# RAG System Directory Structure

This document describes the new directory structure created for the RAG System refactoring.

## Overview

The new structure follows a clean layered architecture with four main layers:
- **Domain Layer**: Core business logic and domain models
- **Application Layer**: Use cases and application services
- **Infrastructure Layer**: Technical capabilities and external integrations
- **Presentation Layer**: HTTP request/response handling

## Directory Structure

```
rag_system/
├── src/                              # Source code
│   ├── domain/                       # Domain layer
│   │   ├── vector_search/            # Vector search domain
│   │   ├── document_parsing/         # Document parsing domain
│   │   ├── knowledge_base/           # Knowledge base domain
│   │   └── shared/                   # Shared domain concepts
│   │
│   ├── application/                  # Application layer
│   │   ├── vector_search/            # Vector search use cases
│   │   ├── document_parsing/         # Document parsing use cases
│   │   ├── knowledge_base/           # Knowledge base use cases
│   │   └── shared/                   # Shared application concepts
│   │
│   ├── infrastructure/               # Infrastructure layer
│   │   ├── vector_db/                # Vector database implementations
│   │   ├── database/                 # Database and ORM models
│   │   ├── external_services/        # External service integrations
│   │   ├── file_storage/             # File storage implementations
│   │   └── parsers/                  # Document parser implementations
│   │
│   ├── presentation/                 # Presentation layer
│   │   ├── api/                      # API routers
│   │   │   └── v1/                   # API version 1 endpoints
│   │   └── schemas/                  # Request/response schemas
│   │
│   ├── config/                       # Configuration management
│   └── shared/                       # Shared utilities
│
├── tests/                            # Test suite
│   ├── unit/                         # Unit tests
│   │   ├── domain/                   # Domain layer tests
│   │   ├── application/              # Application layer tests
│   │   └── infrastructure/           # Infrastructure layer tests
│   ├── integration/                  # Integration tests
│   │   ├── api/                      # API integration tests
│   │   └── database/                 # Database integration tests
│   ├── e2e/                          # End-to-end tests
│   └── fixtures/                     # Test fixtures and data
│
├── docs/                             # Documentation
├── scripts/                          # Utility scripts
└── docker/                           # Docker configuration
```

## Layer Responsibilities

### Domain Layer (`src/domain/`)
- Core business logic and rules
- Domain entities and value objects
- Domain services
- Repository interfaces
- Domain events
- **No external framework dependencies**

### Application Layer (`src/application/`)
- Coordinates domain objects to complete use cases
- Defines application service interfaces
- Handles transaction boundaries
- DTO (Data Transfer Object) conversions
- Command and query handlers

### Infrastructure Layer (`src/infrastructure/`)
- Data persistence implementations
- External service integrations
- File system operations
- Message queues
- Cache implementations

### Presentation Layer (`src/presentation/`)
- HTTP request and response handling
- API route definitions
- Request validation and response serialization
- Exception to HTTP error conversion
- Middleware (logging, authentication, CORS, etc.)

## Configuration (`src/config/`)
- Centralized configuration management
- Environment-specific settings
- Database configuration
- Vector database configuration
- Logging configuration

## Shared Utilities (`src/shared/`)
- Common utilities and helper functions
- Base exceptions
- Logging utilities

## Test Structure (`tests/`)
- **Unit tests**: Test individual components in isolation
- **Integration tests**: Test component interactions
- **E2E tests**: Test complete user scenarios
- **Fixtures**: Shared test data and fixtures

## Status

✅ Task 1.1 completed: All directories and `__init__.py` files have been created successfully.

## Next Steps

The next tasks in Phase 1 are:
- Task 1.2: Set up configuration management system
- Task 1.3: Write configuration management unit tests
- Task 1.4: Establish testing framework
- Task 1.5: Configure logging system
- Task 1.6: Write logging system tests
- Task 1.7: Configure CI/CD pipeline