Upload 15 files

app/.ipynb_checkpoints/__init__-checkpoint.py

@@ -0,0 +1,15 @@
+from flask import Flask
+from app.config import Config
+import os
+
+def create_app():
+    app = Flask(__name__)
+    app.config.from_object(Config)
+    
+    # إنشاء مجلد للملفات المرفوعة
+    os.makedirs(os.path.join(app.instance_path, 'uploads'), exist_ok=True)
+    
+    from app.routes import main
+    app.register_blueprint(main)
+    
+    return app

app/.ipynb_checkpoints/config-checkpoint.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/.ipynb_checkpoints/routes-checkpoint.py

@@ -0,0 +1,41 @@
+from flask import Blueprint, jsonify, request, current_app
+import os
+from werkzeug.utils import secure_filename
+from app.utils import OCRModel
+import torch
+
+main = Blueprint('main', __name__)
+ocr_model = OCRModel()
+
+ALLOWED_EXTENSIONS = {'png', 'jpg', 'jpeg'}
+
+def allowed_file(filename):
+    return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
+
+@main.route('/')
+def index():
+    return jsonify({"message": "Welcome to OCR API!"})
+
+@main.route('/api/ocr', methods=['POST'])
+def process_image():
+    if 'file' not in request.files:
+        return jsonify({"error": "No file part"}), 400
+    
+    file = request.files['file']
+    if file.filename == '':
+        return jsonify({"error": "No selected file"}), 400
+    
+    if file and allowed_file(file.filename):
+        filename = secure_filename(file.filename)
+        filepath = os.path.join(current_app.config['UPLOAD_FOLDER'], filename)
+        file.save(filepath)
+        
+        try:
+            result = ocr_model.process_image(filepath)
+            # حذف الملف بعد المعالجة
+            os.remove(filepath)
+            return jsonify({"result": result})
+        except Exception as e:
+            return jsonify({"error": str(e)}), 500
+    
+    return jsonify({"error": "Invalid file type"}), 400

app/.ipynb_checkpoints/utils-checkpoint.py

@@ -0,0 +1,32 @@
+from transformers import AutoModel, AutoTokenizer
+import os
+import torch
+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):
+        self.tokenizer = AutoTokenizer.from_pretrained('ucaslcl/GOT-OCR2_0', trust_remote_code=True)
+        self.model = AutoModel.from_pretrained(
+            'ucaslcl/GOT-OCR2_0',
+            trust_remote_code=True,
+            low_cpu_mem_usage=True,
+            device_map='cuda' if torch.cuda.is_available() else 'cpu',
+            use_safetensors=True,
+            pad_token_id=self.tokenizer.eos_token_id
+        )
+        self.model = self.model.eval()
+        if torch.cuda.is_available():
+            self.model = self.model.cuda()
+    
+    def process_image(self, image_path):
+        try:
+            result = self.model.chat(self.tokenizer, image_path, ocr_type='format')
+            return result
+        except Exception as e:
+            return str(e)

app/__init__.py

@@ -0,0 +1,15 @@
+from flask import Flask
+from app.config import Config
+import os
+
+def create_app():
+    app = Flask(__name__)
+    app.config.from_object(Config)
+    
+    # إنشاء مجلد للملفات المرفوعة
+    os.makedirs(os.path.join(app.instance_path, 'uploads'), exist_ok=True)
+    
+    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 +1,41 @@
+from flask import Blueprint, jsonify, request, current_app
+import os
+from werkzeug.utils import secure_filename
+from app.utils import OCRModel
+import torch
+
+main = Blueprint('main', __name__)
+ocr_model = OCRModel()
+
+ALLOWED_EXTENSIONS = {'png', 'jpg', 'jpeg'}
+
+def allowed_file(filename):
+    return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
+
+@main.route('/')
+def index():
+    return jsonify({"message": "Welcome to OCR API!"})
+
+@main.route('/api/ocr', methods=['POST'])
+def process_image():
+    if 'file' not in request.files:
+        return jsonify({"error": "No file part"}), 400
+    
+    file = request.files['file']
+    if file.filename == '':
+        return jsonify({"error": "No selected file"}), 400
+    
+    if file and allowed_file(file.filename):
+        filename = secure_filename(file.filename)
+        filepath = os.path.join(current_app.config['UPLOAD_FOLDER'], filename)
+        file.save(filepath)
+        
+        try:
+            result = ocr_model.process_image(filepath)
+            # حذف الملف بعد المعالجة
+            os.remove(filepath)
+            return jsonify({"result": result})
+        except Exception as e:
+            return jsonify({"error": str(e)}), 500
+    
+    return jsonify({"error": "Invalid file type"}), 400

app/utils.py

@@ -0,0 +1,41 @@
+from transformers import AutoModel, AutoTokenizer
+import os
+import torch
+
+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', 'ucaslcl/GOT-OCR2_0')
+        
+        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='auto',  # 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_path):
+        try:
+            with torch.no_grad():  # تحسين الأداء وتقليل استهلاك الذاكرة
+                result = self.model.chat(self.tokenizer, image_path, ocr_type='format')
+            return result
+        except Exception as e:
+            return f"Error processing image: {str(e)}"

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

runtime.txt

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