app.py

import base64
import os
from datetime import datetime
from openai import OpenAI
import gradio as gr

# === Initialize OpenAI Client using Environment Variable ===
openai_api_key = os.environ.get("OPENAI_API_KEY")
if not openai_api_key:
    raise ValueError("OPENAI_API_KEY environment variable is not set.")

client = OpenAI(api_key=openai_api_key)

# === Prompts ===
system_prompt = (
    "You are a detail-oriented assistant that specializes in transcribing and polishing "
    "handwritten notes from images. Your goal is to turn rough, casual, or handwritten "
    "content into clean, structured, and professional-looking text that sounds like it "
    "was written by a human—not an AI. You do not include icons, emojis, or suggest next "
    "steps unless explicitly instructed."
)

user_prompt_template = (
    "You will receive an image of handwritten notes. Transcribe the content accurately, "
    "correcting any spelling or grammar issues. Then, organize it clearly with headings, "
    "bullet points, and proper formatting. Maintain the original intent and voice of the "
    "author, but enhance readability and flow. Do not add embellishments or AI-style phrasing."
)

# === Image processing ===
def encode_image_to_base64(image_file):
    image_bytes = image_file.read()
    return base64.b64encode(image_bytes).decode("utf-8")

# === Transcription function ===
def transcribe_images(files):
    if not files:
        return "No images uploaded."

    results = []
    for file in files:
        encoded_image = encode_image_to_base64(file)
        image_url = f"data:image/jpeg;base64,{encoded_image}"

        response = client.chat.completions.create(
            model="gpt-4-turbo",
            messages=[
                {"role": "system", "content": system_prompt},
                {"role": "user", "content": [
                    {"type": "text", "text": user_prompt_template},
                    {"type": "image_url", "image_url": {"url": image_url}}
                ]}
            ],
            max_tokens=1500
        )

        timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
        result_text = f"🗓️ Transcribed on: {timestamp}\n\n{response.choices[0].message.content}"
        results.append(result_text)

    return "\n\n---\n\n".join(results)

# === Gradio Interface using UploadButton ===
with gr.Blocks() as app:
    with gr.Row():
        uploader = gr.UploadButton(
            label="Upload handwritten note images",
            file_types=[".jpg", ".jpeg", ".png"],
            file_types_multiple=True
        )
    output_box = gr.Textbox(label="Transcribed Output", lines=30)

    uploader.change(fn=transcribe_images, inputs=uploader, outputs=output_box)

# === Launch ===
if __name__ == "__main__":
    app.launch()