> ## Documentation Index
> Fetch the complete documentation index at: https://docs.lindy.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Perplexity

> Search the web with AI-powered research using Perplexity models for real-time information.

<div style={{ display: 'flex', justifyContent: 'center', margin: '2rem 0' }}>
  <div className="video-card">
    <video src="https://lindy-docs-content.nyc3.digitaloceanspaces.com/Human%20in%20Loop.mp4" width="600" autoPlay muted loop playsInline style={{ display: 'block', width: '100%', borderRadius: '16px' }} />
  </div>
</div>

## Overview

The Search Perplexity action gives your agent access to real-time web search with AI-powered research capabilities. Perfect for:

* **Real-time information** — access current news, trends, and up-to-date data
* **Research tasks** — get detailed answers with sources and citations
* **Fact checking** — verify claims and get authoritative information

## Search Perplexity Action

* **What it does**: Searches the web using Perplexity's AI models to provide sourced answers to your queries with real-time information.

<Frame>
  <img src="https://mintcdn.com/lindyai/QWdJNkViLsD1veyH/lindy-brand-assets/perplexity.png?fit=max&auto=format&n=QWdJNkViLsD1veyH&q=85&s=476f0476db319004654da7f75de81b95" alt="Search Perplexity action configuration" width="1876" height="1136" data-path="lindy-brand-assets/perplexity.png" />
</Frame>

### Inputs

* **Query**: The search query or question you want answered
* **Model**: Choose from Perplexity's model lineup based on your needs

### Outputs

* **Response**: The answer to your query
* **Citations**: Sources and references used in the response

### Query Options

You have two ways to set the query:

* **Manual Query**: Write your search query directly
* **AI-Generated Query**: Let your agent craft the optimal query based on workflow context

### Model Selection

| Model                   | Description                                   | Strength |
| ----------------------- | --------------------------------------------- | -------- |
| **Sonar**               | Quick research and basic searches             | ⭐        |
| **Sonar Pro**           | Better searches with more detailed results    | ⭐⭐       |
| **Sonar Reasoning**     | Adds reasoning capabilities to search results | ⭐⭐⭐      |
| **Sonar Reasoning Pro** | Advanced reasoning with better analysis       | ⭐⭐⭐⭐     |
| **Sonar Deep Research** | Uses Perplexity's deep research function      | ⭐⭐⭐⭐⭐    |

<Tip>
  Sonar Reasoning Pro is recommended for most use cases as it provides the best balance of reasoning capability, search quality, and performance.
</Tip>

## Best Practices

<AccordionGroup>
  <Accordion title="Query Optimization">
    * Be specific about what information you need
    * Include timeframes when relevant ("latest", "2024", "recent")
    * Use AI query generation when context is important
    * Test different phrasings for complex topics
    * Include industry or domain context for better results
  </Accordion>

  <Accordion title="Model Selection Strategy">
    * Start with lower-tier models for simple queries
    * Use Deep Research for comprehensive analysis
    * Consider cost vs. thoroughness trade-offs
    * Use Reasoning models when you need logical connections
    * Scale model choice to query complexity
  </Accordion>
</AccordionGroup>

## Next Steps

<CardGroup cols={2}>
  <Card title="Apify Web Scraping" icon="square-code" href="/skills/web-browsing/apify">
    Extract specific data from websites found in your research
  </Card>

  <Card title="Context Management" icon="database" href="/skills/lindy-utilities/context">
    Store important research findings for your agent's memory
  </Card>

  <Card title="Set Variables" icon="database" href="/skills/lindy-utilities/set-variables">
    Save search results for use in other workflow steps
  </Card>

  <Card title="LLM Call" icon="database" href="/skills/lindy-utilities/llm-call">
    Analyze Perplexity results with custom AI prompts
  </Card>
</CardGroup>