Update app.py

app.py

@@ -4,43 +4,29 @@ import streamlit as st
 import docx
 import textract
 from transformers import pipeline
-import threading
-import numpy as np
+
+# Set page title
+st.set_page_config(page_title="Resume Analyzer and Company Suitability Checker")
 
 #####################################
-# Load Models - Optimized with Threading
+# Preload Models
 #####################################
-@st.cache_resource(show_spinner=False)
+@st.cache_resource(show_spinner=True)
 def load_models():
-    """
-    Load all models in parallel using threading to speed up initialization
-    """
-    models = {}
-    
-    def load_summarizer_thread():
-        models['summarizer'] = pipeline("summarization", model="google/pegasus-xsum", device=0 if st.session_state.get('use_gpu', False) else -1)
-    
-    def load_similarity_thread():
-        # Using sentence-similarity pipeline instead of SentenceTransformer
-        models['similarity'] = pipeline("sentence-similarity", model="sentence-transformers/all-MiniLM-L6-v2", 
-                                       device=0 if st.session_state.get('use_gpu', False) else -1)
-    
-    # Start threads to load models in parallel
-    threads = [
-        threading.Thread(target=load_summarizer_thread),
-        threading.Thread(target=load_similarity_thread)
-    ]
-    
-    for thread in threads:
-        thread.start()
-    
-    for thread in threads:
-        thread.join()
-    
-    return models
+    """Load all models at startup"""
+    with st.spinner("Loading AI models... This may take a minute on first run."):
+        models = {}
+        # Load summarization model
+        models['summarizer'] = pipeline("summarization", model="google/pegasus-xsum")
+        # Load similarity model
+        models['similarity'] = pipeline("sentence-similarity", model="sentence-transformers/all-MiniLM-L6-v2")
+        return models
+
+# Preload models immediately when app starts
+models = load_models()
 
 #####################################
-# Function: Extract Text from File - Optimized
+# Function: Extract Text from File
 #####################################
 def extract_text_from_file(file_obj):
     """
@@ -54,18 +40,15 @@ def extract_text_from_file(file_obj):
     if ext == ".docx":
         try:
             document = docx.Document(file_obj)
-            # Use a list comprehension and join for better performance
             text = "\n".join(para.text for para in document.paragraphs if para.text.strip())
         except Exception as e:
             text = f"Error processing DOCX file: {e}"
     elif ext == ".doc":
         try:
-            # Use a context manager for better file handling
             with tempfile.NamedTemporaryFile(delete=False, suffix=".doc") as tmp:
                 tmp.write(file_obj.read())
                 tmp_filename = tmp.name
             text = textract.process(tmp_filename).decode("utf-8")
-            # Clean up the temporary file immediately
             os.unlink(tmp_filename)
         except Exception as e:
             text = f"Error processing DOC file: {e}"
@@ -74,20 +57,19 @@ def extract_text_from_file(file_obj):
     return text
 
 #####################################
-# Function: Summarize Resume Text - Optimized
+# Function: Summarize Resume Text
 #####################################
 def summarize_resume_text(resume_text, models):
     """
-    Generates a concise summary of the resume text using the pre-loaded summarization model.
+    Generates a concise summary of the resume text using the summarization model.
     """
     summarizer = models['summarizer']
-
-    # Optimize text processing - only use essential text
-    # Break text into chunks and summarize important parts
+    
+    # Handle long text
     max_input_length = 1024  # PEGASUS-XSUM limit
     
     if len(resume_text) > max_input_length:
-        # Instead of simple trimming, extract key sections
+        # Process in chunks if text is too long
         chunks = [resume_text[i:i+max_input_length] for i in range(0, min(len(resume_text), 3*max_input_length), max_input_length)]
         summaries = []
         
@@ -96,7 +78,6 @@ def summarize_resume_text(resume_text, models):
             summaries.append(chunk_summary)
         
         candidate_summary = " ".join(summaries)
-        # Summarize again if combined summary is too long
         if len(candidate_summary) > max_input_length:
             candidate_summary = summarizer(candidate_summary[:max_input_length], max_length=150, min_length=40, do_sample=False)[0]['summary_text']
     else:
@@ -105,11 +86,11 @@ def summarize_resume_text(resume_text, models):
     return candidate_summary
 
