Skip to main content

Google

与 Google 云平台 和 AI 工作室 相关的功能

¥Functionality related to Google Cloud Platform and AI Studio

聊天模型​

¥Chat models

Gemini 模型​

¥Gemini Models

通过 ChatGoogleGenerativeAI 访问 Gemini 模型（例如 gemini-1.5-pro 和 gemini-2.0-flex），如果使用 VertexAI，则通过 ChatVertexAI 类访问。

¥Access Gemini models such as gemini-1.5-pro and gemini-2.0-flex through the ChatGoogleGenerativeAI, or if using VertexAI, via the ChatVertexAI class.

tip

请参阅 此部分包含有关安装集成包的一般说明。

¥See this section for general instructions on installing integration packages.

```bash npm2yarn
npm install @langchain/google-genai @langchain/core
```

配置你的 API 密钥。

¥Configure your API key.

```
export GOOGLE_API_KEY=your-api-key
```

```typescript
import { ChatGoogleGenerativeAI } from "@langchain/google-genai";

const model = new ChatGoogleGenerativeAI({
  model: "gemini-pro",
  maxOutputTokens: 2048,
});

// Batch and stream are also supported
const res = await model.invoke([
  [
    "human",
    "What would be a good company name for a company that makes colorful socks?",
  ],
]);
```

较新的 Gemini 模型支持图片输入：

¥More recent Gemini models support image inputs:

```typescript
const visionModel = new ChatGoogleGenerativeAI({
  model: "gemini-2.0-flash",
  maxOutputTokens: 2048,
});
const image = fs.readFileSync("./hotdog.jpg").toString("base64");
const input2 = [
  new HumanMessage({
    content: [
      {
        type: "text",
        text: "Describe the following image.",
      },
      {
        type: "image_url",
        image_url: `data:image/png;base64,${image}`,
      },
    ],
  }),
];

const res = await visionModel.invoke(input2);
```

:::tip

点击 [此处](/docs/integrations/chat/google_generativeai) 获取 `@langchain/google-genai` 特定的集成文档

¥Click [here](/docs/integrations/chat/google_generativeai) for the `@langchain/google-genai` specific integration docs

:::

image_url 的值必须是 base64 编码的图片（例如 data:image/png;base64,abcd124）。

¥The value of image_url must be a base64 encoded image (e.g., data:image/png;base64,abcd124).

Gemma​

使用 ChatGoogle 类通过 AI Studio 访问 gemma-3-27b-it 模型。（此类是 ChatVertexAI 类的超类，可与 Vertex AI 和 AI Studio API 配合使用。）

¥Access the gemma-3-27b-it model through AI Studio using the ChatGoogle class. (This class is a superclass of the ChatVertexAI class that works with both Vertex AI and the AI Studio APIs.)

tip

由于 Gemma 是一个开放模型，因此它也可能适用于包括 Ollama 在内的其他平台。

¥Since Gemma is an open model, it may also be available from other platforms including Ollama.

npm install @langchain/google-gauth @langchain/core

配置你的 API 密钥。

¥Configure your API key.

export GOOGLE_API_KEY=your-api-key
import { ChatGoogle } from "@langchain/google-gauth";

const model = new ChatGoogle({
  model: "gemma-3-27b-it",
});

const res = await model.invoke([
  {
    role: "user",
    content:
      "What would be a good company name for a company that makes colorful socks?",
  },
]);

第三方模型​

¥Third Party Models

请参阅上文，了解如何通过 Vertex AI 设置身份验证以使用这些模型。

¥See above for setting up authentication through Vertex AI to use these models.

Anthropic Claude 模型也可通过 Vertex AI 平台获取。有关启用模型访问权限和要使用的模型名称的更多信息，请参阅 此处。

¥Anthropic Claude models are also available through the Vertex AI platform. See here for more information about enabling access to the models and the model names to use.

PaLM 模型不再受支持。

¥PaLM models are no longer supported.

向量存储​

¥Vector Store

¥Vertex AI Vector Search

Vertex AI 矢量搜索，前身为 Vertex AI Matching Engine，提供业界领先的高规模低延迟向量数据库。这些向量数据库通常被称为向量相似性匹配或近似最近邻 (ANN) 服务。

¥Vertex AI Vector Search, formerly known as Vertex AI Matching Engine, provides the industry's leading high-scale low latency vector database. These vector databases are commonly referred to as vector similarity-matching or an approximate nearest neighbor (ANN) service.

import { MatchingEngine } from "@langchain/community/vectorstores/googlevertexai";

Postgres 向量存储​

¥Postgres Vector Store

@langchain/google-cloud-sql-pg 软件包中的 PostgresVectorStore 模块提供了一种使用 CloudSQL for PostgresSQL 类来存储向量嵌入的方法。

¥The PostgresVectorStore module from the @langchain/google-cloud-sql-pg package provides a way to use the CloudSQL for PostgresSQL to store vector embeddings using the class.

