Upload 4 files

BACKUP.PY

@@ -0,0 +1,335 @@
+import os
+import json
+from flask import Flask, request, render_template, redirect, url_for, session, flash, send_from_directory, send_file
+from werkzeug.utils import secure_filename
+from utils.file_to_text import extract_text_based_on_format, preprocess_text
+from utils.anoter_to_json import process_uploaded_json
+from utils.json_to_spacy import convert_json_to_spacy
+from utils.model import train_model
+import zipfile
+
+app = Flask(__name__)
+app.secret_key = 'your_secret_key'
+
+# Folder paths
+app.config['UPLOAD_FOLDER'] = 'uploads'
+app.config['JSON_FOLDER'] = 'JSON'
+app.config['DATA_FOLDER'] = 'data'
+app.config['MODELS_FOLDER'] = 'Models'
+
+# Allowed file extensions
+ALLOWED_EXTENSIONS = {'pdf', 'docx', 'rsf', 'odt', 'png', 'jpg', 'jpeg', 'json'}
+
+# Function to check file extensions
+def allowed_file(filename):
+    return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
+
+@app.route('/')
+def index():
+    return render_template('upload.html')
+
+# API for uploading Resume files
+@app.route('/upload',methods=['GET', 'POST'])
+def upload_file():
+    try:
+        if 'file' not in request.files:
+            flash('No file part', 'error')
+            return redirect(request.url)
+
+        file = request.files['file']
+        if file.filename == '':
+            flash('No selected file', 'error')
+            return redirect(request.url)
+
+        if file and allowed_file(file.filename):
+            filename = secure_filename(file.filename)
+            file_path = os.path.join(app.config['UPLOAD_FOLDER'], filename)
+            file.save(file_path)
+
+            # Handle text extraction for non-JSON files
+            if not filename.lower().endswith('.json'):
+                return process_other_files(file_path, filename)
+
+        flash('File type not allowed', 'error')
+    except Exception as e:
+        flash(f"Error: {str(e)}", 'error')
+    
+    return redirect(request.url)
+
+# Process non-JSON files, extract text and save to 'resume_text.txt'
+def process_other_files(file_path, filename):
+    try:
+        extracted_text, _ = extract_text_based_on_format(file_path)
+        cleaned_text = preprocess_text(extracted_text)
+
+        os.makedirs(app.config['DATA_FOLDER'], exist_ok=True)
+        resume_file_path = os.path.join(app.config['DATA_FOLDER'], 'resume_text.txt')
+
+        with open(resume_file_path, 'w', encoding='utf-8') as f:
+            f.write(cleaned_text)
+
+        session['uploaded_file'] = filename
+        return render_template('text.html', text=cleaned_text)
+    except Exception as e:
+        flash(f"Error processing file {filename}: {str(e)}", 'error')
+        return redirect(request.referrer)
+
+# API to handle the text editing and saving
+@app.route('/edit_text', methods=['POST'])
+def edit_text():
+    try:
+        # Get the edited text from the form
+        edited_text = request.form['edited_text']
+
+        # Save the edited text back to 'resume_text.txt'
+        resume_file_path = os.path.join(app.config['DATA_FOLDER'], 'resume_text.txt')
+        with open(resume_file_path, 'w', encoding='utf-8') as f:
+            f.write(edited_text)
+
+        flash('Text edited successfully', 'success')
+        # Pass the edited text back to the template
+        return render_template('text.html', text=edited_text)
+    except Exception as e:
+        flash(f"Error saving edited text: {str(e)}", 'error')
+        return redirect(request.referrer)
+    
+# API for downloading the 'resume_text.txt' file
+@app.route('/download', methods=['GET'])
+def download_file():
+    try:
+        return send_from_directory(app.config['DATA_FOLDER'], 'resume_text.txt', as_attachment=True)
+    except Exception as e:
+        flash(f"Error downloading file: {str(e)}", 'error')
+        return redirect(request.referrer)
+
+@app.route('/save_and_download', methods=['POST'])
+def save_and_download():
+    try:
+        # Get the edited text from the form
+        edited_text = request.form['edited_text']
+
+        # Save the edited text back to 'resume_text.txt'
+        resume_file_path = os.path.join(app.config['DATA_FOLDER'], 'resume_text.txt')
+        with open(resume_file_path, 'w', encoding='utf-8') as f:
