HuggingFace hub integration

Integrate with the HuggingFace hub tool using LangChain Python.

Huggingface Tools that supporting text I/O can be loaded directly using the load_huggingface_tool function.

# Requires transformers>=4.29.0 and huggingface_hub>=0.14.1
pip install -qU  transformers huggingface_hub > /dev/null

pip install -qU  langchain-community

from langchain_community.agent_toolkits.load_tools import load_huggingface_tool

tool = load_huggingface_tool("lysandre/hf-model-downloads")

print(f"{tool.name}: {tool.description}")

model_download_counter: This is a tool that returns the most downloaded model of a given task on the Hugging Face Hub. It takes the name of the category (such as text-classification, depth-estimation, etc), and returns the name of the checkpoint

tool.run("text-classification")

'facebook/bart-large-mnli'

---

Edit this page on GitHub or file an issue.

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.