Skip to content

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

Add docs for `0.0.2` (#51)

Patcher995bd4a67fc05d
diff --git a/README.md b/README.md
index 0ebcb1a9..9339e3e3 100644
--- a/README.md
+++ b/README.md
@@ -144,7 +144,7 @@ Add the following two lines to your application code:
```javascript
import DokuMetry from 'dokumetry';
-DokuMetry.init({llm: openai, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
```
##### Example Usage for monitoring `OpenAI` Usage:
@@ -158,7 +158,7 @@ const openai = new OpenAI({
});
// Pass the above `openai` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
-DokuMetry.init({llm: openai, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
async function main() {
const chatCompletion = await openai.chat.completions.create({
diff --git a/docs/0.0.1/dokumetry/node/examples/anthropic/anthropic-completions.mdx b/docs/0.0.1/dokumetry/node/examples/anthropic/anthropic-completions.mdx
index 946996fb..6fbff10e 100644
--- a/docs/0.0.1/dokumetry/node/examples/anthropic/anthropic-completions.mdx
+++ b/docs/0.0.1/dokumetry/node/examples/anthropic/anthropic-completions.mdx
@@ -14,7 +14,7 @@ const anthropic = new Anthropic({
});
// Pass the above `anthropic` object along with your DOKU URL and API key and this will make sure that all Anthropic calls are automatically tracked.
-DokuMetry.init({llm: anthropic, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+DokuMetry.init({llm: anthropic, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
async function main() {
const completion = await anthropic.completions.create({
diff --git a/docs/0.0.1/dokumetry/node/examples/cohere/chat.mdx b/docs/0.0.1/dokumetry/node/examples/cohere/chat.mdx
index c806e971..fdc6a559 100644
--- a/docs/0.0.1/dokumetry/node/examples/cohere/chat.mdx
+++ b/docs/0.0.1/dokumetry/node/examples/cohere/chat.mdx
@@ -7,35 +7,38 @@ description: 'Monitor Cohere Chat API usage'
<CodeGroup>
```javascript No Streaming
-const { CohereClient } = require("cohere-ai");
+import { CohereClient } from "cohere-ai";
import DokuMetry from 'dokumetry';
const cohere = new CohereClient({
token: "<<apiKey>>",
});
-// Pass the above `cohere` object along with your DOKU URL and API key and this will make sure that all Cohere calls are automatically tracked.
-DokuMetry.init({llm: cohere, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+(async () => {
+ // Pass the above `cohere` object along with your DOKU URL and API key and this will make sure that all Cohere calls are automatically tracked.
+ DokuMetry.init({llm: cohere, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
-const response = await cohere.chat({
+ const response = await cohere.chat({
message: 'Say this is a test',
model: 'command',
- });
-print(response)
+ });
+
+ console.log(response)
+})();
```
```javascript Streaming
-const { CohereClient } = require("cohere-ai");
+import { CohereClient } from "cohere-ai";
import DokuMetry from 'dokumetry';
const cohere = new CohereClient({
token: "<<apiKey>>",
});
-// Pass the above `cohere` object along with your DOKU URL and API key and this will make sure that all Cohere calls are automatically tracked.
-DokuMetry.init({llm: cohere, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
(async () => {
+ // Pass the above `cohere` object along with your DOKU URL and API key and this will make sure that all Cohere calls are automatically tracked.
+ DokuMetry.init({llm: cohere, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+
const chatStream = await cohere.chatStream({
chatHistory: [
{ role: "USER", message: "Who discovered gravity?" },
diff --git a/docs/0.0.1/dokumetry/node/examples/cohere/embed.mdx b/docs/0.0.1/dokumetry/node/examples/cohere/embed.mdx
index d6a3fc53..e11ba206 100644
--- a/docs/0.0.1/dokumetry/node/examples/cohere/embed.mdx
+++ b/docs/0.0.1/dokumetry/node/examples/cohere/embed.mdx
@@ -6,17 +6,17 @@ description: 'Monitor Cohere Embed API usage'
## Embed
```javascript
-const { CohereClient } = require("cohere-ai");
+import { CohereClient } from "cohere-ai";
import DokuMetry from 'dokumetry';
const cohere = new CohereClient({
token: "<<apiKey>>",
});
-// Pass the above `cohere` object along with your DOKU URL and API key and this will make sure that all Cohere calls are automatically tracked.
-DokuMetry.init({llm: cohere, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
(async () => {
+ // Pass the above `cohere` object along with your DOKU URL and API key and this will make sure that all Cohere calls are automatically tracked.
+ DokuMetry.init({llm: cohere, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+
const embed = await cohere.embed({
texts: ["hello", "goodbye"],
model: "embed-english-v3.0",
diff --git a/docs/0.0.1/dokumetry/node/examples/cohere/generate.mdx b/docs/0.0.1/dokumetry/node/examples/cohere/generate.mdx
index b7a3035d..b48cdd1c 100644
--- a/docs/0.0.1/dokumetry/node/examples/cohere/generate.mdx
+++ b/docs/0.0.1/dokumetry/node/examples/cohere/generate.mdx
@@ -6,17 +6,17 @@ description: 'Monitor Cohere Generate API usage'
## Generate
```javascript
-const { CohereClient } = require("cohere-ai");
+import { CohereClient } from "cohere-ai";
import DokuMetry from 'dokumetry';
const cohere = new CohereClient({
token: "<<apiKey>>",
});
-// Pass the above `cohere` object along with your DOKU URL and API key and this will make sure that all Cohere calls are automatically tracked.
-DokuMetry.init({llm: cohere, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
(async () => {
+ // Pass the above `cohere` object along with your DOKU URL and API key and this will make sure that all Cohere calls are automatically tracked.
+ DokuMetry.init({llm: cohere, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+
const generate = await cohere.generate({
prompt: "Please explain to me how LLMs work",
});
diff --git a/docs/0.0.1/dokumetry/node/examples/cohere/summarize.mdx b/docs/0.0.1/dokumetry/node/examples/cohere/summarize.mdx
index 20fef3a1..32cfd261 100644
--- a/docs/0.0.1/dokumetry/node/examples/cohere/summarize.mdx
+++ b/docs/0.0.1/dokumetry/node/examples/cohere/summarize.mdx
@@ -6,17 +6,17 @@ description: 'Monitor Cohere Summarize API usage'
## Summarize
```javascript
-const { CohereClient } = require("cohere-ai");
+import { CohereClient } from "cohere-ai";
import DokuMetry from 'dokumetry';
const cohere = new CohereClient({
token: "<<apiKey>>",
});
-// Pass the above `cohere` object along with your DOKU URL and API key and this will make sure that all Cohere calls are automatically tracked.
-DokuMetry.init({llm: cohere, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
-
(async () => {
+ // Pass the above `cohere` object along with your DOKU URL and API key and this will make sure that all Cohere calls are automatically tracked.
+ DokuMetry.init({llm: cohere, dokuUrl: "YOUR_DOKU_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, "
diff --git a/docs/0.0.1/dokumetry/node/examples/openai/audio.mdx b/docs/0.0.1/dokumetry/node/examples/openai/audio.mdx
index ee418a65..cd5c1107 100644
--- a/docs/0.0.1/dokumetry/node/examples/openai/audio.mdx
+++ b/docs/0.0.1/dokumetry/node/examples/openai/audio.mdx
@@ -14,7 +14,7 @@ import DokuMetry from 'dokumetry';
const openai = new OpenAI();
// Pass the above `openai` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
-DokuMetry.init({llm: openai, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
const speechFile = path.resolve("./speech.mp3");
diff --git a/docs/0.0.1/dokumetry/node/examples/openai/chat.mdx b/docs/0.0.1/dokumetry/node/examples/openai/chat.mdx
index 4d72ed4d..4400245f 100644
--- a/docs/0.0.1/dokumetry/node/examples/openai/chat.mdx
+++ b/docs/0.0.1/dokumetry/node/examples/openai/chat.mdx
@@ -14,7 +14,7 @@ import DokuMetry from 'dokumetry';
const openai = new OpenAI();
// Pass the above `openai` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
-DokuMetry.init({llm: openai, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
async function main() {
const completion = await openai.chat.completions.create({
@@ -35,7 +35,7 @@ import DokuMetry from 'dokumetry';
const openai = new OpenAI();
// Pass the above `openai` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
-DokuMetry.init({llm: openai, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
async function main() {
const response = await openai.chat.completions.create({
@@ -66,7 +66,7 @@ import DokuMetry from 'dokumetry';
const openai = new OpenAI();
// Pass the above `openai` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
-DokuMetry.init({llm: openai, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
async function main() {
const completion = await openai.chat.completions.create({
@@ -93,7 +93,7 @@ import DokuMetry from 'dokumetry';
const openai = new OpenAI();
// Pass the above `openai` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
-DokuMetry.init({llm: openai, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
async function main() {
const messages = [{"role": "user", "content": "What's the weather like in Boston today?"}];
@@ -138,7 +138,7 @@ import DokuMetry from 'dokumetry';
const openai = new OpenAI();
// Pass the above `openai` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
-DokuMetry.init({llm: openai, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
async function main() {
const completion = await openai.chat.completions.create({
diff --git a/docs/0.0.1/dokumetry/node/examples/openai/chatCompletions.mdx b/docs/0.0.1/dokumetry/node/examples/openai/chatCompletions.mdx
index d535f7cc..3d7ea2d3 100644
--- a/docs/0.0.1/dokumetry/node/examples/openai/chatCompletions.mdx
+++ b/docs/0.0.1/dokumetry/node/examples/openai/chatCompletions.mdx
@@ -12,7 +12,7 @@ import DokuMetry from 'dokumetry';
const openai = new OpenAI();
// Pass the above `openai` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
-DokuMetry.init({llm: openai, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
async function main() {
const completion = await openai.completions.create({
@@ -34,7 +34,7 @@ import DokuMetry from 'dokumetry';
const openai = new OpenAI();
// Pass the above `openai` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
-DokuMetry.init({llm: openai, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
async function main() {
const stream = await openai.completions.create({
diff --git a/docs/0.0.1/dokumetry/node/examples/openai/embeddings.mdx b/docs/0.0.1/dokumetry/node/examples/openai/embeddings.mdx
index fac7405a..7ecf6b51 100644
--- a/docs/0.0.1/dokumetry/node/examples/openai/embeddings.mdx
+++ b/docs/0.0.1/dokumetry/node/examples/openai/embeddings.mdx
@@ -12,7 +12,7 @@ import DokuMetry from 'dokumetry';
const openai = new OpenAI();
// Pass the above `openai` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
-DokuMetry.init({llm: openai, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
async function main() {
const embedding = await openai.embeddings.create({
diff --git a/docs/0.0.1/dokumetry/node/examples/openai/fine-tuning.mdx b/docs/0.0.1/dokumetry/node/examples/openai/fine-tuning.mdx
index 06ed6f0e..513a8575 100644
--- a/docs/0.0.1/dokumetry/node/examples/openai/fine-tuning.mdx
+++ b/docs/0.0.1/dokumetry/node/examples/openai/fine-tuning.mdx
@@ -12,7 +12,7 @@ import DokuMetry from 'dokumetry';
const openai = new OpenAI();
// Pass the above `openai` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
-DokuMetry.init({llm: openai, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
async function main() {
const fineTune = await openai.fineTuning.jobs.create({
diff --git a/docs/0.0.1/dokumetry/node/examples/openai/image.mdx b/docs/0.0.1/dokumetry/node/examples/openai/image.mdx
index 7a80fd09..06b196ab 100644
--- a/docs/0.0.1/dokumetry/node/examples/openai/image.mdx
+++ b/docs/0.0.1/dokumetry/node/examples/openai/image.mdx
@@ -12,7 +12,7 @@ import DokuMetry from 'dokumetry';
const openai = new OpenAI();
// Pass the above `openai` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
-DokuMetry.init({llm: openai, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
async function main() {
const image = await openai.images.generate({ model: "dall-e-3", prompt: "A cute baby sea otter" });
@@ -31,7 +31,7 @@ import DokuMetry from 'dokumetry';
const openai = new OpenAI();
// Pass the above `openai` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
-DokuMetry.init({llm: openai, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
async function main() {
const image = await openai.images.createVariation({
diff --git a/docs/0.0.1/dokumetry/node/introduction.mdx b/docs/0.0.1/dokumetry/node/intro.mdx
similarity index 94%
rename from docs/0.0.1/dokumetry/node/introduction.mdx
rename to docs/0.0.1/dokumetry/node/intro.mdx
index b97ad601..36194817 100644
--- a/docs/0.0.1/dokumetry/node/introduction.mdx
+++ b/docs/0.0.1/dokumetry/node/intro.mdx
@@ -23,7 +23,7 @@ const openai = new OpenAI({
});
// Pass the above `openai` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
-DokuMetry.init({llm: openai, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
async function main() {
const chatCompletion = await openai.chat.completions.create({
@@ -55,7 +55,7 @@ const cohere = new CohereClient({
});
// Pass the above `cohere` object along with your DOKU URL and API key and this will make sure that all Cohere calls are automatically tracked.
-DokuMetry.init({llm: cohere, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+DokuMetry.init({llm: cohere, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
(async () => {
const prediction = await cohere.generate({
@@ -85,7 +85,7 @@ const anthropic = new Anthropic({
});
// Pass the above `anthropic` object along with your DOKU URL and API key and this will make sure that all Anthropic calls are automatically tracked.
-DokuMetry.init({llm: anthropic, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+DokuMetry.init({llm: anthropic, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
async function main() {
const completion = await anthropic.completions.create({
@@ -107,7 +107,7 @@ The following Anthropic Endpoints are supported for monitoring with DokuMetry
| Parameter | Description | Required |
|-------------------|-----------------------------------------------------------|---------------|
| llm | Language Learning Model (LLM) Object to track | Yes |
-| dokuURL | URL of your Doku Instance | Yes |
+| dokuUrl | URL of your Doku Instance | 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 |
diff --git a/docs/0.0.1/installation.mdx b/docs/0.0.1/installation.mdx
index 913c92ee..68b9c333 100644
--- a/docs/0.0.1/installation.mdx
+++ b/docs/0.0.1/installation.mdx
@@ -51,7 +51,7 @@ Deploy Doku on your Kubernetes cluster using the [Doku Helm chart](https://githu
</Step>
<Step title="Installing the Helm Chart">
```shell shell
- helm install doku dokulabs/doku
+ helm install doku dokulabs/doku --version 0.0.7
```
</Step>
</Steps>
diff --git a/docs/0.0.1/introduction.mdx b/docs/0.0.1/intro.mdx
similarity index 99%
rename from docs/0.0.1/introduction.mdx
rename to docs/0.0.1/intro.mdx
index e0fa613f..36f3fae7 100644
--- a/docs/0.0.1/introduction.mdx
+++ b/docs/0.0.1/intro.mdx
@@ -24,7 +24,7 @@ For Python and NodeJS projects, just import the DokuMetry SDK and initialize it
```javascript NodeJS
import DokuMetry from 'dokumetry';
- DokuMetry.init({llm: openai, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+ DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
```
</CodeGroup>
Find detailed instructions at the [DokuMetry SDK Documentation](/0.0.1/dokumetry/introduction).
diff --git a/docs/0.0.1/quickstart.mdx b/docs/0.0.1/quickstart.mdx
index 797f06bf..9e7588f8 100644
--- a/docs/0.0.1/quickstart.mdx
+++ b/docs/0.0.1/quickstart.mdx
@@ -108,7 +108,7 @@ This guide will walk you through setting up your monitoring system with minimal
```javascript
import DokuMetry from 'dokumetry';
- DokuMetry.init({llm: openai, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+ DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
```
Example Usage for monitoring `OpenAI` Usage:
@@ -122,7 +122,7 @@ This guide will walk you through setting up your monitoring system with minimal
});
// Pass the above `openai` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
- DokuMetry.init({llm: openai, dokuURL: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+ DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
async function main() {
const chatCompletion = await openai.chat.completions.create({
@@ -134,7 +134,7 @@ This guide will walk you through setting up your monitoring system with minimal
main();
```
- Refer to the `dokumetry` [NodeJS SDK repository](https://github.com/dokulabs/dokumetry-node) or the [DokuMetry Docs](/0.0.1/dokumetry/node/introduction) for more advanced configurations and use cases.
+ Refer to the `dokumetry` [NodeJS SDK repository](https://github.com/dokulabs/dokumetry-node) or the [DokuMetry Docs](/0.0.1/dokumetry/node/intro) for more advanced configurations and use cases.
</Step>
</Steps>
</Tab>
diff --git a/docs/0.0.2/api-reference/endpoint/api-keys/create.mdx b/docs/0.0.2/api-reference/endpoint/api-keys/create.mdx
new file mode 100644
index 00000000..cce6cecf
--- /dev/null
+++ b/docs/0.0.2/api-reference/endpoint/api-keys/create.mdx
@@ -0,0 +1,4 @@
+---
+title: 'Create API Key'
+openapi: 'POST /api/keys'
+---
\ No newline at end of file
diff --git a/docs/0.0.2/api-reference/endpoint/api-keys/delete.mdx b/docs/0.0.2/api-reference/endpoint/api-keys/delete.mdx
new file mode 100644
index 00000000..fbb9e963
--- /dev/null
+++ b/docs/0.0.2/api-reference/endpoint/api-keys/delete.mdx
@@ -0,0 +1,4 @@
+---
+title: 'Delete API Key'
+openapi: 'DELETE /api/keys'
+---
\ No newline at end of file
diff --git a/docs/0.0.2/api-reference/endpoint/api-keys/get.mdx b/docs/0.0.2/api-reference/endpoint/api-keys/get.mdx
new file mode 100644
index 00000000..3ecec318
--- /dev/null
+++ b/docs/0.0.2/api-reference/endpoint/api-keys/get.mdx
@@ -0,0 +1,4 @@
+---
+title: 'GET API Key'
+openapi: 'GET /api/keys'
+---
\ No newline at end of file
diff --git a/docs/0.0.2/api-reference/introduction.mdx b/docs/0.0.2/api-reference/introduction.mdx
new file mode 100644
index 00000000..f37f9a3b
--- /dev/null
+++ b/docs/0.0.2/api-reference/introduction.mdx
@@ -0,0 +1,25 @@
+---
+title: 'Introduction'
+description: 'OpenAPI specification for API Endpoints in Doku'
+---
+
+<Card
+ title="API Keys Endpoints"
+ icon="key"
+ href="/0.0.2/api-reference/endpoint/api-keys/create"
+>
+ View the documentation for API Keys
+</Card>
+
+## Authentication
+
+All API endpoints are authenticated using Authetication Header.
+
+```json
+Authorization: <api-key>
+```
+
+<Info>
+For your initial API call, Authorization header can be set to "".
+Store the provided API key securely; it will be required to pass the generated and a valid API Key in Authorization header for subsequent API calls.
+</Info>
\ No newline at end of file
diff --git a/docs/0.0.2/api-reference/openiapi.yml b/docs/0.0.2/api-reference/openiapi.yml
new file mode 100644
index 00000000..f1c7dc5b
--- /dev/null
+++ b/docs/0.0.2/api-reference/openiapi.yml
@@ -0,0 +1,100 @@
+openapi: 3.0.0
+info:
+ title: API Keys Service
+ description: This service manages API keys through GET, POST, and DELETE operations.
+ version: "0.0.2"
+
+servers:
+ - url: https://127.0.0.1:9044/
+
+paths:
+ /api/keys:
+ get:
+ summary: Get a list of API keys
+ operationId: getApiKeys
+ tags:
+ - API Key
+ security:
+ - ApiKeyAuth: []
+ requestBody:
+ required: true
+ content:
+ application/json:
+ schema:
+ $ref: '#/components/schemas/APIKeyRequest'
+ responses:
+ '200':
+ description: A list of API keys
+ content:
+ application/json:
+ schema:
+ $ref: '#/components/schemas/jsonResponse'
+
+ post:
+ summary: Create a new API key
+ operationId: createApiKey
+ tags:
+ - API Key
+ security:
+ - ApiKeyAuth: []
+ requestBody:
+ required: true
+ content:
+ application/json:
+ schema:
+ $ref: '#/components/schemas/APIKeyRequest'
+ responses:
+ '201':
+ description: API key created
+ content:
+ application/json:
+ schema:
+ $ref: '#/components/schemas/jsonResponse'
+
+ delete:
+ summary: Delete an API key
+ operationId: deleteApiKey
+ tags:
+ - API Key
+ security:
+ - ApiKeyAuth: []
+ requestBody:
+ required: true
+ content:
+ application/json:
+ schema:
+ $ref: '#/components/schemas/APIKeyRequest'
+ responses:
+ '200':
+ description: API key deleted
+ content:
+ application/json:
+ schema:
+ $ref: '#/components/schemas/jsonResponse'
+
+components:
+ schemas:
+ APIKeyRequest:
+ type: object
+ required:
+ - name
+ properties:
+ name:
+ type: string
+
+ jsonResponse:
+ type: object
+ required:
+ - status
+ - message
+ properties:
+ status:
+ type: integer
+ message:
+ type: string
+
+ securitySchemes:
+ ApiKeyAuth:
+ type: apiKey
+ in: header
+ name: Authorization
\ No newline at end of file
diff --git a/docs/0.0.2/configuration.mdx b/docs/0.0.2/configuration.mdx
new file mode 100644
index 00000000..cc1f7c53
--- /dev/null
+++ b/docs/0.0.2/configuration.mdx
@@ -0,0 +1,248 @@
+---
+title: 'Configuration'
+description: 'Configuring Options for Doku'
+icon: 'sliders'
+---
+
+This document outlines the various options available for configuring Doku.
