langchain-huggingface requires torch installaion

[marekb-sci]

Checked other resources

• I added a very descriptive title to this issue.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangChain rather than my code.
• The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

pip install langchain-huggingface

Error Message and Stack Trace (if applicable)

No response

Description

I'm using LLM via inference api from huggingface https://huggingface.co/docs/api-inference/index
I can't use the langchain-huggingface as it has extremly have torch dependency, obsolete for my case

System Info

Python 3.9.18

[DarkDk123]

Similar issue! I mostly use langchain-huggingface for inference APIs.
And greatly annoyed by unnecessary large installations i.e. cuda liberaries etc.

There must be a minimal installation of langchain-huggingface as:

pip install langchain-huggingface[inference-api]