Update app.py

app.py

@@ -30,7 +30,7 @@ def extract_embeddings(batch):
     inputs = {k: tf.convert_to_tensor(v) for k, v in batch.items() if k in tokenizer.model_input_names}
     outputs = model(**inputs, output_hidden_states=True, return_dict=True)
     embeddings = outputs.last_hidden_state
-    return {"embeddings": embeddings}
+    return {"embeddings": embeddings.numpy()}  # Ensure the "embeddings" key is present
 
 # Apply the function to extract embeddings in batches
 embeddings_dataset = tokenized_datasets.map(extract_embeddings, batched=True, batch_size=batch_size)