<div align="center"> <img src="assets/autollama-logo.png" alt="AutoLlama Logo" width="200"/> <h1>The Context-Aware RAG Framework</h1> <h2><em>Your Documents Have Context. Now Your RAG Does Too.</em></h2>

</div>

Context isn't a nice-to-have—it's the difference between information and understanding.

For too long, RAG has been about finding chunks, not understanding documents. AutoLlama changes that. Built on Anthropic's breakthrough contextual retrieval methodology, it's the first JavaScript-first RAG framework that actually comprehends your documents the way humans do.

It's like RAG finally learned how to read.

Why Context Changes Everything

Traditional RAG: "Here are 5 chunks that mention 'machine learning'" AutoLlama: "Here's how machine learning evolves through this research paper, building from foundational concepts in Chapter 2 to advanced applications in Chapter 7"

See the difference? That's context at work.

What Makes AutoLlama Revolutionary

🧠 Anthropic's Contextual Retrieval

Stop getting random, disconnected chunks. AutoLlama implements Anthropic's breakthrough methodology that delivers 60% better accuracy by understanding where each piece of information fits in the larger narrative.

🚀 One-Command Setup

No more wrestling with complex configurations. Get started instantly:

Global CLI: npm install -g autollama && autollama init (2-minute setup)
NPX: npx autollama init my-app (instant, no installation)
Docker: docker compose up -d (60-second deploy)
Native: Clone and npm run dev (development mode)

⚡ JavaScript-First Architecture

Built for developers who want power without pain. Full-stack JavaScript with multiple deployment modes:

Local Development: SQLite + embedded services
Hybrid: Mix of local and cloud services
Production: PostgreSQL + enterprise features

🔓 Open Source Freedom

Your documents, your infrastructure, your control. No vendor lock-in, no usage limits, no monthly subscriptions. Just pure, customizable technology.

📊 Real-Time Intelligence

Watch your documents transform from static files into living, searchable knowledge with real-time processing updates and interactive visualizations.

🔌 Native OpenWebUI Integration

Chat with your documents instantly. Built-in RAG pipeline that OpenWebUI automatically discovers—no complex setup required.

🛠️ Installation Methods

🚀 Quick Start (2 Minutes)

The fastest way to get AutoLlama running:

# Install globally 
npm install -g autollama

# Initialize new project with guided setup
autollama init my-rag-project

# Start your RAG framework
autollama start

That's it! Open http://localhost:8080 and start uploading documents.

Alternative Installation Methods

# NPX (no global installation)
npx autollama@latest init my-project

# Docker (traditional method)
git clone https://github.com/autollama/autollama.git
cd autollama && docker compose up -d

🛠️ CLI Commands

AutoLlama includes a full-featured CLI for project management:

# Project initialization
autollama init [project-name]    # Create new project with guided setup
autollama doctor                 # Diagnose system and configuration issues

# Service management  
autollama start                  # Start all services
autollama stop                   # Stop services gracefully
autollama status                 # Show service status and health

# Docker shortcuts
autollama docker:up              # Start Docker containers
autollama docker:down            # Stop Docker containers

Prerequisites

For NPM/CLI Installation

Node.js: 16+ (check with node --version)
NPM: 7+ (check with npm --version)
Memory: 4GB+ RAM recommended
OpenAI API Key: Get from https://platform.openai.com/api-keys

For Docker Installation (Optional)

Docker: 20+ with Docker Compose
Memory: 8GB+ RAM recommended for full containerized setup

Required Software (Docker Method Only)

1. Docker & Docker Compose Installation

For Ubuntu/Debian:

# Update package index
sudo apt update

# Install basic dependencies
sudo apt install curl gnupg apt-transport-https ca-certificates lsb-release

# Add Docker's official GPG key
curl -fsSL https://download.docker.com/linux/debian/gpg | sudo gpg --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg

