langchain/libs/community
Prince Canuma 3587c60396
community[patch]: Fix MLX LLM Stream (#20575)
Closes #20561

This PR fixes MLX LLM stream `AttributeError`. 

Recently, `mlx-lm` changed the token decoding logic, which affected the
LC+MLX integration.

Additionally, I made minor fixes such as: docs example broken link and
enforcing pipeline arguments (max_tokens, temp and etc) for invoke.
   
- **Issue:** #20561
    
- **Twitter handle:** @Prince_Canuma
2024-05-20 17:17:08 -07:00
..
langchain_community community[patch]: Fix MLX LLM Stream (#20575) 2024-05-20 17:17:08 -07:00
scripts langchain[patch],community[minor]: Move some unit tests from langchain to community, use core for fake models (#21190) 2024-05-02 09:57:52 -04:00
tests community[patch]: standardized sparkllm init args (#21633) 2024-05-20 17:11:36 -07:00
Makefile community[minor]: add Kinetica LLM wrapper (#17879) 2024-02-22 16:02:00 -08:00
poetry.lock community: release 0.2.0 (#21834) 2024-05-17 13:49:29 -07:00
pyproject.toml community: release 0.2.0 (#21834) 2024-05-17 13:49:29 -07:00
README.md Batch update of alt text and title attributes for images in md/mdx files across repo (#15357) 2024-01-12 14:37:48 -08:00

🦜🧑‍🤝‍🧑 LangChain Community

Downloads License: MIT

Quick Install

pip install langchain-community

What is it?

LangChain Community contains third-party integrations that implement the base interfaces defined in LangChain Core, making them ready-to-use in any LangChain application.

For full documentation see the API reference.

Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.

📕 Releases & Versioning

langchain-community is currently on version 0.0.x

All changes will be accompanied by a patch version increase.

💁 Contributing

As an open-source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infrastructure, or better documentation.

For detailed information on how to contribute, see the Contributing Guide.