Perplexity AI

Perplexity AI is a web search engine that uses a large language model to process queries and synthesize responses based on web search results. With a conversational approach, Perplexity AI allows users to ask follow-up questions and receive answers with citations to its sources from the internet.

Utilities · Perplexity AI

Details

IDPerplexity AI
ProviderPerplexity AI Inc
CategoryUtilities
From Version6.0.0
Docker Imagedemisto/python3:3.12.8.3296088

README

Perplexity AI is a web search engine that uses a large language model to process queries and synthesize responses based on web search results. With a conversational approach, Perplexity AI allows users to ask follow-up questions and receive answers with citations to its sources from the internet.

Configure Perplexity AI on Cortex XSOAR

  1. Navigate to Settings > Integrations > Servers & Services.
  2. Search for Perplexity AI.
  3. Click Add instance to create and configure a new integration instance.

    Parameter Description Required
    URL for Perplexity AI   True
    Perplexity AI API Key   True
    Cloudflare Access Client Id   False
    Cloudflare Access Client Secret   False
    Perplexity AI Model Available models are: sonar,sonar-pro,sonar-deep-research,sonar-reasoning,sonar-reasoning-pro,r1-1776 True
  4. Click Test to validate the URLs, token, and connection.

Commands

You can execute these commands from the Cortex XSOAR CLI, as part of an automation, or in a playbook.
After you successfully execute a command, a DBot message appears in the War Room with the command details.

deepresearch-chat


Send a chat message. You may need to increase the command timeout in “advanced settings” from the default 5 minutes.

Base Command

deepresearch-chat

Input

Argument Name Description Required
systemmessage The system message to influence how the user message is handled - used in the “system” role. Default is Be precise and concise. Optional
usermessage The user’s question - used in the “users” role. Required
recentfilter Limit search to recent hour, day, week, month. Possible values are: hour, day, week, month. Optional
domainfilter Limit search to these domains. CSV list of domains of up to 3 domains. A ‘-‘ in front of the domain excludes it. Optional
jsonout Include JSON output in context if yes, with markdown in war room. Possible values are: yes, no. Default is no. Optional
citations Include research citations in the output. Possible values are: yes, no. Default is no. Optional
thinking Include thinking in the output. Possible values are: yes, no. Default is no. Optional
contextsize How much context is returned as results. Possible values are: low, medium, high. Default is medium. Optional

Context Output

There is no context output for this command.

Configuration parameters

  • url — URL for Perplexity AI (required)
  • apikey — Perplexity AI API Key (required)
  • cf_auth — Cloudflare Access Client Id
  • model — Perplexity AI Model (required)
  • insecure — Trust any certificate (not secure)
  • proxy — Use system proxy settings

Commands (1)

  • deepresearch-chat

    Send a chat message. You may need to increase the command timeout in "advanced settings" from the default 5 minutes.

category: Utilities
provider: Perplexity AI Inc
commonfields:
  id: Perplexity AI
  version: -1
sectionorder:
  - Connect
  - Collect
configuration:
- defaultvalue: https://api.perplexity.ai
  display: URL for Perplexity AI
  name: url
  required: true
  section: Connect
  type: 0
- display: Perplexity AI API Key
  displaypassword: Perplexity AI API Key
  hiddenusername: true
  name: apikey
  required: true
  section: Connect
  type: 9
- display: Cloudflare Access Client Id
  displaypassword: Cloudflare Access Client Secret
  name: cf_auth
  required: false
  section: Connect
  type: 9
- additionalinfo: 'Available models are: sonar,sonar-pro,sonar-deep-research,sonar-reasoning,sonar-reasoning-pro,r1-1776'
  defaultvalue: sonar-deep-research
  display: Perplexity AI Model
  name: model
  required: true
  type: 0
  section: Collect
- display: Trust any certificate (not secure)
  name: insecure
  type: 8
  section: Connect
  advanced: true
  required: false
- display: Use system proxy settings
  name: proxy
  type: 8
  section: Connect
  advanced: true
  required: false
description: Perplexity AI is a web search engine that uses a large language model to process queries and synthesize responses based on web search results.  With a conversational approach, Perplexity AI allows users to ask follow-up questions and receive answers with citations to its sources from the internet.
display: Perplexity AI
name: Perplexity AI
script:
  commands:
  - arguments:
    - defaultValue: Be precise and concise.
      description: The system message to influence how the user message is handled - used in the "system" role.
      name: systemmessage
    - description: The user's question - used in the "users" role.
      name: usermessage
      required: true
    - auto: PREDEFINED
      description: Limit search to recent hour, day, week, month.
      name: recentfilter
      predefined:
      - hour
      - day
      - week
      - month
    - description: Limit search to these domains. CSV list of domains of up to 3 domains. A '-' in front of the domain excludes it.
      name: domainfilter
    - auto: PREDEFINED
      defaultValue: no
      description: Include JSON output in context if yes, with markdown in war room.
      name: jsonout
      predefined:
      - yes
      - no
    - auto: PREDEFINED
      defaultValue: no
      description: Include research citations in the output.
      name: citations
      predefined:
      - yes
      - no
    - auto: PREDEFINED
      defaultValue: no
      description: Include thinking in the output.
      name: thinking
      predefined:
      - yes
      - no
    - auto: PREDEFINED
      default: true
      defaultValue: medium
      description: How much context is returned as results.
      name: contextsize
      predefined:
      - low
      - medium
      - high
    description: Send a chat message.  You may need to increase the command timeout in "advanced settings" from the default 5 minutes.
    name: deepresearch-chat
    outputs:
    - contextPath: Deepresearch
      description: Research report.
      type: Unknown
  dockerimage: demisto/python3:3.12.8.3296088
  runonce: false
  script: ''
  subtype: python3
  type: python
fromversion: 6.0.0
tests:
- No tests (auto formatted)