Ask your document folder — get a real answer

The scenario keeps the folder's contents in a searchable base and answers questions straight from the documents, without inventing.

  • Answers by meaning, not manual file hunting
  • The base updates as soon as the folder changes
  • Answers from documents — no hallucinating
  • Get the answer to your inbox as well
Pinecone Vector StoreDefault Data LoaderGoogle DriveEmbeddings OpenAI
Connect Postgres PGVector Store and runScriptera

How it works

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

  1. Starts when: Google Drive File Updated
  2. Check: Filter PDF files1
  3. Check: If length > 0_
  4. If yes: Download File From Google Drive1
  5. Then: Pinecone Vector Store1
  6. Then: Pinecone Vector Store
  7. Then: Wait
  8. Check: Loop Items
  9. Then: Send a message
  10. Then: Download File From Google Drive
  11. Then: Default Data Loader
  12. Then: Recursive Character Text Splitter
  13. Then: Vector Store Tool
  14. Then: Pinecone Vector Store (Retrieval)
  15. Starts when: Google Drive File Created
  16. Check: Filter PDF files
  17. Check: If length > 0
  18. Then: Window Buffer Memory
  19. Then: Search files and folders
  20. Starts when: When clicking ‘Execute workflow’
  21. Then: Pinecone – Delete All Vectors
  22. Starts when: When chat message received
  23. Then: Documents finder
  24. Then: OpenAI Chat Model
  25. Then: OpenAI Chat Model1
  26. Then: Embeddings OpenAI
  27. Then: Embeddings OpenAI1
  28. Then: Embeddings OpenAI2
  29. Then: Default Data Loader1
  30. Then: Recursive Character Text Splitter1

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

Similar scenarios