Skip to content

Microsecond inference with the
most capable feature store

Easily train and deploy online models using only SQL, with an open source
extension for PostgreSQL.

Try PostgresML Free Docs

Pure SQL Solution

SELECT pgml.train(
  'My First PostgresML Project', 
  task => 'regression',
  relation_name => 'pgml.digits',
  y_column_name => 'target',
  algorithm => 'xgboost' 
);

Learn more about Training

models

models

SELECT pgml.deploy(
  'My First PostgresML Project', 
  strategy => 'best_score',
  algorithm => 'xgboost'
);

Learn more about Deployments

SELECT
  target,
  pgml.predict(
    'My First PostgresML Project', 
    image
  ) AS prediction
  FROM pgml.digits
ORDER BY prediction DESC;

Learn more about Predictions

models

What's in the box

All your favorite algorithms

Whether you need a simple linear regression, or extreme gradient boosting, we've included support for all classification and regression algorithms in Scikit Learn, XGBoost, LightGBM and pre-trained deep learning models from Hugging Face.

Algorithms

Hyperparameter search

Use either grid or random searches with cross validation on your training set to discover the most important knobs to tweak on your favorite algorithm.

Hyperparameter Search

Blazing fast

With core implementation and bindings written in Rust, use XGBoost, LightGBM and Linfa algorithms at blazing speed with minimal memory utilization and no garbage collection.

Benchmarks

Online and offline support

Predictions are served via a standard Postgres connection to ensure that your core apps can always access both your data and your models in real time. Pure SQL workflows also enable batch predictions to cache results in native Postgres tables for lookup.

Predictions

Fast vector operations

Vector operations make working with learned emebeddings a snap, for things like nearest neighbor searches or other similarity comparisons. Rust and BLAS optimized for maximum performance.

Vector Operations

Managed model deployments

Models can be periodically retrained and automatically promoted to production depending on their key metric. Rollback capability is provided to ensure that you're always able to serve the highest quality predictions, along with historical logs of all deployments for long term study.

Deployments

The performance of Postgres

Since your data never leaves the database, you retain the speed, reliability and security you expect in your foundational stateful services. Leverage your existing infrastructure and the data distribution strategies native to PostgreSQL to deliver new capabilities.

Distributed Training

Instant visualizations

Run standard analysis on your datasets to detect outliers, bimodal distributions, feature correlation, and other common data visualizations on your datasets. Everything is cataloged in the dashboard for easy reference.

Dashboard

Open source

We're building on the shoulders of giants. These machine learning libraries and Postgres have received extensive academic and industry use, and we'll continue their tradition to build with the community.

MIT License


Try PostgresML Free