Update app.py

app.py

@@ -2,9 +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
+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
@@ -32,57 +31,27 @@ def get_gemini_embeddings(text):
         return []
 
 def extract_text_from_resume(resume_file):
-    """ 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 ""
+    # 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
 
 def extract_leadership_experience(resume_text):
-    """ 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"
+    # 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):
-    """ 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}
+    # 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"}
 
 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)
@@ -159,7 +128,7 @@ with gr.Blocks() as demo:
     check_button.click(
         check_similarity, 
         inputs=[job_desc_input, resume_input], 
-        outputs=[results_output, gr.File(label="Download CSV", file_path="/tmp/results.csv")]
+        outputs=[results_output, gr.File(label="Download CSV", value=lambda: save_results_to_csv(results_output))]
     )
 
 demo.launch()