Supabase vector store error

Questions
1

image
image1696×818 87.7 KB

I don’t understand why there is an error? It doesn’t see the database?

2

I think you need to share your whole workflow to get help with this. Did you get any info if you copy and past the error into chat GPT?

3

Not sure if you did, but you have to add the match_documents function to your database. You can run the code below in your supabase sql editor in the left menu.

Make sure you already have a table named documents and that it has the correct vector size. If you don’t have it or the vector size is incorrect drop the table and run 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
);

Then to create the match_documents function run this:

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