你当前正在访问 Microsoft Azure Global Edition 技术文档网站。如果需要访问由世纪互联运营的 Microsoft Azure 中国技术文档网站，请访问 https://docs.azure.cn。

创建搜索索引知识源

注意

Azure AI 搜索可通过Azure门户、REST API 和Azure SDK获取。它也是 Foundry IQ 的基础；Foundry IQ 是一个托管式知识层，可将企业内容转化为供 Microsoft Foundry 门户中的智能体使用的、可复用且具备权限感知能力的知识库。

Important

标记为“预览”的特性、功能或属性不受服务级别协议 (SLA) 保障，不建议用于生产工作负载，并且在正式发布之前可能会更改或受到限制。 Azure AI 搜索预览条款适用于所有预览功能，无论是独立功能还是正式版功能的一部分。

search 索引知识源将现有的Azure AI 搜索索引（包括索引文本和向量）连接到代理检索管道。知识库是在运行时查询知识库时独立创建的、在知识库中引用的，并用作基础数据。

使用支持

Azure 门户	Microsoft Foundry 门户	.NET SDK	Python SDK	Java SDK	JavaScript SDK	REST API
✔️	✔️	✔️	✔️	✔️	✔️	✔️

先决条件

在任意提供代理检索功能的区域中提供的 Azure AI 搜索服务。
包含具有语义配置的纯文本或矢量内容的搜索索引。查看用于代理检索的索引条件。索引必须与知识库位于同一搜索服务上。
创建知识源的权限。使用分配给用户帐户的搜索服务参与者角色（建议）或使用管理员 API 密钥配置无密钥身份验证。

所需 Azure.Search.Documents 软件包：
- 对于 2026-08-01-preview 功能，最新的预览包：dotnet add package Azure.Search.Documents --prerelease
- 对于 2026-04-01 功能，最新稳定版软件包：dotnet add package Azure.Search.Documents
对于无密钥身份验证，请使用 Azure.Identity 软件包：dotnet add package Azure.Identity

所需 azure-search-documents 软件包：
- 对于 2026-08-01-preview 功能，最新的预览包：pip install --pre azure-search-documents
- 对于 2026-04-01 功能，最新稳定版软件包：pip install azure-search-documents
对于无密钥身份验证，请使用 azure-identity 软件包：pip install azure-identity

所需的搜索服务 REST API 版本：
- 对于预览功能： 2026-08-01-preview
- 对于正式发布的功能：2026-04-01
对于无密钥身份验证，请在每个 HTTP 请求的标头中包含AuthorizationMicrosoft Entra ID令牌。

Limitations

智能体检索不会使检索请求遵循底层索引的评分配置文件，包括 defaultScoringProfile。检索响应不呈现 @search.rerankerBoostedScore。

检查现有知识源

知识源是顶级可重用对象。了解现有知识源有助于重复使用或命名新对象。

运行以下代码，按名称和类型列出知识源。

// List knowledge sources by name and type
using Azure.Search.Documents.Indexes;

var indexClient = new SearchIndexClient(new Uri(searchEndpoint), credential);
var knowledgeSources = indexClient.GetKnowledgeSourcesAsync();

Console.WriteLine("Knowledge Sources:");

await foreach (var ks in knowledgeSources)
{
    Console.WriteLine($"  Name: {ks.Name}, Type: {ks.GetType().Name}");
}

Reference：SearchIndexClient

# List knowledge sources by name and type
from azure.core.credentials import AzureKeyCredential
from azure.search.documents.indexes import SearchIndexClient

index_client = SearchIndexClient(endpoint = "search_url", credential = AzureKeyCredential("api_key"))

for ks in index_client.list_knowledge_sources():
    print(f"  - {ks.name} ({ks.kind})")

Reference：SearchIndexClient

### List knowledge sources by name and type
GET {{search-url}}/knowledgesources?api-version={{api-version}}&$select=name,kind
Authorization: Bearer {{token}}

参考：知识源 - 列表

还可以按名称返回单个知识源以查看其 JSON 定义。

using Azure.Search.Documents.Indexes;
using System.Text.Json;

var indexClient = new SearchIndexClient(new Uri(searchEndpoint), credential);

