Ollama App

Run Large Language Models (LLMs) locally on your Home Assistant hardware with complete privacy and no cloud dependency.

Features

🔒 Complete Privacy: All processing happens locally
🚀 Multiple Models: Support for Llama, Mistral, Phi, and more
🎯 REST API: Easy integration with Home Assistant and other services
💾 Model Management: Download, update, and remove models easily
⚡ GPU Support: Acceleration for supported hardware

Installation

Add the J0rsa repository to your Home Assistant
Search for “Ollama” in the App Store (formerly Add-on Store)
Click Install and wait for the download to complete
Configure the app (see Configuration below)
Start the app

Configuration

# Example configuration
gpu_support: false  # Enable if you have compatible GPU
models_path: /data/models  # Where to store models
api_host: 0.0.0.0  # API listening address
api_port: 11434  # API port

Configuration Options

Option	Description	Default
`gpu_support`	Enable GPU acceleration if available	`false`
`models_path`	Directory to store downloaded models	`/data/models`
`api_host`	API listening address	`0.0.0.0`
`api_port`	API listening port	`11434`

Usage

Downloading Models

After starting the app, you can download models using the API:

curl http://homeassistant.local:11434/api/pull -d '{
  "name": "llama2"
}'

Popular Models

llama2: Meta’s Llama 2 model (7B parameters)
mistral: Mistral AI’s 7B model
phi: Microsoft’s Phi-2 model (2.7B)
codellama: Specialized for code generation
neural-chat: Intel’s conversational model

Running Inference

Send a prompt to the model:

curl http://homeassistant.local:11434/api/generate -d '{
  "model": "llama2",
  "prompt": "Why is the sky blue?"
}'

Integration with Home Assistant

You can integrate Ollama with Home Assistant using REST commands:

rest_command:
  ask_ollama:
    url: "http://localhost:11434/api/generate"
    method: POST
    headers:
      Content-Type: "application/json"
    payload: '{"model": "llama2", "prompt": ""}'

Hardware Requirements

Minimum Requirements

CPU: 4 cores recommended
RAM: 8GB minimum (16GB recommended)
Storage: 10GB+ depending on models

Model Size Guidelines

7B models: ~4GB RAM
13B models: ~8GB RAM
30B models: ~16GB RAM

API Documentation

Endpoints

Endpoint	Method	Description
`/api/generate`	POST	Generate text from a prompt
`/api/pull`	POST	Download a model
`/api/tags`	GET	List available models
`/api/delete`	DELETE	Remove a model

Example: List Models

curl http://homeassistant.local:11434/api/tags

Tips and Tricks

Model Selection: Start with smaller models (7B) and upgrade if needed
Performance: Enable GPU support if you have compatible hardware
Storage: Models are stored persistently in /data/models
Memory: Monitor RAM usage, especially with larger models
API Key: Consider adding authentication for external access

Troubleshooting

App Won’t Start

Check logs for error messages
Ensure sufficient RAM is available
Verify port 11434 is not in use

Model Download Fails

Check internet connectivity
Ensure sufficient storage space
Try downloading a smaller model first

Slow Performance

Consider using smaller models
Enable GPU acceleration if available
Close other resource-intensive apps

Support

← Back to Apps

View on GitHub

J0rsa Home Assistant Apps

High-quality Home Assistant apps for backup, AI, networking, and more