Update app.py

app.py

@@ -4,18 +4,17 @@ import re
 import os
 from huggingface_hub import login
 import spacy
-from sklearn.feature_extraction.text import ENGLISH_STOP_WORDS
 
-# Authenticate with Hugging Face
+# ✅ Authenticate using HF token stored in secret
 login(token=os.environ.get("HUGGINGFACEHUB_API_TOKEN"))
 
-# Load summarization model
+# ✅ Load summarization model (lightweight and CPU-friendly)
 summarizer = pipeline("text2text-generation", model="declare-lab/flan-alpaca-base")
 
-# Load SpaCy English model
+# ✅ Load SpaCy English model for NLP keyword extraction
 nlp = spacy.load("en_core_web_sm")
 
-# 🔍 Use SpaCy to extract nouns and proper nouns (contextually relevant keywords)
+# ✅ Extract keywords (nouns & proper nouns, excluding stopwords)
 def extract_relevant_keywords(text):
     doc = nlp(text.lower())
     return set(
@@ -23,7 +22,7 @@ def extract_relevant_keywords(text):
         if token.pos_ in {"NOUN", "PROPN"} and not token.is_stop and len(token.text) > 2
     )
 
-#  Compare keywords with semantic filtering
+# ✅ Match resume keywords with job description
 def compare_keywords(resume_text, job_desc):
     resume_words = extract_relevant_keywords(resume_text)
     job_words = extract_relevant_keywords(job_desc)
@@ -31,78 +30,100 @@ def compare_keywords(resume_text, job_desc):
     missing = job_words - resume_words
     return matched, missing
 
-#  Highlight matched keywords in the resume
+# ✅ Highlight matched keywords in resume text
 def highlight_keywords(resume_text, matched):
     highlighted = resume_text
     for word in sorted(matched, key=len, reverse=True):
         highlighted = re.sub(rf"\b({re.escape(word)})\b", r"**\1**", highlighted, flags=re.IGNORECASE)
     return highlighted
 
-#  LLM-based missing keyword extraction
+# ✅ Use LLM to extract contextually missing skills/tools
 def extract_missing_keywords_with_llm(job_desc, resume_text):
     prompt = f"""
 Given the following job description and resume, list the important skills, tools, and concepts from the job description that are missing or weakly represented in the resume.
+
 Job Description:
 {job_desc}
+
 Resume:
 {resume_text}
+
 Only list the missing keywords as bullet points.
 """
     result = summarizer(prompt, max_new_tokens=300, do_sample=True)[0]
-    return result.get('generated_text', result.get('summary_text', str(result))).strip()
+    return result.get('generated_text', str(result)).strip()
 
-#  Resume improvement prompt
+# ✅ Build LLM prompt to extract resume sections + insights
 def build_dynamic_prompt(job_desc, resume_text, analyze_with_jd):
     prompt = f"""
-Analyze the resume below and organize it into meaningful categories (e.g., Skills, Education, Work Experience, etc.).
-If a job description is provided, compare it against the resume and suggest improvements section by section.
+You are a professional resume analyst.
+
+Classify the content of the resume below into logical sections such as:
+- Education
+- Work Experience
+- Technical Skills
+- Soft Skills
+- Certifications
+- Projects
+- Achievements
+
+Use markdown format with headers (###) for each section.
+
+If a job description is also provided, add relevant suggestions under each section to improve alignment with the job.
+
 Job Description:
 {job_desc if analyze_with_jd else '[None provided]'}
+
 Resume:
 {resume_text}
-Return structured Markdown with headers for each section and improvement suggestions.
+
+Return your output in structured markdown format.
 """
     return prompt
 
-#  Generate analysis result
+# ✅ Generate structured LLM output + keyword analysis
 def analyze_resume(job_desc, resume_text, analyze_with_jd):
     if not resume_text.strip():
         return "⚠️ Please paste your resume text."
 
-    user_prompt = build_dynamic_prompt(job_desc, resume_text, analyze_with_jd)
+    prompt = build_dynamic_prompt(job_desc, resume_text, analyze_with_jd)
 
     try:
-        result = summarizer(user_prompt, max_new_tokens=512, do_sample=True)[0]
-        response_text = result.get('generated_text', result.get('summary_text', str(result))).strip()
+        llm_result = summarizer(prompt, max_new_tokens=512, do_sample=True)[0]
+        structured_response = llm_result.get('generated_text', str(llm_result)).strip()
 
+        # Perform keyword comparison and highlighting
         if analyze_with_jd and job_desc:
             matched, missing = compare_keywords(resume_text, job_desc)
             highlighted_resume = highlight_keywords(resume_text, matched)
             llm_missing_keywords = extract_missing_keywords_with_llm(job_desc, resume_text)
 
-            return f"""### 🔍 Resume with Highlighted Matches
+            return f"""
+### 🔍 Resume with Highlighted Matches
 
 {highlighted_resume}
 
 ---
 
-** Matched Keywords (Semantic Comparison):**
+**✅ Matched Keywords (Semantic Match):**
 {', '.join(sorted(matched)) or 'None'}
 
-** Missing Keywords (Semantic Comparison):**
+**❌ Missing Keywords (Semantic Match):**
 {', '.join(sorted(missing)) or 'None'}
 
-** LLM-Inferred Missing Keywords:**
+**🤖 LLM-Inferred Missing Keywords:**
 {llm_missing_keywords}
 
 ---
 
-{response_text}"""
-        return response_text
+{structured_response}
+"""
+        return structured_response
+
     except Exception as e:
         return f"❌ Error: {str(e)}"
 
-#  Gradio Interface
+# ✅ Gradio UI
 def create_ui():
     with gr.Blocks() as demo:
         with gr.Row():