Skip to content

The agent engineering platform.

docs: `integrations` references update (#25217)

Leonid Ganeline4a812e319313
diff --git a/docs/docs/integrations/chat/llamacpp.ipynb b/docs/docs/integrations/chat/llamacpp.ipynb
index 6ce74e1846..85aedff9cb 100644
--- a/docs/docs/integrations/chat/llamacpp.ipynb
+++ b/docs/docs/integrations/chat/llamacpp.ipynb
@@ -4,9 +4,23 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "# ChatLlamaCpp\n",
- "\n",
- "This notebook provides a quick overview for getting started with chat model intergrated with [llama cpp python](https://github.com/abetlen/llama-cpp-python)."
+ "# Llama.cpp\n",
+ "\n",
+ ">[llama.cpp python](https://github.com/abetlen/llama-cpp-python) library is a simple Python bindings for `@ggerganov`\n",
+ ">[llama.cpp](https://github.com/ggerganov/llama.cpp).\n",
+ ">\n",
+ ">This package provides:\n",
+ ">\n",
+ "> - Low-level access to C API via ctypes interface.\n",
+ "> - High-level Python API for text completion\n",
+ "> - `OpenAI`-like API\n",
+ "> - `LangChain` compatibility\n",
+ "> - `LlamaIndex` compatibility\n",
+ "> - OpenAI compatible web server\n",
+ "> - Local Copilot replacement\n",
+ "> - Function Calling support\n",
+ "> - Vision API support\n",
+ "> - Multiple Models\n"
]
},
{
@@ -410,7 +424,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.11.8"
+ "version": "3.10.12"
}
},
"nbformat": 4,
diff --git a/docs/docs/integrations/chat/octoai.ipynb b/docs/docs/integrations/chat/octoai.ipynb
index 8c2a1bc853..a0bbe98be8 100644
--- a/docs/docs/integrations/chat/octoai.ipynb
+++ b/docs/docs/integrations/chat/octoai.ipynb
@@ -99,7 +99,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.11.7"
+ "version": "3.10.12"
},
"vscode": {
"interpreter": {
diff --git a/docs/docs/integrations/chat/perplexity.ipynb b/docs/docs/integrations/chat/perplexity.ipynb
index f74a410115..4b8e151750 100644
--- a/docs/docs/integrations/chat/perplexity.ipynb
+++ b/docs/docs/integrations/chat/perplexity.ipynb
@@ -17,7 +17,7 @@
"source": [
"# ChatPerplexity\n",
"\n",
- "This notebook covers how to get started with Perplexity chat models."
+ "This notebook covers how to get started with `Perplexity` chat models."
]
},
{
@@ -37,17 +37,31 @@
"from langchain_core.prompts import ChatPromptTemplate"
]
},
+ {
+ "cell_type": "markdown",
+ "id": "b26e2035-2f81-4451-ba44-fa2e2d5aeb62",
+ "metadata": {},
+ "source": [
+ "The code provided assumes that your PPLX_API_KEY is set in your environment variables. If you would like to manually specify your API key and also choose a different model, you can use the following code:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "d986aac6-1bae-4608-8514-d3ba5b35b10e",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "chat = ChatPerplexity(\n",
+ " temperature=0, pplx_api_key=\"YOUR_API_KEY\", model=\"llama-3-sonar-small-32k-online\"\n",
+ ")"
+ ]
+ },
{
"cell_type": "markdown",
"id": "97a8ce3a",
"metadata": {},
"source": [
- "The code provided assumes that your PPLX_API_KEY is set in your environment variables. If you would like to manually specify your API key and also choose a different model, you can use the following code:\n",
- "\n",
- "```python\n",
- "chat = ChatPerplexity(temperature=0, pplx_api_key=\"YOUR_API_KEY\", model=\"llama-3-sonar-small-32k-online\")\n",
- "```\n",
- "\n",
"You can check a list of available models [here](https://docs.perplexity.ai/docs/model-cards). For reproducibility, we can set the API key dynamically by taking it as an input in this notebook."
