Skip to main content
Open In ColabOpen on GitHub

ChatMistralAI

这将帮助您开始使用 Mistral 聊天模型。有关 ChatMistralAI 所有功能和配置的详细文档，请前往 API 参考。ChatMistralAI 类建立在 Mistral API 之上。有关 Mistral 支持的所有模型列表，请查看 此页面。

概述​

集成详情​

类包本地支持可序列化JS 支持包下载量包最新版本
ChatMistralAIlangchain_mistralai❌beta✅PyPI - DownloadsPyPI - Version

模型特性​

工具调用结构化输出JSON 模式图像输入音频输入视频输入Token 级流式输出原生异步Token 使用量Logprobs
✅✅✅❌❌❌✅✅✅❌

设置​

要访问 ChatMistralAI 模型，您需要创建一个 Mistral 帐户，获取 API 密钥，并安装 langchain_mistralai 集成包。

凭据​

需要有效的 API 密钥才能与 API 通信。完成此操作后，请设置 MISTRAL_API_KEY 环境变量：

import getpass
import os

if "MISTRAL_API_KEY" not in os.environ:
    os.environ["MISTRAL_API_KEY"] = getpass.getpass("Enter your Mistral API key: ")

为了启用模型调用的自动化跟踪，请设置您的 LangSmith API 密钥：

# os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
# os.environ["LANGSMITH_TRACING"] = "true"

安装​

LangChain Mistral 集成位于 langchain_mistralai 包中：

%pip install -qU langchain_mistralai

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了：

from langchain_mistralai import ChatMistralAI

llm = ChatMistralAI(
    model="mistral-large-latest",
    temperature=0,
    max_retries=2,
    # other params...
)
API Reference:ChatMistralAI

调用​

messages = [
    (
        "system",
        "You are a helpful assistant that translates English to French. Translate the user sentence.",
    ),
    ("human", "I love programming."),
]
ai_msg = llm.invoke(messages)
ai_msg
AIMessage(content='Sure, I\'d be happy to help you translate that sentence into French! The English sentence "I love programming" translates to "J\'aime programmer" in French. Let me know if you have any other questions or need further assistance!', response_metadata={'token_usage': {'prompt_tokens': 32, 'total_tokens': 84, 'completion_tokens': 52}, 'model': 'mistral-small', 'finish_reason': 'stop'}, id='run-64bac156-7160-4b68-b67e-4161f63e021f-0', usage_metadata={'input_tokens': 32, 'output_tokens': 52, 'total_tokens': 84})
print(ai_msg.content)
Sure, I'd be happy to help you translate that sentence into French! The English sentence "I love programming" translates to "J'aime programmer" in French. Let me know if you have any other questions or need further assistance!

Chaining​

我们可以像这样将我们的模型与提示模板进行 链接：

from langchain_core.prompts import ChatPromptTemplate

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

chain = prompt | llm
chain.invoke(
    {
        "input_language": "English",
        "output_language": "German",
        "input": "I love programming.",
    }
)
API Reference:ChatPromptTemplate
AIMessage(content='Ich liebe Programmierung. (German translation)', response_metadata={'token_usage': {'prompt_tokens': 26, 'total_tokens': 38, 'completion_tokens': 12}, 'model': 'mistral-small', 'finish_reason': 'stop'}, id='run-dfd4094f-e347-47b0-9056-8ebd7ea35fe7-0', usage_metadata={'input_tokens': 26, 'output_tokens': 12, 'total_tokens': 38})

API 参考​

请前往 API 参考 获取所有属性和方法的详细文档。