+            f.write(edited_text)
+
+        flash('Text edited successfully', 'success')
+
+        # Now send the file as a download
+        return send_from_directory(app.config['DATA_FOLDER'], 'resume_text.txt', as_attachment=True)
+
+    except Exception as e:
+        flash(f"Error saving and downloading file: {str(e)}", 'error')
+        return redirect(request.referrer)
+
+
+# API for uploading and processing JSON files
+@app.route('/upload_json', methods=['POST'])
+def upload_json_file():
+    try:
+        if 'file' not in request.files:
+            flash('No file part', 'error')
+            return redirect(request.url)
+
+        file = request.files['file']
+        if file.filename == '':
+            flash('No selected file', 'error')
+            return redirect(request.url)
+
+        if file and file.filename.lower().endswith('.json'):
+            filename = secure_filename(file.filename)
+            json_path = os.path.join(app.config['JSON_FOLDER'], filename)
+            os.makedirs(app.config['JSON_FOLDER'], exist_ok=True)
+            file.save(json_path)
+            session['uploaded_json'] = filename
+            flash(f'JSON file {filename} uploaded successfully')
+        else:
+            flash('File type not allowed', 'error')
+    except Exception as e:
+        flash(f"Error: {str(e)}", 'error')
+
+    return redirect(request.referrer)
+
+# Process uploaded JSON file and save formatted data
+@app.route('/process_json', methods=['GET'])
+def process_json_file():
+    try:
+        json_folder = app.config['JSON_FOLDER']
+        json_files = os.listdir(json_folder)
+
+        if not json_files:
+            flash('No JSON files found in the folder', 'error')
+            return redirect(request.referrer)
+
+        filename = json_files[0]  # Modify logic if needed to handle multiple files
+        json_path = os.path.join(json_folder, filename)
+
+        if not os.path.exists(json_path):
+            flash(f'JSON file {filename} not found', 'error')
+            return redirect(request.referrer)
+
+        process_uploaded_json(json_path)
+        os.makedirs(app.config['DATA_FOLDER'], exist_ok=True)
+        processed_file_path = os.path.join(app.config['DATA_FOLDER'], f'Processed_{filename}')
+
+        flash(f'JSON file {filename} processed successfully')
+    except Exception as e:
+        flash(f"Error processing JSON file: {str(e)}", 'error')
+
+    return redirect(request.referrer)
+
+# API for removing uploaded JSON files
+@app.route('/remove_json', methods=['POST'])
+def remove_all_json_files():
+    try:
+        json_folder = app.config['JSON_FOLDER']
+        for filename in os.listdir(json_folder):
+            file_path = os.path.join(json_folder, filename)
+            if os.path.isfile(file_path):
+                os.remove(file_path)
+            session.pop('uploaded_json', None)
+
+        flash('All JSON files removed successfully')
+    except Exception as e:
+        flash(f"Error removing files: {str(e)}", 'error')
+
+    return redirect(request.referrer)
+
+# API for removing non-JSON files
+@app.route('/remove', methods=['POST'])
+def remove_file():
+    try:
+        upload_folder = app.config['UPLOAD_FOLDER']
+        
+        # Check if the folder exists
+        if os.path.exists(upload_folder):
+            # Loop through all files in the upload folder and remove them
+            for filename in os.listdir(upload_folder):
+                file_path = os.path.join(upload_folder, filename)
+                
+                # Check if it is a file and remove it
+                if os.path.isfile(file_path):
+                    os.remove(file_path)
+            
+            # Clear session data related to uploaded files
+            session.pop('uploaded_file', None)
+            flash('All files removed successfully')
+        else:
+            flash(f"Upload folder does not exist", 'error')
+
+    except Exception as e:
+        flash(f"Error removing files: {str(e)}", 'error')
+
+    return redirect(url_for('index'))
+
+# HTML render routes (modify to fit your structure)
+@app.route('/ner_preview', methods=['GET'])
+def ner_preview():
+    return render_template('anoter.html')
+
+@app.route('/json', methods=['GET'])
+def json_file():
