Files

101 lines
2.6 KiB
Markdown
Raw Permalink Normal View History

2025-11-06 11:08:59 +01:00
# Reason Flow - AI Engineering Reasoning System
An intelligent AI system for complex engineering reasoning with continuous learning capabilities.
## Architecture
- **MODEL1**: Engineering reasoning model that creates step-by-step plans
- **QUERYMODEL**: Execution model that uses tools to carry out plans
- **RAG Pipeline**: Document search and retrieval system
- **6 Specialized Tools**: Query expansion, extraction, reports, web search, PDF search
- **Feedback Loop**: Continuous learning system
## Tech Stack
- **Backend**: Express.js, PostgreSQL, Sequelize
- **Frontend**: React, Socket.io
- **AI Models**: Kimi K2 (Groq), OpenAI
- **RAG**: LangChain, Vector Database
- **Fine-tuning**: SFT, DPO, Correction Memory
## Setup Instructions
1. Install dependencies:
```bash
npm run install-all
```
2. Set up environment variables:
```bash
cp env.example .env
# Edit .env with your API keys and database credentials
```
3. Set up database:
```bash
# Create PostgreSQL database
createdb reason_flow
```
4. Start development servers:
```bash
npm run dev-full
```
## Project Structure
```
reason_flow/
├── server/ # Express.js backend
│ ├── controllers/ # Route controllers
│ ├── models/ # Database models
│ ├── routes/ # API routes
│ ├── services/ # Business logic
│ ├── middleware/ # Custom middleware
│ └── utils/ # Utility functions
├── client/ # React frontend
│ ├── src/
│ │ ├── components/ # React components
│ │ ├── pages/ # Page components
│ │ ├── services/ # API services
│ │ └── utils/ # Utility functions
├── data/ # Training data and documents
├── tests/ # Test files
└── uploads/ # File uploads
```
## Features
- **Intelligent Planning**: AI generates step-by-step engineering plans
- **Tool Execution**: Automated execution using specialized tools
- **Document Search**: RAG-powered document retrieval
- **Continuous Learning**: Feedback loop for model improvement
- **Real-time Chat**: WebSocket-based communication
- **File Upload**: Document processing and indexing
## API Endpoints
- `/api/health` - Health check
- `/api/auth/*` - Authentication
- `/api/chat/*` - Chat functionality
- `/api/models/*` - Model management
- `/api/documents/*` - Document management
- `/api/feedback/*` - Feedback collection
- `/api/tools/*` - Tool execution
## Development
Run tests:
```bash
npm test
```
Build for production:
```bash
npm run build
```
## License
MIT