diff --git a/assets/wechat.jpg b/assets/wechat.jpg
index af45cab08..6f985e8e8 100644
Binary files a/assets/wechat.jpg and b/assets/wechat.jpg differ
diff --git a/docs/docs/application/started_tutorial/chat_knowledge.md b/docs/docs/application/started_tutorial/chat_knowledge.md
index 5fd72eda3..4d4c57652 100644
--- a/docs/docs/application/started_tutorial/chat_knowledge.md
+++ b/docs/docs/application/started_tutorial/chat_knowledge.md
@@ -56,6 +56,23 @@ and click Process, it will take a few minutes to complete the document segmentat
   <img src={'/img/chat_knowledge/doc_segmentation.png'} width="720px" />
 </p>
 
+:::tip
+**Automatic: The document is automatically segmented according to the document type.**
+
+**Chunk size: The number of words in each segment of the document. The default is 512 words.**
+    - chunk size: The number of words in each segment of the document. The default is 512 words.
+    - chunk overlap: The number of words overlapped between each segment of the document. The default is 50 words.
+** Separator:segmentation by separator ** 
+    - separator: The separator of the document. The default is `\n`.
+    - enable_merge: Whether to merge the separator chunks according to chunk_size after splits. The default is `False`.
+** Page: page segmentation, only support .pdf and .pptx document.**
+
+** Paragraph: paragraph segmentation, only support .docx document.**
+    - separator: The paragraph separator of the document. The default is `\n`.
+
+** Markdown header: markdown header segmentation, only support .md document.**
+:::
+
 
 ### Waiting for document vectorization
 
diff --git a/setup.py b/setup.py
index fafd2da51..b4b931749 100644
--- a/setup.py
+++ b/setup.py
@@ -638,7 +638,7 @@ def init_install_requires():
 setuptools.setup(
     name="db-gpt",
     packages=find_packages(exclude=("tests", "*.tests", "*.tests.*", "examples")),
-    version="0.4.4",
+    version="0.4.5",
     author="csunny",
     author_email="cfqcsunny@gmail.com",
     description="DB-GPT is an experimental open-source project that uses localized GPT large models to interact with your data and environment."