Supabase Vector Store Issue

Hi @lhyphendixon :wave: Sorry it’s taken so long to get back to you!

Admittedly, when @oleg is back he may have more to help you with here, as I’m a novice when it comes to Supabase :sweat_smile:

When using your provided workflow, I’m able to get it to successfully run after I used the specific template in Supabase to create a SQL query that enables pgvector extension when creating a table. Perhaps you can take a look at this query and see if anything might be missing in your configuration that you might need?

-- 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,
  embedding jsonb,
  similarity float
language plpgsql
as $$
#variable_conflict use_column
  return query
    (embedding::text)::jsonb as embedding,
    1 - (documents.embedding <=> query_embedding) as similarity
  from documents
  where metadata @> filter
  order by documents.embedding <=> query_embedding
  limit match_count;
1 Like