Use Neon as your dev environment for AWS RDS: accelerate your workflow while reducing costs

AI & Embeddings

Build AI applications with Neon Postgres as your vector database

Vector databases enable efficient storage and retrieval of vector data, which is an essential component in building AI applications that leverage Large Language Models (LLMs).

Neon supports the pgvector open-source extension, which enables Postgres as a vector database for storing and querying embeddings. This means you can leverage the open-source database that you trust as your vector store and forget about migrating data or adding a third-party vector storage solution.

Neon's AI Starter Kit provides resources, starter apps, and examples to help get you started.

Ship faster with Neon's AI Starter Kit

Sign up for Neon Postgres and jumpstart your AI application. Our starter apps and resources will help you get up and running.

Sign Up

The Neon AI Starter Kit includes:

  • Neon Postgres with the latest version of the Postgres pgvector extension for storing vector embeddings
  • A variety of hackable, pre-built AI starter apps:
    • AI chat
    • RAG chat
    • Semantic search
    • Hybrid search
    • Reverse image search
    • Chat with PDF
  • A vector search optimization guide for better AI application performance
  • A scaling guide for scaling your app with Neon's Autoscaling and Read Replica features
  • A collection of AI apps built with Neon that you can reference while building your own app

AI basics

AI starter apps

Hackable, fully-featured, pre-built starter apps to get you up and running.

AI integrations

Learn how to integrate Neon Postgres with LLMs and AI platforms.

Preparing your AI app for production

AI apps built with Neon

AI applications built with Neon Postgres that you can reference as code examples or inspiration.

Feature your app here

Share your AI app on our #showcase channel on Discord for consideration.

AI tools

Learn about popular AI tools and how to use them with Neon Postgres.

Last updated on

Edit this page
Was this page helpful?