// Specify the knowledge source name to retrieve
string ksNameToGet = "earth-knowledge-source";

// Get its definition
var knowledgeSourceResponse = await indexClient.GetKnowledgeSourceAsync(ksNameToGet);
var ks = knowledgeSourceResponse.Value;

// Serialize to JSON for display
var jsonOptions = new JsonSerializerOptions 
{ 
    WriteIndented = true,
    DefaultIgnoreCondition = System.Text.Json.Serialization.JsonIgnoreCondition.Never
};
Console.WriteLine(JsonSerializer.Serialize(ks, ks.GetType(), jsonOptions));

Reference：SearchIndexClient

# Get a knowledge source definition
from azure.core.credentials import AzureKeyCredential
from azure.search.documents.indexes import SearchIndexClient
import json

index_client = SearchIndexClient(endpoint = "search_url", credential = AzureKeyCredential("api_key"))

ks = index_client.get_knowledge_source("knowledge_source_name")
print(json.dumps(ks.as_dict(), indent = 2))

Reference：SearchIndexClient

### Get a knowledge source definition
GET {{search-url}}/knowledgesources/{{knowledge-source-name}}?api-version={{api-version}}
Authorization: Bearer {{token}}

参考：知识源 - 获取

以下 JSON 是搜索索引知识源的示例响应。请注意，知识源指定单个索引名称以及要包含在查询中的索引中的字段。

{
  "name": "my-search-index-ks",
  "kind": "searchIndex",
  "description": "A sample search index knowledge source.",
  "encryptionKey": null,
  "searchIndexParameters": {
    "searchIndexName": "my-search-index",
    "semanticConfigurationName": null,
    "sourceDataFields": [],
    "searchFields": []
  }
}

创建知识源

运行以下代码以创建搜索索引知识源。

注意

从 2026-05-01-preview API 版本开始， semanticConfigurationName 对于搜索索引知识源是可选的。早期 API 版本仍需要 semanticConfigurationName。如果你的知识源需要同时支持较旧的和更新的 API 版本，请继续指定 semanticConfigurationName。

2026-08-01-preview
2026-04-01

// Create a search index knowledge source
using Azure.Search.Documents.Indexes;
using Azure.Search.Documents.Indexes.Models;
using Azure.Identity;

var indexClient = new SearchIndexClient(new Uri(searchEndpoint), new DefaultAzureCredential());

var indexKnowledgeSource = new SearchIndexKnowledgeSource(
    name: knowledgeSourceName,
    searchIndexParameters: new SearchIndexKnowledgeSourceParameters(searchIndexName: indexName)
    {
        SearchFields = { new SearchIndexFieldReference(name: "page_chunk") },
        SourceDataFields = { new SearchIndexFieldReference(name: "id"), new SearchIndexFieldReference(name: "page_chunk"), new SearchIndexFieldReference(name: "page_number") }
    }
);

await indexClient.CreateOrUpdateKnowledgeSourceAsync(indexKnowledgeSource);
Console.WriteLine($"Knowledge source '{knowledgeSourceName}' created or updated successfully.");

Reference：SearchIndexClient、 SearchIndexKnowledgeSource

// Create a search index knowledge source
using Azure.Search.Documents.Indexes;
using Azure.Search.Documents.Indexes.Models;
using Azure.Identity;

var indexClient = new SearchIndexClient(new Uri(searchEndpoint), new DefaultAzureCredential());

var indexKnowledgeSource = new SearchIndexKnowledgeSource(
    name: knowledgeSourceName,
    searchIndexParameters: new SearchIndexKnowledgeSourceParameters(searchIndexName: indexName)
    {
        SemanticConfigurationName = "semantic_config",
        SearchFields = { new SearchIndexFieldReference(name: "page_chunk") },
        SourceDataFields = { new SearchIndexFieldReference(name: "id"), new SearchIndexFieldReference(name: "page_chunk"), new SearchIndexFieldReference(name: "page_number") }
    }
);

await indexClient.CreateOrUpdateKnowledgeSourceAsync(indexKnowledgeSource);
Console.WriteLine($"Knowledge source '{knowledgeSourceName}' created or updated successfully.");

