Create app.py

app.py

@@ -0,0 +1,69 @@
+import gradio as gr
+import torch
+from transformers import pipeline
+import pandas as pd
+import re
+
+# Load pre-trained model for Named Entity Recognition (NER) to extract details
+nlp = pipeline("ner", model="dbmdz/bert-large-cased-finetuned-conll03-english", framework="pt")
+
+def parse_resume(resume_text):
+    """Parse the resume and extract details like name, email, phone, and skills."""
+    # Define regex for phone and email extraction
+    phone_pattern = r'\(?\d{3}\)?[-.\s]?\d{3}[-.\s]?\d{4}'
+    email_pattern = r'[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}'
+
+    # Extract phone and email using regex
+    phone = re.findall(phone_pattern, resume_text)
+    email = re.findall(email_pattern, resume_text)
+
+    # Extract named entities for skills
+    entities = nlp(resume_text)
+    skills = [entity['word'] for entity in entities if 'MISC' in entity['entity']]
+
+    # Handle case if no skills found
+    skills = ", ".join(skills) if skills else "No skills found"
+
+    # Create a dictionary of parsed data (exclude Experience, Education, Certifications)
+    parsed_data = {
+        "Phone": phone[0] if phone else "Not found",
+        "Email": email[0] if email else "Not found",
+        "Skills": skills,
+    }
+
+    return parsed_data
+
+def process_resumes(csv_file):
+    """Process a CSV file of resumes and output a single Excel file."""
+    # Read the CSV file
+    df = pd.read_csv(csv_file.name)
+
+    # Ensure the column with resume text is named 'Resume' (you can adjust this as needed)
+    if 'Resume' not in df.columns:
+        return "Error: The CSV file must contain a 'Resume' column."
+
+    all_parsed_data = []
+
+    # Loop through each row in the CSV and parse the resume text
+    for _, row in df.iterrows():
+        resume_text = row['Resume']  # Assuming the column name is 'Resume'
+        parsed_info = parse_resume(resume_text)
+        all_parsed_data.append(parsed_info)
+
+    # Convert the parsed data into a pandas DataFrame
+    parsed_df = pd.DataFrame(all_parsed_data)
+
+    # Save the DataFrame to an Excel file
+    output_file = "parsed_resumes.xlsx"
+    parsed_df.to_excel(output_file, index=False)
+
+    return output_file
+
+# Define Gradio interface
+gr.Interface(
+    fn=process_resumes,
+    inputs=gr.File(file_count="single", label="Upload Resume CSV"),
+    outputs=gr.File(label="Download Parsed Data (Excel)"),
+    title="AI Resume Parser",
+    description="Upload a CSV file containing resume texts to extract details like Name, Email, Phone, and Skills. The results will be saved in an Excel file."
+).launch()