Google Cloud SQL for PostgreSQL 集成

gcloud config set project YOUR-PROJECT-ID

PROJECT_ID="your-project-id"
REGION="your-project-region" // 示例："us-central1"
INSTANCE_NAME="your-instance"
DB_NAME="your-database-name"
DB_USER="your-database-user"
PASSWORD="your-database-password"

import {
  Column,
  PostgresEngine,
  PostgresEngineArgs,
  PostgresVectorStore,
  PostgresVectorStoreArgs,
  VectorStoreTableArgs,
} from "@langchain/google-cloud-sql-pg";
import { SyntheticEmbeddings } from "@langchain/core/utils/testing"; // 这用作嵌入服务
import * as dotenv from "dotenv";

dotenv.config();

const peArgs: PostgresEngineArgs = {
  user: process.env.DB_USER ?? "",
  password: process.env.PASSWORD ?? "",
};

// PostgresEngine 实例化
const engine: PostgresEngine = await PostgresEngine.fromInstance(
  process.env.PROJECT_ID ?? "",
  process.env.REGION ?? "",
  process.env.INSTANCE_NAME ?? "",
  process.env.DB_NAME ?? "",
  peArgs
);

const vectorStoreArgs: VectorStoreTableArgs = {
  metadataColumns: [new Column("page", "TEXT"), new Column("source", "TEXT")],
};

// 向量存储表初始化
await engine.initVectorstoreTable("my_vector_store_table", 768, vectorStoreArgs);
const embeddingService = new SyntheticEmbeddings({ vectorSize: 768 });

const pvectorArgs: PostgresVectorStoreArgs = {
  metadataColumns: ["page", "source"],
};

// PostgresVectorStore 实例化
const vectorStore = await PostgresVectorStore.initialize(
  engine,
  embeddingService,
  "my_vector_store_table",
  pvectorArgs
);

import { v4 as uuidv4 } from "uuid";
import type { Document } from "@langchain/core/documents";

const document1: Document = {
  pageContent: "细胞的动力源是线粒体",
  metadata: { page: 0, source: "https://example.com" },
};

const document2: Document = {
  pageContent: "建筑物由砖块建成",
  metadata: { page: 1, source: "https://example.com" },
};

const document3: Document = {
  pageContent: "线粒体由脂质构成",
  metadata: { page: 2, source: "https://example.com" },
};

const document4: Document = {
  pageContent: "2024年奥运会在巴黎举行",
  metadata: { page: 3, source: "https://example.com" },
};

const documents = [document1, document2, document3, document4];

const ids = [uuidv4(), uuidv4(), uuidv4(), uuidv4()];

await vectorStore.addDocuments(documents, { ids: ids });

// 删除一个文档
const id1 = ids[0];
await vectorStore.delete({ ids: [id1] });

// 删除多个文档
await vectorStore.delete({ ids: ids });

const filter = `"source" = "https://example.com"`;

const results = await vectorStore.similaritySearch("biology", 2, filter);

for (const doc of results) {
  console.log(`* ${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
}

const filter = `"source" = "https://example.com"`;
const resultsWithScores = await vectorStore.similaritySearchWithScore(
  "biology",
  2,
  filter
);

for (const [doc, score] of resultsWithScores) {
  console.log(
    `* [SIM=${score.toFixed(3)}] ${doc.pageContent} [${JSON.stringify(doc.metadata)}]`
  );
}

const options = {
  k: 4,
  filter: `"source" = 'https://example.com'`,
};

const results = await vectorStoreInstance.maxMarginalRelevanceSearch("biology", options);

for (const doc of results) {
  console.log(`* ${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
}