Reference：SearchIndexClient、 SearchIndexKnowledgeSource

2026-08-01-preview
2026-04-01

# Create a search index knowledge source
from azure.identity import DefaultAzureCredential
from azure.search.documents.indexes import SearchIndexClient
from azure.search.documents.indexes.models import SearchIndexKnowledgeSource, SearchIndexKnowledgeSourceParameters, SearchIndexFieldReference

index_client = SearchIndexClient(endpoint = "<search-endpoint>", credential = DefaultAzureCredential())

knowledge_source = SearchIndexKnowledgeSource(
    name = "my-search-index-ks",
    description= "This knowledge source pulls from an existing index designed for agentic retrieval.",
    encryption_key = None,
    search_index_parameters = SearchIndexKnowledgeSourceParameters(
        search_index_name = "search_index_name",
        source_data_fields = [
            SearchIndexFieldReference(name="description"),
            SearchIndexFieldReference(name="category"),
        ],
        search_fields = [
            SearchIndexFieldReference(name="id")
        ],
    )
)

index_client.create_or_update_knowledge_source(knowledge_source)
print(f"Knowledge source '{knowledge_source.name}' created or updated successfully.")

Reference：SearchIndexClient

# Create a search index knowledge source
from azure.identity import DefaultAzureCredential
from azure.search.documents.indexes import SearchIndexClient
from azure.search.documents.indexes.models import SearchIndexKnowledgeSource, SearchIndexKnowledgeSourceParameters, SearchIndexFieldReference

index_client = SearchIndexClient(endpoint = "<search-endpoint>", credential = DefaultAzureCredential())

knowledge_source = SearchIndexKnowledgeSource(
    name = "my-search-index-ks",
    description= "This knowledge source pulls from an existing index designed for agentic retrieval.",
    encryption_key = None,
    search_index_parameters = SearchIndexKnowledgeSourceParameters(
        search_index_name = "search_index_name",
        semantic_configuration_name = "semantic_configuration_name",
        source_data_fields = [
            SearchIndexFieldReference(name="description"),
            SearchIndexFieldReference(name="category"),
        ],
        search_fields = [
            SearchIndexFieldReference(name="id")
        ],
    )
)

index_client.create_or_update_knowledge_source(knowledge_source)
print(f"Knowledge source '{knowledge_source.name}' created or updated successfully.")

Reference：SearchIndexClient

2026-08-01-preview
2026-04-01

### Create a search index knowledge source
PUT {{search-endpoint}}/knowledgesources/my-search-index-ks?api-version=2026-08-01-preview
Authorization: Bearer {{search-access-token}}
Content-Type: application/json

{
    "name": "my-search-index-ks",
    "kind": "searchIndex",
    "description": "This knowledge source pulls from an existing index designed for agentic retrieval.",
    "encryptionKey": null,
    "searchIndexParameters": {
        "searchIndexName": "<index-name>",
        "sourceDataFields": [
          { "name": "description" },
          { "name": "category" }
        ]
    }
}

参考：知识源 - 创建或更新

### Create a search index knowledge source
PUT {{search-endpoint}}/knowledgesources/my-search-index-ks?api-version=2026-04-01
Authorization: Bearer {{search-access-token}}
Content-Type: application/json

{
    "name": "my-search-index-ks",
    "kind": "searchIndex",
    "description": "This knowledge source pulls from an existing index designed for agentic retrieval.",
    "encryptionKey": null,
    "searchIndexParameters": {
        "searchIndexName": "<index-name>",
        "semanticConfigurationName": "my-semantic-config",
        "sourceDataFields": [
          { "name": "description" },
          { "name": "category" }
        ]
    }
}

参考：知识源 - 创建或更新

在知识库上保留基本筛选器（预览版）

从 2026-05-01-preview API 版本开始，搜索索引知识源可以通过属性保留默认筛选器 baseFilter 。如果希望同一筛选表达式适用于使用该知识源的每个检索请求，请使用 baseFilter，这样调用方就不必在每次调用时重复指定该筛选器。

