langchain/docs/modules/agents/tools/examples/huggingface_tools.ipynb

HuggingFace Tools

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

In [ ]:

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

In [1]:

from langchain.agents 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

In [2]:

tool.run("text-classification")

Out [2]:

'facebook/bart-large-mnli'

In [ ]: