Upload 10 files

Dockerfile

@@ -0,0 +1,37 @@
+FROM python:3.10-slim
+
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PYTHONUNBUFFERED=1
+ENV DEBIAN_FRONTEND=noninteractive
+ENV MODEL_PATH=RufusRubin777/GOT-OCR2_0_CPU
+
+WORKDIR /app
+
+# تثبيت المكتبات الأساسية
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    libpq-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+# نسخ وتثبيت المتطلبات
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# إنشاء وتكوين مجلد الكاش
+RUN mkdir -p /root/.cache/huggingface
+VOLUME /root/.cache/huggingface
+
+# تحميل النموذج مسبقاً
+RUN python -c "from transformers_modules.RufusRubin777.GOT_OCR2_0_CPU.modeling_GOT import GOTModel, GOTConfig; \
+    from transformers import AutoTokenizer; \
+    model_path='RufusRubin777/GOT-OCR2_0_CPU'; \
+    config = GOTConfig.from_pretrained(model_path); \
+    model = GOTModel.from_pretrained(model_path, config=config); \
+    tokenizer = AutoTokenizer.from_pretrained(model_path)"
+
+# نسخ كود التطبيق
+COPY . .
+
+EXPOSE 7863
+
+CMD ["python", "app.py"]

app.py

@@ -0,0 +1,6 @@
+from app import create_app
+
+app = create_app()
+
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=7863)

app/__init__.py

@@ -0,0 +1,9 @@
+from flask import Flask
+
+def create_app():
+    app = Flask(__name__)
+    
+    from app.routes import main
+    app.register_blueprint(main)
+    
+    return app

app/config.py

@@ -0,0 +1,6 @@
+import os
+
+class Config:
+    SECRET_KEY = os.environ.get('SECRET_KEY') or 'your-secret-key'
+    UPLOAD_FOLDER = 'instance/uploads'
+    MAX_CONTENT_LENGTH = 16 * 1024 * 1024  # 16MB max file size

app/routes.py

@@ -0,0 +1,117 @@
+from flask import Blueprint, jsonify, request
+import io
+from app.utils import OCRModel
+
+main = Blueprint('main', __name__)
+ocr_model = OCRModel()
+
+# تحديد امتدادات الملفات المسموح بها
+ALLOWED_EXTENSIONS = {'png', 'jpg', 'jpeg'}
+
+# قائمة الحساسيات المعروفة (يمكن تخصيصها حسب الحاجة)
+KNOWN_ALLERGENS = {
+    'gluten': ['wheat', 'barley', 'gluten'],
+    'dairy': ['milk', 'yogurt', 'cheese', 'lactose'],
+    'nuts': ['nuts', 'peanuts', 'almonds', 'walnuts'],
+    'eggs': ['eggs'],
+    'soy': ['soy'],
+    'fish': ['fish'],
+    'shellfish': ['oyster', 'shrimp', 'shrimp'],
+}
+
+def allowed_file(filename):
+    """التحقق من صحة امتداد الملف"""
+    return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
+
+def find_allergens(text, user_allergens):
+    """البحث عن الحساسيات في النص"""
+    text = text.lower()
+    found_allergens = set()
+    allergen_details = {}
+
+    for allergen in user_allergens:
+        allergen = allergen.strip().lower()
+        # البحث في القائمة الرئيسية للحساسيات
+        if allergen in KNOWN_ALLERGENS:
+            for variant in KNOWN_ALLERGENS[allergen]:
+                if variant.lower() in text:
+                    found_allergens.add(allergen)
+                    allergen_details[allergen] = variant
+        # البحث المباشر عن النص المدخل
+        elif allergen in text:
+            found_allergens.add(allergen)
+            allergen_details[allergen] = allergen
+
+    return found_allergens, allergen_details
+
+@main.route('/')
+def index():
+    return jsonify({
+        "message": "Welcome to the Text Recognition and Sensitivity Checking Service",
+        "endpoints": {
+            "/api/ocr": "POST - Image analysis and sensitivity testing",
+        },
+        "supported_formats": list(ALLOWED_EXTENSIONS),
+        "known_allergens": list(KNOWN_ALLERGENS.keys())
+    })
+
+@main.route('/api/ocr', methods=['POST'])
+def process_image():
+    # التحقق من وجود الملف
+    if 'file' not in request.files:
+        return jsonify({"error": "No file uploaded"}), 400
+    
+    # التحقق من وجود قائمة الحساسيات
+    if 'allergens' not in request.form:
+        return jsonify({"error": "Sensitivities not specified"}), 400
+    
+    file = request.files['file']
+    if file.filename == '':
+        return jsonify({"error": "No file selected"}), 400
+    
+    # التحقق من نوع الملف
+    if not allowed_file(file.filename):
+        return jsonify({
+            "error": "File type not supported",
+            "supported_formats": list(ALLOWED_EXTENSIONS)
+        }), 400
+
+    # تحضير قائمة الحساسيات
+    user_allergens = request.form['allergens'].split(',')
+    
+    try:
+        # قراءة الصورة
+        file_bytes = file.read()
+        file_stream = io.BytesIO(file_bytes)
+        
+        # معالجة الصورة
+        extracted_text = ocr_model.process_image(file_stream)
+        
+        # البحث عن الحساسيات
+        found_allergens, allergen_details = find_allergens(extracted_text, user_allergens)
+        
+        # تحضير الرد
+        response = {
+            "success": True,
+            "extracted_text": extracted_text,
+            "analysis": {
+                "found_allergens": list(found_allergens),
+                "allergen_details": allergen_details,
+                "has_allergens": len(found_allergens) > 0,
+                "warning": "Warning: Allergens found!" if found_allergens else "No allergens found"
+            }
+        }
+        
+        return jsonify(response)
+        
+    except Exception as e:
+        return jsonify({
+            "error": "An error occurred while processing the image.",
+            "details": str(e)
+        }), 500
+
+@main.route('/api/allergens', methods=['GET'])
+def get_known_allergens():
+    return jsonify({
+        "allergens": KNOWN_ALLERGENS
+    })

app/utils.py

@@ -0,0 +1,44 @@
+import os
+from transformers import AutoModel, AutoTokenizer
+
+class OCRModel:
+    _instance = None
+
+    def __new__(cls):
+        if cls._instance is None:
+            cls._instance = super(OCRModel, cls).__new__(cls)
+            cls._instance.initialize()
+        return cls._instance
+
+    def initialize(self):
+        # تحميل النموذج مرة واحدة وتخزينه محلياً
+        model_path = os.getenv('MODEL_PATH', 'RufusRubin777/GOT-OCR2_0_CPU')
+        
+        self.tokenizer = AutoTokenizer.from_pretrained(
+            model_path, 
+            trust_remote_code=True,
+            local_files_only=False  # سيتم تحميل الملفات إذا لم تكن موجودة
+        )
+        
+        self.model = AutoModel.from_pretrained(
+            model_path,
+            trust_remote_code=True,
+            low_cpu_mem_usage=True,
+            device_map='cpu',  # سيختار أفضل جهاز متاح
+            use_safetensors=True,
+            pad_token_id=self.tokenizer.eos_token_id
+        )
+        
+        self.model = self.model.eval()
+
+        
+    def process_image(self, image_stream):
+        try:
+            # فتح الصورة من الذاكرة
+            image = Image.open(image_stream)
+            
+            with torch.no_grad():
+                result = self.model.chat(self.tokenizer, image, ocr_type='format')
+            return result
+        except Exception as e:
+            return f"Error processing image: {str(e)}"

docker-compose.yml

@@ -0,0 +1,21 @@
+version: '3.10'
+
+services:
+  app:
+    build: .
+    ports:
+      - "7863:7863"
+    volumes:
+      - huggingface_cache:/root/.cache/huggingface
+    environment:
+      - MODEL_PATH=RufusRubin777/GOT-OCR2_0_CPU
+    restart: unless-stopped
+    deploy:
+      resources:
+        limits:
+          memory: 4G
+        reservations:
+          memory: 2G
+
+volumes:
+  huggingface_cache:

render.yaml

@@ -0,0 +1,13 @@
+services:
+  - type: web
+    name: my-app
+    env: python
+    repo: https://github.com/ZienabMakhloof/ocr.git
+    branch: main
+    buildCommand: "pip install -r requirements.txt"
+    startCommand: "python app.py"
+    envVars:
+      - key: PYTHON_VERSION
+        value: 3.10.11
+    region: oregon
+    plan: standard

requirements.txt

@@ -0,0 +1,8 @@
+accelerate==1.1.1
+Flask==3.1.0
+torch==2.5.1
+torchvision==0.20.1
+transformers==4.37.2
+tiktoken==0.6.0
+verovio==4.3.1
+gunicorn

runtime.txt

@@ -0,0 +1 @@
+python-3.10.15