 #####################################
-# Function: Compare Candidate Summary to Company Prompt - Using Pipeline
+# Function: Compare Candidate Summary to Company Prompt
 #####################################
 def compute_suitability(candidate_summary, company_prompt, models):
     """
-    Compute the similarity between candidate summary and company prompt using the similarity pipeline.
+    Compute the similarity between candidate summary and company prompt.
     Returns a score in the range [0, 1].
     """
     similarity_pipeline = models['similarity']
@@ -125,130 +106,92 @@ def compute_suitability(candidate_summary, company_prompt, models):
     return score
 
 #####################################
-# Main Resume Processing Logic
+# Streamlit Interface
 #####################################
-def process_resume(file_obj, models):
-    """
-    Extracts text from the uploaded file and then generates a summary
-    using a text summarization model.
+st.title("Resume Analyzer and Company Suitability Checker")
+st.markdown(
     """
-    with st.status("Processing resume...") as status:
-        status.update(label="Extracting text from resume...")
-        resume_text = extract_text_from_file(file_obj)
-        
-        # Check if resume_text is valid
-        if not resume_text or resume_text.strip() == "":
-            status.update(label="Error: No text could be extracted", state="error")
-            return ""
-        
-        status.update(label=f"Extracted {len(resume_text)} characters. Generating summary...")
-        
-        candidate_summary = summarize_resume_text(resume_text, models)
-        status.update(label="Processing complete!", state="complete")
-    
-    return candidate_summary
+Upload your resume file in **.doc** or **.docx** format. The app performs the following tasks:
+1. Extracts text from the resume.
+2. Uses a transformer-based model to generate a concise candidate summary.
+3. Compares the candidate summary with a company profile to produce a suitability score.
+"""
+)
 
-#####################################
-# Streamlit Interface - Optimized
-#####################################
-def main():
-    st.set_page_config(page_title="Resume Analyzer", layout="wide")
+# Use two columns with equal width
+col1, col2 = st.columns(2)
+
+with col1:
+    # File uploader for resume
+    uploaded_file = st.file_uploader("Upload Resume", type=["doc", "docx"])
     
-    # Initialize session state for GPU usage
-    if 'use_gpu' not in st.session_state:
-        st.session_state.use_gpu = False
+    if uploaded_file is not None:
+        st.write(f"{uploaded_file.name}  {uploaded_file.size/1024:.1f}KB")
     
-    # Only show sidebar settings on first run
-    with st.sidebar:
-        st.title("Settings")
-        if st.checkbox("Use GPU (if available)", value=st.session_state.use_gpu):
-            st.session_state.use_gpu = True
+    # Button to process the resume
+    if st.button("Process Resume", type="primary", use_container_width=True):
+        if uploaded_file is None:
+            st.error("Please upload a resume file first.")
         else:
-            st.session_state.use_gpu = False
-        
-        st.info("Using GPU can significantly speed up model inference if available")
-    
-    # Load models - this happens only once due to caching
-    with st.spinner("Loading AI models..."):
-        models = load_models()
-    
-    st.title("Resume Analyzer and Company Suitability Checker")
-    st.markdown(
-        """
-    Upload your resume file in **.doc** or **.docx** format. The app performs the following tasks:
-    1. Extracts text from the resume.
-    2. Uses a transformer-based model to generate a concise candidate summary.
-    3. Compares the candidate summary with a company profile to produce a suitability score.
-    """
-    )
-
-    # Use columns for better layout
-    col1, col2 = st.columns([1, 1])
-    
-    with col1:
-        # File uploader for resume
-        uploaded_file = st.file_uploader("Upload Resume", type=["doc", "docx"])
-        
-        # Button to process the resume
-        if st.button("Process Resume", type="primary", use_container_width=True):
-            if uploaded_file is None:
-                st.error("Please upload a resume file first.")
-            else:
-                candidate_summary = process_resume(uploaded_file, models)
-                if candidate_summary:  # only if summary is generated
+            with st.status("Processing resume...") as status:
+                status.update(label="Extracting text from resume...")
+                resume_text = extract_text_from_file(uploaded_file)
+                
+                if not resume_text or resume_text.strip() == "":
+                    status.update(label="Error: No text could be extracted", state="error")
+                else:
+                    status.update(label=f"Extracted {len(resume_text)} characters. Generating summary...")
+                    candidate_summary = summarize_resume_text(resume_text, models)
                     st.session_state["candidate_summary"] = candidate_summary
-        
-        # Display candidate summary if available
-        if "candidate_summary" in st.session_state:
-            st.subheader("Candidate Summary")
-            st.markdown(st.session_state["candidate_summary"])
+                    status.update(label="Processing complete!", state="complete")
     
