Hugging Face

Use Hugging Face in Sim to generate text completions with the Hugging Face Inference API. Choose a model and supply the prompt for the workflow step.

Usage Instructions

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

Actions

Hugging Face 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", "meta-llama/Llama-3.3-70B-Instruct")
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
contentstringGenerated text content
modelstringModel used for generation
usageobjectToken usage information
prompt_tokensnumberNumber of tokens in the prompt
completion_tokensnumberNumber of tokens in the completion
total_tokensnumberTotal number of tokens used