end of file
diff --git a/docs/latest/integrations/openai/examples/image.mdx b/docs/latest/integrations/openai/examples/image.mdx
deleted file mode 100644
index f327ebf1..00000000
--- a/docs/latest/integrations/openai/examples/image.mdx
+++ /dev/null
@@ -1,94 +0,0 @@
----
-title: 'Image'
-description: 'Monitor OpenAI `image` API usage for cost, performance & user interactions'
----
-
-## Create Image
-
-<Tabs>
- <Tab title="Python">
- ```python
- from openai import OpenAI
- import dokumetry
-
- client = OpenAI(
- api_key = "YOUR_OPENAI_API_KEY"
- )
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- image = client.images.generate(
- model="dall-e-3",
- prompt="Create a dashboard for LLM Observability data",
- n=1,
- size="1024x1024"
- )
-
- print(image.data)
- ```
- </Tab>
- <Tab title="Javascript">
- ```javascript
- import OpenAI from "openai";
- import DokuMetry from 'dokumetry';
-
- const openai = new OpenAI();
-
- // Pass the above `openai` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- async function main() {
- const image = await openai.images.generate({ model: "dall-e-3", prompt: "Create a dashboard for LLM Observability data" });
-
- console.log(image.data);
- }
- main();
- ```
- </Tab>
-</Tabs>
-
-## Create Image Variation
-
-<Tabs>
- <Tab title="Python">
- ```python
- from openai import OpenAI
- import dokumetry
-
- client = OpenAI(
- api_key = "YOUR_OPENAI_API_KEY"
- )
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-
- response = client.images.create_variation(
- image=open("image_edit_original.png", "rb"),
- n=2,
- size="1024x1024"
- )
- ```
- </Tab>
- <Tab title="Javascript">
- ```javascript
- import fs from "fs";
- import OpenAI from "openai";
- import DokuMetry from 'dokumetry';
-
- const openai = new OpenAI();
-
- // Pass the above `openai` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
- async function main() {
- const image = await openai.images.createVariation({
- image: fs.createReadStream("otter.png"),
- });
-
- console.log(image.data);
- }
- main();
- ```
- </Tab>
-</Tabs>
\ No newline at end of file
diff --git a/docs/latest/integrations/openai/introduction.mdx b/docs/latest/integrations/openai/introduction.mdx
deleted file mode 100644
index 041ad753..00000000
--- a/docs/latest/integrations/openai/introduction.mdx
+++ /dev/null
@@ -1,95 +0,0 @@
----
-title: 'OpenAI Integration'
-sidebarTitle: 'Get Started'
----
-
-DokuMetry SDKs (`dokumetry`) empowers you to effortlessly track and monitor OpenAI usage data and metrics from your Python/NodeJS code.
-
-## Get Started
-
-The integration is compatible with
-- OpenAI Python SDK client `>=1.13.0`
-- OpenAI JS/TS SDK client `>=4.28.0`
-
-<Tabs>
- <Tab title="Python">
- ```shell
- pip install dokumetry==0.1.1
- ```
-
- ```python
- from openai import OpenAI
- import dokumetry
-
- client = OpenAI()
-
- dokumetry.init(llm = client, doku_url = "YOUR_DOKU_INGESTER_URL", api_key = "YOUR_DOKU_TOKEN")
- ```
- </Tab>
- <Tab title="Javascript">
- ```shell
- npm install [email protected]
- ```
-
- ```javascript
- import OpenAI from "openai";
- import DokuMetry from 'dokumetry';
-
- const client = new OpenAI();
-
- DokuMetry.init({llm: client, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
- ```
- </Tab>
-</Tabs>
-
-## Supported Endpoints
-
-The following OpenAI Endpoints are supported for monitoring with DokuMetry
-
-- [Chat completions](/latest/integrations/openai/examples/chatCompletions)
-- [Image Create](/latest/integrations/openai/examples/image#create-image) and [Image Variations](/latest/integrations/openai/examples/image#create-image-variation)
-- [Audio Speech Create](/latest/integrations/openai/examples/audio)
-- [Embeddings](/latest/integrations/openai/examples/embeddings)
-- [Fine Tunings](/latest/integrations/openai/examples/fine-tuning)
-- [Completions](/latest/integrations/openai/examples/completions)
-
-## Parameters
-
-<Tabs>
- <Tab title="Python">
- | Parameter | Description | Required |
- |-------------------|-----------------------------------------------------------|---------------|
- | llm | OpenAI Object to track | Yes |
- | doku_url | URL of your Doku Ingester | Yes |
- | api_key | Your Doku API key | Yes |
- | environment | Custom environment tag to include in your metrics | Optional |
- | application_name | Custom application name tag for your metrics | Optional |
- | skip_resp | Skip response from the Doku Ingester for faster execution | Optional |
- </Tab>
- <Tab title="NodeJS">
- | Parameter | Description | Required |
- |-------------------|-----------------------------------------------------------|---------------|
- | llm | OpenAI Object to track | Yes |
- | dokuUrl | URL of your Doku Ingester | Yes |
- | apiKey | Your Doku API key | Yes |
- | environment | Custom environment tag to include in your metrics | Optional |
- | applicationName | Custom application name tag for your metrics | Optional |
- | skipResp | Skip response from the Doku Ingester for faster execution | Optional |
- </Tab>
-</Tabs>
-
-## Advanced Usage
-When using DokuMetry in Production environments, It is recommened to set Skip response parameter to `true` for faster porcessing.
