logo

Hugging Face Component

Drag & Drop LLM Component
Hugging Face Component

Overview

A drag-and-drop component for integrating Hugging Face's inference API. Configure model parameters and connect inputs/outputs to access thousands of open-source models.

Component Configuration

Basic Parameters

  • InputText input for the model
  • System MessageSystem prompt to guide model behavior
  • StreamToggle for streaming responses
  • Model IDe.g., openai-community/gpt2

API Configuration

  • API TokenYour Hugging Face API token
  • Inference EndpointAPI endpoint URL
  • TaskSpecific task for the model

Generation Parameters

  • Max New TokensMaximum tokens to generate (512 default)
  • TemperatureCreativity control (0.8 default)
  • Top KTop-k sampling parameter
  • Top PNucleus sampling (0.95 default)
  • Typical PTypical probability (0.95 default)
  • Repetition PenaltyPenalty for repeated tokens
  • Retry AttemptsNumber of retry attempts (1 default)

Output Connections

  • TextGenerated text output
  • Language ModelModel information and metadata

Usage Tips

  • Choose appropriate model for task
  • Balance sampling parameters
  • Use retry attempts for reliability
  • Monitor token usage limits

Best Practices

  • Secure API token handling
  • Test with smaller token limits
  • Implement proper error handling
  • Consider model-specific parameters