langchain/libs/partners/huggingface/langchain_huggingface/llms
Lucain a2023a1e96
huggingface; fix huggingface_endpoint.py (initialize clients only with supported kwargs) (#26378)
## Description

By default, `HuggingFaceEndpoint` instantiates both the
`InferenceClient` and the `AsyncInferenceClient` with the
`"server_kwargs"` passed as input. This is an issue as both clients
might not support exactly the same kwargs. This has been highlighted in
https://github.com/huggingface/huggingface_hub/issues/2522 by
@morgandiverrez with the `trust_env` parameter. In order to make
`langchain` integration future-proof, I do think it's wiser to forward
only the supported parameters to each client. Parameters that are not
supported are simply ignored with a warning to the user. From a
`huggingface_hub` maintenance perspective, this allows us much more
flexibility as we are not constrained to support the exact same kwargs
in both clients.

## Issue

https://github.com/huggingface/huggingface_hub/issues/2522

## Dependencies

None

## Twitter 

https://x.com/Wauplin

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-09-20 16:05:24 -07:00
..
__init__.py infra: update mypy 1.10, ruff 0.5 (#23721) 2024-07-03 10:33:27 -07:00
huggingface_endpoint.py huggingface; fix huggingface_endpoint.py (initialize clients only with supported kwargs) (#26378) 2024-09-20 16:05:24 -07:00
huggingface_pipeline.py multiple: pydantic 2 compatibility, v0.3 (#26443) 2024-09-13 14:38:45 -07:00