-
-To filter your LLM Usage according application or the environment, set the Application name and Environment paramaters with the actual values.
-
----
-
-<CardGroup cols={2}>
-<Card title="Connections" href="/latest/connections/intro" icon='link'>
-Connect to your existing Observablity Platform
-</Card>
-<Card title="API Reference" href="/latest/api-reference/introduction" icon='code'>
-OpenAPI specification for API Endpoints in Doku
-</Card>
-</CardGroup>
\ No newline at end of file
diff --git a/docs/latest/integrations/pinecone.mdx b/docs/latest/integrations/pinecone.mdx
new file mode 100644
index 00000000..840ec80e
--- /dev/null
+++ b/docs/latest/integrations/pinecone.mdx
@@ -0,0 +1,48 @@
+---
+title: 'Monitor Pinecone using OpenTelemetry'
+sidebarTitle: 'Pinecone'
+---
+
+OpenLIT SDKs provide OpenTelemetry Auto-Instrumentation for monitoring LLM Application using Pinecone which includes performance, Operation stats and more.
+
+The integration is compatible with
+- PineCone Python SDK client `>=2.2.0`
+
+## Get Started
+
+<Steps>
+ <Step title="Install the OpenLIT Python SDK using pip">
+ ```shell
+ pip install openlit
+ ```
+ </Step>
+ <Step title="Add the following two lines to your application code:">
+ Integrating the OpenLIT into LLM applications is straightforward. Start monitoring for your LLM Application with just **one line of code**:
+
+ ```python
+ import openlit
+
+ openlit.init(otlp_endpoint="otlp_backend_endpoint", otlp_headers="otlp_backend_token")
+ ```
+
+ Alternatively, you can configure the OTLP endpoint by setting the `OTEL_EXPORTER_OTLP_ENDPOINT` and the OTLP headers by setting the Appli`OTEL_EXPORTER_OTLP_HEADERS` environmentcation variable as recommended in the OpenTelemetry documentation.
+
+ If your aim is primarily to test or develop without sending telemetry data to an external backend, you can initialize OpenLIT without any parameters. This approach directs all telemetry output to your console, enabling quick diagnostics and local debugging:
+
+ ```python
+ import openlit
+
+ openlit.init()
+ ```
+
+ Refer to the OpenLIT [Python SDK repository](https://github.com/openlit/openlit/tree/main/sdk/python) for more advanced configurations and use cases.
+ </Step>
+</Steps>
+
+---
+
+<CardGroup cols={2}>
+<Card title="Connections" href="/latest/connections/intro" icon='link'>
+Connect to your existing Observablity Platform
+</Card>
+</CardGroup>
\ No newline at end of file
diff --git a/docs/latest/introduction.mdx b/docs/latest/introduction.mdx
index b373823c..d97aa115 100644
--- a/docs/latest/introduction.mdx
+++ b/docs/latest/introduction.mdx
@@ -1,77 +1,36 @@
---
-title: What is Doku?
-description: 'Open-source platform for monitoring and evaluating LLMs at scale'
+title: What is OpenLIT?
