Skip to main content
Google AI 提供多种不同的聊天模型,包括强大的 Gemini 系列。有关最新模型、其功能、上下文窗口等信息,请访问 Google AI 文档 这将帮助您开始使用 ChatGoogleGenerativeAI 聊天模型。有关所有 ChatGoogleGenerativeAI 功能和配置的详细文档,请访问 API 参考
此库将被弃用此库基于 Google 的一个已弃用库,并将被 ChatGoogle 库取代。 新实现应使用 ChatGoogle 库,现有实现应考虑迁移。

概述

集成详情

可序列化Python 支持下载量版本
ChatGoogleGenerativeAI@langchain/google-genaiNPM - DownloadsNPM - Version

模型功能

请参阅下表标题中的链接,了解如何使用特定功能的指南。

设置

您可以通过 @langchain/google-genai 集成包中的 ChatGoogleGenerativeAI 类访问 Google 的 geminigemini-vision 模型,以及 LangChain 中的其他生成模型。
您也可以通过 LangChain VertexAI 和 VertexAI-web 集成访问 Google 的 gemini 模型系列。请参阅 Vertex AI 集成文档

凭证

在此处获取 API 密钥:https://ai.google.dev/tutorials/setup 然后设置 GOOGLE_API_KEY 环境变量:
export GOOGLE_API_KEY="your-api-key"
如果您想自动跟踪模型调用,还可以通过取消注释以下内容来设置您的 LangSmith API 密钥:
# export LANGSMITH_TRACING="true"
# export LANGSMITH_API_KEY="your-api-key"

安装

LangChain ChatGoogleGenerativeAI 集成位于 @langchain/google-genai 包中:
npm install @langchain/google-genai @langchain/core

实例化

现在我们可以实例化我们的模型对象并生成聊天补全:
import { ChatGoogleGenerativeAI } from "@langchain/google-genai"

const llm = new ChatGoogleGenerativeAI({
    model: "gemini-2.5-pro",
    temperature: 0,
    maxRetries: 2,
    // 其他参数...
})

调用

const aiMsg = await llm.invoke([
    [
        "system",
        "您是一个将英语翻译成法语的有用助手。请翻译用户的句子。",
    ],
    ["human", "I love programming."],
])
aiMsg
AIMessage {
  "content": "J'adore programmer. \n",
  "additional_kwargs": {
    "finishReason": "STOP",
    "index": 0,
    "safetyRatings": [
      {
        "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
        "probability": "NEGLIGIBLE"
      },
      {
        "category": "HARM_CATEGORY_HATE_SPEECH",
        "probability": "NEGLIGIBLE"
      },
      {
        "category": "HARM_CATEGORY_HARASSMENT",
        "probability": "NEGLIGIBLE"
      },
      {
        "category": "HARM_CATEGORY_DANGEROUS_CONTENT",
        "probability": "NEGLIGIBLE"
      }
    ]
  },
  "response_metadata": {
    "finishReason": "STOP",
    "index": 0,
    "safetyRatings": [
      {
        "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
        "probability": "NEGLIGIBLE"
      },
      {
        "category": "HARM_CATEGORY_HATE_SPEECH",
        "probability": "NEGLIGIBLE"
      },
      {
        "category": "HARM_CATEGORY_HARASSMENT",
        "probability": "NEGLIGIBLE"
      },
      {
        "category": "HARM_CATEGORY_DANGEROUS_CONTENT",
        "probability": "NEGLIGIBLE"
      }
    ]
  },
  "tool_calls": [],
  "invalid_tool_calls": [],
  "usage_metadata": {
    "input_tokens": 21,
    "output_tokens": 5,
    "total_tokens": 26
  }
}
console.log(aiMsg.content)
J'adore programmer.

