app.py

import base64
import gradio as gr
import requests

def encode_image(image_file):
    with open(image_file.name, "rb") as img_file:
        return base64.b64encode(img_file.read()).decode('utf-8')

def send_to_openai(api_key, image_file):
    base64_image = encode_image(image_file)

    headers = {
        "Content-Type": "application/json",
        "Authorization": f"Bearer {api_key}"
    }

    payload = {
        "model": "gpt-4-vision-preview",
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "type": "text",
                        "text": "Answer in three words only, does the image uploaded have a healthy rice leaf - Yes or No , does the image uploaded have a rice leaf with Major (not small) circular spots - Yes or No , does the image uploaded have a rice leaf have a major yellowish discoloration in some areas (ignore spots) - Yes or No  , DO NOT RESPOND IN MORE THAN THREE WORDS  "
                    },
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": f"data:image/jpeg;base64,{base64_image}"
                        }
                    }
                ]
            }
        ],
        "max_tokens": 300
    }

    response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload)
    # Extract words from the assistant's response
    assistant_response = response.json()['choices'][0]['message']['content']
    words = assistant_response.split('\n')
    
    return ' '.join(words)

iface = gr.Interface(send_to_openai, ["text", "file"], "text")
iface.launch()