Guided Project: AI Chatbot

Build a full-featured conversational AI chatbot with streaming responses, conversation history, and a configurable persona. This is the foundational project every AI developer should have in their portfolio.

---

What You'll Build

A Python-based AI chatbot that:

Maintains multi-turn conversation history
Streams responses for real-time feel
Has a configurable system persona
Handles errors gracefully
Manages context window limits

---

Step 1: Project Setup

mkdir ai-chatbot && cd ai-chatbot
python -m venv venv
source venv/bin/activate  # Windows: venv\Scripts\activate
pip install openai python-dotenv

Create .env:

OPENAI_API_KEY=your-key-here

---

Step 2: Core Chat Logic

Create chatbot.py:

from dotenv import load_dotenv
from openai import OpenAI

load_dotenv()
client = OpenAI()

SYSTEM_PROMPT = """You are a helpful AI assistant named Alex.
You're friendly, concise, and knowledgeable.
When you don't know something, say so honestly.
Keep responses under 200 words unless more detail is requested."""

MAX_MESSAGES = 20  # limit history to prevent context overflow

class Chatbot:
    def __init__(self, system_prompt: str = SYSTEM_PROMPT):
        self.messages = [{"role": "system", "content": system_prompt}]

    def _trim_history(self):
        if len(self.messages) > MAX_MESSAGES:
            # Keep system prompt + last MAX_MESSAGES-1 messages
            self.messages = [self.messages[0]] + self.messages[-(MAX_MESSAGES - 1):]

    def chat(self, user_input: str) -> str:
        self.messages.append({"role": "user", "content": user_input})
        self._trim_history()

        full_response = ""

        # Stream the response token-by-token
        stream = client.chat.completions.create(
            model="gpt-4o-mini",
            messages=self.messages,
            max_tokens=400,
            stream=True,
        )
        for chunk in stream:
            text = chunk.choices[0].delta.content or ""
            print(text, end="", flush=True)
            full_response += text

        print()  # newline after streaming

        self.messages.append({"role": "assistant", "content": full_response})
        return full_response

---

Step 3: CLI Interface

# Add to chatbot.py:

def main():
    print("AI Chatbot | Type 'quit' to exit, 'reset' to clear history")
    print("-" * 50)

    bot = Chatbot()

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (EOFError, KeyboardInterrupt):
            print("\nGoodbye!")
            break

        if not user_input:
            continue
        if user_input.lower() == "quit":
            print("Goodbye!")
            break
        if user_input.lower() == "reset":
            bot = Chatbot()
            print("[Conversation reset]")
            continue

        print("\nAlex: ", end="")
        bot.chat(user_input)

if __name__ == "__main__":
    main()

---

Step 4: Run It

python chatbot.py

---

Step 5: Enhancements (Choose 2)

Once the base chatbot works, add at least 2 of the following:

1. Conversation export — save command writes history to a JSON file
2. Multiple personas — command-line arg to choose persona (tutor, assistant, creative writer)
3. Token tracking — display token count and estimated cost after each message
4. Markdown rendering — use the rich library to render formatted responses
5. Input validation — warn when input is very long and offer to truncate

---

Completion Criteria

[ ] Multi-turn conversation works correctly
[ ] Streaming renders token-by-token
[ ] History is trimmed at the configured limit
[ ] At least 2 enhancements implemented
[ ] README.md with setup instructions

from dotenv import load_dotenv from openai import OpenAI load_dotenv() client = OpenAI() SYSTEM_PROMPT = """You are a helpful AI assistant named Alex. You're friendly, concise, and knowledgeable. When you don't know something, say so honestly. Keep responses under 200 words unless more detail is requested.""" MAX_MESSAGES = 20 # limit history to prevent context overflow class Chatbot: def __init__(self, system_prompt: str = SYSTEM_PROMPT): self.messages = [{"role": "system", "content": system_prompt}] def _trim_history(self): if len(self.messages) > MAX_MESSAGES: # Keep system prompt + last MAX_MESSAGES-1 messages self.messages = [self.messages[0]] + self.messages[-(MAX_MESSAGES - 1):] def chat(self, user_input: str) -> str: self.messages.append({"role": "user", "content": user_input}) self._trim_history() full_response = "" # Stream the response token-by-token stream = client.chat.completions.create( model="gpt-4o-mini", messages=self.messages, max_tokens=400, stream=True, ) for chunk in stream: text = chunk.choices[0].delta.content or "" print(text, end="", flush=True) full_response += text print() # newline after streaming self.messages.append({"role": "assistant", "content": full_response}) return full_response

# Add to chatbot.py: def main(): print("AI Chatbot | Type 'quit' to exit, 'reset' to clear history") print("-" * 50) bot = Chatbot() while True: try: user_input = input("\nYou: ").strip() except (EOFError, KeyboardInterrupt): print("\nGoodbye!") break if not user_input: continue if user_input.lower() == "quit": print("Goodbye!") break if user_input.lower() == "reset": bot = Chatbot() print("[Conversation reset]") continue print("\nAlex: ", end="") bot.chat(user_input) if __name__ == "__main__": main()

Step 5: Enhancements (Choose 2)

Once the base chatbot works, add at least 2 of the following:

---