]
},
@@ -221,7 +235,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.9.18"
+ "version": "3.10.12"
}
},
"nbformat": 4,
diff --git a/docs/docs/integrations/providers/llamacpp.mdx b/docs/docs/integrations/providers/llamacpp.mdx
index 48b12913c2..de7d40a1c5 100644
--- a/docs/docs/integrations/providers/llamacpp.mdx
+++ b/docs/docs/integrations/providers/llamacpp.mdx
@@ -1,26 +1,50 @@
# Llama.cpp
-This page covers how to use [llama.cpp](https://github.com/ggerganov/llama.cpp) within LangChain.
-It is broken into two parts: installation and setup, and then references to specific Llama-cpp wrappers.
+>[llama.cpp python](https://github.com/abetlen/llama-cpp-python) library is a simple Python bindings for `@ggerganov`
+>[llama.cpp](https://github.com/ggerganov/llama.cpp).
+>
+>This package provides:
+>
+> - Low-level access to C API via ctypes interface.
+> - High-level Python API for text completion
+> - `OpenAI`-like API
+> - `LangChain` compatibility
+> - `LlamaIndex` compatibility
+> - OpenAI compatible web server
+> - Local Copilot replacement
+> - Function Calling support
+> - Vision API support
+> - Multiple Models
## Installation and Setup
-- Install the Python package with `pip install llama-cpp-python`
+
+- Install the Python package
+ ```bash
+ pip install llama-cpp-python
+ ````
- Download one of the [supported models](https://github.com/ggerganov/llama.cpp#description) and convert them to the llama.cpp format per the [instructions](https://github.com/ggerganov/llama.cpp)
-## Wrappers
-### LLM
+## Chat models
+
+See a [usage example](/docs/integrations/chat/llamacpp).
+
+```python
+from langchain_community.chat_models import ChatLlamaCpp
+```
+
+## LLMs
+
+See a [usage example](/docs/integrations/llms/llamacpp).
-There exists a LlamaCpp LLM wrapper, which you can access with
```python
from langchain_community.llms import LlamaCpp
```
-For a more detailed walkthrough of this, see [this notebook](/docs/integrations/llms/llamacpp)
-### Embeddings
+## Embedding models
+
+See a [usage example](/docs/integrations/text_embedding/llamacpp).
-There exists a LlamaCpp Embeddings wrapper, which you can access with
```python
from langchain_community.embeddings import LlamaCppEmbeddings
```
-For a more detailed walkthrough of this, see [this notebook](/docs/integrations/text_embedding/llamacpp)
diff --git a/docs/docs/integrations/providers/maritalk.mdx b/docs/docs/integrations/providers/maritalk.mdx
new file mode 100644
index 0000000000..6b0dcda545
--- /dev/null
+++ b/docs/docs/integrations/providers/maritalk.mdx
@@ -0,0 +1,21 @@
+# MariTalk
+
+>[MariTalk](https://www.maritaca.ai/en) is an LLM-based chatbot trained to meet the needs of Brazil.
+
+## Installation and Setup
+
+You have to get the MariTalk API key.
+
+You also need to install the `httpx` Python package.
+
+```bash
+pip install httpx
+```
+
+## Chat models
+
+See a [usage example](/docs/integrations/chat/maritalk).
+
+```python
+from langchain_community.chat_models import ChatMaritalk
+```
diff --git a/docs/docs/integrations/providers/mlx.mdx b/docs/docs/integrations/providers/mlx.mdx
new file mode 100644
index 0000000000..dc859305cd
--- /dev/null
+++ b/docs/docs/integrations/providers/mlx.mdx
@@ -0,0 +1,34 @@
+# MLX
+
+>[MLX](https://ml-explore.github.io/mlx/build/html/index.html) is a `NumPy`-like array framework
+> designed for efficient and flexible machine learning on `Apple` silicon,
+> brought to you by `Apple machine learning research`.
+
+
+## Installation and Setup
+
+Install several Python packages:
+
+```bash
+pip install mlx-lm transformers huggingface_hub
+````
+
+
+## Chat models
+
+
+See a [usage example](/docs/integrations/chat/mlx).
