@Yash Chauhan Hey Yash How are the tokens in Poppy billed? Do you have to connect API keys or does the yearly payment include token usage? It seems that you're using it 😁

Hey Everyone I've been struggling with this problem for 1,5 days straight, and what I've learned is that I lack knowledge. I'm quite new to this whole Database thing, but I solved it. So to anyone who might need this - here's the solution. The picture also shows the solution. This is all due to a one line mess up. Here's a Github thread for the answer as well: https://github.com/orgs/supabase/discussions/23207 Set search_path = public (doesn't work) It has to say: >>>>>Set search_path = public, extensions<<<<< Why this works you can figure out yourself by asking an LLM :) Here is my fully working SQL Editor syntax for Supabase: create schema if not exists extensions; create extension vector with schema extensions; -- Recreate the table with the correct vector reference create table documents ( id bigserial primary key, content text, metadata jsonb, embedding extensions.vector(1536) -- Note the new schema prefix ); -- Recreate the function create or replace function match_documents ( query_embedding extensions.vector(1536), match_count int default null, filter jsonb default '{}' ) returns table ( id bigint, content text, metadata jsonb, similarity float ) language plpgsql set search_path = public, extensions as $$ #variable_conflict use_column begin return query select id, content, metadata, 1 - (documents.embedding <=> query_embedding) as similarity from documents where metadata @> filter order by documents.embedding <=> query_embedding limit match_count; end; $$;

@Nico Asd Okay! That's an honest thought! Thank you 🙏 I figured out how to set up all the API Keys I need in n8n, so now it's all about figuring out how to make my use case user friendly, so it's not over-engineered 🙂

@Oliver B. Yes you are completely right. I figured it out. Thanks! The criterias for an optimized route is the hardest part - that has to come from the business 🙂