> ## Documentation Index
> Fetch the complete documentation index at: https://cndoc-langchain.site/llms.txt
> Use this file to discover all available pages before exploring further.

# PineconeStore 集成

> 使用 LangChain JavaScript 与 PineconeStore 进行集成。

[Pinecone](https://www.pinecone.io/) 是一个向量数据库，为全球一些最优秀的公司提供 AI 动力支持。

本指南提供了开始使用 Pinecone [向量存储](/oss/javascript/integrations/vectorstores)的快速概览。有关所有 `PineconeStore` 功能和配置的详细文档，请访问 [API 参考](https://reference.langchain.com/javascript/langchain-pinecone/PineconeStore)。

## 概览

### 集成详情

| 类                                                                                              | 包                                                              | [Python 支持](https://python.langchain.com/docs/integrations/vectorstores/pinecone/) |                                                版本                                                |
| :--------------------------------------------------------------------------------------------- | :------------------------------------------------------------- | :--------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------: |
| [`PineconeStore`](https://reference.langchain.com/javascript/langchain-pinecone/PineconeStore) | [`@langchain/pinecone`](https://npmjs.com/@langchain/pinecone) |                                          ✅                                         | ![NPM - Version](https://img.shields.io/npm/v/@langchain/pinecone?style=flat-square\&label=%20&) |

## 设置

要使用 Pinecone 向量存储，您需要创建一个 Pinecone 账户、初始化一个索引，并安装 `@langchain/pinecone` 集成包。您还需要安装 [官方 Pinecone SDK](https://www.npmjs.com/package/@pinecone-database/pinecone) 以初始化一个客户端，并将其传递给 `PineconeStore` 实例。

本指南还将使用 [OpenAI 嵌入](/oss/javascript/integrations/embeddings/openai)，这需要您安装 `@langchain/openai` 集成包。如果您愿意，也可以使用[其他支持的嵌入模型](/oss/javascript/integrations/embeddings)。

<CodeGroup>
  ```bash npm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  npm install @langchain/pinecone @langchain/openai @langchain/core @pinecone-database/pinecone@5
  ```

  ```bash yarn theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  yarn add @langchain/pinecone @langchain/openai @langchain/core @pinecone-database/pinecone@5
  ```

  ```bash pnpm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  pnpm add @langchain/pinecone @langchain/openai @langchain/core @pinecone-database/pinecone@5
  ```
</CodeGroup>

### 凭证

注册一个 [Pinecone](https://www.pinecone.io/) 账户并创建一个索引。确保维度与您要使用的嵌入的维度匹配（OpenAI 的 `text-embedding-3-small` 默认为 1536）。完成此操作后，设置 `PINECONE_INDEX`、`PINECONE_API_KEY` 和（可选）`PINECONE_ENVIRONMENT` 环境变量：

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
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";
```

如果您在本指南中使用 OpenAI 嵌入，您还需要设置您的 OpenAI 密钥：

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
process.env.OPENAI_API_KEY = "YOUR_API_KEY";
```

如果您想获得模型调用的自动跟踪，也可以通过取消注释以下内容来设置您的 [LangSmith](/langsmith/home) API 密钥：

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
// process.env.LANGSMITH_TRACING="true"
// process.env.LANGSMITH_API_KEY="your-api-key"
```

## 实例化

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
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",
  }
);
```

## 管理向量存储

### 向向量存储添加项目

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
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"] });
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
[ '1', '2', '3', '4' ]
```

**注意：** 添加文档后，它们需要一点时间才能变得可查询。

### 从向量存储中删除项目

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
await vectorStore.delete({ ids: ["4"] });
```

## 查询向量存储

一旦您的向量存储已创建并且相关文档已添加，您很可能希望在链或代理运行期间对其进行查询。

### 直接查询

执行简单的相似性搜索可以如下进行：

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
// 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)}]`);
}
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
* The powerhouse of the cell is the mitochondria [{"source":"https://example.com"}]
* Mitochondria are made out of lipids [{"source":"https://example.com"}]
```

如果您想执行相似性搜索并接收相应的分数，可以运行：

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
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)}]`);
}
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
* [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"}]
```

### 通过转换为检索器进行查询

您也可以将向量存储转换为 [检索器](/oss/javascript/langchain/retrieval)，以便在您的链中更轻松地使用。

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
const retriever = vectorStore.asRetriever({
  // 可选过滤器
  filter: filter,
  k: 2,
});

await retriever.invoke("biology");
```

```javascript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
[
  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
  }
]
```

### 用于检索增强生成

有关如何将此向量存储用于检索增强生成 (RAG) 的指南，请参阅以下部分：

* [使用 LangChain 构建 RAG 应用](/oss/javascript/langchain/rag)。
* [代理式 RAG](/oss/javascript/langgraph/agentic-rag)
* [检索文档](/oss/javascript/langchain/retrieval)

***

## API 参考

有关所有 `PineconeStore` 功能和配置的详细文档，请访问 [API 参考](https://reference.langchain.com/javascript/langchain-pinecone/PineconeStore)。

***

<div className="source-links">
  <Callout icon="terminal-2">
    [将这些文档](/use-these-docs)通过 MCP 连接到 Claude、VSCode 等，以获取实时答案。
  </Callout>

  <Callout icon="edit">
    [在 GitHub 上编辑此页面](https://github.com/langchain-ai/docs/edit/main/src/oss/javascript/integrations/vectorstores/pinecone.mdx) 或 [提交问题](https://github.com/langchain-ai/docs/issues/new/choose)。
  </Callout>
</div>