# Add Docker repository
echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://download.docker.com/linux/debian $(lsb_release -cs) stable" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null

# Update package index
sudo apt update

# Install Docker
sudo apt install docker-ce docker-ce-cli containerd.io docker-compose-plugin

# Add your user to docker group
sudo usermod -aG docker $USER

# Start and enable Docker
sudo systemctl start docker
sudo systemctl enable docker

For CentOS/RHEL/Fedora:

# Install Docker
sudo dnf install docker docker-compose

# Start and enable Docker
sudo systemctl start docker
sudo systemctl enable docker

# Add user to docker group
sudo usermod -aG docker $USER

For macOS: Download Docker Desktop from https://www.docker.com/products/docker-desktop/

After installation:

# Log out and back in, then verify installation
docker --version
docker compose version

# Test Docker permissions
docker ps

Troubleshooting Docker Permissions: If you encounter "permission denied" errors:

# Refresh group membership without logging out
newgrp docker

# Or use sudo temporarily
sudo docker compose up -d

2. Tailscale Installation (Optional but Recommended)

AutoLlama includes Tailscale integration for secure networking. Install Tailscale before running the containers:

Get your install script:

Visit https://login.tailscale.com/admin/machines/new-linux
Copy your personalized install command
Run it (example format):

curl -fsSL https://tailscale.com/install.sh | sh && sudo tailscale up --auth-key=tskey-auth-YOUR-KEY-HERE

After Tailscale installation:

# Create required config directory
mkdir -p ~/.config

# Create tsauthkey file (required for Docker mount)
touch ~/.config/tsauthkey
chmod 600 ~/.config/tsauthkey

# Verify Tailscale is running
sudo tailscale status

Required Accounts & API Keys

Before starting, obtain the following:

OpenAI API key from https://platform.openai.com/api-keys
Qdrant Cloud account from https://cloud.qdrant.io (or set up local Qdrant)
PostgreSQL database (can use cloud providers or local setup)

Quick Start

Ready to experience contextual RAG? Choose your adventure:

🦙 NPX Installation (Latest - v3.0.7)

New professional setup wizard experience:

# Create new project with guided setup
npx autollama@latest init my-rag-app

# Follow the 4-stage setup wizard, then:
cd my-rag-app
npx autollama start

# 🌐 Your AutoLlama: http://localhost:8080

Features: Interactive configuration, system validation, automated setup, state management for resume capability.

Perfect for: Quick prototyping and testing the new setup experience.

🐳 Docker Installation (Zero-Configuration)

AutoLlama v3.0 features automatic database setup and migrations!

git clone https://github.com/autollama/autollama.git autollama
cd autollama
cp example.env .env
# Add your OPENAI_API_KEY to .env
docker compose up -d

# That's it! No manual database fixes required! 🎉

Auto-Migration Features:

✅ Automatic Schema Setup: Creates all tables and indexes automatically
✅ PostgreSQL Wait Logic: Waits for database readiness before starting
✅ Broken Installation Recovery: Detects and fixes missing schema elements
✅ Extension Management: Enables required PostgreSQL extensions
✅ Migration Tracking: Prevents duplicate migrations with smart detection

Perfect for: Production deployment, team development, enterprise use.

🔧 Native Installation (Maximum Control)

For developers who want full control:

git clone https://github.com/autollama/autollama.git autollama
cd autollama
npm install
npm run setup
npm run dev

Perfect for: Custom deployments, contributing to AutoLlama, advanced configurations.

Configuration

Environment Variables

Key configuration options in .env:

# AI Services
OPENAI_API_KEY=your_openai_api_key_here

# Database Configuration
DATABASE_URL=postgresql://user:password@host:5432/autollama
QDRANT_URL=https://your-cluster.qdrant.io
QDRANT_API_KEY=your_qdrant_api_key

# Contextual Embeddings (Enhanced Processing)
ENABLE_CONTE

Autollama

Install / Use

README