Bot Module

​

Overview

​

Functions

​

start()

async def start(update: Update, context: ContextTypes.DEFAULT_TYPE) -> None

• Greets the user with their name using HTML formatting
• Introduces MilesONerd AI capabilities
• Directs users to the /help command for more information

​

help_command()

async def help_command(update: Update, context: ContextTypes.DEFAULT_TYPE) -> None

• Displays all available commands (/start, /help, /about)
• Explains message handling capabilities:
  • Short questions: Quick responses using lightweight model
  • Long messages: Summarization and detailed response
  • Summarization requests: Using ‘summarize’ or ‘tldr’ keywords
  • Chat-related queries: Optimized conversation handling
  • Regular messages: Comprehensive AI-powered responses

​

about_command()

async def about_command(update: Update, context: ContextTypes.DEFAULT_TYPE) -> None

• Provides information about MilesONerd AI features:
  • Advanced language understanding
  • Internet search integration
  • Continuous learning from interactions
  • Multiple AI models for different tasks
• Credits the technology stack (python-telegram-bot and Hugging Face models)

​

handle_message()

async def handle_message(update: Update, context: ContextTypes.DEFAULT_TYPE) -> None

1. Long messages (>100 words)
   • Uses BART for summarization
   • Uses Llama for response generation based on summary
   • Max length: 200 tokens
2. Summarization requests (keywords: ‘summarize’, ‘summary’, ‘tldr’)
   • Uses BART summarization model
3. Chat/conversation queries (keywords: ‘chat’, ‘conversation’, ‘talk’)
   • Uses Llama model
   • Max length: 200 tokens
4. Short queries (less than 10 words)
   • Uses Llama for quick responses
   • Max length: 100 tokens
5. Default messages
   • Uses Llama for general responses
   • Max length: 150 tokens

• Logs errors using the logger
• Sends a user-friendly error message on failure
• Shows typing indicator while processing

​

initialize()

async def initialize() -> bool

• Calls ai_handler.initialize_models() to load AI models
• Logs initialization progress and results
• Returns initialization status

• Catches and logs any exceptions during initialization
• Returns False on failure

​

main()

def main() -> None

1. Environment Setup
   • Retrieves TELEGRAM_BOT_TOKEN from environment variables
   • Exits if token is not found
2. Application Creation
   • Creates Telegram Application with bot token
   • Sets up event loop for async operations
3. Model Initialization
   • Runs initialize() to load AI models
   • Exits if initialization fails
4. Handler Registration
   • Registers command handlers: /start, /help, /about
   • Registers message handler for text messages (excluding commands)
5. Bot Execution
   • Starts polling for updates
   • Allows all update types
   • Logs startup message

• Validates presence of bot token
• Ensures models are initialized before starting
• Properly closes event loop on exit
• Handles KeyboardInterrupt for graceful shutdown
• Re-raises exceptions for proper error handling

​

Dependencies

import asyncio
import logging
import os
from dotenv import load_dotenv
from telegram import Update
from telegram.ext import Application, CommandHandler, MessageHandler, filters, ContextTypes
from ai_handler import ai_handler

​

Environment Variables

• TELEGRAM_BOT_TOKEN (required): Telegram bot authentication token

​

Logging

logging.basicConfig(
    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
    level=logging.INFO
)