Aufwand für die Abfragelogik festlegen (Vorschau)

• Das neueste Azure.Search.Documents Vorschaupaket: dotnet add package Azure.Search.Documents --prerelease

• Für die schlüssellose Authentifizierung das Paket Azure.Identity: dotnet add package Azure.Identity

• Das neueste azure-search-documents Vorschaupaket: pip install --pre azure-search-documents

• Für die schlüssellose Authentifizierung das Paket azure-identity: pip install azure-identity

• Die Version 2026-08-01-preview der Search Service REST API.

• Fügen Sie für die schlüssellose Authentifizierung ein Microsoft Entra ID-Token in den Authorization Header jeder HTTP-Anforderung ein.

using Azure.Identity;
using Azure.Search.Documents.Indexes;
using Azure.Search.Documents.Indexes.Models;
using Azure.Search.Documents.KnowledgeBases.Models;

var endpoint = new Uri("<search-endpoint>");
var credential = new DefaultAzureCredential();
var knowledgeBaseName = "<knowledge-base-name>";

var indexClient = new SearchIndexClient(endpoint, credential);
var knowledgeBase = (
    await indexClient.GetKnowledgeBaseAsync(knowledgeBaseName)).Value;
knowledgeBase.RetrievalReasoningEffort =
    new KnowledgeRetrievalAutoReasoningEffort();
await indexClient.CreateOrUpdateKnowledgeBaseAsync(knowledgeBase);

Referenz:KnowledgeBase

Wenn Sie eine andere Ebene verwenden möchten, ersetzen Sie diese durch KnowledgeRetrievalAutoReasoningEffort , oder KnowledgeRetrievalLowReasoningEffortKnowledgeRetrievalMediumReasoningEffort.KnowledgeRetrievalMinimalReasoningEffort

from azure.identity import DefaultAzureCredential
from azure.search.documents.indexes import SearchIndexClient
from azure.search.documents.knowledgebases.models import (
    KnowledgeRetrievalAutoReasoningEffort,
)

endpoint = "<search-endpoint>"
credential = DefaultAzureCredential()
knowledge_base_name = "<knowledge-base-name>"

index_client = SearchIndexClient(endpoint, credential)
knowledge_base = index_client.get_knowledge_base(knowledge_base_name)
knowledge_base.retrieval_reasoning_effort = (
    KnowledgeRetrievalAutoReasoningEffort()
)
index_client.create_or_update_knowledge_base(knowledge_base)

Referenz:KnowledgeBase

Wenn Sie eine andere Ebene verwenden möchten, ersetzen Sie diese durch KnowledgeRetrievalAutoReasoningEffort , oder KnowledgeRetrievalLowReasoningEffortKnowledgeRetrievalMediumReasoningEffort.KnowledgeRetrievalMinimalReasoningEffort

@api-version = 2026-08-01-preview
@knowledge-base-url = {{search-endpoint}}/knowledgebases/{{knowledge-base-name}}

PUT {{knowledge-base-url}}?api-version={{api-version}}
Content-Type: application/json
Authorization: Bearer {{search-access-token}}

{
  "name": "{{knowledge-base-name}}",
  "knowledgeSources": [
    {
      "name": "{{knowledge-source-name}}"
    }
  ],
  "models": [
    {
      "kind": "azureOpenAI",
      "azureOpenAIParameters": {
        "resourceUri": "{{aoai-endpoint}}",
        "authIdentity": null,
        "deploymentId": "{{model-deployment-name}}",
        "modelName": "{{model-name}}"
      }
    }
  ],
  "retrievalReasoningEffort": {
    "kind": "auto"
  }
}

Referenz:Knowledge Basen – Erstellen oder Aktualisieren

Um eine andere Ebene zu verwenden, setzen Sie retrievalReasoningEffort.kind auf minimal, low oder medium.

using Azure.Identity;
using Azure.Search.Documents.KnowledgeBases;
using Azure.Search.Documents.KnowledgeBases.Models;

var endpoint = new Uri("<search-endpoint>");
var credential = new DefaultAzureCredential();
var knowledgeBaseName = "<knowledge-base-name>";

var kbClient = new KnowledgeBaseRetrievalClient(
    endpoint, knowledgeBaseName, credential);
var request = new KnowledgeBaseRetrievalRequest
{
    RetrievalReasoningEffort =
        new KnowledgeRetrievalLowReasoningEffort(),
    OutputMode = KnowledgeRetrievalOutputMode.AnswerSynthesis
};

request.Messages.Add(
    new KnowledgeBaseMessage(
        content: new[] {
            new KnowledgeBaseMessageTextContent("What is the return policy?")
        }
    ) { Role = "user" }
);

var result = await kbClient.RetrieveAsync(request);

Referenz:KnowledgeBaseRetrievalRequest

from azure.identity import DefaultAzureCredential
from azure.search.documents.knowledgebases import KnowledgeBaseRetrievalClient
from azure.search.documents.knowledgebases.models import (
    KnowledgeBaseMessage,
    KnowledgeBaseMessageTextContent,
    KnowledgeBaseRetrievalRequest,
    KnowledgeRetrievalOutputMode,
    KnowledgeRetrievalLowReasoningEffort,
)

endpoint = "<search-endpoint>"
credential = DefaultAzureCredential()
knowledge_base_name = "<knowledge-base-name>"

kb_client = KnowledgeBaseRetrievalClient(
    endpoint,
    credential,
    knowledge_base_name=knowledge_base_name,
)
request = KnowledgeBaseRetrievalRequest(
    messages=[
        KnowledgeBaseMessage(
            role="user",
            content=[
                KnowledgeBaseMessageTextContent(
                    text="What is the return policy?"
                )
            ],
        )
    ],
    retrieval_reasoning_effort=KnowledgeRetrievalLowReasoningEffort(),
    output_mode=KnowledgeRetrievalOutputMode.ANSWER_SYNTHESIS,
)

result = kb_client.retrieve(request)

Referenz:KnowledgeBaseRetrievalRequest

@api-version = 2026-08-01-preview
@retrieve-url = {{search-endpoint}}/knowledgebases/{{knowledge-base-name}}/retrieve

POST {{retrieve-url}}?api-version={{api-version}}
Content-Type: application/json
Authorization: Bearer {{search-access-token}}

{
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What is the return policy?"
        }
      ]
    }
  ],
  "retrievalReasoningEffort": {
    "kind": "low"
  },
  "outputMode": "answerSynthesis"
}

Reference:Knowledge Retrieval - Abrufen