重排序

POST

/v1/rerank

给定一个提示，该模型将返回一个或多个预测的完成，并且还可以返回每个位置的替代标记的概率。

为提供的提示和参数创建完成

官方文档：https://docs.siliconflow.cn/cn/api-reference/rerank/create-rerank

Request

Authorization

Provide your bearer token in the

Authorization

header when making requests to protected resources.

Example:

Authorization: Bearer ********************

Header Params

Body Params application/json

Example

 {
    "model": "qwen3-rerank",
    "documents": [
        "文本排序模型广泛用于搜索引擎 and 推荐系统中，它们根据文本相关性对候选文本进行排序",
        "量子计算是计算科学的一个前沿领域",
        "预训练语言模型的发展给文本排序模型带来了新的进展"
    ],
    "query": "什么是文本排序模型",
    "top_n": 2,
    "instruct": "Given a web search query, retrieve relevant passages that answer the query."
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location '/v1/rerank' \
--header 'Accept: application/json' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
    "model": "qwen3-rerank",
    "documents": [
        "文本排序模型广泛用于搜索引擎 and 推荐系统中，它们根据文本相关性对候选文本进行排序",
        "量子计算是计算科学的一个前沿领域",
        "预训练语言模型的发展给文本排序模型带来了新的进展"
    ],
    "query": "什么是文本排序模型",
    "top_n": 2,
    "instruct": "Given a web search query, retrieve relevant passages that answer the query."
}'

Responses

🟢200OK

application/json

Bodyapplication/json

Examples

OK成功示例

{
    "id": "chatcmpl-123",
    "object": "chat.completion",
    "created": 1677652288,
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "\n\nHello there, how may I assist you today?"
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 9,
        "completion_tokens": 12,
        "total_tokens": 21
    }
}

Modified at 2026-03-30 11:39:32

python 连续对话

Callback协议