Alibaba Cloud Model Studio:Text rerank

Model rerank memberikan skor ulang pada dokumen yang dikembalikan oleh pengambilan awal sehingga hasil yang paling relevan muncul di bagian atas.

Ikhtisar model

• Max input tokens per item: Token maksimum per kueri atau dokumen. Jika input satu kueri atau dokumen melebihi batas ini, API akan mengembalikan error HTTP 400 dan tidak memotong input.
• Max documents: Dokumen maksimum per permintaan. Untuk qwen3-vl-rerank, batasnya bervariasi berdasarkan jenis dokumen (teks, gambar, video, atau campuran).
• Max input tokens per request: Dihitung sebagai Query Tokens × Jumlah dokumen + Total token dokumen. Tidak boleh melebihi batas per permintaan.

Batasan input

Prasyarat

Dapatkan Kunci API dan tetapkan Kunci API sebagai Variabel lingkungan. Untuk menggunakan SDK: instal DashScope SDK.

HTTP

Setiap model menggunakan titik akhir yang berbeda:

• qwen3-rerank: POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-api/v1/reranks
• qwen3-vl-rerank / gte-rerank-v2: POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/rerank/text-rerank/text-rerank

Ganti {WorkspaceId} dengan workspace ID Anda yang sebenarnya.

Kedua API tersebut berbeda dalam struktur badan permintaan dan format respons. Lihat contoh permintaan dan respons untuk setiap model.

# Ini adalah URL wilayah Singapura. Ganti WorkspaceId dengan workspace ID Anda yang sebenarnya. URL berbeda-beda tergantung wilayah.
curl --request POST \
  --url https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/reranks \
  --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
        "model": "qwen3-rerank",
        "documents": [
                "Rerank models are widely used in search engines and recommendation systems. They sort candidate documents based on text relevance.",
                "Quantum computing is a cutting-edge field of computer science.",
                "The development of pre-trained language models has brought new advancements to rerank models."
        ],
        "query": "What is a rerank model?",
        "top_n": 2,
        "instruct": "Given a web search query, retrieve relevant passages that answer the query."
}'

curl --location 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/rerank/text-rerank/text-rerank' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "qwen3-vl-rerank",
    "input":{
         "query": {"text": "What is a rerank model?"},
         "documents": [
            {"text": "Rerank models are widely used in search engines and recommendation systems. They sort candidate documents based on text relevance."},
            {"image": "https://img.alicdn.com/imgextra/i3/O1CN01rdstgY1uiZWt8gqSL_!!6000000006071-0-tps-1970-356.jpg"},
            {"video": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250107/lbcemt/new+video.mp4"}
         ]
    },
    "parameters": {
        "return_documents": true,
        "top_n": 2,
        "fps": 1.0
    }
}'

curl --location 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/rerank/text-rerank/text-rerank' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "qwen3-vl-rerank",
    "input":{
         "query": {"image": "https://img.alicdn.com/imgextra/i3/O1CN01rdstgY1uiZWt8gqSL_!!6000000006071-0-tps-1970-356.jpg"},
         "documents": [
            {"text": "Text rerank models are widely used in search engines and recommendation systems to sort candidate captions based on text relevance."},
            {"image": "https://img.alicdn.com/imgextra/i3/O1CN01rdstgY1uiZWt8gqSL_!!6000000006071-0-tps-1970-356.jpg"},
            {"video": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250107/lbcemt/new+video.mp4"}
         ]
    },
    "parameters": {
        "return_documents": true,
        "top_n": 2,
        "fps": 1.0
    }
}'

curl --location 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/rerank/text-rerank/text-rerank' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "gte-rerank-v2",
    "input":{
         "query": "What is a rerank model?",
         "documents": [
         "Rerank models are widely used in search engines and recommendation systems. They sort candidate documents based on text relevance.",
         "Quantum computing is a cutting-edge field of computer science.",
         "The development of pre-trained language models has brought new advancements to rerank models."
         ]
    },
    "parameters": {
        "return_documents": true,
        "top_n": 2
    }
}'

