Build AI Applications
on a Scalable Solution

Our open source software scales Postgres horizontally for your interactive AI powered applications, with the latest LLMs, vector operations, classical Machine Learning and good old Postgres application workloads.

Docs
PostgresML Demo

How It
Works

Use the expressive power of SQL along with the most advanced machine learning algorithms and pretrained models in a high performance database.

PostgresML indexes application data alongside computed features like embedding vectors with your machine learning models all together in a seamless shared memory space. This eliminates network calls, process boundaries, data duplication and other unnecessary complexity, which makes it more reliable, efficient, fast and simple.

Our serverless platform is built around our custom Postgres pooler PgCat, which allows you to scale your inference layer to millions of predictions per second across multiple GPU accelerated machines.

Try Now For Free
timer

Fast

Up to 40x performance improvement over traditional microservice architectures. Shared memory between data and models in a single process eliminates network calls, process boundaries and data duplication.

Copy icon

Comprehensive

PostgresML can download state-of-the-art open source models from HuggingFace, or train your own end to end. It also supports many algorithms like Torch, Tensorflow, XGBoost, LightGBM, and all the classical ones in Scikit.

Double right arrow

Scalable

Scale your inference layer to millions of predictions per second in our GPU accelerated cloud. Start for free with our serverless option, or use dedicated Postgres replicas.

Circle icon

Simple

PostgresML is your application and vector database, model store, feature store, inference server and ML deployment pipeline, with support for all major languages and application frameworks as clients.

Download icon

Your Data

Efficiently load data or features from upstream sources with Postgres replication, or connect your application directly through our custom load balancer, PgCat.

Copy icon

Highly Available

Abstract everything behind a single connection string with smart query routing, sharding, and enterprise-grade managed infrastructure.

How to Use It

Download icon

Train

SELECT pgml.train(
  'Sales Forecasting',
  task => 'regression',
  relation_name => 'historical_sales',
  y_column_name => 'next_week_sales',
  algorithm => 'xgboost'
);
Learn About Training
Upload icon

Deploy

SELECT pgml.deploy(
  'Sales Forecasting',
  strategy => 'best_score',
  algorithm => 'xgboost'
); 
Learn About Deployments
Timer icon

Predict

SELECT pgml.predict(
  'Sales Forecasting',
  ARRAY[
    last_week_sales,
    week_of_year
  ]
) AS prediction
ORDER BY prediction DESC;
Learn About Predictions

What Adopters Say

Quote icon

"Absolutely brilliant" on PgCat, our sharded PostgreSQL proxy.

Carnegie Mellon
Quote icon

"The improvement is quite remarkable" on PostgresML v2.0.

Scaling Postgres
Quote icon

"Bleeding edge stuff in a matter of minutes."

Hasura
Quote icon

"I'm itching to apply it everywhere I set my foot!"

Stone Cross Foundation
Quote icon

"The simplicity and ergonomics are really exciting."

Practical AI
Rotating cube Rotating cube

Start Now
With Machine Learning

Product features

Discover All Features

download icon

Fastest Inference

PostgresML eliminates separation between your model server and datastore, minimizing latency and computation costs. You can even generate embeddings on the fly in queries. Our benchmarks show a 8x-40x improvement over Python HTTP microservices.

Overview
download icon

All Your Favorite Algorithms

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

Algorithms
download icon

Hyperparameter Search

Use either grid or random searches with cross validation on your training data to discover the most important knobs to tweak on your favorite algorithm, with best practices automatically enforced for testing model quality before deploying to production.

Hyperparameters
download icon

Online & Offline

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.

download icon

Scheduled Training

Automate workflows to retain models periodically, taking advantage of auto scaling with dedicated resources like GPU's to optimize training times while alleviating loads on the primary database.

download icon

Open Source

PostgresML is entirely open source, including the ML libraries we support and the underlying database, Postgres (of course).

Open Source
download icon

Managed Deployments

Use either grid or random searches with cross validation on your training data to discover the most important knobs to tweak on your favorite algorithm, with the best practices enforced for testing modal quality before deploying to production.

download icon

Fast Vector Operations

Vector operations make working with learning embeddings a snap, for things like nearest neighbor searches or other similarity comparisons. Further optimized with BLAS for maximum performance.

download icon

Instant Visualizations

You can build common data visualizations to detect outliers, bimodal distributions, feature correlations, and much more.

8x-40x

Faster than Python

<1 ms

Prediction Latency

47

Algorithms

1M+

QPS on EC2

We Have the Perfect
Plan For You

ellipse

Serverless

$0

Starting at

For startups
Free, without cache acceleration

  • Checkmark $0.25/hr per GB GPU cache
  • Checkmark Multi GPU burst capability
  • Checkmark Cache your models on the GPU
  • Checkmark Instant scalability up to 256GB GPU
  • Checkmark Scale further with advanced sharding functionality
triangle

Dedicated

$0.60/hr

Starting at

For orgs of any size
Dedicated cluster with fixed hardware

  • Checkmark Choose CPU, RAM or GPU resources
  • Checkmark Horizontally scalable inference with replicas
  • Checkmark High availability for your production applications
  • Checkmark Multiple users
  • Checkmark Multiple databases
  • Checkmark Automated Backups
  • Checkmark Metrics
  • Checkmark Logs
square

Enterprise

--

Custom Pricing

For orgs with custom needs
Your hardware, your way

  • Checkmark Customized hardware
  • Checkmark Solution Architecture support
  • Checkmark Private VPC/On-prem deployments
  • Checkmark Access Control Lists
  • Checkmark Single Sign-on
Contact Us
Powered by PostgresML Logo PostgresML