ActionHugging FaceUpdated September 2026
How do I run chat completion on Hugging Face?
Short answer: You can hugging face chat completion in Hugging Face by hand from its own interface, but it won’t repeat itself. On TinyCommand, add the Hugging Face Hugging Face Chat Completion action to a workflow, map its 6 inputs from any upstream app, and it runs automatically every time the trigger fires. No code, and a free tier to start.
Inputs
The fields this action accepts.
Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.
| Field | Type | Required | Description |
|---|---|---|---|
Model model | options | Required | Which model to use |
User Message message | string | Required | User message to send to the model |
System Prompt system_prompt | string | Optional | Optional system instructions that shape the model's behavior |
Temperature temperature | string | Optional | Sampling temperature (0–2). Higher = more random. |
Max Tokens max_tokens | string | Optional | Maximum tokens to generate in the response |
Top P top_p | string | Optional | Nucleus sampling threshold (0–1) |
Sample request
{"model": "{{trigger.model}}","message": "e.g. Summarize this article in 3 bullets","system_prompt": "e.g. You are a helpful assistant.","temperature": "0.7","max_tokens": "1024"}
Returns
{"id": "chatcmpl-abc123","model": "meta-llama/Llama-3.3-70B-Instruct","usage": {"total_tokens": 60,"prompt_tokens": 10,"completion_tokens": 50},"choices": [{"message": {"role": "assistant","content": "Sample response"},"finish_reason": "stop"}]}
Use these fields in downstream nodes for routing, logging, or error handling.
Triggered by
Apps that pair well as the trigger for Hugging Face Chat Completion.
Any of these apps can fire this action as part of a workflow.
FAQ
Questions about Hugging Face Chat Completion.
What does the Hugging Face Chat Completion action do in Hugging Face?
Runs chat completion against any text-generation model on Hugging Face Hub that supports the TGI server. OpenAI-compatible message-array shape. Model selection via model ID (e.g., meta-llama/Llama-3.3-70B-Instruct).
What inputs does Hugging Face Chat Completion require?
Required: Model, User Message. Every input accepts a static value or a variable from any upstream node in your workflow.
Can I use dynamic inputs from earlier workflow nodes?
Yes. Any field on this action can pull values from upstream nodes, whether that's a form response, a trigger payload, an AI output, or a lookup result.
What happens if Hugging Face returns an error?
The run history shows the failed step with its input and the error message Hugging Face returned, so you can fix the input and run the workflow again. Automatic retries are built into HTTP steps only, where you can also set your own retry count and delay.
Does Hugging Face Chat Completion support batch operations?
Run Hugging Face Chat Completion inside a loop to process each item in an array. TinyCommand does not throttle calls for you, so for large arrays add a Delay step if you need to stay within Hugging Face's rate limits.
More actions
Other Hugging Face actions.
Action
HF Feature Extraction (Embeddings)
Generates sentence embeddings from any sentence-transformers or BGE-class model on the HF Hub. For RAG-pipeline vector generation when you want a specific HF-hosted embedding model.
ActionHF Text Classification
Runs any classifier model from HF Hub on text input — sentiment, toxicity, NER, intent. Pick the right classifier for your use case from the broad Hub catalog.
ActionHF Text to Image
Generates images from text using any HF-hosted image model (SDXL, SD3.5, Flux variants, community fine-tunes). For accessing niche or specific image models from the broad HF catalog.