app.py

# Import the necessary libraries
import gradio as gr
import openai
import base64
import io
import requests


# Function to encode the image to base64
def encode_image_to_base64(image):
    buffered = io.BytesIO()
    image.save(buffered, format="JPEG")
    img_str = base64.b64encode(buffered.getvalue()).decode("utf-8")
    return img_str


# Function to send the image to the OpenAI API and get a response
def ask_openai_with_image(instruction, json_prompt, low_quality_mode, image):
    # Set the OpenAI API key
    openai.api_key = os.getenv("API_KEY")

    # Encode the uploaded image to base64
    base64_image = encode_image_to_base64(image)

    instruction = instruction.strip()

    if json_prompt.strip() != "":
        instruction = f"{instruction}\n\nReturn in JSON format and include the following attributes:\n\n{json_prompt.strip()}"

    # Create the payload with the base64 encoded image
    payload = {
        "model": "gpt-4-vision-preview",
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "type": "text",
                        "text": instruction,
                    },
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": f"data:image/jpeg;base64,{base64_image}",
                            "detail": "low" if low_quality_mode else "high",
                        },
                    },
                ],
            }
        ],
        "max_tokens": 4095,
    }

    # Send the request to the OpenAI API
    response = requests.post(
        "https://api.openai.com/v1/chat/completions",
        headers={"Authorization": f"Bearer {openai.api_key}"},
        json=payload,
    )

    # Check if the request was successful
    if response.status_code == 200:
        response_json = response.json()
        print("Response JSON:", response_json)  # Print the raw response JSON
        try:
            # Attempt to extract the content text
            return response_json["choices"][0]["message"]["content"]
        except Exception as e:
            # If there is an error in the JSON structure, print it
            print("Error in JSON structure:", e)
            print("Full JSON response:", response_json)
            return "Error processing the image response."
    else:
        # If an error occurred, return the error message
        return f"Error: {response.text}"


json_schema = gr.Textbox(
    label="JSON Attributes",
    info="Define a list of attributes to force the model to respond in valid json format. Leave blank to disable json formatting.",
    lines=3,
    placeholder="""Example: 
- name: Name of the object
- color: Color of the object
""",
)

instructions = gr.Textbox(
    label="Instructions",
    info="Instructions for the vision model to follow. Leave blank to use default.",
    lines=2,
    placeholder="""Default:
I've uploaded an image and I'd like to know what it depicts and any interesting details you can provide.""",
)

low_quality_mode = gr.Checkbox(
    label="Low Quality Mode",
    info="See here: https://platform.openai.com/docs/guides/vision/low-or-high-fidelity-image-understanding.",
)

# Create a Gradio interface
vision_playground = gr.Interface(
    fn=ask_openai_with_image,
    inputs=[
        instructions,
        json_schema,
        low_quality_mode,
        gr.Image(type="pil", label="Image"),
    ],
    outputs=[gr.Markdown()],
    title="GPT-4-Vision Playground",
    description="Upload an image and get a description from GPT-4 with Vision.",
)

# Launch the app
vision_playground.launch()