Actions13
- Agent Actions
- Datastore Actions
- Query Actions
- Reranker Actions
- LMUnit Actions
- Parser Actions
Reranker → Rerank documents
AI-generatedSummary
Rerank documents against a query using Contextual AI.
Inputs
- query (required) — The query to rerank documents against.
- documents (required) — Comma-separated list of document texts to rerank.
- instruction — Optional instruction for the reranker.
- model — Rerank model to use. Options: ctxl-rerank-v2-instruct-multilingual, ctxl-rerank-v2-instruct-multilingual-mini, ctxl-rerank-v1-instruct.
- topN — Number of top-ranked results to return. Leave 0 to return all results.
- metadata — Comma-separated metadata strings. Must match the number of documents if provided.
- authentication — Authentication method to use. Defaults to API Key.
Output shape
object
Returns the raw API response from the Contextual AI reranking endpoint containing ranked document results. Includes pairedItem mapping for n8n item tracking.