PineconeStore 集成

process.env.PINECONE_API_KEY = "your-pinecone-api-key";
process.env.PINECONE_INDEX = "your-pinecone-index";

// 可选
process.env.PINECONE_ENVIRONMENT = "your-pinecone-environment";

process.env.OPENAI_API_KEY = "YOUR_API_KEY";

// process.env.LANGSMITH_TRACING="true"
// process.env.LANGSMITH_API_KEY="your-api-key"

import { PineconeStore } from "@langchain/pinecone";
import { OpenAIEmbeddings } from "@langchain/openai";

import { Pinecone as PineconeClient } from "@pinecone-database/pinecone";

const embeddings = new OpenAIEmbeddings({
  model: "text-embedding-3-small",
});

const pinecone = new PineconeClient();
// 将自动读取 PINECONE_API_KEY 和 PINECONE_ENVIRONMENT 环境变量
const pineconeIndex = pinecone.Index(process.env.PINECONE_INDEX!);

const vectorStore = await PineconeStore.fromExistingIndex(
  embeddings,
  {
    pineconeIndex,
    // 允许同时进行的最大批处理请求数。每批为 1000 个向量。
    maxConcurrency: 5,
    // 您也可以在此处传递命名空间
    // namespace: "foo",
  }
);

import type { Document } from "@langchain/core/documents";

const document1: Document = {
  pageContent: "The powerhouse of the cell is the mitochondria",
  metadata: { source: "https://example.com" }
};

const document2: Document = {
  pageContent: "Buildings are made out of brick",
  metadata: { source: "https://example.com" }
};

const document3: Document = {
  pageContent: "Mitochondria are made out of lipids",
  metadata: { source: "https://example.com" }
};

const document4: Document = {
  pageContent: "The 2024 Olympics are in Paris",
  metadata: { source: "https://example.com" }
}

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

await vectorStore.addDocuments(documents, { ids: ["1", "2", "3", "4"] });

[ '1', '2', '3', '4' ]

await vectorStore.delete({ ids: ["4"] });

// 可选过滤器
const filter = { source: "https://example.com" };

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

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

* The powerhouse of the cell is the mitochondria [{"source":"https://example.com"}]
* Mitochondria are made out of lipids [{"source":"https://example.com"}]

const similaritySearchWithScoreResults = await vectorStore.similaritySearchWithScore("biology", 2, filter)

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

* [SIM=0.165] The powerhouse of the cell is the mitochondria [{"source":"https://example.com"}]
* [SIM=0.148] Mitochondria are made out of lipids [{"source":"https://example.com"}]

const retriever = vectorStore.asRetriever({
  // 可选过滤器
  filter: filter,
  k: 2,
});

await retriever.invoke("biology");

[
  Document {
    pageContent: 'The powerhouse of the cell is the mitochondria',
    metadata: { source: 'https://example.com' },
    id: undefined
  },
  Document {
    pageContent: 'Mitochondria are made out of lipids',
    metadata: { source: 'https://example.com' },
    id: undefined
  }
]