Update app.py

app.py

@@ -4,23 +4,26 @@ import re
 import os
 from huggingface_hub import login
 import spacy
+from sklearn.feature_extraction.text import ENGLISH_STOP_WORDS
 
-# Authenticate with Hugging Face token
+# Authenticate with Hugging Face
 login(token=os.environ.get("HUGGINGFACEHUB_API_TOKEN"))
 
-# Load models
+# Load summarization model
 summarizer = pipeline("text2text-generation", model="declare-lab/flan-alpaca-base")
+
+# Load SpaCy English model
 nlp = spacy.load("en_core_web_sm")
 
-# Extract contextually relevant keywords using spaCy
+# 🔍 Use SpaCy to extract nouns and proper nouns (contextually relevant keywords)
 def extract_relevant_keywords(text):
     doc = nlp(text.lower())
     return set(
-        token.lemma_ for token in doc
+        token.text for token in doc
         if token.pos_ in {"NOUN", "PROPN"} and not token.is_stop and len(token.text) > 2
     )
 
-# Compare resume and JD for keyword matches
+#  Compare keywords with semantic filtering
 def compare_keywords(resume_text, job_desc):
     resume_words = extract_relevant_keywords(resume_text)
     job_words = extract_relevant_keywords(job_desc)
@@ -28,57 +31,40 @@ def compare_keywords(resume_text, job_desc):
     missing = job_words - resume_words
     return matched, missing
 
-# Highlight matched words in resume text
+#  Highlight matched keywords in the resume
 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 keyword extraction from JD
+#  LLM-based missing keyword extraction
 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.
-Only list the missing keywords as bullet points.
-
 Job Description:
 {job_desc}
-
 Resume:
 {resume_text}
+Only list the missing keywords as bullet points.
 """
-    result = summarizer(prompt, max_new_tokens=300, do_sample=False)[0]
-    raw_text = result.get('generated_text', result.get('summary_text', str(result))).strip()
+    result = summarizer(prompt, max_new_tokens=300, do_sample=True)[0]
+    return result.get('generated_text', result.get('summary_text', str(result))).strip()
 
-    # Clean and deduplicate
-    lines = re.findall(r"-\s*(.+)", raw_text)
-    cleaned = list({kw.strip().lower() for kw in lines if len(kw.strip()) > 2})
-    return ', '.join(sorted(cleaned)) or "None"
-
-# Prompt builder for structured LLM resume analysis
+#  Resume improvement prompt
 def build_dynamic_prompt(job_desc, resume_text, analyze_with_jd):
     prompt = f"""
-Act as a resume evaluator. Break the following resume into meaningful sections such as:
-- Technical Skills
-- Soft Skills
-- Education
-- Experience
-- Certifications
-- Projects (if present)
-
-Then, if a job description is provided, highlight what improvements are needed in each section to better align with the job role.
-
+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.
 Job Description:
 {job_desc if analyze_with_jd else '[None provided]'}
-
 Resume:
 {resume_text}
-
-Output your response in markdown format with section headings.
+Return structured Markdown with headers for each section and improvement suggestions.
 """
     return prompt
 
-# Core analysis function
+#  Generate analysis result
 def analyze_resume(job_desc, resume_text, analyze_with_jd):
     if not resume_text.strip():
         return "⚠️ Please paste your resume text."
@@ -86,7 +72,7 @@ def analyze_resume(job_desc, resume_text, analyze_with_jd):
     user_prompt = build_dynamic_prompt(job_desc, resume_text, analyze_with_jd)
 
     try:
-        result = summarizer(user_prompt, max_new_tokens=512, do_sample=False)[0]
+        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()
 
         if analyze_with_jd and job_desc:
@@ -95,28 +81,21 @@ def analyze_resume(job_desc, resume_text, analyze_with_jd):
             llm_missing_keywords = extract_missing_keywords_with_llm(job_desc, resume_text)
 
             return f"""### 🔍 Resume with Highlighted Matches
-
 {highlighted_resume}
-
 ---
-
-**✅ Matched Keywords (Semantic Match):**
+** Matched Keywords (Semantic Comparison):**
 {', '.join(sorted(matched)) or 'None'}
-
-**❌ Missing Keywords (Semantic Match):**
+** Missing Keywords (Semantic Comparison):**
 {', '.join(sorted(missing)) or 'None'}
-
-**🤖 LLM-Inferred Missing Keywords:**
+** LLM-Inferred Missing Keywords:**
 {llm_missing_keywords}
-
 ---
-
 {response_text}"""
         return response_text
     except Exception as e:
         return f"❌ Error: {str(e)}"
 
-# Gradio interface
+#  Gradio Interface
 def create_ui():
     with gr.Blocks() as demo:
         with gr.Row():