Update Dockerfile

Dockerfile

@@ -1,70 +1,157 @@
-# Use an official Python runtime as a parent image
-FROM python:3.9-slim
-
-# Set environment variables for Python
-ENV PYTHONDONTWRITEBYTECODE 1
-ENV PYTHONUNBUFFERED 1
-
-# Set environment variables for Hugging Face cache to /tmp (which is writable)
-ENV TRANSFORMERS_CACHE=/tmp/huggingface
-ENV HF_HOME=/tmp/huggingface
-
-# Ensure permissions are correct for /tmp/huggingface (optional, but just in case)
-RUN mkdir -p /tmp/huggingface && chmod -R 777 /tmp/huggingface
-
-# Create cache directories for Hugging Face and Matplotlib
-RUN mkdir -p /app/.cache/huggingface /app/.cache/matplotlib
-
-# Set environment variables for Hugging Face and Matplotlib cache
-ENV TRANSFORMERS_CACHE=/app/.cache/huggingface
-ENV HF_HOME=/app/.cache/huggingface
-ENV MPLCONFIGDIR=/app/.cache/matplotlib
-
-# Adding permission for the cache
-RUN chmod -R 777 /app/.cache
-
-# Give write permissions to the /app directory
-RUN chmod -R 777 /app
-
-# Create /app/logs directory and set permissions for logging
-RUN mkdir -p /app/logs && chmod -R 777 /app/logs
-
-# Set the working directory
-WORKDIR /app
-
-# Install system dependencies, including libgomp
-RUN apt-get update && apt-get install -y \
-    libgl1-mesa-glx \
-    libgomp1 \
-    libglib2.0-0 \
-    && rm -rf /var/lib/apt/lists/*
-
-# Set environment variables for Matplotlib and Hugging Face cache directories
-ENV MPLCONFIGDIR=/tmp/matplotlib
-ENV TRANSFORMERS_CACHE=/tmp/transformers_cache
-
-# Copy the requirements file into the container at /app
-COPY requirements.txt /app/
-
-# Install any needed packages specified in requirements.txt
-RUN pip install --no-cache-dir --upgrade -r requirements.txt
-
-# Create directories for session storage, uploads, and cache
-RUN mkdir -p /app/flask_sessions /app/uploads /tmp/matplotlib /tmp/transformers_cache && chmod -R 777 /app/flask_sessions /app/uploads /tmp/matplotlib /tmp/transformers_cache
-
-# Set permission for the Paddle OCR
-ENV PADDLEOCR_MODEL_DIR=/tmp/.paddleocr
-RUN mkdir -p /tmp/.paddleocr && chmod -R 777 /tmp/.paddleocr
-
-# Copy the rest of the application code to /app
-COPY . /app/
-
-# Expose the port that the app runs on
-EXPOSE 7860
-
-# Set environment variables for Flask
-ENV FLASK_APP=app.py
-ENV FLASK_ENV=production
-
-# Command to run the Flask app using Gunicorn with 1 worker
-CMD ["gunicorn", "--workers=1", "--bind=0.0.0.0:7860", "--timeout=120", "app:app"]
+# libraries
+from flask import Flask, render_template, request, redirect, url_for, flash, session, send_from_directory
+import os
+import logging
+from utility.utils import extract_text_from_images, Data_Extractor, json_to_llm_str, process_extracted_text, process_resume_data
+from backup.backup import NER_Model
+from paddleocr import PaddleOCR
+
+# Configure logging
+logging.basicConfig(
+    level=logging.INFO,
+    handlers=[
+        logging.StreamHandler()  # Remove FileHandler and log only to the console
+    ]
+)
+
+# Flask App
+app = Flask(__name__)
+app.secret_key = 'your_secret_key'
+app.config['UPLOAD_FOLDER'] = 'uploads/'
+app.config['RESULT_FOLDER'] = 'uploads/'
+
+UPLOAD_FOLDER = 'static/uploads/'
+RESULT_FOLDER = 'static/results/'
+os.makedirs(UPLOAD_FOLDER, exist_ok=True)
+os.makedirs(RESULT_FOLDER, exist_ok=True)
+
+if not os.path.exists(app.config['UPLOAD_FOLDER']):
+    os.makedirs(app.config['UPLOAD_FOLDER'])
+
+if not os.path.exists(app.config['RESULT_FOLDER']):
+    os.makedirs(app.config['RESULT_FOLDER'])
+
+# Set the PaddleOCR home directory to a writable location
+os.environ['PADDLEOCR_HOME'] = '/tmp/.paddleocr' 
+
+# Check if PaddleOCR home directory is writable
+if not os.path.exists('/tmp/.paddleocr'):
+    os.makedirs('/tmp/.paddleocr', exist_ok=True)
+    logging.info("Created PaddleOCR home directory.")
