📚 Documentation   •   🖥️ Application   •   🏠 Home

• Install pyenv
  • Install python 3.12: pyenv install 3.12
• Install pyenv-virtualenv
• Install poetry
• Create a virtualenv: pyenv virtualenv 3.12 python-airline-support-bot
  • Activate the virtualenv: pyenv activate python-airline-support-bot
• Install dependencies: poetry install
• Install pre-commit: poetry run pre-commit install

An AI-powered airline customer support bot that can handle flight-related questions using OpenAI's GPT models with intelligent tool calling.

• 🤖 AI Tool Calling: Uses OpenAI's function calling to intelligently choose when to look up flight information
• Flight Information: Check real-time flight status, gates, terminals, and schedules
• Intelligent Conversations: Natural language processing for customer inquiries
• Smart Function Selection: AI automatically decides which tools to use based on customer questions
• Multi-topic Support: Handles questions about:
  • Flight schedules and status
  • Booking assistance
  • Baggage policies
  • Check-in procedures
  • Cancellation and refund policies
  • Special assistance requests
  • Frequent flyer programs
  • General travel information
• Command Line Interface: Easy-to-use interactive CLI
• Programmatic API: Use the bot in your own applications

The bot uses OpenAI's function calling feature to intelligently decide when to look up flight information:

• Automatic Detection: The AI determines when a customer question requires flight data
• Smart Tool Selection: Chooses the appropriate tool (flight lookup, route search, or general info)
• Contextual Responses: Combines tool results with natural language responses

1. get_flight_info: Look up specific flight details by flight number
2. search_flights_by_route: Find flights between cities
3. get_all_flights: List all available flights

• Python 3.12+
• OpenAI API key (Get one here)

1. Clone the repository:

   git clone <repository-url>
   cd python-airline-support-bot

2. Install dependencies using Poetry:

   poetry install

3. Set up your OpenAI API key:

   export OPENAI_API_KEY="your_api_key_here"

   Or create a .env file:

   echo "OPENAI_API_KEY=your_api_key_here" > .env

Run the bot in interactive mode:

poetry run airline-bot

Or using Python directly:

poetry run python -m python_airline_support_bot.cli

You: What's the status of flight AA123?
🤖 Bot: I'll look up flight AA123 for you.

Flight AA123:
• Route: New York (JFK) → Los Angeles (LAX)
• Departure: 08:00 AM
• Arrival: 11:30 AM
• Status: On Time
• Terminal: Terminal 4
• Gate: A12

Flight AA123 is currently on time and will be departing from gate A12 in Terminal 4.

You: Can you find flights from New York to Los Angeles?
🤖 Bot: Let me search for flights from New York to Los Angeles.

Found 1 flight(s) from New York to Los Angeles:

Flight AA123:
• Route: New York (JFK) → Los Angeles (LAX)
• Departure: 08:00 AM
• Arrival: 11:30 AM
• Status: On Time
• Terminal: Terminal 4
• Gate: A12

You: What's your baggage policy?
🤖 Bot: I'd be happy to help you with baggage information! For carry-on bags, most airlines allow one personal item and one carry-on bag...

The AI automatically chooses which tools to use:

from python_airline_support_bot import AirlineSupportBot

# Initialize the bot
bot = AirlineSupportBot()

# Ask questions - AI will automatically use tools when needed
response = bot.process_message("What's the status of flight AA123?")
print(response)

# The AI will automatically call get_flight_info tool and format the response

# Direct access to public methods is still available
flights = bot.get_available_flights()
for flight in flights:
    print(f"{flight.flight_number}: {flight.status}")

# Search for flights by route
ny_to_la_flights = bot.search_flights_by_route("New York", "Los Angeles")
for flight in ny_to_la_flights:
    print(f"Found: {flight.flight_number} - {flight.departure_time}")

The bot comes with sample flight data for demonstration:

• __init__(api_key: Optional[str] = None): Initialize the bot
• process_message(user_message: str) -> str: Process a user message and return response (uses AI tool calling)
• reset_conversation(): Clear conversation history
• get_available_flights() -> List[FlightInfo]: Get all available flights
• search_flights_by_route(departure_city: str, arrival_city: str) -> List[FlightInfo]: Search flights

The AI can automatically call these functions based on user questions:

• get_flight_info(flight_number: str): Look up specific flight details
• search_flights_by_route(departure_city: str, arrival_city: str): Search flights by route
• get_all_flights(): Get all available flights

class FlightInfo(BaseModel):
    flight_number: str
    departure_city: str
    arrival_city: str
    departure_time: str
    arrival_time: str
    status: str
    gate: Optional[str] = None
    terminal: Optional[str] = None

• OPENAI_API_KEY: Your OpenAI API key (required)
• OPENAI_MODEL: OpenAI model to use (default: gpt-3.5-turbo)
• MAX_TOKENS: Maximum tokens for responses (default: 500)

You can extend the bot by:

1. Adding new tools: Extend the _create_tools() method and _execute_function() method
2. Adding more flight data: Modify the _create_sample_flight_data() method
3. Connecting to real APIs: Replace the sample data with calls to airline APIs
4. Customizing responses: Modify the system prompt in _create_system_prompt()