A support bot with an answer base and expert handoff

How it works

To connect Slack and Qdrant Vector Store, you don't need a developer: a ready-made scenario links them in minutes.

1. Starts when: Telegram Trigger
2. Then: Extract Group ID
3. Then: PrepareReplyFlag_Code
4. Check: QuestionOrReply_Switch
5. If yes: QuestionFilter_Code
6. Check: ValidQuestion_IF
7. If yes: Set Original Question
8. Then: Search Answer In Pinecone
9. Then: Filter Similar Answers
10. Then: Restore Original Question
11. Then: Get First Answered Document
12. Check: Check If Answer Exists
13. If yes: Edit Fields
14. Then: Send Auto Answer
15. If no: EditFields_AddUserID_Metadata
16. Then: CreateTicket_Code
17. Then: Pinecone Vector Store
18. Then: CheckCacheHit
19. Check: CacheHitIF
20. If yes: SendCachedAnswer
21. If no: Pinecone_ParseResult_Code
22. Then: SendToExpert_Message
23. If no: Reformulate_Message
24. If no: IsExpert_Code
25. Check: IsExpert_IF
26. If yes: AddUserID_Metadata_Reply
27. Then: Extract_Original_Question
28. Then: GetFirstResult
29. Then: ExpertReply_Message
30. Then: Set_QA_for_Pinecone
31. Then: WrapForPinecone
32. Then: Pinecone_Add_Answer
33. Then: Embeddings OpenAI
34. Then: Default Data Loader
35. Then: Recursive Character Text Splitter
36. Then: Embeddings OpenAI1
37. Then: Default Data Loader1
38. Then: Recursive Character Text Splitter1
39. Then: Embeddings OpenAI3

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