ActionCohereUpdated May 2026

How do I create text embeddings with Cohere?

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

Use this action All 4 Cohere 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
Texts (JSON array) texts	array	Required	Array of strings to embed
Model model	options	Optional	Model. Options: English v3, Multilingual v3, English Light v3
Input Type input_type	options	Required	Input Type. Options: Search Document (for indexing), Search Query (for querying), Classification, Clustering

Sample request

{
  "texts": "{{trigger.texts}}",
  "model": "{{trigger.model}}",
  "input_type": "{{trigger.input_type}}"
}

Returns

{
  "id": "abc",
  "meta": {
    "api_version": {
      "version": "1"
    }
  },
  "embeddings": [
    [
      0.1,
      0.2,
      0.3
    ]
  ]
}

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

Triggered by

Apps that pair well as the trigger for Create Embeddings.

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

Google Sheets → Cohere

2 Google Sheets triggers

HubSpot → Cohere

18 HubSpot triggers

FAQ

Questions about Create Embeddings.

What does the Create Embeddings action do in Cohere?

Generates vector embeddings for text using Cohere's embed-v3 model. Supports input_type (search_document, search_query, classification, clustering), which materially improves retrieval quality, so set it correctly.

What inputs does Create Embeddings require?

Required: Texts (JSON array), Input Type. 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 Cohere 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 Create Embeddings support batch operations?

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

More actions