Database name does not exist when searching Supabase documents with n8n

[Mohamed_Necib2]

Hi everyone,

I’m trying to run a search query in my Supabase vector database from an n8n workflow, but I keep getting this error:

“Error searching for documents: 42P01 relation “dna_builder_personality_interview” does not exist null”

What confuses me is that my actual database/table has a different name — I created a database called “dna_builder_personality_interview". but then I have deleted it. The new one if called: “brand ia analysis”.

To create the database I used this:

-- Enable the pgvector extension to work with embedding vectors
create extension vector;

-- Create a table to store your documents
create table documents (
  id bigserial primary key,
  content text, -- corresponds to Document.pageContent
  metadata jsonb, -- corresponds to Document.metadata
  embedding vector(1536) -- 1536 works for OpenAI embeddings, change if needed
);

-- Create a function to search for documents
create function match_documents (
  query_embedding vector(1536),
  match_count int default null,
  filter jsonb DEFAULT '{}'
) returns table (
  id bigint,
  content text,
  metadata jsonb,
  similarity float
)
language plpgsql
as $$
#variable_conflict use_column
begin
  return query
  select
    id,
    content,
    metadata,
    1 - (documents.embedding <=> query_embedding) as similarity
  from documents
  where metadata @> filter
  order by documents.embedding <=> query_embedding
  limit match_count;
end;
$$;

My questions:

1. Why would n8n (or the integration) be trying to query dna_builder_personality_interview instead of my real table name?

Thanks in advance for any pointers!

[jabbson]

Hey @Mohamed_Necib2 hope all is good.

Would you like to share:

• you workflow
• exact sql you used to create the table and the match function?