+description: 'OpenTelemetry-native GenAI and LLM Application Observability'
---
-<iframe
- width="560"
- height="315"
- src="https://www.youtube.com/embed/6jhxVesllEY?si=M8dkLVVE2G7WhmBo"
- title="Demo: Monitoring LLM Application with Doku"
- frameborder="0"
- allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; playsinline"
- allowfullscreen
-></iframe>
-
-Doku is an **open-source LLMOps tool** engineered to enables developers with comprehensive capabilities to monitor, analyze, and optimize LLM applications. It provides valuable real-time data on **LLM usage, performance, and costs**. Through seamless integrations with leading LLM platforms, including OpenAI, Cohere, and Anthropic, Doku acts as a central command center for all your LLM needs. It effectively guides your efforts, ensuring that your LLM applications not only operate at peak efficiency but also scale successfully.
-
-## Why use Doku?
-Get advanced monitoring and evaluation for your LLM applications with these key benefits:
-
-- **Granular Usage Insights of your LLM Applications**: Assess your LLM's performance and costs with fine-grained control, breaking down metrics by environment (such as staging or production) or application, to optimize for efficiency and scalability.
-- **Real-Time Data Streaming**: Unlike other platforms where you might wait minutes to see your data due to data being sent in batches, Doku is able to display data as it streams. This immediate insight enables quick decision-making and adjustments.
-- **Zero Added Latency**: Doku's smart data handling ensures rapid data processing without impacting your application's performance, maintaining the responsiveness of your LLM applications.
-- **Connect to Observability Platforms**: Doku seamlessly connects with leading observability platforms like Grafana Cloud and Datadog, among others to automatically export data.
-
-## How it works
<Frame>
- <img src="https://github.com/dokulabs/.github/blob/main/profile/assets/white-docs-connections-banner.gif?raw=true" />
+ <img src="https://github.com/openlit/.github/blob/main/profile/assets/github-readme-main-banner.png?raw=true" />
</Frame>
-### Step 1: Instrument your Application
-Integrating the `dokumetry` SDK into LLM applications is straightforward with SDKs designed for Python and NodeJS. Start monitoring for your LLM Application with just **two lines of code**:
-
-<CodeGroup>
-```python python
-import dokumetry
-
-dokumetry.init(llm=openai, doku_url="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")
-```
+OpenLIT is an **OpenTelemetry-native** GenAI and LLM Application Observability tool. It's designed to make the integration process of observability into GenAI projects as easy as pie – literally, with just **a single line of code**. Whether you're working with popular LLM Libraries such as OpenAI and HuggingFace or leveraging vector databases like ChromaDB, OpenLIT ensures your applications are monitored seamlessly, providing critical insights to improve performance and reliability.
-```javascript NodeJS
-import DokuMetry from 'dokumetry';
+This project proudly follows the [Semantic Conventions](https://github.com/open-telemetry/semantic-conventions/tree/main/docs/gen-ai) of the OpenTelemetry community, consistently updating to align with the latest standards in observability.
-DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})
-```
-</CodeGroup>
+## What is LIT?
+LIT stands for Learning Interpretability Tool. It refers to a visual, interactive model-understanding and data visualization tool ad a term introduced by [Google](https://developers.google.com/machine-learning/glossary#learning-interpretability-tool-lit).
-### Step 2: Data processed by Doku Ingester
-Once the `dokumetry` SDKs are configured in your LLM application, Monitoring data starts streaming to the [Doku Ingester](https://github.com/dokulabs/doku/tree/main/src/ingester#readme). It processes and safely stores your data in ClickHouse, keeping your LLM Monitoring data **secure** and **compliant** in your environment.
-
-You can choose to use a new ClickHouse database setup or connect to your existing one to work with Doku.
-
-### Step 3: Visualize and analyze
-With your LLM monitoring data processed and securely stored, you can now leverage the Doku UI for in-depth visualization and analysis. Doku UI allows you to explore LLM costs, token usage, performance metrics, and user interactions in an intuitive interface. This powerful tool enhances your ability to observe and optimize your LLM applications, ensuring you make data-driven decisions for improvement.
-
-<Frame>
- <img src="https://github.com/dokulabs/.github/blob/main/profile/assets/doku-client-1.jpg?raw=true" />
- <img src="https://github.com/dokulabs/.github/blob/main/profile/assets/doku-client-2.jpg?raw=true" />
- <img src="https://github.com/dokulabs/.github/blob/main/profile/assets/doku-client-3.jpg?raw=true" />
-</Frame>
+## ⚡ Features
+- **OpenTelemetry-native**: Native support ensures that integrating OpenLIT into your projects feels more like a natural extension rather than an additional layer of complexity.
