mirror of
https://github.com/hwchase17/langchain.git
synced 2026-06-09 10:17:00 +00:00
54542b9385
This PR addresses the common issue where users struggle to pass custom parameters to OpenAI-compatible APIs like LM Studio, vLLM, and others. The problem occurs when users try to use `model_kwargs` for custom parameters, which causes API errors. ## Problem Users attempting to pass custom parameters (like LM Studio's `ttl` parameter) were getting errors: ```python # ❌ This approach fails llm = ChatOpenAI( base_url="http://localhost:1234/v1", model="mlx-community/QwQ-32B-4bit", model_kwargs={"ttl": 5} # Causes TypeError: unexpected keyword argument 'ttl' ) ``` ## Solution The `extra_body` parameter is the correct way to pass custom parameters to OpenAI-compatible APIs: ```python # ✅ This approach works correctly llm = ChatOpenAI( base_url="http://localhost:1234/v1", model="mlx-community/QwQ-32B-4bit", extra_body={"ttl": 5} # Custom parameters go in extra_body ) ``` ## Changes Made 1. **Enhanced Documentation**: Updated the `extra_body` parameter docstring with comprehensive examples for LM Studio, vLLM, and other providers 2. **Added Documentation Section**: Created a new "OpenAI-compatible APIs" section in the main class docstring with practical examples 3. **Unit Tests**: Added tests to verify `extra_body` functionality works correctly: - `test_extra_body_parameter()`: Verifies custom parameters are included in request payload - `test_extra_body_with_model_kwargs()`: Ensures `extra_body` and `model_kwargs` work together 4. **Clear Guidance**: Documented when to use `extra_body` vs `model_kwargs` ## Examples Added **LM Studio with TTL (auto-eviction):** ```python ChatOpenAI( base_url="http://localhost:1234/v1", api_key="lm-studio", model="mlx-community/QwQ-32B-4bit", extra_body={"ttl": 300} # Auto-evict after 5 minutes ) ``` **vLLM with custom sampling:** ```python ChatOpenAI( base_url="http://localhost:8000/v1", api_key="EMPTY", model="meta-llama/Llama-2-7b-chat-hf", extra_body={ "use_beam_search": True, "best_of": 4 } ) ``` ## Why This Works - `model_kwargs` parameters are passed directly to the OpenAI client's `create()` method, causing errors for non-standard parameters - `extra_body` parameters are included in the HTTP request body, which is exactly what OpenAI-compatible APIs expect for custom parameters Fixes #32115. <!-- START COPILOT CODING AGENT TIPS --> --- 💬 Share your feedback on Copilot coding agent for the chance to win a $200 gift card! Click [here](https://survey.alchemer.com/s3/8343779/Copilot-Coding-agent) to start the survey. --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: mdrxy <61371264+mdrxy@users.noreply.github.com> Co-authored-by: Mason Daugherty <github@mdrxy.com> Co-authored-by: Mason Daugherty <mason@langchain.dev>
58 lines
1.3 KiB
Markdown
58 lines
1.3 KiB
Markdown
# langchain-mistralai
|
|
|
|
This package contains the LangChain integrations for [MistralAI](https://docs.mistral.ai) through their [mistralai](https://pypi.org/project/mistralai/) SDK.
|
|
|
|
## Installation
|
|
|
|
```bash
|
|
pip install -U langchain-mistralai
|
|
```
|
|
|
|
## Chat Models
|
|
|
|
This package contains the `ChatMistralAI` class, which is the recommended way to interface with MistralAI models.
|
|
|
|
To use, install the requirements, and configure your environment.
|
|
|
|
```bash
|
|
export MISTRAL_API_KEY=your-api-key
|
|
```
|
|
|
|
Then initialize
|
|
|
|
```python
|
|
from langchain_core.messages import HumanMessage
|
|
from langchain_mistralai.chat_models import ChatMistralAI
|
|
|
|
chat = ChatMistralAI(model="mistral-small")
|
|
messages = [HumanMessage(content="say a brief hello")]
|
|
chat.invoke(messages)
|
|
```
|
|
|
|
`ChatMistralAI` also supports async and streaming functionality:
|
|
|
|
```python
|
|
# For async...
|
|
await chat.ainvoke(messages)
|
|
|
|
# For streaming...
|
|
for chunk in chat.stream(messages):
|
|
print(chunk.content, end="", flush=True)
|
|
```
|
|
|
|
## Embeddings
|
|
|
|
With `MistralAIEmbeddings`, you can directly use the default model 'mistral-embed', or set a different one if available.
|
|
|
|
### Choose model
|
|
|
|
`embedding.model = 'mistral-embed'`
|
|
|
|
### Simple query
|
|
|
|
`res_query = embedding.embed_query("The test information")`
|
|
|
|
### Documents
|
|
|
|
`res_document = embedding.embed_documents(["test1", "another test"])`
|