\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 生成式 AI 也支持代码执行。使用内置的 `CodeExecutionTool`，您可以让模型生成代码、执行代码，并在最终完成中使用结果：
```typescript theme={null}
import { CodeExecutionTool } from "@google/generative-ai";
import { ChatGoogleGenerativeAI } from "@langchain/google-genai";
const codeExecutionTool: CodeExecutionTool = {
codeExecution: {}, // Simply pass an empty object to enable it.
};
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 });
```
```text theme={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对话历史回传给模型：
```typescript theme={null}
const codeExecutionExplanation = await codeExecutionModel.invoke([
codeExecutionResult,
{
role: "user",
content: "Please explain the question I asked, the code you wrote, and the answer you got.",
}
])
console.log(codeExecutionExplanation.content);
```
```text theme={null}
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一次性传递给模型，缓存输入 Token，然后在后续请求中引用缓存的 Token 以降低成本。您可以使用 `GoogleAICacheManager` 类创建一个 `CachedContent` 对象，然后使用 `enableCachedContent()` 方法将 `CachedContent` 对象传递给您的 `ChatGoogleGenerativeAIModel`。
```typescript theme={null}
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);
// uploads file for caching
const pathToVideoFile = "/path/to/video/file";
const displayName = "example-video";
const fileResult = await fileManager.uploadFile(pathToVideoFile, {
displayName,
mimeType: "video/mp4",
});
// creates cached content AFTER uploading is finished
const cachedContent = await cacheManager.create({
model: "models/gemini-2.5-flash",
displayName: displayName,
systemInstruction: "You are an expert video analyzer, and your job is to answer " +
"the user's query based on the video file you have access to.",
contents: [
{
role: "user",
parts: [
{
fileData: {
mimeType: fileResult.file.mimeType,
fileUri: fileResult.file.uri,
},
},
],
},
],
ttlSeconds: 300,
});
// passes cached video to model
const model = new ChatGoogleGenerativeAI({});
model.useCachedContent(cachedContent);
// invokes model with cached video
await model.invoke("Summarize the video");
```
**注意**
* 上下文缓存的最低输入 Token 数为 32,768，最高值与给定模型的最高值相同。
## Gemini 提示词常见问题解答
截至本文档编写时（2023/12/12），Gemini 对其接受的提示词的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，您最多只能提供 1 条“人类”（用户）类型的消息。您不能传递多条消息（尽管单个人类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，将与第一条人类消息合并。
3. 对于常规聊天对话，消息必须遵循人类/ai/人类/ai 交替模式。您不能连续提供 2 条 AI 或人类消息。
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](https://reference.langchain.com/javascript/langchain-google-genai/ChatGoogleGenerativeAI)。
***
> 官方原文：[src/oss/javascript/integrations/chat/google\_generative\_ai.mdx](https://github.com/langchain-ai/docs/blob/main/src/oss/javascript/integrations/chat/google_generative_ai.mdx) · 非官方翻译，译文由 AI 生成，以英文原文为准。
This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.