+    return render_template('savejson.html')
+
+@app.route('/spacy', methods=['GET'])
+def spacy_file():
+    return render_template('saveSpacy.html')
+
+# @app.route('/text', methods=['GET'])
+# def spacy_file():
+#     return render_template('text.html')
+
+@app.route('/to_sapcy', methods=['POST'])
+def to_sapcy():
+    try:
+        # Path to the JSON file
+        json_file_path = 'data/Json_Data.json'
+        # Convert the JSON file to a .spacy file
+        spacy_file_path = 'data/Spacy_data.spacy'
+        
+        # Call the conversion function
+        convert_json_to_spacy(json_file_path, spacy_file_path)
+        
+        flash('Model training data converted successfully', 'success')
+    except Exception as e:
+        flash(f"Error during conversion: {str(e)}", 'error')
+
+    return redirect(request.referrer)
+
+@app.route('/train_model_endpoint', methods=['POST'])
+def train_model_endpoint():
+    try:
+        # Get the number of epochs and model version from the request
+        epochs = int(request.form.get('epochs', 10))  # Default to 10 if not provided
+        version = request.form.get('model_version', 'v1')  # Default to 'v1' if not provided
+        
+        # Call the training function with user-defined parameters
+        model_path = f"./Models/ner_model_{version}"
+        train_model(epochs, model_path)
+        
+        flash('Model training completed successfully', 'success')
+    except Exception as e:
+        flash(f"Error during training: {str(e)}", 'error')
+
+    return redirect(url_for('index'))
+
+# API for removing all files from specific folders
+@app.route('/remove_files', methods=['POST'])
+def remove_files():
+    try:
+        # Define folders to clear
+        folders_to_clear = [app.config['UPLOAD_FOLDER'], app.config['JSON_FOLDER']]
+
+        for folder_path in folders_to_clear:
+            # Remove all files from the specified folder
+            for filename in os.listdir(folder_path):
+                file_path = os.path.join(folder_path, filename)
+                if os.path.isfile(file_path):
+                    os.remove(file_path)
+
+        # Clear session variables related to the removed folders
+        session.pop('uploaded_file', None)
+        session.pop('uploaded_json', None)
+
+        flash('All files removed from folder successfully')
+    except Exception as e:
+        flash(f"Error removing files: {str(e)}", 'error')
+
+    return redirect(url_for('index'))
+
+# API for downloading the latest trained model
+@app.route('/download_model', methods=['GET'])
+def download_latest_model():
+    try:
+        models_dir = app.config['MODELS_FOLDER']
+        model_files = os.listdir(models_dir)
+
+        if not model_files:
+            flash('No model files found', 'error')
+            return redirect(request.referrer)
+
+        # Sort model files and get the latest one
+        latest_model_file = sorted(model_files, reverse=True)[0]
+        
+        # Full path to the latest model file
+        model_path = os.path.join(models_dir, latest_model_file)
+        
+        if not os.path.exists(model_path):
+            flash('Model file not found on the server', 'error')
+            return redirect(request.referrer)
+        
+        # Create a zip file with the model
+        zip_filename = os.path.join(models_dir, f"{latest_model_file}.zip")
+        
+        with zipfile.ZipFile(zip_filename, 'w') as zipf:
+            zipf.write(model_path, os.path.basename(model_path))
+        
+        # Send the zip file as a download
+        return send_file(zip_filename, as_attachment=True)
+    
+    except Exception as e:
+        flash(f"Error while downloading the model: {str(e)}", 'error')
+        return redirect(request.referrer)
+
+if __name__ == '__main__':
+    app.run(debug=True)

main.py

@@ -0,0 +1,350 @@
+import os
+import json
+from flask import Flask, request, render_template, redirect, url_for, session, flash, send_from_directory, send_file
+from werkzeug.utils import secure_filename
+from utils.file_to_text import extract_text_based_on_format, preprocess_text
+from utils.anoter_to_json import process_uploaded_json
+from utils.json_to_spacy import convert_json_to_spacy
+from utils.model import train_model
+import zipfile
+
