Update app.py

app.py

@@ -163,11 +163,7 @@ def initialize_data_and_model():
         
         def extract_skills_llm(text: str) -> list[str]:
             if not isinstance(text, str) or len(text.strip()) < 20 or not LLM_PIPELINE: return []
-            prompt = f"""
-Instruct: You are an expert technical recruiter. Extract the key skills from the job description text. List technical and soft skills as a comma-separated string.
-[Example 1] Text: "Requires 3+ years of experience in cloud infrastructure. Must be proficient in AWS, particularly EC2 and S3. Experience with Terraform for IaC is a plus." Extracted Skills: cloud infrastructure, aws, ec2, s3, terraform, infrastructure as code
-[Example 2] Text: "Seeking a team lead with strong project management abilities. Must communicate effectively with stakeholders and manage timelines using Agile methodologies like Scrum." Extracted Skills: project management, leadership, stakeholder communication, agile, scrum
-[Actual Task] Text: "{text}" Extracted Skills:"""
+            prompt = f"""Instruct: You are an expert technical recruiter... [omitted for brevity]"""
             try:
                 response = LLM_PIPELINE(prompt, max_new_tokens=150, do_sample=False, temperature=0.1, return_full_text=False)
                 skills_text = response[0]['generated_text'].strip()
@@ -202,7 +198,7 @@ Instruct: You are an expert technical recruiter. Extract the key skills from the
         def expand_skills_with_llm(job_title: str, existing_skills: list) -> list:
             if not LLM_PIPELINE or not job_title or not existing_skills: return []
             skills_to_add = 6 - len(existing_skills)
-            prompt = f"""Instruct: A job has the title "{job_title}" and requires the skills: {', '.join(existing_skills)}. Based on this, what are {skills_to_add} additional, closely related skills typically required for such a role? List only the new skills, separated by commas. Do not repeat skills from the original list. Additional Skills:"""
+            prompt = f"""Instruct: A job has the title "{job_title}"... [omitted for brevity]"""
             try:
                 response = LLM_PIPELINE(prompt, max_new_tokens=50, do_sample=True, temperature=0.5, return_full_text=False)
                 new_skills_text = response[0]['generated_text'].strip()
@@ -279,7 +275,6 @@ def get_job_matches(dream_job: str, top_n: int):
 def analyze_skills(dream_job, initial_matches_df, skills_text, top_n):
     user_skills = [_norm_skill_token(s) for s in skills_text.split(',') if _norm_skill_token(s)]
     if not user_skills:
-        # If skills are cleared, just show the original table without skill scores and hide the second table
         table1_df = pd.DataFrame(initial_matches_df).head(top_n)
         table1_to_show = table1_df[['job_title', 'company', 'Similarity Score']]
         table1_to_show['Similarity Score'] = table1_to_show['Similarity Score'].map('{:.2%}'.format)
@@ -287,27 +282,27 @@ def analyze_skills(dream_job, initial_matches_df, skills_text, top_n):
 
     status = "Analyzing skills and finding new job matches..."
     
-    # --- 1. Rerank the first table ---
-    rerank_df = pd.DataFrame(initial_matches_df) # Make sure it's a DataFrame
-    rerank_df['Skill Match Score'] = rerank_df['Skills'].apply(lambda job_skills: calculate_skill_match_score(user_skills, job_skills))
-    rerank_df = rerank_df.sort_values(by='Skill Match Score', ascending=False)
+    # --- LOGIC FOR TABLE 1 (Reranked Initial Jobs) ---
+    reranked_initial_jobs = pd.DataFrame(initial_matches_df)
+    reranked_initial_jobs['Skill Match Score'] = reranked_initial_jobs['Skills'].apply(lambda js: calculate_skill_match_score(user_skills, js))
+    reranked_initial_jobs = reranked_initial_jobs.sort_values(by='Skill Match Score', ascending=False)
     
-    table1_to_show = rerank_df.head(top_n)[['job_title', 'company', 'Similarity Score', 'Skill Match Score']]
-    table1_to_show['Similarity Score'] = table1_to_show['Similarity Score'].map('{:.2%}'.format)
-    table1_to_show['Skill Match Score'] = table1_to_show['Skill Match Score'].map('{:.2%}'.format)
+    table1_df = reranked_initial_jobs.head(top_n)[['job_title', 'company', 'Similarity Score', 'Skill Match Score']]
+    table1_df['Similarity Score'] = table1_df['Similarity Score'].map('{:.2%}'.format)
+    table1_df['Skill Match Score'] = table1_df['Skill Match Score'].map('{:.2%}'.format)
 
-    # --- 2. Find new jobs for the second table ---
+    # --- LOGIC FOR TABLE 2 (New Skill-Based Jobs) ---
     combined_query = dream_job + ". My current skills are: " + skills_text
-    new_matches_df = find_job_matches(combined_query, top_k=top_n)
-    # Calculate skill match for this new table as well
-    new_matches_df['Skill Match Score'] = new_matches_df['Skills'].apply(lambda job_skills: calculate_skill_match_score(user_skills, job_skills))
+    newly_found_jobs = find_job_matches(combined_query, top_k=top_n)
+    newly_found_jobs['Skill Match Score'] = newly_found_jobs['Skills'].apply(lambda js: calculate_skill_match_score(user_skills, js))
     
-    table2_to_show = new_matches_df[['job_title', 'company', 'Similarity Score', 'Skill Match Score']]
-    table2_to_show['Similarity Score'] = table2_to_show['Similarity Score'].map('{:.2%}'.format)
-    table2_to_show['Skill Match Score'] = table2_to_show['Skill Match Score'].map('{:.2%}'.format)
+    table2_df = newly_found_jobs[['job_title', 'company', 'Similarity Score', 'Skill Match Score']]
+    table2_df['Similarity Score'] = table2_df['Similarity Score'].map('{:.2%}'.format)
+    table2_df['Skill Match Score'] = table2_df['Skill Match Score'].map('{:.2%}'.format)
 
     status = f"Re-ranked initial jobs and found new jobs for your skills."
-    return status, table1_to_show, table2_to_show, gr.update(visible=True)
+    # Return in the correct order for the UI components
+    return status, table1_df, table2_df, gr.update(visible=True)
 
 def find_matches_and_rank_with_check(dream_job: str, top_n: int):
     if not dream_job:
@@ -320,7 +315,6 @@ def find_matches_and_rank_with_check(dream_job: str, top_n: int):
         return "Status: Awaiting confirmation.", None, pd.DataFrame(), gr.update(visible=False), gr.update(visible=False), gr.update(value=alert_message, visible=True), gr.update(visible=True), pd.DataFrame(), gr.update(visible=False)
     
     status, emb_matches, table_to_show, dropdown_update, accordion_update = get_job_matches(dream_job, top_n)
-    # Hide the second table on a new search
     return status, emb_matches, table_to_show, dropdown_update, accordion_update, gr.update(visible=False), gr.update(visible=False), pd.DataFrame(), gr.update(visible=False)
 
 def find_matches_and_rank_anyway(dream_job: str, top_n: int):