Mandala
Tools

Hugging Face

Use Hugging Face Inference API

Usage Instructions

Integrate Hugging Face into the workflow. Can generate completions using the Hugging Face Inference API.

Tools

huggingface_chat

Generate completions using Hugging Face Inference API

Input

ParameterTypeRequiredDescription
systemPromptstringNoSystem prompt to guide the model behavior
contentstringYesThe user message content to send to the model
providerstringYesThe provider to use for the API request (e.g., novita, cerebras, etc.)
modelstringYesModel to use for chat completions (e.g., deepseek/deepseek-v3-0324)
maxTokensnumberNoMaximum number of tokens to generate
temperaturenumberNoSampling temperature (0-2). Higher values make output more random
apiKeystringYesHugging Face API token

Output

ParameterTypeDescription
successbooleanOperation success status
outputobjectChat completion results

Notes

  • Category: tools
  • Type: huggingface
Hugging Face