Is there a way to get an n8n agent to call/chat with two separate supabase tables?

[ReinventNYC]

Is there a way to get an n8n agent to call/chat with two separate supabase tables?

[ihortom]

Sure, why not. You can connect many tools to AI Agent.

[Eddy_is_here]

What’s the best approach? To create multiple Supabase vector store tools or just input multiple table names into the field? (Is this even possible? @ihortom)

[Dennis_Harley]

I also face this same issue.
So I’m using the Supabase Documentation, linked by this section of n8n documentation

-- 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 $$
#variable_conflict use_column
begin
  return query
  select
    id,
    content,
    metadata,
    1 - (documents.embedding <=> query_embedding) as similarity
  from documents
  where metadata @> filter
  order by documents.embedding <=> query_embedding
  limit match_count;
end;
$$;

And then I want to create another function, let’s just say match_buildings. The vector_store from n8n kept using match_documents by default even when it’s been stated to use match_buildings.

I don’t have any alternative except of using different supabase credentials if I want to use another function from the supabase.

[Gesture2867]

You can achieve this with a custom query option like this: