I’m afraid I’m new to n8n and I’ve been having this trouble for a while now
My AI agent works as an acoustic assistant that asks the user a serie of questions in order to get representative information of their place and offer a simple acoustic report. I need to get the full conversation in order to know the user answers and pass them into a message model node so it generates the report and sends it to me via mailjet.
I save every conversation in supabase and try to retrieve the conversation data from sessionID row, but the error comes at this point.
I would be very grateful if anyone could give me some advice on how to fix my workflow. Thank you!
Hi welcome to the community
your supabase node is missing some stuff, what are the table name and the filter field name that you use for it? and whats the error that youre encountering?
I realized I should assign my sessionID from the chat beginning in order to get the rows (chats) that match with it, but I don’t really know how to fix my workflow to achieve that
first of all, i think you just need to connect your supabase node to your AI Agent node above, but first you need to attach an output parser first in the AI Agent and strucuted the output in a way that when the conversation is finished, they will tell you, something like
{
isFinished: true
}
and based on that response, you put an if node in between the ai agent and the supabase, if its true then you fetch all the convos
and i think the way you need to filter it is not using IS but use Equals on your supabase node