Skip to content
NEWError doctor and Watchtower: failed n8n runs explained in plain words, and emailed to you. See what is new

Library / RAG & Knowledge Bases

RAG & Knowledge Bases

Build Web Vector Datasets with Bright Data and Gemini

When you run it, Bright Data crawls a website, Gemini creates embeddings, and an AI agent stores them in Pinecone for use with LLMs.

Import it free Sign in to open it

What it does

## Note Please make sure to set the URL for web crawling. Web-Unlocker Product is being utilized for performing the web scrapping. This workflow is utilizing the Basic LLM Chain, Information Extraction with the AI Agents for formatting, extracting and persisting the response in PineCone Vector Database

The steps

  1. When clicking ‘Test workflow’
  2. AI Agent
  3. Pinecone Vector Store
  4. Embeddings Google Gemini
  5. Default Data Loader
  6. Recursive Character Text Splitter
  7. Google Gemini Chat Model1
  8. Google Gemini Chat Model2
  9. Google Gemini Chat Model
  10. Structured Output Parser
  11. Set Fields - URL and Webhook URL
  12. Make a web request
  13. Structured JSON Data Formatter
  14. Webhook for structured data

16 steps in total.

Similar automations

RAG & Knowledge BasesBuild Vector Datasets with Bright Data, Gemini and Pinecone48 stepsBuilding Blocks & UtilitiesCompare Two Datasets with the Compare Datasets Node4 stepsBuilding Blocks & UtilitiesCompare Two Datasets for Differences5 stepsReports, Analytics & DashboardsCompare Two MySQL Order Datasets5 steps