Utilizar a síntese de resposta para respostas baseadas em citação no Pesquisa de IA do Azure  (versão de pré-visualização)

• O pacote de versão prévia Azure.Search.Documents mais recente: dotnet add package Azure.Search.Documents --prerelease

• Para autenticação sem chave, o Azure.Identity pacote: dotnet add package Azure.Identity

• O pacote de versão prévia azure-search-documents mais recente: pip install --pre azure-search-documents

• Para autenticação sem chave, o azure-identity pacote: pip install azure-identity

• A versão 2026-08-01-preview da API REST do Serviço de Pesquisa.

• Para autenticação sem chave, inclua um token Microsoft Entra ID no Authorization cabeçalho de cada solicitação HTTP.

Defina OutputMode como "answerSynthesis" na definição KnowledgeBase. Opcionalmente, defina AnswerInstructions para personalizar a saída da resposta. O exemplo a seguir instrui a base de dados de conhecimento a Use concise bulleted lists.

var aoaiParams = new AzureOpenAIVectorizerParameters
{
    ResourceUri = new Uri("<aoai-endpoint>"),
    DeploymentName = "<aoai-gpt-deployment>",
    ModelName = "<aoai-gpt-model>",
};

var knowledgeBase = new KnowledgeBase(
    name: "<knowledge-base-name>",
    knowledgeSources: new[] { new KnowledgeSourceReference("<knowledge-source-name>") })
{
    Models = { new KnowledgeBaseAzureOpenAIModel(aoaiParams) },
    OutputMode = "answerSynthesis",
    AnswerInstructions = "Use concise bulleted lists",
};

await indexClient.CreateOrUpdateKnowledgeBaseAsync(knowledgeBase);

Reference:SearchIndexClient, KnowledgeBase

Defina output_mode como "answerSynthesis" na definição KnowledgeBase. Opcionalmente, defina answer_instructions para personalizar a saída da resposta. O exemplo a seguir instrui a base de dados de conhecimento a Use concise bulleted lists.

from azure.search.documents.indexes import SearchIndexClient
from azure.search.documents.indexes.models import (
    AzureOpenAIVectorizerParameters,
    KnowledgeBase,
    KnowledgeBaseAzureOpenAIModel,
    KnowledgeSourceReference,
)

aoai_params = AzureOpenAIVectorizerParameters(
    resource_url="<aoai-endpoint>",
    deployment_name="<aoai-gpt-deployment>",
    model_name="<aoai-gpt-model>",
)

knowledge_base = KnowledgeBase(
    name="<knowledge-base-name>",
    models=[KnowledgeBaseAzureOpenAIModel(azure_open_ai_parameters=aoai_params)],
    knowledge_sources=[KnowledgeSourceReference(name="<knowledge-source-name>")],
    output_mode="answerSynthesis",
    answer_instructions="Use concise bulleted lists",
)

index_client = SearchIndexClient(endpoint=search_endpoint, credential=credential)
index_client.create_or_update_knowledge_base(knowledge_base)

Reference:SearchIndexClient, KnowledgeBase

Defina outputMode para "answerSynthesis" na definição da base de conhecimento. Opcionalmente, defina answerInstructions para personalizar a saída da resposta. O exemplo a seguir instrui a base de dados de conhecimento a Use concise bulleted lists.

### Enable answer synthesis in a knowledge base
PUT {{search-endpoint}}/knowledgebases/{{knowledge-base-name}}?api-version=2026-08-01-preview
Content-Type: application/json
Authorization: Bearer {{search-access-token}}

{
    "name": "{{knowledge-base-name}}",
    "knowledgeSources": [ ... // OMITTED FOR BREVITY ],
    "models": [ ... // OMITTED FOR BREVITY ],
    "outputMode": "answerSynthesis",
    "answerInstructions": "Use concise bulleted lists"
}

Referência:Base de Dados de Conhecimento – Criar ou Atualizar

Defina OutputMode para "answerSynthesis" em um KnowledgeBaseRetrievalRequest.

var client = new KnowledgeBaseRetrievalClient(
    endpoint: new Uri(searchEndpoint),
    knowledgeBaseName: knowledgeBaseName,
    credential: credential);

var request = new KnowledgeBaseRetrievalRequest();
request.Messages.Add(
    new KnowledgeBaseMessage(
        content: new[]
        {
            new KnowledgeBaseMessageTextContent("What is healthcare?")
        }) { Role = "user" });
request.OutputMode = "answerSynthesis";

var result = await client.RetrieveAsync(request);

Reference:KnowledgeBaseRetrievalClient, KnowledgeBaseRetrievalRequest

Defina output_mode para "answerSynthesis" em um KnowledgeBaseRetrievalRequest.

from azure.search.documents.knowledgebases import KnowledgeBaseRetrievalClient
from azure.search.documents.knowledgebases.models import (
    KnowledgeBaseMessage,
    KnowledgeBaseMessageTextContent,
    KnowledgeBaseRetrievalRequest,
)

agent_client = KnowledgeBaseRetrievalClient(
    endpoint=search_endpoint,
    credential=credential,
    knowledge_base_name=knowledge_base_name,
)

request = KnowledgeBaseRetrievalRequest(
    messages=[
        KnowledgeBaseMessage(
            role="user",
            content=[KnowledgeBaseMessageTextContent(text="What is healthcare?")],
        )
    ],
    output_mode="answerSynthesis",
)

result = agent_client.retrieve(retrieval_request=request)

Reference:KnowledgeBaseRetrievalClient, KnowledgeBaseRetrievalRequest

Defina outputMode para "answerSynthesis" em uma solicitação de recuperação.

### Enable answer synthesis in a retrieve request
POST {{search-endpoint}}/knowledgebases/{{knowledge-base-name}}/retrieve?api-version=2026-08-01-preview
Content-Type: application/json
Authorization: Bearer {{search-access-token}}

{
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "What is healthcare?"
                }
            ]
        }
    ],
    "outputMode": "answerSynthesis"
}

Referência:Recuperação de Conhecimento – Recuperar