+- **Granular Usage Insights of your LLM Applications**: Assess your LLM's performance and costs with fine-grained control, breaking down metrics by environment (such as staging or production) or application, to optimize for efficiency and scalability.
+- **Vendor-Neutral SDKs**: In the spirit of OpenTelemetry, OpenLIT's SDKs are agnostic of the backend vendors. This means you can confidently use OpenLIT with various telemetry backends, like Grafana Tempo, without worrying about compatibility issues.
-For those with a preferred observability platform, you can also integrate and visualize this data elsewhere with ease. This flexibility ensures optimal monitoring workflow integration, regardless of your platform choice. For more details on how to set up these connections, check out the [Connections](/latest/connections/intro) guide.
## Getting Started
-Select from the following guides to learn more about how to use Doku:
+Select from the following guides to learn more about how to use OpenLIT:
<CardGroup cols={2}>
<Card title="Quickstart" href="/latest/quickstart" icon='bolt'>
Get Started with monitoring your LLM Applications in 2 simple steps
</Card>
<Card title="Integrations" href="/latest/integrations/introduction" icon='circle-nodes'>
-Integrate your LLM Provider with Doku
+Integrate your LLM Provider with OpenLIT
</Card>
<Card title="Installation" href="/latest/installation" icon='circle-down'>
-Deploy Doku in your preferred environment
+Deploy OpenLIT in your preferred environment
</Card>
<Card title="Connections" href="/latest/connections/intro" icon='link'>
Connect to your existing Observablity Platform
diff --git a/docs/latest/quickstart.mdx b/docs/latest/quickstart.mdx
index 26e596bf..2db14e76 100644
--- a/docs/latest/quickstart.mdx
+++ b/docs/latest/quickstart.mdx
@@ -1,197 +1,84 @@
---
title: 'Quickstart'
-description: 'Quickly start **monitoring** your **LLM Applications** in just **two lines** of code'
+description: 'Quickly start **monitoring** your **LLM Applications** in just **a single line** of code'
icon: 'bolt'
---
-This guide will walk you through setting up monitoring for your LLM Application with minimal effort. In just a few steps, you'll be able to track and analyze the performance and usage of your Large Language Model (LLM) applications.
+This guide will walk you through setting up OpenTelemetry Auto Instrumentation for monitoring your LLM Application. In just a few steps, you'll be able to track and analyze the performance and usage of your GenAI and LLM Applications.
+In this guide, we'll show how you can send OpenTelemetry traces and metrics from your LLM Applications to Grafana Cloud
<Steps>
- <Step title="Deploy Doku">
- <Steps>
- <Step title="Prepare your Environment">
- ```yaml docker-compose.yml
- version: '3.8'
-
- services:
- clickhouse:
- image: clickhouse/clickhouse-server:24.2.2
- container_name: clickhouse
- environment:
- CLICKHOUSE_PASSWORD: ${DOKU_DB_PASSWORD:-DOKU}
- CLICKHOUSE_USER: ${DOKU_DB_USER:-default}
- volumes:
- - clickhouse-data:/var/lib/clickhouse
- ports:
- - "9000:9000"
- - "8123:8123"
- restart: always
-
- doku-ingester:
- image: ghcr.io/dokulabs/doku-ingester:0.1.3
- container_name: doku-ingester
- environment:
- DOKU_DB_HOST: clickhouse
- DOKU_DB_PORT: 9000
- DOKU_DB_NAME: ${DOKU_DB_NAME:-default}
- DOKU_DB_USER: ${DOKU_DB_USER:-default}
- DOKU_DB_PASSWORD: ${DOKU_DB_PASSWORD:-DOKU}
- ports:
- - "9044:9044"
- depends_on:
- - clickhouse
- restart: always
-
- doku-client:
- image: ghcr.io/dokulabs/doku-client:0.1.3
- container_name: doku-client
- environment:
- INIT_DB_HOST: clickhouse
- INIT_DB_PORT: 8123
- INIT_DB_DATABASE: ${DOKU_DB_NAME:-default}
- INIT_DB_USERNAME: ${DOKU_DB_USER:-default}
- INIT_DB_PASSWORD: ${DOKU_DB_PASSWORD:-DOKU}
- SQLITE_DATABASE_URL: file:/app/client/data/data.db
- ports:
- - "3000:3000"
- depends_on:
- - clickhouse
- volumes:
- - doku-client-data:/app/client/data
- restart: always
-
- volumes:
- clickhouse-data:
- doku-client-data:
- ```
- </Step>
- <Step title="Launch Doku">
- ```shell
- docker-compose up -d
- ```
- </Step>
- </Steps>
- </Step>
- <Step title="Access Doku UI and Generate an API Key">
- With Doku running, the next step is to access the Doku UI and generate an API key for secure communication between your applications and Doku.
