---
title: AI Life Coach
emoji: 🧘
colorFrom: purple
colorTo: blue
sdk: streamlit
sdk_version: "1.24.0"
app_file: app.py
pinned: false
---

# AI Life Coach 🧘

Your personal AI-powered life coaching assistant.

## Features

- Personalized life coaching conversations
- Redis-based conversation memory
- Multiple LLM provider support (Ollama, Hugging Face, OpenAI)
- Dynamic model selection
- Remote Ollama integration via ngrok
- Session management
- Weather information integration
- Text-to-speech capabilities

## How to Use

1. Select a user from the sidebar
2. Configure your Ollama connection (if using remote Ollama)
3. Choose your preferred model
4. Start chatting with your AI Life Coach!

## Requirements

All requirements are specified in . The app automatically handles:
- Streamlit UI
- FastAPI backend (for future expansion)
- Redis connection for persistent memory
- Multiple LLM integrations
- Weather service integration
- Text-to-speech capabilities

## Environment Variables

Configure these in your Hugging Face Space secrets or local  file:

- : Your Ollama server URL (default: ngrok URL)
- : Default model name (default: mistral)
- : Hugging Face API token (for Hugging Face models and TTS)
- : Hugging Face inference API endpoint
- : Whether to use fallback providers (true/false)
- : Redis server hostname (default: localhost)
- : Redis server port (default: 6379)
- : Redis username (optional)
- : Redis password (optional)
- : OpenWeather API key (for weather features)
- : Tavily API key (for web search)

## Architecture

This application consists of:
- Streamlit frontend ()
- Core LLM abstraction ()
- Memory management ()
- Session management ()
- Configuration management ()
- API endpoints (in  directory for future expansion)
- Services ( directory):
  - Weather service ()
  - Text-to-speech service ()
  - Ollama monitor ()

Built with Python, Streamlit, FastAPI, and Redis.