Skip to main content

Supabase Hybrid Search

Langchain supports hybrid search with a Supabase Postgres database. The hybrid search combines the postgres pgvector extension (similarity search) and Full-Text Search (keyword search) to retrieve documents. You can add documents via SupabaseVectorStore addDocuments function. SupabaseHybridKeyWordSearch accepts embedding, supabase client, number of results for similarity search, and number of results for keyword search as parameters. The getRelevantDocuments function produces a list of documents that has duplicates removed and is sorted by relevance score.


Install the library with

npm install -S @supabase/supabase-js

Create a table and search functions in your database

Run this in your database:

-- 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 similarity 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
return query
1 - (documents.embedding <=> query_embedding) as similarity
from documents
where metadata @> filter
order by documents.embedding <=> query_embedding
limit match_count;

-- Create a function to keyword search for documents
create function kw_match_documents(query_text text, match_count int)
returns table (id bigint, content text, metadata jsonb, similarity real)
as $$

return query execute
format('select id, content, metadata, ts_rank(to_tsvector(content), plainto_tsquery($1)) as similarity
from documents
where to_tsvector(content) @@ plainto_tsquery($1)
order by similarity desc
limit $2')
using query_text, match_count;
$$ language plpgsql;


npm install @langchain/openai @langchain/community
import { OpenAIEmbeddings } from "@langchain/openai";
import { createClient } from "@supabase/supabase-js";
import { SupabaseHybridSearch } from "@langchain/community/retrievers/supabase";

export const run = async () => {
const client = createClient(
process.env.SUPABASE_URL || "",
process.env.SUPABASE_PRIVATE_KEY || ""

const embeddings = new OpenAIEmbeddings();

const retriever = new SupabaseHybridSearch(embeddings, {
// Below are the defaults, expecting that you set up your supabase table and functions according to the guide above. Please change if necessary.
similarityK: 2,
keywordK: 2,
tableName: "documents",
similarityQueryName: "match_documents",
keywordQueryName: "kw_match_documents",

const results = await retriever.getRelevantDocuments("hello bye");


API Reference: