Metadata-Version: 2.1
Name: graphbook_huggingface
Version: 0.0.2
Summary: Graphbook Huggingface Plugin for no-code Huggingface workflows
Home-page: https://graphbook.ai
License: MIT
Keywords: huggingface,ml,workflow,framework,pytorch,data science,machine learning,ai
Author: Richard Franklin
Author-email: rsamf@graphbook.ai
Requires-Python: >=3.10,<4.0
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Dist: datasets (>=2.21.0,<3.0.0)
Requires-Dist: transformers (>=4.44.2,<5.0.0)
Project-URL: Documentation, https://docs.graphbook.ai
Project-URL: Repository, https://github.com/graphbookai/graphbook
Description-Content-Type: text/markdown

<p align="center">
  <a href="https://graphbook.ai">
    <img src="https://github.com/graphbookai/graphbook/blob/main/docs/_static/graphbook.png?raw=true" alt="Logo" width=256>
  </a>

  <h1 align="center">Graphbook Huggingface</h1>

  <p align="center">
    A Huggingface Plugin to drag-and-drop models and datasets onto Graphbook workflows
  </p>
</p>

This plugin contains a web panel for searching and drag-and-dropping models and datasets from [Huggingface Hub](https://huggingface.co/) onto their graphbook workflows.
It also contains the following nodes:

* `HuggingfacePipeline` for model usage from transformers package
* `HuggingfaceDataset` for dataset usage from the datasets package
* `AssignModelOutputsToNotes` to assign HF model outputs to incoming Notes

## Getting started
1. `pip install graphbook_huggingface`
1. `graphbook --config hf.config.yaml`


