Update app.py

app.py

@@ -1,6 +1,7 @@
 import os
 import tempfile
 import re
+import time
 import streamlit as st
 import docx
 import textract
@@ -51,7 +52,7 @@ def extract_text_from_file(file_obj):
 def load_summarizer():
     """
     Loads the summarization pipeline using a transformer model.
-    We use the model "ainize/bart-base-cnn" for summarization.
+    We use the model "google/pegasus-xsum" for summarization.
     """
     return pipeline("summarization", model="google/pegasus-xsum")
 
@@ -61,11 +62,14 @@ def summarize_resume_text(resume_text):
     If the resume text is very long, we trim it to avoid hitting the model's maximum input size.
     """
     summarizer = load_summarizer()
-    # In case the resume text is too long, we trim it.
+
+    # Trim resume_text if it's too long
     max_input_length = 1024  # adjust as needed
     if len(resume_text) > max_input_length:
+        st.info(f"Resume text is longer than {max_input_length} characters. Trimming text for summarization...")
         resume_text = resume_text[:max_input_length]
-    # The summarization pipeline returns a list of summaries.
+    
+    # Generate summary
     summary_result = summarizer(resume_text, max_length=150, min_length=40, do_sample=False)
     candidate_summary = summary_result[0]['summary_text']
     return candidate_summary
@@ -92,8 +96,20 @@ def process_resume(file_obj):
     Extracts text from the uploaded file and then generates a summary
     using a text summarization model.
     """
+    st.info("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() == "":
+        st.error("No text could be extracted. Please check your resume file!")
+        return ""
+    
+    st.info(f"Text extraction complete. Extracted {len(resume_text)} characters.")
+    time.sleep(0.5)  # slight delay to let the user read the info message
+    
+    st.info("Generating candidate summary, please wait...")
     candidate_summary = summarize_resume_text(resume_text)
+    st.info("Candidate summary generated.")
     return candidate_summary
 
 #####################################
@@ -115,7 +131,7 @@ 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 text summarization model (**ainize/bart-base-cnn**) to generate a concise candidate summary.
+2. Uses a transformer-based text summarization model (**google/pegasus-xsum**) to generate a concise candidate summary.
 3. Compares the candidate summary with a company profile (using Sentence-BERT) to produce a suitability score.
 """
 )
@@ -130,9 +146,11 @@ if st.button("Process Resume"):
     else:
         with st.spinner("Processing resume..."):
             candidate_summary = process_resume(uploaded_file)
-            st.session_state["candidate_summary"] = candidate_summary
-        st.subheader("Candidate Summary")
-        st.markdown(candidate_summary)
+            if candidate_summary:  # only if summary is generated
+                st.session_state["candidate_summary"] = candidate_summary
+        if candidate_summary:
+            st.subheader("Candidate Summary")
+            st.markdown(candidate_summary)
 
 # Pre-defined company prompt for Google LLC.
 default_company_prompt = (