> For the complete documentation index, see [llms.txt](https://tailwindsdocs.innovativesol.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://tailwindsdocs.innovativesol.com/readme/chatflows/langchain/vector-stores/supabase.md).
# Supabase
## Prerequisite
1. Register an account for [Supabase](https://supabase.com/)
2. Click **New project**
3. Input required fields
| Field Name | Description |
| ------------------------- | -------------------------------------------------- |
| **Name** | name of the project to be created. (e.g. AcmeCorp) |
| **Database** **Password** | password to your postgres database |
4. Click **Create new project** and wait for the project to finish setting up
5. Click **SQL Editor**
6. Click **New query**
7. Copy and Paste the below SQL query and run it by `Ctrl + Enter` or click **RUN**. Take note of the table name and function name.
* **Table name**: `documents`
* **Query name**: `match_documents`
```plsql
-- 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 $$
#variable_conflict use_column
begin
return query
select
id,
content,
metadata,
1 - (documents.embedding <=> query_embedding) as similarity
from documents
where metadata @> filter
order by documents.embedding <=> query_embedding
limit match_count;
end;
$$;
```
If some cases, you might be using [Record Manager](/readme/chatflows/langchain/record-managers.md) to keep track of the upserts and prevent duplications. Since Record Manager generates a random UUID for each embeddings, you will have to change the id column entity to text:
```sql
-- Enable the pgvector extension to work with embedding vectors
create extension vector;
-- Create a table to store your documents
create table documents (
id text primary key, -- CHANGE TO TEXT
content text,
metadata jsonb,
embedding vector(1536)
);
-- 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 text, -- CHANGE TO TEXT
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 and Paste each details (*API Key, URL, Table Name, Query Name*) into **Supabase** node
4. **Document** can be connected with any node under [**Document Loader**](/readme/chatflows/langchain/document-loaders.md) category
5. **Embeddings** can be connected with any node under [**Embeddings** ](/readme/chatflows/langchain/embeddings.md)category
## Filtering
Let's say you have different documents upserted, each specified with a unique value under the metadata key `{source}`
You can use metadata filtering to query specific metadata:
**UI**
**API**
```json
"overrideConfig": {
"supabaseMetadataFilter": {
"source": "henry"
}
}
```
## Resources
* [LangChain JS Supabase](https://js.langchain.com/docs/modules/indexes/vector_stores/integrations/supabase)
* [Supabase Blog Post](https://supabase.com/blog/openai-embeddings-postgres-vector)
* [Metadata Filtering](https://js.langchain.com/docs/integrations/vectorstores/supabase#metadata-filtering)