+For ease of use and clarity, we recommend naming the configuration file `doku.yml`
+
+
+## Properties
+
+<ResponseField name="ingester_port" type="String">
+ The `ingesterPort` specifies the network port that the Ingestion Server will listen to for incoming data. You can set this to any available port on your system.
+
+**Example**:
+```yaml
+ingesterPort: 9044
+```
+</ResponseField>
+
+### Pricing Information Source
+
+Doku supports using either a local file or a URL to retrieve LLM Pricing data. Comment out the option you do not wish to use.
+<Info>
+We strongly recommend using the `url` method with the value set as `https://raw.githubusercontent.com/dokulabs/ingester/main/assets/pricing.json`.
+
+This ensures that you automatically retrieve the latest pricing information upon each startup, as the developers at Doku consistently refresh the pricing file with current data from OpenAI, Cohere and Anthropic.
+</Info>
+
+<ResponseField name="local_file" type="Object">
+ Local File containing the Pricing Information JSON
+ <Expandable title="properties">
+ <ResponseField name="path" type="String">
+ Specify the local file system path to a JSON file containing the LLM Pricing data.
+ </ResponseField>
+ </Expandable>
+
+ **Example**:
+ ```yaml
+ pricingInfo:
+ localFile:
+ path: "/assets/pricing.json"
+ ```
+</ResponseField>
+
+<ResponseField name="url" type="String">
+ Provide the URL where the pricing data JSON file can be downloaded. Ensure the given URL is accessible.
+
+ **Example**:
+ ```yaml
+ pricingInfo:
+ url: "https://raw.githubusercontent.com/dokulabs/ingester/main/assets/pricing.json"
+ ```
+</ResponseField>
+
+
+### Database Configuration
+
+<ResponseField name="dbConfig" type="Object">
+ Configure the database connection details to connect Doku with TimescaleDB (or another Postgres compatible DB).
+ <Expandable title="properties">
+ <ResponseField name="name" type="String">
+ Database name.
+ </ResponseField>
+ <ResponseField name="username" type="String">
+ The username for the database.
+ </ResponseField>
+ <ResponseField name="password" type="String">
+ The password for the database.
+ </ResponseField>
+ <ResponseField name="host" type="String">
+ Host address for the database.
+ </ResponseField>
+ <ResponseField name="port" type="String">
+ Network port for the database connection.
+ </ResponseField>
+ <ResponseField name="sslMode" type="String">
+ The SSL mode for the database connection (e.g., "require" if SSL is needed).
+ </ResponseField>
+ <ResponseField name="maxOpenConns" type="String">
+ Maximum number of concurrent open database connections.
+ </ResponseField>
+ <ResponseField name="maxIdleConns" type="String">
+ Maximum number of idle database connections.
+ </ResponseField>
+ <ResponseField name="dataTable" type="String">
+ Name of the table to store LLM Data.
+ </ResponseField>
+ <ResponseField name="apiKeyTable" type="String">
+ Name of the table to store API Keys.
+ </ResponseField>
+ </Expandable>
+
+ **Example**:
+ ```yaml
+ dbConfig:
+ name: "mydatabase"
+ username: "myusername"
+ password: "mypassword"
+ host: "mydbhost.example.com"
+ port: 5432
+ sslMode: "require"
+ maxOpenConns: 15
+ maxIdleConns: 10
+ dataTable: "llm_data"
+ apiKeyTable: "api_keys"
+ ```
+</ResponseField>
+
+
+### Observability Platform Configuration
+
+<ResponseField name="observabilityPlatform" type="Object">
+ Choose the external platform you wish to use for exporting observability data from Doku and set `enabled` to `true`. Fill in the required fields for the chosen platform. Only one platform can be selected at a time.
+
+ The following sections show example configurations for different platforms - Grafana Cloud, New Relic, and DataDog. You will need to uncomment the applicable section and provide necessary credentials such as URLs, User IDs, and API Keys corresponding to your account on the observability platform.
+ <Expandable title="properties">
+ <ResponseField name="enabled" type="boolean">
+ Boolean parameter to configure external Observability Platform
+ </ResponseField>
+ <ResponseField name="grafanaCloud" type="Object">
+ Configuration for connecting Doku with Grafana Cloud.
+ <Expandable title="properties">
+ <ResponseField name="promUrl" type="String">
+ URL to the Influx Line Proxy URL of the Grafana Cloud Prometheus Instance.
+ </ResponseField>
+ <ResponseField name="promUsername" type="String">
+ Prometheus User ID of the Grafana Cloud Prometheus Instance.
+ </ResponseField>
+ <ResponseField name="lokiUrl" type="String">
+ URL of the Loki Push URL of the Grafana Cloud Loki Instance.
+ </ResponseField>
+ <ResponseField name="lokiUsername" type="String">
+ Loki Username of the Grafana Cloud Loki Instance.
+ </ResponseField>
+ <ResponseField name="accessToken" type="String">
+ Access Token of the Grafana Cloud Instance.
+ </ResponseField>
+ **Example**:
+ ```yaml
+ observabilityPlatform:
+ enabled: true
+ grafanaCloud:
+ promUrl: "https://your-grafana-prometheus-url"
+ promUsername: "your-prom-user-id"
+ lokiUrl: "https://your-grafana-loki-url"
+ lokiUsername: "your-loki-user-id"
+ accessToken: "your-grafana-cloud-access-token"
+ ```
+ </Expandable>
+ </ResponseField>
+ <ResponseField name="datadog" type="Object">
+ Configuration for connecting Doku with DataDog.
+ <Expandable title="properties">
+ <ResponseField name="metricsUrl" type="String">
+ URL to the DataDog Metrics API.
+ </ResponseField>
+ <ResponseField name="logsUrl" type="String">
+ URL to the DataDog Logs API.
+ </ResponseField>
+ <ResponseField name="apiKey" type="String">
+ API Key of the DataDog Account.
+ </ResponseField>
+ **Example**:
+ ```yaml
+ observabilityPlatform:
+ enabled: true
+ datadog:
+ metricsUrl: "https://api.datadoghq.com/api/v1/series"
+ logsUrl: "https://http.logs.datadoghq.com/api/v2/logs"
+ apiKey: "datadog-api-key"
+ ```
+ </Expandable>
+ </ResponseField>
+ <ResponseField name="newRelic" type="Object">
+ Configuration for connecting Doku with New Relic.
+ <Expandable title="properties">
+ <ResponseField name="metricsUrl" type="String">
+ URL to the New Relic Metric API.
+ </ResponseField>
+ <ResponseField name="logsUrl" type="String">
+ URL to the New Relic Log API.
+ </ResponseField>
+ <ResponseField name="apiKey" type="String">
+ Ingest API Key of the New Relic Account.
+ </ResponseField>
+ **Example**:
+ ```yaml
+ observabilityPlatform:
+ enabled: true
+ newRelic:
+ metricsUrl: "https://metric-api.newrelic.com/metric/v1"
+ logsUrl: "https://log-api.newrelic.com/log/v1"
+ apiKey: "newrelic-api-key"
+ ```
+ </Expandable>
+ </ResponseField>
+ </Expandable>
+</ResponseField>
+
+Ensure that the file is correctly formatted in YAML and all necessary fields are populated based on your deployment needs. Save the file and restart the Doku service to apply the new configuration.
+
+## Example Configuration File
+
+```yaml doku.yml
+ingesterPort: 9044 # Port to run the Ingestion Server on, Example: 9044
+
+# Comment out either 'localFile' or 'url' to use only one at a time.
+pricingInfo:
+ # localFile:
+ # path: "/assets/pricing.json" # Path to local JSON file with LLM Pricing data
+ url: "https://raw.githubusercontent.com/dokulabs/ingester/main/assets/pricing.json" # URL to download Pricing data file
+
+# Configuration for the Doku Backend Database (TimescaleDB)
+dbConfig:
+ name: "DBNAME" # Name of the database, Example: "postgres"
+ username: "USERNAME" # Username to connect to the database, Example: "admin"
+ password: "PASSWORD" # Password to connect to the database, Example: "DOKU"
+ host: "HOSTURL" # Hostname of the database, Example: "174.21.1.2"
+ port: DBPORT # Port of the database, Example: 5432
+ sslMode: SSLMODE # SSL Mode of the database, Example: "require"
+ maxOpenConns: MAXOPENCONNS # Maximum number of open connections to the database, Example: 15
+ maxIdleConns: MAXOPENCONNS # Maximum number of idle connections to the database, Example: 15
+ dataTable: DATATABLE # Name of the table to store LLM Data, Example: "DOKU"
+ apiKeyTable: APIKEYTABLE # Name of the table to store API Keys, Example: "APIKEYS"
+
+# Configure Platform to export LLM Observability Data from Doku
+# Only one platform can be enabled at a time, To enable a platform, set enabled to true and fill in the required fields for that platform.
+observabilityPlatform:
+ enabled: false # Enable or Disable the Observability Platform, Example: true
+ # grafanaCloud:
+ # promUrl: "influx-line-proxy-url" # URL to the Influx Line Proxy URL of the Grafana Cloud Prometheus Instance
+ # promUsername: "prometheus-userid" # Prometheus User ID of the Grafana Cloud Prometheus Instance
+ # lokiUrl: "loki-push-url" # URL to the Loki Push URL of the Grafana Cloud Loki Instance
+ # lokiUsername: "loki-username" # Loki Username of the Grafana Cloud Loki Instance
+ # accessToken: "grafana-cloud-access-token" # Access Token of the Grafana Cloud Instance
+
+ # newRelic:
+ # metricsUrl: "https://metric-api.newrelic.com/metric/v1" # URL to the New Relic Metric API
+ # logsUrl: "https://log-api.newrelic.com/log/v1" # URL to the New Relic Log API
+ # key: "newrelic-api-key" # Ingest API Key of the New Relic Account
+
+ # datadog:
+ # metricsUrl: "https://api.datadoghq.com/api/v1/series" # URL to the DataDog Metrics API
+ # logsUrl: "https://http.logs.datadoghq.com/api/v2/logs" # URL to the DataDog Logs API
+ # apiKey: "datadog-api-key" # API Key of the DataDog Account
+```
\ No newline at end of file
diff --git a/docs/0.0.2/dokumetry/introduction.mdx b/docs/0.0.2/dokumetry/introduction.mdx
new file mode 100644
index 00000000..248e7bc4
--- /dev/null
+++ b/docs/0.0.2/dokumetry/introduction.mdx
@@ -0,0 +1,74 @@
+---
+title: 'Overview'
+description: 'Seamlessly send LLM usage data to Doku'
+---
+
+[DokuMetry SDK](https://www.npmjs.com/package/dokumetry) (`dokumetry`) empowers you to effortlessly track and monitor language learning model (LLM) usage data and metrics from your Python/NodeJS code. It seamlessly integrates with major LLM Platforms:
+
+
+DokuMetry SDKs can currently track and monitor API usage for the below platforms
+<CardGroup cols={3}>
+ <Card
+ title="OpenAI"
+ icon={
+ <svg role="img" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg">
+ <title>OpenAI</title>
+ <path d="M22.2819 9.8211a5.9847 5.9847 0 0 0-.5157-4.9108 6.0462 6.0462 0 0 0-6.5098-2.9A6.0651 6.0651 0 0 0 4.9807 4.1818a5.9847 5.9847 0 0 0-3.9977 2.9 6.0462 6.0462 0 0 0 .7427 7.0966 5.98 5.98 0 0 0 .511 4.9107 6.051 6.051 0 0 0 6.5146 2.9001A5.9847 5.9847 0 0 0 13.2599 24a6.0557 6.0557 0 0 0 5.7718-4.2058 5.9894 5.9894 0 0 0 3.9977-2.9001 6.0557 6.0557 0 0 0-.7475-7.0729zm-9.022 12.6081a4.4755 4.4755 0 0 1-2.8764-1.0408l.1419-.0804 4.7783-2.7582a.7948.7948 0 0 0 .3927-.6813v-6.7369l2.02 1.1686a.071.071 0 0 1 .038.052v5.5826a4.504 4.504 0 0 1-4.4945 4.4944zm-9.6607-4.1254a4.4708 4.4708 0 0 1-.5346-3.0137l.142.0852 4.783 2.7582a.7712.7712 0 0 0 .7806 0l5.8428-3.3685v2.3324a.0804.0804 0 0 1-.0332.0615L9.74 19.9502a4.4992 4.4992 0 0 1-6.1408-1.6464zM2.3408 7.8956a4.485 4.485 0 0 1 2.3655-1.9728V11.6a.7664.7664 0 0 0 .3879.6765l5.8144 3.3543-2.0201 1.1685a.0757.0757 0 0 1-.071 0l-4.8303-2.7865A4.504 4.504 0 0 1 2.3408 7.872zm16.5963 3.8558L13.1038 8.364 15.1192 7.2a.0757.0757 0 0 1 .071 0l4.8303 2.7913a4.4944 4.4944 0 0 1-.6765 8.1042v-5.6772a.79.79 0 0 0-.407-.667zm2.0107-3.0231l-.142-.0852-4.7735-2.7818a.7759.7759 0 0 0-.7854 0L9.409 9.2297V6.8974a.0662.0662 0 0 1 .0284-.0615l4.8303-2.7866a4.4992 4.4992 0 0 1 6.6802 4.66zM8.3065 12.863l-2.02-1.1638a.0804.0804 0 0 1-.038-.0567V6.0742a4.4992 4.4992 0 0 1 7.3757-3.4537l-.142.0805L8.704 5.459a.7948.7948 0 0 0-.3927.6813zm1.0976-2.3654l2.602-1.4998 2.6069 1.4998v2.9994l-2.5974 1.4997-2.6067-1.4997Z" />
+ </svg>
+ }
+ iconType="duotone"
+ >
+ </Card>
+ <Card
+ title="Cohere"
+ icon={
+ <svg role="image" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 75 75">
+ <g>
+ <g>
+ <g>
+ <path d="M24.3,44.7c2,0,6-0.1,11.6-2.4c6.5-2.7,19.3-7.5,28.6-12.5c6.5-3.5,9.3-8.1,9.3-14.3C73.8,7,66.9,0,58.3,0
+ h-36C10,0,0,10,0,22.3S9.4,44.7,24.3,44.7z">
+ </path>
+ <path d="M30.4,60c0-6,3.6-11.5,9.2-13.8l11.3-4.7C62.4,36.8,75,45.2,75,57.6C75,67.2,67.2,75,57.6,75l-12.3,0
+ C37.1,75,30.4,68.3,30.4,60z">
+ </path>
+ <path d="M12.9,47.6L12.9,47.6C5.8,47.6,0,53.4,0,60.5v1.7C0,69.2,5.8,75,12.9,75h0c7.1,0,12.9-5.8,12.9-12.9v-1.7
+ C25.7,53.4,20,47.6,12.9,47.6z">
+ </path>
+ </g>
+ </g>
+ </g>
+ </svg>
+ }
+ iconType="duotone"
+ >
+ </Card>
+ <Card
+ title="Anthropic"
+ icon={
+ <svg viewBox="0 0 256 176" 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>
+ <path d="M66.1828124,106.221191 C66.1828124,106.221191 90.1624677,44.4471185 90.1624677,44.4471185 C90.1624677,44.4471185 114.142128,106.221191 114.142128,106.221191 C114.142128,106.221191 66.1828124,106.221191 66.1828124,106.221191 C66.1828124,106.221191 66.1828124,106.221191 66.1828124,106.221191 Z M70.0705318,0 C70.0705318,0 0,175.780074 0,175.780074 C0,175.780074 39.179211,175.780074 39.179211,175.780074 C39.179211,175.780074 53.5097704,138.86606 53.5097704,138.86606 C53.5097704,138.86606 126.817544,138.86606 126.817544,138.86606 C126.817544,138.86606 141.145724,175.780074 141.145724,175.780074 C141.145724,175.780074 180.324935,175.780074 180.324935,175.780074 C180.324935,175.780074 110.254409,0 110.254409,0 C110.254409,0 70.0705318,0 70.0705318,0 C70.0705318,0 70.0705318,0 70.0705318,0 Z"></path>
+ </svg>
+ }
+ iconType="duotone"
+ >
+ </Card>
+</CardGroup>
+
+All LLM observability data collected by DokuMetry is sent directly to the Doku Platform for streamlined tracking.
+
+## Features
+
+- **Effortless Setup:** Integrate full-featured LLM usage monitoring into your application with just two lines of code.
+- **Efficient Performance:** Designed for near-zero latency impact, allowing your applications to run smoothly without compromise.
+- **Secure and Reliable**: DokuMetry SDKs prioritize the safety and integrity of your data. All data transmission to Doku is conducted over secure HTTP, ensuring that your observability data is protected during transit.
+
+## Supported Languages
+
+<CardGroup cols={2}>
+<Card title="Python" href="/0.0.2/dokumetry/python" icon="python">
+</Card>
+<Card title="NodeJS" href="/0.0.2/dokumetry/node" icon="node-js">
+</Card>
+</CardGroup>
diff --git a/docs/0.0.2/dokumetry/node/examples/anthropic/anthropic-completions.mdx b/docs/0.0.2/dokumetry/node/examples/anthropic/anthropic-completions.mdx
new file mode 100644
index 00000000..6fbff10e
--- /dev/null
+++ b/docs/0.0.2/dokumetry/node/examples/anthropic/anthropic-completions.mdx
@@ -0,0 +1,29 @@
+---
+title: 'Completions'
+description: 'Monitor Anthropic Completions API Usage'
+---
+
+## Completions
+
+```javascript
+import Anthropic from '@anthropic-ai/sdk';
+import DokuMetry from 'dokumetry';
+
+const anthropic = new Anthropic({
+ apiKey: 'my_api_key', // defaults to process.env["ANTHROPIC_API_KEY"]
+});
+
+// Pass the above `anthropic` object along with your DOKU URL and API key and this will make sure that all Anthropic calls are automatically tracked.
+DokuMetry.init({llm: anthropic, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+
+async function main() {
+ const completion = await anthropic.completions.create({
+ model: 'claude-2',
+ max_tokens_to_sample: 300,
+ prompt: `${Anthropic.HUMAN_PROMPT} Hello, Claude{Anthropic.AI_PROMPT}`,
+ });
+ console.log(completion.completion);
+}
+main().catch(console.error);
+```
+
diff --git a/docs/0.0.2/dokumetry/node/examples/cohere/chat.mdx b/docs/0.0.2/dokumetry/node/examples/cohere/chat.mdx
new file mode 100644
index 00000000..fdc6a559
--- /dev/null
+++ b/docs/0.0.2/dokumetry/node/examples/cohere/chat.mdx
@@ -0,0 +1,60 @@
+---
+title: 'Chat'
+description: 'Monitor Cohere Chat API usage'
+---
+
+## Chat
+<CodeGroup>
+
+```javascript No Streaming
+import { CohereClient } from "cohere-ai";
+import DokuMetry from 'dokumetry';
+
+const cohere = new CohereClient({
+ token: "<<apiKey>>",
+});
+
+(async () => {
+ // Pass the above `cohere` object along with your DOKU URL and API key and this will make sure that all Cohere calls are automatically tracked.
+ DokuMetry.init({llm: cohere, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+
+ const response = await cohere.chat({
+ message: 'Say this is a test',
+ model: 'command',
+ });
+
+ console.log(response)
+})();
+```
+
+```javascript Streaming
+import { CohereClient } from "cohere-ai";
+import DokuMetry from 'dokumetry';
+
+const cohere = new CohereClient({
+ token: "<<apiKey>>",
+});
+
+(async () => {
+ // Pass the above `cohere` object along with your DOKU URL and API key and this will make sure that all Cohere calls are automatically tracked.
+ DokuMetry.init({llm: cohere, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+
+ const chatStream = await cohere.chatStream({
+ chatHistory: [
+ { role: "USER", message: "Who discovered gravity?" },
+ { role: "CHATBOT", message: "The man who is widely credited with discovering gravity is Sir Isaac Newton" }
+ ],
+ message: "What year was he born?",
+ // perform web search before answering the question. You can also use your own custom connector.
