fix: limit token lengths

app.py

@@ -56,7 +56,7 @@ def vectorize_dataset(split: str, column: str):
     global df
     global ds
     df = ds[split].to_polars()
-    embeddings = model.encode(df[column], max_length=512 * 4)
+    embeddings = model.encode(df[column], max_length=512)
     df = df.with_columns(pl.Series(embeddings).alias("embeddings"))
 
 
@@ -153,4 +153,5 @@ with gr.Blocks() as demo:
     )
 
     btn_run.click(fn=run_query, inputs=query_input, outputs=results_output)
+
 demo.launch()