Refactor:remove use less convert for FastEmbed (#8984)

### What problem does this PR solve?

remove use less convert for FastEmbed

### Type of change

- [x] Refactoring

rag/llm/embedding_model.py

         # Using the internal tokenizer to encode the texts and get the total
         # number of tokens
         encoding = self._model.model.tokenizer.encode(text)
-        embedding = next(self._model.query_embed(text)).tolist()
-
+        embedding = next(self._model.query_embed(text))
         return np.array(embedding), len(encoding.ids)