A ticket assistant answering from their history — in chat

The scenario gathers open tickets with comments into a Postgres PGVector Store base and answers support questions based on the issues and their discussions.

  • Answers from real tickets and discussions
  • Tickets gathered on schedule
  • Search by meaning, not by words
  • Also available as an assistant tool
Pinecone Vector StoreEmbeddings OpenAIMCP ServerDefault Data Loader
Connect Postgres PGVector Store and launchScriptera

How it works

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

  1. Starts when: Schedule Trigger
  2. Check: Cycles
  3. Then: Extract Issues
  4. Then: Extract Relevant Info
  5. Check: Merge Comments
  6. Then: Convert to txt
  7. Then: Pinecone Vector Store
  8. Check: All openissues are loaded?
  9. Then: Get Comments
  10. Then: Create Comment array
  11. Then: Document Chunker
  12. Then: Embeddings OpenAI
  13. Starts when: MCP Server Trigger
  14. Then: openissues
  15. Then: openIssues (Data Loader)
  16. Then: AI Agent
  17. Then: OpenAI Chat Model
  18. Then: Simple Memory
  19. Then: SLA
  20. Starts when: Chat
  21. Then: openIssues
  22. Then: Embeddings OpenAI1
  23. Then: MCP RAG

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

Similar scenarios