Understanding a Simple ChatGPT – Like Clone Built with Streamlit and OpenAI And Deploy it On Cloud

This Python application creates a basic ChatGPT-style chatbot using Streamlit for the user interface and the OpenAI API for generating AI responses. Users can enter their own OpenAI API key, ask questions, and receive real-time AI-generated answers.

What This Application Does

• Creates a web-based chatbot interface using Streamlit.
• Allows users to securely enter their OpenAI API key.
• Stores conversation history during the session.
• Sends user messages to the OpenAI model.
• Streams AI responses in real time for a smooth chat experience.
• Maintains the conversation context so the AI can respond intelligently to follow-up questions.

Here I give the chatbot code, show how to deploy this on local machine, and then on cloud.

The full code is given below. The explanation of the code is provided below the code

# app.py
# To run:  python -m  streamlit run  app.py
# Open URL: http://localhost:8501

from openai import OpenAI
import streamlit as st

st.title("ChatGPT-like Clone")

# Sidebar API Key
api_key = st.sidebar.text_input(
    "Enter OpenAI API Key",
    type="password"
)

if not api_key:
    st.info("Please enter your OpenAI API Key in the sidebar.")
    st.stop()

client = OpenAI(api_key=api_key)

# Model
if "openai_model" not in st.session_state:
    st.session_state["openai_model"] = "gpt-4o-mini"

# Chat history
if "messages" not in st.session_state:
    st.session_state.messages = []

# Display chat history
for message in st.session_state.messages:
    with st.chat_message(message["role"]):
        st.markdown(message["content"])

# User input
if prompt := st.chat_input("What is up?"):

    st.session_state.messages.append(
        {"role": "user", "content": prompt}
    )

    with st.chat_message("user"):
        st.markdown(prompt)

    with st.chat_message("assistant"):

        stream = client.chat.completions.create(
            model=st.session_state["openai_model"],
            messages=st.session_state.messages,
            stream=True,
        )

        response = st.write_stream(stream)

    st.session_state.messages.append(
        {"role": "assistant", "content": response}
    )

Code Breakdown

1. Import Required Libraries

from openai import OpenAI
import streamlit as st

These libraries provide access to the OpenAI API and Streamlit web components.

2. Create the Application Title

st.title("ChatGPT-like Clone")

Displays the title at the top of the web page.

3. Accept OpenAI API Key

api_key = st.sidebar.text_input(
    "Enter OpenAI API Key",
    type="password"
)

Creates a password-protected input field in the sidebar where users enter their OpenAI API key.

4. Validate API Key

if not api_key:
    st.info("Please enter your OpenAI API Key in the sidebar.")
    st.stop()

Stops the application until a valid API key is provided.

5. Initialize OpenAI Client

client = OpenAI(api_key=api_key)

Creates a connection to OpenAI using the user-provided API key.

6. Set the AI Model

st.session_state["openai_model"] = "gpt-4o-mini"

Specifies the OpenAI model that will generate responses.

7. Store Chat History

st.session_state.messages = []

Keeps track of all user and assistant messages during the session.

8. Display Previous Messages

for message in st.session_state.messages:

Shows the conversation history whenever the page refreshes.

9. Accept User Input

prompt = st.chat_input("What is up?")

Provides a chat input box where users can ask questions.

10. Generate AI Responses

stream = client.chat.completions.create(
    model=st.session_state["openai_model"],
    messages=st.session_state.messages,
    stream=True,
)

Sends the conversation history to OpenAI and requests a streamed response.

1. Display Streaming Output

response = st.write_stream(stream)

Shows the AI response as it is being generated, creating a real-time chat experience.

12. Save the AI Response

st.session_state.messages.append(
    {"role": "assistant", "content": response}
)

Stores the assistant’s response so it becomes part of future conversations.

How to run this code

Step 1: Install Python

Download and install Python from: Python Official Website

Step 2: Create a Project Folder

Create a new folder and save your code as app.py.

Example:

chatgpt-clone/
│
└── app.py

Step 3: Create a Virtual Environment (Recommended)

Open a terminal in the project folder and run:

python -m venv venv

Activate it:

Windows

venv\Scripts\activate

Mac/Linux

source venv/bin/activate

Step 4: Install Required Packages

Install Streamlit and OpenAI:

pip install streamlit openai

Verify installation:

pip list

You should see both streamlit and openai in the package list.

Step 5: Run the Application

Execute:

streamlit run app.py

or

python -m streamlit run app.py

Step 6: Open the Application

After the command runs successfully, Streamlit will display a URL similar to:

Local URL: http://localhost:8501

Open that URL in your web browser.

---

Step 7: Enter Your OpenAI API Key

1. Obtain an API key from: OpenAI Platform
2. Paste the key into the sidebar input field.
3. Start chatting with the AI assistant.

Steps To deploy this application on cloud

Step 1: Create a GitHub Repository

1. Log in to GitHub
2. Click New Repository.
3. Give your repository a name (for example, chatgpt-clone).
4. Make it Public.
5. Click Create Repository.

Step 2: Upload Your Files

Your repository should contain at least:

chatgpt-clone/
│
├── app.py
└── requirements.txt

Create a requirements.txt file containing:

streamlit
openai

Upload both files to GitHub.

Step 3: Sign in to Streamlit Community Cloud

Go to:

Streamlit Community Cloud

Sign in using your GitHub account.

---

Step 4: Create a New App

1. Click Create App.
2. Select your GitHub repository.
3. Choose the branch (usually main).
4. Set the main file path:

app.py

5. Click Deploy.

Step 5: Wait for Deployment

Streamlit will:

• Clone your GitHub repository
• Install dependencies from requirements.txt
• Launch your application

This usually takes 1–2 minutes.

---

Step 6: Access Your App

After deployment, Streamlit will provide a public URL similar to:

https://your-app-name.streamlit.app

Anyone with this URL can access your application.