A knowledge base from your documents where every piece keeps its context

The scenario takes documents from your pruffme, cuts them into meaningful pieces and adds context to each, then stores them in the Postgres PGVector Store knowledge base — so an assistant answers more accurately.

  • Every document piece keeps its context
  • The assistant answers accurately, not off-target
  • Documents from storage into a knowledge base by themselves
  • Fewer confidently wrong answers
Pinecone Vector StoreEmbeddings Google GeminiDefault Data Loader
Connect a knowledge base and launchScriptera

How it works

To create pruffme records from Postgres PGVector Store without manual input, use a ready-made scenario.

  1. Starts when: When clicking ‘Test workflow’
  2. Then: Get Document From Google Drive
  3. Then: Extract Text Data From Google Document
  4. Then: Split Document Text Into Sections
  5. Then: Prepare Sections For Looping
  6. Check: Loop Over Items
  7. Then: AI Agent - Prepare Context
  8. Then: Concatenate the context and section text
  9. Then: Pinecone Vector Store
  10. Then: OpenRouter Chat Model
  11. Then: Embeddings Google Gemini
  12. Then: Default Data Loader
  13. Then: Recursive Character Text Splitter

You can launch this Postgres PGVector Store + pruffme integration in Scriptera: describe the task in plain words — the scenario is built, launched and monitored for you.

Similar scenarios