How do I set up Supabasa for an agent in a telegram conversation?

Questions
,
1

Hello everyone
I am a beginner and I cannot solve my problem - how to make a database for an agent who remembers information about each participant in a telegram conversation and can respond personally. Of course, you can’t do this through simple memory, so I have two options.:

  1. Make memory through Postgres - as I know, this is an improved simple memory and it is probably better suited for regular telegram messages.
  2. Make a full-fledged configuration in Supabasa, but I don’t understand how it will work quickly if the information is divided into chunks during RAG, and there are small messages and there is nothing to divide. But a different setup via gpt does not work, errors come out and gpt confuses itself.
    Please give me some guidance, then I’ll figure it out for myself. Thank you in advance

Describe the problem/error/question

What is the error message (if any)?

Please share your workflow

(Select the nodes on your canvas and use the keyboard shortcuts CMD+C/CTRL+C and CMD+V/CTRL+V to copy and paste the workflow.)

Share the output returned by the last node

Information on your n8n setup

  • n8n version:
  • Database (default: SQLite):
  • n8n EXECUTIONS_PROCESS setting (default: own, main):
  • Running n8n via (Docker, npm, n8n cloud, desktop app):
  • Operating system:
2

hey @DaviDjaN welcome to n8n community!

here is how you can achieve

In example above I have added chat id as key.
Chat Id is unique for each user, So whenever a user comes after some time aiagent will be able to fetch data unique to that user.

1 Like