ollama-remote-chat-cli 0.1.0

Remote CLI client for Ollama servers - Network-ready chat interface with history tracking and inference control

Ollama Chat CLI

A feature-rich command-line interface for Ollama with chat history, inference settings, and beautiful UI.

Features

• Beautiful Claude Code-style interface
• Chat history with session management
• Configurable inference settings (temperature, top_p, context window, etc.)
• Real-time context tracking and token usage
• Easy model switching and management
• Search through chat history
• Support for local and remote Ollama servers
• Secure configuration with .env file

Requirements

• Python 3.7+
• Ollama installed and running
• pip (Python package manager)

Quick Start

1. Clone the Repository

git clone https://github.com/yourusername/ollama-chat-cli.git
cd ollama-chat-cli

2. Install Dependencies

pip install -r requirements.txt

Or if using the package:

pip install -e .

3. Configure Your Connection

Copy the example environment file:

cp .env.example .env

Edit .env with your preferred connection method (see below).

4. Run the CLI

python ollama_chat/cli.py

Or if installed as a package:

ollama-chat
# or the short alias:
oc

Configuration Methods

Method 1: Local Connection (Default)

If Ollama is running on the same machine:

OLLAMA_HOST=http://localhost:11434
OLLAMA_MODEL=llama2

Setup:

1. Install Ollama from ollama.ai
2. Run: ollama serve
3. Pull a model: ollama pull llama2

---

Method 2: Hostname Connection (.local / mDNS)

For connecting to another computer on your local network using its hostname:

OLLAMA_HOST=http://my-computer.local:11434
OLLAMA_MODEL=gemma3:12b

Setup:

1. Find your computer's hostname:

   • Windows: hostname in CMD
   • Mac: System Preferences → Sharing → Computer Name
   • Linux: hostname in terminal

2. Ensure mDNS/Bonjour is working:

   • Windows: Install Bonjour Print Services
   • Mac/Linux: Built-in

3. Test connection: ping my-computer.local

4. Configure firewall to allow port 11434

Common hostnames:

• desktop.local
• macbook.local
• xav-pcx.local
• server.local

---

Method 3: Static IP Address

If your computer has a fixed IP on your network:

OLLAMA_HOST=http://192.168.1.100:11434
OLLAMA_MODEL=mistral

Setup:

1. Set a static IP on your Ollama server machine

2. Find your IP address:

   • Windows: ipconfig → IPv4 Address
   • Mac: ifconfig en0 | grep inet
   • Linux: ip addr show

3. Configure firewall to allow port 11434

4. Test: Open browser to http://192.168.1.100:11434 (should show "Ollama is running")

---

Method 4: Dynamic IP (Current Session)

For temporary connections when IP changes:

OLLAMA_HOST=http://192.168.1.XXX:11434
OLLAMA_MODEL=llama2

Setup:

1. Find current IP (see Method 3)
2. Update .env each time IP changes
3. Consider using hostname (Method 2) instead for permanent setup

---

Method 5: Remote Server

For connecting to Ollama on a remote server:

OLLAMA_HOST=https://ollama.myserver.com
OLLAMA_MODEL=llama3.3

Setup:

1. Set up Ollama on remote server
2. Configure reverse proxy (nginx/caddy) with SSL
3. Open firewall port (11434 or custom)
4. Test connection: curl https://ollama.myserver.com/api/tags

---

Method 6: Docker

If running Ollama in Docker:

OLLAMA_HOST=http://localhost:11434
OLLAMA_MODEL=llama2

Setup:

docker run -d -p 11434:11434 --name ollama ollama/ollama
docker exec -it ollama ollama pull llama2

---

Method 7: WSL (Windows Subsystem for Linux)

Accessing Windows host from WSL:

OLLAMA_HOST=http://host.docker.internal:11434
OLLAMA_MODEL=llama2

Or find Windows IP from WSL:

ip route | grep default | awk '{print $3}'

---

Available Commands

Command	Description
/help	Show all available commands
/models	List available models
/switch	Switch to a different model
/pull	Download a new model
/delete	Delete a model
/host	Change Ollama host URL
/config	Show current configuration
/settings	Configure inference settings (temperature, etc.)
/modelinfo	Show detailed model information
/history	View chat history
/search	Search chat history
/clear	Clear conversation context
/new	Start a new chat session
/multi	Enter multi-line input mode
/exit	Exit the chat

Inference Settings

Configure AI behavior with /settings:

• Temperature (0.0-2.0): Controls creativity

  • 0.1-0.3 for coding/math
  • 0.6-0.8 for general chat
  • 1.0-1.5 for creative writing

• Top P (0.0-1.0): Nucleus sampling (default: 0.9)

• Top K (1-100): Token choice limits (default: 40)

• Context Window (128-32768): Conversation memory (default: 2048)

• Max Output (1-4096): Response length (default: 512)

Troubleshooting

"Could not connect to Ollama"

1. Verify Ollama is running:

   curl http://localhost:11434
   # Should return: "Ollama is running"
   

2. Check firewall settings:

   • Windows: Allow port 11434 in Windows Firewall
   • Mac: System Preferences → Security → Firewall Options
   • Linux: sudo ufw allow 11434

3. For hostname issues:

   # Test if hostname resolves
   ping your-hostname.local
   
   # If it fails, use IP address instead
   

4. For Docker:

   docker ps  # Verify container is running
   docker logs ollama  # Check logs
   

"Model not found"

# List available models
ollama list

# Pull the model you want
ollama pull llama2

"Permission denied"

# Make sure config directory is writable
chmod 755 ~/.ollama_chat_config.json

File Structure

ollama-chat-cli/
├── ollama_chat/
│   ├── __init__.py
│   ├── __main__.py
│   ├── cli.py           # Main CLI application
│   ├── ui.py            # UI components and banner
│   ├── api.py           # Ollama API client
│   ├── config.py        # Configuration management
│   ├── commands.py      # Command handlers
│   └── history.py       # Chat history manager
├── .env.example         # Example configuration
├── .gitignore          
├── setup.py            
├── requirements.txt    
└── README.md

Security Notes

• .env file is gitignored and won't be committed
• Config files are stored in your home directory
• Never commit your actual .env file to Git
• For remote connections, use HTTPS with proper SSL certificates

License

MIT License - feel free to use and modify!

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Support

If you encounter any issues, please open an issue on GitHub.