now running
llama 3.1
 __   _   __ ___ __   __   __   __      
|__) / \ /__` | / _` |__) |__  /__` |\/| | 
|   \__/ .__/ | \__> | \  |___ .__/ |  | |__
Open Source Wikipedia Chatbot
This chatbot demo is performing RAG with open-source models right inside Postgres.
Options
Temperature:
MaxTokens:
Top P:
Top K:
Presence Penalty:
Frequency Penalty:
delete
Clear History
"I have a full proof of concept chatbot fully synced
to document changes, all done in 3 hours flat."
Founder @

Why build your chatbot on PostgresML

feature image
All-in-one RAG
Combine LLMs, vector memory, embedding generation, re-ranking, summarization and custom models into a single query
feature image
Simplified Infrastructure
Significantly reduce complex data pipelines with in-database architecture that cuts dev time for builders and latency for users.
feature image
High accuracy
Eliminate hallucinations and deliver real-time responses without endless fine-tuning or training.
feature image
Built-in security
Securely productionize the latest LLMs on your data with a mature, battle-tested database and fewer data transfers between microservices.
feature image
Advanced serach and retrieval features
    Hybrid search
    BTREE, KNN & ANN
    Multi-modal search
feature image
Speed and scalability
No network latencies, no waiting ages for data to arrive in your modeling environment. Scale your data alongside your models to millions of requests
feature image
All-in-one RAG
Combine LLMs, vector memory, embedding generation, re-ranking, summarization and custom models into a single query
feature image
Simplified Infrastructure
Significantly reduce complex data pipelines with in-database architecture that cuts dev time for builders and latency for users.
feature image
High accuracy
Eliminate hallucinations and deliver real-time responses without endless fine-tuning or training.
feature image
Built-in security
Securely productionize the latest LLMs on your data with a mature, battle-tested database and fewer data transfers between microservices.
feature image
Advanced serach and retrieval features
    Hybrid search
    BTREE, KNN & ANN
    Multi-modal search
feature image
Speed and scalability
No network latencies, no waiting ages for data to arrive in your modeling environment. Scale your data alongside your models to millions of requests

How it works

SELECT under_the_hood();

Don't get locked in
to a black box

    Transparency: Easily inspect and understand the SQL-based operations that power the platform (or use Python, JS, C or Rust)
    Customization: Extend platform capabilities by modifying or adding to SQL operations
    Felxibility: Use PGML for your complete workflow, or in tandem with the solutions that work for you

Chat wherever
your users are

Bring factual memory and lightning-speed responses to you website, Discord, Slack and more with a seamless integration to your preferred communication platform

Better price for performance

Our pricing is based on the models you use. It’s designed to minimize costs and operations. You’ll also save because you can replace many existing tools.

View pricing arrow_forward

Start your free
project today

Get Started See Pricing
Start building with PostgresML
Start building with PostgresML

Docs

Docs
Get started with our dev-friendly documentation.

Blog

Blog
Get the latest product updates and guides to help build your leading AI application.

Community

Community
We’re active on our Discord. Connect with the team and fellow PostgresML builders.
PostgresML Logo PostgresML

product

Korvus PGML PpCat Learning PostgresML VPC

solutions

LLMs Embeddings Vector Database Supervised Learning RAG Search Chatbot

Resources

Company

About Careers Privacy Terms of Service Contact

Community

GitHub Discord Formerly Twitter YouTube LinkedIn

PostgresML 2024 Ⓒ All rights reserved.