ActionHugging FaceUpdated May 2026

How do I generate embeddings on Hugging Face?

Short answer: Drop the "Hugging Face → HF Feature Extraction (Embeddings)" action anywhere in your workflow, map the inputs from upstream nodes, and publish.

Use this action All 4 Hugging Face actions

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	string	Required	HF embedding model id
Text text	string	Required	Text (required)

Sample request

{
  "model": "e.g. BAAI/bge-large-en-v1.5",
  "text": "{{trigger.text}}"
}

Returns

[
  0.0123,
  -0.0456,
  0.0789
]

Use these fields in downstream nodes for routing, logging, or error handling.

Triggered by

Apps that pair well as the trigger for HF Feature Extraction (Embeddings).

Any of these apps can fire this action as part of a workflow.

Google Sheets → Hugging Face

2 Google Sheets triggers

HubSpot → Hugging Face

18 HubSpot triggers

FAQ

Questions about HF Feature Extraction (Embeddings).

What does the HF Feature Extraction (Embeddings) action do in Hugging Face?

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.

What inputs does HF Feature Extraction (Embeddings) require?

Required: Model, Text. 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 workflow pauses on the failed node, the error message is captured in the run log, and you can retry the run with one click. Auto-retry policies are configurable per workflow with exponential backoff up to 5 attempts.

Does HF Feature Extraction (Embeddings) support batch operations?

Yes. Run HF Feature Extraction (Embeddings) inside a Loop node to process arrays. Tiny Command handles Hugging Face's rate limits automatically so you don't have to throttle manually.

More actions