Update app.py

app.py

@@ -3,7 +3,6 @@ import requests
 import os
 import csv
 from sentence_transformers import util
-import fitz  # PyMuPDF for PDF extraction
 
 # Set up API endpoint and API Key
 api_key = os.getenv("GOOGLE_API_KEY")  # Store your API Key in environment variables
@@ -31,20 +30,12 @@ def get_gemini_embeddings(text):
         return []
 
 def extract_text_from_resume(resume_file):
-    # Extract text from PDF resume file using PyMuPDF
-    text = ""
-    try:
-        # Open the PDF file
-        with fitz.open(resume_file.name) as doc:
-            for page in doc:
-                text += page.get_text()
-    except Exception as e:
-        print(f"Error extracting text from {resume_file.name}: {e}")
-    return text
+    # 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"
 
 def extract_leadership_experience(resume_text):
     # Logic to extract leadership experience from resume text
-    # (For simplicity, we'll just return a placeholder)
     return "Leadership Experience Example"
 
 def extract_entities_via_gemini(resume_text):
@@ -52,7 +43,6 @@ def extract_entities_via_gemini(resume_text):
     return {"name": "John Doe", "email": "john.doe@example.com", "contact": "123-456-7890"}
 
 def save_results_to_csv(results):
-    # Save the results to a CSV file and return the file path
     csv_file_path = "/tmp/results.csv"
     with open(csv_file_path, mode='w', newline='') as file:
         writer = csv.writer(file)
@@ -63,24 +53,25 @@ def save_results_to_csv(results):
 
 def check_similarity(job_description, resume_files):
     results = []
-    
+
     # Get embeddings for the job description using Gemini 1.5 Flash
     job_emb = get_gemini_embeddings(job_description)
     
     if not job_emb:
-        return "Error in embedding job description using Gemini 1.5 Flash API."
+        # In case of an error, return an empty DataFrame and an error message
+        return [["Error in embedding job description using Gemini 1.5 Flash API."]], None
     
     for resume_file in resume_files:
         resume_text = extract_text_from_resume(resume_file)
         if not resume_text:
-            results.append((resume_file.name, 0, "Not Eligible", None, "No leadership experience", "No Email", "No Contact"))
+            results.append([resume_file.name, 0, "Not Eligible", None, "No leadership experience", "No Email", "No Contact"])
             continue
         
         # Get embeddings for the resume using Gemini 1.5 Flash
         resume_emb = get_gemini_embeddings(resume_text)
         
         if not resume_emb:
-            results.append((resume_file.name, 0, "Not Eligible", None, "No leadership experience", "No Email", "No Contact"))
+            results.append([resume_file.name, 0, "Not Eligible", None, "No leadership experience", "No Email", "No Contact"])
             continue
         
         # Calculate similarity score between job description and resume
@@ -92,7 +83,7 @@ def check_similarity(job_description, resume_files):
 
         if similarity_score >= 0.50:
             candidate_name = contact_info.get('name', 'Unknown Candidate')
-            results.append((
+            results.append([
                 resume_file.name, 
                 similarity_percentage, 
                 "Eligible", 
@@ -100,9 +91,9 @@ def check_similarity(job_description, resume_files):
                 leadership_experience,
                 contact_info.get('email', 'No Email'), 
                 contact_info.get('contact', 'No Contact')
-            ))
+            ])
         else:
-            results.append((
+            results.append([
                 resume_file.name, 
                 similarity_percentage, 
                 "Not Eligible", 
@@ -110,9 +101,9 @@ def check_similarity(job_description, resume_files):
                 leadership_experience,
                 contact_info.get('email', 'No Email'), 
                 contact_info.get('contact', 'No Contact')
-            ))
-
-    # Return results and the path to the CSV file
+            ])
+    
+    # Save results to CSV and return them
     csv_file_path = save_results_to_csv(results)
     return results, csv_file_path