Rerank documents | EmpirioLabs AI Docs

Sort candidate documents by semantic relevance to a query. Returns each document’s original index plus a 0-1 relevance score (higher = more relevant). Score is relative to the request and not comparable across requests.

Built for RAG and search refinement: feed in the top-N hits from your vector store / BM25 / hybrid retriever, and the model returns a tighter, better-ordered shortlist.

Sort candidate `documents` by semantic relevance to a `query`. Returns each document's original index plus a 0-1 relevance score (higher = more relevant). Score is relative to the request and not comparable across requests. Built for RAG and search refinement: feed in the top-N hits from your vector store / BM25 / hybrid retriever, and the model returns a tighter, better-ordered shortlist.

Authentifizierung

AuthorizationBearer

Pass your EmpirioLabs API key as a bearer token. The Anthropic-style x-api-key header is also accepted on every endpoint.

Anfrage

This endpoint expects an object.

modelstringErforderlich

querystringErforderlich

Query text. Max 4,000 tokens.

documentslist of stringsErforderlich

Candidate documents to sort. Max 500 items, each up to 4,000 tokens.

top_nintegerOptional1-500

Number of top-ranked documents to return. Defaults to all.

instructstringOptional

Custom English instruction guiding the sort. Defaults to a Q&A retrieval policy. Pass "Retrieve semantically similar text." for similarity sorting.

return_documentsbooleanOptionalStandardwert ist false

When true, return the original document text alongside each result.

Antwort

Sorted relevance scores.

outputobject

usageobject

request_idstring

$	curl -X POST https://api.empiriolabs.ai/v1/reranks \
>	-H "Authorization: Bearer <token>" \
>	-H "Content-Type: application/json" \
>	-d '{
>	"model": "qwen3-rerank",
>	"query": "What is a rerank model?",
>	"documents": [
>	"Rerank models sort candidate documents by relevance.",
>	"Quantum computing is a cutting-edge field of computer science.",
>	"Pre-trained language models advanced rerank models."
>	]
>	}'

1	{
2	"output": {
3	"results": [
4	{
5	"index": 1,
6	"relevance_score": 1.1,
7	"document": {
8	"text": "string"
9	}
10	}
11	]
12	},
13	"usage": {
14	"prompt_tokens": 1,
15	"completion_tokens": 1,
16	"total_tokens": 1
17	},
18	"request_id": "string"
19	}