Prerequisites
Before you begin, ensure you have:- Docker 24.0+ with Docker Compose v2 installed
- Operating System: Linux (Ubuntu 22.04+), macOS, or Windows with WSL2
- Hardware: Minimum 8GB RAM, 20GB disk space
- API Keys:
- Anthropic API key (for AI features) OR self-hosted LLM setup
For production deployments, see our comprehensive Deployment Guide.
Step 1: Clone the Repository
Step 2: Create Environment Configuration
Copy the example environment file:.env and configure the following minimum required variables:
Step 3: Start Omni Services
Launch all services using Docker Compose:The first startup will take a few minutes as Docker pulls images and initializes the database.
Step 4: Verify Installation
Check that all services are running:omni-webomni-searcheromni-indexeromni-aipostgresrediscaddy
Step 5: Access Omni
Open your browser and navigate to:- Click “Create Account”
- Enter your email and password
- The first user is automatically granted admin privileges
Congratulations! Omni is now running on your local machine.
Step 6: Connect Your First Data Source
Now let’s connect a data source so you have something to search.Google Workspace
Connect Drive, Docs, and Gmail
Atlassian
Connect Confluence and JIRA
Web
Crawl and index websites
Quick Connector Setup Example
Here’s how to connect a website using the Web connector:- Navigate to Settings → Integrations
- Under Available Integrations, find the Web connector and click Connect
- Enter the root URL of the website you want to index (e.g.,
https://docs.example.com) - Click Connect and wait for initial sync
What’s Next?
Now that Omni is running, explore these features:Search Your Data
Learn how to use Omni’s search interface
AI Assistant
Ask questions and get AI-powered answers
Add More Connectors
Connect additional data sources
Deploy to Production
Move to a production environment
Common Issues
Services won't start
Services won't start
Check Docker logs for errors:Common causes:
- Port 3000 already in use
- Insufficient memory (needs 8GB+ RAM)
- Missing environment variables
Cannot access http://localhost:3000
Cannot access http://localhost:3000
Verify the web service is running:Check if port 3000 is accessible:
Database connection errors
Database connection errors
Ensure PostgreSQL is fully started:Wait for the message: “database system is ready to accept connections”
AI responses not working
AI responses not working
Check your LLM provider configuration:
- Verify
ANTHROPIC_API_KEYis set correctly - Check API key has sufficient credits
- Review AI service logs:
Stopping Omni
To stop all services:Configuration Tips
For better performance in development:- Increase Docker Resources: Allocate at least 8GB RAM to Docker
- Use SSD Storage: Database performance improves significantly with SSDs
- Configure Log Levels: Set
LOG_LEVEL=infoin.envfor less verbose logs
Next Steps
Architecture Overview
Learn how Omni works under the hood