azure-search-documents-ts

Azure AI Search SDK for TypeScript

使用向量、混合和语义搜索功能构建搜索应用。

安装

npm install @azure/search-documents @azure/identity

环境变量

AZURE_SEARCH_ENDPOINT=https://<service-name>.search.windows.net
AZURE_SEARCH_INDEX_NAME=my-index
AZURE_SEARCH_ADMIN_KEY=<admin-key>  # Optional if using Entra ID

身份验证

import { SearchClient, SearchIndexClient } from "@azure/search-documents";
import { DefaultAzureCredential } from "@azure/identity";

const endpoint = process.env.AZURE_SEARCH_ENDPOINT!;
const indexName = process.env.AZURE_SEARCH_INDEX_NAME!;
const credential = new DefaultAzureCredential();

// For searching
const searchClient = new SearchClient(endpoint, indexName, credential);

// For index management
const indexClient = new SearchIndexClient(endpoint, credential);

版本、架构和授权

代码片段是包含占位符的独立片段，并非可直接运行的完整程序。使用前请核实已安装的 SDK 类型、实际索引架构以及嵌入模型和维度。请根据经过身份验证的身份在服务端设置文档安全筛选器；切勿信任客户端提供的筛选器来实施访问控制。创建或更新索引，以及上传或删除记录，都需要对目标资源具有精确的授权，并且可能改变付费服务的状态。

核心工作流

创建包含向量字段的索引

import { SearchIndex, SearchField, VectorSearch } from "@azure/search-documents";

const index: SearchIndex = {
  name: "products",
  fields: [
    { name: "id", type: "Edm.String", key: true },
    { name: "title", type: "Edm.String", searchable: true },
    { name: "description", type: "Edm.String", searchable: true },
    { name: "category", type: "Edm.String", filterable: true, facetable: true },
    {
      name: "embedding",
      type: "Collection(Edm.Single)",
      searchable: true,
      vectorSearchDimensions: 1536,
      vectorSearchProfileName: "vector-profile",
    },
  ],
  vectorSearch: {
    algorithms: [
      { name: "hnsw-algorithm", kind: "hnsw" },
    ],
    profiles: [
      { name: "vector-profile", algorithmConfigurationName: "hnsw-algorithm" },
    ],
  },
};

await indexClient.createOrUpdateIndex(index);

索引文档

const documents = [
  { id: "1", title: "Widget", description: "A useful widget", category: "Tools", embedding: [...] },
  { id: "2", title: "Gadget", description: "A cool gadget", category: "Electronics", embedding: [...] },
];

const result = await searchClient.uploadDocuments(documents);
const failures = result.results.filter((item) => !item.succeeded);
if (failures.length) throw new Error(`Indexing failed for ${failures.length} documents`);
console.log(`Indexed ${result.results.length} documents`);

全文搜索

const results = await searchClient.search("widget", {
  select: ["id", "title", "description"],
  filter: "category eq 'Tools'",
  orderBy: ["title asc"],
  top: 10,
});

for await (const result of results.results) {
  console.log(`${result.document.title}: ${result.score}`);
}

向量搜索

const queryVector = await getEmbedding("useful tool"); // Your embedding function

const results = await searchClient.search("*", {
  vectorSearchOptions: {
    queries: [
      {
        kind: "vector",
        vector: queryVector,
        fields: ["embedding"],
        kNearestNeighborsCount: 10,
      },
    ],
  },
  select: ["id", "title", "description"],
});

for await (const result of results.results) {
  console.log(`${result.document.title}: ${result.score}`);
}

混合搜索（文本 + 向量）

const queryVector = await getEmbedding("useful tool");

const results = await searchClient.search("tool", {
  vectorSearchOptions: {
    queries: [
      {
        kind: "vector",
        vector: queryVector,
        fields: ["embedding"],
        kNearestNeighborsCount: 50,
      },
    ],
  },
  select: ["id", "title", "description"],
  top: 10,
});

语义搜索

// Index must have semantic configuration
const index: SearchIndex = {
  name: "products",
  fields: [...],
  semanticSearch: {
    configurations: [
      {
        name: "semantic-config",
        prioritizedFields: {
          titleField: { name: "title" },
          contentFields: [{ name: "description" }],
        },
      },
    ],
  },
};

// Search with semantic ranking
const results = await searchClient.search("best tool for the job", {
  queryType: "semantic",
  semanticSearchOptions: {
    configurationName: "semantic-config",
    captions: { captionType: "extractive" },
    answers: { answerType: "extractive", count: 3 },
  },
  select: ["id", "title", "description"],
});

for await (const result of results.results) {
  console.log(`${result.document.title}`);
  console.log(`  Caption: ${result.captions?.[0]?.text}`);
  console.log(`  Reranker Score: ${result.rerankerScore}`);
}

筛选和分面

// Filter syntax
const results = await searchClient.search("*", {
  filter: "category eq 'Electronics' and price lt 100",
  facets: ["category,count:10", "brand"],
});

// Access facets
for (const [facetName, facetResults] of Object.entries(results.facets || {})) {
  console.log(`${facetName}:`);
  for (const facet of facetResults) {
    console.log(`  ${facet.value}: ${facet.count}`);
  }
}

自动补全和建议

// Create suggester in index
const index: SearchIndex = {
  name: "products",
  fields: [...],
  suggesters: [
    { name: "sg", sourceFields: ["title", "description"] },
  ],
};

// Autocomplete
const autocomplete = await searchClient.autocomplete("wid", "sg", {
  mode: "twoTerms",
  top: 5,
});

// Suggestions
const suggestions = await searchClient.suggest("wid", "sg", {
  select: ["title"],
  top: 5,
});

批量操作

// Batch upload, merge, delete
const batch = [
  { upload: { id: "1", title: "New Item" } },
  { merge: { id: "2", title: "Updated Title" } },
  { delete: { id: "3" } },
];

const result = await searchClient.indexDocuments({ actions: batch });

关键类型

import {
  SearchClient,
  SearchIndexClient,
  SearchIndexerClient,
  SearchIndex,
  SearchField,
  SearchOptions,
  VectorSearch,
  SemanticSearch,
  SearchIterator,
} from "@azure/search-documents";

最佳实践

1. 使用混合搜索 - 结合向量和文本，获得最佳结果
2. 启用语义排序 - 提高自然语言查询的相关性
3. 批量上传文档 - 使用包含多个文档的数组调用 uploadDocuments，而非逐个上传
4. 使用筛选器保障安全 - 使用筛选器实现文档级安全控制
5. 增量索引 - 使用 mergeOrUploadDocuments 进行更新
6. 监控查询性能 - 在生产环境中谨慎使用 includeTotalCount: true

适用场景

当任务符合概述中描述的工作流或操作时，可使用此技能。

限制

• 仅当任务明确符合上述范围时，才使用此技能。
• 不要将输出视为针对特定环境进行验证、测试或专家审查的替代品。
• 如果缺少必需的输入、权限、安全边界或成功标准，请暂停并要求澄清。