Skip to content
NEWMarketplace and the trig8n Agent: sell what you build, and get plans and changes that are tested before you see them. See what is new

Library / RAG & Knowledge Bases

RAG & Knowledge Bases

Insert and Retrieve Documents in a Vector Store

When you run it manually, it loads essay documents into a vector store with OpenAI embeddings and retrieves them for question answering.

What it does

# Insert and retrieve documents ## Overview Automated workflow: Insert and retrieve documents. This workflow integrates 16 different services: stickyNote, httpRequest, textSplitterRecursiveCharacterTextSplitter, code, splitOut. It contains 32 nodes and follows best practices for error handling and security. ## Workflow Details - Total Nodes: 32 - Node Types: 16 - Error Handling: ✅ Implemented - Security: ✅ Hardened (no sensitive data) - Documentation: ✅ Complete ## Node Breakdown - When clicking "Execute Workflow": manualTrigger - Fetch Essay List: httpRequest - Extract essay names: html - Split out into items: splitOut - Fetch essay texts: httpRequest - Limit to first 3: limit - Extract Text Only: html - Sticky Note3: stickyNote - Sticky Note5: stickyNote - Recursive Character Text Splitter1: textSplitterRecursiveCharacterTextSplitter - ... and 22 more nodes ## Usage Instructions 1. Configure Credentials: Set up all required API keys and credentials 2. Update Variables: Replace any placeholder values with actual data 3. Test Workflow: Run in test mode to verify functionality 4. Deploy: Activate the workflow for production use ## Security Notes - All sensitive data has been removed or replaced with placeholders - Error handling is implemented for reliability - Follow security best practices when configuring credentials ## Troubleshooting - Check error logs if workflow fails - Verify all credentials are properly configured - Ensure all required services are accessible

The steps

  1. When clicking "Execute Workflow"
  2. Fetch Essay List
  3. Extract essay names
  4. Split out into items
  5. Fetch essay texts
  6. Limit to first 3
  7. Extract Text Only
  8. Recursive Character Text Splitter1
  9. Generate response
  10. Compose citations
  11. Answer the query based on chunks
  12. Prepare chunks
  13. Set max chunks to send to model
  14. Embeddings OpenAI2

42 steps in total.

Similar automations