A messenger bot that answers clients from your documents

Upload your materials — the scenario answers clients in the messenger from them: it finds the right spot in your documents and gives an accurate answer, not vague words.

  • Builds a knowledge base from your documents in Box
  • Answers clients in Mattermost from your materials
  • Finds the right spot and answers to the point
  • Works around the clock, no live agent
Qdrant Vector StoreEmbeddings OpenAIDefault Data LoaderWebhook
Connect Qdrant and goScriptera

How it works

To connect Qdrant 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: Create collection
  3. Then: Refresh collection
  4. Then: Get folder
  5. Then: Download Files
  6. Then: Qdrant Vector Store
  7. Starts when: Respond to Webhook
  8. Then: AI Agent
  9. Then: Send
  10. Then: OpenAI Chat Model
  11. Then: Embeddings OpenAI
  12. Then: Default Data Loader
  13. Then: Token Splitter
  14. Starts when: Verify
  15. Starts when: Respond
  16. Check: is Message?
  17. If no: Only message
  18. Then: Window Buffer Memory
  19. Then: OpenAI Chat Model1
  20. Then: Retrive Qdrant Vector Store
  21. Then: Embeddings OpenAI2
  22. Then: RAG

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

Similar scenarios