Answers from your own documents — with a quote from the source

Upload your documents and ask questions about them in plain words. The scenario finds the right passage, answers and shows the quote it drew from.

  • Ask your documents questions in plain language
  • Answers cite the source — you see where it came from
  • Documents pulled from novofon
  • Search by meaning, not exact wording
Pinecone Vector StoreDefault Data LoaderEmbeddings OpenAI
Connect Postgres PGVector Store and launchScriptera

How it works

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

  1. Starts when: When clicking "Execute Workflow"
  2. Then: Set file URL in Google Drive
  3. Then: Download file
  4. Then: Pinecone Vector Store
  5. Starts when: When chat message received
  6. Then: Set max chunks to send to model
  7. Then: Get top chunks matching query
  8. Then: Prepare chunks
  9. Then: Answer the query based on chunks
  10. Then: Compose citations
  11. Then: Generate response
  12. Then: OpenAI Chat Model1
  13. Then: Default Data Loader
  14. Then: Embeddings OpenAI2
  15. Then: Embeddings OpenAI
  16. Then: Recursive Character Text Splitter

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

Similar scenarios