跳到主要内容
版本：V1.1.0

Simple 示例

本示例以服务器模式的 seekdb 为例，演示了 Embedding Functions 的基础操作，以帮助您快速了解如何使用 Embedding Functions。

  1. 连接 seekdb。
  2. 创建带有 Embedding Functions 的 collection。
  3. 使用 documents 添加数据（会自动生成 vectors）。
  4. 使用 query texts 进行查询（会自动生成 vectors）。
  5. 打印查询结果。

示例​

import { SeekdbClient } from "seekdb";

async function main() {
  // ==================== Step 1: Create Client Connection ====================
  // Server mode (connecting to seekdb server or OceanBase)
  const client = new SeekdbClient({
    host: "127.0.0.1",
    port: 2881,
    database: "test",
    user: "root",
    password: "",
  });

  // ==================== Step 2: Create a Collection with Embedding Function ====================
  // A collection is like a table that stores documents with vector embeddings
  const collectionName = "my_simple_collection";

  // Create collection with default embedding function
  // The embedding function will automatically convert documents to embeddings

  // Default embedding function is used if no embedding function is provided
  const collection = await client.createCollection({
    name: collectionName,
  });

  console.log(
    `Created collection '${collection.name}' with dimension: ${collection.dimension}`,
  );
  console.log(`Embedding function: ${collection.embeddingFunction?.name}`);

  // ==================== Step 3: Add Data to Collection ====================
  // With embedding function, you can add documents directly without providing embeddings
  // The embedding function will automatically generate embeddings from documents

  const documents = [
    "Machine learning is a subset of artificial intelligence",
    "Python is a popular programming language",
    "Vector databases enable semantic search",
    "Neural networks are inspired by the human brain",
    "Natural language processing helps computers understand text",
  ];

  const ids = ["id1", "id2", "id3", "id4", "id5"];

  // Add data with documents only - embeddings will be auto-generated by embedding function
  await collection.add({
    ids,
    documents, // embeddings will be automatically generated
    metadatas: [
      { category: "AI", index: 0 },
      { category: "Programming", index: 1 },
      { category: "Database", index: 2 },
      { category: "AI", index: 3 },
      { category: "NLP", index: 4 },
    ],
  });

  console.log(`\nAdded ${documents.length} documents to collection`);
  console.log(
    "Note: Embeddings were automatically generated from documents using the embedding function",
  );

  // ==================== Step 4: Query the Collection ====================
  // With embedding function, you can query using text directly
  // The embedding function will automatically convert query text to query vector

  // Query using text - query vector will be auto-generated by embedding function
  const queryText = "artificial intelligence and machine learning";

  const results = await collection.query({
    queryTexts: queryText, // Query text - will be embedded automatically
    nResults: 3, // Return top 3 most similar documents
    include: ["documents", "metadatas", "distances"],
  });

  console.log(`\nQuery: '${queryText}'`);
  console.log(`Query results: ${results.ids[0].length} items found`);

  // ==================== Step 5: Print Query Results ====================
  for (let i = 0; i < results.ids[0].length; i++) {
    console.log(`\nResult ${i + 1}:`);
    console.log(`  ID: ${results.ids[0][i]}`);
    console.log(`  Distance: ${results.distances?.[0][i]?.toFixed(4)}`);
    if (results.documents) {
      console.log(`  Document: ${results.documents[0][i]}`);
    }
    if (results.metadatas) {
      console.log(`  Metadata: ${JSON.stringify(results.metadatas[0][i])}`);
    }
  }

  // ==================== Step 6: Cleanup ====================
  await client.deleteCollection(collectionName);
  console.log(`\nDeleted collection '${collectionName}'`);

  await client.close();
}

main().catch(console.error);

相关文档​

Contents

编辑此页