Update app.py

app.py

@@ -4,67 +4,73 @@ import csv
 import re
 import requests
 from sentence_transformers import SentenceTransformer, util
+from PyPDF2 import PdfReader  # For handling PDF files
 
 # Initialize Sentence-Transformer model
 model = SentenceTransformer('paraphrase-MiniLM-L6-v2')
 
+# Get Google API key from Hugging Face Secrets
+google_api_key = os.getenv("GOOGLE_API_KEY")  # Get the key from environment variables
+
 # Define a function to extract leadership experience from resume text
 def extract_leadership_experience(resume_text):
-    # Define leadership-related keywords/phrases
     leadership_keywords = [
         "led", "managed", "team lead", "supervised", "coordinated", "directed", 
         "oversaw", "responsible for", "led a team", "executed", "mentored", 
         "project manager", "leadership role", "department head", "team captain"
     ]
     
-    # Convert resume text to lower case for case-insensitive matching
     resume_text_lower = resume_text.lower()
-    
-    # Look for matches in the resume text
     leadership_experience = []
     for keyword in leadership_keywords:
         if re.search(r"\b" + re.escape(keyword) + r"\b", resume_text_lower):
             leadership_experience.append(keyword)
 
-    # Return leadership experience as a string
-    if leadership_experience:
-        return ", ".join(set(leadership_experience))
-    else:
-        return "No leadership experience found"
-
-# Define a function to extract contact info using Gemini API (simulated here)
-def extract_entities_via_gemini(resume_text):
-    # This is a simulation of the Google Gemini API. Replace with your actual API calls.
-    response = requests.post(
-        "https://your-gemini-api-endpoint.com",  # Replace with actual endpoint
-        data={"text": resume_text}
-    )
+    return ", ".join(set(leadership_experience)) if leadership_experience else "No leadership experience found"
+
+# Function to extract name, email, and contact information using Google API
+def extract_entities_via_google(resume_text):
+    endpoint = "https://language.googleapis.com/v1/documents:analyzeEntities"  # Google NLP API endpoint
+    headers = {
+        "Content-Type": "application/json",
+        "Authorization": f"Bearer {google_api_key}"  # Use the Google API key here
+    }
+    
+    # Define request payload for Google API
+    payload = {
+        "document": {
+            "type": "PLAIN_TEXT",
+            "content": resume_text
+        }
+    }
+    
+    # Make the API request to Google
+    response = requests.post(endpoint, json=payload, headers=headers)
     
-    # Simulate successful response with mock data
     if response.status_code == 200:
         data = response.json()
-        return {
-            "name": data.get("name", "Unknown"),
-            "email": data.get("email", "No Email"),
-            "contact": data.get("contact", "No Contact")
-        }
+        entities = data.get("entities", [])
+        # Extracting name, email, and contact details (mocked here as needed)
+        name = next((entity['name'] for entity in entities if entity['type'] == 'PERSON'), 'Unknown')
+        email = next((entity['name'] for entity in entities if 'email' in entity['name'].lower()), 'No Email')
+        contact = next((entity['name'] for entity in entities if 'phone' in entity['name'].lower()), 'No Contact')
+        return {"name": name, "email": email, "contact": contact}
     else:
-        return {
-            "name": "Unknown",
-            "email": "No Email",
-            "contact": "No Contact"
-        }
+        return {"name": "Unknown", "email": "No Email", "contact": "No Contact"}
 
-# Function to extract text from resumes (assumes .pdf or .txt files)
+# Function to extract text from resumes (.txt, .pdf)
 def extract_text_from_resume(resume_file):
-    # Add your extraction logic here based on the file type (e.g., PDF, DOCX, TXT)
     try:
         if resume_file.name.endswith('.txt'):
             with open(resume_file.name, 'r') as file:
                 return file.read()
         elif resume_file.name.endswith('.pdf'):
-            # Add logic to extract text from PDF
-            return "Extracted text from PDF file"
+            # Use PyPDF2 to extract text from PDF
+            pdf_reader = PdfReader(resume_file.name)
+            text = ""
+            for page in pdf_reader.pages:
+                text += page.extract_text()
+            return text
         else:
             return ""
     except Exception as e:
@@ -95,16 +101,13 @@ def check_similarity(job_description, resume_files):
         resume_emb = model.encode(resume_text, convert_to_tensor=True)
         similarity_score = util.pytorch_cos_sim(job_emb, resume_emb)[0][0].item()
 
-        # Convert similarity score to percentage
         similarity_percentage = similarity_score * 100
 
-        # Extract leadership experience
         leadership_experience = extract_leadership_experience(resume_text)
 
-        # Extract name, email, and contact info using Google Gemini API
-        contact_info = extract_entities_via_gemini(resume_text)
+        # Extract name, email, and contact info using Google API
+        contact_info = extract_entities_via_google(resume_text)
 
-        # Set a higher similarity threshold for eligibility
         if similarity_score >= 0.50:
             candidate_name = contact_info.get('name', 'Unknown Candidate')
             results.append((
@@ -127,15 +130,11 @@ def check_similarity(job_description, resume_files):
                 contact_info.get('contact', 'No Contact')
             ))
 
-    # Now return results and the file path of the CSV
+    # Return results and CSV file path
     csv_file_path = save_results_to_csv(results)
     return results, csv_file_path
 
-# Function to download the results as a CSV file
-def download_results(results):
-    return save_results_to_csv(results)
-
-# Define Gradio Interface
+# Gradio interface
 with gr.Blocks() as demo:
     with gr.Row():
         job_desc_input = gr.Textbox(label="Job Description", lines=3)
@@ -146,8 +145,8 @@ with gr.Blocks() as demo:
     # Define the button to trigger similarity check
     check_button = gr.Button("Check Similarity")
     
-    # Set up the button's action
-    check_button.click(check_similarity, inputs=[job_desc_input, resume_input], outputs=[results_output, gr.File(label="Download CSV", file=download_results)])
+    # Set up button's action
+    check_button.click(check_similarity, inputs=[job_desc_input, resume_input], outputs=[results_output, gr.File(label="Download CSV", value=save_results_to_csv)])
 
-# Launch the Gradio interface
+# Launch Gradio interface
 demo.launch()