Spaces:
Sleeping
Sleeping
# libraries | |
from flask import Flask, render_template, request, redirect, url_for, flash, session, send_from_directory | |
import os | |
from utility.utils import extract_text_from_images,Data_Extractor,json_to_llm_str,process_extracted_text,process_resume_data | |
# Flask App | |
app = Flask(__name__) | |
app.secret_key = 'your_secret_key' | |
app.config['UPLOAD_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']) | |
def index(): | |
uploaded_files = session.get('uploaded_files', []) | |
return render_template('index.html', uploaded_files=uploaded_files) | |
def upload_file(): | |
if 'files' not in request.files: | |
flash('No file part') | |
return redirect(request.url) | |
files = request.files.getlist('files') # Get multiple files | |
if not files or all(file.filename == '' for file in files): | |
flash('No selected files') | |
return redirect(request.url) | |
uploaded_files = [] | |
for file in files: | |
if file: | |
filename = file.filename | |
file.save(os.path.join(app.config['UPLOAD_FOLDER'], filename)) | |
uploaded_files.append(filename) | |
session['uploaded_files'] = uploaded_files | |
flash('Files successfully uploaded') | |
return redirect(url_for('index')) | |
def remove_file(): | |
uploaded_files = session.get('uploaded_files', []) | |
for filename in uploaded_files: | |
os.remove(os.path.join(app.config['UPLOAD_FOLDER'], filename)) | |
session.pop('uploaded_files', None) | |
flash('Files successfully removed') | |
return redirect(url_for('index')) | |
def process_file(): | |
uploaded_files = session.get('uploaded_files', []) | |
if not uploaded_files: | |
flash('No files selected for processing') | |
return redirect(url_for('index')) | |
# Create a list of file paths for the extracted text function | |
file_paths = [os.path.join(app.config['UPLOAD_FOLDER'], filename) for filename in uploaded_files] | |
# Extract text from all images | |
extracted_text,processed_Img = extract_text_from_images(file_paths,RESULT_FOLDER) | |
# Convert PDF to text | |
print("extracted_text----------------------------",extracted_text) | |
print("extracted_text type----------------------------",type(extracted_text)) | |
print("processed_Img----------------------------",processed_Img) | |
print("processed_Img type----------------------------",type(processed_Img)) | |
try: | |
# Call the Gemma model API and get the professional data | |
llmText=json_to_llm_str(extracted_text) | |
print("llmText---------->",llmText) | |
LLMdata = Data_Extractor(llmText) | |
print("LLMdata----------------------------",LLMdata) | |
except Exception as e: | |
# Handling any exceptions during the process | |
print(f"An error occurred: {e}") | |
# Run the backup model in case of an exception | |
print("Running backup model...") | |
cont_data=process_extracted_text(extracted_text) | |
print("cont_data----------------------------",cont_data) | |
#storing the paresed results | |
processed_data = process_resume_data(LLMdata,cont_data,extracted_text) | |
session['processed_data'] = processed_data | |
session['processed_Img'] = processed_Img | |
flash('Data processed and analyzed successfully ') | |
return redirect(url_for('result')) | |
def result(): | |
processed_data = session.get('processed_data', {}) | |
processed_Img = session.get('processed_Img', {}) | |
return render_template('result.html', data=processed_data,Img=processed_Img) | |
def uploaded_file(filename): | |
return send_from_directory(app.config['UPLOAD_FOLDER'], filename) | |
if __name__ == '__main__': | |
app.run(debug=True) |