- 1. Open your browser and go to Doku UI at `127.0.0.1:3000/login`
- 2. Login using theb default credentials
- - Email as `[email protected]`
- - Password as `dokulabsuser`
- 3. Once you have logged into Doku UI, Go to [API Keys page](http://127.0.0.1:3000/api-keys) and Create an API Key. Copy the generated API Key.
-
- <Tip>Alternatively, you can use the HTTP API to create your Doku API Key. For further details, take a look at the [API Reference](/latest/api-reference/endpoint/api-keys/create) section.</Tip>
- </Step>
- <Step title="Instrument your Application">
- Choose the appropriate SDK for your LLM application's programming language and follow the steps to integrate monitoring with just **two lines of code**.
- <Tabs>
- <Tab title="Python">
- <Steps>
- <Step title="Install the dokumetry Python SDK using pip">
- ```shell
- pip install dokumetry
- ```
- </Step>
- <Step title="Add the following two lines to your application code:">
- Add the snippet below to your Python application, replace `YOUR_DOKU_TOKEN` with API key you created in Step 2.
-
- ```python
- import dokumetry
-
- dokumetry.init(llm=client, doku_url="http://127.0.0.1:9044/", api_key="YOUR_DOKU_TOKEN")
- ```
-
- Example Usage for monitoring `OpenAI` Usage:
-
- ```python
- from openai import OpenAI
- import dokumetry
-
- client = OpenAI(
- api_key="YOUR_OPENAI_KEY"
- )
-
- # Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- dokumetry.init(llm=client, doku_url="http://127.0.0.1:9044/", api_key="YOUR_DOKU_TOKEN")
-
- chat_completion = client.chat.completions.create(
- messages=[
- {
- "role": "user",
- "content": "What is LLM Observability",
- }
- ],
- model="gpt-3.5-turbo",
- )
- ```
-
- Refer to the `dokumetry` [Python SDK repository](https://github.com/dokulabs/dokumetry-python) for more advanced configurations and use cases.
- </Step>
- </Steps>
- </Tab>
- <Tab title="NodeJS">
- <Steps>
- <Step title="Install the dokumetry NodeJS SDK using npm">
- ```shell
- npm install dokumetry
- ```
- </Step>
- <Step title="Add the following two lines to your application code">
- Add the snippet below to your NodeJS application, replace `YOUR_DOKU_TOKEN` with API key you created in Step 2.
- ```javascript
- import DokuMetry from 'dokumetry';
-
- DokuMetry.init({llm: openai, dokuUrl: "http://127.0.0.1:9044/", apiKey: "YOUR_DOKU_TOKEN"})
- ```
-
- Example Usage for monitoring `OpenAI` Usage:
-
- ```javascript
- import OpenAI from 'openai';
- import DokuMetry from 'dokumetry';
-
- const openai = new OpenAI({
- apiKey: 'My API Key', // defaults to process.env["OPENAI_API_KEY"]
- });
-
- // Pass the above `openai` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- DokuMetry.init({llm: openai, dokuUrl: "http://127.0.0.1:9044/", apiKey: "YOUR_DOKU_TOKEN"})
-
- async function main() {
- const chatCompletion = await openai.chat.completions.create({
- messages: [{ role: 'user', content: 'What are the key to effective observability?' }],
- model: 'gpt-3.5-turbo',
- });
- }
-
- main();
- ```
-
- Refer to the `dokumetry` [NodeJS SDK repository](https://github.com/dokulabs/dokumetry-node) for more advanced configurations and use cases.
