Update app.py

app.py

@@ -1,13 +1,12 @@
-import time
 import gradio as gr
-from sentence_transformers import SentenceTransformer
+from sentence_transformers import SentenceTransformer, util
 import os
 from PyPDF2 import PdfReader
 import docx
 import re
 import google.generativeai as genai
 import pandas as pd
-import concurrent.futures
+import time
 
 # Load pre-trained embedding model for basic analysis
 sentence_model = SentenceTransformer('paraphrase-MiniLM-L6-v2')
@@ -21,6 +20,51 @@ genai.configure(api_key=api_key)
 # Maximum resumes to process
 MAX_RESUMES = 10
 
+# Define the key leadership and management skills you're looking for
+required_skills = [
+    "strategic planning", 
+    "team management", 
+    "project management", 
+    "decision making", 
+    "communication", 
+    "leadership", 
+    "conflict resolution", 
+    "delegation", 
+    "performance management", 
+    "budget management", 
+    "resource allocation", 
+    "staff development", 
+    "change management", 
+    "risk management", 
+    "problem solving", 
+    "negotiation", 
+    "executive leadership", 
+    "organizational skills", 
+    "business development", 
+    "stakeholder management", 
+    "collaboration", 
+    "emotional intelligence", 
+    "coaching", 
+    "mentoring", 
+    "time management", 
+    "cross-functional team leadership", 
+    "innovation", 
+    "organizational culture", 
+    "team motivation", 
+    "employee engagement", 
+    "organizational design", 
+    "continuous improvement", 
+    "decision-making under pressure", 
+    "adaptability", 
+    "accountability", 
+    "team building", 
+    "succession planning", 
+    "strategic partnerships", 
+    "executive presence", 
+    "influencing", 
+    "visionary leadership"
+]
+
 # Helper Functions
 def extract_text_from_file(file_path):
     ext = os.path.splitext(file_path)[1].lower()
@@ -107,42 +151,6 @@ def calculate_overall_match(leadership_years, management_years, skills, required
     overall_match = (leadership_score * leadership_weight) + (management_score * management_weight) + (skill_score * skills_weight)
     return round(overall_match, 2)
 
-def process_resume(resume, job_desc, required_skills):
-    resume_text = extract_text_from_file(resume.name)
-
-    if not resume_text.strip():
-        return {
-            "Resume": resume.name,
-            "Candidate Name": "N/A",
-            "Email": "N/A",
-            "Contact": "N/A",
-            "Overall Match Percentage": 0.0,
-            "Gemini Analysis": "Failed to extract text from resume."
-        }
-
-    # Detailed analysis with Gemini API
-    try:
-        gemini_analysis = analyze_with_gemini(resume_text, job_desc)
-        # Extract leadership and management details
-        leadership_years, management_years, skills = extract_management_details(gemini_analysis)
-        # Calculate overall match percentage
-        overall_match = calculate_overall_match(leadership_years, management_years, skills, required_skills)
-        # Extract candidate details
-        name, email, contact = extract_candidate_details(gemini_analysis)
-    except Exception as e:
-        gemini_analysis = f"Gemini analysis failed: {str(e)}"
-        name, email, contact = "N/A", "N/A", "N/A"
-        overall_match = 0.0
-
-    return {
-        "Resume": resume.name,
-        "Candidate Name": name,
-        "Email": email,
-        "Contact": contact,
-        "Overall Match Percentage": overall_match,
-        "Gemini Analysis": gemini_analysis
-    }
-
 def process_resumes(job_desc_file, resumes):
     if not job_desc_file or not resumes:
         return "Please upload a job description and resumes for analysis."
@@ -153,16 +161,43 @@ def process_resumes(job_desc_file, resumes):
     # Load job description text
     job_desc = extract_text_from_file(job_desc_file)
 
-    # Define the key leadership and management skills you're looking for
-    required_skills = ["strategic planning", "team management", "project management", "decision making", "communication"]
-
     results = []
-    for idx, resume in enumerate(resumes):
-        # Add a small delay between requests to avoid rate-limiting
-        if idx > 0:  # Skip delay for the first request
-            time.sleep(5)  # Adjust the delay to suit your needs (e.g., 5 seconds)
-        
-        results.append(process_resume(resume, job_desc, required_skills))
+    for resume in resumes:
+        resume_text = extract_text_from_file(resume.name)
+
+        if not resume_text.strip():
+            results.append({
+                "Resume": resume.name,
+                "Candidate Name": "N/A",
+                "Email": "N/A",
+                "Contact": "N/A",
+                "Overall Match Percentage": 0.0,
+                "Gemini Analysis": "Failed to extract text from resume."
+            })
+            continue
+
+        # Detailed analysis with Gemini API
+        try:
+            gemini_analysis = analyze_with_gemini(resume_text, job_desc)
+            # Extract leadership and management details
+            leadership_years, management_years, skills = extract_management_details(gemini_analysis)
+            # Calculate overall match percentage
+            overall_match = calculate_overall_match(leadership_years, management_years, skills, required_skills)
+            # Extract candidate details
+            name, email, contact = extract_candidate_details(gemini_analysis)
+        except Exception as e:
+            gemini_analysis = f"Gemini analysis failed: {str(e)}"
+            name, email, contact = "N/A", "N/A", "N/A"
+            overall_match = 0.0
+
+        results.append({
+            "Resume": resume.name,
+            "Candidate Name": name,
+            "Email": email,
+            "Contact": contact,
+            "Overall Match Percentage": f"{overall_match}%",
+            "Gemini Analysis": gemini_analysis
+        })
 
     # Create a pandas DataFrame for better formatting and downloadable output
     df = pd.DataFrame(results)