Supabase

Prerequisite

1. Register an account for Supabase

2. Click New project\

   
3. Input required fields Name, name of the project to be created. (e.g. LangFlux) Database Password, password to your postgres database. (e.g. click Generate a password)\

   
4. Click Create new project and wait for the project to finish setting up

5. Click SQL Editor\

   
6. Click New query\

   
7. Copy & Paste query and run it by Ctrl + Enter or click RUN Table name: documents Query name: match_documents

   Copy

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

   

Setup

1. Click Project Settings\

   
2. Get your Project URL & API Key

   
3. Copy & Paste each details (API Key, URL, Table Name, Query Name) into Supabase Upsert Document node or Supabase Load Existing node

4. Document can be connected with any node under Document Loader category

5. Embeddings can be connected with any node under Embeddings category

Resources

• LangChain JS Supabase

• Supabase Blog Post