SafeRag Support

1. First Launch Setup

When you first launch SafeRag:

1. The app will check if Ollama is installed
2. If not installed, you'll be guided through Ollama installation
3. Create your first user account (becomes admin automatically)
4. Download your first AI model (we recommend Llama 3.2 to start)
5. Start chatting!

2. Downloading AI Models

SafeRag makes model management easy:

• Go to Settings → Models
• Click "Download New Model"
• Choose from available models (Llama, Mistral, Gemma, etc.)
• Wait for download to complete (can be several GB)
• Model appears in chat mode selector

SafeRag won't start - what should I check?

• Verify macOS 14.0+ (About This Mac)
• Check if Ollama is running (ollama list in Terminal)
• Ensure at least 5GB free disk space
• Try restarting Ollama: killall ollama && ollama serve
• Check Console app for error messages

How do I upload documents for RAG?

To use RAG (Retrieval-Augmented Generation):

1. Click the Documents tab in the sidebar
2. Click "Upload Document" button
3. Select PDF, DOCX, TXT, or MD files
4. Wait for processing (creates vector embeddings)
5. Document appears in your library
6. Enable RAG mode in chat to query your documents

AI responses are slow - how can I speed them up?

• Use smaller models: Llama 3.2 8B instead of 70B
• Upgrade RAM: 16GB+ helps significantly
• Apple Silicon: M-series chips provide excellent AI performance
• Close other apps: Free up system resources
• Reduce context length: Shorter conversations process faster

How do I add more users?

Multi-user setup (requires Pro):

1. Log in as admin user
2. Go to Settings → Users
3. Click "Add User"
4. Enter username, email, password
5. Assign role (Admin or User)
6. New user can now log in

Where is my data stored?

All SafeRag data is stored locally:

• Location: ~/Library/Application Support/io.halldor.SafeRag/
• Database: data/chat.db (SQLite)
• Vector DB: data/rag/ (LanceDB)
• Backups: backups/
• Audit logs: audit/

How do I backup my data?

SafeRag supports encrypted backups:

1. Go to Settings → Data
2. Click "Create Backup"
3. Choose backup location
4. Encrypted .saferag file is created
5. To restore: Settings → Data → Restore Backup

Can I export my data?

Yes! Complete data portability:

• Settings → Data → Export All Data
• Creates JSON file with all chats, documents, settings
• Individual chats can be exported via chat menu
• Documents can be re-downloaded from library

What's the difference between Free and Pro?

Free Version:

• Single user (admin only)
• Up to 5 RAG documents
• All chat modes
• Model selection
• Session management

Pro Version ($29 one-time):

• Up to 5 users with RBAC
• Unlimited RAG documents
• Watch folder automation
• Data export functionality
• Audit logging
• Advanced compliance features

How do I upgrade to Pro?

If purchased via Mac App Store:

• Click "Upgrade to Pro" in any Pro feature
• Complete purchase through App Store
• Pro features unlock immediately

If purchased directly:

• Contact support@corixa.io for license key
• Enter license key in Settings → License

Ollama Connection Error

Symptoms: "Cannot connect to Ollama" or red status indicator

Note: SafeRag includes a bundled Ollama - no separate installation needed.

Solutions:

1. Quit SafeRag completely (Cmd+Q) and restart it
2. If you have a separate Ollama installed, quit it to avoid port conflicts
3. Restart your Mac if the issue persists

Database Locked Error

Symptoms: "Database is locked" when trying to save

Solutions:

1. Quit SafeRag completely
2. Check for multiple SafeRag processes: ps aux | grep SafeRag
3. Kill duplicate processes if found
4. Restart SafeRag
5. If persists, restore from backup

RAG Not Finding My Documents

Symptoms: RAG mode enabled but documents not referenced

Solutions:

1. Verify documents are fully processed (green checkmark)
2. Ensure RAG mode is enabled in chat (toggle in chat input)
3. Try more specific questions related to document content
4. Check embedding model is downloaded (Settings → Models)
5. Re-upload document if processing failed