langchain/libs/partners/huggingface
Ella Charlaix c401254770
huggingface: Add ipex support to HuggingFaceEmbeddings (#29386)
ONNX and OpenVINO models are available by specifying the `backend`
argument (the model is loaded using `optimum`
https://github.com/huggingface/optimum)

```python
from langchain_huggingface import HuggingFaceEmbeddings

embedding = HuggingFaceEmbeddings(
    model_name=model_id,
    model_kwargs={"backend": "onnx"},
)
```

With this PR we also enable the IPEX backend 



```python
from langchain_huggingface import HuggingFaceEmbeddings

embedding = HuggingFaceEmbeddings(
    model_name=model_id,
    model_kwargs={"backend": "ipex"},
)
```
2025-02-07 15:21:09 -08:00
..
langchain_huggingface huggingface: Add ipex support to HuggingFaceEmbeddings (#29386) 2025-02-07 15:21:09 -08:00
scripts multiple: pydantic 2 compatibility, v0.3 (#26443) 2024-09-13 14:38:45 -07:00
tests partners: Fixed the procedure of initializing pad_token_id (#29500) 2025-02-03 21:40:33 -05:00
.gitignore
LICENSE
Makefile infra: add UV_FROZEN to makefiles (#29642) 2025-02-06 14:36:54 -05:00
pyproject.toml infra: migrate to uv (#29566) 2025-02-06 13:36:26 -05:00
README.md
uv.lock infra: migrate to uv (#29566) 2025-02-06 13:36:26 -05:00

langchain-huggingface

This package contains the LangChain integrations for huggingface related classes.

Installation and Setup

  • Install the LangChain partner package
pip install langchain-huggingface