Skip to main content

Hugging Face Inference API (Serverless)

This document provides information on how to integrate Hugging Face models though Hugging Face's Inference API (Serverless). For information about integrating with Inference Endpoint (Dedicated), please refer to other documents.

Requisites​

To use models provided by Hugging Face, you need to have an Hugging Face API key. You can get one by signing up at Hugging Face.

Required credentials:

  • HUGGING_FACE_API_KEY: Your Hugging Face API key.

Supported Models:​

NOTE: Only models that are labeled as 'Feature Extraction' and available to Inference API are supported by this integration.

Feature Extraction

Wildcard​

  • Model schema id: hugging_face/wildcard

Since Hugging Face is a platform that hosts thousands of models, TaskingAI created a wildcard model that can integrate all eligible models on Hugging Face. Currently, the eligible models are Feature Extraction models that are available to Hugging Face Inference API (Serverless) service.

To integrate a specific model, pass the model id to the Provider Model Id parameter, for example, sentence-transformers/paraphrase-MiniLM-L6-v2.

Hugging Face Deploy