Update app.py

app.py

@@ -1,89 +1,82 @@
-import streamlit as st
-import re
 import json
 import pandas as pd
-from datetime import datetime
+import gradio as gr
 import google.generativeai as genai
-import PyPDF2 as pdf
-import io
-import os
+import openai
+from PyPDF2 import PdfReader
 
-
-
-# Get API Key from environment variables
-api_key = os.getenv('GOOGLE_API_KEY')  # Hugging Face should use environment variables for sensitive keys
-genai.configure(api_key=api_key)
-
-# Function to get response from the Gemini model
-def get_gemini_response(input_text):
-    try:
-        model = genai.GenerativeModel('gemini-1.5-flash')
-        response = model.generate_content(input_text)
-        return response.text
-    except Exception as e:
-        return f"Error in Gemini API: {str(e)}"  # Return error message if API fails
-
-# Function to extract text from uploaded PDF
-def input_pdf_text(uploaded_file):
-    if not uploaded_file:
-        raise ValueError("No file uploaded.")
-    
-    file_stream = io.BytesIO(uploaded_file)
-    reader = pdf.PdfReader(file_stream)
-    text = ""
-    for page in reader.pages:
-        page_text = page.extract_text()
-        if page_text:  # Check if page contains any text
-            text += page_text
-    if not text:
-        raise ValueError("PDF file is empty or could not be read.")
+# Function to extract text from the uploaded PDF resume
+def input_pdf_text(resume_file):
+    with open(resume_file, "rb") as file_stream:
+        reader = PdfReader(file_stream)
+        text = ""
+        for page in reader.pages:
+            text += page.extract_text()
     return text
 
-# Function to extract name, email, and contact from the resume text
+# Function to extract contact details (name, email, and contact number) from the resume text
 def extract_contact_info(resume_text):
-    name_match = re.search(r"^(?P<name>[A-Za-z\s]+)$", resume_text, re.MULTILINE)
-    name = name_match.group('name') if name_match else "Not Available"
-    email_match = re.search(r"[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}", resume_text)
-    email = email_match.group(0) if email_match else "Not Available"
-    contact_match = re.search(r"\+?\d{1,2}\s?\(?\d{1,4}\)?\s?\d{10}", resume_text)
-    contact = contact_match.group(0) if contact_match else "Not Available"
+    # Here we simulate the extraction. You can add regex or NLP models for more accurate extraction.
+    name = "Monisha Jegadeesan"
+    email = "Bmonishaj.65@gmail.com"
+    contact = "+91 9035212894"
     return name, email, contact
 
-# Refined Prompt Template for Gemini API
+# Prepare prompt format
 input_prompt = """
-Act as a highly skilled Applicant Tracking System (ATS) with expertise in evaluating resumes for management and team leadership roles. Your task is to assess the resume against the provided job description, focusing on a detailed analysis.
-
-Instructions:
-1. **Direct Management/Team Leadership Experience**: Identify instances where the candidate has formal responsibility for managing a team, such as leading projects or directly managing team members.
-2. **Indirect Management/Team Leadership Experience**: Identify instances where the candidate provides guidance or mentorship, such as mentoring junior engineers or organizing team activities without direct management responsibility.
-3. **Mentoring/Guiding**: Identify cases where the candidate has guided or mentored others, even if not in a formal management role.
-4. **Match Percentage**: Calculate the match percentage by identifying and counting keywords and phrases relevant to management and team leadership from the job description. Include years of experience as a factor in the match.
-5. **Missing Keywords**: Identify essential keywords that are present in the job description but absent from the resume. These should be management and leadership-related terms and specific role requirements.
-6. **Experience**: Calculate the total years of experience by summing all relevant years of experience in management and team leadership roles. Focus on the years explicitly mentioned in the resume.
-
-Return the output **strictly as JSON** with these keys:
-- `"JD_Match_Percentage"`: The match percentage between the resume and job description.
-- `"Missing_Keywords"`: A list of missing keywords.
-- `"Total_Experience_Years"`: The candidate's total years of relevant experience.
-- `"Direct_Management_Experience"`: List of direct management/team leadership experience.
-- `"Indirect_Management_Experience"`: List of indirect management/team leadership experience.
-- `"Mentoring_Guiding_Experience"`: List of mentoring or guiding experience.
-- `"Name"`: The candidate's full name.
-- `"Email"`: The candidate's email address.
-- `"Contact"`: The candidate's contact number.
-- `"Profile_Summary"`: A brief summary of the candidate's qualifications.
-
-Input:
-- Resume Text: "{text}"
-- Job Description: "{jd}"
+You are an AI-powered assistant helping in resume screening for job roles.
+Based on the following resume text, compare it with the given job description and provide the following:
+1. JD_Match_Percentage: Percentage of match between JD and Resume.
+2. Missing_Keywords: List of keywords from the JD that are missing in the resume.
+3. Total_Experience_Years: Total years of experience mentioned in the resume.
+4. Direct_Management_Experience: Specific experience where the candidate had direct management responsibility.
+5. Indirect_Management_Experience: Specific experience where the candidate had indirect management responsibility.
+6. Mentoring_Guiding_Experience: Specific mentoring or guiding experience.
+7. Name: Full name of the candidate.
+8. Email: Candidate's email address.
+9. Contact: Candidate's contact number.
+10. Profile_Summary: Summary of the candidate's profile based on the resume text.
+
+Resume Text:
+{text}
+
+Job Description (JD):
+{jd}
 """
 
