聊天管道

这将帮助您开始使用 Pipeshift 聊天模型。有关所有 ChatPipeshift 功能和配置的详细文档，请前往 API 参考。

概述

集成详细信息

类	包	本地化	序列 化	JS 支持	软件包下载	最新包装
ChatPipeshift	langchain-pipeshift	❌	-	❌

模型特点

工具调用	结构化输出	JSON 模式	图像输入	音频输入	视频输入	令牌级流式处理	本机异步	Token 使用情况	日志
❌	❌	✅	✅	❌	❌	✅	✅	✅	-

设置

要访问 Pipeshift 模型，您需要在 Pipeshift 上创建一个帐户，获取 API 密钥，并安装langchain-pipeshift集成包。

凭据

前往 Pipeshift 注册 Pipeshift 并生成 API 密钥。完成此作后，设置 PIPESHIFT_API_KEY 环境变量：

import getpass
import os

if not os.getenv("PIPESHIFT_API_KEY"):
    os.environ["PIPESHIFT_API_KEY"] = getpass.getpass("Enter your Pipeshift API key: ")

如果您想自动跟踪模型调用，您还可以通过取消下面的注释来设置您的 LangSmith API 密钥：

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

安装

LangChain Pipeshift 集成位于langchain-pipeshift包：

%pip install -qU langchain-pipeshift

Note: you may need to restart the kernel to use updated packages.

实例

现在我们可以实例化我们的 Model 对象并生成聊天补全：

from langchain_pipeshift import ChatPipeshift

llm = ChatPipeshift(
    model="meta-llama/Meta-Llama-3.1-8B-Instruct",
    temperature=0,
    max_tokens=512,
    # other params...
)

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='Here is the translation:\n\nJe suis amoureux du programme. \n\nHowever, a more common translation would be:\n\nJ\'aime programmer.\n\nNote that "Je suis amoureux" typically implies romantic love, whereas "J\'aime" is a more casual way to express affection or enjoyment for an activity, in this case, programming.', additional_kwargs={}, response_metadata={}, id='run-5cad8e5c-d089-44a8-8dcd-22736cde7d7b-0')

print(ai_msg.content)

Here is the translation:

Je suis amoureux du programme. 

However, a more common translation would be:

J'aime programmer.

Note that "Je suis amoureux" typically implies romantic love, whereas "J'aime" is a more casual way to express affection or enjoyment for an activity, in this case, programming.

链接

我们可以用 prompt 模板链接我们的模型，如下所示：

from langchain_core.prompts import ChatPromptTemplate

prompt = ChatPromptTemplate(
    [
        (
            "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 参考：ChatPromptTemplate

AIMessage(content="Das ist schön! Du liebst Programmieren! (That's great! You love programming!)\n\nWould you like to know the German translation of a specific programming-related term or phrase, or would you like me to help you with something else?", additional_kwargs={}, response_metadata={}, id='run-8a4b7d56-23d9-43a7-8fb2-e05f556d94bd-0')

API 参考

有关所有 ChatPipeshift 功能和配置的详细文档，请访问 API 参考：https://dashboard.pipeshift.com/docs

相关

• 聊天模型概念指南
• 聊天模型操作指南