Ipril - Grammar Assistant Bot

You can try this bot on Telegram by searching for @IprilBot or clicking the link to start a conversation.

A Telegram bot that helps users improve their writing in multiple languages using AI-powered grammar correction.

Features

• Grammar correction in 6 languages (English, Spanish, French, German, Italian, Russian)
• User language preference persistence
• Rate limiting (15 requests/minute per user)
• Automated daily backups
• Error handling and logging
• Unit tests for core functionality

Commands

• /start - Welcome message with instructions
• /setlang [code] - Change language preference
• /currentlang - Show current language

Example Results

Here are some examples of how the bot corrects grammar and engages in conversation:

🇺🇸 English (en)

User: /setlang en
Bot: Language set to English!

User: "Je mange un pomme"
Bot: "[Correction: Je mange une pomme] What do you like to eat?"

🇪🇸 Spanish (es)

User: /setlang es
Bot: ¡Idioma configurado a español!

User: "I goes to the store"
Bot: "[Corrección: I go to the store] ¿Qué te gusta comprar en la tienda?"

🇫🇷 French (fr)

User: /setlang fr
Bot: Langue définie sur français !

User: "Je vais au parc"
Bot: "[Correction: Je vais au parc] Qu'aimes-tu faire au parc?"

🇩🇪 German (de)

User: /setlang de
Bot: Sprache auf Deutsch eingestellt!

User: "Io mangiare la pizza"
Bot: "[Korrektur: Io mangio la pizza] Was isst du gerne?"

🇮🇹 Italian (it)

User: /setlang it
Bot: Lingua impostata su italiano!

User: "Я ходить в магазин"
Bot: "[Correzione: Я хожу в магазин] Cosa ti piace comprare?"

🇷🇺 Russian (ru)

User: /setlang ru
Bot: Язык установлен на русский!

User: "Yo ir al parque"
Bot: "[Исправление: Yo voy al parque] Что тебе нравится делать в парке?"

The bot not only corrects grammar but also:

• Maintains conversation context
• Corrects grammar in the input language (including the "Correction:" text)
• Asks follow-up questions in the chosen language
• Supports 6 languages
• Remembers user preferences
• Has a rate limit of 15 requests per minute

Setup

1. Clone the repository
2. Install dependencies:

   pip install -r requirements.txt

3. Copy .env.example to .env and fill in your credentials:

   cp .env.example .env

4. Edit .env with your:
   • Telegram Bot Token (from @BotFather)
   • DeepSeek API Key

Local Development

1. Create a virtual environment:

   python -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate

2. Run the bot:

   python bot.py

3. Run tests:

   pytest tests/ -v

Testing

The project includes unit tests for core functionality:

• User data management
• Rate limiting
• Bot initialization
• Data persistence

Run tests locally:

pytest tests/ -v

File Structure

• bot.py - Main bot implementation
• requirements.txt - Python dependencies
• .env - Environment variables (not in git)
• user_data.json - User preferences storage
• backups/ - Daily backups of user data
• bot.log - Application logs
• tests/ - Unit tests

Error Handling

The bot includes comprehensive error handling for:

• API failures
• Invalid inputs
• Rate limit exceeded
• File system operations

All errors are logged to bot.log for debugging.

License

MIT License