以下示例将基本筛选器存储在搜索索引知识库上。

var knowledgeSource = new SearchIndexKnowledgeSource(
    name: "public-docs-ks",
    searchIndexParameters: new SearchIndexKnowledgeSourceParameters(searchIndexName: "public-docs-index")
    {
        BaseFilter = "isPublished eq true and accessScope eq 'public'"
    }
);

await indexClient.CreateOrUpdateKnowledgeSourceAsync(knowledgeSource);

Reference：SearchIndexKnowledgeSourceParameters

knowledge_source = SearchIndexKnowledgeSource(
    name="public-docs-ks",
    search_index_parameters=SearchIndexKnowledgeSourceParameters(
        search_index_name="public-docs-index",
        base_filter="isPublished eq true and accessScope eq 'public'",
    ),
)

index_client.create_or_update_knowledge_source(knowledge_source)

Reference：SearchIndexKnowledgeSourceParameters

PUT {{search-endpoint}}/knowledgesources/public-docs-ks?api-version=2026-08-01-preview
Content-Type: application/json
Authorization: Bearer {{search-access-token}}

{
  "name": "public-docs-ks",
  "kind": "searchIndex",
  "searchIndexParameters": {
    "searchIndexName": "public-docs-index",
    "baseFilter": "isPublished eq true and accessScope eq 'public'"
  }
}

参考：知识源 - 创建或更新

在检索时， knowledgeSourceParams.filterAddOn 向存储的基本筛选器添加特定于请求的约束：

var retrievalRequest = new KnowledgeBaseRetrievalRequest();
retrievalRequest.KnowledgeSourceParams.Add(
    new SearchIndexKnowledgeSourceParams("public-docs-ks")
    {
        FilterAddOn = "category eq 'Benefits'"
    }
);

request = KnowledgeBaseRetrievalRequest(
    knowledge_source_params=[
        SearchIndexKnowledgeSourceParams(
            knowledge_source_name="public-docs-ks",
            filter_add_on="category eq 'Benefits'",
        ),
    ],
)

{
  "knowledgeSourceParams": [
    {
      "knowledgeSourceName": "public-docs-ks",
      "kind": "searchIndex",
      "filterAddOn": "category eq 'Benefits'"
    }
  ]
}

有效筛选器组合为：

baseFilter AND filterAddOn

由于这些筛选器是通过 AND 组合的，filterAddOn 只能进一步缩小持久保存的基础筛选器。它不能取代或扩大它。

配置查询提示（预览版）

从 2026-08-01-preview API 版本开始，查询提示将指导查询规划模型从用户请求生成筛选器和排名提升。将默认提示信息存储在 searchIndexParameters.queryHints 中，其中可同时包含筛选器和权重提升。

以下示例在针对 product-docs-index 的知识源上存储了一个筛选器提示和一个 fieldValue 增强，其中包含一个可按 productFamily 筛选的字段和一个可按 language 搜索的字段。

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

var endpoint = new Uri("<search-endpoint>");
var indexClient = new SearchIndexClient(
    endpoint,
    new DefaultAzureCredential());

var queryHints = new SearchIndexKnowledgeSourceQueryHints();
queryHints.Filters.Add(
    new SearchIndexKnowledgeSourceFilterHint(
        "productFamily",
        ["Model-X100", "Model-X200"])
    {
        FilterInstructions =
            "Filter only when the user names a model."
    });

var languageBoost =
    new SearchIndexKnowledgeSourceFieldValueBoost(
        "language",
        2.0);
languageBoost.FieldValues.Add("en-US");
languageBoost.FieldValues.Add("ja-JP");
languageBoost.BoostInstructions =
    "Prefer the language requested by the user.";
queryHints.Boosts.Add(languageBoost);

var knowledgeSource = new SearchIndexKnowledgeSource(
    "product-docs-ks",
    new SearchIndexKnowledgeSourceParameters(
        "product-docs-index")
    {
        QueryHints = queryHints
    });

await indexClient.CreateOrUpdateKnowledgeSourceAsync(
    knowledgeSource);