安全设置

Gemini 模型具有默认的安全设置,可以被覆盖。如果您从模型收到大量“安全警告”,可以尝试调整模型的 safety_settings 属性。例如,要关闭危险内容的安全阻止,您可以从 @google/generative-ai 包导入枚举,然后按如下方式构造您的 LLM:
import { ChatGoogleGenerativeAI } from "@langchain/google-genai";
import { HarmBlockThreshold, HarmCategory } from "@google/generative-ai";

const llmWithSafetySettings = new ChatGoogleGenerativeAI({
  model: "gemini-2.5-pro",
  temperature: 0,
  safetySettings: [
    {
      category: HarmCategory.HARM_CATEGORY_HARASSMENT,
      threshold: HarmBlockThreshold.BLOCK_LOW_AND_ABOVE,
    },
  ],
  // 其他参数...
});

工具调用

使用 Google AI 进行工具调用与其他模型的工具调用基本相同,但在模式上有一些限制。 Google AI API 不允许工具模式包含具有未知属性的对象。例如,以下 Zod 模式将抛出错误: const invalidSchema = z.object({ properties: z.record(z.unknown()) }); const invalidSchema2 = z.record(z.unknown()); 相反,您应该明确定义对象字段的属性。以下是一个示例:
import { tool } from "@langchain/core/tools";
import { ChatGoogleGenerativeAI } from "@langchain/google-genai";
import * as z from "zod";

// 定义您的工具
const fakeBrowserTool = tool((_) => {
  return "搜索结果是 xyz..."
}, {
  name: "browser_tool",
  description: "当您需要在网络上查找内容或总结网页时很有用。",
  schema: z.object({
    url: z.string().describe("要搜索的网页 URL。"),
    query: z.string().optional().describe("可选的搜索查询。"),
  }),
})

const llmWithTool = new ChatGoogleGenerativeAI({
  model: "gemini-pro",
}).bindTools([fakeBrowserTool]) // 将工具绑定到模型

const toolRes = await llmWithTool.invoke([
  [
    "human",
    "搜索网络并告诉我今晚纽约的天气情况。使用一个流行的天气网站",
  ],
]);

console.log(toolRes.tool_calls);
[
  {
    name: 'browser_tool',
    args: {
      url: 'https://www.weather.com',
      query: 'weather tonight in new york'
    },
    type: 'tool_call'
  }
]

内置 Google 搜索检索

Google 还提供了一个内置的搜索工具,您可以使用它来基于真实世界信息生成内容。以下是如何使用它的示例:
import { DynamicRetrievalMode, GoogleSearchRetrievalTool } from "@google/generative-ai";
import { ChatGoogleGenerativeAI } from "@langchain/google-genai";

const searchRetrievalTool: GoogleSearchRetrievalTool = {
  googleSearchRetrieval: {
    dynamicRetrievalConfig: {
      mode: DynamicRetrievalMode.MODE_DYNAMIC,
      dynamicThreshold: 0.7, // 默认为 0.7
    }
  }
};
const searchRetrievalModel = new ChatGoogleGenerativeAI({
  model: "gemini-2.5-pro",
  temperature: 0,
  maxRetries: 0,
}).bindTools([searchRetrievalTool]);

const searchRetrievalResult = await searchRetrievalModel.invoke("Who won the 2024 MLB World Series?");

