Skip to content

Building a Chatbot with Python and the OpenAI API

DodaTech 1 min read

In this tutorial, you'll learn about Building a Chatbot with Python and the OpenAI API. We cover key concepts, practical examples, and best practices to help you understand and apply this topic effectively.

What You'll Learn

Build a working AI chatbot in Python using the OpenAI API, with conversation memory and a clean CLI interface.

Why It Matters

Chatbots are the most common LLM application. Every developer should know how to integrate LLM APIs into their projects.

Real-World Use

Customer support bots, coding assistants, FAQ bots, and internal Q&A tools.

Prerequisites

pip install openai python-dotenv

Get an API key from platform.openai.com/api-keys.

Step 1: Basic Chat Completion

from openai import OpenAI

client = OpenAI()  # Reads OPENAI_API_KEY from env

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {"role": "user", "content": "What is machine learning?"}
    ]
)

print(response.choices[0].message.content)

Expected output:

Machine learning is a branch of artificial intelligence that enables systems
to learn and improve from experience without being explicitly programmed.

Step 2: Chat with History

messages = [
    {"role": "system", "content": "You are a helpful coding assistant."},
    {"role": "user", "content": "Write a Python function to reverse a string."}
]

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=messages
)

reply = response.choices[0].message.content
print(reply)

# Add to history for follow-up
messages.append({"role": "assistant", "content": reply})
messages.append({"role": "user", "content": "Now make it handle None inputs"})

Step 3: CLI Chatbot

from OpenAI import OpenAI

client = OpenAI()
messages = [{"role": "system", "content": "You are a helpful assistant."}]

print("Chatbot ready! Type 'quit' to exit.")

while True:
    user_input = input("\nYou: ")
    if user_input.lower() == "quit":
        break

    messages.append({"role": "user", "content": user_input})
    response = client.chat.completions.create(
        model="gpt-4o-mini", messages=messages
    )
    reply = response.choices[0].message.content
    print(f"Bot: {reply}")
    messages.append({"role": "assistant", "content": reply})

Managing Token Usage

# Count tokens roughly (4 chars ≈ 1 token)
total_chars = sum(len(m["content"]) for m in messages)
estimated_tokens = total_chars // 4

# Trim history when too long
if len(messages) > 20:
    messages = [messages[0]] + messages[-10:]

Practice

Build a chatbot that:

  1. Remembers user preferences across the conversation
  2. Can search Wikipedia when asked for facts
  3. Formats code responses with language labels
← Previous Prompt Engineering Guide: How to Talk to LLMs Next → Introduction to Neural Networks — How AI Learns

Built by the developers of DodaTech

Doda Browser, DodaZIP & Durga Antivirus Pro

Home Browse Ai Ml