ChatPerplexity

本指南将帮助你开始使用 Perplexity 聊天模型。有关 ChatPerplexity 所有功能和配置的详细文档，请参阅 API 参考。

¥This guide will help you getting started with Perplexity chat models. For detailed documentation of all ChatPerplexity features and configurations head to the API reference.

概述

¥Overview

集成详情

¥Integration details

Class	Package	Local	Serializable	PY support	Package downloads	Package latest
ChatPerplexity	@langchain/community	❌	beta	✅

模型特性

¥Model features

有关如何使用特定功能的指南，请参阅下方表格标题中的链接。

¥See the links in the table headers below for guides on how to use specific features.

Tool calling	Structured output	JSON mode	Image input	Audio input	Video input	Token-level streaming	Token usage	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。

¥Note that at the time of writing, Perplexity only supports structured outputs on certain usage tiers.

设置

¥Setup

要访问 Perplexity 模型，你需要创建一个 Perplexity 账户、获取 API 密钥并安装 @langchain/community 集成包。

¥To access Perplexity models you’ll need to create a Perplexity account, get an API key, and install the @langchain/community integration package.

凭证

¥Credentials

前往 https://perplexity.ai 注册 Perplexity 并生成 API 密钥。完成此操作后，请设置 PERPLEXITY_API_KEY 环境变量：

¥Head to https://perplexity.ai to sign up for Perplexity and generate an API key. Once you’ve done this set the PERPLEXITY_API_KEY environment variable:

export PERPLEXITY_API_KEY="your-api-key"

如果你想自动追踪模型调用，也可以通过取消注释以下内容来设置你的 LangSmith API 密钥：

¥If you want to get automated tracing of your model calls you can also set your LangSmith API key by uncommenting below:

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

安装

¥Installation

LangChain Perplexity 集成位于 @langchain/community 包中：

¥The LangChain Perplexity integration lives in the @langchain/community package:

tip

请参阅 此部分包含有关安装集成包的一般说明。

¥See this section for general instructions on installing integration packages.

npm

npm i @langchain/community @langchain/core

yarn

yarn add @langchain/community @langchain/core

pnpm

pnpm add @langchain/community @langchain/core

实例化

¥Instantiation

现在我们可以实例化我们的模型对象并生成聊天补全：

¥Now we can instantiate our model object and generate chat completions:

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

¥Invocation

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.

链接

¥Chaining

我们可以使用如下提示模板对我们的模型进行 chain 操作：

¥We can chain our model with a prompt template like so:

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

¥API reference

有关 ChatPerplexity 所有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

¥For detailed documentation of all ChatPerplexity features and configurations head to the API reference: https://api.js.langchain.com/classes/_langchain_community.chat_models_perplexity.ChatPerplexity.html