Update app.py

app.py

@@ -1,34 +1,42 @@
 import gradio as gr
 from sentence_transformers import CrossEncoder
+import torch
 
-# Load a Semantic Textual Similarity CrossEncoder
-model = CrossEncoder("cross-encoder/stsb-roberta-large")
+# Load MS MARCO CrossEncoder (query-document relevance)
+MODEL_NAME = "cross-encoder/ms-marco-MiniLM-L-12-v2"
+model = CrossEncoder(MODEL_NAME)
 
 def predict_similarity(s1, s2):
-    score = model.predict([(s1, s2)])[0]   # already continuous
-    return round(float(score), 4)
+    # Get raw score (logit)
+    score = model.predict([(s1, s2)])[0]
+    # Apply sigmoid to map to 0–1
+    similarity = torch.sigmoid(torch.tensor(score)).item()
+    return round(similarity, 4)
 
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
-    gr.Markdown("## 🔎 Semantic Textual Similarity (CrossEncoder)")
-    gr.Markdown("Score ranges 0 (unrelated) → 1 (identical meaning).")
+    gr.Markdown("## 🔎 Query–Document Relevance (CrossEncoder)")
+    gr.Markdown(
+        f"Model: **{MODEL_NAME}**\n\n"
+        "Scores are mapped with sigmoid to the range **0 (irrelevant) → 1 (highly relevant)**."
+    )
 
     with gr.Row():
-        s1 = gr.Textbox(label="Sentence 1", placeholder="Type first sentence...")
-        s2 = gr.Textbox(label="Sentence 2", placeholder="Type second sentence...")
+        s1 = gr.Textbox(label="Query", placeholder="Enter your search query...")
+        s2 = gr.Textbox(label="Document Chunk", placeholder="Enter a document chunk...")
 
     btn = gr.Button("Compute Similarity 🚀")
-    out = gr.Number(label="Similarity Score (0–1)")
+    out = gr.Number(label="Relevance Score (0–1)")
 
     btn.click(fn=predict_similarity, inputs=[s1, s2], outputs=out)
 
     gr.Examples(
         examples=[
-            ["I am a boy", "I am a girl"],
-            ["I am happy today", "I am feeling a bit curious and joyful today"],
-            ["I am going", "I am moving from you"],
-            ["The sun is hot", "Ice cream is cold"],
+            ["What is the capital of France?", "Paris is the capital city of France."],
+            ["I am happy today", "I am feeling joyful and excited right now."],
+            ["Python programming", "Bananas are yellow fruits."],
+            ["Machine learning applications", "ML is widely used in healthcare and finance."],
         ],
         inputs=[s1, s2],
     )
 
-demo.launch()
+demo.launch(enable_queue=True)