MenuBase/library-docs.md

# Base Project Library Documentation

## Overview
A modular Python library designed for building applications that work with LLMs, translation services, and file processing, with a focus on Windows environments.

## Table of Contents
1. [Installation](#installation)
2. [Project Structure](#project-structure)
3. [Core Components](#core-components)
4. [Services](#services)
5. [Utilities](#utilities)
6. [Examples](#examples)

## Installation

### Requirements
```
Python 3.8+
```

### Dependencies
```bash
pip install -r requirements.txt
```

Required packages:
```text
python-dotenv>=1.0.0
openai>=1.0.0
google-cloud-translate>=3.0.0
pandas>=2.0.0
openpyxl>=3.0.0
langid>=1.1.6
tk>=0.1.0
```

## Project Structure
```
base_project/
├── config/
│   ├── __init__.py
│   ├── api_keys.py        # API key management
│   ├── api_setup.py       # GUI for API configuration
│   └── settings.py        # General settings
│
├── services/
│   ├── llm/              # LLM Services
│   │   ├── base.py
│   │   ├── openai_service.py
│   │   ├── grok_service.py
│   │   ├── ollama_service.py
│   │   ├── batch_processor.py
│   │   └── llm_factory.py
│   │
│   ├── excel/            # Excel Services
│   │   └── excel_service.py
│   │
│   └── translation/      # Translation Services
│       ├── base.py
│       ├── google_translate.py
│       └── translation_factory.py
│
├── utils/
│   ├── file_utils.py     # File handling utilities
│   ├── gui_utils.py      # GUI utilities
│   ├── logger_utils.py   # Logging utilities
│   └── progress_bar.py   # Progress tracking
│
├── menu.py              # Main application interface
├── requirements.txt
└── README.md
```

## Core Components

### 1. API Key Management
The APIKeyManager provides secure storage and retrieval of API keys:

```python
from config.api_keys import APIKeyManager

# Get API keys
openai_key = APIKeyManager.get_openai_key()
google_key = APIKeyManager.get_google_key()

# Store new key
APIKeyManager.store_key("openai", "your-key-here")
```

### 2. GUI Interface
The main menu provides a user-friendly interface:

```python
from menu import MainMenu
import tkinter as tk

def main():
    root = tk.Tk()
    app = MainMenu(root)
    root.mainloop()
```

## Services

### LLM Services
Modular services for different LLM providers with a unified interface.

#### Factory Pattern Usage
```python
from services.llm.llm_factory import LLMFactory

# Create service instance
llm_service = LLMFactory.create_service("openai", model="gpt-4")

# Generate text
response = llm_service.generate_text("Tell me a joke")
```

#### Batch Processing
Efficient processing of multiple items:

```python
from services.llm.batch_processor import BatchProcessor, BatchConfig

# Configure batch processing
config = BatchConfig(
    batch_size=20,
    progress_callback=lambda msg: print(msg)
)

# Create processor
processor = BatchProcessor(llm_service, config)

# Process items
items = [{"text": "Process this"}, {"text": "And this"}]
results = processor.process_batch(
    items=items,
    system_prompt="You are a helpful assistant.",
    template="Process these items: {items}"
)
```

### Translation Services
Translation capabilities with multiple provider support.

#### Google Translate
```python
from services.translation.translation_factory import TranslationFactory

# Create translator
translator = TranslationFactory.create_service("google")

# Translate text
translated = translator.translate_text(
    "Hello world",
    target_language="es"
)

# Batch translation
texts = ["Hello", "World"]
translations = translator.translate_batch(
    texts,
    target_language="es"
)
```

### Excel Services
Robust Excel file handling with retry mechanism and formatting.

```python
from services.excel.excel_service import ExcelService

# Create service
excel_service = ExcelService()

# Read with retries
df = excel_service.read_excel("input.xlsx")

# Save with formatting
format_options = {
    'freeze_row': 2,
    'max_column_width': 50,
    'wrap_threshold': 50,
}

excel_service.save_excel(
    df,
    "output.xlsx",
    format_options=format_options
)
```

## Utilities

### Progress Bar
Visual progress tracking in console:

```python
from utils.progress_bar import ProgressBar

# Create progress bar
progress = ProgressBar(
    total=100,
    prefix="Processing:",
    suffix="Complete"
)

# Update progress
progress.start()
for i in range(100):
    progress.increment()
progress.finish()
```

### Logging
Centralized logging with file and GUI output:

```python
from utils.logging_manager import LoggingManager

# Initialize logging
logger = LoggingManager("./logs")

# Log messages
logger.logger.info("Process started")
logger.logger.error("An error occurred")
```

## Best Practices

1. **API Keys**
   - Never hardcode API keys
   - Use environment variables or the APIKeyManager
   - Store sensitive data securely

2. **Error Handling**
   - Always use try-except blocks for external services
   - Implement retries for network operations
   - Log errors appropriately

3. **Resource Management**
   - Use context managers for file operations
   - Close connections and handlers properly
   - Clean up temporary files

4. **Batch Processing**
   - Use appropriate batch sizes
   - Implement progress tracking
   - Handle partial failures gracefully

## Common Issues and Solutions

### 1. File Access Errors
```python
# Use retry mechanism
excel_service = ExcelService(max_retries=5)
```

### 2. API Rate Limits
```python
# Configure batch size appropriately
config = BatchConfig(batch_size=10, retry_delay=3)
```

### 3. Memory Management
```python
# Process large files in chunks
for chunk in pd.read_excel("large.xlsx", chunksize=1000):
    process_chunk(chunk)
```

## Contributing Guidelines

1. Follow PEP 8 style guide
2. Add type hints to new functions
3. Include docstrings for all modules and functions
4. Add unit tests for new features
5. Update documentation when adding features

## License

MIT License - Feel free to use and modify as needed.