community: Skip Login to HuggubgFaceHub when token is not set

[mirkenstein]

Thank you for contributing to LangChain!

• HuggingFaceEndpoint: "Skip Login to HuggingFaceHub"

  • Where: langchain, community, llm, huggingface_endpoint

• PR message: Delete this entire checklist and replace with

  • Description: Skip login to huggingface hub when when huggingfacehub_api_token is not set. This is needed when using custom endpoint_url outside of HuggingFaceHub.
  • Issue: the issue # it fixes Handling huggingfacehub_api_token=None for HuggingFaceEndpoint #20342 and HuggingFaceEndpoint requires a HuggingFace API key even when using self hosted models #19685
  • Dependencies: None

• Add tests and docs:

  1. Tested with locally available TGI endpoint
  2. Example Usage

from langchain_community.llms import HuggingFaceEndpoint

llm = HuggingFaceEndpoint(
    endpoint_url='http://localhost:8080',
    server_kwargs={
        "headers": {"Content-Type": "application/json"}
    }
)
resp = llm.invoke("Tell me a joke")
print(resp)

Also tested against HF Endpoints

from langchain_community.llms import HuggingFaceEndpoint
huggingfacehub_api_token = "hf_xyz"
repo_id = "mistralai/Mistral-7B-Instruct-v0.2"
llm = HuggingFaceEndpoint(
   huggingfacehub_api_token=huggingfacehub_api_token,
   repo_id=repo_id,
)
resp = llm.invoke("Tell me a joke")
print(resp)

Additional guidelines:

• Make sure optional dependencies are imported within a function.
• Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests.
• Most PRs should not touch more than one package.
• Changes should be backwards compatible.
• If you are adding something to community, do not re-import it in langchain.

If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, hwchase17.

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

1 Ignored Deployment

Name	Status	Preview	Comments	Updated (UTC)
langchain	⬜️ Ignored (Inspect)	Visit Preview		May 31, 2024 3:53pm

[nwmoon]

it is necessary function !!

[mirkenstein]

Mentioning @mspronesti and @hwchase17 since you were the reviewers on my other HuggingFace PR #21282

[mirkenstein]

@eyurtsev

[mirkenstein]

There is a new official library released from Huggning Face
https://huggingface.co/blog/langchain
The new library still has the same issue.

Here is the deprecation warning when using the current community library.

LangChainDeprecationWarning: The class `HuggingFaceEndpoint` was deprecated in LangChain 0.0.37 and will be removed in 0.3. An updated version of the class exists in the from langchain-huggingface package and should be used instead. To use it run `pip install -U from langchain-huggingface` and import as `from from langchain_huggingface import llms import HuggingFaceEndpoint`.
  warn_deprecated(

[mirkenstein]

There is a new official library released from Huggning Face https://huggingface.co/blog/langchain The new library still has the same issue.

Here is the deprecation warning when using the current community library.

LangChainDeprecationWarning: The class `HuggingFaceEndpoint` was deprecated in LangChain 0.0.37 and will be removed in 0.3. An updated version of the class exists in the from langchain-huggingface package and should be used instead. To use it run `pip install -U from langchain-huggingface` and import as `from from langchain_huggingface import llms import HuggingFaceEndpoint`.
  warn_deprecated(

The current library is not deprecated yet and it looks like it will be around for quite some time. We can make this change also in the new langchain-huggingface https://github.com/langchain-ai/langchain/blob/master/libs/partners/huggingface/langchain_huggingface/llms/huggingface_endpoint.py as soon as this one gets merged.

[matthewgrossman]

@mirkenstein Any reason to not just bundle that change into this PR as well? Would help keep the change unified across both clients, easier to track down the original PR, etc

[mirkenstein]

@mirkenstein Any reason to not just bundle that change into this PR as well? Would help keep the change unified across both clients, easier to track down the original PR, etc

One of the guidelines states that "Most PRs should not touch more than one package"
I applied the same change to the partner library and now the checks are failing at "CI / CI Success (pull_request)" step.

[mirkenstein]

@mirkenstein Any reason to not just bundle that change into this PR as well? Would help keep the change unified across both clients, easier to track down the original PR, etc

One of the guidelines states that "Most PRs should not touch more than one package" I applied the same change to the partner library and now the checks are failing at "CI / CI Success (pull_request)" step.

Created #22365 for the new partner client.