+ connectors: [{ id: "web-search" }],
+ });
+
+ for await (const message of chatStream) {
+ if (message.eventType === "text-generation") {
+ console.log(message);
+ }
+ }
+})();
+```
+
+</CodeGroup>
\ No newline at end of file
diff --git a/docs/0.0.2/dokumetry/node/examples/cohere/embed.mdx b/docs/0.0.2/dokumetry/node/examples/cohere/embed.mdx
new file mode 100644
index 00000000..e11ba206
--- /dev/null
+++ b/docs/0.0.2/dokumetry/node/examples/cohere/embed.mdx
@@ -0,0 +1,27 @@
+---
+title: 'Embed'
+description: 'Monitor Cohere Embed API usage'
+---
+
+## Embed
+
+```javascript
+import { CohereClient } from "cohere-ai";
+import DokuMetry from 'dokumetry';
+
+const cohere = new CohereClient({
+ token: "<<apiKey>>",
+});
+
+(async () => {
+ // Pass the above `cohere` object along with your DOKU URL and API key and this will make sure that all Cohere calls are automatically tracked.
+ DokuMetry.init({llm: cohere, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+
+ const embed = await cohere.embed({
+ texts: ["hello", "goodbye"],
+ model: "embed-english-v3.0",
+ inputType: "classification",
+ });
+ console.log(embed);
+})();
+```
\ No newline at end of file
diff --git a/docs/0.0.2/dokumetry/node/examples/cohere/generate.mdx b/docs/0.0.2/dokumetry/node/examples/cohere/generate.mdx
new file mode 100644
index 00000000..b48cdd1c
--- /dev/null
+++ b/docs/0.0.2/dokumetry/node/examples/cohere/generate.mdx
@@ -0,0 +1,26 @@
+---
+title: 'Generate'
+description: 'Monitor Cohere Generate API usage'
+---
+
+## Generate
+
+```javascript
+import { CohereClient } from "cohere-ai";
+import DokuMetry from 'dokumetry';
+
+const cohere = new CohereClient({
+ token: "<<apiKey>>",
+});
+
+(async () => {
+ // Pass the above `cohere` object along with your DOKU URL and API key and this will make sure that all Cohere calls are automatically tracked.
+ DokuMetry.init({llm: cohere, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+
+ const generate = await cohere.generate({
+ prompt: "Please explain to me how LLMs work",
+ });
+
+ console.log(generate);
+})();
+```
\ No newline at end of file
diff --git a/docs/0.0.2/dokumetry/node/examples/cohere/summarize.mdx b/docs/0.0.2/dokumetry/node/examples/cohere/summarize.mdx
new file mode 100644
index 00000000..32cfd261
--- /dev/null
+++ b/docs/0.0.2/dokumetry/node/examples/cohere/summarize.mdx
@@ -0,0 +1,45 @@
+---
+title: 'Summarize'
+description: 'Monitor Cohere Summarize API usage'
+---
+
+## Summarize
+
+```javascript
+import { CohereClient } from "cohere-ai";
+import DokuMetry from 'dokumetry';
+
+const cohere = new CohereClient({
+ token: "<<apiKey>>",
+});
+
+(async () => {
+ // Pass the above `cohere` object along with your DOKU URL and API key and this will make sure that all Cohere calls are automatically tracked.
+ DokuMetry.init({llm: cohere, dokuUrl: "YOUR_DOKU_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);
+})();
+```
\ No newline at end of file
diff --git a/docs/0.0.2/dokumetry/node/examples/openai/audio.mdx b/docs/0.0.2/dokumetry/node/examples/openai/audio.mdx
new file mode 100644
index 00000000..cd5c1107
--- /dev/null
+++ b/docs/0.0.2/dokumetry/node/examples/openai/audio.mdx
@@ -0,0 +1,32 @@
+---
+title: 'Audio'
+description: 'Monitor OpenAI Audio API usage'
+---
+
+## Create Speech
+
+```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 URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_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();
+```
\ No newline at end of file
diff --git a/docs/0.0.2/dokumetry/node/examples/openai/chat.mdx b/docs/0.0.2/dokumetry/node/examples/openai/chat.mdx
new file mode 100644
index 00000000..4400245f
--- /dev/null
+++ b/docs/0.0.2/dokumetry/node/examples/openai/chat.mdx
@@ -0,0 +1,157 @@
+---
+title: 'Chat'
+description: 'Monitor OpenAI Chat Completions API usage'
+---
+
+## Chat Completions
+
+<CodeGroup>
+
+```javascript Default
+import OpenAI from "openai";
+import DokuMetry from 'dokumetry';
+
+const openai = new OpenAI();
+
+// Pass the above `openai` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+
+async function main() {
+ const completion = await openai.chat.completions.create({
+ messages: [{ role: "system", content: "You are a helpful assistant." }],
+ 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 URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_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 URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_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 helpful assistant."},
+ {"role": "user", "content": "Hello!"}
+ ],
+ 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 URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_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 URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+
+async function main() {
+ const completion = await openai.chat.completions.create({
+ messages: [{ role: "user", content: "Hello!" }],
+ model: "gpt-3.5-turbo",
+ logprobs: true,
+ top_logprobs: 2,
+ });
+
+ console.log(completion.choices[0]);
+}
+
+main();
+```
+
+</CodeGroup>
\ No newline at end of file
diff --git a/docs/0.0.2/dokumetry/node/examples/openai/chatCompletions.mdx b/docs/0.0.2/dokumetry/node/examples/openai/chatCompletions.mdx
new file mode 100644
index 00000000..3d7ea2d3
--- /dev/null
+++ b/docs/0.0.2/dokumetry/node/examples/openai/chatCompletions.mdx
@@ -0,0 +1,53 @@
+---
+title: 'Completions'
+description: 'Monitor OpenAI Completions API Usage'
+---
+
+## Completions
+<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 URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+
+async function main() {
+ const completion = await openai.completions.create({
+ model: "gpt-3.5-turbo-instruct",
+ prompt: "Say this is a test.",
+ max_tokens: 7,
+ temperature: 0,
+ });
+
+ console.log(completion);
+}
+main();
+```
+
+```javascript Streaming
+import OpenAI from "openai";
+import DokuMetry from 'dokumetry';
+
+const openai = new OpenAI();
+
+// Pass the above `openai` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+
+async function main() {
+ const stream = await openai.completions.create({
+ model: "gpt-3.5-turbo-instruct",
+ prompt: "Say this is a test.",
+ stream: true,
+ });
+
+ for await (const chunk of stream) {
+ console.log(chunk.choices[0].text)
+ }
+}
+main();
+```
+
+</CodeGroup>
\ No newline at end of file
diff --git a/docs/0.0.2/dokumetry/node/examples/openai/embeddings.mdx b/docs/0.0.2/dokumetry/node/examples/openai/embeddings.mdx
new file mode 100644
index 00000000..7ecf6b51
--- /dev/null
+++ b/docs/0.0.2/dokumetry/node/examples/openai/embeddings.mdx
@@ -0,0 +1,28 @@
+---
+title: 'Embeddings'
+description: 'Monitor OpenAI Embeddings API usage'
+---
+
+## Create Embeddings
+
+```javascript
+import OpenAI from "openai";
+import DokuMetry from 'dokumetry';
+
+const openai = new OpenAI();
+
+// Pass the above `openai` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_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();
+```
diff --git a/docs/0.0.2/dokumetry/node/examples/openai/fine-tuning.mdx b/docs/0.0.2/dokumetry/node/examples/openai/fine-tuning.mdx
new file mode 100644
index 00000000..513a8575
--- /dev/null
+++ b/docs/0.0.2/dokumetry/node/examples/openai/fine-tuning.mdx
@@ -0,0 +1,26 @@
+---
+title: 'Fine Tuning'
+description: 'Monitor OpenAI Fine Tuning API usage'
+---
+
+## Create Fine Tuning Job
+
+```javascript
+import OpenAI from "openai";
+import DokuMetry from 'dokumetry';
+
+const openai = new OpenAI();
+
+// Pass the above `openai` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+
+async function main() {
+ const fineTune = await openai.fineTuning.jobs.create({
+ training_file: "file-abc123"
+ });
+
+ console.log(fineTune);
+}
+
+main();
+```
\ No newline at end of file
diff --git a/docs/0.0.2/dokumetry/node/examples/openai/image.mdx b/docs/0.0.2/dokumetry/node/examples/openai/image.mdx
new file mode 100644
index 00000000..06b196ab
--- /dev/null
+++ b/docs/0.0.2/dokumetry/node/examples/openai/image.mdx
@@ -0,0 +1,44 @@
+---
+title: 'Image'
+description: 'Monitor OpenAI Image API usage'
+---
+
+## Create Image
+
+```javascript
+import OpenAI from "openai";
+import DokuMetry from 'dokumetry';
+
+const openai = new OpenAI();
+
+// Pass the above `openai` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+
+async function main() {
+ const image = await openai.images.generate({ model: "dall-e-3", prompt: "A cute baby sea otter" });
+
+ console.log(image.data);
+}
+main();
+```
+
+## Create Image Variation
+```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 URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+
+async function main() {
+ const image = await openai.images.createVariation({
+ image: fs.createReadStream("otter.png"),
+ });
+
+ console.log(image.data);
+}
+main();
+```
\ No newline at end of file
diff --git a/docs/0.0.2/dokumetry/node/introduction.mdx b/docs/0.0.2/dokumetry/node/introduction.mdx
new file mode 100644
index 00000000..92984a8d
--- /dev/null
+++ b/docs/0.0.2/dokumetry/node/introduction.mdx
@@ -0,0 +1,125 @@
+---
+title: 'Introduction'
+description: 'Monitor your NodeJS LLM Application with DokuMetry'
+---
+
+DokuMetry Node SDK is the official library from Doku to send LLM usage data from your NodeJS application to Doku.
+
+## Installation
+``` shell shell
+npm install dokumetry
+```
+
+## Usage
+
+### OpenAI
+
+```javascript openai.js
+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 URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", 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();
+```
+
+The following OpenAI Endpoints are supported for monitoring with DokuMetry
+
+- [Chat completions](/0.0.2/dokumetry/node/examples/openai/chat)
+- [Image Create](/0.0.2/dokumetry/node/examples/openai/image#create-image) and [Image Variations](/0.0.2/dokumetry/node/examples/openai/image#create-image-variation)
+- [Audio Speech Create](/0.0.2/dokumetry/node/examples/openai/audio)
+- [Embeddings](/0.0.2/dokumetry/node/examples/openai/embeddings)
+- [Fine Tunings](/0.0.2/dokumetry/node/examples/openai/fine-tuning)
+- [Completions](/0.0.2/dokumetry/node/examples/openai/chatCompletions)
+
+### Cohere
+
+```javascript cohere.js
+import { CohereClient } from "cohere-ai";
+import DokuMetry from 'dokumetry';
+
+const cohere = new CohereClient({
+ apiKey: "YOUR_API_KEY",
+});
+
+// Pass the above `cohere` object along with your DOKU URL and API key and this will make sure that all Cohere calls are automatically tracked.
+DokuMetry.init({llm: cohere, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+
+(async () => {
+ const prediction = await cohere.generate({
+ prompt: "hello",
+ maxTokens: 10,
+ });
+
+ console.log("Received prediction", prediction);
+})();
+```
+
+The following Cohere Endpoints are supported for monitoring with DokuMetry
+
+- [Chat](/0.0.2/dokumetry/node/examples/cohere/chat)
+- [Generate](/0.0.2/dokumetry/node/examples/cohere/generate)
+- [Summarize](/0.0.2/dokumetry/node/examples/cohere/summarize)
+- [Embed](/0.0.2/dokumetry/node/examples/cohere/embed)
+
+### Anthropic
+
+```javascript anthropic.js
+import Anthropic from '@anthropic-ai/sdk';
+import DokuMetry from 'dokumetry';
+
+const anthropic = new Anthropic({
+ apiKey: 'my api key', // defaults to process.env["ANTHROPIC_API_KEY"]
+});
+
+// Pass the above `anthropic` object along with your DOKU URL and API key and this will make sure that all Anthropic calls are automatically tracked.
+DokuMetry.init({llm: anthropic, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+
+async function main() {
+ const completion = await anthropic.completions.create({
+ model: 'claude-2',
+ max_tokens_to_sample: 300,
+ prompt: `${Anthropic.HUMAN_PROMPT} how does a court case get to the Supreme Court?${Anthropic.AI_PROMPT}`,
+ });
+}
+
+main();
+```
+
+The following Anthropic Endpoints are supported for monitoring with DokuMetry
+
+- [Completions](/0.0.2/dokumetry/node/examples/anthropic/anthropic-completions)
+
+## Parameters
+
+| Parameter | Description | Required |
+|-------------------|-----------------------------------------------------------|---------------|
+| llm | Language Learning Model (LLM) Object to track | Yes |
+| dokuUrl | URL of your Doku Instance | 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 |
+
+## Advanced Usage
+When using DokuMetry in Production environments, It is recommened to set `skipResp: True` for faster porcessing.
+
+To filter your LLM Usage according application or the environment, set the `application` and `environment` parameters with the actual values.
+
+
+## Requirements
+NodeJS >= 18.0 is supported.
+
+If you are interested in other runtime environments, please open or upvote an issue on [GitHub](https://github.com/dokulabs/doku/issues).
\ No newline at end of file
diff --git a/docs/0.0.2/dokumetry/python/examples/anthropic/anthropic-completions.mdx b/docs/0.0.2/dokumetry/python/examples/anthropic/anthropic-completions.mdx
new file mode 100644
index 00000000..b2ea104b
--- /dev/null
+++ b/docs/0.0.2/dokumetry/python/examples/anthropic/anthropic-completions.mdx
@@ -0,0 +1,27 @@
+---
+title: 'Completions'
+description: 'Monitor Anthropic Completions API Usage'
+---
+
+## Completions
+
+```javascript
+from anthropic import Anthropic, HUMAN_PROMPT, AI_PROMPT
+import dokumetry
+
+anthropic = Anthropic(
+ # defaults to os.environ.get("ANTHROPIC_API_KEY")
+ api_key="my_api_key",
+)
+
+# Pass the above `anthropic` object along with your DOKU URL and API key and this will make sure that all Anthropic calls are automatically tracked.
+dokumetry.init(llm=anthropic, doku_url="YOUR_DOKU_URL", api_key="YOUR_DOKU_TOKEN")
+
+completion = anthropic.completions.create(
+ model="claude-2",
+ max_tokens_to_sample=300,
+ prompt=f"{HUMAN_PROMPT} Hello, Claude{AI_PROMPT}",
+)
+print(completion.completion)
+```
+
diff --git a/docs/0.0.2/dokumetry/python/examples/cohere/chat.mdx b/docs/0.0.2/dokumetry/python/examples/cohere/chat.mdx
new file mode 100644
index 00000000..d8f8fb92
--- /dev/null
+++ b/docs/0.0.2/dokumetry/python/examples/cohere/chat.mdx
@@ -0,0 +1,52 @@
+---
+title: 'Chat'
+description: 'Monitor Cohere Chat API usage'
+---
+
+## Chat
+<CodeGroup>
+
+```python No Streaming
+import cohere
+import dokumetry
+
+co = cohere.Client('<<apiKey>>')
+
+# Pass the above `co` object along with your DOKU URL and API key and this will make sure that all Cohere calls are automatically tracked.
+dokumetry.init(llm=co, doku_url="YOUR_DOKU_URL", api_key="YOUR_DOKU_TOKEN")
+
+response = co.chat(
+ chat_history=[
+ {"role": "USER", "message": "Who discovered gravity?"},
+ {"role": "CHATBOT", "message": "The man who is widely credited with discovering gravity is Sir Isaac Newton"}
+ ],
+ message="What year was he born?",
+ # perform web search before answering the question. You can also use your own custom connector.
+ connectors=[{"id": "web-search"}]
+)
+print(response)
+```
+
+```python Streaming
+import cohere
+import dokumetry
+
+co = cohere.Client('<<apiKey>>')
+
+# Pass the above `co` object along with your DOKU URL and API key and this will make sure that all Cohere calls are automatically tracked.
+dokumetry.init(llm=co, doku_url="YOUR_DOKU_URL", api_key="YOUR_DOKU_TOKEN")
+
+response = co.chat(
+ chat_history=[
+ {"role": "USER", "message": "Who discovered gravity?"},
+ {"role": "CHATBOT", "message": "The man who is widely credited with discovering gravity is Sir Isaac Newton"}
+ ],
+ message="What year was he born?",
+ stream=True,
+ # perform web search before answering the question. You can also use your own custom connector.
+ connectors=[{"id": "web-search"}]
+)
+print(response)
+```
+
+</CodeGroup>
\ No newline at end of file
diff --git a/docs/0.0.2/dokumetry/python/examples/cohere/co-summarize.mdx b/docs/0.0.2/dokumetry/python/examples/cohere/co-summarize.mdx
new file mode 100644
index 00000000..c9bfcc05
--- /dev/null
+++ b/docs/0.0.2/dokumetry/python/examples/cohere/co-summarize.mdx
@@ -0,0 +1,44 @@
+---
+title: 'Summarize'
+description: 'Monitor Cohere Summarize API usage'
+---
+
+## Summarize
+
+```python
+import cohere
+import dokumetry
+
+co = cohere.Client('<<apiKey>>')
+
+# Pass the above `co` object along with your DOKU URL and API key and this will make sure that all Cohere calls are automatically tracked.
+dokumetry.init(llm=co, doku_url="YOUR_DOKU_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)
+```
\ No newline at end of file
diff --git a/docs/0.0.2/dokumetry/python/examples/cohere/embed.mdx b/docs/0.0.2/dokumetry/python/examples/cohere/embed.mdx
new file mode 100644
index 00000000..05900ae2
--- /dev/null
+++ b/docs/0.0.2/dokumetry/python/examples/cohere/embed.mdx
@@ -0,0 +1,23 @@
+---
+title: 'Embed'
+description: 'Monitor Cohere Embed API usage'
+---
+
+## Embed
+
+```python
+import cohere
+import dokumetry
+
+co = cohere.Client('<<apiKey>>')
+
+# Pass the above `co` object along with your DOKU URL and API key and this will make sure that all Cohere calls are automatically tracked.
+dokumetry.init(llm=co, doku_url="YOUR_DOKU_URL", api_key="YOUR_DOKU_TOKEN")
+
+response = co.embed(
+ texts=['hello', 'goodbye'],
+ model='embed-english-v3.0',
+ input_type='classification'
+)
+print(response)
+```
\ No newline at end of file
diff --git a/docs/0.0.2/dokumetry/python/examples/cohere/generate.mdx b/docs/0.0.2/dokumetry/python/examples/cohere/generate.mdx
new file mode 100644
index 00000000..b137a0c9
--- /dev/null
+++ b/docs/0.0.2/dokumetry/python/examples/cohere/generate.mdx
@@ -0,0 +1,21 @@
+---
+title: 'Generate'
+description: 'Monitor Cohere Generate API usage'
+---
+
+## Generate
+
+```python
+import cohere
+import dokumetry
+
+co = cohere.Client('<<apiKey>>')
+
+# Pass the above `co` object along with your DOKU URL and API key and this will make sure that all Cohere calls are automatically tracked.
