Update app.py

app.py

@@ -1,78 +1,49 @@
 import gradio as gr
-import os
-import csv
-import re
 import requests
-from sentence_transformers import SentenceTransformer, util
+import json
+import os
+from sentence_transformers import util
 
-# Initialize Sentence-Transformer model
-model = SentenceTransformer('paraphrase-MiniLM-L6-v2')
+# Set up API endpoint and API Key
+api_key = os.getenv("GOOGLE_API_KEY")  # Store your API Key in environment variables
+api_url = "https://generativelanguage.googleapis.com/v1beta/models/gemini-1-2:embedText"  # Adjust as per your model version
 
-# 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"
+headers = {
+    "Authorization": f"Bearer {api_key}",
+    "Content-Type": "application/json"
+}
 
-# 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}
-    )
+def get_gemini_embeddings(text):
+    data = {
+        "model": "gemini-1-2",  # Replace with the actual model you are using
+        "text": text
+    }
+
+    # Send POST request to Gemini API
+    response = requests.post(api_url, headers=headers, json=data)
     
-    # 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")
-        }
+        response_data = response.json()
+        return response_data.get("embeddings", [])
     else:
-        return {
-            "name": "Unknown",
-            "email": "No Email",
-            "contact": "No Contact"
-        }
+        print(f"Error: {response.status_code} - {response.text}")
+        return []
 
-# Function to extract text from resumes (assumes .pdf or .txt files)
 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"
-        else:
-            return ""
-    except Exception as e:
-        return ""
+    # Extract text from resume (you can use libraries like PyPDF2 or textract for PDFs)
+    return "Sample resume text"
+
+def extract_leadership_experience(resume_text):
+    # Logic to extract leadership experience from resume text
+    return "Leadership Experience Example"
+
+def extract_entities_via_gemini(resume_text):
+    # 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"}
 
-# Function to save results to CSV
 def save_results_to_csv(results):
-    csv_file_path = "/tmp/resume_results.csv"
+    import csv
+    csv_file_path = "/tmp/results.csv"
     with open(csv_file_path, mode='w', newline='') as file:
         writer = csv.writer(file)
         writer.writerow(["Resume Name", "Similarity Score (%)", "Eligibility", "Name", "Leadership Experience", "Email", "Contact"])
@@ -80,31 +51,35 @@ def save_results_to_csv(results):
             writer.writerow(result)
     return csv_file_path
 
-# Function to check similarity and process resumes
 def check_similarity(job_description, resume_files):
     results = []
-    job_emb = model.encode(job_description, convert_to_tensor=True)
-
+    
+    # Get embeddings for the job description using Gemini
+    job_emb = get_gemini_embeddings(job_description)
+    
+    if not job_emb:
+        return "Error in embedding job description using Gemini API."
+    
     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"))
             continue
         
-        # Check for similarity between resume and job description
-        resume_emb = model.encode(resume_text, convert_to_tensor=True)
+        # Get embeddings for the resume using Gemini
+        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"))
+            continue
+        
+        # Calculate similarity score between job description and resume
         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)
 
-        # Set a higher similarity threshold for eligibility
         if similarity_score >= 0.50:
             candidate_name = contact_info.get('name', 'Unknown Candidate')
             results.append((
@@ -127,15 +102,13 @@ def check_similarity(job_description, resume_files):
                 contact_info.get('contact', 'No Contact')
             ))
 
-    # Now return results and the file path of the CSV
     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 UI
 with gr.Blocks() as demo:
     with gr.Row():
         job_desc_input = gr.Textbox(label="Job Description", lines=3)
@@ -143,7 +116,6 @@ with gr.Blocks() as demo:
 
     results_output = gr.Dataframe(headers=["Resume Name", "Similarity Score (%)", "Eligibility", "Name", "Leadership Experience", "Email", "Contact"])
 
-    # Define the button to trigger similarity check
     check_button = gr.Button("Check Similarity")
 
     # Set up button's action
@@ -153,5 +125,4 @@ with gr.Blocks() as demo:
         outputs=[results_output, gr.File(label="Download CSV", value=download_results)]
     )
 
-# Launch Gradio interface
 demo.launch()