Postgres
ML
search
Solutions
smart_toy
Chatbots
manage_search
Site Search
e911_emergency
Fraud Detection
avg_pace
Forecasting
Solutions
Pricing
Docs
Blog
Company
smart_toy
About
work
Careers
alternate_email
Contact
Company
search
5.4K
GitHub
Sign In
Start Your Project
arrow_back
Back
Chatbots
Site Search
Fraud Detection
Forecasting
arrow_back
Back
About
Careers
Contact
search
Documentation
list_alt
INTRODUCTION
Overview
Getting started
expand_more
Create your database
Connect your app
Import your data
expand_more
Logical replication
Foreign Data Wrappers
Move data with COPY
Migrate with pg_dump
sdk
API
Overview
SQL extension
expand_more
pgml.deploy()
pgml.embed()
pgml.chunk()
pgml.generate()
pgml.predict()
expand_more
Batch Predictions
pgml.train()
expand_more
Regression
Classification
Clustering
Data Pre-processing
Hyperparameter Search
Joint Optimization
pgml.transform()
expand_more
Fill Mask
Question Answering
Summarization
Text Classification
Text Generation
Text-to-Text Generation
Token Classification
Translation
Zero-shot Classification
pgml.tune()
Client SDK
expand_more
Collections
Pipelines
Vector Search
Document Search
Tutorials
expand_more
Semantic Search
Semantic Search Using Instructor Model
dashboard
PRODUCT
Cloud database
expand_more
Serverless
Dedicated
Enterprise
Vector database
PgCat pooler
expand_more
Features
Installation
Configuration
account_circle
USE CASES
OpenSourceAI
Chatbots
expand_more
Example Application
Search
Embeddings
expand_more
Generating LLM embeddings with open source models
Tuning vector recall while generating query embeddings in the database
Personalize embedding results with application data in your database
Supervised Learning
Natural Language Processing
Fraud Detection
Recommendation Engine
Time-series Forecasting
school
RESOURCES
FAQs
Data Storage & Retrieval
expand_more
Tabular data
Documents
Partitioning
LLM based pipelines with PostgresML and dbt (data build tool)
Benchmarks
expand_more
PostgresML is 8-40x faster than Python HTTP microservices
Scaling to 1 Million Requests per Second
MindsDB vs PostgresML
GGML Quantized LLM support for Huggingface Transformers
Making Postgres 30 Percent Faster in Production
Developer Docs
expand_more
Local Docker Development
Installation
Contributing
Distributed Training
GPU Support
Deploying PostgresML
expand_more
Monitoring
Self-hosting
expand_more
Pooler
Building from source
Replication
Backups
Running on EC2
Docs
expand_more
Documentation
list_alt
INTRODUCTION
Overview
Getting started
expand_more
Create your database
Connect your app
Import your data
expand_more
Logical replication
Foreign Data Wrappers
Move data with COPY
Migrate with pg_dump
sdk
API
Overview
SQL extension
expand_more
pgml.deploy()
pgml.embed()
pgml.chunk()
pgml.generate()
pgml.predict()
expand_more
Batch Predictions
pgml.train()
expand_more
Regression
Classification
Clustering
Data Pre-processing
Hyperparameter Search
Joint Optimization
pgml.transform()
expand_more
Fill Mask
Question Answering
Summarization
Text Classification
Text Generation
Text-to-Text Generation
Token Classification
Translation
Zero-shot Classification
pgml.tune()
Client SDK
expand_more
Collections
Pipelines
Vector Search
Document Search
Tutorials
expand_more
Semantic Search
Semantic Search Using Instructor Model
dashboard
PRODUCT
Cloud database
expand_more
Serverless
Dedicated
Enterprise
Vector database
PgCat pooler
expand_more
Features
Installation
Configuration
account_circle
USE CASES
OpenSourceAI
Chatbots
expand_more
Example Application
Search
Embeddings
expand_more
Generating LLM embeddings with open source models
Tuning vector recall while generating query embeddings in the database
Personalize embedding results with application data in your database
Supervised Learning
Natural Language Processing
Fraud Detection
Recommendation Engine
Time-series Forecasting
school
RESOURCES
FAQs
Data Storage & Retrieval
expand_more
Tabular data
Documents
Partitioning
LLM based pipelines with PostgresML and dbt (data build tool)
Benchmarks
expand_more
PostgresML is 8-40x faster than Python HTTP microservices
Scaling to 1 Million Requests per Second
MindsDB vs PostgresML
GGML Quantized LLM support for Huggingface Transformers
Making Postgres 30 Percent Faster in Production
Developer Docs
expand_more
Local Docker Development
Installation
Contributing
Distributed Training
GPU Support
Deploying PostgresML
expand_more
Monitoring
Self-hosting
expand_more
Pooler
Building from source
Replication
Backups
Running on EC2
Monitoring
Postgres
ML
solutions
Overview
Chatbot
Site Search
(coming soon!)
Fraud Detection
(coming soon!)
Forecasting
(coming soon!)
Resources
Documentation
Blog
Pricing
Company
About
Careers
Privacy
Terms of Service
Contact
Community
GitHub
Discord
Formerly Twitter
YouTube
LinkedIn
PostgresML 2023 Ⓒ All rights reserved.