+dokumetry.init(llm=co, doku_url="YOUR_DOKU_URL", api_key="YOUR_DOKU_TOKEN")
+
+response = co.generate(
+ prompt='Please explain to me how LLMs work',
+)
+print(response)
+```
\ No newline at end of file
diff --git a/docs/0.0.2/dokumetry/python/examples/openai/audio.mdx b/docs/0.0.2/dokumetry/python/examples/openai/audio.mdx
new file mode 100644
index 00000000..c927bb36
--- /dev/null
+++ b/docs/0.0.2/dokumetry/python/examples/openai/audio.mdx
@@ -0,0 +1,25 @@
+---
+title: 'Audio'
+description: 'Monitor OpenAI Audio API usage'
+---
+
+## Create Speech
+
+```python
+from pathlib import Path
+from openai import OpenAI
+import dokumetry
+
+client = OpenAI()
+
+# Pass the above `client` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+dokumetry.init(llm=client, doku_url="YOUR_DOKU_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)
+```
\ No newline at end of file
diff --git a/docs/0.0.2/dokumetry/python/examples/openai/chat.mdx b/docs/0.0.2/dokumetry/python/examples/openai/chat.mdx
new file mode 100644
index 00000000..5c97d068
--- /dev/null
+++ b/docs/0.0.2/dokumetry/python/examples/openai/chat.mdx
@@ -0,0 +1,143 @@
+---
+title: 'Chat'
+description: 'Monitor OpenAI Chat Completions API usage'
+---
+
+## Chat Completions
+
+<CodeGroup>
+
+```python Default
+from openai import OpenAI
+import dokumetry
+
+client = OpenAI()
+
+# Pass the above `client` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+dokumetry.init(llm=client, doku_url="YOUR_DOKU_URL", api_key="YOUR_DOKU_TOKEN")
+
+completion = client.chat.completions.create(
+ model="gpt-3.5-turbo",
+ messages=[
+ {"role": "system", "content": "You are a helpful assistant."},
+ {"role": "user", "content": "Hello!"}
+ ]
+)
+
+print(completion.choices[0].message)
+```
+
+```python Image Input
+from openai import OpenAI
+import dokumetry
+
+client = OpenAI()
+
+# Pass the above `client` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+dokumetry.init(llm=client, doku_url="YOUR_DOKU_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()
+
+# Pass the above `client` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+dokumetry.init(llm=client, doku_url="YOUR_DOKU_URL", api_key="YOUR_DOKU_TOKEN")
+
+completion = client.chat.completions.create(
+ model="gpt-3.5-turbo",
+ messages=[
+ {"role": "system", "content": "You are a helpful assistant."},
+ {"role": "user", "content": "Hello!"}
+ ],
+ stream=True
+)
+
+for chunk in completion:
+ print(chunk.choices[0].delta)
+```
+
+```python Functions
+from openai import OpenAI
+import dokumetry
+
+client = OpenAI()
+
+# Pass the above `client` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+dokumetry.init(llm=client, doku_url="YOUR_DOKU_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()
+
+# Pass the above `client` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+dokumetry.init(llm=client, doku_url="YOUR_DOKU_URL", api_key="YOUR_DOKU_TOKEN")
+
+completion = client.chat.completions.create(
+ model="gpt-3.5-turbo",
+ messages=[
+ {"role": "user", "content": "Hello!"}
+ ],
+ logprobs=True,
+ top_logprobs=2
+)
+
+print(completion.choices[0].message)
+print(completion.choices[0].logprobs)
+```
+
+</CodeGroup>
\ No newline at end of file
diff --git a/docs/0.0.2/dokumetry/python/examples/openai/completions.mdx b/docs/0.0.2/dokumetry/python/examples/openai/completions.mdx
new file mode 100644
index 00000000..ab3beb87
--- /dev/null
+++ b/docs/0.0.2/dokumetry/python/examples/openai/completions.mdx
@@ -0,0 +1,45 @@
+---
+title: 'Completions'
+description: 'Monitor OpenAI Completions API Usage'
+---
+
+## Completions
+<CodeGroup>
+```python No Streaming
+from openai import OpenAI
+import dokumetry
+
+client = OpenAI()
+
+# Pass the above `client` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+dokumetry.init(llm=client, doku_url="YOUR_DOKU_URL", api_key="YOUR_DOKU_TOKEN")
+
+client.completions.create(
+ model="gpt-3.5-turbo-instruct",
+ prompt="Say this is a test",
+ max_tokens=7,
+ temperature=0
+)
+```
+
+```python Streaming
+from openai import OpenAI
+import dokumetry
+
+client = OpenAI()
+
+# Pass the above `client` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+dokumetry.init(llm=client, doku_url="YOUR_DOKU_URL", api_key="YOUR_DOKU_TOKEN")
+
+for chunk in client.completions.create(
+ model="gpt-3.5-turbo-instruct",
+ prompt="Say this is a test",
+ max_tokens=7,
+ temperature=0,
+ stream=True
+):
+
+print(chunk.choices[0].text)
+```
+
+</CodeGroup>
\ No newline at end of file
diff --git a/docs/0.0.2/dokumetry/python/examples/openai/embeddings.mdx b/docs/0.0.2/dokumetry/python/examples/openai/embeddings.mdx
new file mode 100644
index 00000000..6c22743a
--- /dev/null
+++ b/docs/0.0.2/dokumetry/python/examples/openai/embeddings.mdx
@@ -0,0 +1,22 @@
+---
+title: 'Embeddings'
+description: 'Monitor OpenAI Embeddings API usage'
+---
+
+## Create Embeddings
+
+```python
+from openai import OpenAI
+import dokumetry
+
+client = OpenAI()
+
+# Pass the above `client` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+dokumetry.init(llm=client, doku_url="YOUR_DOKU_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"
+)
+```
diff --git a/docs/0.0.2/dokumetry/python/examples/openai/fine-tuning.mdx b/docs/0.0.2/dokumetry/python/examples/openai/fine-tuning.mdx
new file mode 100644
index 00000000..4de9f9c7
--- /dev/null
+++ b/docs/0.0.2/dokumetry/python/examples/openai/fine-tuning.mdx
@@ -0,0 +1,21 @@
+---
+title: 'Fine Tuning'
+description: 'Monitor OpenAI Fine Tuning API usage'
+---
+
+## Create Fine Tuning Job
+
+```python
+from openai import OpenAI
+import dokumetry
+
+client = OpenAI()
+
+# Pass the above `client` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+dokumetry.init(llm=client, doku_url="YOUR_DOKU_URL", api_key="YOUR_DOKU_TOKEN")
+
+client.fine_tuning.jobs.create(
+ training_file="file-abc123",
+ model="gpt-3.5-turbo"
+)
+```
\ No newline at end of file
diff --git a/docs/0.0.2/dokumetry/python/examples/openai/image.mdx b/docs/0.0.2/dokumetry/python/examples/openai/image.mdx
new file mode 100644
index 00000000..87df73ea
--- /dev/null
+++ b/docs/0.0.2/dokumetry/python/examples/openai/image.mdx
@@ -0,0 +1,40 @@
+---
+title: 'Image'
+description: 'Monitor OpenAI Image API usage'
+---
+
+## Create Image
+
+```python
+from openai import OpenAI
+import dokumetry
+
+client = OpenAI()
+
+# Pass the above `client` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+dokumetry.init(llm=client, doku_url="YOUR_DOKU_URL", api_key="YOUR_DOKU_TOKEN")
+
+client.images.generate(
+ model="dall-e-3",
+ prompt="A cute baby sea otter",
+ n=1,
+ size="1024x1024"
+)
+```
+
+## Create Image Variation
+```python
+from openai import OpenAI
+import dokumetry
+
+client = OpenAI()
+
+# Pass the above `client` object along with your DOKU URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+dokumetry.init(llm=client, doku_url="YOUR_DOKU_URL", api_key="YOUR_DOKU_TOKEN")
+
+response = client.images.create_variation(
+ image=open("image_edit_original.png", "rb"),
+ n=2,
+ size="1024x1024"
+)
+```
\ No newline at end of file
diff --git a/docs/0.0.2/dokumetry/python/introduction.mdx b/docs/0.0.2/dokumetry/python/introduction.mdx
new file mode 100644
index 00000000..92e19a8c
--- /dev/null
+++ b/docs/0.0.2/dokumetry/python/introduction.mdx
@@ -0,0 +1,119 @@
+---
+title: 'Introduction'
+description: 'Monitor your Python LLM Application with DokuMetry'
+---
+
+DokuMetry Python SDK is the official library from Doku to send LLM usage data from your Python application to Doku.
+
+## Installation
+``` shell shell
+pip install dokumetry
+```
+
+## Usage
+
+### OpenAI
+
+``` python openai.py
+from openai import OpenAI
+import dokumetry
+
+client = OpenAI(
+ api_key="YOUR_OPENAI_KEY"
+)
+
+# Pass the above `client` object along with your Doku URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+dokumetry.init(llm=client, doku_url="YOUR_DOKU_URL", api_key="YOUR_DOKU_TOKEN")
+
+chat_completion = client.chat.completions.create(
+ messages=[
+ {
+ "role": "user",
+ "content": "What is LLM Observability",
+ }
+ ],
+ model="gpt-3.5-turbo",
+)
+```
+
+The following OpenAI Endpoints are supported for monitoring with DokuMetry
+
+- [Chat completions](/0.0.2/dokumetry/python/examples/openai/chat)
+- [Image Create](/0.0.2/dokumetry/python/examples/openai/image#create-image) and [Image Variations](/0.0.2/dokumetry/python/examples/openai/image#create-image-variation)
+- [Audio Speech Create](/0.0.2/dokumetry/python/examples/openai/audio)
+- [Embeddings](/0.0.2/dokumetry/python/examples/openai/embeddings)
+- [Fine Tunings](/0.0.2/dokumetry/python/examples/openai/fine-tuning)
+- [Completions](/0.0.2/dokumetry/python/examples/openai/completions)
+
+### Cohere
+
+```python cohere.py
+import cohere
+import dokumetry
+
+# initialize the Cohere Client with an API Key
+co = cohere.Client('YOUR_API_KEY')
+
+# Pass the above `co` object along with your Doku URL and API key and this will make sure that all Cohere calls are automatically tracked.
+dokumetry.init(llm=co, doku_url="YOUR_DOKU_URL", api_key="YOUR_DOKU_TOKEN")
+
+# generate a prediction for a prompt
+prediction = co.chat(message='What is LLM Observability?', model='command')
+
+# print the predicted text
+print(f'Chatbot: {prediction.text}')
+```
+
+The following Cohere Endpoints are supported for monitoring with DokuMetry
+
+- [Chat](/0.0.2/dokumetry/python/examples/cohere/chat)
+- [Generate](/0.0.2/dokumetry/python/examples/cohere/generate)
+- [Summarize](/0.0.2/dokumetry/python/examples/cohere/co-summarize)
+- [Embed](/0.0.2/dokumetry/python/examples/cohere/embed)
+
+### Anthropic
+
+```python anthropic.py
+from anthropic import Anthropic, HUMAN_PROMPT, AI_PROMPT
+import dokumetry
+
+anthropic = Anthropic(
+ # defaults to os.environ.get("ANTHROPIC_API_KEY")
+ api_key="my api key",
+)
+
+# Pass the above `anthropic` object along with your Doku URL and API key and this will make sure that all Anthropic calls are automatically tracked.
+dokumetry.init(llm=anthropic, doku_url="YOUR_DOKU_URL", api_key="YOUR_DOKU_TOKEN")
+
+completion = anthropic.completions.create(
+ model="claude-2",
+ max_tokens_to_sample=300,
+ prompt=f"{HUMAN_PROMPT} What is LLM Observability?{AI_PROMPT}",
+)
+print(completion.completion)
+```
+
+The following Anthropic Endpoints are supported for monitoring with DokuMetry
+
+- [Completions](/0.0.2/dokumetry/python/examples/anthropic/anthropic-completions.mdx)
+
+## Parameters
+
+| Parameter | Description | Required |
+|-------------------|-----------------------------------------------------------|---------------|
+| llm | Language Learning Model (LLM) Object to track | Yes |
+| doku_url | URL of your Doku Instance | 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 |
+
+## Advanced Usage
+When using DokuMetry in Production environments, It is recommened to set `skip_resp = true` for faster porcessing.
+
+To filter your LLM Usage according application or the environment, set the `application` and `environment` paramaters with the actual values.
+
+## Requirements
+Python >= 3.7 is supported.
+
+If you are interested in other runtime environments, please open or upvote an issue on [GitHub](https://github.com/dokulabs/doku/issues).
\ No newline at end of file
diff --git a/docs/0.0.2/installation.mdx b/docs/0.0.2/installation.mdx
new file mode 100644
index 00000000..5dbbb68e
--- /dev/null
+++ b/docs/0.0.2/installation.mdx
@@ -0,0 +1,273 @@
+---
+title: 'Installing Doku'
+description: 'Deploy Doku in your preferred environment'
+icon: 'circle-down'
+---
+
+Doku flexibly adapts to your preferred environment. Select a deployment method that best fits your setup:
+
+<CardGroup cols={2}>
+ <Card
+ title="Kubernetes"
+ icon={<svg role="img" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg">
+ <title>Kubernetes</title>
+ <path fill="#FFA500" d="M10.204 14.35l.007.01-.999 2.413a5.171 5.171 0 0 1-2.075-2.597l2.578-.437.004.005a.44.44 0 0 1 .484.606zm-.833-2.129a.44.44 0 0 0 .173-.756l.002-.011L7.585 9.7a5.143 5.143 0 0 0-.73 3.255l2.514-.725.002-.009zm1.145-1.98a.44.44 0 0 0 .699-.337l.01-.005.15-2.62a5.144 5.144 0 0 0-3.01 1.442l2.147 1.523.004-.002zm.76 2.75l.723.349.722-.347.18-.78-.5-.623h-.804l-.5.623.179.779zm1.5-3.095a.44.44 0 0 0 .7.336l.008.003 2.134-1.513a5.188 5.188 0 0 0-2.992-1.442l.148 2.615.002.001zm10.876 5.97l-5.773 7.181a1.6 1.6 0 0 1-1.248.594l-9.261.003a1.6 1.6 0 0 1-1.247-.596l-5.776-7.18a1.583 1.583 0 0 1-.307-1.34L2.1 5.573c.108-.47.425-.864.863-1.073L11.305.513a1.606 1.606 0 0 1 1.385 0l8.345 3.985c.438.209.755.604.863 1.073l2.062 8.955c.108.47-.005.963-.308 1.34zm-3.289-2.057c-.042-.01-.103-.026-.145-.034-.174-.033-.315-.025-.479-.038-.35-.037-.638-.067-.895-.148-.105-.04-.18-.165-.216-.216l-.201-.059a6.45 6.45 0 0 0-.105-2.332 6.465 6.465 0 0 0-.936-2.163c.052-.047.15-.133.177-.159.008-.09.001-.183.094-.282.197-.185.444-.338.743-.522.142-.084.273-.137.415-.242.032-.024.076-.062.11-.089.24-.191.295-.52.123-.736-.172-.216-.506-.236-.745-.045-.034.027-.08.062-.111.088-.134.116-.217.23-.33.35-.246.25-.45.458-.673.609-.097.056-.239.037-.303.033l-.19.135a6.545 6.545 0 0 0-4.146-2.003l-.012-.223c-.065-.062-.143-.115-.163-.25-.022-.268.015-.557.057-.905.023-.163.061-.298.068-.475.001-.04-.001-.099-.001-.142 0-.306-.224-.555-.5-.555-.275 0-.499.249-.499.555l.001.014c0 .041-.002.092 0 .128.006.177.044.312.067.475.042.348.078.637.056.906a.545.545 0 0 1-.162.258l-.012.211a6.424 6.424 0 0 0-4.166 2.003 8.373 8.373 0 0 1-.18-.128c-.09.012-.18.04-.297-.029-.223-.15-.427-.358-.673-.608-.113-.12-.195-.234-.329-.349-.03-.026-.077-.062-.111-.088a.594.594 0 0 0-.348-.132.481.481 0 0 0-.398.176c-.172.216-.117.546.123.737l.007.005.104.083c.142.105.272.159.414.242.299.185.546.338.743.522.076.082.09.226.1.288l.16.143a6.462 6.462 0 0 0-1.02 4.506l-.208.06c-.055.072-.133.184-.215.217-.257.081-.546.11-.895.147-.164.014-.305.006-.48.039-.037.007-.09.02-.133.03l-.004.002-.007.002c-.295.071-.484.342-.423.608.061.267.349.429.645.365l.007-.001.01-.003.129-.029c.17-.046.294-.113.448-.172.33-.118.604-.217.87-.256.112-.009.23.069.288.101l.217-.037a6.5 6.5 0 0 0 2.88 3.596l-.09.218c.033.084.069.199.044.282-.097.252-.263.517-.452.813-.091.136-.185.242-.268.399-.02.037-.045.095-.064.134-.128.275-.034.591.213.71.248.12.556-.007.69-.282v-.002c.02-.039.046-.09.062-.127.07-.162.094-.301.144-.458.132-.332.205-.68.387-.897.05-.06.13-.082.215-.105l.113-.205a6.453 6.453 0 0 0 4.609.012l.106.192c.086.028.18.042.256.155.136.232.229.507.342.84.05.156.074.295.145.457.016.037.043.09.062.129.133.276.442.402.69.282.247-.118.341-.435.213-.71-.02-.039-.045-.096-.065-.134-.083-.156-.177-.261-.268-.398-.19-.296-.346-.541-.443-.793-.04-.13.007-.21.038-.294-.018-.022-.059-.144-.083-.202a6.499 6.499 0 0 0 2.88-3.622c.064.01.176.03.213.038.075-.05.144-.114.28-.104.266.039.54.138.87.256.154.06.277.128.448.173.036.01.088.019.13.028l.009.003.007.001c.297.064.584-.098.645-.365.06-.266-.128-.537-.423-.608zM16.4 9.701l-1.95 1.746v.005a.44.44 0 0 0 .173.757l.003.01 2.526.728a5.199 5.199 0 0 0-.108-1.674A5.208 5.208 0 0 0 16.4 9.7zm-4.013 5.325a.437.437 0 0 0-.404-.232.44.44 0 0 0-.372.233h-.002l-1.268 2.292a5.164 5.164 0 0 0 3.326.003l-1.27-2.296h-.01zm1.888-1.293a.44.44 0 0 0-.27.036.44.44 0 0 0-.214.572l-.003.004 1.01 2.438a5.15 5.15 0 0 0 2.081-2.615l-2.6-.44-.004.005z"/></svg>}
+ href="/0.0.2/installation#kubernetes"
+ >
+ Deploy Doku in a Kubernetes Cluster using Helm
+ </Card>
+ <Card
+ title="Docker"
+ icon="docker"
+ href="/0.0.2/installation#docker"
+ >
+ Deploy Doku using docker compose
+ </Card>
+ <Card
+ title="Linux"
+ icon="linux"
+ href="/0.0.2/installation#linux"
+ >
+ Deploy Doku in a Linux Host
+ </Card>
+ <Card
+ title="Windows"
+ icon="windows"
+ href="/0.0.2/installation#windows"
+ >
+ Deploy Doku in a Windows Host
+ </Card>
+</CardGroup>
+
+## Kubernetes
+
+Deploy Doku on your Kubernetes cluster using the [Doku Helm chart](https://github.com/dokulabs/helm/tree/main/charts/doku) 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 update
+ ```
+ </Step>
+ <Step title="Installing the Helm Chart">
+ ```shell shell
+ helm install doku dokulabs/doku
+ ```
+ </Step>
+</Steps>
+<Info>As Doku does not have a built-in visualization UI yet, it is preferred that you set up the observabilityPlatform configuration within the [values.yaml](https://github.com/dokulabs/helm/blob/main/charts/doku/values.yaml) file. Doing so enables visualization of the LLM Observability data processed by Doku using an external observability platform.</Info>
+
+## Docker
+Quickly spin up Doku using Docker for a fast and straightforward setup.
+
+<Steps>
+ <Step title="Install TimescaleDB">
+ <Steps>
+ <Step title="Pull TimescaleDB Image">
+ ```shell
+ docker pull timescale/timescaledb-ha:pg14-latest
+ ```
+ </Step>
+ <Step title="Run TimescaleDB Image">
+ ```shell
+ docker run -d --name timescaledb -p 127.0.0.1:5432:5432 \
+ -e POSTGRES_PASSWORD=password timescale/timescaledb-ha:pg14-latest
+ ```
+ </Step>
+ </Steps>
+ </Step>
+ <Step title="Install Doku">
+ <Steps>
+ <Step title="Pull Doku Image">
+ ```shell
+ docker pull ghcr.io/dokulabs/doku-ingester:0.0.2
+ ```
+ </Step>
+ <Step title="Create a Doku Configuration file">
+ Create a file named `doku.yml` in the current directory. This YAML configuration file will contain all the necessary details for Doku to connect to your TimescaleDB instance and other services. Here is an example configuration:
+
+ ```yaml doku.yml
+ ingesterPort: 9044
+
+ pricingInfo:
+ url: https://raw.githubusercontent.com/dokulabs/ingester/main/assets/pricing.json # URL to download Pricing data file
+
+ # Configuration for the Doku Backend Database (TimescaleDB)
+ dbConfig:
+ name: DBNAME # Name of the database, Example: "postgres"
+ username: USERNAME # Username to connect to the database, Example: "admin"
+ password: PASSWORD # Password to connect to the database, Example: "DOKU"
+ host: HOSTURL # Hostname of the database, Example: "174.21.1.2"
+ port: DBPORT # Port of the database, Example: 5432
+ sslMode: SSLMODE # SSL Mode of the database, Example: "require"
+ maxOpenConns: MAXOPENCONNS # Maximum number of open connections to the database, Example: 15
+ maxIdleConns: MAXOPENCONNS # Maximum number of idle connections to the database, Example: 15
+ dataTable: DATATABLE # Name of the table to store LLM Data, Example: "DOKU"
+ apiKeyTable: APIKEYTABLE # Name of the table to store API Keys, Example: "APIKEYS"
+
+ observabilityPlatform:
+ enabled: false
+ ```
+ Be sure to replace the placeholder values with your actual database details and desired settings.
+ <Info>
+ As Doku does not have a built-in visualization UI yet, it is preferred that you set up the observabilityPlatform configuration within the [Doku Configuration file (`doku.yml`)](/0.0.2/configuration#observability-platform-configuration) file.
+
+ Doing so enables visualization of the LLM Observability data processed by Doku using an external observability platform.
+ </Info>
+ </Step>
+ <Step title="Run the Doku Image">
+ ```shell
+ docker run -d --name doku -p 127.0.0.2:9044:9044 -v /doku.yml:/doku.yml dokulabs/ingester:0.0.2 --config /doku.yml
+ ```
+ </Step>
+ </Steps>
+ </Step>
+</Steps>
+
+## Linux
+<Steps>
+ <Step title="Install TimescaleDB">
+ Follow the Instructions [here](https://docs.timescale.com/self-hosted/latest/install/installation-linux/#installing-self-hosted-timescaledb-on-debian-based-systems) to install TimescaleDB in your Linux host.