- </Step>
- </Steps>
- </Tab>
- </Tabs>
- </Step>
- <Step title="Visualize and Analyze">
- Once you have Doku Ingester and `DokuMetry` SKDs set up, you can instantly get insights into how your LLM applications. Just head over to Doku UI at `127.0.0.1:3000` on your browser to start exploring.
-
-With Doku, you get a simple, powerful view into important info like how much you're spending on LLMs, which parts of your app are using them the most, and how well they're performing. Find out which LLM models are favorites among your applications, and dive deep into performance details to make smart decisions. This setup is perfect for optimizing your app performance and keeping an eye on costs.
- <Frame>
- <img src="https://github.com/dokulabs/.github/blob/main/profile/assets/doku-client-1.jpg?raw=true" />
- <img src="https://github.com/dokulabs/.github/blob/main/profile/assets/doku-client-2.jpg?raw=true" />
- <img src="https://github.com/dokulabs/.github/blob/main/profile/assets/doku-client-3.jpg?raw=true" />
- </Frame>
- </Step>
+ <Step title="Install the OpenLIT Python SDK using pip">
+ ```shell
+ pip install openlit
+ ```
+ </Step>
+ <Step title="Add the following two lines to your application code:">
+ Add the snippet below to your Python application.
+
+ ```python
+ openlit.init(
+ otlp_endpoint="https://otlp-gateway-prod-us-east-0.grafana.net/otlp",
+ otlp_headers="Authorization=Basic%20<base64 encoded Instance ID and API Token>"
+ )
+ ```
+
+ Alternatively, You can also choose to set these values using `OTEL_EXPORTER_OTLP_ENDPOINT` and `OTEL_EXPORTER_OTLP_HEADERS` environment variables
+
+ ```python
+ openlit.init()
+ ```
+
+ ```env
+ export OTEL_EXPORTER_OTLP_ENDPOINT = "https://otlp-gateway-prod-us-east-0.grafana.net/otlp"
+ export OTEL_EXPORTER_OTLP_HEADERS = "Authorization=Basic%20<base64 encoded Instance ID and API Token>"
+ ```
+
+ Example Usage for monitoring `OpenAI` Usage:
+
+ ```python
+ from openai import OpenAI
+ import openlit
+
+ openlit.init()
+
+ client = OpenAI(
+ api_key="YOUR_OPENAI_KEY"
+ )
+
+ chat_completion = client.chat.completions.create(
+ messages=[
+ {
+ "role": "user",
+ "content": "What is LLM Observability",
+ }
+ ],
+ model="gpt-3.5-turbo",
+ )
+ ```
+
+ Refer to the OpenLIT [Python SDK repository](https://github.com/openlit/openlit/tree/main/sdk/python) for more advanced configurations and use cases.
+ </Step>
+ <Step title="Visualize and Analyze in Grafana">
+ With the LLM Observability data now being collected and sent to your chosen OpenTelemetry backend, the next step is to visualize and analyze this data to glean insights into your application's performance, behavior, and identify areas of improvement. Here is how you would use the data in Grafana, follow these detailed instructions to explore your LLM application's Telemetry data.
+
+ - Select the **Explore** option from Grafana's sidebar.
+ - At the top, ensure the correct Tempo data source is selected from the dropdown menu.
+ - Use the **Query** field to specify any particular traces you are interested in, or leave it empty to browse through all the available traces.
+ - You can adjust the time range to focus on specific periods of interest.
+ - Hit **Run Query** to fetch your trace data. You'll see a visual representation of your traces along with detailed information on particular spans when clicked.
+ </Step>
</Steps>
-You're all set! Following these steps should have you on your way to effectively monitoring your LLM applications. If you have any questions or need support, reach out to our [community](https://join.slack.com/t/doku-0tq5728/shared_invite/zt-2a9aql9xx-FN5EIZ2DtZ~XtJoYdxUDtA).
+You're all set! Following these steps should have you on your way to effectively monitoring your LLM applications.
+
+If you have any questions or need support, reach out to our [community](https://join.slack.com/t/openlit/shared_invite/zt-2etnfttwg-TjP_7BZXfYg84oAukY8QRQ).
