app.py.old2

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

# === OpenAI API Setup ===
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)

# === OCI Object Storage Setup ===
oci_config = {
    "user": os.environ.get("OCI_USER"),
    "tenancy": os.environ.get("OCI_TENANCY"),
    "fingerprint": os.environ.get("OCI_FINGERPRINT"),
    "region": os.environ.get("OCI_REGION"),
    "key_content": os.environ.get("OCI_PRIVATE_KEY")
}

# Optional: access OCI Object Storage (if needed)
try:
    object_storage = oci.object_storage.ObjectStorageClient(oci_config)
except Exception as e:
    print("Failed to initialize OCI Object Storage client:", e)

# === 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."
)

# === Encode uploaded bytes ===
def encode_image_to_base64(file_bytes):
    return base64.b64encode(file_bytes).decode("utf-8")

# === Transcription logic ===
def transcribe_image(file_bytes):
    if not file_bytes:
        return "No image uploaded."

    encoded = encode_image_to_base64(file_bytes)
    image_url = f"data:image/jpeg;base64,{encoded}"

    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")
    return f"🗓️ Transcribed on: {timestamp}\n\n{response.choices[0].message.content}"

# === Gradio Interface ===
with gr.Blocks() as app:
    gr.Markdown("## Handwritten Note Transcriber\nUpload a handwritten note image for professional transcription.")
    input_file = gr.File(label="Upload image", type="binary", file_types=[".jpg", ".jpeg", ".png"])
    output_text = gr.Textbox(label="Transcription Output", lines=30)
    input_file.change(fn=transcribe_image, inputs=input_file, outputs=output_text)

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