+ </Step>
+ <Step title="Create a Doku Configuration file">
+ Create a file named `doku.yml` in the current directory. This YAML configuration file will contain all the necessary details for Doku to connect to your TimescaleDB instance and other services. Here is an example configuration:
+
+ ```yaml doku.yml
+ ingesterPort: 9044
+
+ pricingInfo:
+ url: https://raw.githubusercontent.com/dokulabs/doku/main/assets/pricing.json # URL to download Pricing data file
+
+ # Configuration for the Doku Backend Database (TimescaleDB)
+ dbConfig:
+ name: DBNAME # Name of the database, Example: "postgres"
+ username: USERNAME # Username to connect to the database, Example: "admin"
+ password: PASSWORD # Password to connect to the database, Example: "DOKU"
+ host: HOSTURL # Hostname of the database, Example: "174.21.1.2"
+ port: DBPORT # Port of the database, Example: 5432
+ sslMode: SSLMODE # SSL Mode of the database, Example: "require"
+ maxOpenConns: MAXOPENCONNS # Maximum number of open connections to the database, Example: 15
+ maxIdleConns: MAXOPENCONNS # Maximum number of idle connections to the database, Example: 15
+ dataTable: DATATABLE # Name of the table to store LLM Data, Example: "DOKU"
+ apiKeyTable: APIKEYTABLE # Name of the table to store API Keys, Example: "APIKEYS"
+
+ observabilityPlatform:
+ enabled: false
+ ```
+ Be sure to replace the placeholder values with your actual database details and desired settings.
+ <Info>
+ As Doku does not have a built-in visualization UI yet, it is preferred that you set up the observabilityPlatform configuration within the [Doku Configuration file (`doku.yml`)](/0.0.2/configuration#observability-platform-configuration) file.
+
+ Doing so enables visualization of the LLM Observability data processed by Doku using an external observability platform.
+ </Info>
+ </Step>
+ <Step title="Install Doku in a linux Host">
+ <Tabs>
+ <Tab title="Linux">
+ <CodeGroup>
+ ```shell amd64
+ curl -O -L https://github.com/dokulabs/doku/releases/download/0.0.2/ingester-linux-amd64
+ chmod +x ingester-linux-amd64
+ ./ingester-linux-amd64 --config doku.yml
+ ```
+
+ ```shell arm64
+ curl -O -L https://github.com/dokulabs/doku/releases/download/0.0.2/ingester-linux-arm64
+ chmod +x ingester-linux-arm64
+ ./ingester-linux-arm64 --config doku.yml
+ ```
+
+ ```shell arm
+ curl -O -L https://github.com/dokulabs/doku/releases/download/0.0.2/ingester-linux-arm
+ chmod +x ingester-linux-arm
+ ./ingester-linux-arm --config doku.yml
+ ```
+
+ ```shell ppc64le
+ curl -O -L https://github.com/dokulabs/doku/releases/download/0.0.2/ingester-linux-ppc64le
+ chmod +x ingester-linux-ppc64le
+ ./ingester-linux-ppc64le --config doku.yml
+ ```
+ </CodeGroup>
+ </Tab>
+ <Tab title="Darwin">
+ <CodeGroup>
+ ```shell amd64
+ curl -O -L https://github.com/dokulabs/doku/releases/download/0.0.2/ingester-darwin-amd64
+ chmod +x ingester-darwin-amd64
+ ./ingester-darwin-amd64 --config doku.yml
+ ```
+
+ ```shell arm64
+ curl -O -L https://github.com/dokulabs/doku/releases/download/0.0.2/ingester-darwin-arm64
+ chmod +x ingester-darwin-arm64
+ ./ingester-darwin-arm64 --config doku.yml
+ ```
+ </CodeGroup>
+ </Tab>
+ </Tabs>
+ </Step>
+</Steps>
+
+## Windows
+<Steps>
+ <Step title="Install TimescaleDB">
+ <Steps>
+ Download and install the Visual C++ Redistributable for Visual Studio from [www.microsoft.com](https://www.microsoft.com/en-us/download/details.aspx?id=48145).
+
+ Download and install PostgreSQL from [www.postgresql.org](https://www.postgresql.org/download/windows/). You might need to add the `pg_config` file location to your path. In the Windows Search tool, search for `system environment variables`. The path should be `C:\Program Files\PostgreSQL\<version>\bin`.
+
+ Download the TimescaleDB installation `.zip` file from [Windows releases](https://docs.timescale.com/self-hosted/latest/install/installation-windows/#windows-releases).
+
+ Locate the downloaded file on your local file system, and extract the files.
+
+ In the extracted TimescaleDB directory, right-click the `setup.exe` file and select `Run as Administrator` to start the installer.
+ </Steps>
+ </Step>
+ <Step title="Create a Doku Configuration file">
+ Create a file named `doku.yml` in the current directory. This YAML configuration file will contain all the necessary details for Doku to connect to your TimescaleDB instance and other services. Here is an example configuration:
+
+ ```yaml doku.yml
+ ingesterPort: 9044
+
+ pricingInfo:
+ url: https://raw.githubusercontent.com/dokulabs/doku/main/assets/pricing.json # URL to download Pricing data file
+
+ # Configuration for the Doku Backend Database (TimescaleDB)
+ dbConfig:
+ name: DBNAME # Name of the database, Example: "postgres"
+ username: USERNAME # Username to connect to the database, Example: "admin"
+ password: PASSWORD # Password to connect to the database, Example: "DOKU"
+ host: HOSTURL # Hostname of the database, Example: "174.21.1.2"
+ port: DBPORT # Port of the database, Example: 5432
+ sslMode: SSLMODE # SSL Mode of the database, Example: "require"
+ maxOpenConns: MAXOPENCONNS # Maximum number of open connections to the database, Example: 15
+ maxIdleConns: MAXOPENCONNS # Maximum number of idle connections to the database, Example: 15
+ dataTable: DATATABLE # Name of the table to store LLM Data, Example: "DOKU"
+ apiKeyTable: APIKEYTABLE # Name of the table to store API Keys, Example: "APIKEYS"
+
+ observabilityPlatform:
+ enabled: false
+ ```
+ Be sure to replace the placeholder values with your actual database details and desired settings.
+ <Info>
+ As Doku does not have a built-in visualization UI yet, it is preferred that you set up the observabilityPlatform configuration within the [Doku Configuration file (`doku.yml`)](/0.0.2/configuration#observability-platform-configuration) file.
+
+ Doing so enables visualization of the LLM Observability data processed by Doku using an external observability platform.
+ </Info>
+ </Step>
+ <Step title="Install Doku in a Windows Host">
+ <CodeGroup>
+ ```shell amd64
+ invoke-WebRequest -Uri "https://github.com/dokulabs/doku/releases/download/0.0.2/ingester-windows-amd64" -OutFile "ingester.exe"
+ .\ingester.exe --config doku.yml
+ ```
+
+ ```shell 386
+ invoke-WebRequest -Uri "https://github.com/dokulabs/doku/releases/download/0.0.2/ingester-windows-386" -OutFile "ingester.exe"
+ .\ingester.exe --config doku.yml
+ ```
+ </CodeGroup>
+ </Step>
+</Steps>
+
diff --git a/docs/0.0.2/integrations/datadog.mdx b/docs/0.0.2/integrations/datadog.mdx
new file mode 100644
index 00000000..92dffa4f
--- /dev/null
+++ b/docs/0.0.2/integrations/datadog.mdx
@@ -0,0 +1,17 @@
+---
+title: 'DataDog'
+description: 'Connect Doku to DataDog'
+---
+
+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)
+
+Add the following to your doku configuration file(`doku.yml`).
+
+```yaml doku.yml
+observabilityPlatform:
+ enabled: true # Enable or Disable the Observability Platform, Example: true
+ datadog:
+ metricsUrl: <your-datadog-metrics-url> # URL to the DataDog Metrics API
+ logsUrl: <your-datadog-logs-url> # URL to the DataDog Logs API
+ apiKey: <your-datadog-api-key> # API Key of the DataDog Account
+```
\ No newline at end of file
diff --git a/docs/0.0.2/integrations/grafanacloud.mdx b/docs/0.0.2/integrations/grafanacloud.mdx
new file mode 100644
index 00000000..044bba27
--- /dev/null
+++ b/docs/0.0.2/integrations/grafanacloud.mdx
@@ -0,0 +1,2351 @@
+---
+title: 'Grafana Cloud'
+description: 'Connect Doku to Grafana Cloud'
+---
+
+<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>
+
+Doku can automatically send LLM usage data from Doku to Grafana Cloud using the [Grafana Cloud Influx Telegraf](https://grafana.com/docs/grafana-cloud/send-data/metrics/metrics-influxdb/push-from-telegraf/) and [Loki Push HTTP API](https://grafana.com/docs/loki/latest/reference/api/#push-log-entries-to-loki)
+
+Add the following to your doku configuration file(`doku.yml`).
+
+```yaml doku.yml
+observabilityPlatform:
+ enabled: true # Enable or Disable the Observability Platform, Example: true
+ grafanaCloud:
+ promUrl: <your-grafana-cloud-influx-line-proxy-url> # URL to the Influx Line Proxy URL of the Grafana Cloud Prometheus Instance
+ promUsername: <your-prometheus-userid> # Prometheus User ID of the Grafana Cloud Prometheus Instance
+ lokiUrl: <your-loki-push-url> # URL to the Loki Push URL of the Grafana Cloud Loki Instance
+ lokiUsername: <your-loki-username> # Loki Username of the Grafana Cloud Loki Instance
+ accessToken: <your-grafana-cloud-access-token> # Access Token of the Grafana Cloud Instance
+```
+
+## 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": 14,
+ "links": [
+ {
+ "icon": "info",
+ "tags": [],
+ "targetBlank": true,
+ "title": "Doku Documentation",
+ "tooltip": "",
+ "type": "link",
+ "url": "https://docs.dokulabs.com/"
+ },
+ {
+ "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": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "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": "10.4.0-65875",
+ "transparent": true,
+ "type": "text"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "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": "10.4.0-65875",
+ "transparent": true,
+ "type": "text"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "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": "10.4.0-65875",
+ "transparent": true,
+ "type": "text"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "description": "This panel shows the total number of requests sent to Large Language Models (LLM) Platforms in the selected time interval.",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "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": "10.4.0-65875",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "disableTextWrap": false,
+ "editorMode": "code",
+ "expr": "count_over_time(doku_llm_requestDuration{job=\"doku\", applicationName=~\"$Application\", environment=~\"$Environment\"}[$__interval])",
+ "format": "table",
+ "fullMetaSearch": false,
+ "includeNullMetadata": true,
+ "legendFormat": "__auto",
+ "range": true,
+ "rawQuery": true,
+ "rawSql": "SELECT count(*) FROM DOKU\nWHERE $__timeFilter(time)",
+ "refId": "A",
+ "sql": {
+ "columns": [
+ {
+ "name": "COUNT",
+ "parameters": [
+ {
+ "name": "environment",
+ "type": "functionParameter"
+ }
+ ],
+ "type": "function"
+ }
+ ],
+ "groupBy": [
+ {
+ "property": {
+ "type": "string"
+ },
+ "type": "groupBy"
+ }
+ ],
+ "limit": 50
+ },
+ "table": "doku",
+ "useBackend": false
+ }
+ ],
+ "title": "Total Requests",
+ "transformations": [
+ {
+ "id": "groupBy",
+ "options": {
+ "fields": {
+ "Value": {
+ "aggregations": [
+ "sum"
+ ],
+ "operation": "aggregate"
+ },
+ "job": {
+ "aggregations": [],
+ "operation": "groupby"
+ }
+ }
+ }
+ }
+ ],
+ "transparent": true,
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "description": "This panel shows the average time taken to process each request by the Large Language Models (LLM), offering a snapshot of system performance and efficiency.",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 5
+ }
+ ]
+ },
+ "unit": "s",
+ "unitScale": true
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 3,
+ "w": 4,
+ "x": 6,
+ "y": 4
+ },
+ "id": 4,
+ "options": {
+ "colorMode": "background",
+ "graphMode": "area",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showPercentChange": false,
+ "textMode": "auto",
+ "wideLayout": true
+ },
+ "pluginVersion": "10.4.0-65875",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "disableTextWrap": false,
+ "editorMode": "code",
+ "expr": "doku_llm_requestDuration{job=\"doku\", applicationName=~\"$Application\", environment=~\"$Environment\"}",
+ "format": "table",
+ "fullMetaSearch": false,
+ "includeNullMetadata": true,
+ "legendFormat": "__auto",
+ "range": true,
+ "rawQuery": true,
+ "rawSql": "SELECT AVG(requestduration) FROM doku\nWHERE $__timeFilter(time)",
+ "refId": "A",
+ "sql": {
+ "columns": [
+ {
+ "name": "AVG",
+ "parameters": [
+ {
+ "name": "requestduration",
+ "type": "functionParameter"
+ }
+ ],
+ "type": "function"
+ }
+ ],
+ "groupBy": [
+ {
+ "property": {
+ "type": "string"
+ },
+ "type": "groupBy"
+ }
+ ],
+ "limit": 50
+ },
+ "table": "doku",
+ "useBackend": false
+ }
+ ],
+ "title": "Avg Request Duration",
+ "transformations": [
+ {
+ "id": "groupBy",
+ "options": {
+ "fields": {
+ "Value": {
+ "aggregations": [
+ "mean"
+ ],
+ "operation": "aggregate"
+ },
+ "job": {
+ "aggregations": [],
+ "operation": "groupby"
+ }
+ }
+ }
+ }
+ ],
+ "transparent": true,
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "description": "This panel shows the average count of Total tokens used per LLM request",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 1000
+ }
+ ]
+ },
+ "unit": "none",
+ "unitScale": true
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 3,
+ "w": 4,
+ "x": 10,
+ "y": 4
+ },
+ "id": 5,
+ "options": {
+ "colorMode": "background",
+ "graphMode": "area",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showPercentChange": false,
+ "textMode": "auto",
+ "wideLayout": true
+ },
+ "pluginVersion": "10.4.0-65875",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "disableTextWrap": false,
+ "editorMode": "code",
+ "expr": "doku_llm_totalTokens{job=\"doku\", applicationName=~\"$Application\", environment=~\"$Environment\"}",
+ "format": "table",
+ "fullMetaSearch": false,
+ "includeNullMetadata": true,
+ "legendFormat": "__auto",
+ "range": true,
+ "rawQuery": true,
+ "rawSql": "SELECT AVG(totaltokens) FROM doku\nWHERE $__timeFilter(time)",
+ "refId": "A",
+ "sql": {
+ "columns": [
+ {
+ "name": "AVG",
+ "parameters": [
+ {
+ "name": "totaltokens",
+ "type": "functionParameter"
+ }
+ ],
+ "type": "function"
+ }
+ ],
+ "groupBy": [
+ {
+ "property": {
+ "type": "string"
+ },
+ "type": "groupBy"
+ }
+ ],
+ "limit": 50
+ },
+ "table": "doku",
+ "useBackend": false
+ }
+ ],
+ "title": "Avg Tokens per Request",
+ "transformations": [
+ {
+ "id": "groupBy",
+ "options": {
+ "fields": {
+ "Value": {
+ "aggregations": [
+ "mean"
+ ],
+ "operation": "aggregate"
+ },
+ "job": {
+ "aggregations": [],
+ "operation": "groupby"
+ }
+ }
+ }
+ }
+ ],
+ "transparent": true,
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "description": "This panel shows the average cost incurred per request to the LLM, helping monitor and optimize budget allocation for LLM usage.",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 5
+ }
+ ]
+ },
+ "unit": "currencyUSD",
+ "unitScale": true
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 3,
+ "w": 4,
+ "x": 14,
+ "y": 4
+ },
+ "id": 6,
+ "options": {
+ "colorMode": "background",
+ "graphMode": "area",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showPercentChange": false,
+ "textMode": "auto",
+ "wideLayout": true
+ },
+ "pluginVersion": "10.4.0-65875",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "disableTextWrap": false,
+ "editorMode": "code",
+ "expr": "doku_llm_usageCost{job=\"doku\", applicationName=~\"$Application\", environment=~\"$Environment\"}",
+ "format": "table",
+ "fullMetaSearch": false,
+ "includeNullMetadata": true,
+ "legendFormat": "__auto",
+ "range": true,
+ "rawQuery": true,
+ "rawSql": "SELECT AVG(usagecost) FROM doku \nWHERE $__timeFilter(time)",
+ "refId": "A",
+ "sql": {
+ "columns": [
+ {
+ "name": "AVG",
+ "parameters": [
+ {
+ "name": "usagecost",
+ "type": "functionParameter"
+ }
+ ],
+ "type": "function"
+ }
+ ],
+ "groupBy": [
+ {
+ "property": {
+ "type": "string"
+ },
+ "type": "groupBy"
+ }
+ ],
+ "limit": 50
+ },
+ "table": "doku",
+ "useBackend": false
+ }
+ ],
+ "title": "Avg Cost / Request",
+ "transformations": [
+ {
+ "id": "groupBy",
+ "options": {
+ "fields": {
+ "Value": {
+ "aggregations": [
+ "mean"
+ ],
+ "operation": "aggregate"
+ },
+ "job": {
+ "aggregations": [],
+ "operation": "groupby"
+ }
+ }
+ }
+ }
+ ],
+ "transparent": true,
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "description": "This panel shows the total cost on LLM requests over the selected period.",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "continuous-BlPu"
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ }
+ ]
+ },
+ "unit": "currencyUSD",
+ "unitScale": true
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 3,
+ "w": 6,
+ "x": 18,
+ "y": 4
+ },
+ "id": 10,
+ "options": {
+ "colorMode": "background",
+ "graphMode": "area",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showPercentChange": false,
+ "textMode": "auto",
+ "wideLayout": true
+ },
+ "pluginVersion": "10.4.0-65875",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "disableTextWrap": false,
+ "editorMode": "code",
+ "expr": "doku_llm_usageCost{job=\"doku\", applicationName=~\"$Application\", environment=~\"$Environment\"}",
+ "format": "table",
+ "fullMetaSearch": false,
+ "includeNullMetadata": true,
+ "legendFormat": "__auto",
+ "range": true,
+ "rawQuery": true,
+ "rawSql": "SELECT SUM(usagecost) FROM doku\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",
+ "useBackend": false
+ }
+ ],
+ "title": "Total Cost",
+ "transformations": [
+ {
+ "id": "groupBy",
+ "options": {
+ "fields": {
+ "Value": {
+ "aggregations": [
+ "sum"
+ ],
+ "operation": "aggregate"
+ },
+ "job": {
+ "aggregations": [],
+ "operation": "groupby"
+ }
+ }
+ }
+ }
+ ],
+ "transparent": true,
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "description": "This panel shows the count of API requests made to LLMs over the selected time.",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "continuous-BlPu"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "series",
+ "axisGridShow": true,
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 54,
+ "gradientMode": "hue",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "smooth",
+ "lineStyle": {
+ "dash": [
+ 10,
+ 10
+ ],
+ "fill": "dash"
+ },
+ "lineWidth": 2,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "always",
+ "spanNulls": true,
+ "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": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "disableTextWrap": false,
+ "editorMode": "code",
+ "expr": "count(count_over_time(doku_llm_requestDuration{job=\"doku\", applicationName=~\"$Application\", environment=~\"$Environment\"}[$__interval]))",
+ "format": "time_series",
+ "fullMetaSearch": false,
+ "includeNullMetadata": true,
+ "legendFormat": "Requests",
+ "range": true,
+ "rawQuery": true,
+ "rawSql": "SELECT\n DATE_TRUNC('day', \"time\") AS \"time\",\n COUNT(endpoint) AS total_requests\nFROM \n doku\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",
+ "useBackend": false
+ }
+ ],
+ "title": "Total Requests overtime",
+ "transformations": [],
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "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.",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "fixedColor": "blue",
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ }
+ },
+ "mappings": [],
+ "unit": "none",
+ "unitScale": true
+ },
+ "overrides": [
+ {
+ "__systemRef": "hideSeriesFrom",
+ "matcher": {
+ "id": "byNames",
+ "options": {
+ "mode": "exclude",
+ "names": [
+ "Value (sum)",
+ "Chat"
+ ],
+ "prefix": "All except:",
+ "readOnly": true
+ }
+ },
+ "properties": [
+ {
+ "id": "custom.hideFrom",
+ "value": {
+ "legend": false,
+ "tooltip": false,
+ "viz": true
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 9,
+ "w": 6,
+ "x": 0,
+ "y": 12
+ },
+ "id": 12,
+ "options": {
+ "displayLabels": [
+ "name",
+ "value"
+ ],
+ "legend": {
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true,
+ "values": []
+ },
+ "pieType": "pie",
+ "reduceOptions": {
+ "calcs": [
