Update app.py

app.py

@@ -2,6 +2,8 @@ import gradio as gr
 import requests
 import os
 import csv
+import fitz  # PyMuPDF for PDF text extraction
+import re  # For entity extraction
 from sentence_transformers import util
 
 # Set up API endpoint and API Key
@@ -30,19 +32,57 @@ def get_gemini_embeddings(text):
         return []
 
 def extract_text_from_resume(resume_file):
-    # Extract text from resume (for example, using PyPDF2 or textract for PDFs)
-    # This placeholder should be replaced with actual code for resume text extraction
-    return "Sample resume text"
+    """ Extract text from resume files (PDF or TXT). """
+    if resume_file.name.endswith('.pdf'):
+        doc = fitz.open(resume_file.name)
+        text = ""
+        for page in doc:
+            text += page.get_text()
+        return text
+    elif resume_file.name.endswith('.txt'):
+        with open(resume_file.name, 'r') as file:
+            return file.read()
+    else:
+        return ""
 
 def extract_leadership_experience(resume_text):
-    # Logic to extract leadership experience from resume text
-    return "Leadership Experience Example"
+    """ Logic to extract leadership experience from resume text. """
+    # Simple logic: Extract phrases related to leadership, you can refine this logic.
+    leadership_keywords = ["leader", "led", "managed", "directed", "supervised"]
+    leadership_experience = []
+    
+    for sentence in resume_text.split('.'):
+        if any(keyword in sentence.lower() for keyword in leadership_keywords):
+            leadership_experience.append(sentence.strip())
+    
+    return " | ".join(leadership_experience) if leadership_experience else "No leadership experience"
 
 def extract_entities_via_gemini(resume_text):
-    # Logic to extract named entities (e.g., Name, Email, Contact) using Gemini API
-    return {"name": "John Doe", "email": "john.doe@example.com", "contact": "123-456-7890"}
+    """ Extract entities like name, email, contact information. """
+    # Simple regex-based entity extraction
+    name = "Unknown"
+    email = "No Email"
+    contact = "No Contact"
+    
+    # Extract name (simple assumption - look for "Name: <some name>" format)
+    name_match = re.search(r"Name:\s*([A-Za-z\s]+)", resume_text)
+    if name_match:
+        name = name_match.group(1)
+    
+    # Extract email
+    email_match = re.search(r"[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}", resume_text)
+    if email_match:
+        email = email_match.group(0)
+    
+    # Extract contact number (simple assumption - look for numbers with optional dashes)
+    contact_match = re.search(r"\(?\d{3}\)?[\s\-]?\d{3}[\s\-]?\d{4}", resume_text)
+    if contact_match:
+        contact = contact_match.group(0)
+    
+    return {"name": name, "email": email, "contact": contact}
 
 def save_results_to_csv(results):
+    """ Save results to CSV file. """
     csv_file_path = "/tmp/results.csv"
     with open(csv_file_path, mode='w', newline='') as file:
         writer = csv.writer(file)