A site chat assistant that answers from your articles

How it works

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

1. Starts when: When clicking ‘Test workflow’
2. Then: Wordpress - Get all posts
3. Check: Merge Wordpress Posts and Pages
4. Then: Set fields1
5. Check: Filter - Only published & unprotected content
6. Then: HTML To Markdown
7. Then: Supabase Vector Store
8. Then: Aggregate
9. Then: Supabase - Store workflow execution
10. Then: Wordpress - Get all pages
11. Then: Embeddings OpenAI
12. Then: Default Data Loader
13. Then: Token Splitter
14. Then: Embeddings OpenAI1
15. Then: OpenAI Chat Model
16. Then: Postgres Chat Memory
17. Starts when: Respond to Webhook
18. Then: Set fields
19. Then: AI Agent
20. Then: Embeddings OpenAI2
21. Then: Default Data Loader1
22. Then: Token Splitter1
23. Then: Markdown1
24. Then: Store documents on Supabase
25. Then: Aggregate1
26. Then: Store workflow execution id and timestamptz
27. Then: Postgres
28. Then: Wordpress - Get posts modified after last workflow execution
29. Check: Merge retrieved WordPress posts and pages
30. Then: Set fields2
31. Check: Filter - Only published and unprotected content
32. Check: Loop Over Items
33. Then: Postgres - Filter on existing documents
34. Check: Switch
35. If yes: Supabase - Delete row if documents exists
36. Then: Aggregate2
37. Then: Set fields3
38. If no: Set fields4
39. Then: Wordpress - Get posts modified after last workflow execution1
40. Starts when: Every 30 seconds
41. Then: Aggregate documents
42. Then: Postgres - Create documents table
43. Then: Postgres - Create workflow execution history table
44. Starts when: When chat message received
45. Then: Supabase - Retrieve documents from chatinput

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