Reference：SearchIndexKnowledgeSourceParameters

from azure.identity import DefaultAzureCredential
from azure.search.documents.indexes import SearchIndexClient
from azure.search.documents.indexes.models import (
    SearchIndexKnowledgeSource,
    SearchIndexKnowledgeSourceFieldValueBoost,
    SearchIndexKnowledgeSourceFilterHint,
    SearchIndexKnowledgeSourceParameters,
    SearchIndexKnowledgeSourceQueryHints,
)

endpoint = "<search-endpoint>"
index_client = SearchIndexClient(
    endpoint=endpoint,
    credential=DefaultAzureCredential(),
)

query_hints = SearchIndexKnowledgeSourceQueryHints(
    filters=[
        SearchIndexKnowledgeSourceFilterHint(
            field="productFamily",
            field_values=["Model-X100", "Model-X200"],
            filter_instructions=(
                "Filter only when the user names a model."
            ),
        )
    ],
    boosts=[
        SearchIndexKnowledgeSourceFieldValueBoost(
            field="language",
            field_values=["en-US", "ja-JP"],
            boost=2.0,
            boost_instructions=(
                "Prefer the language requested by the user."
            ),
        )
    ],
)

knowledge_source = SearchIndexKnowledgeSource(
    name="product-docs-ks",
    search_index_parameters=SearchIndexKnowledgeSourceParameters(
        search_index_name="product-docs-index",
        query_hints=query_hints,
    ),
)

index_client.create_or_update_knowledge_source(knowledge_source)

Reference：SearchIndexKnowledgeSourceParameters

PUT {{search-endpoint}}/knowledgesources('product-docs-ks')?api-version=2026-08-01-preview
Content-Type: application/json
Authorization: Bearer {{search-access-token}}

{
  "name": "product-docs-ks",
  "kind": "searchIndex",
  "searchIndexParameters": {
    "searchIndexName": "product-docs-index",
    "queryHints": {
      "filters": [{
        "field": "productFamily",
        "fieldValues": ["Model-X100", "Model-X200"],
        "filterInstructions": "Filter only when the user names a model."
      }],
      "boosts": [{
        "kind": "fieldValue",
        "field": "language",
        "fieldValues": ["en-US", "ja-JP"],
        "boost": 2.0,
        "boostInstructions": "Prefer the language requested by the user."
      }]
    }
  }
}

参考：知识源 - 创建或更新

根据以下要求配置每个提示：

Hint	字段要求	`fieldValues` 行为	集合限制
筛选器	`field` 必须标识可筛选索引字段。	必填。列出所有允许值。如果请求不映射到列出的值，则指示规划器不筛选该字段。	包含唯一字段的最多五个提示。每个值最多可包含 128 个字符，一个提示中的所有值最多可包含 2,048 个字符。
`fieldValue` 提升	`field` 必须标识使用语言、标准或默认分析器的可搜索字段。	可选示例。如果省略它们，请使用 `boostInstructions` 说明要从请求中选择的值。	包含唯一字段的最多五个提示。每个提示最多可以包含 20 个值，每个值 128 个字符，组合 1,024 个字符。
`multiWordExpression` 提升	省略 `field`。索引必须至少包含一个使用语言、标准或默认分析器的可搜索字段。	特定领域短语的可选示例。	一个提示。它最多可以包含 20 个值，每个值包含 128 个字符，组合了 1,024 个字符。

对于任一提升类型， boost 是必需的，并且必须是大于 1.0的有限数。较高的值使匹配文档在排名中具有更大的影响，而无需排除其他文档。将每个可选 filterInstructions 或 boostInstructions 值限制为 1,024 个字符。

对于无法用单个词语体现含义的领域特定短语，请使用 multiWordExpression 提升。在 fieldValues 中提供示例短语，或者省略这些短语，并让 boostInstructions 和用户的请求来指导短语的选择：

{
  "boosts": [{
    "kind": "multiWordExpression",
    "fieldValues": ["deferred tax", "wash sale"],
    "boost": 3.0,
    "boostInstructions": "Boost domain terms used as complete phrases."
  }]
}

