A movie recommender: describe it in words, get three picks

A ready chat recommender searches movies by the meaning of your request in a Postgres PGVector Store catalog and returns three spot-on picks — honoring both what you want and what you don't.

  • Picks movies from a description in your own words
  • Honors both your 'want' and your 'don't'
  • Suggests real movies from a catalog, no made-up ones
  • Replies with a ready set of three picks
GitHubEmbeddings OpenAIDefault Data LoaderQdrant Vector Store
Connect Postgres PGVector Store and launchScriptera

How it works

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

  1. Starts when: When clicking ‘Test workflow’
  2. Then: GitHub
  3. Then: Extract from File
  4. Then: Qdrant Vector Store
  5. Then: Embeddings OpenAI
  6. Then: Default Data Loader
  7. Then: Token Splitter
  8. Starts when: When chat message received
  9. Then: AI Agent
  10. Then: OpenAI Chat Model
  11. Then: Call n8n Workflow Tool
  12. Then: Window Buffer Memory
  13. Starts when: Execute Workflow Trigger
  14. Then: Embedding Recommendation Request with Open AI
  15. Then: Extracting Embedding
  16. Check: Merge
  17. Then: Calling Qdrant Recommendation API
  18. Then: Retrieving Recommended Movies Meta Data
  19. Then: Split Out
  20. Check: Merge1
  21. Then: Selecting Fields Relevant for Agent
  22. Then: Aggregate
  23. Then: Split Out1
  24. Then: Embedding Anti-Recommendation Request with Open AI
  25. Then: Extracting Embedding1

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

Similar scenarios