Answers from your PDF documents — in plain words

The scenario reads your PDFs from storage, recognizes text even in scans, and answers questions about the documents — with a pointer to the source.

  • Ask in words — get an answer
  • Reads even scanned PDFs
  • Answers with a pointer to the document
  • Pulls files straight from Microsoft OneDrive
Embeddings OpenAIDefault Data LoaderQdrant Vector Store
Connect Postgres PGVector Store and launchScriptera

How it works

To connect Postgres PGVector Store and Microsoft OneDrive, you don't need a developer: a ready-made scenario links them in minutes.

  1. Starts when: When clicking ‘Test workflow’
  2. Then: Refresh collection
  3. Then: Search PDFs
  4. Check: Loop Over Items1
  5. Then: Edit Fields1
  6. Then: Execute Workflow
  7. Then: Mistral Upload
  8. Then: Mistral Signed URL
  9. Then: Mistral DOC OCR
  10. Then: Code
  11. Check: Loop Over Items
  12. Then: Set page
  13. Then: Qdrant Vector Store
  14. Then: Wait
  15. Then: Embeddings OpenAI
  16. Then: Default Data Loader
  17. Then: Token Splitter
  18. Starts when: When chat message received
  19. Then: Question and Answer Chain
  20. Then: Google Gemini Chat Model
  21. Then: Vector Store Retriever
  22. Then: Qdrant Vector Store1
  23. Then: Embeddings OpenAI1
  24. Starts when: When Executed by Another Workflow
  25. Then: Get PDF
  26. Then: Create collection
  27. Then: Summarization Chain
  28. Then: Set summary
  29. Then: Google Gemini Chat Model1

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

Similar scenarios