Logo

Perplexity LLM

Installation

npm i @llamaindex/perplexity
pnpm add @llamaindex/perplexity
yarn add @llamaindex/perplexity
bun add @llamaindex/perplexity

Usage

import { Settings } from "llamaindex";
import { perplexity } from "@llamaindex/perplexity";
Settings.llm = perplexity({
apiKey: "<YOUR_API_KEY>",
model: "sonar", // or available models 
});

Example

import { perplexity } from "@llamaindex/perplexity";

const perplexityLlm = perplexity({
  apiKey: "<YOUR_API_KEY>",
  model: "sonar", // or avaiable models
});

async function main() {
  const response = await perplexityLlm.chat({
    messages: [
      {
        role: "system",
        content: "You are an AI assistant",
      },
      {
        role: "user",
        content: "Tell me about San Francisco",
      },
    ],
    stream: false,
  });
  console.log(response);

  const stream = await perplexityLlm.chat({
    messages: [
      {
        role: "system",
        content: "You are a creative AI assistant that tells engaging stories",
      },
      {
        role: "user",
        content: "Tell me a short story",
      },
    ],
    stream: true,
  });

  console.log("\nStreaming response:");
  for await (const chunk of stream) {
    process.stdout.write(chunk.delta);
  }
}

Full Example

import { perplexity } from "@llamaindex/perplexity";
import { Document, Settings, VectorStoreIndex } from "llamaindex";

// Use the perplexity LLM
Settings.llm = perplexity({ model: "sonar", apiKey: "<YOUR_API_KEY>" });

async function main() {
  const document = new Document({ text: essay, id_: "essay" });

  // Load and index documents
  const index = await VectorStoreIndex.fromDocuments([document]);

  // get retriever
  const retriever = index.asRetriever();

  // Create a query engine
  const queryEngine = index.asQueryEngine({
    retriever,
  });

  const query = "What is the meaning of life?";

  // Query
  const response = await queryEngine.query({
    query,
  });

  // Log the response
  console.log(response.response);
}

Available Models

The following models are available:

  • sonar: 128k context window
  • sonar-pro: 200k context window
  • sonar-deep-research: 128k context window
  • sonar-reasoning: 128k context window
  • sonar-reasoning-pro: 128k context window
  • r1-1776: 128k context window

Limitations

Currently does not support function calling.

API Reference

Edit on GitHub

Last updated on