[InferenceClient / langchain-HuggingFaceEndpoint] impossible to used Langchain HuggingFaceEndpoint whith trust_env=True

[morgandiverrez]

Describe the bug

HuggingFaceEndpoint in the partners libs HuggingFace in the Langchain librairy cannot be used withtrust_env = True/False.

When we used the server_kwargs for set trust_env in client, this libs create AsyncInferenceClient and InferenceClient everytime, but InferenceClient everytime, but Client and AsyncInferenceClient doesn't have same parameter (trust_env in async and not in InferenceClient everytime, but InferenceClient everytime, but Client for exemple) .
if we used server_kwargs, we need to have same parameter in InferenceClient everytime, but Client doesn't have trust_env parameter.

I can fixed this in a PR by add trust_env parameter

Reproduction

from langchain_huggingface .llms import HuggingFaceEndpoint

HuggingFaceEndpoint(
endpoint_url="http://localhost:8010/",
max_new_tokens=512,
temperature=0.01,
repetition_penalty=1.03,
huggingfacehub_api_token="my-api-key",
server_kwargs={"trust_env"=True}
}

Logs

File "/home/Morgan.Diverrez/code/GitHub/tock-arkea/gen-ai/orchestrator-server/src/main/python/server/src/gen_ai_orchestrator/services/langchain/factories/llm/hugging_face_tgi_llm_factory.py", line 40, in get_language_model
    return HuggingFaceEndpoint(
  File "/home/Morgan.Diverrez/code/GitHub/tock-arkea/gen-ai/orchestrator-server/src/main/python/server/.venv/lib/python3.9/site-packages/pydantic/v1/main.py", line 341, in __init__
    raise validation_error
pydantic.v1.error_wrappers.ValidationError: 1 validation error for HuggingFaceEndpoint
__root__
  __init__() got an unexpected keyword argument 'trust_env' (type=type_error)

System info

- huggingface_hub version: 0.25.0.dev0
- Platform: Linux-5.15.0-117-generic-x86_64-with-glibc2.31
- Python version: 3.9.18
- Running in iPython ?: No
- Running in notebook ?: No
- Running in Google Colab ?: No
- Token path ?: /home/Morgan.Diverrez/.cache/huggingface/token
- Has saved token ?: True
- Who am I ?: morganDiverrez
- Configured git credential helpers: store
- FastAI: N/A
- Tensorflow: N/A
- Torch: N/A
- Jinja2: 3.1.4
- Graphviz: N/A
- keras: N/A
- Pydot: N/A
- Pillow: N/A
- hf_transfer: N/A
- gradio: N/A
- tensorboard: N/A
- numpy: 1.26.4
- pydantic: 2.8.2
- aiohttp: 3.10.5
- ENDPOINT: https://huggingface.co
- HF_HUB_CACHE: /home/Morgan.Diverrez/.cache/huggingface/hub
- HF_ASSETS_CACHE: /home/Morgan.Diverrez/.cache/huggingface/assets
- HF_TOKEN_PATH: /home/Morgan.Diverrez/.cache/huggingface/token
- HF_HUB_OFFLINE: False
- HF_HUB_DISABLE_TELEMETRY: False
- HF_HUB_DISABLE_PROGRESS_BARS: None
- HF_HUB_DISABLE_SYMLINKS_WARNING: False
- HF_HUB_DISABLE_EXPERIMENTAL_WARNING: False
- HF_HUB_DISABLE_IMPLICIT_TOKEN: False
- HF_HUB_ENABLE_HF_TRANSFER: False
- HF_HUB_ETAG_TIMEOUT: 10
- HF_HUB_DOWNLOAD_TIMEOUT: 10

[morgandiverrez]

hello, @Wauplin what do you think about this PR ?

[Wauplin]

As explained in #2525, I'll close this issue without merging in favor of langchain-ai/langchain#26378 that just got merged. Thanks again for reporting @morgandiverrez 🤗