-    with col2:
-        # Pre-defined company prompt for Google LLC.
-        default_company_prompt = (
-            "Google LLC, a global leader in technology and innovation, specializes in internet services, cloud computing, "
-            "artificial intelligence, and software development. As part of Alphabet Inc., Google seeks candidates with strong "
-            "problem-solving skills, adaptability, and collaboration abilities. Technical roles require proficiency in programming "
-            "languages such as Python, Java, C++, Go, or JavaScript, with expertise in data structures, algorithms, and system design. "
-            "Additionally, skills in AI, cybersecurity, UX/UI design, and digital marketing are highly valued. Google fosters a culture "
-            "of innovation, expecting candidates to demonstrate creativity, analytical thinking, and a passion for cutting-edge technology."
-        )
+    # Display candidate summary if available
+    if "candidate_summary" in st.session_state:
+        st.subheader("Candidate Summary")
+        st.markdown(st.session_state["candidate_summary"])
 
-        # Company prompt text area.
-        company_prompt = st.text_area(
-            "Enter company details:",
-            value=default_company_prompt,
-            height=150,
-        )
+with col2:
+    # Pre-defined company prompt for Google LLC.
+    default_company_prompt = (
+        "Google LLC, a global leader in technology and innovation, specializes in internet services, cloud computing, "
+        "artificial intelligence, and software development. As part of Alphabet Inc., Google seeks candidates with strong "
+        "problem-solving skills, adaptability, and collaboration abilities. Technical roles require proficiency in programming "
+        "languages such as Python, Java, C++, Go, or JavaScript, with expertise in data structures, algorithms, and system design. "
+        "Additionally, skills in AI, cybersecurity, UX/UI design, and digital marketing are highly valued. Google fosters a culture "
+        "of innovation, expecting candidates to demonstrate creativity, analytical thinking, and a passion for cutting-edge technology."
+    )
 
-        # Button to compute the suitability score.
-        if st.button("Compute Suitability Score", type="primary", use_container_width=True):
-            if "candidate_summary" not in st.session_state:
-                st.error("Please process the resume first!")
+    # Company prompt text area.
+    company_prompt = st.text_area(
+        "Enter company details:",
+        value=default_company_prompt,
+        height=150,
+    )
+
+    # Button to compute the suitability score.
+    if st.button("Compute Suitability Score", type="primary", use_container_width=True):
+        if "candidate_summary" not in st.session_state:
+            st.error("Please process the resume first!")
+        else:
+            candidate_summary = st.session_state["candidate_summary"]
+            if candidate_summary.strip() == "":
+                st.error("Candidate summary is empty; please check your resume file.")
+            elif company_prompt.strip() == "":
+                st.error("Please enter the company information.")
             else:
-                candidate_summary = st.session_state["candidate_summary"]
-                if candidate_summary.strip() == "":
-                    st.error("Candidate summary is empty; please check your resume file.")
-                elif company_prompt.strip() == "":
-                    st.error("Please enter the company information.")
+                with st.spinner("Computing suitability score..."):
+                    score = compute_suitability(candidate_summary, company_prompt, models)
+                
+                # Display score with a progress bar for visual feedback
+                st.success(f"Suitability Score: {score:.2f} (range 0 to 1)")
+                st.progress(score)
+                
+                # Add interpretation of score
+                if score > 0.75:
+                    st.info("Excellent match! Your profile appears very well suited for this company.")
+                elif score > 0.5:
+                    st.info("Good match. Your profile aligns with many aspects of the company's requirements.")
+                elif score > 0.3:
+                    st.info("Moderate match. Consider highlighting more relevant skills or experience.")
                 else:
-                    with st.spinner("Computing suitability score..."):
-                        score = compute_suitability(candidate_summary, company_prompt, models)
-                    
-                    # Display score with a progress bar for visual feedback
-                    st.success(f"Suitability Score: {score:.2f} (range 0 to 1)")
-                    st.progress(score)
-                    
-                    # Add interpretation of score
-                    if score > 0.75:
-                        st.info("Excellent match! Your profile appears very well suited for this company.")
-                    elif score > 0.5:
-                        st.info("Good match. Your profile aligns with many aspects of the company's requirements.")
-                    elif score > 0.3:
-                        st.info("Moderate match. Consider highlighting more relevant skills or experience.")
-                    else:
-                        st.info("Low match. Your profile may need significant adjustments to better align with this company.")
-
-
-if __name__ == "__main__":
-    main()
+                    st.info("Low match. Your profile may need significant adjustments to better align with this company.")