console.log(searchRetrievalResult.content);
The Los Angeles Dodgers won the 2024 World Series, defeating the New York Yankees in Game 5 on October 30, 2024, by a score of 7-6. This victory marks the Dodgers' eighth World Series title and their first in a full season since 1988.  They achieved this win by overcoming a 5-0 deficit, making them the first team in World Series history to win a clinching game after being behind by such a margin.  The Dodgers also became the first team in MLB postseason history to overcome a five-run deficit, fall behind again, and still win.  Walker Buehler earned the save in the final game, securing the championship for the Dodgers.
响应还包括有关搜索结果的元数据:
console.dir(searchRetrievalResult.response_metadata?.groundingMetadata, { depth: null });
{
  searchEntryPoint: {
    renderedContent: '<style>\n' +
      '.container {\n' +
      '  align-items: center;\n' +
      '  border-radius: 8px;\n' +
      '  display: flex;\n' +
      '  font-family: Google Sans, Roboto, sans-serif;\n' +
      '  font-size: 14px;\n' +
      '  line-height: 20px;\n' +
      '  padding: 8px 12px;\n' +
      '}\n' +
      '.chip {\n' +
      '  display: inline-block;\n' +
      '  border: solid 1px;\n' +
      '  border-radius: 16px;\n' +
      '  min-width: 14px;\n' +
      '  padding: 5px 16px;\n' +
      '  text-align: center;\n' +
      '  user-select: none;\n' +
      '  margin: 0 8px;\n' +
      '  -webkit-tap-highlight-color: transparent;\n' +
      '}\n' +
      '.carousel {\n' +
      '  overflow: auto;\n' +
      '  scrollbar-width: none;\n' +
      '  white-space: nowrap;\n' +
      '  margin-right: -12px;\n' +
      '}\n' +
      '.headline {\n' +
      '  display: flex;\n' +
      '  margin-right: 4px;\n' +
      '}\n' +
      '.gradient-container {\n' +
      '  position: relative;\n' +
      '}\n' +
      '.gradient {\n' +
      '  position: absolute;\n' +
      '  transform: translate(3px, -9px);\n' +
      '  height: 36px;\n' +
      '  width: 9px;\n' +
      '}\n' +
      '@media (prefers-color-scheme: light) {\n' +
      '  .container {\n' +
      '    background-color: #fafafa;\n' +
      '    box-shadow: 0 0 0 1px #0000000f;\n' +
      '  }\n' +
      '  .headline-label {\n' +
      '    color: #1f1f1f;\n' +
      '  }\n' +
      '  .chip {\n' +
      '    background-color: #ffffff;\n' +
      '    border-color: #d2d2d2;\n' +
      '    color: #5e5e5e;\n' +
      '    text-decoration: none;\n' +
      '  }\n' +
      '  .chip:hover {\n' +
      '    background-color: #f2f2f2;\n' +
      '  }\n' +
      '  .chip:focus {\n' +
      '    background-color: #f2f2f2;\n' +
      '  }\n' +
      '  .chip:active {\n' +
      '    background-color: #d8d8d8;\n' +
      '    border-color: #b6b6b6;\n' +
      '  }\n' +
      '  .logo-dark {\n' +
      '    display: none;\n' +
      '  }\n' +
      '  .gradient {\n' +
      '    background: linear-gradient(90deg, #fafafa 15%, #fafafa00 100%);\n' +
      '  }\n' +
      '}\n' +
      '@media (prefers-color-scheme: dark) {\n' +
      '  .container {\n' +
      '    background-color: #1f1f1f;\n' +
      '    box-shadow: 0 0 0 1px #ffffff26;\n' +
      '  }\n' +
      '  .headline-label {\n' +
      '    color: #fff;\n' +
      '  }\n' +
      '  .chip {\n' +
      '    background-color: #2c2c2c;\n' +
      '    border-color: #3c4043;\n' +
      '    color: #fff;\n' +
      '    text-decoration: none;\n' +
      '  }\n' +
      '  .chip:hover {\n' +
      '    background-color: #353536;\n' +
      '  }\n' +
      '  .chip:focus {\n' +
      '    background-color: #353536;\n' +
      '  }\n' +
      '  .chip:active {\n' +
      '    background-color: #464849;\n' +
      '    border-color: #53575b;\n' +
      '  }\n' +
      '  .logo-light {\n' +
      '    display: none;\n' +
      '  }\n' +
      '  .gradient {\n' +
      '    background: linear-gradient(90deg, #1f1f1f 15%, #1f1f1f00 100%);\n' +
      '  }\n' +
      '}\n' +
      '</style>\n' +
      '<div class="container">\n' +
      '  <div class="headline">\n' +
      '    <svg class="logo-light" width="18" height="18" viewBox="9 9 35 35" fill="none" xmlns="http://www.w3.org/2000/svg">\n' +
