diff --git a/examples/hello_hybrid_sparse_dense.py b/examples/hello_hybrid_sparse_dense.py
index 3c30d03d1..98541c521 100644
--- a/examples/hello_hybrid_sparse_dense.py
+++ b/examples/hello_hybrid_sparse_dense.py
@@ -1,9 +1,18 @@
 # A demo showing hybrid semantic search with dense and sparse vectors using Milvus.
 # You can optionally choose to use the BGE-M3 model to embed the text as dense
-# and sparse vectors, or simply use random generated vectors as the example.
-
-# To use BGE-M3 model, you need to install the optional `model` module in pymilvus:
+# and sparse vectors, or simply use random generated vectors as an example.
+# Note that the sparse vector search feature is only available in Milvus 2.4.0 or
+# higher version. Make sure you follow https://milvus.io/docs/install_standalone-docker.md
+# to set up the latest version of Milvus in your local environment.
+
+# To connect to Milvus server, you need the python client library called pymilvus.
+# To use BGE-M3 model, you need to install the optional `model` module in pymilvus.
+# You can get them by simply running the following commands:
+# pip install pymilvus
 # pip install pymilvus[model]
+
+# If true, use BGE-M3 model to generate dense and sparse vectors.
+# If false, use random numbers to compose dense and sparse vectors.
 use_bge_m3 = True
 
 # The overall steps are as follows:
@@ -112,4 +121,4 @@ def random_embedding(texts):
 # text: Artificial intelligence was founded as an academic discipline in 1956. distance 0.016129031777381897
 
 # Drop the collection to clean up the data.
-utility.drop_collection(col_name)
\ No newline at end of file
+utility.drop_collection(col_name)