app.py

import gradio as gr
import pdfplumber
import re
import openpyxl
from transformers import pipeline

# Function to extract text from PDF
def extract_text_from_pdf(pdf_path):
    with pdfplumber.open(pdf_path) as pdf:
        text = ''
        for page in pdf.pages:
            text += page.extract_text()
    return text

# Load Llama model for parsing (replace with actual model path if available)
model_name = "meta-llama/Llama-3.1-70B-Instruct"  # Replace with the model path or identifier
nlp = pipeline("text2text-generation", model=model_name)

# Function to parse the resume text for name, email, phone, and skills
def parse_resume(text):
    # Define the prompts for each type of information
    prompts = {
        "name": "Extract the name from this resume:\n",
        "email": "Extract the email address from this resume:\n",
        "phone": "Extract the phone number from this resume:\n",
        "skills": "Extract the technical skills from this resume:\n"
    }

    results = {}

    for key, prompt in prompts.items():
        # Get the model response for each field
        response = nlp(prompt + text)
        
        if key == 'email':
            # Use regex to validate email format
            email = re.findall(r'\S+@\S+', response[0]['generated_text'])
            results[key] = email[0] if email else None
        elif key == 'phone':
            # Use regex to validate phone number format
            phone = re.findall(r'\b\d{10,15}\b', response[0]['generated_text'])
            results[key] = phone[0] if phone else None
        elif key == 'skills':
            # Extract technical skills
            results[key] = response[0]['generated_text']
        else:
            results[key] = response[0]['generated_text']
    
    return results

# Function to save parsed data to Excel file
def save_to_excel(parsed_data, output_file):
    wb = openpyxl.Workbook()
    ws = wb.active
    ws.append(["Name", "Email", "Phone", "Skills"])

    for data in parsed_data:
        ws.append([data["name"], data["email"], data["phone"], data["skills"]])
    
    wb.save(output_file)

# Function to process PDF files and output an Excel file
def process_pdfs(pdfs):
    parsed_data = []
    
    for pdf in pdfs:
        # Extract text from the PDF
        text = extract_text_from_pdf(pdf.name)
        
        # Parse the text for relevant details
        parsed_info = parse_resume(text)
        
        # Add parsed information to the list
        parsed_data.append(parsed_info)

    # Save the parsed data to an Excel file
    output_file = "parsed_resumes.xlsx"
    save_to_excel(parsed_data, output_file)

    return output_file

# Gradio interface setup
iface = gr.Interface(
    fn=process_pdfs,
    inputs=gr.File(file_count="multiple", type="file"),
    outputs=gr.File(),
    live=True
)

# Launch the Gradio app
iface.launch()