跳到主要内容

ChatPerplexity

本指南将帮助您开始使用 Perplexity 聊天模型。有关所有 ChatPerplexity 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PY 支持包下载量最新包
ChatPerplexity@langchain/communitybetaNPM - DownloadsNPM - Version

模型功能

请参阅下方表格标题中的链接,以获取有关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Token 级别流式传输Token 使用量Logprobs

请注意,在撰写本文时,Perplexity 仅在某些使用层级上支持结构化输出。

设置

要访问 Perplexity 模型,您需要创建一个 Perplexity 帐户,获取 API 密钥,并安装 @langchain/community 集成包。

凭证

访问 https://perplexity.ai 注册 Perplexity 并生成 API 密钥。完成后,设置 PERPLEXITY_API_KEY 环境变量

export PERPLEXITY_API_KEY="your-api-key"

如果您想获取模型调用的自动追踪,您还可以通过取消注释下方内容来设置您的 LangSmith API 密钥

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

安装

LangChain Perplexity 集成位于 @langchain/community 包中

提示

请参阅此部分,获取有关安装集成包的通用说明。

yarn add @langchain/community @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完成

import { ChatPerplexity } from "@langchain/community/chat_models/perplexity";

const llm = new ChatPerplexity({
model: "sonar",
temperature: 0,
maxTokens: undefined,
timeout: undefined,
maxRetries: 2,
// other params...
});

调用

const aiMsg = await llm.invoke([
{
role: "system",
content:
"You are a helpful assistant that translates English to French. Translate the user sentence.",
},
{
role: "user",
content: "I love programming.",
},
]);
aiMsg;
AIMessage {
"id": "run-71853938-aa30-4861-9019-f12323c09f9a",
"content": "J'adore la programmation.",
"additional_kwargs": {
"citations": [
"https://careersatagoda.com/blog/why-we-love-programming/",
"https://henrikwarne.com/2012/06/02/why-i-love-coding/",
"https://forum.freecodecamp.org/t/i-love-programming-but/497502",
"https://ilovecoding.org",
"https://thecodinglove.com"
]
},
"response_metadata": {
"tokenUsage": {
"promptTokens": 20,
"completionTokens": 9,
"totalTokens": 29
}
},
"tool_calls": [],
"invalid_tool_calls": []
}
console.log(aiMsg.content);
J'adore la programmation.

链式调用

我们可以像这样使用提示模板链式调用我们的模型

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 {
"id": "run-a44dc452-4a71-423d-a4ee-50a2d7c90abd",
"content": "**English to German Translation:**\n\n\"I love programming\" translates to **\"Ich liebe das Programmieren.\"**\n\nIf you'd like to express your passion for programming in more detail, here are some additional translations:\n\n- **\"Programming is incredibly rewarding and fulfilling.\"** translates to **\"Das Programmieren ist unglaublich lohnend und erfüllend.\"**\n- **\"I enjoy solving problems through coding.\"** translates to **\"Ich genieße es, Probleme durch Codieren zu lösen.\"**\n- **\"I find the process of creating something from nothing very satisfying.\"** translates to **\"Ich finde den Prozess, etwas aus dem Nichts zu schaffen, sehr befriedigend.\"**",
"additional_kwargs": {
"citations": [
"https://careersatagoda.com/blog/why-we-love-programming/",
"https://henrikwarne.com/2012/06/02/why-i-love-coding/",
"https://dev.to/dvddpl/coding-is-boring-why-do-you-love-coding-cl0",
"https://forum.freecodecamp.org/t/i-love-programming-but/497502",
"https://ilovecoding.org"
]
},
"response_metadata": {
"tokenUsage": {
"promptTokens": 15,
"completionTokens": 149,
"totalTokens": 164
}
},
"tool_calls": [],
"invalid_tool_calls": []
}

API 参考

有关所有 ChatPerplexity 功能和配置的详细文档,请参阅 API 参考:https://api.js.langchain.com/classes/\_langchain_community.chat_models_perplexity.ChatPerplexity.html

  • 聊天模型概念指南
  • 聊天模型操作指南

此页面对您有帮助吗?


您也可以留下详细的反馈 在 GitHub 上.