# AboutMe AI Chat Demo

A comprehensive AI agent system with multi-service architecture for personal knowledge management and intelligent query responses.

## Architecture Overview

```
User Query → Chat Gateway → LangGraph Supervisor → [Librarian | Opencode | Brain]
                                    ↓
                            Knowledge Service (ChromaDB) ← Airflow ← Gitea API
```

## Services

| Service | Port | Technology | Purpose |
|---------|------|------------|---------|
| Frontend | 5173 | Vite + React + TS | Chat UI |
| Chat Gateway | 8000 | FastAPI | API entry point |
| LangGraph | 8090 | FastAPI + LangGraph | Agent orchestration |
| Knowledge | 8080 | FastAPI + ChromaDB | RAG / Vector search |
| Airflow | 8081 | Apache Airflow | Scheduled ingestion |
| PostgreSQL | 5432 | Postgres 15 | Chat history |

## Quick Start

```bash
# 1. Ensure Docker network exists
docker network create ai-mesh

# 2. Start Knowledge Service
cd knowledge_service && docker-compose up -d

# 3. Start LangGraph Service
cd ../langgraph_service && docker-compose up -d

# 4. Start Chat Demo
cd ../aboutme_chat_demo && docker-compose up -d

# 5. Start Airflow (optional)
cd ../airflow && docker-compose up -d
```

## Environment Variables

Create `.env` files in each service directory:

**knowledge_service/.env:**
```
OPENROUTER_API_KEY=your_key_here
GITEA_URL=https://gitea.lab.audasmedia.com.au
GITEA_TOKEN=your_token
GITEA_USERNAME=sam
```

**langgraph_service/.env:**
```
OPENCODE_PASSWORD=sam4jo
```

**airflow/.env:**
```
AIRFLOW_UID=1000
GITEA_TOKEN=your_token
```

## Project Structure

```
aboutme_chat_demo/
├── frontend/          # React chat interface
├── backend/           # FastAPI gateway (routes to LangGraph)
├── plan.md            # Full project roadmap
└── code_1.md          # Implementation guide

knowledge_service/
├── main.py            # FastAPI + ChromaDB
├── gitea_scraper.py   # Gitea API integration
└── docker-compose.yml

langgraph_service/
├── main.py            # FastAPI entry point
├── supervisor_agent.py # LangGraph orchestration
└── docker-compose.yml

airflow/
├── dags/              # Workflow definitions
│   └── gitea_ingestion_dag.py
└── docker-compose.yml
```

## Technologies

- **Frontend:** Vite, React 19, TypeScript, Tailwind CSS, TanStack Query
- **Backend:** FastAPI, Python 3.11, httpx
- **AI/ML:** LangGraph, LangChain, ChromaDB, OpenRouter API
- **Orchestration:** Apache Airflow (CeleryExecutor)
- **Infrastructure:** Docker, Docker Compose

## Documentation

- `plan.md` - Complete project roadmap (7 phases)
- `code_1.md` - Modular implementation guide
- `code.md` - Legacy implementation reference

## License

MIT