Upload 10 files

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,32 @@
+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
+
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    libpq-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+RUN mkdir -p /root/.cache/huggingface
+VOLUME /root/.cache/huggingface
+
+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)"
+
+COPY . .
+
+EXPOSE 7860
+
+CMD ["python", "app.py"]

README.md

@@ -1,10 +1,12 @@
----
-title: Ocrsensitive
-emoji: 📚
-colorFrom: gray
-colorTo: indigo
-sdk: docker
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: Ocrfood
+emoji: 🏢
+colorFrom: pink
+colorTo: blue
+sdk: gradio
+sdk_version: 5.6.0
+app_file: app.py
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

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=7860)

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 +1,140 @@
+# routes.py
+from flask import Blueprint, jsonify, request
+import io
+from app.utils import OCRModel
+import logging
+
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+main = Blueprint('main', __name__)
+ocr_model = OCRModel()
+
+ALLOWED_EXTENSIONS = {'png', 'jpg', 'jpeg'}
+
+KNOWN_ALLERGENS = {
+    'gluten': ['wheat', 'barley', 'rye', 'oats', 'gluten', 'flour', 'bread', 'pasta'],
+    'dairy': ['milk', 'yogurt', 'cheese', 'lactose', 'cream', 'butter', 'whey'],
+    'nuts': ['nuts', 'peanuts', 'almonds', 'walnuts', 'cashews', 'pistachios'],
+    'eggs': ['eggs', 'egg', 'albumin', 'mayonnaise'],
+    'soy': ['soy', 'soybeans', 'tofu', 'edamame'],
+    'fish': ['fish', 'salmon', 'tuna', 'cod', 'tilapia'],
+    'shellfish': ['shellfish', 'shrimp', 'crab', 'lobster', 'oyster', 'mussels'],
+    'sesame': ['sesame', 'tahini'],
+    'mustard': ['mustard'],
+    'celery': ['celery'],
+    'lupin': ['lupin'],
+    'sulfites': ['sulfites', 'sulphites']
+}
+
+def allowed_file(filename):
+    """Validate file extension"""
+    return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
+
+def find_allergens(text, user_allergens):
+    """Finding Sensitivities in the Text"""
+    text = text.lower()
+    found_allergens = set()
+    allergen_details = {}
+    allergen_locations = {}
+
+    for allergen in user_allergens:
+        allergen = allergen.strip().lower()
+        if allergen in KNOWN_ALLERGENS:
+            for variant in KNOWN_ALLERGENS[allergen]:
+                if variant.lower() in text:
+                    found_allergens.add(allergen)
+                    allergen_details[allergen] = variant
+                    # Store the location of the word in the text
+                    allergen_locations[allergen] = text.index(variant.lower())
+        elif allergen in text:
+            found_allergens.add(allergen)
+            allergen_details[allergen] = allergen
+            allergen_locations[allergen] = text.index(allergen)
+
+    return found_allergens, allergen_details, allergen_locations
+
+@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",
+            "/api/allergens": "GET - List of known allergens"
+        },
+        "supported_formats": list(ALLOWED_EXTENSIONS),
+        "known_allergens": list(KNOWN_ALLERGENS.keys())
+    })
+
+@main.route('/api/ocr', methods=['POST'])
+def process_image():
+    try:
+        # Check if file exists
+        if 'file' not in request.files:
+            logger.warning("No file uploaded")
+            return jsonify({"error": "No file uploaded"}), 400
+        
+        # Check the list of allergies
+        if 'allergens' not in request.form:
+            logger.warning("Allergens not specified")
+            return jsonify({"error": "Allergens not specified"}), 400
+        
+        file = request.files['file']
+        if file.filename == '':
+            logger.warning("No file selected")
+            return jsonify({"error": "No file selected"}), 400
+        
+        # Check file type
+        if not allowed_file(file.filename):
+            logger.warning(f"Invalid file type: {file.filename}")
+            return jsonify({
+                "error": "File type not supported",
+                "supported_formats": list(ALLOWED_EXTENSIONS)
+            }), 400
+
+        # Prepare a list of allergies.
+        user_allergens = request.form['allergens'].split(',')
+        logger.info(f"Processing image for allergens: {user_allergens}")
+        
+        # Read image
+        file_bytes = file.read()
+        file_stream = io.BytesIO(file_bytes)
+        
+        # Processing image
+        extracted_text = ocr_model.process_image(file_stream)
+        logger.info(f"Extracted text: {extracted_text}")
+        
+        # Searching for allergies
+        found_allergens, allergen_details, allergen_locations = find_allergens(extracted_text, user_allergens)
+        
+        # Response
+        response = {
+            "success": True,
+            "extracted_text": extracted_text,
+            "analysis": {
+                "found_allergens": list(found_allergens),
+                "allergen_details": allergen_details,
+                "allergen_locations": allergen_locations,
+                "has_allergens": len(found_allergens) > 0,
+                "warning": "⚠️ Warning: Allergens found!" if found_allergens else "✅ No allergens found",
+                "severity": "high" if len(found_allergens) > 0 else "none"
+            }
+        }
+        
+        logger.info(f"Analysis completed successfully: {found_allergens}")
+        return jsonify(response)
+        
+    except Exception as e:
+        logger.error(f"Error processing request: {str(e)}", exc_info=True)
+        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,
+        "total_count": len(KNOWN_ALLERGENS),
+        "last_updated": "2024-03-24"  # Update this date when the list is updated.
+    })

