loaded model using AutoModel and manual pooling

app.py

@@ -55,13 +55,13 @@ def get_embedding(request: EmbedRequest):
     try:
         encoded_input = tokenizer(request.text, padding=True, truncation=True, return_tensors='pt').to(device)
         model_output = model(**encoded_input)
-        embedding=model.encode(request.text).tolist()
+        # embedding=model.encode(request.text).tolist()
         sentence_embedding = mean_pooling(model_output, encoded_input['attention_mask'])
         
         normalized_embedding = F.normalize(sentence_embedding, p=2, dim=1)
         
         embedding_list = normalized_embedding[0].tolist()
-        return EmbedResponse(embedding=embedding)
+        return EmbedResponse(embedding=embedding_list)
     except Exception as e:
         logger.error("Error during embedding generation %s",e)
         return HTTPException(status_code=500,detail="Error generating embeddings")