Perplexity Sonar AI Research Assistant Integration - n8n Workflow

Content Creators & Marketers: Need verified, cited information quickly for articles or blog posts.
Data Analysts: Required to perform rapid, structured searches on recent topics using a reliable research API.
n8n Automation Engineers: Looking for advanced n8n templates integrating cutting-edge AI services like Perplexity.
Researchers & Academics: Want to streamline the initial search phase of their investigations, leveraging the power of an automated n8n node.

Leveraging the power of AI for research is critical in today's fast-paced environment. This highly efficient n8n workflow turns a simple input query into a professional research request submitted directly to the Perplexity Sonar model. Unlike standard LLMs, Perplexity specializes in search and citation, providing high-quality, verifiable answers. This specific n8n template is designed to be called as a sub-workflow, making it a reusable component in larger n8n automation projects. The entire n8n process ensures that you receive clean, relevant, and fully extracted content, transforming your n8n workflow into a high-powered research assistant.

This automation functions as a modular component, starting with an internal n8n trigger.

1. Trigger & Input: The n8n workflow begins with the 'When Executed by Another Workflow' n8n trigger, which allows it to receive input data (specifically, the query field) from a parent n8n workflow or an external API call.
2. Define Variables: The 'Set Prompt Variables' n8n node establishes the context for the AI. It defines a detailed System prompt outlining the AI assistant's helpful persona and captures the input query as the User prompt.
3. API Request: The 'Perplexity Research Content1' n8n node, an HTTP Request n8n node, sends the structured prompt to the Perplexity API (/chat/completions). Key parameters are set to enforce research quality, including using the robust sonar model, setting a low temperature for factual output (0.2), and crucially, setting returncitations: true and restricting the search to recent data (searchrecency_filter: "month"). This is the core action of this n8n template.

1. Extract Output: Finally, the 'Extract API Response' n8n node utilizes a Set n8n node to parse the complex JSON response from Perplexity and extract only the clean message.content, returning the concise research result to the calling n8n workflow.

To use this n8n template, follow these steps:

1. Import: Copy the provided n8n workflow JSON and paste it directly into your n8n instance using the 'New' -> 'Import from JSON' option.
2. Perplexity Credentials: You must configure the required credentials for the HTTP Request n8n node ('Perplexity Research Content1').
Click on the Credential field (labeled 'Header Auth account 2').
Select 'Create New Credential' for the 'HTTP Header Auth' type.
* The Perplexity API requires an Authorization header. Set the header name to Authorization and the header value to Bearer YOURPERPLEXITYAPI_KEY.
3. Testing: Since this n8n workflow uses an internal n8n trigger, you can test it manually by clicking 'Execute Workflow' and providing a test input object like {"query": "What were the key updates in n8n version 1.0?"}.

1. Integration: This n8n workflow is designed to be called via the 'Execute Workflow' n8n node from another main automation flow.

This n8n workflow leverages several key n8n nodes to achieve seamless research automation:

When Executed by Another Workflow (n8n trigger):
Function: Serves as the entry point for this sub-workflow, receiving the research query from a parent n8n process. This specialized n8n trigger makes the template reusable.
Key Configuration: Input Source set to Passthrough to receive all data from the parent execution.

Set Prompt Variables (Set n8n node):
Function: Constructs the necessary System and User message objects required by the Perplexity chat completion API.
Key Configuration: Dynamically pulls the User query using {{ $json.query }}.

Perplexity Research Content1 (HTTP Request n8n node):
Function: The core of the n8n automation, sending the request to api.perplexity.ai.
Key Configuration: Uses the sonar model, sets a low temperature (0.2) for accuracy, specifies maxtokens: 4000, and enables search integrity with returncitations: true and searchrecencyfilter: "month".

Extract API Response (Set n8n node):
Function: Cleans up the response by isolating the relevant text from the nested JSON structure returned by the API, ensuring a clean output from the n8n workflow.
Key Configuration: Extracts the content using the expression ={{ $json.choices[0].message.content }}.