Skip to main content
POST
Rerank
Дата обновления: 2026-06-06

Overview

Reorder a set of documents by semantic relevance to a query. Commonly used as the second-stage reranking step in RAG (Retrieval-Augmented Generation) pipelines.
Implemented following the SiliconFlow Rerank API format.

Supported Models

Request Parameters

string
обязательно
Reranking model name, e.g. gte-rerank-v2
string
обязательно
Query text
string[]
обязательно
List of documents to rerank
integer
Return the top N results. Defaults to returning all
boolean
по умолчанию:"true"
Whether to include the original document text in the response

Response Format

Code Examples

Typical RAG Pipeline

The number of input documents for reranking should not exceed 100. Too many documents will increase latency and cost.