Practice: LLM Prompt Architecture

# Practice: Simulate an LLM chat application
# This illustrates the structure of LLM API calls

import random
random.seed(42)

# Simplified LLM responses (real version calls OpenAI/Anthropic API)
def simulate_llm_response(messages, temperature=0.7):
    """
    Simulate an LLM response.
    Real code: use openai.chat.completions.create(model="gpt-4o", messages=messages)
    """
    # Find the last user message
    user_message = ""
    for msg in reversed(messages):
        if msg["role"] == "user":
            user_message = msg["content"].lower()
            break
    
    # Simplified pattern matching (real LLM would generate actual responses)
    responses = {
        "what is ai": "Artificial Intelligence is technology that enables computers to perform tasks that normally require human intelligence, like recognizing images, understanding language, and making decisions.",
        "what is machine learning": "Machine Learning is a type of AI where computers learn patterns from data instead of following explicitly programmed rules.",
        "what is an llm": "A Large Language Model (LLM) is a type of AI trained on vast amounts of text. It generates responses by predicting the most likely next token given the context.",
        "hello": "Hello! I am your AI learning assistant. Ask me anything about Artificial Intelligence!",
        "bye": "Goodbye! Keep learning and stay curious.",
    }
    
    for key, response in responses.items():
        if key in user_message:
            return response
    
    return "That is a great question about AI! Could you be more specific? I can answer questions about what AI is, machine learning, LLMs, and more."

# Build the chatbot
class SimpleChat:
    def __init__(self, system_prompt):
        self.messages = [{"role": "system", "content": system_prompt}]
    
    def chat(self, user_input):
        self.messages.append({"role": "user", "content": user_input})
        response = simulate_llm_response(self.messages)
        self.messages.append({"role": "assistant", "content": response})
        return response
    
    def show_history(self):
        print("Conversation History:")
        for msg in self.messages:
            if msg["role"] != "system":
                print(f"  {msg['role'].upper()}: {msg['content']}")

# Run the chatbot
chat = SimpleChat(
    system_prompt="You are a helpful AI tutor. Explain concepts clearly and simply."
)

test_questions = [
    "Hello",
    "What is AI?",
    "What is machine learning?",
    "What is an LLM?",
    "Bye",
]

print("Simulated LLM Chat Application:")
print()
for question in test_questions:
    response = chat.chat(question)
    print(f"User: {question}")
    print(f"AI: {response}")
    print()