Postgres + GPUs for ML/AI applications.
| Documentation | Blog | Discord |
Why do ML/AI in Postgres?
Data for ML & AI systems is inherently larger and more dynamic than the models. It's more efficient, manageable and reliable to move models to the database, rather than constantly moving data to the models.
- In-Database ML/AI: Run machine learning and AI operations directly within PostgreSQL
- GPU Acceleration: Leverage GPU power for faster computations and model inference
- Large Language Models: Integrate and use state-of-the-art LLMs from Hugging Face
- RAG Pipeline: Built-in functions for chunking, embedding, ranking, and transforming text
- Vector Search: Efficient similarity search using pgvector integration
- Diverse ML Algorithms: 47+ classification and regression algorithms available
- High Performance: 8-40X faster inference compared to HTTP-based model serving
- Scalability: Support for millions of transactions per second and horizontal scaling
- NLP Tasks: Wide range of natural language processing capabilities
- Security: Enhanced data privacy by keeping models and data together
- Seamless Integration: Works with existing PostgreSQL tools and client libraries
The only prerequisites for using PostgresML is a Postgres database with our open-source pgml extension installed.
Our serverless cloud is the easiest and recommend way to get started.
Sign up for a free PostgresML account. You'll get a free database in seconds, with access to GPUs and state of the art LLMs.
If you don't want to use our cloud you can self host it.
docker run \
-it \
-v postgresml_data:/var/lib/postgresql \
-p 5433:5432 \
-p 8000:8000 \
ghcr.io/postgresml/postgresml:2.7.12 \
sudo -u postgresml psql -d postgresml
For more details, take a look at our Quick Start with Docker documentation.
We have a number of other tools and libraries that are specifically designed to work with PostgreML. Remeber PostgresML is a postgres extension running inside of Postgres so you can connect with psql and use any of your favorite tooling and client libraries like psycopg to connect and run queries.
PostgresML Specific Client Libraries:
- Korvus - Korvus is a Python, JavaScript, Rust and C search SDK that unifies the entire RAG pipeline in a single database query.
- postgresml-django - postgresml-django is a Python module that integrates PostgresML with Django ORM.
Recommended Postgres Poolers:
- pgcat - pgcat is a PostgreSQL pooler with sharding, load balancing and failover support.
PostgresML brings models directly to your data, eliminating the need for costly and time-consuming data transfers. This approach significantly enhances performance, security, and scalability for AI-driven applications.
By running models within the database, PostgresML enables:
- Reduced latency and improved query performance
- Enhanced data privacy and security
- Simplified infrastructure management
- Seamless integration with existing database operations
PostgresML supports a wide range of state-of-the-art deep learning architectures available on the Hugging Face model hub. This integration allows you to:
- Access thousands of pre-trained models
- Utilize cutting-edge NLP, computer vision, and other AI models
- Easily experiment with different architectures
While cloud-based LLM providers offer powerful capabilities, making API calls from within the database can introduce latency, security risks, and potential compliance issues. Currently, PostgresML does not directly support integration with remote LLM providers like OpenAI.
PostgresML transforms your PostgreSQL database into a powerful vector database for Retrieval-Augmented Generation (RAG) applications. It leverages pgvector for efficient storage and retrieval of embeddings.
Our RAG implementation is built on four key SQL functions:
- Chunk: Splits text into manageable segments
- Embed: Generates vector embeddings from text using pre-trained models
- Rank: Performs similarity search on embeddings
- Transform: Applies language models for text generation or transformation
For more information on using RAG with PostgresML see our guide on Unified RAG.
The pgml.chunk function chunks documents using the specified splitter. This is typically done before embedding.
pgml.chunk(
splitter TEXT, -- splitter name
text TEXT, -- text to embed
kwargs JSON -- optional arguments (see below)
)
See pgml.chunk docs for more information.
The pgml.embed function generates embeddings from text using in-database models.
pgml.embed(
transformer TEXT,
"text" TEXT,
kwargs JSONB
)
See pgml.embed docs for more information.
The pgml.rank function uses Cross-Encoders to score sentence pairs.
This is typically used as a re-ranking step when performing search.
pgml.rank(
transformer TEXT,
query TEXT,
documents TEXT[],
kwargs JSONB
)
Docs coming soon.
The pgml.transform function can be used to generate text.
SELECT pgml.transform(
task => TEXT OR JSONB, -- Pipeline initializer arguments
inputs => TEXT[] OR BYTEA[], -- inputs for inference
args => JSONB -- (optional) arguments to the pipeline.
)
See pgml.transform docs for more information.
See our Text Generation guide for a guide on generating text.
Some highlights:
- 47+ classification and regression algorithms
- 8 - 40X faster inference than HTTP based model serving
- Millions of transactions per second
- Horizontal scalability
Training a classification model
Training
SELECT * FROM pgml.train(
'Handwritten Digit Image Classifier',
algorithm => 'xgboost',
'classification',
'pgml.digits',
'target'
);
Inference
SELECT pgml.predict(
'My Classification Project',
ARRAY[0.1, 2.0, 5.0]
) AS prediction;
The pgml.transform function exposes a number of available NLP tasks.
Available tasks are: