Update app.py

app.py

@@ -258,20 +258,18 @@ def extract_skills_and_work(text):
 #####################################
 # Function: Summarize Resume Text - Optimized
 #####################################
-def summarize_resume_text(resume_text, models):
+def summarize_resume_text(resume_text):
     """
     Generates a structured summary of the resume text - optimized for speed
     """
     start_time = time.time()
     
-    summarizer = models['summarizer']
-    
-    # First, generate a quick summary
+    # First, generate a quick summary using pre-loaded model
     max_input_length = 1024  # Model limit
     
     # Only summarize the first portion of text for speed
     text_to_summarize = resume_text[:min(len(resume_text), max_input_length)]
-    base_summary = summarizer(text_to_summarize)[0]['summary_text']
+    base_summary = models['summarizer'](text_to_summarize)[0]['summary_text']
     
     # Extract information in parallel where possible
     with concurrent.futures.ThreadPoolExecutor() as executor:
@@ -301,23 +299,20 @@ def summarize_resume_text(resume_text, models):
 #####################################
 # Function: Compare Candidate Summary to Company Prompt - Optimized
 #####################################
+# Fixed: Use underscore prefix for non-hashable arguments to tell Streamlit not to hash them
 @st.cache_data(show_spinner=False)
-def compute_suitability(candidate_summary, company_prompt, models):
+def compute_suitability(candidate_summary, company_prompt, _feature_extractor=None):
     """
     Compute the similarity between candidate summary and company prompt.
     Returns a score in the range [0, 1] and execution time.
     """
     start_time = time.time()
     
-    feature_extractor = models['feature_extractor']
+    feature_extractor = _feature_extractor or models['feature_extractor']
     
-    # Extract features (embeddings) - parallelize this
-    with concurrent.futures.ThreadPoolExecutor() as executor:
-        candidate_future = executor.submit(feature_extractor, candidate_summary)
-        company_future = executor.submit(feature_extractor, company_prompt)
-        
-        candidate_features = candidate_future.result()
-        company_features = company_future.result()
+    # Extract features (embeddings)
+    candidate_features = feature_extractor(candidate_summary)
+    company_features = feature_extractor(company_prompt)
     
     # Convert to numpy arrays and flatten if needed
     candidate_vec = np.mean(np.array(candidate_features[0]), axis=0)
@@ -369,7 +364,7 @@ if uploaded_file is not None and company_prompt and st.button("Analyze Resume"):
     else:
         # Step 2: Generate summary
         status_text.text("Step 2/3: Analyzing resume and generating summary...")
-        summary, summarization_time = summarize_resume_text(resume_text, models)
+        summary, summarization_time = summarize_resume_text(resume_text)
         progress_bar.progress(75)
         
         # Display summary
@@ -379,7 +374,8 @@ if uploaded_file is not None and company_prompt and st.button("Analyze Resume"):
         
         # Step 3: Compute similarity
         status_text.text("Step 3/3: Calculating compatibility with company profile...")
-        similarity_score, similarity_time = compute_suitability(summary, company_prompt, models)
+        # Pass the feature extractor with an underscore prefix to avoid hashing issues
+        similarity_score, similarity_time = compute_suitability(summary, company_prompt, _feature_extractor=models['feature_extractor'])
         progress_bar.progress(100)
         
         # Clear status messages