Update app.py

app.py

@@ -4,6 +4,8 @@ import docx
 import os
 from PyPDF2 import PdfReader
 import re
+from google.cloud import language_v1
+from google.oauth2 import service_account
 
 # Load pre-trained model for sentence embedding
 model = SentenceTransformer('paraphrase-MiniLM-L6-v2')
@@ -11,43 +13,11 @@ model = SentenceTransformer('paraphrase-MiniLM-L6-v2')
 # Define maximum number of resumes
 MAX_RESUMES = 10
 
-# Function to load job description from file path
-def load_job_description(job_desc_file):
-    if not os.path.exists(job_desc_file):
-        return "Job description file not found."
-    with open(job_desc_file, 'r') as file:
-        job_description = file.read()
-    if not job_description.strip():
-        return "Job description is empty."
-    return job_description
-
-# Function to check similarity between resumes and job description
-def check_similarity(job_description, resume_files):
-    results = []
-    job_emb = model.encode(job_description, convert_to_tensor=True)
-
-    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"))
-            continue
-        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
-
-        # Identify leadership experience from resume
-        leadership_experience = extract_leadership_experience(resume_text)
-
-        # Set a higher similarity threshold for eligibility
-        if similarity_score >= 0.50:
-            candidate_name = extract_candidate_name(resume_text)
-            results.append((resume_file.name, similarity_percentage, "Eligible", candidate_name, leadership_experience))
-        else:
-            results.append((resume_file.name, similarity_percentage, "Not Eligible", None, leadership_experience))
-
-    return results
+# Google Cloud NLP Client Initialization
+def init_nlp_client():
+    credentials = service_account.Credentials.from_service_account_info(gr.Secret('GOOGLE_API_KEY_SECRET'))
+    client = language_v1.LanguageServiceClient(credentials=credentials)
+    return client
 
 # Extract text from resume (handles .txt, .pdf, .docx)
 def extract_text_from_resume(resume_file):
@@ -90,6 +60,56 @@ def extract_candidate_name(resume_text):
         return matches[0]  # Returns the first match
     return "Unknown Candidate"
 
+# Function to extract email and contact from resume using regex
+def extract_contact_info(resume_text):
+    contact_info = {}
+
+    # Extract email using regex
+    email_regex = r'[\w\.-]+@[\w\.-]+'
+    emails = re.findall(email_regex, resume_text)
+    if emails:
+        contact_info['email'] = emails[0]  # Take the first email found
+    
+    # Extract phone numbers using regex (basic phone number formats)
+    phone_regex = r'\+?\d{1,4}[\s\-]?\(?\d{1,3}\)?[\s\-]?\d{3,4}[\s\-]?\d{4}'
+    phone_numbers = re.findall(phone_regex, resume_text)
+    if phone_numbers:
+        contact_info['contact'] = phone_numbers[0]  # Take the first phone number found
+    
+    return contact_info
+
+# Function to extract entities using Google NLP API with a prompt
+def extract_entities(resume_text):
+    client = init_nlp_client()
+    
+    # Prepare the text for analysis
+    document = language_v1.Document(content=resume_text, type_=language_v1.Document.Type.PLAIN_TEXT)
+    
+    # Create a system prompt asking to extract name, contact, and email
+    system_prompt = """
+    Please extract the candidate's name, contact information (phone number), and email address from the resume.
+    The resume text is provided below. If no email or contact is found, return 'No Email' or 'No Contact'.
+    Please also provide the candidate's full name if it can be identified.
+    """
+
+    # Append the prompt and resume text together
+    full_text = system_prompt + "\n\n" + resume_text
+
+    # Use Google NLP API to analyze entities
+    response = client.analyze_entities(request={'document': document})
+    
+    entities = {}
+    for entity in response.entities:
+        entity_type = language_v1.Entity.Type(entity.type_).name
+        if entity_type == 'PERSON':
+            entities['name'] = entity.name
+        if entity_type == 'PHONE_NUMBER':
+            entities['contact'] = entity.name
+        if entity_type == 'EMAIL':
+            entities['email'] = entity.name
+    
+    return entities
+
 # Extract leadership experience (looking for keywords like manager, team lead, leadership)
 def extract_leadership_experience(resume_text):
     leadership_keywords = ['manager', 'management', 'team lead', 'supervised', 'leadership', 'head', 'coordinator']
@@ -98,12 +118,71 @@ def extract_leadership_experience(resume_text):
             return "Has leadership experience"
     return "No leadership experience"
 
+# Function to check similarity between resumes and job description
+def check_similarity(job_description, resume_files):
+    results = []
+    job_emb = model.encode(job_description, convert_to_tensor=True)
+
+    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"))
+            continue
+        
+        # Check for similarity between resume and job description
+        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 using Google NLP or regex
+        contact_info = extract_contact_info(resume_text)
+        nlp_entities = extract_entities(resume_text)
+
+        # Set a higher similarity threshold for eligibility
+        if similarity_score >= 0.50:
+            candidate_name = nlp_entities.get('name', extract_candidate_name(resume_text))
+            results.append((
+                resume_file.name, 
+                similarity_percentage, 
+                "Eligible", 
+                candidate_name, 
+                leadership_experience,
+                contact_info.get('email', 'No Email'), 
+                contact_info.get('contact', 'No Contact')
+            ))
+        else:
+            results.append((
+                resume_file.name, 
+                similarity_percentage, 
+                "Not Eligible", 
+                None, 
+                leadership_experience,
+                contact_info.get('email', 'No Email'), 
+                contact_info.get('contact', 'No Contact')
+            ))
+
+    return results
+
 # Gradio Interface Components
 job_desc_input = gr.File(label="Upload Job Description (TXT)", type="filepath")
 resumes_input = gr.Files(label="Upload Resumes (TXT, DOCX, PDF)", type="filepath")
 
 # Gradio Outputs
-results_output = gr.Dataframe(headers=["Resume File", "Similarity Score (%)", "Eligibility", "Candidate Name", "Leadership Experience"], label="Analysis Results")
+results_output = gr.Dataframe(headers=[
+    "Resume File", 
+    "Similarity Score (%)", 
+    "Eligibility", 
+    "Candidate Name", 
+    "Leadership Experience", 
+    "Email", 
+    "Contact"], 
+    label="Analysis Results"
+)
 
 # Gradio Interface
 interface = gr.Interface(
@@ -111,7 +190,7 @@ interface = gr.Interface(
     inputs=[job_desc_input, resumes_input],
     outputs=[results_output],
     title="HR Assistant - Resume Screening & Leadership Experience",
-    description="Upload job description and resumes to screen candidates for managerial and team leadership roles."
+    description="Upload job description and resumes to screen candidates for managerial and team leadership roles and extract candidate details."
 )
 
 interface.launch()