+app = Flask(__name__)
+app.secret_key = 'your_secret_key'
+
+# Folder paths
+app.config['UPLOAD_FOLDER'] = 'uploads'
+app.config['JSON_FOLDER'] = 'JSON'
+app.config['DATA_FOLDER'] = 'data'
+app.config['MODELS_FOLDER'] = 'Models'
+
+# Allowed file extensions
+ALLOWED_EXTENSIONS = {'pdf', 'docx', 'rsf', 'odt', 'png', 'jpg', 'jpeg', 'json'}
+
+# Function to check file extensions
+def allowed_file(filename):
+    return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
+
+# HTML render routes (modify to fit your structure)
+@app.route('/')
+def index():
+    return render_template('upload.html')
+@app.route('/guide')
+def guide():
+    return render_template('guide.html')
+
+@app.route('/ner_preview', methods=['GET'])
+def ner_preview():
+    return render_template('anoter.html')
+
+@app.route('/json', methods=['GET'])
+def json_file():
+    return render_template('savejson.html')
+
+@app.route('/spacy', methods=['GET'])
+def spacy_file():
+    return render_template('saveSpacy.html')
+
+@app.route('/text_preview', methods=['GET'])
+def text_preview():
+    try:
+        resume_file_path = os.path.join(app.config['DATA_FOLDER'], 'resume_text.txt')
+        if not os.path.exists(resume_file_path):
+            flash('Resume text not found', 'error')
+            return redirect(url_for('index'))
+        
+        with open(resume_file_path, 'r') as f:
+            text = f.read()
+        return render_template('text.html', text=text)
+    except Exception as e:
+        flash(f"Error loading text preview: {str(e)}", 'error')
+        return redirect(url_for('index'))
+
+# API for uploading Resume files
+@app.route('/upload',methods=['GET', 'POST'])
+def upload_file():
+    try:
+        if 'file' not in request.files:
+            flash('No file part', 'error')
+            return redirect(request.url)
+
+        file = request.files['file']
+        if file.filename == '':
+            flash('No selected file', 'error')
+            return redirect(request.url)
+
+        if file and allowed_file(file.filename):
+            filename = secure_filename(file.filename)
+            file_path = os.path.join(app.config['UPLOAD_FOLDER'], filename)
+            file.save(file_path)
+
+            # Handle text extraction for non-JSON files
+            if not filename.lower().endswith('.json'):
+                return process_other_files(file_path, filename)
+
+        flash('File type not allowed', 'error')
+    except Exception as e:
+        flash(f"Error: {str(e)}", 'error')
+    
+    return redirect(request.url)
+
+# Process non-JSON files, extract text and save to 'resume_text.txt'
+def process_other_files(file_path, filename):
+    try:
+        extracted_text, _ = extract_text_based_on_format(file_path)
+        cleaned_text = preprocess_text(extracted_text)
+
+        os.makedirs(app.config['DATA_FOLDER'], exist_ok=True)
+        resume_file_path = os.path.join(app.config['DATA_FOLDER'], 'resume_text.txt')
+
+        with open(resume_file_path, 'w', encoding='utf-8') as f:
+            f.write(cleaned_text)
+
+        session['uploaded_file'] = filename
+        return render_template('text.html', text=cleaned_text)
+    except Exception as e:
+        flash(f"Error processing file {filename}: {str(e)}", 'error')
+        return redirect(request.referrer)
+
+# API to handle the text editing and saving
+@app.route('/edit_text', methods=['POST'])
+def edit_text():
+    try:
+        # Get the edited text from the form
+        edited_text = request.form['edited_text']
+
+        # Save the edited text back to 'resume_text.txt'
+        resume_file_path = os.path.join(app.config['DATA_FOLDER'], 'resume_text.txt')
+        with open(resume_file_path, 'w', encoding='utf-8') as f:
+            f.write(edited_text)
+
+        flash('Text edited successfully', 'success')
+        # Pass the edited text back to the template
+        return render_template('text.html', text=edited_text)
+    except Exception as e:
+        flash(f"Error saving edited text: {str(e)}", 'error')
+        return redirect(request.referrer)
+    
+# API for downloading the 'resume_text.txt' file
+@app.route('/download', methods=['GET'])
+def download_file():
+    try:
+        return send_from_directory(app.config['DATA_FOLDER'], 'resume_text.txt', as_attachment=True)