{
    "object": "list",
    "results": [
        {
            "index": 0,
            "relevance_score": 0.9334521178273196
        },
        {
            "index": 2,
            "relevance_score": 0.34100082626411193
        }
    ],
    "model": "qwen3-rerank",
    "id": "85ba5752-1900-47d2-8896-23f99b13f6e1",
    "usage": {
        "total_tokens": 79
    }
}

{
    "output": {
        "results": [
            {
                "document": {
                    "text": "Rerank models are widely used in search engines and recommendation systems. They sort candidate documents based on text relevance."
                },
                "index": 0,
                "relevance_score": 0.9334521178273196
            },
            {
                "document": {
                    "text": "The development of pre-trained language models has brought new advancements to rerank models."
                },
                "index": 2,
                "relevance_score": 0.34100082626411193
            }
        ]
    },
    "usage": {
        "total_tokens": 79
    },
    "request_id": "85ba5752-1900-47d2-8896-23f99b13f6e1"
}

{
    "code":"InvalidApiKey",
    "message":"Invalid API-key provided.",
    "request_id":"fb53c4ec-1c12-4fc4-a580-cdb7c3261fc1"
}

Gunakan SDK

Contoh

Panggil API model rerank.

Nama parameter SDK sesuai dengan API HTTP, tetapi strukturnya berbeda. HTTP menggunakan objek input dan parameters bersarang; SDK menggunakan struktur datar.

import dashscope
# Wilayah Tiongkok (Beijing). Ganti {WorkspaceId} dengan workspace ID Anda yang sebenarnya. Konfigurasi bervariasi tergantung wilayah.
dashscope.base_http_api_url = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1"

def text_rerank():
    resp = dashscope.TextReRank.call(
        model="gte-rerank-v2",
        query="What is a rerank model?",
        documents=[
            "Rerank models are widely used in search engines and recommendation systems. They sort candidate documents based on text relevance.",
            "Quantum computing is a cutting-edge field of computer science.",
            "The development of pre-trained language models has brought new advancements to rerank models."
        ],
        top_n=2,
        return_documents=True
    )
    print(resp)

if __name__ == '__main__':
    text_rerank()

Gunakan qwen3-vl-rerank untuk penyusunan ulang multimodal dengan kueri gambar.

import dashscope
from http import HTTPStatus
import json
# Wilayah Tiongkok (Beijing). Ganti {WorkspaceId} dengan workspace ID Anda yang sebenarnya.
dashscope.base_http_api_url = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1"

def vl_rerank():
    resp = dashscope.TextReRank.call(
        model="qwen3-vl-rerank",
        query={"image": "https://img.alicdn.com/imgextra/i3/O1CN01rdstgY1uiZWt8gqSL_!!6000000006071-0-tps-1970-356.jpg"},
        documents=[
            {"text": "Rerank models are widely used in search engines and recommendation systems. They sort candidate documents based on text relevance."},
            {"image": "https://img.alicdn.com/imgextra/i3/O1CN01rdstgY1uiZWt8gqSL_!!6000000006071-0-tps-1970-356.jpg"},
            {"video": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250107/lbcemt/new+video.mp4"}
        ],
        top_n=2,
        return_documents=True
    )
    if resp.status_code == HTTPStatus.OK:
        print(json.dumps(resp, default=str, ensure_ascii=False, indent=4))
    else:
        print(resp)

if __name__ == '__main__':
    vl_rerank()

Contoh output

{
    "status_code": 200,
    "request_id": "4b0805c0-6b36-490d-8bc1-4365f4c89905",
    "code": "",
    "message": "",
    "output": {
        "results": [
            {
                "index": 0,
                "relevance_score": 0.9334521178273196,
                "document": {
                    "text": "Rerank models are widely used in search engines and recommendation systems. They sort candidate documents based on text relevance."
                }
            },
            {
                "index": 2,
                "relevance_score": 0.34100082626411193,
                "document": {
                    "text": "The development of pre-trained language models has brought new advancements to rerank models."
                }
            }
        ]
    },
    "usage": {
        "total_tokens": 79
    }
}

Kode error

Jika pemanggilan model gagal dan mengembalikan pesan error, lihat Kode error untuk penyelesaian.