      '      <path fill-rule="evenodd" clip-rule="evenodd" d="M42.8622 27.0064C42.8622 25.7839 42.7525 24.6084 42.5487 23.4799H26.3109V30.1568H35.5897C35.1821 32.3041 33.9596 34.1222 32.1258 35.3448V39.6864H37.7213C40.9814 36.677 42.8622 32.2571 42.8622 27.0064V27.0064Z" fill="#4285F4"/>\n' +
      '      <path fill-rule="evenodd" clip-rule="evenodd" d="M26.3109 43.8555C30.9659 43.8555 34.8687 42.3195 37.7213 39.6863L32.1258 35.3447C30.5898 36.3792 28.6306 37.0061 26.3109 37.0061C21.8282 37.0061 18.0195 33.9811 16.6559 29.906H10.9194V34.3573C13.7563 39.9841 19.5712 43.8555 26.3109 43.8555V43.8555Z" fill="#34A853"/>\n' +
      '      <path fill-rule="evenodd" clip-rule="evenodd" d="M16.6559 29.8904C16.3111 28.8559 16.1074 27.7588 16.1074 26.6146C16.1074 25.4704 16.3111 24.3733 16.6559 23.3388V18.8875H10.9194C9.74388 21.2072 9.06992 23.8247 9.06992 26.6146C9.06992 29.4045 9.74388 32.022 10.9194 34.3417L15.3864 30.8621L16.6559 29.8904V29.8904Z" fill="#FBBC05"/>\n' +
      '      <path fill-rule="evenodd" clip-rule="evenodd" d="M26.3109 16.2386C28.85 16.2386 31.107 17.1164 32.9095 18.8091L37.8466 13.8719C34.853 11.082 30.9659 9.3736 26.3109 9.3736C19.5712 9.3736 13.7563 13.245 10.9194 18.8875L16.6559 23.3388C18.0195 19.2636 21.8282 16.2386 26.3109 16.2386V16.2386Z" fill="#EA4335"/>\n' +
      '    </svg>\n' +
      '    <svg class="logo-dark" width="18" height="18" viewBox="0 0 48 48" xmlns="http://www.w3.org/2000/svg">\n' +
      '      <circle cx="24" cy="23" fill="#FFF" r="22"/>\n' +
      '      <path d="M33.76 34.26c2.75-2.56 4.49-6.37 4.49-11.26 0-.89-.08-1.84-.29-3H24.01v5.99h8.03c-.4 2.02-1.5 3.56-3.07 4.56v.75l3.91 2.97h.88z" fill="#4285F4"/>\n' +
      '      <path d="M15.58 25.77A8.845 8.845 0 0 0 24 31.86c1.92 0 3.62-.46 4.97-1.31l4.79 3.71C31.14 36.7 27.65 38 24 38c-5.93 0-11.01-3.4-13.45-8.36l.17-1.01 4.06-2.85h.8z" fill="#34A853"/>\n' +
      '      <path d="M15.59 20.21a8.864 8.864 0 0 0 0 5.58l-5.03 3.86c-.98-2-1.53-4.25-1.53-6.64 0-2.39.55-4.64 1.53-6.64l1-.22 3.81 2.98.22 1.08z" fill="#FBBC05"/>\n' +
      '      <path d="M24 14.14c2.11 0 4.02.75 5.52 1.98l4.36-4.36C31.22 9.43 27.81 8 24 8c-5.93 0-11.01 3.4-13.45 8.36l5.03 3.85A8.86 8.86 0 0 1 24 14.14z" fill="#EA4335"/>\n' +
      '    </svg>\n' +
      '    <div class="gradient-container"><div class="gradient"></div></div>\n' +
      '  </div>\n' +
      '  <div class="carousel">\n' +
      '    <a class="chip" href="https://vertexaisearch.cloud.google.com/grounding-api-redirect/AZnLMfyXqJN3K4FKueRIZDY2Owjs5Rw4dqgDOc6ZjYKsFo4GgENxLktR2sPHtNUuEBIUeqmUYc3jz9pLRq2cgSpc-4EoGBwQSTTpKk71CX7revnXUa54r9LxcxKgYxrUNBm5HpEm6JDNeJykc6NacPYv43M2wgkrhHCHCzHRyjEP2YR0Pxq4JQMUuOrLeTAYWB9oUb87FE5ksfuB6gimqO5-6uS3psR6">who won the 2024 mlb world series</a>\n' +
      '  </div>\n' +
      '</div>\n'
  },
  groundingChunks: [
    {
      web: {
        uri: 'https://vertexaisearch.cloud.google.com/grounding-api-redirect/AZnLMfwvs0gpiM4BbIcNXZnnp4d4ED_rLnIYz2ZwM-lwFnoUxXNlKzy7ZSbbs_E27yhARG6Gx2AuW7DsoqkWPfDFMqPdXfvG3n0qFOQxQ4MBQ9Ox9mTk3KH5KPRJ79m8V118RQRyhi6oK5qg5-fLQunXUVn_a42K7eMk7Kjb8VpZ4onl8Glv1lQQsAK7YWyYkQ7WkTHDHVGB-vrL2U2yRQ==',
        title: 'foxsports.com'
      }
    },
    {
      web: {
        uri: 'https://vertexaisearch.cloud.google.com/grounding-api-redirect/AZnLMfwxwBq8VYgKAhf3UC8U6U5D-i0lK4TwP-2Jf8ClqB-sI0iptm9GxgeaH1iHFbSi-j_C3UqYj8Ok0YDTyvg87S7JamU48pndrd467ZQbI2sI0yWxsCCZ_dosXHwemBHFL5TW2hbAqasq93CfJ09cp1jU',
        title: 'mlb.com'
      }
    }
  ],
  groundingSupports: [
    {
      segment: {
        endIndex: 131,
        text: 'The Los Angeles Dodgers won the 2024 World Series, defeating the New York Yankees in Game 5 on October 30, 2024, by a score of 7-6.'
      },
      groundingChunkIndices: [ 0, 1 ],
      confidenceScores: [ 0.7652759, 0.7652759 ]
    },
    {
      segment: {
        startIndex: 401,
        endIndex: 531,
        text: 'The Dodgers also became the first team in MLB postseason history to overcome a five-run deficit, fall behind again, and still win.'
      },
      groundingChunkIndices: [ 1 ],
      confidenceScores: [ 0.8487609 ]
    }
  ],
  retrievalMetadata: { googleSearchDynamicRetrievalScore: 0.93359375 },
  webSearchQueries: [ 'who won the 2024 mlb world series' ]
}

