Skip to main content

ChatMistralAI

Mistral AI 是一个为其强大的开源模型提供托管的平台。

这将帮助你开始使用 ChatMistralAI 的聊天模型。有关所有 ChatMistralAI 功能和配置的详细文档,请参阅API 参考

概述

集成详情

本地可序列化Python 支持包下载量最新包
ChatMistralAI@langchain/mistralaiNPM - 下载量NPM - 版本

模型特性

请参阅下表标题中的链接,了解如何使用特定功能的指南。

工具调用结构化输出JSON 模式图像输入音频输入视频输入逐 token 流式传输token 使用情况logprobs

准备

要访问 Mistral AI 模型,你需要创建一个 Mistral AI 账户,获取 API 密钥,并安装 @langchain/mistralai 集成包。

凭证

点击此处注册 Mistral AI 并生成一个 API 密钥。完成此操作后,请设置 MISTRAL_API_KEY 环境变量:

export MISTRAL_API_KEY="your-api-key"

如果你想对模型调用进行自动追踪,也可以取消注释以下 LangSmith API 密钥的设置:

# export LANGSMITH_TRACING="true"
# export LANGSMITH_API_KEY="your-api-key"

安装

LangChain ChatMistralAI 集成位于 @langchain/mistralai 包中:

:::提示 请参阅安装集成包的一般说明部分。 :::

yarn add @langchain/mistralai @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结果:

import { ChatMistralAI } from "@langchain/mistralai";

const llm = new ChatMistralAI({
model: "mistral-large-latest",
temperature: 0,
maxRetries: 2,
// other params...
});

调用

向 Mistral 发送聊天消息时,需遵循以下要求:

  • 第一条消息 不能 是助手(AI)消息。
  • 消息 必须 在用户和助手(AI)之间交替发送。
  • 消息 不能 以助手(AI)或系统消息结尾。
const aiMsg = await llm.invoke([
[
"system",
"You are a helpful assistant that translates English to French. Translate the user sentence.",
],
["human", "I love programming."],
]);
aiMsg;
AIMessage {
"content": "J'adore la programmation.",
"additional_kwargs": {},
"response_metadata": {
"tokenUsage": {
"completionTokens": 9,
"promptTokens": 27,
"totalTokens": 36
},
"finish_reason": "stop"
},
"tool_calls": [],
"invalid_tool_calls": [],
"usage_metadata": {
"input_tokens": 27,
"output_tokens": 9,
"total_tokens": 36
}
}
console.log(aiMsg.content);
J'adore la programmation.

链式调用

我们可以像这样将模型与提示模板链式调用

import { ChatPromptTemplate } from "@langchain/core/prompts";

const prompt = ChatPromptTemplate.fromMessages([
[
"system",
"You are a helpful assistant that translates {input_language} to {output_language}.",
],
["human", "{input}"],
]);

const chain = prompt.pipe(llm);
await chain.invoke({
input_language: "English",
output_language: "German",
input: "I love programming.",
});
AIMessage {
"content": "Ich liebe Programmieren.",
"additional_kwargs": {},
"response_metadata": {
"tokenUsage": {
"completionTokens": 7,
"promptTokens": 21,
"totalTokens": 28
},
"finish_reason": "stop"
},
"tool_calls": [],
"invalid_tool_calls": [],
"usage_metadata": {
"input_tokens": 21,
"output_tokens": 7,
"total_tokens": 28
}
}

工具调用

Mistral 的 API 为其部分模型支持工具调用功能。您可以通过此页面查看哪些模型支持工具调用。

以下示例演示了如何使用该功能:

import { ChatMistralAI } from "@langchain/mistralai";
import { ChatPromptTemplate } from "@langchain/core/prompts";
import { z } from "zod";
import { tool } from "@langchain/core/tools";

const calculatorSchema = z.object({
operation: z
.enum(["add", "subtract", "multiply", "divide"])
.describe("The type of operation to execute."),
number1: z.number().describe("The first number to operate on."),
number2: z.number().describe("The second number to operate on."),
});

const calculatorTool = tool(
(input) => {
return JSON.stringify(input);
},
{
name: "calculator",
description: "A simple calculator tool",
schema: calculatorSchema,
}
);

// Bind the tool to the model
const modelWithTool = new ChatMistralAI({
model: "mistral-large-latest",
}).bindTools([calculatorTool]);

const calcToolPrompt = ChatPromptTemplate.fromMessages([
[
"system",
"You are a helpful assistant who always needs to use a calculator.",
],
["human", "{input}"],
]);

// Chain your prompt, model, and output parser together
const chainWithCalcTool = calcToolPrompt.pipe(modelWithTool);

const calcToolRes = await chainWithCalcTool.invoke({
input: "What is 2 + 2?",
});
console.log(calcToolRes.tool_calls);
[
{
name: 'calculator',
args: { operation: 'add', number1: 2, number2: 2 },
type: 'tool_call',
id: 'DD9diCL1W'
}
]

钩子函数

Mistral AI 支持三种事件的自定义钩子函数:beforeRequest(请求前)、requestError(请求错误)和 response(响应)。每种钩子函数类型的函数签名示例如下所示:

const beforeRequestHook = (
req: Request
): Request | void | Promise<Request | void> => {
// Code to run before a request is processed by Mistral
};

const requestErrorHook = (err: unknown, req: Request): void | Promise<void> => {
// Code to run when an error occurs as Mistral is processing a request
};

const responseHook = (res: Response, req: Request): void | Promise<void> => {
// Code to run before Mistral sends a successful response
};

将这些钩子添加到聊天模型中,可以通过将它们作为参数传递来自动添加:

import { ChatMistralAI } from "@langchain/mistralai";

const modelWithHooks = new ChatMistralAI({
model: "mistral-large-latest",
temperature: 0,
maxRetries: 2,
beforeRequestHooks: [beforeRequestHook],
requestErrorHooks: [requestErrorHook],
responseHooks: [responseHook],
// other params...
});

或者在实例化后分配并手动添加它们:

import { ChatMistralAI } from "@langchain/mistralai";

const model = new ChatMistralAI({
model: "mistral-large-latest",
temperature: 0,
maxRetries: 2,
// other params...
});

model.beforeRequestHooks = [...model.beforeRequestHooks, beforeRequestHook];
model.requestErrorHooks = [...model.requestErrorHooks, requestErrorHook];
model.responseHooks = [...model.responseHooks, responseHook];

model.addAllHooksToHttpClient();

方法 addAllHooksToHttpClient 在分配完整的更新后的钩子列表之前,会清除所有当前已添加的钩子,以避免钩子重复。

可以逐个移除钩子,也可以一次性从模型中清除所有钩子。

model.removeHookFromHttpClient(beforeRequestHook);

model.removeAllHooksFromHttpClient();

API 参考

有关 ChatMistralAI 所有功能和配置的详细文档,请访问 API 参考:https://api.js.langchain.com/classes/langchain_mistralai.ChatMistralAI.html


Was this page helpful?


You can also leave detailed feedback on GitHub.