app/utils.py

@@ -0,0 +1,105 @@
+# utils.py
+import os
+from transformers import AutoModel, AutoTokenizer
+from PIL import Image, ImageEnhance, ImageFilter
+import torch
+import logging
+
+logger = logging.getLogger(__name__)
+
+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):
+        try:
+            logger.info("Initializing OCR model...")
+            
+            # Model initilization
+            self.tokenizer = AutoTokenizer.from_pretrained('RufusRubin777/GOT-OCR2_0_CPU', trust_remote_code=True)
+            self.model = AutoModel.from_pretrained(
+                'RufusRubin777/GOT-OCR2_0_CPU',
+                trust_remote_code=True,
+                low_cpu_mem_usage=True,
+                device_map='cpu',
+                use_safetensors=True,
+                pad_token_id=self.tokenizer.eos_token_id
+            )
+            
+            # choose cpu
+            self.device = "cpu"  
+            self.model = self.model.eval().cpu()
+            
+            logger.info("Model initialization completed successfully")
+            
+        except Exception as e:
+            logger.error(f"Error initializing model: {str(e)}", exc_info=True)
+            raise
+
+    def preprocess_image(self, image):
+        """Image preprocessing to improve text recognition quality"""
+        try:
+            # Convert image to RGB if it is not already
+            if image.mode != 'RGB':
+                image = image.convert('RGB')
+
+            # Improve contrast
+            enhancer = ImageEnhance.Contrast(image)
+            image = enhancer.enhance(1.5)
+
+            # Improve Sharpness
+            enhancer = ImageEnhance.Sharpness(image)
+            image = enhancer.enhance(1.5)
+
+            # Improve Brightness
+            enhancer = ImageEnhance.Brightness(image)
+            image = enhancer.enhance(1.2)
+
+            # Apply a filter to soften the image a little.
+            image = image.filter(ImageFilter.SMOOTH)
+
+            return image
+        except Exception as e:
+            logger.error(f"Error in image preprocessing: {str(e)}", exc_info=True)
+            raise
+
+    def process_image(self, image_stream):
+        try:
+            logger.info("Starting image processing")
+            
+            # Save image temporarily because the model requires a file path.
+            temp_image_path = "temp_image.jpg"
+            
+            # Reset the start pointer for BytesIO
+            image_stream.seek(0)
+            
+            # Open and save the image temporarily.
+            image = Image.open(image_stream).convert('RGB')
+            processed_image = self.preprocess_image(image)
+            processed_image.save(temp_image_path)
+            
+            # ocr 
+            try:
+                result = self.model.chat(self.tokenizer, temp_image_path, ocr_type='format')
+                logger.info(f"Successfully extracted text: {result[:100]}...")
+                
+                # Delete temporary file
+                if os.path.exists(temp_image_path):
+                    os.remove(temp_image_path)
+                
+                return result.strip()
+                
+            except Exception as e:
+                logger.error(f"Error in OCR processing: {str(e)}", exc_info=True)
+                if os.path.exists(temp_image_path):
+                    os.remove(temp_image_path)
+                raise
+            
+        except Exception as e:
+            logger.error(f"Error in image processing: {str(e)}", exc_info=True)
+            return f"Error processing image: {str(e)}"

docker-compose.yml

@@ -0,0 +1,21 @@
+version: '3.10'
+
+services:
+  app:
+    build: .
+    ports:
+      - "7860:7860"
+    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:

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