An assistant that answers from the files in your storage

The scenario turns files from your storage into a knowledge base, keeps it up to date and answers questions from those documents.

  • Answers from your documents
  • The base updates in step with storage
  • Adds new, updates changed
  • Ask a question — get an answer from the current version
Embeddings OpenAIDefault Data LoaderQdrant Vector Store
Connect Postgres PGVector Store and goScriptera

How it works

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

  1. Starts when: When clicking ‘Test workflow’
  2. Then: Clear collection
  3. Then: Get files
  4. Check: Loop Over Items
  5. Then: Download files
  6. Then: Qdrant Vector Store
  7. Then: Wait
  8. Then: Embeddings OpenAI1
  9. Then: Default Data Loader1
  10. Then: Create collection
  11. Then: Recursive Character Text Splitter
  12. Then: Embeddings OpenAI2
  13. Then: Default Data Loader
  14. Then: Recursive Character Text Splitter1
  15. Then: Delete single file
  16. Then: Download file
  17. Then: Update single file
  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 OpenAI
  24. Then: Edit Fields3

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

Similar scenarios