A team-chat assistant that answers from your company documents

An employee asks a question in your Telegram — the assistant finds the answer in your documents from your Box (stored in the Postgres PGVector Store knowledge base) and replies right in the chat.

  • Answers from your documents, not guesswork
  • The answer right in your team chat
  • Takes repetitive questions off your plate
  • People find the answer themselves
Embeddings OpenAIQdrant Vector StoreDefault Data Loader
Connect a knowledge base and launchScriptera

How it works

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

  1. Starts when: Get message
  2. Then: AI Agent
  3. Then: Send message
  4. Then: Simple Memory
  5. Then: Embeddings OpenAI1
  6. Then: RAG
  7. Then: Calculator
  8. Starts when: When clicking ‘Test workflow’
  9. Then: Create collection
  10. Then: Refresh collection
  11. Then: Get folder
  12. Then: Download Files
  13. Then: Qdrant Vector Store1
  14. Then: Default Data Loader
  15. Then: Token Splitter
  16. Then: Embeddings OpenAI2
  17. Then: Anthropic Chat Model

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

Similar scenarios