init

Signed-off-by: bitliu <bitliu@tencent.com>

app.py

@@ -5,6 +5,24 @@ from transformers import AutoTokenizer, AutoModelForSequenceClassification, Auto
 
 # ============== Model Configurations ==============
 MODELS = {
+    "📚 Category Classifier": {
+        "id": "LLM-Semantic-Router/category_classifier_modernbert-base_model",
+        "description": "Classifies prompts into academic/professional categories.",
+        "type": "sequence",
+        "labels": {
+            0: ("biology", "🧬"), 1: ("business", "💼"), 2: ("chemistry", "🧪"),
+            3: ("computer science", "💻"), 4: ("economics", "📈"), 5: ("engineering", "⚙️"),
+            6: ("health", "🏥"), 7: ("history", "📜"), 8: ("law", "⚖️"),
+            9: ("math", "🔢"), 10: ("other", "📦"), 11: ("philosophy", "🤔"),
+            12: ("physics", "⚛️"), 13: ("psychology", "🧠"),
+        },
+        "examples": [
+            "What is photosynthesis and how does it work?",
+            "Explain the concept of supply and demand in economics",
+            "What are the key principles of contract law?",
+            "How do neural networks learn from data?",
+        ],
+    },
     "🛡️ Fact Check": {
         "id": "LLM-Semantic-Router/halugate-sentinel",
         "description": "Determines whether a prompt requires external factual verification.",
@@ -29,24 +47,6 @@ MODELS = {
             "What's the weather like today?",
         ],
     },
-    "📚 Category Classifier": {
-        "id": "LLM-Semantic-Router/category_classifier_modernbert-base_model",
-        "description": "Classifies prompts into academic/professional categories.",
-        "type": "sequence",
-        "labels": {
-            0: ("biology", "🧬"), 1: ("business", "💼"), 2: ("chemistry", "🧪"),
-            3: ("computer science", "💻"), 4: ("economics", "📈"), 5: ("engineering", "⚙️"),
-            6: ("health", "🏥"), 7: ("history", "📜"), 8: ("law", "⚖️"),
-            9: ("math", "🔢"), 10: ("other", "📦"), 11: ("philosophy", "🤔"),
-            12: ("physics", "⚛️"), 13: ("psychology", "🧠"),
-        },
-        "examples": [
-            "What is photosynthesis and how does it work?",
-            "Explain the concept of supply and demand in economics",
-            "What are the key principles of contract law?",
-            "How do neural networks learn from data?",
-        ],
-    },
     "🔒 PII Detector": {
         "id": "LLM-Semantic-Router/pii_classifier_modernbert-base_model",
         "description": "Detects the primary type of PII in the text.",
@@ -190,17 +190,14 @@ def main():
     st.subheader("📝 Input")
     text_input = st.text_area("Enter text to analyze:", height=120, placeholder="Type your text here...", key="input_area")
 
-    # Examples section - clickable buttons
+    # Examples section - clickable buttons with actual content
     st.markdown("**💡 Try an example:**")
-    example_cols = st.columns(len(model_config["examples"]))
-    for i, (col, example) in enumerate(zip(example_cols, model_config["examples"])):
-        with col:
-            if st.button(f"Example {i+1}", key=f"ex_{i}", use_container_width=True, help=example):
-                st.session_state.text_input = example
-                st.rerun()
-
-    # Show example text preview
-    st.caption("Hover over buttons to preview examples")
+    for i, example in enumerate(model_config["examples"]):
+        # Truncate long examples for button display
+        display_text = example if len(example) <= 60 else example[:57] + "..."
+        if st.button(display_text, key=f"ex_{i}", use_container_width=True):
+            st.session_state.text_input = example
+            st.rerun()
 
     st.markdown("---")