---
<CardGroup cols={2}>
<Card title="Integrations" href="/latest/integrations/introduction" icon='circle-nodes'>
-Integrate your LLM Provider with Doku
+Integrate your LLM Provider with OpenLIT
</Card>
<Card title="Connections" href="/latest/connections/intro" icon='link'>
Connect to your existing Observablity Platform
diff --git a/docs/mint.json b/docs/mint.json
index 7ffe1561..d4330e02 100644
--- a/docs/mint.json
+++ b/docs/mint.json
@@ -45,9 +45,7 @@
"group": "Introduction",
"pages": [
"latest/introduction",
- "latest/quickstart",
- "latest/installation",
- "latest/configuration"
+ "latest/quickstart"
],
"version": "latest"
},
@@ -57,85 +55,31 @@
"pages": [
"latest/integrations/introduction",
{
- "group": "OpenAI",
+ "group": "LLMs",
"version": "latest",
"pages": [
- "latest/integrations/openai/introduction",
- {
- "group": "Examples",
- "version": "latest",
- "pages": [
- "latest/integrations/openai/examples/chatCompletions",
- "latest/integrations/openai/examples/image",
- "latest/integrations/openai/examples/embeddings",
- "latest/integrations/openai/examples/audio",
- "latest/integrations/openai/examples/fine-tuning",
- "latest/integrations/openai/examples/completions"
- ]
- }
+ "latest/integrations/openai",
+ "latest/integrations/anthropic",
+ "latest/integrations/cohere",
+ "latest/integrations/mistral",
+ "latest/integrations/azure-openai",
+ "latest/integrations/huggingface"
]
},
{
- "group": "Cohere",
+ "group": "VectorDBs",
"version": "latest",
"pages": [
- "latest/integrations/cohere/introduction",
- {
- "group": "Examples",
- "version": "latest",
- "pages": [
- "latest/integrations/cohere/examples/cochat",
- "latest/integrations/cohere/examples/generate",
- "latest/integrations/cohere/examples/summarize",
- "latest/integrations/cohere/examples/embed"
- ]
- }
+ "latest/integrations/chromadb",
+ "latest/integrations/pinecone"
]
},
{
- "group": "Anthropic",
+ "group": "Frameworks",
"version": "latest",
"pages": [
- "latest/integrations/anthropic/introduction",
- {
- "group": "Examples",
- "version": "latest",
- "pages": [
- "latest/integrations/anthropic/examples/messages"
- ]
- }
- ]
- },
- {
- "group": "Mistral",
- "version": "latest",
- "pages": [
- "latest/integrations/mistral/introduction",
- {
- "group": "Examples",
- "version": "latest",
- "pages": [
- "latest/integrations/mistral/examples/mistral-chat",
- "latest/integrations/mistral/examples/embedding"
- ]
- }
- ]
- },
- {
- "group": "Azure OpenAI",
- "version": "latest",
- "pages": [
- "latest/integrations/azure-openai/introduction",
- {
- "group": "Examples",
- "version": "latest",
- "pages": [
- "latest/integrations/azure-openai/examples/chat",
- "latest/integrations/azure-openai/examples/image",
- "latest/integrations/azure-openai/examples/embeddings",
- "latest/integrations/azure-openai/examples/completions"
- ]
- }
+ "latest/integrations/langchain",
+ "latest/integrations/litellm"
]
}
]
@@ -144,39 +88,12 @@
"group": "Connections",
"pages": [
"latest/connections/intro",
- "latest/connections/grafanaoss",
- "latest/connections/grafanacloud",
"latest/connections/datadog",
- "latest/connections/new-relic",
+ "latest/connections/grafana-tempo",
+ "latest/connections/grafanacloud",
+ "latest/connections/dynatrace",
"latest/connections/signoz",
- "latest/connections/dynatrace"
- ],
- "version": "latest"
- },
- {
- "group": "API Reference",
- "pages": [
- "latest/api-reference/introduction",
- {
- "group": "API Keys",
- "icon": "key",
- "pages": [
- "latest/api-reference/endpoint/api-keys/create",
- "latest/api-reference/endpoint/api-keys/get",
- "latest/api-reference/endpoint/api-keys/delete"
- ],
- "version": "latest"
- },
- {
- "group": "Connections",
- "icon": "link",
- "pages": [
- "latest/api-reference/endpoint/connections/create",
- "latest/api-reference/endpoint/connections/delete",
- "latest/api-reference/endpoint/connections/get"
- ],
- "version": "latest"
- }
+ "latest/connections/new-relic"
],
"version": "latest"
}