+    except Exception as e:
+        flash(f"Error downloading file: {str(e)}", 'error')
+        return redirect(request.referrer)
+
+@app.route('/save_and_download', methods=['POST'])
+def save_and_download():
+    try:
+        # Get the edited text from the form
+        edited_text = request.form['edited_text']
+
+        # Save the edited text back to 'resume_text.txt'
+        resume_file_path = os.path.join(app.config['DATA_FOLDER'], 'resume_text.txt')
+        with open(resume_file_path, 'w', encoding='utf-8') as f:
+            f.write(edited_text)
+
+        # flash('Text edited successfully', 'success')
+
+        # Now send the file as a download
+        return send_from_directory(app.config['DATA_FOLDER'], 'resume_text.txt', as_attachment=True)
+
+    except Exception as e:
+        flash(f"Error saving and downloading file: {str(e)}", 'error')
+        return redirect(request.referrer)
+
+
+# API for uploading and processing JSON files
+@app.route('/upload_json', methods=['POST'])
+def upload_json_file():
+    try:
+        if 'file' not in request.files:
+            flash('No file part', 'error')
+            return redirect(request.url)
+
+        file = request.files['file']
+        if file.filename == '':
+            flash('No selected file', 'error')
+            return redirect(request.url)
+
+        if file and file.filename.lower().endswith('.json'):
+            filename = secure_filename(file.filename)
+            json_path = os.path.join(app.config['JSON_FOLDER'], filename)
+            os.makedirs(app.config['JSON_FOLDER'], exist_ok=True)
+            file.save(json_path)
+            session['uploaded_json'] = filename
+            flash(f'JSON file {filename} uploaded successfully')
+        else:
+            flash('File type not allowed', 'error')
+    except Exception as e:
+        flash(f"Error: {str(e)}", 'error')
+
+    return redirect(request.referrer)
+
+# Process uploaded JSON file and save formatted data
+@app.route('/process_json', methods=['GET'])
+def process_json_file():
+    try:
+        json_folder = app.config['JSON_FOLDER']
+        json_files = os.listdir(json_folder)
+
+        if not json_files:
+            flash('No JSON files found in the folder', 'error')
+            return redirect(request.referrer)
+
+        filename = json_files[0]  # Modify logic if needed to handle multiple files
+        json_path = os.path.join(json_folder, filename)
+
+        if not os.path.exists(json_path):
+            flash(f'JSON file {filename} not found', 'error')
+            return redirect(request.referrer)
+
+        process_uploaded_json(json_path)
+        os.makedirs(app.config['DATA_FOLDER'], exist_ok=True)
+        processed_file_path = os.path.join(app.config['DATA_FOLDER'], f'Processed_{filename}')
+
+        flash(f'JSON file {filename} processed successfully')
+    except Exception as e:
+        flash(f"Error processing JSON file: {str(e)}", 'error')
+
+    return redirect(request.referrer)
+
+# API for removing uploaded JSON files
+@app.route('/remove_json', methods=['POST'])
+def remove_all_json_files():
+    try:
+        json_folder = app.config['JSON_FOLDER']
+        for filename in os.listdir(json_folder):
+            file_path = os.path.join(json_folder, filename)
+            if os.path.isfile(file_path):
+                os.remove(file_path)
+            session.pop('uploaded_json', None)
+
+        flash('All JSON files removed successfully')
+    except Exception as e:
+        flash(f"Error removing files: {str(e)}", 'error')
+
+    return redirect(request.referrer)
+
+# API for removing non-JSON files
+@app.route('/remove', methods=['POST'])
+def remove_file():
+    try:
+        upload_folder = app.config['UPLOAD_FOLDER']
+        
+        # Check if the folder exists
+        if os.path.exists(upload_folder):
+            # Loop through all files in the upload folder and remove them
+            for filename in os.listdir(upload_folder):
+                file_path = os.path.join(upload_folder, filename)
+                
+                # Check if it is a file and remove it
+                if os.path.isfile(file_path):
+                    os.remove(file_path)
+            
+            # Clear session data related to uploaded files
