برنامه خواننده فاکتور با Genai در 10 دقیقه – آموزش

you are an expert in python programming with high skills of huggingface smolagents library and other required libraries. Generate a complete project with any number of required python program files and functions to implement a web application (using flask and basic html css and js) that requires no user auth, with a page having a mandatory image file upload option part of a form submission. after submitting, it should be parsed by a vision lang model and then the parsed output should be written as a doc file and then emailed to a default email id

chmod +x flask_vlm_app.sh
./flask_vlm_app.sh

from flask import Flask, render_template, request, send_file
import os
from werkzeug.utils import secure_filename
from image_processor import process_image
from document_generator import create_doc
from email_sender import send_email

app = Flask(__name__)
app.config['UPLOAD_FOLDER'] = 'uploads'
app.config['OUTPUT_FOLDER'] = 'outputs'
DEFAULT_EMAIL = "amrs.tech@gmail.com"

os.makedirs(app.config['UPLOAD_FOLDER'], exist_ok=True)
os.makedirs(app.config['OUTPUT_FOLDER'], exist_ok=True)

@app.route('/')
def index():
    return render_template('index.html')

@app.route('/upload', methods=['POST'])
def upload():
    if 'image' not in request.files:
        return "No file part", 400
    file = request.files['image']
    if file.filename == '':
        return "No selected file", 400

    filename = secure_filename(file.filename)
    filepath = os.path.join(app.config['UPLOAD_FOLDER'], filename)
    file.save(filepath)

    extracted_text = process_image(filepath)

    doc_path = os.path.join(app.config['OUTPUT_FOLDER'], f"{os.path.splitext(filename)[0]}.docx")
    create_doc(extracted_text, doc_path)

    send_email(DEFAULT_EMAIL, doc_path)

    return send_file(doc_path, as_attachment=True)

if __name__ == '__main__':
    app.run(debug=True)

from transformers import AutoProcessor, AutoModelForImageTextToText
from PIL import Image
import torch

def process_image(image_path):
    processor = AutoProcessor.from_pretrained("HuggingFaceTB/SmolVLM-500M-Instruct")
    model = AutoModelForImageTextToText.from_pretrained("HuggingFaceTB/SmolVLM-500M-Instruct")

    conversation = [
        {
            "role": "user",
            "content":[
                {"type": "image", "url": image_path},
                {"type": "text", "text": "Describe this image in detail."}
            ]
        }
    ]

    inputs = processor.apply_chat_template(
        conversation,
        add_generation_prompt=True,
        tokenize=True,
        return_dict=True,
        return_tensors="pt",
    ).to(model.device)

    output_ids = model.generate(**inputs, max_new_tokens=400)
    generated_texts = processor.batch_decode(output_ids, skip_special_tokens=True)
    print("OUTPUT==>",generated_texts)
    return generated_texts

import smtplib
import os
from email.message import EmailMessage

def send_email(recipient, file_path):
    EMAIL_ADDRESS = os.getenv("EMAIL_ADDRESS")
    EMAIL_PASSWORD = os.getenv("EMAIL_PASSWORD")
    # print('emailauth==>',EMAIL_ADDRESS, EMAIL_PASSWORD)

    msg = EmailMessage()
    msg['Subject'] = 'Extracted Text Document'
    msg['From'] = EMAIL_ADDRESS
    msg['To'] = recipient
    msg.set_content("Please find the extracted text document attached.")

    with open(file_path, 'rb') as f:
        msg.add_attachment(
            f.read(),
            maintype='application',
            subtype='octet-stream',
            filename=os.path.basename(file_path),
            disposition='inline'
        )

    with smtplib.SMTP('smtp.gmail.com', 587) as server:
        server.starttls()
        server.login(EMAIL_ADDRESS, EMAIL_PASSWORD)
        server.send_message(msg)

flask_vlm_app/        # Project root
│── uploads/          # Folder for uploaded images (created dynamically)
│── outputs/          # Folder for generated documents (created dynamically)
│── templates/        # HTML template directory
│   └── index.html    # Webpage for image upload
│── app.py            # Main Flask application
│── image_processor.py # Processes image using a vision-language model
│── document_generator.py # Creates .docx file from extracted text
│── email_sender.py   # Sends extracted text document via email
│── requirements.txt  # List of required dependencies (if needed)

Flask==3.0.3
torch==2.6.0
transformers
pillow==11.1.0
python-docx==1.1.2