+ "allValues"
+ ],
+ "fields": "",
+ "values": true
+ },
+ "tooltip": {
+ "mode": "single",
+ "sort": "asc"
+ }
+ },
+ "pluginVersion": "10.4.0-65875",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "disableTextWrap": false,
+ "editorMode": "code",
+ "expr": "count_over_time(doku_llm_requestDuration{job=\"doku\", applicationName=~\"$Application\", environment=~\"$Environment\"}[$__interval])",
+ "format": "table",
+ "fullMetaSearch": false,
+ "includeNullMetadata": true,
+ "legendFormat": "__auto",
+ "range": true,
+ "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.completions%' 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\n WHERE $__timeFilter(time)\n ) AS subquery\n GROUP BY category",
+ "refId": "A",
+ "sql": {
+ "columns": [
+ {
+ "parameters": [],
+ "type": "function"
+ }
+ ],
+ "groupBy": [
+ {
+ "property": {
+ "type": "string"
+ },
+ "type": "groupBy"
+ }
+ ],
+ "limit": 50
+ },
+ "useBackend": false
+ }
+ ],
+ "title": "Usage by Category",
+ "transformations": [
+ {
+ "id": "groupBy",
+ "options": {
+ "fields": {
+ "Value": {
+ "aggregations": [
+ "sum"
+ ],
+ "operation": "aggregate"
+ },
+ "generation": {
+ "aggregations": [],
+ "operation": "groupby"
+ }
+ }
+ }
+ }
+ ],
+ "transparent": true,
+ "type": "piechart"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "description": "Displays the cost breakdown by provider (OpenAI, Cohere, Anthropic) for LLM requests, offering insights into financial deployment across different services.",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ }
+ },
+ "mappings": [],
+ "unit": "currencyUSD",
+ "unitScale": true
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 9,
+ "w": 6,
+ "x": 6,
+ "y": 12
+ },
+ "id": 16,
+ "options": {
+ "displayLabels": [
+ "name",
+ "value"
+ ],
+ "legend": {
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true,
+ "values": []
+ },
+ "pieType": "pie",
+ "reduceOptions": {
+ "calcs": [
+ "allValues"
+ ],
+ "fields": "",
+ "values": true
+ },
+ "tooltip": {
+ "mode": "single",
+ "sort": "asc"
+ }
+ },
+ "pluginVersion": "10.4.0-65875",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "disableTextWrap": false,
+ "editorMode": "code",
+ "expr": "doku_llm_usageCost{job=\"doku\", applicationName=~\"$Application\", environment=~\"$Environment\"}",
+ "format": "table",
+ "fullMetaSearch": false,
+ "includeNullMetadata": true,
+ "legendFormat": "__auto",
+ "range": true,
+ "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\nWHERE $__timeFilter(time)\nGROUP BY\n provider\nORDER BY\n total_cost DESC;",
+ "refId": "A",
+ "sql": {
+ "columns": [
+ {
+ "parameters": [],
+ "type": "function"
+ }
+ ],
+ "groupBy": [
+ {
+ "property": {
+ "type": "string"
+ },
+ "type": "groupBy"
+ }
+ ],
+ "limit": 50
+ },
+ "useBackend": false
+ }
+ ],
+ "title": "Usage cost by Provider",
+ "transformations": [
+ {
+ "id": "groupBy",
+ "options": {
+ "fields": {
+ "Value": {
+ "aggregations": [
+ "sum"
+ ],
+ "operation": "aggregate"
+ },
+ "generation": {
+ "aggregations": []
+ },
+ "platform": {
+ "aggregations": [],
+ "operation": "groupby"
+ }
+ }
+ }
+ }
+ ],
+ "transparent": true,
+ "type": "piechart"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "description": "This panel presents a pie chart detailing the distribution of expenses for LLM requests by various applications. It shows how budget allocations are consumed by different applications, enabling a deeper understanding of cost drivers and facilitating cost optimization efforts.",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ }
+ },
+ "mappings": [],
+ "unit": "currencyUSD",
+ "unitScale": true
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 9,
+ "w": 6,
+ "x": 12,
+ "y": 12
+ },
+ "id": 24,
+ "options": {
+ "displayLabels": [
+ "name",
+ "value"
+ ],
+ "legend": {
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true,
+ "values": []
+ },
+ "pieType": "pie",
+ "reduceOptions": {
+ "calcs": [
+ "allValues"
+ ],
+ "fields": "/.*/",
+ "values": true
+ },
+ "tooltip": {
+ "mode": "single",
+ "sort": "asc"
+ }
+ },
+ "pluginVersion": "10.4.0-65875",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "disableTextWrap": false,
+ "editorMode": "code",
+ "expr": "doku_llm_usageCost{job=\"doku\", applicationName=~\"$Application\", environment=~\"$Environment\"}",
+ "format": "table",
+ "fullMetaSearch": false,
+ "includeNullMetadata": true,
+ "legendFormat": "__auto",
+ "range": true,
+ "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\nWHERE $__timeFilter(time)\nGROUP BY\n provider\nORDER BY\n total_cost DESC;",
+ "refId": "A",
+ "sql": {
+ "columns": [
+ {
+ "parameters": [],
+ "type": "function"
+ }
+ ],
+ "groupBy": [
+ {
+ "property": {
+ "type": "string"
+ },
+ "type": "groupBy"
+ }
+ ],
+ "limit": 50
+ },
+ "useBackend": false
+ }
+ ],
+ "title": "Usage cost by Application",
+ "transformations": [
+ {
+ "id": "groupBy",
+ "options": {
+ "fields": {
+ "Value": {
+ "aggregations": [
+ "sum"
+ ],
+ "operation": "aggregate"
+ },
+ "applicationName": {
+ "aggregations": [],
+ "operation": "groupby"
+ }
+ }
+ }
+ }
+ ],
+ "transparent": true,
+ "type": "piechart"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "description": "Visualizes the allocation of LLM request expenses across different environments, such as development, staging, and production. This breakdown helps in tracking and managing costs with respect to operational environments.",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ }
+ },
+ "mappings": [],
+ "unit": "currencyUSD",
+ "unitScale": true
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 9,
+ "w": 6,
+ "x": 18,
+ "y": 12
+ },
+ "id": 25,
+ "options": {
+ "displayLabels": [
+ "name",
+ "value"
+ ],
+ "legend": {
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true,
+ "values": []
+ },
+ "pieType": "pie",
+ "reduceOptions": {
+ "calcs": [
+ "allValues"
+ ],
+ "fields": "/.*/",
+ "values": true
+ },
+ "tooltip": {
+ "mode": "single",
+ "sort": "asc"
+ }
+ },
+ "pluginVersion": "10.4.0-65875",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "disableTextWrap": false,
+ "editorMode": "code",
+ "expr": "doku_llm_usageCost{job=\"doku\", applicationName=~\"$Application\", environment=~\"$Environment\"}",
+ "format": "table",
+ "fullMetaSearch": false,
+ "includeNullMetadata": true,
+ "legendFormat": "__auto",
+ "range": true,
+ "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\nWHERE $__timeFilter(time)\nGROUP BY\n provider\nORDER BY\n total_cost DESC;",
+ "refId": "A",
+ "sql": {
+ "columns": [
+ {
+ "parameters": [],
+ "type": "function"
+ }
+ ],
+ "groupBy": [
+ {
+ "property": {
+ "type": "string"
+ },
+ "type": "groupBy"
+ }
+ ],
+ "limit": 50
+ },
+ "useBackend": false
+ }
+ ],
+ "title": "Usage cost by Environment",
+ "transformations": [
+ {
+ "id": "groupBy",
+ "options": {
+ "fields": {
+ "Value": {
+ "aggregations": [
+ "sum"
+ ],
+ "operation": "aggregate"
+ },
+ "applicationName": {
+ "aggregations": []
+ },
+ "environment": {
+ "aggregations": [],
+ "operation": "groupby"
+ }
+ }
+ }
+ }
+ ],
+ "transparent": true,
+ "type": "piechart"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "description": "This panel shows the average count of Prompt tokens used per LLM request",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "continuous-YlBl"
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ },
+ {
+ "color": "red",
+ "value": 5
+ }
+ ]
+ },
+ "unit": "none",
+ "unitScale": true
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 3,
+ "w": 6,
+ "x": 0,
+ "y": 21
+ },
+ "id": 9,
+ "options": {
+ "colorMode": "background",
+ "graphMode": "area",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showPercentChange": false,
+ "textMode": "auto",
+ "wideLayout": true
+ },
+ "pluginVersion": "10.4.0-65875",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "disableTextWrap": false,
+ "editorMode": "code",
+ "expr": "doku_llm_promptTokens{job=\"doku\", applicationName=~\"$Application\", environment=~\"$Environment\"}",
+ "format": "table",
+ "fullMetaSearch": false,
+ "includeNullMetadata": true,
+ "legendFormat": "__auto",
+ "range": true,
+ "rawQuery": true,
+ "rawSql": "SELECT AVG(prompttokens) FROM doku 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",
+ "useBackend": false
+ }
+ ],
+ "title": "Avg Prompt Tokens / Request",
+ "transformations": [
+ {
+ "id": "groupBy",
+ "options": {
+ "fields": {
+ "Value": {
+ "aggregations": [
+ "mean"
+ ],
+ "operation": "aggregate"
+ },
+ "job": {
+ "aggregations": [],
+ "operation": "groupby"
+ }
+ }
+ }
+ }
+ ],
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "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": "continuous-BlYlRd"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "series",
+ "axisGridShow": true,
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 50,
+ "gradientMode": "hue",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": 86400000,
+ "lineInterpolation": "smooth",
+ "lineStyle": {
+ "dash": [
+ 10,
+ 10
+ ],
+ "fill": "dash"
+ },
+ "lineWidth": 1,
+ "pointSize": 6,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "always",
+ "spanNulls": true,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "fieldMinMax": false,
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "none",
+ "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": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "disableTextWrap": false,
+ "editorMode": "code",
+ "expr": "avg(doku_llm_completionTokens{job=\"doku\", applicationName=~\"$Application\", environment=~\"$Environment\"})",
+ "format": "time_series",
+ "fullMetaSearch": false,
+ "includeNullMetadata": true,
+ "legendFormat": "Completion Tokens",
+ "range": true,
+ "rawQuery": true,
+ "rawSql": "SELECT prompttokens AS \"Prompt Tokens\", \"time\" AS \"time\", completiontokens AS \"Completion Tokens\", totaltokens AS \"Total Tokens\" FROM doku",
+ "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",
+ "useBackend": false
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "disableTextWrap": false,
+ "editorMode": "builder",
+ "expr": "avg(doku_llm_promptTokens)",
+ "format": "time_series",
+ "fullMetaSearch": false,
+ "hide": false,
+ "includeNullMetadata": true,
+ "legendFormat": "Prompt Tokens",
+ "range": true,
+ "rawQuery": true,
+ "rawSql": "SELECT prompttokens AS \"Prompt Tokens\", \"time\" AS \"time\", completiontokens AS \"Completion Tokens\", totaltokens AS \"Total Tokens\" FROM doku",
+ "refId": "B",
+ "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",
+ "useBackend": false
+ }
+ ],
+ "title": "Token usage overtime",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "description": "This panel shows the average count of Completion tokens used per LLM request",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "continuous-BlPu"
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "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": "10.4.0-65875",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "disableTextWrap": false,
+ "editorMode": "code",
+ "expr": "doku_llm_completionTokens{job=\"doku\", applicationName=~\"$Application\", environment=~\"$Environment\"}",
+ "format": "table",
+ "fullMetaSearch": false,
+ "includeNullMetadata": true,
+ "legendFormat": "__auto",
+ "range": true,
+ "rawQuery": true,
+ "rawSql": "SELECT AVG(completiontokens) FROM doku WHERE \n $__timeFilter(\"time\")",
+ "refId": "A",
+ "sql": {
+ "columns": [
+ {
+ "name": "AVG",
+ "parameters": [
+ {
+ "name": "completiontokens",
+ "type": "functionParameter"
+ }
+ ],
+ "type": "function"
+ }
+ ],
+ "groupBy": [
+ {
+ "property": {
+ "type": "string"
+ },
+ "type": "groupBy"
+ }
+ ],
+ "limit": 50
+ },
+ "table": "doku",
+ "useBackend": false
+ }
+ ],
+ "title": "Avg Completion Tokens / Request",
+ "transformations": [
+ {
+ "id": "groupBy",
+ "options": {
+ "fields": {
+ "Value": {
+ "aggregations": [
+ "mean"
+ ],
+ "operation": "aggregate"
+ },
+ "job": {
+ "aggregations": [],
+ "operation": "groupby"
+ }
+ }
+ }
+ }
+ ],
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "description": "Displays the frequency of model usage over time, identifying the most utilised models and showcasing usage trends across different periods",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "fixedColor": "purple",
+ "mode": "continuous-YlBl"
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "none",
+ "unitScale": true
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 6,
+ "w": 12,
+ "x": 0,
+ "y": 27
+ },
+ "id": 13,
+ "options": {
+ "displayMode": "lcd",
+ "maxVizHeight": 165,
+ "minVizHeight": 0,
+ "minVizWidth": 75,
+ "namePlacement": "left",
+ "orientation": "horizontal",
+ "reduceOptions": {
+ "calcs": [
+ "allValues"
+ ],
+ "fields": "",
+ "values": true
+ },
+ "showUnfilled": true,
+ "sizing": "auto",
+ "valueMode": "color"
+ },
+ "pluginVersion": "10.4.0-65875",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "disableTextWrap": false,
+ "editorMode": "code",
+ "expr": "topk(5,count by(model) (sum_over_time(doku_llm_requestDuration{job=\"doku\", applicationName=~\"$Application\", environment=~\"$Environment\"}[$__interval])))",
+ "format": "table",
+ "fullMetaSearch": false,
+ "includeNullMetadata": true,
+ "legendFormat": "__auto",
+ "range": true,
+ "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\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",
+ "useBackend": false
+ }
+ ],
+ "title": "Top models by usage",
+ "transformations": [
+ {
+ "id": "groupBy",
+ "options": {
+ "fields": {
+ "Value": {
+ "aggregations": [
+ "sum"
+ ],
+ "operation": "aggregate"
+ },
+ "model": {
+ "aggregations": [],
+ "operation": "groupby"
+ }
+ }
+ }
+ },
+ {
+ "id": "sortBy",
+ "options": {
+ "fields": {},
+ "sort": [
+ {
+ "desc": true,
+ "field": "Value (sum)"
+ }
+ ]
+ }
+ }
+ ],
+ "type": "bargauge"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "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": 23,
+ "gradientMode": "hue",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineStyle": {
+ "dash": [
+ 10,
+ 10
+ ],
+ "fill": "dash"
+ },
+ "lineWidth": 1,
+ "pointSize": 9,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "always",
+ "spanNulls": true,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "none",
+ "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": "10.4.0-65875",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "disableTextWrap": false,
+ "editorMode": "code",
+ "expr": "sum_over_time(doku_llm_totalTokens{job=\"doku\", applicationName=~\"$Application\", environment=~\"$Environment\"}[$__interval])",
+ "format": "time_series",
+ "fullMetaSearch": false,
+ "includeNullMetadata": true,
+ "legendFormat": "{{model}}",
+ "range": true,
+ "rawQuery": true,
+ "rawSql": "SELECT \n DATE_TRUNC('day', \"time\") AS \"time\",\n model,\n COUNT(*) AS \"Model:\"\nFROM \n doku\nWHERE \n $__timeFilter(\"time\")\nGROUP BY \n 1, model\nORDER BY \n \"time\" ASC, model;",
+ "refId": "A",
+ "sql": {
+ "columns": [
+ {
+ "parameters": [
+ {
+ "name": "model",
+ "type": "functionParameter"
+ }
+ ],
+ "type": "function"
+ }
+ ],
+ "groupBy": [
+ {
+ "property": {
+ "type": "string"
+ },
+ "type": "groupBy"
+ }
+ ],
+ "limit": 50
+ },
+ "table": "doku",
+ "useBackend": false
+ }
+ ],
+ "title": "Token usage by model",
+ "transformations": [],
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "loki",
+ "uid": "grafanacloud-logs"
+ },
+ "description": "Displays a log of all prompt messages sent to the LLM, providing insights into the inputs and interactions leading up to LLM responses.",
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 0,
+ "y": 33
+ },
+ "id": 26,
+ "options": {
+ "dedupStrategy": "none",
+ "enableLogDetails": true,
+ "prettifyLogMessage": true,
+ "showCommonLabels": false,
+ "showLabels": false,
+ "showTime": true,
+ "sortOrder": "Descending",
+ "wrapLogMessage": false
+ },
+ "pluginVersion": "10.4.0-65875",
+ "targets": [
+ {
+ "datasource": {
+ "type": "loki",
+ "uid": "grafanacloud-logs"
+ },
+ "editorMode": "code",
+ "expr": "{job=\"doku\", type=\"prompt\", applicationName=~\"$Application\", environment=~\"$Environment\"}",
+ "hide": false,
+ "queryType": "range",
+ "refId": "B"
+ }
+ ],
+ "title": "Prompts",
+ "transformations": [
+ {
+ "id": "extractFields",
+ "options": {
+ "format": "auto",
+ "source": "labels"
+ }
+ }
+ ],
+ "transparent": true,
+ "type": "logs"
+ },
+ {
+ "datasource": {
+ "type": "loki",
+ "uid": "grafanacloud-logs"
+ },
+ "description": "Displays a log of all responses from the LLM, offering a comprehensive view of how the model interprets prompts and the information it generates.",
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 12,
+ "y": 33
+ },
+ "id": 27,
+ "options": {
+ "dedupStrategy": "none",
+ "enableLogDetails": true,
+ "prettifyLogMessage": true,
+ "showCommonLabels": false,
+ "showLabels": false,
+ "showTime": true,
+ "sortOrder": "Descending",
+ "wrapLogMessage": true
+ },
+ "pluginVersion": "10.4.0-65875",
+ "targets": [
+ {
+ "datasource": {
+ "type": "loki",
+ "uid": "grafanacloud-logs"
+ },
+ "editorMode": "code",
+ "expr": "{job=\"doku\", type=\"response\", applicationName=~\"$Application\", environment=~\"$Environment\"}",
+ "hide": false,
+ "queryType": "range",
+ "refId": "B"
+ }
+ ],
+ "title": "Responses",
+ "transformations": [
+ {
+ "id": "extractFields",
+ "options": {
+ "format": "auto",
+ "source": "labels"
+ }
+ }
+ ],
+ "transparent": true,
+ "type": "logs"
+ }
+ ],
+ "refresh": "",
+ "schemaVersion": 39,
+ "tags": [
+ "Doku",
+ "OpenAI",
+ "Cohere",
+ "Anthropic"
+ ],
+ "templating": {
+ "list": [
+ {
+ "current": {
+ "selected": true,
+ "text": [
+ "All"
+ ],
+ "value": [
+ "$__all"
+ ]
+ },
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "definition": "label_values(applicationName)",
+ "hide": 0,
+ "includeAll": true,
+ "label": "Application",
+ "multi": true,
+ "name": "Application",
+ "options": [],
+ "query": {
+ "qryType": 1,
+ "query": "label_values(applicationName)",
+ "refId": "PrometheusVariableQueryEditor-VariableQuery"
+ },
+ "refresh": 1,
+ "regex": "",
+ "skipUrlSync": false,
+ "sort": 0,
+ "type": "query"
+ },
+ {
+ "current": {
+ "selected": true,
+ "text": [
+ "All"
+ ],
+ "value": [
+ "$__all"
+ ]
+ },
+ "datasource": {
+ "type": "prometheus",
+ "uid": "grafanacloud-prom"
+ },
+ "definition": "label_values(environment)",
+ "hide": 0,
+ "includeAll": true,
+ "label": "Environment",
+ "multi": true,
+ "name": "Environment",
+ "options": [],
+ "query": {
+ "qryType": 1,
+ "query": "label_values(environment)",
+ "refId": "PrometheusVariableQueryEditor-VariableQuery"
+ },
+ "refresh": 1,
+ "regex": "",
+ "skipUrlSync": false,
+ "sort": 0,
+ "type": "query"
+ }
+ ]
+ },
+ "time": {
+ "from": "now-24h",
+ "to": "now"
+ },
+ "timepicker": {},
+ "timezone": "",
+ "title": "Doku - LLM Monitoring",
+ "uid": "doku-llm-monitoring",
+ "version": 1,
+ "weekStart": ""
+ }
+ ```
+</Accordion>
+
diff --git a/docs/0.0.2/integrations/grafanaoss.mdx b/docs/0.0.2/integrations/grafanaoss.mdx
new file mode 100644
index 00000000..89470b28
--- /dev/null
+++ b/docs/0.0.2/integrations/grafanaoss.mdx
@@ -0,0 +1,1846 @@
+---
+title: 'Grafana OSS'
+description: 'Connect Doku to Grafana OSS'
+---
+
+<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 (`TimescaleDB`) 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 **Data Sources**.
+1. Click the **Add data source** button.
+1. In the search box, type "PostgreSQL" as `TimescaleDB` is an extension of PostgreSQL
+1.In the settings form, fill in the details to connect to your TimescaleDB/PostgreSQL database:
+ - **Name**: Enter the name for the datasource as `Doku`.
