Alibaba Cloud Model Studio:Rerank de texte

Un modèle de rerank réévalue les documents issus d'une recherche initiale pour placer les résultats les plus pertinents en tête de liste.

Présentation des modèles

• Tokens d'entrée max. par élément : nombre maximal de tokens par requête ou document. Le dépassement de cette limite entraîne une troncature susceptible de réduire la précision du classement.
• Documents max. : nombre maximal de documents par requête. Pour qwen3-vl-rerank, cette limite varie selon le type de document (texte, image, vidéo ou mixte).
• Tokens d'entrée max. par requête : valeur calculée selon la formule Query Tokens × Number of documents + Total document tokens. Cette valeur ne doit pas excéder la limite par requête.

Limitations d'entrée

Prérequis

Obtenez une clé API et définissez-la comme variable d'environnement. Pour utiliser le SDK, installez le DashScope SDK.

HTTP

Remplacez {WorkspaceId} par votre ID d'espace de travail.

Cette section décrit l'API HTTP DashScope.

# This is the Singapore region URL. Replace WorkspaceId with your actual workspace ID. URLs differ by region.
curl --request POST \
  --url 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-rerank",
        "input": {
            "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?"
        },
        "parameters": {
            "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
    }
}'

{
    "output": {
        "results": [
            {
                "index": 0,
                "relevance_score": 0.9334521178273196
            },
            {
                "index": 2,
                "relevance_score": 0.34100082626411193
            }
        ]
    },
    "request_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"
    }

Utilisation du SDK

Exemple

Appelez l'API du modèle de rerank.

Les noms de paramètres du SDK correspondent à ceux de l'API HTTP, mais leur structure diffère. L'API HTTP utilise des objets imbriqués input et parameters , tandis que le SDK emploie une structure plate.

import dashscope
# China (Beijing) region. Replace {WorkspaceId} with your actual workspace ID. The configuration varies by region.
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()

Utilisez qwen3-vl-rerank pour un rerank multimodal avec une requête image.

import dashscope
from http import HTTPStatus
import json
# China (Beijing) region. Replace {WorkspaceId} with your actual workspace ID.
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()

Exemple de sortie

{
    "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
    }
}

Codes d'erreur

Si l'appel du modèle échoue et renvoie un message d'erreur, consultez Codes d'erreur pour résoudre le problème.