Add proper Hugging Face Spaces configuration to README.md
Browse files
README.md
CHANGED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
title: AI Life Coach
|
| 3 |
+
emoji: 🧘
|
| 4 |
+
colorFrom: purple
|
| 5 |
+
colorTo: blue
|
| 6 |
+
sdk: streamlit
|
| 7 |
+
sdk_version: "1.24.0"
|
| 8 |
+
app_file: app.py
|
| 9 |
+
pinned: false
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# AI Life Coach 🧘
|
| 13 |
+
|
| 14 |
+
Your personal AI-powered life coaching assistant.
|
| 15 |
+
|
| 16 |
+
## Features
|
| 17 |
+
|
| 18 |
+
- Personalized life coaching conversations
|
| 19 |
+
- Redis-based conversation memory
|
| 20 |
+
- Multiple LLM provider support (Ollama, Hugging Face, OpenAI)
|
| 21 |
+
- Dynamic model selection
|
| 22 |
+
- Remote Ollama integration via ngrok
|
| 23 |
+
|
| 24 |
+
## How to Use
|
| 25 |
+
|
| 26 |
+
1. Select a user from the sidebar
|
| 27 |
+
2. Configure your Ollama connection (if using remote Ollama)
|
| 28 |
+
3. Choose your preferred model
|
| 29 |
+
4. Start chatting with your AI Life Coach!
|
| 30 |
+
|
| 31 |
+
## Requirements
|
| 32 |
+
|
| 33 |
+
All requirements are specified in `requirements.txt`. The app automatically handles:
|
| 34 |
+
- Streamlit UI
|
| 35 |
+
- FastAPI backend (for future expansion)
|
| 36 |
+
- Redis connection for persistent memory
|
| 37 |
+
- Multiple LLM integrations
|
| 38 |
+
|
| 39 |
+
## Environment Variables
|
| 40 |
+
|
| 41 |
+
Configure these in your Hugging Face Space secrets or local `.env` file:
|
| 42 |
+
|
| 43 |
+
- `OLLAMA_HOST`: Your Ollama server URL (default: ngrok URL)
|
| 44 |
+
- `LOCAL_MODEL_NAME`: Default model name (default: mistral)
|
| 45 |
+
- `HF_TOKEN`: Hugging Face API token (for Hugging Face models)
|
| 46 |
+
- `HF_API_ENDPOINT_URL`: Hugging Face inference API endpoint
|
| 47 |
+
- `USE_FALLBACK`: Whether to use fallback providers (true/false)
|
| 48 |
+
- `REDIS_HOST`: Redis server hostname (default: localhost)
|
| 49 |
+
- `REDIS_PORT`: Redis server port (default: 6379)
|
| 50 |
+
- `REDIS_USERNAME`: Redis username (optional)
|
| 51 |
+
- `REDIS_PASSWORD`: Redis password (optional)
|
| 52 |
+
|
| 53 |
+
## Architecture
|
| 54 |
+
|
| 55 |
+
This application consists of:
|
| 56 |
+
- Streamlit frontend (`app.py`)
|
| 57 |
+
- Core LLM abstraction (`core/llm.py`)
|
| 58 |
+
- Memory management (`core/memory.py`)
|
| 59 |
+
- Configuration management (`utils/config.py`)
|
| 60 |
+
- API endpoints (in `api/` directory for future expansion)
|
| 61 |
+
|
| 62 |
+
Built with Python, Streamlit, FastAPI, and Redis.
|