+# Function to interact with Gemini API
+def get_gemini_response(prompt):
+    # Replace this with actual interaction with Gemini or OpenAI APIs
+    # Here we simulate a mock response, but you'll need actual API calls
+    response = {
+        "JD_Match_Percentage": 75,
+        "Missing_Keywords": [
+            "Team Lead", "Project Management", "Leadership", "Team Building",
+            "Decision Making", "Problem Solving", "Team Motivation"
+        ],
+        "Total_Experience_Years": 3.5,
+        "Direct_Management_Experience": [],
+        "Indirect_Management_Experience": [
+            "Guiding junior engineers on programming and software design tasks to enable timely delivery of products to customers.",
+            "Mentored sixteen pairs of students on research projects, with supervision through regular team-wise progress meetings."
+        ],
+        "Mentoring_Guiding_Experience": [
+            "Guiding junior engineers on programming and software design tasks to enable timely delivery of products to customers.",
+            "Mentored sixteen pairs of students on research projects, with supervision through regular team-wise progress meetings.",
+            "Guided by Prof. Yulia Tsvetkov", "Guided by Prof. Veni Madhavan"
+        ],
+        "Name": "Monisha Jegadeesan",
+        "Email": "Bmonishaj.65@gmail.com",
+        "Contact": "+91 9035212894",
+        "Profile_Summary": "Monisha Jegadeesan is a Software Engineer with 3.5 years of experience in Google. She has a strong background in Natural Language Processing, Machine Learning, and software development. She has experience guiding junior engineers and mentoring students on research projects. Monisha has a Master's degree in Computer Science and Engineering from the Indian Institute of Technology Madras."
+    }
+    # Simulating response as JSON string
+    return json.dumps(response)
+
+# Main processing function for resume
 def process_resume(job_desc, resume_file):
     # Read the uploaded resume file
-    try:
-        resume_text = input_pdf_text(resume_file)
-    except ValueError as e:
-        return str(e), None  # Return the error message if PDF processing fails
+    resume_text = input_pdf_text(resume_file)
     
     # Extract contact info (name, email, contact)
     name, email, contact = extract_contact_info(resume_text)
@@ -91,61 +84,53 @@ def process_resume(job_desc, resume_file):
     # Prepare the prompt with resume and job description text
     prompt = input_prompt.format(text=resume_text, jd=job_desc)
     
-    # Get the response from Gemini model
+    # Get the response from Gemini model (or API)
     response_text = get_gemini_response(prompt)
-    
-    # Check if the response is empty or an error message
-    if not response_text or response_text.startswith("Error"):
-        return f"Error: {response_text}", None
 
-    # Try to parse the response as JSON
+    # Print the response to inspect it
+    print("Model response:", response_text)
+
+    # Strip any unwanted spaces or newline characters
+    response_text = response_text.strip()
+
     try:
+        # Try parsing the response as JSON
         response_data = json.loads(response_text)
-        
-        # Add extracted contact info to the JSON response
-        response_data['Name'] = name
-        response_data['Email'] = email
-        response_data['Contact'] = contact
-        
-        # Process and create DataFrame for CSV
-        df = pd.DataFrame([response_data])
-
-        # Save the results to CSV in memory
-        csv_filename = "ATS_Analysis_Results.csv"
-        df.to_csv(csv_filename, index=False)
-        
-        # Return DataFrame and CSV file for download
-        return df.to_dict(orient="records")[0], csv_filename
-    
     except json.JSONDecodeError:
+        # If JSON decoding fails, print the raw response for debugging
+        print("Error: The model's response is not in JSON format.")
+        print("Raw response:", response_text)
         return f"Error: The model's response is not in JSON format. Here is the response: {response_text}", None
 
-# Streamlit interface
-def streamlit_interface():
-    st.title("Resume Analysis with Gemini")
-    
-    # Job description input
-    job_desc = st.text_area("Paste Job Description", height=200)
-    
-    # Resume upload
-    resume_file = st.file_uploader("Upload Resume (PDF)", type="pdf")
-    
-    if st.button('Analyze Resume'):
-        if job_desc and resume_file:
-            result, csv_file = process_resume(job_desc, resume_file.getvalue())
-            if csv_file:
-                st.json(result)  # Display analysis results in JSON format
-                st.download_button(
-                    label="Download CSV", 
-                    data=csv_file, 
-                    file_name="ATS_Analysis_Results.csv", 
-                    mime="text/csv"
-                )
-            else:
-                st.error(result)  # Show error if any
-        else:
-            st.warning("Please provide both the job description and resume.")
-            
-# Run Streamlit interface
-if __name__ == "__main__":
-    streamlit_interface()
+    # Add extracted contact info to the JSON response
+    response_data['Name'] = name
+    response_data['Email'] = email
+    response_data['Contact'] = contact
+
+    # Process and create DataFrame for CSV
+    df = pd.DataFrame([response_data])
+
+    # Save the results to CSV in memory
+    csv_filename = "ATS_Analysis_Results.csv"
+    df.to_csv(csv_filename, index=False)
+
+    # Return DataFrame and CSV file for download
+    return df.to_dict(orient="records")[0], csv_filename
+
+# Gradio interface setup
+def gradio_interface(job_desc, resume_file):
+    result, csv_file = process_resume(job_desc, resume_file)
+    return result, gr.File.update(value=csv_file, visible=True)
+
+# Define Gradio interface
+resume_file_input = gr.File(label="Upload Resume (PDF)", type="file")
+job_desc_input = gr.Textbox(label="Enter Job Description", placeholder="Paste job description here")
+
+# Gradio interface layout
+with gr.Blocks() as demo:
+    job_desc_input
+    resume_file_input
+    gr.Button("Process Resume").click(gradio_interface, inputs=[job_desc_input, resume_file_input], outputs=["json", "file"])
+
+# Launch the Gradio interface
+demo.launch()