$ yarn add @langchain/google-cloud-sql-pg

设置环境变量：

¥Set your environment variables:

PROJECT_ID="your-project-id"
REGION="your-project-region"
INSTANCE_NAME="your-instance"
DB_NAME="your-database-name"
DB_USER="your-database-user"
PASSWORD="your-database-password"

通过 PostgresEngine 类创建数据库连接：

¥Create a DB connection through the PostgresEngine class:

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

初始化向量存储表：

¥Initialize the vector store table:

await engine.initVectorstoreTable(
  "my_vector_store_table",
  768,
  vectorStoreArgs
);

创建一个向量存储实例：

¥Create a vector store instance:

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

工具​

¥Tools

¥Google Search

  • 按照 这些说明 操作设置自定义搜索引擎

    ¥Set up a Custom Search Engine, following these instructions

  • 从上一步获取 API 密钥和自定义搜索引擎 ID，并分别将它们设置为环境变量 GOOGLE_API_KEY 和 GOOGLE_CSE_ID。

    ¥Get an API Key and Custom Search Engine ID from the previous step, and set them as environment variables GOOGLE_API_KEY and GOOGLE_CSE_ID respectively

有一个 GoogleCustomSearch 实用程序可以封装此 API。要导入此实用程序：

¥There exists a GoogleCustomSearch utility which wraps this API. To import this utility:

import { GoogleCustomSearch } from "@langchain/community/tools/google_custom_search";

我们可以轻松地将此封装器加载为工具（与代理一起使用）。我们可以使用以下方法来实现：

¥We can easily load this wrapper as a Tool (to use with an Agent). We can do this with:

const tools = [new GoogleCustomSearch({})];
// Pass this variable into your agent.

聊天历史记录​

¥Chat history

Postgres 聊天消息历史记录​

¥Postgres Chat Message History

@langchain/google-cloud-sql-pg 软件包中的 PostgresChatMessageHistory 函数提供了一种使用 CloudSQL for PostgresSQL 存储消息并提供对话历史记录的方法。

¥The PostgresChatMessageHistory from the @langchain/google-cloud-sql-pg package provides a way to use the CloudSQL for PostgresSQL to store messages and provide conversation history.

$ yarn add @langchain/google-cloud-sql-pg

注意：查看本页面的 [Postgres Vector Store](#Postgres Vector Store) 部分，了解如何安装软件包并初始化数据库连接。

¥Note: See the [Postgres Vector Store](#Postgres Vector Store) section on this page to learn how to install the package and initialize a DB connection.

初始化聊天历史记录表：

¥Initialize the chat history table:

await engine.initChatHistoryTable("chat_message_table");

创建一个聊天消息历史记录实例：

¥Create a chat message history instance:

const historyInstance = await PostgresChatMessageHistory.initialize(
  engine,
  "test",
  "chat_message_table"
);

文档加载器​

¥Document Loaders

Postgres 加载器​

¥Postgres Loader

@langchain/google-cloud-sql-pg 中的 PostgresLoader 提供了一种使用 CloudSQL for PostgresSQL 将数据加载为 LangChain Document 的方法。

¥The PostgresLoader from @langchain/google-cloud-sql-pg provides a way to use the CloudSQL for PostgresSQL to load data as LangChain Documents.

注意：查看本页面的 [Postgres Vector Store](#Postgres Vector Store) 部分，了解如何安装软件包并初始化数据库连接。

¥Note: See the [Postgres Vector Store](#Postgres Vector Store) section on this page to learn how to install the package and initialize a DB connection.

创建一个加载器实例：

¥Create a loader instance:

const documentLoaderArgs: PostgresLoaderOptions = {
  tableName: "test_table_custom",
  contentColumns: ["fruit_name", "variety"],
  metadataColumns: [
    "fruit_id",
    "quantity_in_stock",
    "price_per_unit",
    "organic",
  ],
  format: "text",
};

const documentLoaderInstance = await PostgresLoader.initialize(
  PEInstance,
  documentLoaderArgs
);

const documents = await documentLoaderInstance.load();