Update app.py

app.py

@@ -66,7 +66,7 @@ def load_models():
             # Use pipeline if available
             models['evaluator'] = pipeline(
                 "sentiment-analysis", 
-                model="nlptown/bert-base-multilingual-uncased-sentiment"
+                model="lxyuan/distilbert-base-multilingual-cased-sentiments-student"
             )
         else:
             # Fall back to basic model loading
@@ -210,11 +210,7 @@ def evaluate_job_fit(resume_summary, job_requirements, models):
         analysis_prompt = analysis_prompt[:max_prompt_length]
     
     # Use sentiment analysis model for evaluation
-    # This is a smart use of a simple model - we're phrasing our prompt
-    # so that a positive sentiment = good match, negative sentiment = poor match
-    
     fit_score = 0  # Default score
-    fit_assessment = ""
     
     # Run multiple sub-analyses to build confidence in our result
     sub_analyses = []
@@ -224,10 +220,10 @@ def evaluate_job_fit(resume_summary, job_requirements, models):
         if has_pipeline and 'evaluator' in models:
             result = models['evaluator'](prompt_text)
             # Convert sentiment to score
-            if result[0]['label'] == 'POSITIVE' and result[0]['score'] > 0.9:
+            if result[0]['label'] == 'POSITIVE' and result[0]['score'] > 0.8:
                 return 2  # Strong positive = good fit
-            elif result[0]['label'] == 'POSITIVE':
-                return 1  # Positive but not strong = potential fit
+            elif result[0]['label'] == 'NEUTRAL':
+                return 1  # neutral fit = potential fit
             else:
                 return 0  # Negative = not fit
         else:
@@ -247,7 +243,7 @@ def evaluate_job_fit(resume_summary, job_requirements, models):
             positive_prob = probabilities[0][1].item()  # Positive class probability
             
             # Convert probability to score
-            if positive_prob > 0.9:
+            if positive_prob > 0.8:
                 return 2
             elif positive_prob > 0.6:
                 return 1
@@ -297,19 +293,30 @@ def evaluate_job_fit(resume_summary, job_requirements, models):
     else:
         fit_score = 0
     
-    # Count matching skills for detailed assessment
+    # Extract key information from resume for assessment
+    # Parse name, age, industry from resume summary
+    name_match = re.search(r'Name:\s*(.*?)(?=\n|\Z)', resume_summary)
+    name = name_match.group(1).strip() if name_match else "The candidate"
+    
+    age_match = re.search(r'Age:\s*(.*?)(?=\n|\Z)', resume_summary)
+    age = age_match.group(1).strip() if age_match else "unspecified age"
+    
+    industry_match = re.search(r'Expected Industry:\s*(.*?)(?=\n|\Z)', resume_summary)
+    industry = industry_match.group(1).strip() if industry_match else "unspecified industry"
+    
+    # Count matching skills but don't show the percentage in output
     resume_lower = resume_summary.lower()
     matching_skills = [skill for skill in required_skills if skill.lower() in resume_lower]
     missing_skills = [skill for skill in required_skills if skill.lower() not in resume_lower]
-    skills_match_percentage = int(len(matching_skills) / max(1, len(required_skills)) * 100)
     
-    # Generate assessment text based on score
+    # Generate assessment text based on score with more holistic evaluation
     if fit_score == 2:
-        fit_assessment = f"{fit_score}: Strong match with {skills_match_percentage}% skill alignment and suitable experience for {job_title}. Candidate demonstrates relevant background and meets key requirements."
+        fit_assessment = f"{fit_score}: {name} demonstrates strong alignment with the {job_title} position. Their background in {industry} and professional experience appear well-suited for this role's requirements. The technical expertise matches what the position demands."
     elif fit_score == 1:
-        fit_assessment = f"{fit_score}: Potential match with {skills_match_percentage}% skill alignment. Candidate meets some requirements for {job_title} but may have gaps in {', '.join(missing_skills[:3])}{'...' if len(missing_skills) > 3 else ''}."
+        fit_assessment = f"{fit_score}: {name} shows potential for the {job_title} role with some relevant experience, though there are gaps in certain technical areas. Their {industry} background provides partial alignment with the position requirements. Additional training might be needed in {', '.join(missing_skills[:2])} if pursuing this opportunity."
     else:
-        fit_assessment = f"{fit_score}: Limited match with only {skills_match_percentage}% skill alignment for {job_title}. Significant gaps in required skills and experience suggests this may not be the right fit."
+        # For score 0, be constructive but honest
+        fit_assessment = f"{fit_score}: {name}'s current background shows limited alignment with this {job_title} position. Their experience level and technical background differ significantly from the role requirements. A position better matching their {industry} expertise might be more suitable."
     
     execution_time = time.time() - start_time