+ - **Host**: Provide the host address and port of your PostgreSQL server (e.g., `127.0.0.1`).
+ - **Database**: Enter the name of the database. Default database used by Doku is `postgres`.
+ - **TLS/SSL Setiing**: Enter the securtity to use for connection. Default used by Doku is `require`.
+ - **User**: The username for the database. Default user used by Doku is `admin`.
+ - **Password**: The password for the database. Default password used by Doku is `Doku`.
+1. Optionally customize the **Max open connections**, **Max idle connections**, and **Connection Max Lifetime**.
+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": 8,
+ "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-postgresql-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": "10.2.3",
+ "transparent": true,
+ "type": "text"
+ },
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${datasource}"
+ },
+ "gridPos": {
+ "h": 4,
+ "w": 2,
+ "x": 11,
+ "y": 0
+ },
+ "id": 2,
+ "options": {
+ "code": {
+ "language": "plaintext",
+ "showLineNumbers": false,
+ "showMiniMap": false
+ },
+ "content": "![Doku Logo](https://github.com/dokulabs/.github/blob/main/profile/assets/favicon.png?raw=true)",
+ "mode": "markdown"
+ },
+ "pluginVersion": "10.2.3",
+ "transparent": true,
+ "type": "text"
+ },
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${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": "10.2.3",
+ "transparent": true,
+ "type": "text"
+ },
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${datasource}"
+ },
+ "description": "This panel shows the total number of requests sent to Large Language Models (LLM) Platforms in the selected time interval.",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "fixedColor": "yellow",
+ "mode": "continuous-BlPu"
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ }
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 3,
+ "w": 6,
+ "x": 0,
+ "y": 4
+ },
+ "id": 3,
+ "options": {
+ "colorMode": "background",
+ "graphMode": "area",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "textMode": "auto",
+ "wideLayout": true
+ },
+ "pluginVersion": "10.2.3",
+ "targets": [
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${datasource}"
+ },
+ "editorMode": "code",
+ "format": "table",
+ "rawQuery": true,
+ "rawSql": "SELECT count(*) FROM DOKU_DATA\nWHERE $__timeFilter(time)",
+ "refId": "A",
+ "sql": {
+ "columns": [
+ {
+ "name": "COUNT",
+ "parameters": [
+ {
+ "name": "environment",
+ "type": "functionParameter"
+ }
+ ],
+ "type": "function"
+ }
+ ],
+ "groupBy": [
+ {
+ "property": {
+ "type": "string"
+ },
+ "type": "groupBy"
+ }
+ ],
+ "limit": 50
+ },
+ "table": "doku"
+ }
+ ],
+ "title": "Total Requests",
+ "transparent": true,
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${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"
+ },
+ "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
+ },
+ "textMode": "auto",
+ "wideLayout": true
+ },
+ "pluginVersion": "10.2.3",
+ "targets": [
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${datasource}"
+ },
+ "editorMode": "code",
+ "format": "table",
+ "rawQuery": true,
+ "rawSql": "SELECT AVG(requestduration) FROM DOKU_DATA\nWHERE $__timeFilter(time)",
+ "refId": "A",
+ "sql": {
+ "columns": [
+ {
+ "name": "AVG",
+ "parameters": [
+ {
+ "name": "requestduration",
+ "type": "functionParameter"
+ }
+ ],
+ "type": "function"
+ }
+ ],
+ "groupBy": [
+ {
+ "property": {
+ "type": "string"
+ },
+ "type": "groupBy"
+ }
+ ],
+ "limit": 50
+ },
+ "table": "doku"
+ }
+ ],
+ "title": "Avg Request Duration",
+ "transparent": true,
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${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"
+ },
+ "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
+ },
+ "textMode": "auto",
+ "wideLayout": true
+ },
+ "pluginVersion": "10.2.3",
+ "targets": [
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${datasource}"
+ },
+ "editorMode": "code",
+ "format": "table",
+ "rawQuery": true,
+ "rawSql": "SELECT AVG(totaltokens) FROM DOKU_DATA\nWHERE $__timeFilter(time)",
+ "refId": "A",
+ "sql": {
+ "columns": [
+ {
+ "name": "AVG",
+ "parameters": [
+ {
+ "name": "totaltokens",
+ "type": "functionParameter"
+ }
+ ],
+ "type": "function"
+ }
+ ],
+ "groupBy": [
+ {
+ "property": {
+ "type": "string"
+ },
+ "type": "groupBy"
+ }
+ ],
+ "limit": 50
+ },
+ "table": "doku"
+ }
+ ],
+ "title": "Avg Tokens per Request",
+ "transparent": true,
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${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"
+ },
+ "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
+ },
+ "textMode": "auto",
+ "wideLayout": true
+ },
+ "pluginVersion": "10.2.3",
+ "targets": [
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${datasource}"
+ },
+ "editorMode": "code",
+ "format": "table",
+ "rawQuery": true,
+ "rawSql": "SELECT AVG(usagecost) FROM DOKU_DATA \nWHERE $__timeFilter(time)",
+ "refId": "A",
+ "sql": {
+ "columns": [
+ {
+ "name": "AVG",
+ "parameters": [
+ {
+ "name": "usagecost",
+ "type": "functionParameter"
+ }
+ ],
+ "type": "function"
+ }
+ ],
+ "groupBy": [
+ {
+ "property": {
+ "type": "string"
+ },
+ "type": "groupBy"
+ }
+ ],
+ "limit": 50
+ },
+ "table": "doku"
+ }
+ ],
+ "title": "Avg Cost / Request",
+ "transparent": true,
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${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"
+ },
+ "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
+ },
+ "textMode": "auto",
+ "wideLayout": true
+ },
+ "pluginVersion": "10.2.3",
+ "targets": [
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${datasource}"
+ },
+ "editorMode": "code",
+ "format": "table",
+ "rawQuery": true,
+ "rawSql": "SELECT SUM(usagecost) FROM DOKU_DATA\nWHERE $__timeFilter(time)",
+ "refId": "A",
+ "sql": {
+ "columns": [
+ {
+ "name": "SUM",
+ "parameters": [
+ {
+ "name": "usagecost",
+ "type": "functionParameter"
+ }
+ ],
+ "type": "function"
+ }
+ ],
+ "groupBy": [
+ {
+ "property": {
+ "type": "string"
+ },
+ "type": "groupBy"
+ }
+ ],
+ "limit": 50
+ },
+ "table": "doku"
+ }
+ ],
+ "title": "Total Cost",
+ "transparent": true,
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${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"
+ },
+ "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-postgresql-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_DATA\nWHERE\n $__timeFilter(\"time\")\nGROUP BY \n DATE_TRUNC('day', \"time\")\nORDER BY \n \"time\";",
+ "refId": "A",
+ "sql": {
+ "columns": [
+ {
+ "alias": "\"Prompt Tokens\"",
+ "parameters": [
+ {
+ "name": "prompttokens",
+ "type": "functionParameter"
+ }
+ ],
+ "type": "function"
+ },
+ {
+ "alias": "\"time\"",
+ "parameters": [
+ {
+ "name": "\"time\"",
+ "type": "functionParameter"
+ }
+ ],
+ "type": "function"
+ },
+ {
+ "alias": "\"Completion Tokens\"",
+ "parameters": [
+ {
+ "name": "completiontokens",
+ "type": "functionParameter"
+ }
+ ],
+ "type": "function"
+ },
+ {
+ "alias": "\"Total Tokens\"",
+ "parameters": [
+ {
+ "name": "totaltokens",
+ "type": "functionParameter"
+ }
+ ],
+ "type": "function"
+ }
+ ],
+ "groupBy": [
+ {
+ "property": {
+ "type": "string"
+ },
+ "type": "groupBy"
+ }
+ ],
+ "limit": 50
+ },
+ "table": "doku"
+ }
+ ],
+ "title": "Total Requests / Day",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${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": []
+ },
+ "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$/",
+ "values": true
+ },
+ "tooltip": {
+ "mode": "single",
+ "sort": "asc"
+ }
+ },
+ "pluginVersion": "10.2.3",
+ "targets": [
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${datasource}"
+ },
+ "editorMode": "code",
+ "format": "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.completions%' 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_DATA\n WHERE $__timeFilter(time)\n ) AS subquery\n GROUP BY category",
+ "refId": "A",
+ "sql": {
+ "columns": [
+ {
+ "parameters": [],
+ "type": "function"
+ }
+ ],
+ "groupBy": [
+ {
+ "property": {
+ "type": "string"
+ },
+ "type": "groupBy"
+ }
+ ],
+ "limit": 50
+ }
+ }
+ ],
+ "title": "Usage by Category",
+ "transparent": true,
+ "type": "piechart"
+ },
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${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"
+ },
+ "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-postgresql-datasource",
+ "uid": "${datasource}"
+ },
+ "editorMode": "code",
+ "format": "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_DATA\nWHERE $__timeFilter(time)\nGROUP BY\n provider\nORDER BY\n total_cost DESC;",
+ "refId": "A",
+ "sql": {
+ "columns": [
+ {
+ "parameters": [],
+ "type": "function"
+ }
+ ],
+ "groupBy": [
+ {
+ "property": {
+ "type": "string"
+ },
+ "type": "groupBy"
+ }
+ ],
+ "limit": 50
+ }
+ }
+ ],
+ "title": "Usage cost by Provider",
+ "transparent": true,
+ "type": "piechart"
+ },
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${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"
+ },
+ "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-postgresql-datasource",
+ "uid": "${datasource}"
+ },
+ "editorMode": "code",
+ "format": "table",
+ "rawQuery": true,
+ "rawSql": " SELECT\n applicationName,\n sum(usageCost) AS \"usageCost\"\n FROM\n DOKU_DATA\n WHERE $__timeFilter(time)\n GROUP BY\n applicationName\n ORDER BY\n \"usageCost\" DESC",
+ "refId": "A",
+ "sql": {
+ "columns": [
+ {
+ "parameters": [],
+ "type": "function"
+ }
+ ],
+ "groupBy": [
+ {
+ "property": {
+ "type": "string"
+ },
+ "type": "groupBy"
+ }
+ ],
+ "limit": 50
+ }
+ }
+ ],
+ "title": "Usage cost by Application",
+ "transparent": true,
+ "type": "piechart"
+ },
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${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"
+ },
+ "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-postgresql-datasource",
+ "uid": "${datasource}"
+ },
+ "editorMode": "code",
+ "format": "table",
+ "rawQuery": true,
+ "rawSql": " SELECT\n environment,\n sum(usageCost) AS \"usageCost\"\n FROM\n DOKU_DATA\n WHERE $__timeFilter(time)\n GROUP BY\n environment\n ORDER BY\n \"usageCost\" DESC",
+ "refId": "A",
+ "sql": {
+ "columns": [
+ {
+ "parameters": [],
+ "type": "function"
+ }
+ ],
+ "groupBy": [
+ {
+ "property": {
+ "type": "string"
+ },
+ "type": "groupBy"
+ }
+ ],
+ "limit": 50
+ }
+ }
+ ],
+ "title": "Usage cost by Environment",
+ "transparent": true,
+ "type": "piechart"
+ },
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${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"
+ },
+ {
+ "color": "red",
+ "value": 5
+ }
+ ]
+ },
+ "unit": "none"
+ },
+ "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
+ },
+ "textMode": "auto",
+ "wideLayout": true
+ },
+ "pluginVersion": "10.2.3",
+ "targets": [
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${datasource}"
+ },
+ "editorMode": "code",
+ "format": "table",
+ "rawQuery": true,
+ "rawSql": "SELECT AVG(prompttokens) FROM DOKU_DATA WHERE \n $__timeFilter(\"time\")",
+ "refId": "A",
+ "sql": {
+ "columns": [
+ {
+ "name": "AVG",
+ "parameters": [
+ {
+ "name": "prompttokens",
+ "type": "functionParameter"
+ }
+ ],
+ "type": "function"
+ }
+ ],
+ "groupBy": [
+ {
+ "property": {
+ "type": "string"
+ },
+ "type": "groupBy"
+ }
+ ],
+ "limit": 50
+ },
+ "table": "doku"
+ }
+ ],
+ "title": "Avg Prompt Tokens / Request",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${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"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ }
+ },
+ "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-postgresql-datasource",
+ "uid": "${datasource}"
+ },
+ "editorMode": "code",
+ "format": "time_series",
+ "rawQuery": true,
+ "rawSql": "SELECT prompttokens AS \"Prompt Tokens\", \"time\" AS \"time\", completiontokens AS \"Completion Tokens\", totaltokens AS \"Total Tokens\" FROM DOKU_DATA",
+ "refId": "A",
+ "sql": {
+ "columns": [
+ {
+ "alias": "\"Prompt Tokens\"",
+ "parameters": [
+ {
+ "name": "prompttokens",
+ "type": "functionParameter"
+ }
+ ],
+ "type": "function"
+ },
+ {
+ "alias": "\"time\"",
+ "parameters": [
+ {
+ "name": "\"time\"",
+ "type": "functionParameter"
+ }
+ ],
+ "type": "function"
+ },
+ {
+ "alias": "\"Completion Tokens\"",
+ "parameters": [
+ {
+ "name": "completiontokens",
+ "type": "functionParameter"
+ }
+ ],
+ "type": "function"
+ },
+ {
+ "alias": "\"Total Tokens\"",
+ "parameters": [
+ {
+ "name": "totaltokens",
+ "type": "functionParameter"
+ }
+ ],
+ "type": "function"
+ }
+ ],
+ "groupBy": [
+ {
+ "property": {
+ "type": "string"
+ },
+ "type": "groupBy"
+ }
+ ],
+ "limit": 50
+ },
+ "table": "doku"
+ }
+ ],
+ "title": "Token usage",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${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"
+ },
+ {
+ "color": "red",
+ "value": 5
+ }
+ ]
+ },
+ "unit": "none"
+ },
+ "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
+ },
+ "textMode": "auto",
+ "wideLayout": true
+ },
+ "pluginVersion": "10.2.3",
+ "targets": [
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${datasource}"
+ },
+ "editorMode": "code",
+ "format": "table",
+ "rawQuery": true,
+ "rawSql": "SELECT AVG(completiontokens) FROM DOKU_DATA WHERE \n $__timeFilter(\"time\")",
+ "refId": "A",
+ "sql": {
+ "columns": [
+ {
+ "name": "AVG",
+ "parameters": [
+ {
+ "name": "completiontokens",
+ "type": "functionParameter"
+ }
+ ],
+ "type": "function"
+ }
+ ],
+ "groupBy": [
+ {
+ "property": {
+ "type": "string"
+ },
+ "type": "groupBy"
+ }
+ ],
+ "limit": 50
+ },
+ "table": "doku"
+ }
+ ],
+ "title": "Avg Completion Tokens / Request",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${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"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "none"
+ },
+ "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$/",
+ "values": true
+ },
+ "showUnfilled": true,
+ "sizing": "manual",
+ "valueMode": "text"
+ },
+ "pluginVersion": "10.2.3",
+ "targets": [
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${datasource}"
+ },
+ "editorMode": "code",
+ "format": "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_DATA\n WHERE $__timeFilter(time)\n GROUP BY \n model\n ORDER BY \n percentage_usage DESC\n ) sub\nLIMIT 5;",
+ "refId": "A",
+ "sql": {
+ "columns": [
+ {
+ "parameters": [
+ {
+ "name": "model",
+ "type": "functionParameter"
+ }
+ ],
+ "type": "function"
+ }
+ ],
+ "groupBy": [
+ {
+ "property": {
+ "type": "string"
+ },
+ "type": "groupBy"
+ }
+ ],
+ "limit": 50
+ },
+ "table": "doku"
+ }
+ ],
+ "title": "Top models by usage",
+ "type": "bargauge"
+ },
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${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"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ }
+ },
+ "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-postgresql-datasource",
+ "uid": "${datasource}"
+ },
+ "editorMode": "code",
+ "format": "time_series",
+ "rawQuery": true,
+ "rawSql": "SELECT \n DATE_TRUNC('day', \"time\") AS \"time\",\n model,\n COUNT(*) AS \"Model:\"\nFROM \n DOKU_DATA\nWHERE \n $__timeFilter(\"time\")\nGROUP BY \n 1, model\nORDER BY \n \"time\" ASC, model;",
+ "refId": "A",
+ "sql": {
+ "columns": [
+ {
+ "parameters": [
+ {
+ "name": "model",
+ "type": "functionParameter"
+ }
+ ],
+ "type": "function"
+ }
+ ],
+ "groupBy": [
+ {
+ "property": {
+ "type": "string"
+ },
+ "type": "groupBy"
+ }
+ ],
+ "limit": 50
+ },
+ "table": "doku"
+ }
+ ],
+ "title": "Model usage by day",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${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"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "currencyUSD"
+ },
+ "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": "10.2.3",
+ "targets": [
+ {
+ "datasource": {
+ "type": "grafana-postgresql-datasource",
+ "uid": "${datasource}"
+ },
+ "editorMode": "code",
+ "format": "table",
+ "rawQuery": true,
+ "rawSql": "SELECT \"time\", applicationName, model, prompt, response, usageCost FROM DOKU_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": true,
+ "text": "grafana-postgresql-datasource",
+ "value": "dbd38750-cf8a-4f35-a031-af943c441f1d"
+ },
+ "hide": 0,
+ "includeAll": false,
+ "label": "Datasource",
+ "multi": false,
+ "name": "datasource",
+ "options": [],
+ "query": "grafana-postgresql-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": 1,
+ "weekStart": ""
+ }
+ ```
+</Accordion>
+
diff --git a/docs/0.0.2/integrations/intro.mdx b/docs/0.0.2/integrations/intro.mdx
new file mode 100644
index 00000000..5d27c61a
--- /dev/null
+++ b/docs/0.0.2/integrations/intro.mdx
@@ -0,0 +1,21 @@
+---
+title: 'Introduction'
+description: 'Connect to your existing Observablity Platform'
+---
+
+Doku streamlines the observability experience by delivering processed LLM data right to the observability platform you are already familiar with. We recognize how crucial it is for developers to aggregate all application-related data, encompassing LLM usage metrics, into a single source of truth.
+
+This integration allows you to visualize and assess your entire application landscape in one integrated Observability platform, thereby refining your monitoring approaches and sharpening your decision-making.
+
+Below is a list of observability platforms that work seamlessly with Doku, allowing for integrated and expanded insights.
