Jina Rerank: Jina AI action

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: Jina Reranker v2 Multilingual
Query query	string	Required	Query (required)
Documents documents	array	Required	Documents (array)
Top N top_n	string	Optional	5

Sample request

{
  "model": "{{trigger.model}}",
  "query": "{{trigger.query}}",
  "documents": "{{trigger.documents}}",
  "top_n": "5"
}

Returns

{
  "results": [
    {
      "index": 0,
      "document": {
        "text": "..."
      },
      "relevance_score": 0.95
    }
  ]
}

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

FAQ

Questions about Jina Rerank.

What does the Jina Rerank action do in Jina AI?

Second-stage reranker for RAG — takes a query and candidate documents, returns them re-scored by relevance using the cross-encoder. Significantly improves RAG answer quality vs single-stage retrieval.

What inputs does Jina Rerank require?

Required: Query, Documents. 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 Jina AI 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 Jina Rerank support batch operations?

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

More actions

Other Jina AI actions.

Action

Jina Embeddings

Generates embeddings using jina-embeddings-v3 — 1024d multilingual embeddings, strong on the MTEB leaderboard. For RAG vector generation in workflows that need solid retrieval accuracy across many languages.

Action

Jina Reader (URL → LLM-ready)

Fetches any URL and returns cleaned-text Markdown ready to drop into an LLM prompt. Handles JS-rendered pages, strips ads/nav, preserves structure. The distinctive Jina feature.

How do I rerank documents with Jina?

The fields this action accepts.

Apps that pair well as the trigger for Jina Rerank.

Questions about Jina Rerank.

Other Jina AI actions.

Send jina rerank from your workflows.