Document analysis and recommendations — right in your team chat

The scenario takes a document from chat, reads it, finds similar past cases in the knowledge base and replies with recommendations.

  • Just drop the file into Telegram
  • Recommendations lean on past cases from Postgres PGVector Store
  • Reference data is pulled from Google Sheets
  • The answer comes back to the same chat — visible to everyone
Pinecone Vector StoreEmbeddings Azure OpenAIGoogle Sheets ToolReranker Cohere
Connect Postgres PGVector Store and goScriptera

How it works

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

  1. Starts when: Slack Trigger
  2. Then: AI Agent
  3. Then: Download file
  4. Then: Extract from File
  5. Then: AI Agent1
  6. Then: Pinecone Vector Store5
  7. Then: AI Agent3
  8. Then: Edit Fields
  9. Then: Send a message
  10. Then: Azure OpenAI Chat Model1
  11. Then: Pinecone Vector Store2
  12. Then: Embeddings Azure OpenAI2
  13. Then: Get row(s) in sheet in Google Sheets
  14. Then: Reranker Cohere1
  15. Then: Structured Output Parser1
  16. Then: Embeddings Azure OpenAI5
  17. Then: Reranker Cohere3
  18. Then: Azure OpenAI Chat Model3
  19. Then: Auto-fixing Output Parser
  20. Then: Structured Output Parser2
  21. Then: Azure OpenAI Chat Model
  22. Then: Structured Output Parser

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

Similar scenarios