代码执行

Google Generative AI 还支持代码执行。使用内置的 CodeExecutionTool,您可以使模型生成代码、执行代码,并在最终补全中使用结果:
import { CodeExecutionTool } from "@google/generative-ai";
import { ChatGoogleGenerativeAI } from "@langchain/google-genai";

const codeExecutionTool: CodeExecutionTool = {
  codeExecution: {}, // 只需传递一个空对象即可启用它。
};
const codeExecutionModel = new ChatGoogleGenerativeAI({
  model: "gemini-2.5-pro",
  temperature: 0,
  maxRetries: 0,
}).bindTools([codeExecutionTool]);

const codeExecutionResult = await codeExecutionModel.invoke("Use code execution to find the sum of the first and last 3 numbers in the following list: [1, 2, 3, 72638, 8, 727, 4, 5, 6]");

console.dir(codeExecutionResult.content, { depth: null });
[
  {
    type: 'text',
    text: "Here's how to find the sum of the first and last three numbers in the given list using Python:\n" +
      '\n'
  },
  {
    type: 'executableCode',
    executableCode: {
      language: 'PYTHON',
      code: '\n' +
        'my_list = [1, 2, 3, 72638, 8, 727, 4, 5, 6]\n' +
        '\n' +
        'first_three_sum = sum(my_list[:3])\n' +
        'last_three_sum = sum(my_list[-3:])\n' +
        'total_sum = first_three_sum + last_three_sum\n' +
        '\n' +
        'print(f"{first_three_sum=}")\n' +
        'print(f"{last_three_sum=}")\n' +
        'print(f"{total_sum=}")\n' +
        '\n'
    }
  },
  {
    type: 'codeExecutionResult',
    codeExecutionResult: {
      outcome: 'OUTCOME_OK',
      output: 'first_three_sum=6\nlast_three_sum=15\ntotal_sum=21\n'
    }
  },
  {
    type: 'text',
    text: 'Therefore, the sum of the first three numbers (1, 2, 3) is 6, the sum of the last three numbers (4, 5, 6) is 15, and their total sum is 21.\n'
  }
]
您还可以将此生成内容作为聊天历史传递回模型:
const codeExecutionExplanation = await codeExecutionModel.invoke([
  codeExecutionResult,
  {
    role: "user",
    content: "请解释我提出的问题、您编写的代码以及您得到的答案。",
  }
])

console.log(codeExecutionExplanation.content);
You asked for the sum of the first three and the last three numbers in the list `[1, 2, 3, 72638, 8, 727, 4, 5, 6]`.

