A chatbot that answers from your documents

Your PDFs go into a knowledge base, and the chat bot answers questions strictly from them, picking the most precise fragments.

  • Answers from your PDFs
  • Picks the most precise fragments
  • No made-up answers
  • Load documents once
Embeddings OpenAIDefault Data LoaderSupabase Vector StoreReranker Cohere
Set it upScriptera

How it works

To connect sbermegamarket and Supabase, you don't need a developer: a ready-made scenario links them in minutes.

  1. Starts when: Chat Interface
  2. Then: RAG Agent
  3. Then: AI Model (OpenAI)
  4. Then: Search Embeddings
  5. Then: Conversation Memory
  6. Starts when: Load Documents Trigger
  7. Then: Download PDF from Drive
  8. Then: Extract PDF Content
  9. Then: Store in Vector Database
  10. Then: Document Embeddings
  11. Then: Process Document Text
  12. Then: Knowledge Base Search
  13. Then: Cohere Reranker

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

Similar scenarios