A site assistant that answers from your material — and knows which site it's on

A visitor asks a question — the scenario works out which site it came from and answers from the right knowledge base, keeping the thread of the conversation.

  • Answers from your own material, not boilerplate
  • Several sites, one scenario
  • Searches by meaning, not exact wording
  • Remembers the conversation with each visitor
Postgres Chat MemoryPinecone Vector StoreEmbeddings CohereWebhook
Connect Postgres PGVector Store and launchScriptera

How it works

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

  1. Starts when: Webhook
  2. Check: Switch
  3. If yes: AI Agent1 ghostwritingpartner
  4. Starts when: Respond to Webhook1
  5. If no: AI Agent ebook-wr
  6. Starts when: Respond to Webhook2
  7. If no: AI Agent for groton
  8. Starts when: Respond to Webhook
  9. Then: Postgres Chat Memory
  10. Then: OpenRouter Chat Model
  11. Then: Pinecone Vector Store5
  12. Then: Embeddings Cohere
  13. Then: Pinecone Vector Store6
  14. Then: Embeddings Cohere6
  15. Then: Pinecone Vector Store7
  16. Then: Embeddings Cohere7
  17. Then: Pinecone Vector Store9
  18. Then: Embeddings Cohere9
  19. Then: Pinecone Vector Store10
  20. Then: Embeddings Cohere10
  21. Then: Postgres Chat Memory1
  22. Then: OpenRouter Chat Model1
  23. Then: Pinecone Vector Store8
  24. Then: Embeddings Cohere8
  25. Then: Postgres Chat Memory2
  26. Then: OpenRouter Chat Model2
  27. Then: Pinecone Vector Store11
  28. Then: Embeddings Cohere11

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

Similar scenarios