Search, Summarize Web Data with Perplexity, Gemini AI & Bright Data to Webhooks

Name: Search, Summarize Web Data with Perplexity, Gemini AI & Bright Data to Webhooks
Rating: 5 (5 reviews)
Author: Free N8N

Beginner

9 nodes connected

detail.loadingPreview

Free N8N Temples

400 views

12 downloads

Data ProcessingAIAPI IntegrationAutomationBright DataGoogle GeminiPerplexitySummarizationWeb Scraping

Automate web scraping and data summarization using Bright Data and AI models like Google Gemini, sending structured output to webhooks.

About This Workflow

This workflow leverages Bright Data's web scraping capabilities to fetch data from Perplexity.ai, specifically about BrightData. The extracted HTML content is then processed for readability and summarized using Google Gemini's AI models. Finally, the structured and summarized output is sent to a webhook for further processing or integration.

Key Features

Bright Data Integration: Triggers Perplexity searches and downloads snapshot data via Bright Data API.
AI-Powered Summarization: Utilizes Google Gemini (Flash Exp) for text extraction and summarization.
Data Processing Pipeline: Includes nodes for data loading, text splitting, information extraction, and summarization.
Error Handling: Checks for errors in the Bright Data snapshot process.
Webhook Notification: Sends the final processed output to a specified webhook URL.

How To Use

Trigger: The workflow starts with a manual trigger ('When clicking ‘Test workflow’').
Perplexity Search: The Perplexity Search Request node initiates a search on Perplexity.ai for information about BrightData using Bright Data's API.
Snapshot Trigger: The search triggers a Bright Data snapshot, and its ID is captured.
Status Check Loop: The Check Snapshot Status node polls the Bright Data API for the snapshot's progress. The If node controls this loop, waiting for the status to be 'ready' before proceeding or waiting if not.
Download Snapshot: Once ready, the Download Snapshot node fetches the data from Bright Data.
Data Extraction: The Readable Data Extractor uses Google Gemini Chat Model1 to convert the HTML answer into readable text.
Text Splitting & Loading: The Recursive Character Text Splitter and Default Data Loader prepare the text for the summarization model.
Summarization: The Summarization of search result node uses Google Gemini Chat Model to summarize the extracted content.
Webhook Notification: The final summarized output is sent to the Webhook Notifier node.

Apps Used

API Integration

Automation

Bright Data

Google Gemini

Perplexity

Summarization

Web Scraping

Workflow JSON

{
  "id": "482bd7c8-9ed0-417c-9e6f-1b4ed73707aa",
  "name": "Search, Summarize Web Data with Perplexity, Gemini AI & Bright Data to Webhooks",
  "nodes": 9,
  "category": "Data Processing",
  "status": "active",
  "version": "1.0.0"
}

Note: This is a sample preview. The full workflow JSON contains node configurations, credentials placeholders, and execution logic.

Get This Workflow

ID: 482bd7c8-9ed0...

About the Author

N8N_Community_Pick

Curator

Hand-picked high quality workflows from the global community.

Statistics

Downloads12

Rating5/5

Get Custom Workflow

Need a specific automation? Our experts can build it for you.

Trusted by top companies
7+ years experience

Related Workflows

Discover more workflows you might like

Beginner

Data Processingmetadatamultilinguallocalization

Multilingual Metadata Generation from Gmail and Google Sheets

Automate structured metadata generation in English and Chinese by processing Gmail emails and Google Sheets data.

11 nodes

472

View Workflow

Advanced

Data Processingmetadatainternationalizationlocalization

Generate Structured Metadata in English and Chinese

This workflow demonstrates how to generate structured metadata in both English and Chinese. It fetches data, processes it, and saves it in a structured format.

26 nodes

462

View Workflow

Intermediate

Data Processingmetadatalocalizationmultilingual

Generate Structured Metadata with Multiple Languages

This workflow demonstrates generating structured metadata, specifically supporting both English and Chinese output.

12 nodes

269

View Workflow

Trigger: The workflow starts with a manual trigger ('When clicking ‘Test workflow’').
Perplexity Search: The Perplexity Search Request node initiates a search on Perplexity.ai for information about BrightData using Bright Data's API.
Snapshot Trigger: The search triggers a Bright Data snapshot, and its ID is captured.
Status Check Loop: The Check Snapshot Status node polls the Bright Data API for the snapshot's progress. The If node controls this loop, waiting for the status to be 'ready' before proceeding or waiting if not.
Download Snapshot: Once ready, the Download Snapshot node fetches the data from Bright Data.
Data Extraction: The Readable Data Extractor uses Google Gemini Chat Model1 to convert the HTML answer into readable text.
Text Splitting & Loading: The Recursive Character Text Splitter and Default Data Loader prepare the text for the summarization model.
Summarization: The Summarization of search result node uses Google Gemini Chat Model to summarize the extracted content.
Webhook Notification: The final summarized output is sent to the Webhook Notifier node.

{ "id": "482bd7c8-9ed0-417c-9e6f-1b4ed73707aa", "name": "Search, Summarize Web Data with Perplexity, Gemini AI & Bright Data to Webhooks", "nodes": 9, "category": "Data Processing", "status": "active", "version": "1.0.0" }