ActionCohereUpdated May 2026

How do I rerank RAG candidates with Cohere?

Short answer: Drop the "Cohere → Rerank" 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
Query query	string	Required	The search query to rank documents against
Documents (JSON array) documents	array	Required	Array of text strings to rerank
Model model	options	Optional	Model. Options: Rerank v3.5 (latest), Rerank English v3, Rerank Multilingual v3
Top N top_n	string	Optional	Number of most relevant documents to return

Sample request

{
  "query": "e.g. What is the refund policy?",
  "documents": "{{trigger.documents}}",
  "model": "{{trigger.model}}",
  "top_n": "e.g. 3"
}

Returns

{
  "results": [
    {
      "index": 2,
      "document": {
        "text": "Returns accepted within 30 days..."
      },
      "relevance_score": 0.98
    },
    {
      "index": 0,
      "document": {
        "text": "Our refund policy allows..."
      },
      "relevance_score": 0.85
    }
  ]
}

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

Triggered by

Apps that pair well as the trigger for Rerank.

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 Rerank.

What does the Rerank action do in Cohere?

Reranks a list of documents by relevance to a query using Cohere's Rerank model. Essential last-mile step in any serious RAG pipeline; meaningfully lifts precision over vector-only retrieval.

What inputs does Rerank require?

Required: Query, Documents (JSON array). 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 Rerank support batch operations?

Yes. Run Rerank 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