Update app.py

app.py

@@ -9,8 +9,11 @@ model = AutoModelForSequenceClassification.from_pretrained(model_name)
 model.eval()
 
 # Function to compute relevance score (in logits) and dynamically adjust threshold
-def get_relevance_score_and_excerpt(query, *paragraphs, threshold_weight):
-    if not query.strip() or not any(p.strip() for p in paragraphs):
+def get_relevance_score_and_excerpt(query, paragraph1, paragraph2, paragraph3, threshold_weight):
+    # Handle empty input for paragraphs
+    paragraphs = [p for p in [paragraph1, paragraph2, paragraph3] if p.strip()]
+    
+    if not query.strip() or not paragraphs:
         return "Please provide both a query and at least one document paragraph.", ""
 
     ranked_paragraphs = []
@@ -74,7 +77,7 @@ def get_relevance_score_and_excerpt(query, *paragraphs, threshold_weight):
     relevance_scores = [round(p["logit"], 4) for p in ranked_paragraphs]
     highlighted_texts = [p["highlighted_text"] for p in ranked_paragraphs]
 
-    return "\n".join([f"Relevance Score: {score}" for score in relevance_scores]), "\n\n".join(highlighted_texts)
+    return "\n".join([f"Relevance Score (Logits): {score}" for score in relevance_scores]), "\n\n".join(highlighted_texts)
 
 # Define Gradio interface with a slider for threshold adjustment and ability to add multiple paragraphs
 interface = gr.Interface(
@@ -97,4 +100,4 @@ interface = gr.Interface(
 )
 
 if __name__ == "__main__":
-    interface.launch()
+    interface.launch()