Modify app.py with list[list] typehints

app.py

@@ -25,26 +25,19 @@ sentiment_model.eval()
 
 
 # ==============================
-# FUNCTION (SIGNATURE UNCHANGED)
-# Input: DataFrame
-# Output: DataFrame
+# CORE FUNCTION
 # ==============================
 
-def nlp_encode_sentence(df: pd.DataFrame) -> pd.DataFrame:
+def nlp_encode_sentence(values):
 
-    # Convert safely in case input is list-of-lists
-    df = pd.DataFrame(df, columns=["value"])
+    # values will be list of lists
+    df = pd.DataFrame(values, columns=["value"])
 
     feature_rows = []
 
     for sentence in df["value"]:
 
-        inputs = tokenizer(
-            sentence,
-            return_tensors="pt",
-            truncation=True,
-            padding=True
-        )
+        inputs = tokenizer(sentence, return_tensors="pt", truncation=True, padding=True)
 
         with torch.no_grad():
             outputs = bert_model(**inputs)
@@ -79,20 +72,41 @@ def nlp_encode_sentence(df: pd.DataFrame) -> pd.DataFrame:
             sentiment_score
         ])
 
-    # Return as array (important for Gradio compatibility)
     return feature_rows
 
 
 # ==============================
-# GRADIO INTERFACE
+# GRADIO APP (BLOCKS VERSION)
 # ==============================
 
-demo = gr.Interface(
-    fn=nlp_encode_sentence,
-    inputs=gr.Dataframe(type="array"),
-    outputs=gr.Dataframe(type="array"),
-    api_name="encode"
-)
+with gr.Blocks() as demo:
+    gr.Markdown("### NLP Encoder")
+
+    input_data = gr.Dataframe(
+        headers=["value"],
+        datatype=["str"],
+        type="array"
+    )
+
+    output_data = gr.Dataframe(
+        headers=[
+            "embedding_mean",
+            "embedding_median",
+            "embedding_std",
+            "embedding_min",
+            "embedding_max",
+            "sentiment_score"
+        ],
+        type="array"
+    )
+
+    btn = gr.Button("Run")
+
+    btn.click(
+        fn=nlp_encode_sentence,
+        inputs=input_data,
+        outputs=output_data
+    )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()