Skip to main content
Supabase provides Postgres with pgvector for AI applications. With Portkey, generate embeddings using 1600+ models and store them in Supabase for efficient retrieval.

​
Prerequisites

​
Setup

​
1. Install Dependencies

pip install portkey-ai supabase

​
2. Prepare Database

1

Create Supabase Project

Go to Supabase and create a new project.
2

Enable pgvector

In Database → Extensions, enable pgvector. Or run:
create extension vector;
3

Create Documents Table

Create a table for documents and embeddings. OpenAI’s text-embedding-ada-002 outputs 1536 dimensions:
create table documents (
  id bigserial primary key,
  content text,
  embedding vector(1536)
);

​
3. Configure Clients

from portkey_ai import Portkey
from supabase import create_client, Client

# Supabase
supabase: Client = create_client(
    "YOUR_SUPABASE_PROJECT_URL",
    "YOUR_SUPABASE_API_KEY"
)

# Portkey
client = Portkey(
    api_key="YOUR_PORTKEY_API_KEY",
    provider="@openai-prod"
)

​
Generate & Store Embeddings

# Generate embedding
response = client.embeddings.create(
    model="text-embedding-ada-002",
    input="The food was delicious and the waiter..."
)

embedding = response.data[0].embedding

# Store in Supabase
result = supabase.table('documents').insert({
    "content": "The food was delicious and the waiter...",
    "embedding": embedding
}).execute()

​
Switch Providers

Change the provider to use different embedding models: 
# Cohere embeddings (1024 dimensions)
client = Portkey(
    api_key="YOUR_PORTKEY_API_KEY",
    provider="@cohere-prod"
)

response = client.embeddings.create(
    model="embed-english-v3.0",
    input_type="search_query",
    input="The food was delicious and the waiter..."
)
Cohere’s embed-english-v3.0 outputs 1024 dimensions. Create a separate table with vector(1024) for Cohere embeddings.

​
Next Steps

Model Catalog

Set up embedding providers

Supported Providers

See all 1600+ supported models