+            session.pop('uploaded_file', None)
+            flash('All files removed successfully')
+        else:
+            flash(f"Upload folder does not exist", 'error')
+
+    except Exception as e:
+        flash(f"Error removing files: {str(e)}", 'error')
+
+    return redirect(url_for('index'))
+
+
+@app.route('/to_sapcy', methods=['POST'])
+def to_sapcy():
+    try:
+        # Path to the JSON file
+        json_file_path = 'data/Json_Data.json'
+        # Convert the JSON file to a .spacy file
+        spacy_file_path = 'data/Spacy_data.spacy'
+        
+        # Call the conversion function
+        convert_json_to_spacy(json_file_path, spacy_file_path)
+        
+        flash('Model training data converted successfully', 'success')
+    except Exception as e:
+        flash(f"Error during conversion: {str(e)}", 'error')
+
+    return redirect(request.referrer)
+
+@app.route('/train_model_endpoint', methods=['POST'])
+def train_model_endpoint():
+    try:
+        # Get the number of epochs and model version from the request
+        epochs = int(request.form.get('epochs', 10))  # Default to 10 if not provided
+        version = request.form.get('model_version', 'v1')  # Default to 'v1' if not provided
+        
+        # Call the training function with user-defined parameters
+        model_path = f"./Models/ner_model_{version}"
+        train_model(epochs, model_path)
+        
+        flash('Model training completed successfully', 'success')
+    except Exception as e:
+        flash(f"Error during training: {str(e)}", 'error')
+
+    return redirect(url_for('index'))
+
+# API for removing all files from specific folders
+@app.route('/remove_files', methods=['POST'])
+def remove_files():
+    try:
+        # Define folders to clear
+        folders_to_clear = [app.config['UPLOAD_FOLDER'], app.config['JSON_FOLDER'], app.config['MODELS_FOLDER'] ]
+
+        for folder_path in folders_to_clear:
+            # Remove all files from the specified folder
+            for filename in os.listdir(folder_path):
+                file_path = os.path.join(folder_path, filename)
+                if os.path.isfile(file_path):
+                    os.remove(file_path)
+
+        # Clear session variables related to the removed folders
+        session.pop('uploaded_file', None)
+        session.pop('uploaded_json', None)
+
+        flash('All files removed from folder successfully')
+    except Exception as e:
+        flash(f"Error removing files: {str(e)}", 'error')
+
+    return redirect(url_for('index'))
+
+# API for downloading the latest trained model
+@app.route('/download_model', methods=['GET'])
+def download_latest_model():
+    try:
+        models_dir = app.config['MODELS_FOLDER']
+        model_files = os.listdir(models_dir)
+
+        if not model_files:
+            flash('No model files found', 'error')
+            return redirect(request.referrer)
+
+        # Sort model files and get the latest one
+        latest_model_file = sorted(model_files, reverse=True)[0]
+        
+        # Full path to the latest model file
+        model_path = os.path.join(models_dir, latest_model_file)
+        
+        if not os.path.exists(model_path):
+            flash('Model file not found on the server', 'error')
+            return redirect(request.referrer)
+        
+        # Create a zip file with the model
+        zip_filename = os.path.join(models_dir, f"{latest_model_file}.zip")
+        
+        with zipfile.ZipFile(zip_filename, 'w') as zipf:
+            zipf.write(model_path, os.path.basename(model_path))
+        
+        # Send the zip file as a download
+        return send_file(zip_filename, as_attachment=True)
+    
+    except Exception as e:
+        flash(f"Error while downloading the model: {str(e)}", 'error')
+        return redirect(request.referrer)
+
+if __name__ == '__main__':
+    app.run(debug=True)

readme

@@ -0,0 +1,150 @@
+\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\
+\\----------- **Resume Parser** ----------\\
+\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\
+
+# Overview:
+This project is a comprehensive Resume Parsing tool built using Python,
+integrating the Mistral-Nemo-Instruct-2407 model for primary parsing.
