Documents into crisp meaning-blocks for precise helper answers

The scenario takes a document from novofon, cuts the text and repackages it into short meaning-blocks, storing them for search in inmemory — so the helper answers more precisely.

  • Helper answers land, not miss
  • Text cut into self-contained blocks
  • Search by meaning, not by a wall of text
  • Load the documents once
Default Data LoaderEmbeddings OpenAI
Connect inmemory and goScriptera

How it works

To connect novofon and Default Data Loader, you don't need a developer: a ready-made scenario links them in minutes.

  1. Starts when: When clicking ‘Execute workflow’
  2. Then: Download .TXT File for Ingest
  3. Then: Extract Text from .TXT File
  4. Then: Chunk Text
  5. Check: Loop Over Chunks
  6. Then: Blockify Ingest API
  7. Then: Extract IdeaBlocks from API Response
  8. Then: Simple IdeaBlock Vector Store
  9. Then: Query Data Tool
  10. Then: AI Agent
  11. Starts when: RAG Chatbot
  12. Then: Default Data Loader
  13. Then: Embed Individual IdeaBlocks (Already Separated)
  14. Then: Embeddings OpenAI
  15. Then: OpenAI Chat Model

You can launch this novofon + Default Data Loader integration in Scriptera: describe the task in plain words — the scenario is built, launched and monitored for you.

Similar scenarios