+
+```python
+from langchain_community.chat_models.mlx import ChatMLX
+```
+
+## LLMs
+
+### MLX Local Pipelines
+
+See a [usage example](/docs/integrations/llms/mlx_pipelines).
+
+```python
+from langchain_community.llms.mlx_pipeline import MLXPipeline
+```
diff --git a/docs/docs/integrations/providers/octoai.mdx b/docs/docs/integrations/providers/octoai.mdx
new file mode 100644
index 0000000000..d4a064c7c7
--- /dev/null
+++ b/docs/docs/integrations/providers/octoai.mdx
@@ -0,0 +1,37 @@
+# OctoAI
+
+>[OctoAI](https://docs.octoai.cloud/docs) offers easy access to efficient compute
+> and enables users to integrate their choice of AI models into applications.
+> The `OctoAI` compute service helps you run, tune, and scale AI applications easily.
+
+
+## Installation and Setup
+
+- Install the `openai` Python package:
+ ```bash
+ pip install openai
+ ````
+- Register on `OctoAI` and get an API Token from [your OctoAI account page](https://octoai.cloud/settings).
+
+
+## Chat models
+
+See a [usage example](/docs/integrations/chat/octoai).
+
+```python
+from langchain_community.chat_models import ChatOctoAI
+```
+
+## LLMs
+
+See a [usage example](/docs/integrations/llms/octoai).
+
+```python
+from langchain_community.llms.octoai_endpoint import OctoAIEndpoint
+```
+
+## Embedding models
+
+```python
+from langchain_community.embeddings.octoai_embeddings import OctoAIEmbeddings
+```
diff --git a/docs/docs/integrations/providers/perplexity.mdx b/docs/docs/integrations/providers/perplexity.mdx
new file mode 100644
index 0000000000..9e89994f54
--- /dev/null
+++ b/docs/docs/integrations/providers/perplexity.mdx
@@ -0,0 +1,25 @@
+# Perplexity
+
+>[Perplexity](https://www.perplexity.ai/pro) is the most powerful way to search
+> the internet with unlimited Pro Search, upgraded AI models, unlimited file upload,
+> image generation, and API credits.
+>
+> You can check a [list of available models](https://docs.perplexity.ai/docs/model-cards).
+
+## Installation and Setup
+
+Install a Python package:
+
+```bash
+pip install openai
+````
+
+Get your API key from [here](https://docs.perplexity.ai/docs/getting-started).
+
+## Chat models
+
+See a [usage example](/docs/integrations/chat/perplexity).
+
+```python
+from langchain_community.chat_models import ChatPerplexity
+```
diff --git a/docs/docs/integrations/text_embedding/llamacpp.ipynb b/docs/docs/integrations/text_embedding/llamacpp.ipynb
index d57f58716a..375ee76f6b 100644
--- a/docs/docs/integrations/text_embedding/llamacpp.ipynb
+++ b/docs/docs/integrations/text_embedding/llamacpp.ipynb
@@ -4,9 +4,23 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "# Llama-cpp\n",
+ "# Llama.cpp\n",
"\n",
- "This notebook goes over how to use Llama-cpp embeddings within LangChain"
+ ">[llama.cpp python](https://github.com/abetlen/llama-cpp-python) library is a simple Python bindings for `@ggerganov`\n",
+ ">[llama.cpp](https://github.com/ggerganov/llama.cpp).\n",
+ ">\n",
+ ">This package provides:\n",
+ ">\n",
+ "> - Low-level access to C API via ctypes interface.\n",
+ "> - High-level Python API for text completion\n",
+ "> - `OpenAI`-like API\n",
+ "> - `LangChain` compatibility\n",
+ "> - `LlamaIndex` compatibility\n",
+ "> - OpenAI compatible web server\n",
+ "> - Local Copilot replacement\n",
+ "> - Function Calling support\n",
+ "> - Vision API support\n",
+ "> - Multiple Models\n"
]
},
{
@@ -80,9 +94,9 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.9.1"
+ "version": "3.10.12"
}
},
"nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
}