+If Mistral fails or encounters issues,
+the system falls back to a custom-trained spaCy model to ensure continued functionality.
+The tool is wrapped with a Flask API and has a user interface built using HTML and CSS.
+
+
+# Installation Guide:
+
+1. Create and Activate a Virtual Environment
+    python -m venv venv
+    source venv/bin/activate  # For Linux/Mac
+    # or
+    venv\Scripts\activate  # For Windows
+
+    # NOTE: If the virtual environment (venv) is already created, you can skip the creation step and just activate.
+        - For Linux/Mac:
+            source venv/bin/activate
+        - For Windows:
+            venv\Scripts\activate
+
+2. Install Required Libraries
+    pip install -r requirements.txt
+
+    # Ensure the following dependencies are included:
+    - Flask
+    - spaCy
+    - huggingface_hub
+    - PyMuPDF
+    - python-docx
+    - Tesseract-OCR (for image-based parsing)
+
+; NOTE : If any model or library is not installed, you can install it using:
+    pip install <model_name>
+    _Replace <model_name> with the specific model or library you need to install_
+
+3. Set up Hugging Face Token
+    - Add your Hugging Face token to the .env file as:
+    HF_TOKEN=<your_huggingface_token>
+
+
+# File Structure Overview:
+    Mistral_With_Spacy/
+    │
+    ├── Spacy_Models/
+    │   └── ner_model_05_3  # Pretrained spaCy model directory for resume parsing
+    │
+    ├── templates/
+    │   ├── index.html  # UI for file upload
+    │   └── result.html  # Display parsed results in structured JSON
+    │
+    ├── uploads/  # Directory for uploaded resume files
+    │
+    ├── utils/
+    │   ├── mistral.py  # Code for calling Mistral API and handling responses
+    │   ├── spacy.py  # spaCy fallback model for parsing resumes
+    │   ├── error.py  # Error handling utilities
+    │   └── fileTotext.py  # Functions to extract text from different file formats (PDF, DOCX, etc.)
+    │
+    ├── venv/  # Virtual environment
+    │
+    ├── .env  # Environment variables file (contains Hugging Face token)
+    │
+    ├── main.py  # Flask app handling API routes for uploading and processing resumes
+    │
+    └── requirements.txt  # Dependencies required for the project
+
+
+# Program Overview:
+
+    # Mistral Integration (utils/mistral.py)
+        - Mistral API Calls: Uses Hugging Faces Mistral-Nemo-Instruct-2407 model to parse resumes.
+        - Personal and Professional Extraction: Two functions extract personal and professional information in structured JSON format.
+        - Fallback Mechanism: If Mistral fails, spaCys NER model is used as a fallback.
+
+    # SpaCy Integration (utils/spacy.py)
+        - Custom Trained Model: Uses a spaCy model (ner_model_05_3) trained specifically for resume parsing.
+        - Named Entity Recognition: Extracts key information like Name, Email, Contact, Location, Skills, Experience, etc., from resumes.
+        - Validation: Includes validation for extracted emails and contacts.
+
+    # File Conversion (utils/fileTotext.py)
+       - Text Extraction: Handles different resume formats (PDF, DOCX, ODT, RSF, and images like PNG, JPG, JPEG) and extracts text for further processing.
+          - PDF Files: Uses PyMuPDF to extract text and, if necessary, Tesseract-OCR for image-based PDF content.
+          - DOCX Files: Uses `python-docx` to extract structured text from Word documents.
+          - ODT Files: Uses `odfpy` to extract text from ODT (OpenDocument) files.
+          - RSF Files: Reads plain text from RSF files.
+          - Images (PNG, JPG, JPEG): Uses Tesseract-OCR to extract text from image-based resumes.
+            Note: For Tesseract-OCR, install it locally by following the [installation guide](https://github.com/UB-Mannheim/tesseract/wiki).
+          - Hyperlink Extraction: Extracts hyperlinks from PDF files, capturing any embedded URLs during the parsing process.
+
+
+    # Error Handling (utils/error.py)
+        - Manages API response errors, file format issues, and ensures smooth fallbacks without crashing the app.
+
+    # Flask API (main.py)
+        Endpoints:
+        - /upload for uploading resumes.
