ActionDeepInfraUpdated May 2026

How do I generate embeddings via DeepInfra?

Short answer: Drop the "DeepInfra → DeepInfra Embeddings" action anywhere in your workflow, map the inputs from upstream nodes, and publish.

Use this action All 3 DeepInfra 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	options	Optional	Model. Options: BGE Large EN v1.5, BGE M3, Sentence Transformers MiniLM
Text input	string	Required	Text (required)

Sample request

{
  "model": "{{trigger.model}}",
  "input": "{{trigger.input}}"
}

Returns

{
  "data": [
    {
      "embedding": [
        0.012
      ]
    }
  ],
  "model": "BAAI/bge-large-en-v1.5",
  "usage": {
    "prompt_tokens": 5
  }
}

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

Triggered by

Apps that pair well as the trigger for DeepInfra Embeddings.

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

Google Sheets → DeepInfra

2 Google Sheets triggers

HubSpot → DeepInfra

18 HubSpot triggers

FAQ

Questions about DeepInfra Embeddings.

What does the DeepInfra Embeddings action do in DeepInfra?

Generates embeddings from DeepInfra-hosted models (BGE, sentence-transformers). For RAG pipeline vector generation on a budget-friendly OSS inference provider.

What inputs does DeepInfra Embeddings require?

Required: 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 DeepInfra 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 DeepInfra Embeddings support batch operations?

Yes. Run DeepInfra Embeddings inside a Loop node to process arrays. Tiny Command handles DeepInfra's rate limits automatically so you don't have to throttle manually.

More actions