Here's a breakdown of the code:

1. **`my_list = [1, 2, 3, 72638, 8, 727, 4, 5, 6]`**: This line defines the list of numbers you provided.

2. **`first_three_sum = sum(my_list[:3])`**: This calculates the sum of the first three numbers.  `my_list[:3]` is a slice of the list that takes elements from the beginning up to (but not including) the index 3.  So, it takes elements at indices 0, 1, and 2, which are 1, 2, and 3. The `sum()` function then adds these numbers together.

3. **`last_three_sum = sum(my_list[-3:])`**: This calculates the sum of the last three numbers. `my_list[-3:]` is a slice that takes elements starting from the third element from the end and goes to the end of the list. So it takes elements at indices -3, -2, and -1 which correspond to 4, 5, and 6. The `sum()` function adds these numbers.

4. **`total_sum = first_three_sum + last_three_sum`**: This adds the sum of the first three numbers and the sum of the last three numbers to get the final result.

5. **`print(f"{first_three_sum=}")`**, **`print(f"{last_three_sum=}")`**, and **`print(f"{total_sum=}")`**: These lines print the calculated sums in a clear and readable format.


The output of the code was:

* `first_three_sum=6`
* `last_three_sum=15`
* `total_sum=21`

Therefore, the answer to your question is 21.

上下文缓存

上下文缓存允许您将某些内容传递给模型一次,缓存输入令牌,然后在后续请求中引用缓存的令牌以降低成本。您可以使用 GoogleAICacheManager 类创建 CachedContent 对象,然后使用 enableCachedContent() 方法将 CachedContent 对象传递给您的 ChatGoogleGenerativeAIModel
import { ChatGoogleGenerativeAI } from "@langchain/google-genai";
import {
  GoogleAICacheManager,
  GoogleAIFileManager,
} from "@google/generative-ai/server";

const fileManager = new GoogleAIFileManager(process.env.GOOGLE_API_KEY);
const cacheManager = new GoogleAICacheManager(process.env.GOOGLE_API_KEY);

// 上传文件以供缓存
const pathToVideoFile = "/path/to/video/file";
const displayName = "example-video";
const fileResult = await fileManager.uploadFile(pathToVideoFile, {
    displayName,
    mimeType: "video/mp4",
});

// 上传完成后创建缓存内容
const cachedContent = await cacheManager.create({
    model: "models/gemini-2.5-flash",
    displayName: displayName,
    systemInstruction: "您是一位专家视频分析师,您的工作是根据您有权访问的视频文件回答用户的查询。",
    contents: [
        {
            role: "user",
            parts: [
                {
                    fileData: {
                        mimeType: fileResult.file.mimeType,
                        fileUri: fileResult.file.uri,
                    },
                },
            ],
        },
    ],
    ttlSeconds: 300,
});

// 将缓存的视频传递给模型
const model = new ChatGoogleGenerativeAI({});
model.useCachedContent(cachedContent);

// 使用缓存的视频调用模型
await model.invoke("总结视频");
注意
  • 上下文缓存的最小输入令牌数为 32,768,最大值与给定模型的最大值相同。

Gemini 提示常见问题

截至本文档撰写之时(2023/12/12),Gemini 对其接受的提示类型和结构有一些限制。具体来说:
  1. 当提供多模态(图像)输入时,您最多只能传递 1 条“human”(用户)类型的消息。您不能传递多条消息(尽管单条 human 消息可以包含多个内容条目)。
  2. 系统消息不受原生支持,如果存在,将与第一条 human 消息合并。
  3. 对于常规聊天对话,消息必须遵循 human/ai/human/ai 交替模式。您不能连续提供 2 条 AI 或 human 消息。
  4. 如果消息违反 LLM 的安全检查,可能会被阻止。在这种情况下,模型将返回空响应。

API 参考

有关所有 ChatGoogleGenerativeAI 功能和配置的详细文档,请访问 API 参考