+        - Displays parsed results in JSON format on the results page.
+        - UI: Simple interface for uploading resumes and viewing the parsing results.
+
+
+# Tree map of your program:
+
+    main.py
+    ├── Handles API side
+    ├── File upload/remove
+    ├── Process resumes
+    └── Show result
+    utils
+    ├── fileTotext.py
+    │   └── Converts files to text
+    │       ├── PDF
+    │       ├── DOCX
+    │       ├── RTF
+    │       ├── ODT
+    │       ├── PNG
+    │       ├── JPG
+    │       └── JPEG
+    ├── mistral.py
+    │   ├── Mistral API Calls
+    │   │   └── Uses Mistral-Nemo-Instruct-2407 model
+    │   ├── Personal and Professional Extraction
+    │   │   ├── Extracts personal information
+    │   │   └── Extracts professional information
+    │   └── Fallback Mechanism
+    │       └── Uses spaCy NER model if Mistral fails
+    └── spacy.py
+        ├── Custom Trained Model
+        │   └── Uses spaCy model (ner_model_05_3)
+        ├── Named Entity Recognition
+        │   └── Extracts key information (Name, Email, Contact, etc.)
+        └── Validation
+            └── Validates emails and contacts
+
+
+# References:
+
+- [Flask Documentation](https://flask.palletsprojects.com/)
+- [spaCy Documentation](https://spacy.io/usage)
+- [Mistral Documentation](https://docs.mistral.ai/)
+- [Hugging Face Hub API](https://huggingface.co/docs/huggingface_hub/index)
+- [PyMuPDF (MuPDF) Documentation](https://pymupdf.readthedocs.io/en/latest/)
+- [python-docx Documentation](https://python-docx.readthedocs.io/en/latest/)
+- [Tesseract OCR Documentation](https://github.com/UB-Mannheim/tesseract/wiki)
+- [Virtual Environments in Python](https://docs.python.org/3/tutorial/venv.html)

requirements.txt

@@ -0,0 +1,71 @@
+amqp==5.2.0
+annotated-types==0.7.0
+billiard==4.2.0
+blinker==1.8.2
+blis==0.7.11
+catalogue==2.0.10
+celery==5.4.0
+certifi==2024.8.30
+charset-normalizer==3.3.2
+click==8.1.7
+click-didyoumean==0.3.1
+click-plugins==1.1.1
+click-repl==0.3.0
+cloudpathlib==0.19.0
+colorama==0.4.6
+confection==0.1.5
+cymem==2.0.8
+defusedxml==0.7.1
+Flask==3.0.3
+Flask-SQLAlchemy==3.1.1
+greenlet==3.1.0
+idna==3.10
+itsdangerous==2.2.0
+Jinja2==3.1.4
+kombu==5.4.1
+langcodes==3.4.0
+language_data==1.2.0
+lxml==5.3.0
+marisa-trie==1.2.0
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+mdurl==0.1.2
+murmurhash==1.0.10
+numpy==1.26.4
+odfpy==1.4.1
+packaging==24.1
+pdf2image==1.17.0
+pillow==10.4.0
+preshed==3.0.9
+prompt_toolkit==3.0.47
+pydantic==2.9.1
+pydantic_core==2.23.3
+Pygments==2.18.0
+PyMuPDF==1.24.10
+PyMuPDFb==1.24.10
+pytesseract==0.3.13
+python-dateutil==2.9.0.post0
+python-docx==1.1.2
+requests==2.32.3
+rich==13.8.1
+setuptools==75.0.0
+shellingham==1.5.4
+six==1.16.0
+smart-open==7.0.4
+spacy==3.7.6
+spacy-legacy==3.0.12
+spacy-loggers==1.0.5
+SQLAlchemy==2.0.34
+srsly==2.4.8
+thinc==8.2.5
+tqdm==4.66.5
+typer==0.12.5
+typing_extensions==4.12.2
+tzdata==2024.1
+urllib3==2.2.3
+vine==5.1.0
+wasabi==1.1.3
+wcwidth==0.2.13
+weasel==0.4.1
+Werkzeug==3.0.4
+wrapt==1.16.0