Vectorizer quick start with VoyageAI

This page shows you how to create a vectorizer and run a semantic search on the automatically embedded data on a self-hosted Postgres instance. To follow this tutorial you need to have a Voyage AI account API key. You can get one here.

Setup a local development environment

To set up a development environment for Voyage AI, create a docker-compose file that includes:

The official TimescaleDB docker image with pgai, pgvectorscale and timescaledb included
The pgai vectorizer worker image

On your local machine:

Create the Docker configuration for a local developer environment

Create the following docker-compose.yml in a new directory:

name: pgai
services:
 db:
   image: timescale/timescaledb-ha:pg17
   environment:
     POSTGRES_PASSWORD: postgres
     VOYAGE_API_KEY: your-api-key
   ports:
     - "5432:5432"
   volumes:
     - data:/home/postgres/pgdata/data
 vectorizer-worker:
   image: timescale/pgai-vectorizer-worker:latest
   environment:
     PGAI_VECTORIZER_WORKER_DB_URL: postgres://postgres:postgres@db:5432/postgres
     VOYAGE_API_KEY: your-api-key
   command: [ "--poll-interval", "5s" ]
volumes:
 data:

Start the services
```
 docker compose up -d
```

Install pgai in your database

docker compose run --rm --entrypoint "python -m pgai install -d postgres://postgres:postgres@db:5432/postgres" vectorizer-worker

Create and run a vectorizer

Now you can create and run a vectorizer. A vectorizer is a pgai concept, it processes data in a table and automatically creates embeddings for it.

Connect to the database in your local developer environment
- Docker: docker compose exec -it db psql
- psql: psql postgres://postgres:postgres@localhost:5432/postgres

Enable pgai on the database

CREATE EXTENSION IF NOT EXISTS ai CASCADE;

Create the blog table with the following schema

CREATE TABLE blog (
    id SERIAL PRIMARY KEY,
    title TEXT,
    authors TEXT,
    contents TEXT,
    metadata JSONB
);

Insert some data into blog

INSERT INTO blog (title, authors, contents, metadata)
VALUES
('Getting Started with PostgreSQL', 'John Doe', 'PostgreSQL is a powerful, open source object-relational database system...', '{"tags": ["database", "postgresql", "beginner"], "read_time": 5, "published_date": "2024-03-15"}'),

('10 Tips for Effective Blogging', 'Jane Smith, Mike Johnson', 'Blogging can be a great way to share your thoughts and expertise...', '{"tags": ["blogging", "writing", "tips"], "read_time": 8, "published_date": "2024-03-20"}'),

('The Future of Artificial Intelligence', 'Dr. Alan Turing', 'As we look towards the future, artificial intelligence continues to evolve...', '{"tags": ["AI", "technology", "future"], "read_time": 12, "published_date": "2024-04-01"}'),

('Healthy Eating Habits for Busy Professionals', 'Samantha Lee', 'Maintaining a healthy diet can be challenging for busy professionals...', '{"tags": ["health", "nutrition", "lifestyle"], "read_time": 6, "published_date": "2024-04-05"}'),

('Introduction to Cloud Computing', 'Chris Anderson', 'Cloud computing has revolutionized the way businesses operate...', '{"tags": ["cloud", "technology", "business"], "read_time": 10, "published_date": "2024-04-10"}');

Create a vectorizer for blog

SELECT ai.create_vectorizer(
  'blog'::regclass,
  loading => ai.loading_column('contents'),
  embedding => ai.embedding_voyageai(
    'voyage-3-lite',
    512
  ),
  destination => ai.destination_table('blog_contents_embeddings')
);

Check the vectorizer worker logs

docker compose logs -f vectorizer-worker

You see the vectorizer worker pick up the table and process it.

 vectorizer-worker-1  | 2024-10-23 12:56:36 [info     ] running vectorizer             vectorizer_id=1

See the embeddings in action

Run the following search query to retrieve the embeddings:

SELECT
    chunk,
    embedding <=>  ai.voyageai_embed('voyage-3-lite', 'good food') as distance
FROM blog_contents_embeddings
ORDER BY distance;

The results look like:

Chunk	Distance
Maintaining a healthy diet can be challenging for busy professionals...	0.6102883386268212
Blogging can be a great way to share your thoughts and expertise...	0.7245166465928164
PostgreSQL is a powerful, open source object-relational database system...	0.7789760644464416
As we look towards the future, artificial intelligence continues to evolve...	0.9036547272308249
Cloud computing has revolutionized the way businesses operate...	0.9131323552491029

That's it, you're done. You now have a table in Postgres that pgai vectorizer automatically creates and syncs embeddings for. You can use this vectorizer for semantic search, RAG or any other AI app you can think of! If you have any questions, reach out to us on Discord.

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!