Update app.py

app.py

@@ -45,6 +45,7 @@ def compute_embeddings(*input_texts):
     batch_dict = tokenizer(processed_texts, max_length=max_length - 1, return_attention_mask=False, padding=False, truncation=True)
     batch_dict['input_ids'] = [input_ids + [tokenizer.eos_token_id] for input_ids in batch_dict['input_ids']]
     batch_dict = tokenizer.pad(batch_dict, padding=True, return_attention_mask=True, return_tensors='pt')
+    batch_dict = {k: v.to(device) for k, v in batch_dict.items()}
     outputs = model(**batch_dict)
     embeddings = last_token_pool(outputs.last_hidden_state, batch_dict['attention_mask'])
     embeddings = F.normalize(embeddings, p=2, dim=1)