Update readme

Signed-off-by: Jael Gu <mengjia.gu@zilliz.com>

README.md

@@ -7,7 +7,7 @@
 ## Description
 
 A text embedding operator takes a sentence, paragraph, or document in string as an input
-and output an embedding vector in ndarray which captures the input's core semantic elements.
+and outputs token embeddings which captures the input's core semantic elements.
 This operator is implemented with pre-trained models from [Huggingface Transformers](https://huggingface.co/docs/transformers).
 
 <br />
@@ -329,18 +329,12 @@ If None, the operator will use default tokenizer by `model_name` from Huggingfac
 
 <br />
 
-***return_sentence_emb***: *bool*
-
-The flag to output a sentence embedding for each text, defaults to True.
-If False, the operator returns token embeddings for each text.
-
-<br />
 
 ## Interface
 
 The operator takes a piece of text in string as input.
 It loads tokenizer and pre-trained model using model name.
-and then return text embedding in ndarray.
+and then return text embedding(s) in ndarray.
 
 ***\_\_call\_\_(txt)***
 
@@ -349,8 +343,8 @@ and then return text embedding in ndarray.
 ***data***: *Union[str, list]*
 
 ​	The text in string or a list of texts.
-If data is string, the operator returns embedding(s) in ndarray.
-If data is a list, the operator returns embedding(s) in a list.
+If data is string, the operator returns token embedding(s) in ndarray.
+If data is a list, the operator returns token embedding(s) in a list.
 
 **Returns**: