app.py

import gradio as gr
import openai
import base64
from PIL import Image
import io

# Function to send the request to OpenAI API with an image or text input
def generate_response(input_text, image, openai_api_key, reasoning_effort="medium"):
    if not openai_api_key:
        return "Error: No API key provided."

    openai.api_key = openai_api_key

    # Process the input depending on whether it's text or an image
    if image:
        # Convert the image to base64 string
        image_info = get_base64_string_from_image(image)
        input_text = f"data:image/png;base64,{image_info}"

    # Prepare the messages for OpenAI API
    messages = [
        {"role": "user", "content": [{"type": "image_url", "image_url": {"url": input_text}}]}
    ]

    try:
        # Call OpenAI API with the "o1" model
        response = openai.ChatCompletion.create(
            model="o1",  # Using model "o1"
            messages=messages,
            reasoning_effort=reasoning_effort,  # Set reasoning_effort for the response
            max_completion_tokens=2000  # Limit response tokens to 2000
        )

        return response["choices"][0]["message"]["content"]
    except Exception as e:
        return f"Error calling OpenAI API: {str(e)}"

# Function to convert an uploaded image to a base64 string
def get_base64_string_from_image(pil_image):
    # Convert PIL Image to bytes
    buffered = io.BytesIO()
    pil_image.save(buffered, format="PNG")
    img_bytes = buffered.getvalue()
    base64_str = base64.b64encode(img_bytes).decode("utf-8")
    return base64_str

# The function that will be used by Gradio interface
def chatbot(input_text, image, openai_api_key, reasoning_effort, history=[]):
    response = generate_response(input_text, image, openai_api_key, reasoning_effort)
    
    # Append the response to the history
    history.append((f"User: {input_text}", f"Assistant: {response}"))
    
    return "", history

# Function to clear the chat history
def clear_history():
    return "", []

# Gradio interface setup
def create_interface():
    with gr.Blocks() as demo:
        gr.Markdown("# Multimodal Chatbot (Text + Image)")

        # Add a description after the title
        gr.Markdown("""
        ### Description:
        This is a multimodal chatbot that can handle both text and image inputs. 
        - You can ask questions or provide text, and the assistant will respond.
        - You can also upload an image, and the assistant will process it and answer questions about the image.
        - Enter your OpenAI API key to start interacting with the model.
        - You can use the 'Clear History' button to remove the conversation history.
        """)

        with gr.Row():
            openai_api_key = gr.Textbox(label="Enter OpenAI API Key", type="password", placeholder="sk-...", interactive=True)
        
        with gr.Row():
            image_input = gr.Image(label="Upload an Image", type="pil")  # Image upload input
            input_text = gr.Textbox(label="Enter Text Question", placeholder="Ask a question or provide text", lines=2)
        
        with gr.Row():
            reasoning_effort = gr.Dropdown(
                label="Reasoning Effort",
                choices=["low", "medium", "high"],
                value="medium"
            )
            submit_btn = gr.Button("Send")
            clear_btn = gr.Button("Clear History")

        chat_history = gr.Chatbot()

        # Button interactions
        submit_btn.click(fn=chatbot, inputs=[input_text, image_input, openai_api_key, reasoning_effort, chat_history], outputs=[input_text, chat_history])
        clear_btn.click(fn=clear_history, inputs=[], outputs=[chat_history, chat_history])

    return demo

# Run the interface
if __name__ == "__main__":
    demo = create_interface()
    demo.launch()