Update app.py

app.py

@@ -1,11 +1,10 @@
 import gradio as gr
+import requests
 from sentence_transformers import SentenceTransformer, util
 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')
@@ -13,13 +12,12 @@ model = SentenceTransformer('paraphrase-MiniLM-L6-v2')
 # Define maximum number of resumes
 MAX_RESUMES = 10
 
-# 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
+# Function to fetch Google API key from Hugging Face Secrets
+def get_google_api_key():
+    api_key = gr.secret('GOOGLE_API_KEY')  # Fetching the API key from Hugging Face secrets
+    return api_key
 
-# Extract text from resume (handles .txt, .pdf, .docx)
+# Function to extract text from resume (handles .txt, .pdf, .docx)
 def extract_text_from_resume(resume_file):
     file_extension = os.path.splitext(resume_file)[1].lower()
     if file_extension not in ['.txt', '.pdf', '.docx']:
@@ -52,64 +50,6 @@ def read_docx_file(file_path):
         text += para.text
     return text
 
-# Extract candidate name from resume text
-def extract_candidate_name(resume_text):
-    name_pattern = re.compile(r'\b([A-Z][a-z]+ [A-Z][a-z]+)\b')
-    matches = name_pattern.findall(resume_text)
-    if matches:
-        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']
@@ -118,6 +58,43 @@ def extract_leadership_experience(resume_text):
             return "Has leadership experience"
     return "No leadership experience"
 
+# System prompt to extract candidate details using Gemini API
+def extract_entities_via_gemini(resume_text):
+    api_key = get_google_api_key()  # Fetch the API key from Hugging Face secrets
+    endpoint = "https://gemini.googleapis.com/v1/documents:analyzeEntities"  # Placeholder API endpoint (adjust as necessary)
+
+    headers = {
+        "Authorization": f"Bearer {api_key}",
+        "Content-Type": "application/json"
+    }
+
+    document = {
+        "document": {
+            "type": "PLAIN_TEXT",
+            "content": resume_text
+        }
+    }
+    
+    # Send request to Gemini or another NLP API
+    response = requests.post(endpoint, headers=headers, json=document)
+
+    if response.status_code != 200:
+        return {"error": "Failed to extract entities from resume"}
+    
+    # Process the response from the Gemini API (or similar NLP API)
+    entities = response.json().get('entities', [])
+    extracted_info = {}
+
+    for entity in entities:
+        if entity['type'] == 'PERSON':
+            extracted_info['name'] = entity['name']
+        if entity['type'] == 'EMAIL':
+            extracted_info['email'] = entity['name']
+        if entity['type'] == 'PHONE_NUMBER':
+            extracted_info['contact'] = entity['name']
+    
+    return extracted_info
+
 # Function to check similarity between resumes and job description
 def check_similarity(job_description, resume_files):
     results = []
@@ -126,7 +103,7 @@ def check_similarity(job_description, resume_files):
     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"))
+            results.append((resume_file.name, 0, "Not Eligible", None, "No leadership experience", "No Email", "No Contact"))
             continue
         
         # Check for similarity between resume and job description
@@ -139,13 +116,12 @@ def check_similarity(job_description, resume_files):
         # 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)
+        # Extract name, email, and contact info using Google Gemini API
+        contact_info = extract_entities_via_gemini(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))
+            candidate_name = contact_info.get('name', 'Unknown Candidate')
             results.append((
                 resume_file.name, 
                 similarity_percentage,