+
+<CardGroup cols={2}>
+ <Card title="Grafana OSS" href="/0.0.2/integrations/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>
+ <Card title="Grafana Cloud" href="/0.0.2/integrations/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>
+ <Card title="DataDog" href="/0.0.2/integrations/datadog" icon={<svg role="img" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Datadog</title><path d="M19.57 17.04l-1.997-1.316-1.665 2.782-1.937-.567-1.706 2.604.087.82 9.274-1.71-.538-5.794zm-8.649-2.498l1.488-.204c.241.108.409.15.697.223.45.117.97.23 1.741-.16.18-.088.553-.43.704-.625l6.096-1.106.622 7.527-10.444 1.882zm11.325-2.712l-.602.115L20.488 0 .789 2.285l2.427 19.693 2.306-.334c-.184-.263-.471-.581-.96-.989-.68-.564-.44-1.522-.039-2.127.53-1.022 3.26-2.322 3.106-3.956-.056-.594-.15-1.368-.702-1.898-.02.22.017.432.017.432s-.227-.289-.34-.683c-.112-.15-.2-.199-.319-.4-.085.233-.073.503-.073.503s-.186-.437-.216-.807c-.11.166-.137.48-.137.48s-.241-.69-.186-1.062c-.11-.323-.436-.965-.343-2.424.6.421 1.924.321 2.44-.439.171-.251.288-.939-.086-2.293-.24-.868-.835-2.16-1.066-2.651l-.028.02c.122.395.374 1.223.47 1.625.293 1.218.372 1.642.234 2.204-.116.488-.397.808-1.107 1.165-.71.358-1.653-.514-1.713-.562-.69-.55-1.224-1.447-1.284-1.883-.062-.477.275-.763.445-1.153-.243.07-.514.192-.514.192s.323-.334.722-.624c.165-.109.262-.178.436-.323a9.762 9.762 0 0 0-.456.003s.42-.227.855-.392c-.318-.014-.623-.003-.623-.003s.937-.419 1.678-.727c.509-.208 1.006-.147 1.286.257.367.53.752.817 1.569.996.501-.223.653-.337 1.284-.509.554-.61.99-.688.99-.688s-.216.198-.274.51c.314-.249.66-.455.66-.455s-.134.164-.259.426l.03.043c.366-.22.797-.394.797-.394s-.123.156-.268.358c.277-.002.838.012 1.056.037 1.285.028 1.552-1.374 2.045-1.55.618-.22.894-.353 1.947.68.903.888 1.609 2.477 1.259 2.833-.294.295-.874-.115-1.516-.916a3.466 3.466 0 0 1-.716-1.562 1.533 1.533 0 0 0-.497-.85s.23.51.23.96c0 .246.03 1.165.424 1.68-.039.076-.057.374-.1.43-.458-.554-1.443-.95-1.604-1.067.544.445 1.793 1.468 2.273 2.449.453.927.186 1.777.416 1.997.065.063.976 1.197 1.15 1.767.306.994.019 2.038-.381 2.685l-1.117.174c-.163-.045-.273-.068-.42-.153.08-.143.241-.5.243-.572l-.063-.111c-.348.492-.93.97-1.414 1.245-.633.359-1.363.304-1.838.156-1.348-.415-2.623-1.327-2.93-1.566 0 0-.01.191.048.234.34.383 1.119 1.077 1.872 1.56l-1.605.177.759 5.908c-.337.048-.39.071-.757.124-.325-1.147-.946-1.895-1.624-2.332-.599-.384-1.424-.47-2.214-.314l-.05.059a2.851 2.851 0 0 1 1.863.444c.654.413 1.181 1.481 1.375 2.124.248.822.42 1.7-.248 2.632-.476.662-1.864 1.028-2.986.237.3.481.705.876 1.25.95.809.11 1.577-.03 2.106-.574.452-.464.69-1.434.628-2.456l.714-.104.258 1.834 11.827-1.424zM15.05 6.848c-.034.075-.085.125-.007.37l.004.014.013.032.032.073c.14.287.295.558.552.696.067-.011.136-.019.207-.023.242-.01.395.028.492.08.009-.048.01-.119.005-.222-.018-.364.072-.982-.626-1.308-.264-.122-.634-.084-.757.068a.302.302 0 0 1 .058.013c.186.066.06.13.027.207m1.958 3.392c-.092-.05-.52-.03-.821.005-.574.068-1.193.267-1.328.372-.247.191-.135.523.047.66.511.382.96.638 1.432.575.29-.038.546-.497.728-.914.124-.288.124-.598-.058-.698m-5.077-2.942c.162-.154-.805-.355-1.556.156-.554.378-.571 1.187-.041 1.646.053.046.096.078.137.104a4.77 4.77 0 0 1 1.396-.412c.113-.125.243-.345.21-.745-.044-.542-.455-.456-.146-.749"/></svg>}>
+ </Card>
+ <Card title="New Relic" href="/0.0.2/integrations/new-relic" icon={<svg role="img" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>New Relic</title><path d="M8.0015 14.3091v7.384L12.0008 24V12.0008L1.6078 5.9996v4.6167ZM12.0008 0 2.8232 5.2976 6.8209 7.606l5.1799-2.9893 6.3936 3.6913v7.384l-5.1783 2.9908v4.6167l9.176-5.2991V5.9996Z"/></svg>}>
+ </Card>
+</CardGroup>
\ No newline at end of file
diff --git a/docs/0.0.2/integrations/new-relic.mdx b/docs/0.0.2/integrations/new-relic.mdx
new file mode 100644
index 00000000..391c8b9c
--- /dev/null
+++ b/docs/0.0.2/integrations/new-relic.mdx
@@ -0,0 +1,17 @@
+---
+title: 'New Relic'
+description: 'Connect Doku to New Relic'
+---
+
+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/)
+
+Add the following to your doku configuration file(`doku.yml`).
+
+```yaml doku.yml
+observabilityPlatform:
+ enabled: true # Enable or Disable the Observability Platform, Example: true
+ newRelic:
+ metricsUrl: <your-new-relic-metrics-url> # URL to the New Relic Metric API
+ logsUrl: <your-new-relic-logs-url> # URL to the New Relic Log API
+ key: <your-new-relic-api-key> # Ingest API Key of the New Relic Account
+```
\ No newline at end of file
diff --git a/docs/0.0.2/introduction.mdx b/docs/0.0.2/introduction.mdx
new file mode 100644
index 00000000..2814e6c6
--- /dev/null
+++ b/docs/0.0.2/introduction.mdx
@@ -0,0 +1,111 @@
+---
+title: What is Doku?
+description: 'Monitor and evalute your LLM Applications'
+---
+
+Doku is an open-source observability tool engineered for Large Language Models (LLMs). Designed for ease of integration into existing LLM applications, Doku offers unparalleled insights into usage, performance, and overhead—allowing you to analyze, optimize, and scale your AI applications and LLM usage effectively.
+
+Whether you're working with OpenAI, Cohere, or Anthropic, It tracks all your LLM requests transparently and conveys the insights needed to make data-driven decisions. From monitoring usage and understanding latencies to managing costs and collaborating effortlessly, Doku grants you the lens to view your models in high definition.
+
+## How it works
+
+<Frame>
+ <img src="https://raw.githubusercontent.com/dokulabs/.github/main/profile/assets/banner.gif" />
+</Frame>
+### Application Integration with Two Lines of Code
+Start by incorporating the DokuMetry SDK into your application. With SDKs tailored for both Python and NodeJS, Doku fits into your tech stack with minimal changes. Just a **two lines** of code is all it takes to begin:
+
+For Python and NodeJS projects, just import the DokuMetry SDK and initialize it as follows:
+ <CodeGroup>
+ ```python python
+ import dokumetry
+ dokumetry.init(llm=openai, doku_url="YOUR_DOKU_URL", api_key="YOUR_DOKU_TOKEN")
+ ```
+
+ ```javascript NodeJS
+ import DokuMetry from 'dokumetry';
+ DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", apiKey: "YOUR_DOKU_TOKEN"})
+ ```
+ </CodeGroup>
+Find detailed instructions at the [DokuMetry SDK Documentation](/0.0.2/dokumetry/introduction).
+
+### The Doku Ingester: Your Data Processing Workhorse
+
+Upon SDK setup, data from your LLM operations is automatically collected. The DokuMetry SDKs transmit this usage data over HTTP in the background to the [Doku Ingester](https://github.com/dokulabs/doku/tree/main/src/ingester#readme).
+
+The ingester is the core engine where the magic happens:
+- **Data Collection**: Effortlessly captures live data from your LLM interactions without complicating your existing codebase.
+- **Cost Analysis**: Enriches your data with cost considerations, providing a financial perspective to your analytics.
+- **Secure Storage**: All processed information is securely stored in TimescaleDB, providing you with a scalable, time-series database that can handle large volumes of observability data.
+
+You have the choice to set up a fresh TimescaleDB instance or connect Doku to your existing one. Whichever path you choose, your data resides within your control, reinforcing your data security and operational compliance.
+
+## Features
+Leveraging Doku, you can get:
+
+- **In-depth LLM Monitoring**: Track every request to LLM platforms like OpenAI with precision, ensuring comprehensive visibility over your model's interactions.
+- **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.
+- **Connect to Observability Platforms**: Export LLM Observablity data and insights from Doku to popular observability platforms such as Grafana Cloud or Datadog.
+- **Team-centric Workflow**: Enhance team collaboration with seamless data sharing capabilities, creating an integrated environment for observability-driven teamwork.
+
+## Supported LLM Platforms
+<CardGroup cols={3}>
+ <Card
+ title="OpenAI"
+ icon={
+ <svg role="img" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg">
+ <title>OpenAI</title>
+ <path d="M22.2819 9.8211a5.9847 5.9847 0 0 0-.5157-4.9108 6.0462 6.0462 0 0 0-6.5098-2.9A6.0651 6.0651 0 0 0 4.9807 4.1818a5.9847 5.9847 0 0 0-3.9977 2.9 6.0462 6.0462 0 0 0 .7427 7.0966 5.98 5.98 0 0 0 .511 4.9107 6.051 6.051 0 0 0 6.5146 2.9001A5.9847 5.9847 0 0 0 13.2599 24a6.0557 6.0557 0 0 0 5.7718-4.2058 5.9894 5.9894 0 0 0 3.9977-2.9001 6.0557 6.0557 0 0 0-.7475-7.0729zm-9.022 12.6081a4.4755 4.4755 0 0 1-2.8764-1.0408l.1419-.0804 4.7783-2.7582a.7948.7948 0 0 0 .3927-.6813v-6.7369l2.02 1.1686a.071.071 0 0 1 .038.052v5.5826a4.504 4.504 0 0 1-4.4945 4.4944zm-9.6607-4.1254a4.4708 4.4708 0 0 1-.5346-3.0137l.142.0852 4.783 2.7582a.7712.7712 0 0 0 .7806 0l5.8428-3.3685v2.3324a.0804.0804 0 0 1-.0332.0615L9.74 19.9502a4.4992 4.4992 0 0 1-6.1408-1.6464zM2.3408 7.8956a4.485 4.485 0 0 1 2.3655-1.9728V11.6a.7664.7664 0 0 0 .3879.6765l5.8144 3.3543-2.0201 1.1685a.0757.0757 0 0 1-.071 0l-4.8303-2.7865A4.504 4.504 0 0 1 2.3408 7.872zm16.5963 3.8558L13.1038 8.364 15.1192 7.2a.0757.0757 0 0 1 .071 0l4.8303 2.7913a4.4944 4.4944 0 0 1-.6765 8.1042v-5.6772a.79.79 0 0 0-.407-.667zm2.0107-3.0231l-.142-.0852-4.7735-2.7818a.7759.7759 0 0 0-.7854 0L9.409 9.2297V6.8974a.0662.0662 0 0 1 .0284-.0615l4.8303-2.7866a4.4992 4.4992 0 0 1 6.6802 4.66zM8.3065 12.863l-2.02-1.1638a.0804.0804 0 0 1-.038-.0567V6.0742a4.4992 4.4992 0 0 1 7.3757-3.4537l-.142.0805L8.704 5.459a.7948.7948 0 0 0-.3927.6813zm1.0976-2.3654l2.602-1.4998 2.6069 1.4998v2.9994l-2.5974 1.4997-2.6067-1.4997Z" />
+ </svg>
+ }
+ iconType="duotone"
+ >
+ </Card>
+ <Card
+ title="Cohere"
+ icon={
+ <svg role="image" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 75 75">
+ <g>
+ <g>
+ <g>
+ <path d="M24.3,44.7c2,0,6-0.1,11.6-2.4c6.5-2.7,19.3-7.5,28.6-12.5c6.5-3.5,9.3-8.1,9.3-14.3C73.8,7,66.9,0,58.3,0
+ h-36C10,0,0,10,0,22.3S9.4,44.7,24.3,44.7z">
+ </path>
+ <path d="M30.4,60c0-6,3.6-11.5,9.2-13.8l11.3-4.7C62.4,36.8,75,45.2,75,57.6C75,67.2,67.2,75,57.6,75l-12.3,0
+ C37.1,75,30.4,68.3,30.4,60z">
+ </path>
+ <path d="M12.9,47.6L12.9,47.6C5.8,47.6,0,53.4,0,60.5v1.7C0,69.2,5.8,75,12.9,75h0c7.1,0,12.9-5.8,12.9-12.9v-1.7
+ C25.7,53.4,20,47.6,12.9,47.6z">
+ </path>
+ </g>
+ </g>
+ </g>
+ </svg>
+ }
+ iconType="duotone"
+ >
+ </Card>
+ <Card
+ title="Anthropic"
+ icon={
+ <svg viewBox="0 0 256 176" 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>
+ <path d="M66.1828124,106.221191 C66.1828124,106.221191 90.1624677,44.4471185 90.1624677,44.4471185 C90.1624677,44.4471185 114.142128,106.221191 114.142128,106.221191 C114.142128,106.221191 66.1828124,106.221191 66.1828124,106.221191 C66.1828124,106.221191 66.1828124,106.221191 66.1828124,106.221191 Z M70.0705318,0 C70.0705318,0 0,175.780074 0,175.780074 C0,175.780074 39.179211,175.780074 39.179211,175.780074 C39.179211,175.780074 53.5097704,138.86606 53.5097704,138.86606 C53.5097704,138.86606 126.817544,138.86606 126.817544,138.86606 C126.817544,138.86606 141.145724,175.780074 141.145724,175.780074 C141.145724,175.780074 180.324935,175.780074 180.324935,175.780074 C180.324935,175.780074 110.254409,0 110.254409,0 C110.254409,0 70.0705318,0 70.0705318,0 C70.0705318,0 70.0705318,0 70.0705318,0 Z"></path>
+ </svg>
+ }
+ iconType="duotone"
+ >
+ </Card>
+</CardGroup>
+
+## Getting Started
+Select from the following guides to learn more about how to use Doku:
+
+<CardGroup cols={2}>
+<Card title="Quickstart" href="/0.0.2/quickstart" icon='bolt'>
+Get Started with monitoring your LLM Applications in 3 simple steps
+</Card>
+<Card title="Integrations" href="/0.0.2/integrations/intro" icon='connectdevelop'>
+Connect to your existing Observablity Platform
+</Card>
+</CardGroup>
\ No newline at end of file
diff --git a/docs/0.0.2/quickstart.mdx b/docs/0.0.2/quickstart.mdx
new file mode 100644
index 00000000..5be690d1
--- /dev/null
+++ b/docs/0.0.2/quickstart.mdx
@@ -0,0 +1,150 @@
+---
+title: 'Quickstart'
+description: 'Quickly start **monitoring** your **LLM Applications** in just **two lines** of code'
+icon: 'bolt'
+---
+
+This guide will walk you through setting up your monitoring system 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.
+
+## Prerequistes
+- Ensure you have access to a **Kubernetes Cluster**. You can quickly spin up a Kubernetes Cluster using [Kind](https://github.com/kubernetes-sigs/kind?tab=readme-ov-file#installation-and-usage)
+
+## Get Started
+
+<Steps>
+ <Step title="Install Doku in a Kubernetes Cluster">
+ <Steps>
+ <Step title="Helm Repo Setup">
+ ```shell shell
+ helm repo add dokulabs https://dokulabs.github.io/helm/
+ helm repo update
+ ```
+ </Step>
+ <Step title="Installing the Helm Chart">
+ ```shell shell
+ helm install doku dokulabs/doku
+ ```
+ </Step>
+ </Steps>
+ </Step>
+ <Step title="Generate an API Key">
+ With Doku running, the next step is to [generate an API key](/0.0.2/api-reference/endpoint/api-keys/create) for secure communication between your applications and Doku.
+
+ To generate your first API key, you can use the following command:
+
+ ```shell shell
+ curl --request POST \
+ --url https://<your-doku-url>/api/keys \
+ --header 'Authorization: ""' \
+ --header 'Content-Type: application/json' \
+ --data '{
+ "name": "Admin"
+ }'
+ ```
+
+ Make sure to store the returned API key securely, as it's necessary for authorizing future API calls with Doku.
+
+ <Info>
+ During your initial request to generate an API key, you can leave the Authorization header empty (i.e., `""`). For subsequent requests, you will need to supply the generated API key.
+ </Info>
+
+ </Step>
+ <Step title="Instrument your code">
+ Choose the appropriate SDK for your application's programming language and follow the steps to integrate monitoring with just a couple of 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, replacing `YOUR_DOKU_URL` and `YOUR_DOKU_TOKEN` with corresponding values.
+
+ ```python
+ import dokumetry
+
+ dokumetry.init(llm=client, doku_url="YOUR_DOKU_URL", 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 URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+ dokumetry.init(llm=client, doku_url="YOUR_DOKU_URL", 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) or the [DokuMetry Docs](/0.0.2/dokumetry/python/introduction) 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, replacing `YOUR_DOKU_URL` and `YOUR_DOKU_TOKEN` with corresponding values.
+ ```javascript
+ import DokuMetry from 'dokumetry';
+
+ DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", 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 URL and API key and this will make sure that all OpenAI calls are automatically tracked.
+ DokuMetry.init({llm: openai, dokuUrl: "YOUR_DOKU_URL", 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) or the [DokuMetry Docs](/0.0.2/dokumetry/node/introduction) for more advanced configurations and use cases.
+ </Step>
+ </Steps>
+ </Tab>
+ </Tabs>
+ </Step>
+</Steps>
+
+## (Optional) Export Data
+<Card title="Integrations" href="/0.0.2/integrations/intro" icon='connectdevelop'>
+Connect to your existing Observablity Platform
+</Card>
+
+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).
\ No newline at end of file
diff --git a/docs/mint.json b/docs/mint.json
index 99dfff44..7b0f6e19 100644
--- a/docs/mint.json
+++ b/docs/mint.json
@@ -1,6 +1,6 @@
{
"$schema": "https://mintlify.com/schema.json",
- "versions": ["0.0.1"],
+ "versions": ["0.0.2", "0.0.1"],
"name": "Doku",
"logo": {
"dark": "https://github.com/dokulabs/.github/blob/main/profile/assets/dark-bg-with-text-logo.jpg?raw=true",
@@ -45,7 +45,138 @@
{
"group": "Get Started",
"pages": [
- "0.0.1/introduction",
+ "0.0.2/introduction",
+ "0.0.2/quickstart",
+ "0.0.2/installation",
+ "0.0.2/configuration"
+ ],
+ "version": "0.0.2"
+ },
+ {
+ "group": "DokuMetry",
+ "version": "0.0.2",
+ "pages": [
+ "0.0.2/dokumetry/introduction",
+ {
+ "group": "Python",
+ "version": "0.0.2",
+ "icon": "python",
+ "pages": [
+ "0.0.2/dokumetry/python/introduction",
+ {
+ "group": "Examples",
+ "version": "0.0.2",
+ "pages": [
+ {
+ "group": "OpenAI",
+ "version": "0.0.2",
+ "pages": [
+ "0.0.2/dokumetry/python/examples/openai/chat",
+ "0.0.2/dokumetry/python/examples/openai/image",
+ "0.0.2/dokumetry/python/examples/openai/embeddings",
+ "0.0.2/dokumetry/python/examples/openai/audio",
+ "0.0.2/dokumetry/python/examples/openai/fine-tuning",
+ "0.0.2/dokumetry/python/examples/openai/completions"
+ ]
+ },
+ {
+ "group": "Cohere",
+ "version": "0.0.2",
+ "pages": [
+ "0.0.2/dokumetry/python/examples/cohere/chat",
+ "0.0.2/dokumetry/python/examples/cohere/generate",
+ "0.0.2/dokumetry/python/examples/cohere/co-summarize",
+ "0.0.2/dokumetry/python/examples/cohere/embed"
+ ]
+ },
+ {
+ "group": "Anthropic",
+ "version": "0.0.2",
+ "pages": [
+ "0.0.2/dokumetry/python/examples/anthropic/anthropic-completions"
+ ]
+ }
+ ]
+ }
+ ]
+ },
+ {
+ "group": "NodeJS",
+ "version": "0.0.2",
+ "icon": "node-js",
+ "pages": [
+ "0.0.2/dokumetry/node/introduction",
+ {
+ "group": "Examples",
+ "version": "0.0.2",
+ "pages": [
+ {
+ "group": "OpenAI",
+ "version": "0.0.2",
+ "pages": [
+ "0.0.2/dokumetry/node/examples/openai/chat",
+ "0.0.2/dokumetry/node/examples/openai/image",
+ "0.0.2/dokumetry/node/examples/openai/embeddings",
+ "0.0.2/dokumetry/node/examples/openai/audio",
+ "0.0.2/dokumetry/node/examples/openai/fine-tuning",
+ "0.0.2/dokumetry/node/examples/openai/chatCompletions"
+ ]
+ },
+ {
+ "group": "Cohere",
+ "version": "0.0.2",
+ "pages": [
+ "0.0.2/dokumetry/node/examples/cohere/chat",
+ "0.0.2/dokumetry/node/examples/cohere/generate",
+ "0.0.2/dokumetry/node/examples/cohere/summarize",
+ "0.0.2/dokumetry/node/examples/cohere/embed"
+ ]
+ },
+ {
+ "group": "Anthropic",
+ "version": "0.0.2",
+ "pages": [
+ "0.0.2/dokumetry/node/examples/anthropic/anthropic-completions"
+ ]
+ }
+ ]
+ }
+ ]
+ }
+ ]
+ },
+ {
+ "group": "Integrations",
+ "pages": [
+ "0.0.2/integrations/intro",
+ "0.0.2/integrations/grafanaoss",
+ "0.0.2/integrations/grafanacloud",
+ "0.0.2/integrations/datadog",
+ "0.0.2/integrations/new-relic"
+ ],
+ "version": "0.0.2"
+ },
+ {
+ "group": "API Reference",
+ "pages": [
+ "0.0.2/api-reference/introduction",
+ {
+ "group": "API Keys",
+ "icon": "key",
+ "pages": [
+ "0.0.2/api-reference/endpoint/api-keys/create",
+ "0.0.2/api-reference/endpoint/api-keys/get",
+ "0.0.2/api-reference/endpoint/api-keys/delete"
+ ],
+ "version": "0.0.2"
+ }
+ ],
+ "version": "0.0.2"
+ },
+ {
+ "group": "Get Started",
+ "pages": [
+ "0.0.1/intro",
"0.0.1/quickstart",
"0.0.1/installation",
"0.0.1/configuration"
@@ -105,7 +236,7 @@
"version": "0.0.1",
"icon": "node-js",
"pages": [
- "0.0.1/dokumetry/node/introduction",
+ "0.0.1/dokumetry/node/intro",
{
"group": "Examples",
"version": "0.0.1",