+else:
+    logging.info("PaddleOCR home directory exists.")
+
+@app.route('/')
+def index():
+    uploaded_files = session.get('uploaded_files', [])
+    logging.info(f"Accessed index page, uploaded files: {uploaded_files}")
+    return render_template('index.html', uploaded_files=uploaded_files)
+
+@app.route('/upload', methods=['POST'])
+def upload_file():
+    if 'files' not in request.files:
+        flash('No file part')
+        logging.warning("No file part found in the request")
+        return redirect(request.url)
+
+    files = request.files.getlist('files')  
+    if not files or all(file.filename == '' for file in files):
+        flash('No selected files')
+        logging.warning("No files selected for upload")
+        return redirect(request.url)
+
+    uploaded_files = session.get('uploaded_files', [])
+    for file in files:
+        if file:
+            filename = file.filename
+            file_path = os.path.join(app.config['UPLOAD_FOLDER'], filename)
+            file.save(file_path)
+            uploaded_files.append(filename)
+            logging.info(f"Uploaded file: {filename} at {file_path}")
+
+    session['uploaded_files'] = uploaded_files  
+    flash('Files successfully uploaded')
+    logging.info(f"Files successfully uploaded: {uploaded_files}")
+    return redirect(url_for('index'))
+
+@app.route('/remove_file')
+def remove_file():
+    uploaded_files = session.get('uploaded_files', [])
+    for filename in uploaded_files:
+        file_path = os.path.join(app.config['UPLOAD_FOLDER'], filename)
+        if os.path.exists(file_path):
+            os.remove(file_path)
+            logging.info(f"Removed file: {filename}")
+        else:
+            logging.warning(f"File not found for removal: {file_path}")  # More specific log
+
+    session.pop('uploaded_files', None)  
+    flash('Files successfully removed')
+    logging.info("All uploaded files removed")
+    return redirect(url_for('index'))
+
+@app.route('/process', methods=['POST'])
+def process_file():
+    uploaded_files = session.get('uploaded_files', [])
+    if not uploaded_files:
+        flash('No files selected for processing')
+        logging.warning("No files selected for processing")
+        return redirect(url_for('index'))
+
+    file_paths = [os.path.join(app.config['UPLOAD_FOLDER'], filename) for filename in uploaded_files]
+    logging.info(f"Processing files: {file_paths}")
+
+    extracted_text = {}
+    processed_Img = {}
+
+    try:
+        extracted_text, processed_Img = extract_text_from_images(file_paths, RESULT_FOLDER)
+        logging.info(f"Extracted text: {extracted_text}")
+        logging.info(f"Processed images: {processed_Img}")
+
+        llmText = json_to_llm_str(extracted_text)
+        logging.info(f"LLM text: {llmText}")
+        
+        LLMdata = Data_Extractor(llmText)
+        logging.info(f"LLM data: {LLMdata}")
+
+    except Exception as e:
+        logging.error(f"Error during LLM processing: {e}")
+        logging.info("Running backup model...")
+
+        LLMdata = {}
+       
+        if extracted_text:
+            text = json_to_llm_str(extracted_text)
+            LLMdata = NER_Model(text)
+            logging.info(f"NER model data: {LLMdata}")
+        else:
+            logging.warning("No extracted text available for backup model")
+
+    cont_data = process_extracted_text(extracted_text)
+    logging.info(f"Contextual data: {cont_data}")
+
+    processed_data = process_resume_data(LLMdata, cont_data, extracted_text)
+    logging.info(f"Processed data: {processed_data}")
+
+    session['processed_data'] = processed_data
+    session['processed_Img'] = processed_Img
+    flash('Data processed and analyzed successfully')
+    logging.info("Data processed and analyzed successfully")
+    return redirect(url_for('result'))
+
+@app.route('/result')
+def result():
+    processed_data = session.get('processed_data', {})
+    processed_Img = session.get('processed_Img', {})
+    logging.info(f"Displaying results: Data - {processed_data}, Images - {processed_Img}")
+    return render_template('result.html', data=processed_data, Img=processed_Img)
+
+@app.route('/uploads/<filename>')
+def uploaded_file(filename):
+    logging.info(f"Serving file: {filename}")
+    return send_from_directory(app.config['UPLOAD_FOLDER'], filename)
+
+if __name__ == '__main__':
+    logging.info("Starting Flask app")
+    app.run(debug=True)