Update app.py

app.py

@@ -410,80 +410,90 @@ def analyze_google_fit(resume_summary):
     
     # Create a more specific prompt for T5 that focuses on detailed assessment
     prompt = f"""
-        Generate a professional expert assessment for a Google job candidate.
-        Skills detected: {skills_text}.
-        Strongest area: {top_category} ({categories_sorted[0][1]["adjusted_score"]}%).
-        Weakest area: {weak_category} ({categories_sorted[-1][1]["adjusted_score"]}%).
-        Overall match: {match_percentage}%.
+Generate a professional expert assessment for a Google job candidate.
+Skills detected: {skills_text}.
+Strongest area: {top_category} ({categories_sorted[0][1]["adjusted_score"]}%).
+Weakest area: {weak_category} ({categories_sorted[-1][1]["adjusted_score"]}%).
+Overall match: {match_percentage}%.
 
-        Write an evaluative assessment that analyzes the candidate's fit for Google.
-        Start with "This candidate" and:
-        - Evaluate their technical skills in relation to Google's standards
-        - Assess their strengths and potential contributions
-        - Provide specific areas where improvement is needed
-        - Give an overall evaluation of their Google fit
+Write an evaluative assessment that analyzes the candidate's fit for Google.
+Start with "This candidate" and provide an expert evaluation of their Google fit.
 
-        Your assessment should be an expert evaluation, not a summary of their resume.
-        Include specific actionable advice for improvement.
+This candidate"""
 
-        This candidate
-        """
-    
     try:
         # Generate the assessment using T5
         assessment_results = models['evaluator'](
             prompt, 
             max_length=300,
             do_sample=True,
-            temperature=0.75,  # Slightly higher temperature for more evaluative content
+            temperature=0.75,
             num_return_sequences=3
         )
     
-        # Find the best response
+        # Find the best response with much more thorough cleaning
         best_assessment = None
         for result in assessment_results:
-            text = result['generated_text'].strip()
-        
-            # Clean up and check if valid
-            text = re.sub(r'Generate a professional expert assessment.*?Overall match:.*?%\.', '', text, flags=re.DOTALL)
-            text = re.sub(r'Write an evaluative assessment.*?This candidate', 'This candidate', text, flags=re.DOTALL)
+            # Get the raw text
+            raw_text = result['generated_text'].strip()
         
-            # Check if it's a good response - looking for evaluative language
-            if (text.lower().startswith("this candidate") and 
-                len(text) > 100 and 
-                ("would" in text.lower() or "could" in text.lower() or "should" in text.lower() or 
-                    "needs" in text.lower() or "requires" in text.lower() or "lacks" in text.lower())):
-                best_assessment = text
-                break
+            # Extract just the part that starts with "This candidate"
+            if "This candidate" in raw_text:
+                # Find the start of the actual assessment
+                start_idx = raw_text.find("This candidate")
+                text = raw_text[start_idx:]
+            
+                # Check if it's actually an assessment (not just instructions)
+                if len(text) > 50 and not any(x in text.lower() for x in [
+                    "actionable advice", 
+                    "include specific", 
+                    "make an assessment", 
+                    "evaluate their", 
+                    "assess their", 
+                    "provide specific areas"
+                ]):
+                    best_assessment = text
+                    break
     
-        # Use the best response or the first one if none were ideal
+        # Use the best response or generate a fallback if none were ideal
         if best_assessment:
             assessment = best_assessment
         else:
-            # Use first response but clean it up
-            text = assessment_results[0]['generated_text']
-            text = re.sub(r'Generate a professional expert assessment.*?Overall match:.*?%\.', '', text, flags=re.DOTALL)
-            text = re.sub(r'Write an evaluative assessment.*?This candidate', 'This candidate', text, flags=re.DOTALL)
-        
-            # Remove numbering or bullets if present
-            text = re.sub(r'[-•]\s', '', text)
-            text = re.sub(r'\d\.\s', '', text)
-        
-            if not text.lower().startswith("this candidate"):
-                text = "This candidate " + text
-            
-            assessment = text
+            # Generate a completely manual assessment since T5 responses contain too many instructions
+            assessment = f"""This candidate demonstrates solid {top_category} with proficiency in {skills_text}. 
+However, they would need to strengthen their {weak_category} to meet Google's high standards. 
+To become more competitive, they should develop advanced problem-solving skills through algorithmic 
+challenges and contribute to open-source projects. Overall, at {match_percentage}% match, 
+they show potential but require targeted skill development before being ready for Google."""
         
     except Exception as e:
-        # Fall back to manual assessment - making this more evaluative
+        # Fallback to a completely manual assessment
         print(f"Error in T5 assessment generation: {e}")
-        assessment = f"""This candidate shows promise in {top_category} but would need significant development in {weak_category} to meet Google's standards. Their technical skills in {skills_text} align with Google's engineering needs, but they would benefit from developing stronger problem-solving capabilities and a more innovative approach to complex challenges. At {match_percentage}%, they could become a more competitive candidate with targeted improvement in these areas."""
-    
-    # Final cleanup
-    # Remove any remaining artifacts or formatting
-    assessment = re.sub(r'\n+', ' ', assessment)
+        assessment = f"""This candidate demonstrates solid {top_category} with proficiency in {skills_text}. 
+However, they would need to strengthen their {weak_category} to meet Google's high standards. 
+To become more competitive, they should develop advanced problem-solving skills through algorithmic 
+challenges and contribute to open-source projects. Overall, at {match_percentage}% match, 
+they show potential but require targeted skill development before being ready for Google."""
+
+    # Final cleanup - more aggressive to remove any remaining instructions
+    assessment = re.sub(r'include specific actionable advice.*?improvement\.', '', assessment, flags=re.DOTALL|re.IGNORECASE)
+    assessment = re.sub(r'make an assessment.*?resume\.', '', assessment, flags=re.DOTALL|re.IGNORECASE)
+    assessment = re.sub(r'evaluate their technical skills.*?google\.', '', assessment, flags=re.DOTALL|re.IGNORECASE)
+    assessment = re.sub(r'assess their strengths.*?contributions', '', assessment, flags=re.DOTALL|re.IGNORECASE)
+    assessment = re.sub(r'provide specific areas.*?needed', '', assessment, flags=re.DOTALL|re.IGNORECASE)
+    assessment = re.sub(r'give an overall.*?google', '', assessment, flags=re.DOTALL|re.IGNORECASE)
+
+    # Clean up any double spaces, newlines, etc.
     assessment = re.sub(r'\s+', ' ', assessment)
     assessment = assessment.strip()
+
+    # If cleaning removed too much text, use the fallback
+    if len(assessment) < 50 or not assessment.startswith("This candidate"):
+        assessment = f"""This candidate demonstrates solid {top_category} with proficiency in {skills_text}. 
+    However, they would need to strengthen their {weak_category} to meet Google's high standards. 
+    To become more competitive, they should develop advanced problem-solving skills through algorithmic 
+    challenges and contribute to open-source projects. Overall, at {match_percentage}% match, 
+    they show potential but require targeted skill development before being ready for Google."""
     
     # Make sure percentages are consistent
     assessment = re.sub(r'\b\d{1,2}%\b', f"{match_percentage}%", assessment)