设计查询提示时，请记住以下行为：

提示是按尽力而为原则提供的，因此模型可能不会为每个请求都生成筛选器或提升。对于所需的约束（如授权边界），请改用文档级访问控制或确定性筛选器。
提示需要模型驱动的查询规划，因此当检索推理投入低于 minimal 时，不会应用这些提示。在其他工作级别，当存储 queryHints 的对象包含筛选器时，GPT-4o 或 GPT-4.1 系列模型返回 HTTP 400。服务会在应用 queryHintOverrides 之前检查已存储的筛选器，因此，空覆盖项或仅包含提升设置的覆盖项都不会绕过此验证。单独存储和fieldValuemultiWordExpression提升不会触发验证。
生成的筛选器通过使用与和结合。生成的 boost 在保留原始词项的同时，使用完整的 Lucene 语法重写查询。
查询提示以索引值为依据。它们不配置分析器或启用语言检测。 language这些示例中的值是普通索引元数据。

若要为单个检索请求覆盖已存储的查询提示，并验证生成的筛选器或提升设置，请参阅在查询时覆盖已存储的查询提示（预览版）。

分配给知识库

如果对知识源感到满意，请将其添加到知识库。

查询知识库

配置知识库后，调用检索操作或 MCP 终结点以查询知识源。

删除知识源

在删除知识库之前，必须删除引用它的任何知识库或更新知识库定义以删除引用。对于生成索引和索引器管道的知识源，也会删除所有 生成的对象 。但是，如果使用现有索引创建知识源，则不会删除索引。

如果尝试删除正在使用的知识源，该操作将失败并返回受影响的知识库列表。

删除知识源：

获取搜索服务上所有知识库的列表。

using Azure.Search.Documents.Indexes;

var indexClient = new SearchIndexClient(new Uri(searchEndpoint), credential);
var knowledgeBases = indexClient.GetKnowledgeBasesAsync();

Console.WriteLine("Knowledge Bases:");

await foreach (var kb in knowledgeBases)
{
    Console.WriteLine($"  - {kb.Name}");
}

Reference：SearchIndexClient

示例响应可能如下所示：

 {
     "@odata.context": "https://my-search-service.search.windows.net/$metadata#knowledgebases(name)",
     "value": [
     {
         "name": "my-kb"
     },
     {
         "name": "my-kb-2"
     }
     ]
 }

获取单个知识库定义以检查知识源引用。

using Azure.Search.Documents.Indexes;
using System.Text.Json;

var indexClient = new SearchIndexClient(new Uri(searchEndpoint), credential);

// Specify the knowledge base name to retrieve
string kbNameToGet = "earth-knowledge-base";

// Get a specific knowledge base definition
var knowledgeBaseResponse = await indexClient.GetKnowledgeBaseAsync(kbNameToGet);
var kb = knowledgeBaseResponse.Value;

// Serialize to JSON for display
string json = JsonSerializer.Serialize(kb, new JsonSerializerOptions { WriteIndented = true });
Console.WriteLine(json);

Reference：SearchIndexClient

示例响应可能如下所示：

 {
   "Name": "earth-knowledge-base",
   "KnowledgeSources": [
     {
       "Name": "earth-knowledge-source"
     }
   ],
   "Models": [
     {}
   ],
   "RetrievalReasoningEffort": {},
   "OutputMode": {},
   "ETag": "\u00220x8DE278629D782B3\u0022",
   "EncryptionKey": null,
   "Description": null,
   "RetrievalInstructions": null,
   "AnswerInstructions": null
 }

删除知识库，或者如果有多个知识库，请更新知识库以删除源。此示例显示删除。

using Azure.Search.Documents.Indexes;
var indexClient = new SearchIndexClient(new Uri(searchEndpoint), credential);

await indexClient.DeleteKnowledgeBaseAsync(knowledgeBaseName);
System.Console.WriteLine($"Knowledge base '{knowledgeBaseName}' deleted successfully.");

Reference：SearchIndexClient

删除知识源。

await indexClient.DeleteKnowledgeSourceAsync(knowledgeSourceName);
System.Console.WriteLine($"Knowledge source '{knowledgeSourceName}' deleted successfully.");

Reference：SearchIndexClient

获取搜索服务上所有知识库的列表。

# Get knowledge bases
from azure.core.credentials import AzureKeyCredential
from azure.search.documents.indexes import SearchIndexClient

index_client = SearchIndexClient(endpoint = "search_url", credential = AzureKeyCredential("api_key"))

print("Knowledge Bases:")
for kb in index_client.list_knowledge_bases():
    print(f"  - {kb.name}")

