Update app.py

app.py

@@ -1,19 +1,42 @@
 import gradio as gr
 from keybert import KeyBERT
 from sentence_transformers import SentenceTransformer
+import re
 
 # ✅ Load Hugging Face model (no API key needed)
 model = SentenceTransformer('all-MiniLM-L6-v2')
 kw_model = KeyBERT(model)
 
-# 🔍 Keyword extraction function
+# 🔍 Helper: Clean keywords from text (split on commas, newlines)
+def clean_keywords(text):
+    keywords = re.split(r"[,\n]", text.lower())
+    return set(kw.strip() for kw in keywords if kw.strip())
+
+# 🔍 Main function
 def extract_keywords(job_desc, resume_text, analyze_with_jd):
     if not resume_text.strip():
-        return "Please paste your resume."
+        return "⚠️ Please paste your resume text."
+
+    # Step 1: Combine input for keyword extraction
+    combined_text = job_desc + "\n\n" + resume_text if analyze_with_jd and job_desc else resume_text
+    extracted_keywords = kw_model.extract_keywords(combined_text, top_n=15, stop_words='english')
+    extracted_set = set([kw.lower() for kw, _ in extracted_keywords])
+
+    # Step 2: Tokenize job description and resume separately
+    jd_tokens = clean_keywords(job_desc) if analyze_with_jd and job_desc else set()
+    resume_tokens = clean_keywords(resume_text)
+
+    # Step 3: Match and miss
+    matched = sorted(jd_tokens & resume_tokens)
+    missing = sorted(jd_tokens - resume_tokens)
+
+    # Step 4: Output
+    result = ""
+    result += f"🔍 **Extracted Keywords:** {', '.join(extracted_set)}\n\n"
+    result += f"✅ **Matched (Job & Resume):** {', '.join(matched) or 'None'}\n"
+    result += f"❌ **Missing in Resume:** {', '.join(missing) or 'None'}\n"
 
-    text = job_desc + "\n\n" + resume_text if analyze_with_jd and job_desc else resume_text
-    keywords = kw_model.extract_keywords(text, top_n=10, stop_words='english')
-    return ", ".join([kw for kw, _ in keywords]) if keywords else "No keywords found."
+    return result
 
 # 🎛️ Gradio UI
 with gr.Blocks() as demo:
@@ -23,7 +46,7 @@ with gr.Blocks() as demo:
             job_desc = gr.Textbox(label="Job Description", lines=6, placeholder="Paste job description here...")
             resume_text = gr.Textbox(label="Resume Text", lines=12, placeholder="Paste resume content here...")
         with gr.Column():
-            output_keywords = gr.Textbox(label="Extracted Keywords", lines=12)
+            output_keywords = gr.Markdown(label="Keyword Match Result")  # Markdown for styled output
 
     resume_text.change(fn=extract_keywords, inputs=[job_desc, resume_text, analyze_checkbox], outputs=output_keywords)
     job_desc.change(fn=extract_keywords, inputs=[job_desc, resume_text, analyze_checkbox], outputs=output_keywords)