Update app.py

app.py

@@ -3,30 +3,42 @@ from transformers import pipeline
 import re
 import os
 from huggingface_hub import login
+import spacy
+from sklearn.feature_extraction.text import ENGLISH_STOP_WORDS
 
-# ✅ Authenticate using HF token stored in secret
+# Authenticate with Hugging Face
 login(token=os.environ.get("HUGGINGFACEHUB_API_TOKEN"))
 
-# ✅ Use a lightweight instruction-tuned model compatible with CPU
+# Load summarization model
 summarizer = pipeline("text2text-generation", model="declare-lab/flan-alpaca-base")
 
-# ✅ Highlight matching and find missing keywords
-from sklearn.feature_extraction.text import ENGLISH_STOP_WORDS
+# Load SpaCy English model
+nlp = spacy.load("en_core_web_sm")
+
+# 🔍 Use SpaCy to extract nouns and proper nouns (contextually relevant keywords)
+def extract_relevant_keywords(text):
+    doc = nlp(text.lower())
+    return set(
+        token.text for token in doc
+        if token.pos_ in {"NOUN", "PROPN"} and not token.is_stop and len(token.text) > 2
+    )
 
+#  Compare keywords with semantic filtering
 def compare_keywords(resume_text, job_desc):
-    resume_words = set(re.findall(r"\b\w{3,}\b", resume_text.lower())) - ENGLISH_STOP_WORDS
-    job_words = set(re.findall(r"\b\w{3,}\b", job_desc.lower())) - ENGLISH_STOP_WORDS
+    resume_words = extract_relevant_keywords(resume_text)
+    job_words = extract_relevant_keywords(job_desc)
     matched = resume_words & job_words
     missing = job_words - resume_words
     return matched, missing
 
+#  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
 
-# 🔍 Use LLM to extract missing keywords contextually 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.
@@ -39,7 +51,7 @@ 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()
 
-# 🔍 Prompt for dynamic section classification and feedback
+#  Resume improvement prompt
 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.).
@@ -52,7 +64,7 @@ Return structured Markdown with headers for each section and improvement suggest
 """
     return prompt
 
-# 🧠 Function to call Hugging Face model and get structured resume feedback
+#  Generate analysis result
 def analyze_resume(job_desc, resume_text, analyze_with_jd):
     if not resume_text.strip():
         return "⚠️ Please paste your resume text."
@@ -62,16 +74,35 @@ def analyze_resume(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()
+
         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\n\n{highlighted_resume}\n\n---\n**✅ Matched Keywords (Basic Comparison):**\n{', '.join(sorted(matched)) or 'None'}\n\n**❌ Missing Keywords (Basic Comparison):**\n{', '.join(sorted(missing)) or 'None'}\n\n**🤖 LLM-Inferred Missing Keywords:**\n{llm_missing_keywords}\n\n---\n{response_text}"
+
+            return f"""### 🔍 Resume with Highlighted Matches
+
+{highlighted_resume}
+
+---
+
+** Matched Keywords (Semantic Comparison):**
+{', '.join(sorted(matched)) or 'None'}
+
+** Missing Keywords (Semantic Comparison):**
+{', '.join(sorted(missing)) or 'None'}
+
+** LLM-Inferred Missing Keywords:**
+{llm_missing_keywords}
+
+---
+
+{response_text}"""
         return response_text
     except Exception as e:
         return f"❌ Error: {str(e)}"
 
-# 🎛️ Gradio UI
+#  Gradio Interface
 def create_ui():
     with gr.Blocks() as demo:
         with gr.Row():