Reference：SearchIndexClient

示例响应可能如下所示：

 {
     "@odata.context": "https://my-search-service.search.windows.net/$metadata#knowledgebases(name)",
     "value": [
     {
         "name": "my-kb"
     },
     {
         "name": "my-kb-2"
     }
     ]
 }

获取单个知识库定义以检查知识源引用。

# Get a knowledge base definition
from azure.core.credentials import AzureKeyCredential
from azure.search.documents.indexes import SearchIndexClient

index_client = SearchIndexClient(endpoint = "search_url", credential = AzureKeyCredential("api_key"))
kb = index_client.get_knowledge_base("knowledge_base_name")
print(kb)

Reference：SearchIndexClient

示例响应可能如下所示：

 {
   "name": "my-kb",
   "description": null,
   "retrievalInstructions": null,
   "answerInstructions": null,
   "outputMode": null,
   "knowledgeSources": [
     {
       "name": "my-blob-ks"
     }
   ],
   "models": [],
   "encryptionKey": null,
   "retrievalReasoningEffort": {
     "kind": "low"
   }
 }

删除知识库，或者如果有多个知识库，请更新知识库以删除源。此示例显示删除。

# Delete a knowledge base
from azure.core.credentials import AzureKeyCredential 
from azure.search.documents.indexes import SearchIndexClient

index_client = SearchIndexClient(endpoint = "search_url", credential = AzureKeyCredential("api_key"))
index_client.delete_knowledge_base("knowledge_base_name")
print(f"Knowledge base deleted successfully.")

Reference：SearchIndexClient

删除知识源。

# Delete a knowledge source
from azure.core.credentials import AzureKeyCredential 
from azure.search.documents.indexes import SearchIndexClient

index_client = SearchIndexClient(endpoint = "search_url", credential = AzureKeyCredential("api_key"))
index_client.delete_knowledge_source("knowledge_source_name")
print(f"Knowledge source deleted successfully.")

Reference：SearchIndexClient

获取搜索服务上所有知识库的列表。

### Get knowledge bases
GET {{search-url}}/knowledgebases?api-version={{api-version}}&$select=name
Authorization: Bearer {{token}}

参考：知识库 - 列表

示例响应可能如下所示：

 {
     "@odata.context": "https://my-search-service.search.windows.net/$metadata#knowledgebases(name)",
     "value": [
     {
         "name": "my-kb"
     },
     {
         "name": "my-kb-2"
     }
     ]
 }

获取单个知识库定义以检查知识源引用。

### Get a knowledge base definition
GET {{search-url}}/knowledgebases/{{knowledge-base-name}}?api-version={{api-version}}
Authorization: Bearer {{token}}

参考：知识库 - 获取

示例响应可能如下所示：

 {
   "name": "my-kb",
   "description": null,
   "retrievalInstructions": null,
   "answerInstructions": null,
   "outputMode": null,
   "knowledgeSources": [
     {
       "name": "my-blob-ks"
     }
   ],
   "models": [],
   "encryptionKey": null,
   "retrievalReasoningEffort": {
     "kind": "low"
   }
 }

删除知识库，或者如果有多个知识库，请更新知识库以删除源。此示例显示删除。

### Delete a knowledge base
DELETE {{search-url}}/knowledgebases/{{knowledge-base-name}}?api-version={{api-version}}
Authorization: Bearer {{token}}

参考：知识库 - 删除

删除知识源。

### Delete a knowledge source
DELETE {{search-url}}/knowledgesources/{{knowledge-source-name}}?api-version={{api-version}}
Authorization: Bearer {{token}}

参考：知识源 - 删除

反馈

此页面是否有帮助？

Last updated on 2026-09-17

创建搜索索引知识源

使用支持

先决条件

Limitations

检查现有知识源

创建知识源

在知识库上保留基本筛选器（预览版）

配置查询提示（预览版）

分配给知识库

查询知识库

删除知识源

相关内容

反馈

其他资源