Short answer: Drop the "Cohere → Create Embeddings" action anywhere in your workflow, map the inputs from upstream nodes, and publish.
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 |
{"texts": "{{trigger.texts}}","model": "{{trigger.model}}","input_type": "{{trigger.input_type}}"}
{"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.
Any of these apps can fire this action as part of a workflow.
Triggered by anything in the catalog. Free tier available. No credit card.