Update app.py

app.py

@@ -1,22 +1,19 @@
 from transformers import pipeline
 import gradio as gr
 
-# Load a pre-trained sentiment analysis model for demo purposes
-# You can replace this with your fine-tuned model later
 classifier = pipeline("text-classification", model="nlptown/bert-base-multilingual-uncased-sentiment")
 
 def match_profile(resume_text, linkedin_text):
-    """
-    Combines resume and LinkedIn text, sends to classifier,
-    and returns a Suitability Score (0-100).
-    """
-    input_text = resume_text + " " + linkedin_text
-    result = classifier(input_text)
-    label = result[0]['label']
-    score = result[0]['score'] * 100
-    return f"Predicted Label: {label}\nSuitability Score: {score:.2f}"
+    try:
+        # Combine input safely and truncate
+        input_text = (resume_text + " " + linkedin_text)[:1000]  # Trim to 1000 chars
+        result = classifier(input_text)
+        label = result[0]['label']
+        score = result[0]['score'] * 100
+        return f"Predicted Label: {label}\nSuitability Score: {score:.2f}"
+    except Exception as e:
+        return f"❌ Error: {str(e)}"
 
-# Gradio Interface
 interface = gr.Interface(
     fn=match_profile,
     inputs=[
@@ -28,5 +25,4 @@ interface = gr.Interface(
     description="This tool matches an agent’s resume and LinkedIn profile using a BERT model and returns a suitability score."
 )
 
-# Launch the app
 interface.launch()