Getting Started

NeurondB
Quick Start Guide

Get NeurondB up and running in minutes. NeurondB is a production-ready PostgreSQL extension that transforms your database into an AI platform with vector search, ML inference, and hybrid retrieval.

Installation Quick Start Full Installation Guide

Installation

Install NeurondB on your system with these simple steps

Prerequisites

PostgreSQL 16, 17, or 18
PostgreSQL development headers
GCC C compiler
Build tools (make, autoconf)

System Requirements

Minimum 4GB RAM recommended
SSD storage for index performance
Network access for model downloads

Ubuntu/Debian

# Install PostgreSQL development packages
sudo apt-get update
sudo apt-get install -y postgresql-17 \
    postgresql-server-dev-17 \
    build-essential \
    libcurl4-openssl-dev \
    libssl-dev \
    zlib1g-dev

# Clone and build NeurondB
git clone https://github.com/pgElephant/NeurondB.git
cd NeurondB
make PG_CONFIG=/usr/lib/postgresql/17/bin/pg_config
sudo make install PG_CONFIG=/usr/lib/postgresql/17/bin/pg_config

macOS

# Install PostgreSQL via Homebrew
brew install postgresql@17

# Clone and build NeurondB
git clone https://github.com/pgElephant/NeurondB.git
cd NeurondB
make PG_CONFIG=/opt/homebrew/opt/postgresql@17/bin/pg_config
sudo make install PG_CONFIG=/opt/homebrew/opt/postgresql@17/bin/pg_config

Rocky Linux / RHEL

# Install PostgreSQL development packages
sudo dnf install -y postgresql17-server \
    postgresql17-devel \
    gcc \
    make \
    curl-devel \
    openssl-devel \
    zlib-devel

# Clone and build NeurondB
git clone https://github.com/pgElephant/NeurondB.git
cd NeurondB
make PG_CONFIG=/usr/pgsql-17/bin/pg_config
sudo make install PG_CONFIG=/usr/pgsql-17/bin/pg_config

Quick Start

Create your first vector search in minutes

Step 1: Create Extension

CREATE EXTENSION neurondb;

Step 2: Create Table with Vector Column

CREATE TABLE documents (
    id SERIAL PRIMARY KEY,
    title TEXT,
    content TEXT,
    embedding vector(384)
);

Step 3: Generate Embeddings and Search

-- Insert document with embedding
INSERT INTO documents (title, content, embedding) VALUES
    ('Machine Learning', 'Introduction to ML', 
     embed_text('Introduction to Machine Learning'));

-- Semantic search
SELECT title, content,
       embedding <-> embed_text('artificial intelligence') AS distance
FROM documents
ORDER BY distance
LIMIT 10;

You're Ready!

NeurondB is now installed and ready to use. Explore advanced features like HNSW indexing, hybrid search, and RAG pipelines in our comprehensive documentation.

Learn about Vector Types →Understanding Embeddings →

NeurondBQuick Start Guide