diff --git a/api/apps/dialog_app.py b/api/apps/dialog_app.py
index 2969c1246..b59b02638 100644
--- a/api/apps/dialog_app.py
+++ b/api/apps/dialog_app.py
@@ -38,6 +38,7 @@ def set_dialog():
     if not rerank_id: req["rerank_id"] = ""
     similarity_threshold = req.get("similarity_threshold", 0.1)
     vector_similarity_weight = req.get("vector_similarity_weight", 0.3)
+    if vector_similarity_weight is None: vector_similarity_weight = 0.3
     llm_setting = req.get("llm_setting", {})
     default_prompt = {
         "system": """你是一个智能助手，请总结知识库的内容来回答问题，请列举知识库中的数据详细回答。当所有知识库内容都与问题无关时，你的回答必须包括“知识库中未找到您要的答案！”这句话。回答需要考虑聊天历史。
diff --git a/api/utils/file_utils.py b/api/utils/file_utils.py
index a5af5edd3..ca5a16c43 100644
--- a/api/utils/file_utils.py
+++ b/api/utils/file_utils.py
@@ -156,7 +156,7 @@ def filename_type(filename):
         return FileType.PDF.value
 
     if re.match(
-            r".*\.(doc|docx|ppt|pptx|yml|xml|htm|json|csv|txt|ini|xls|xlsx|wps|rtf|hlp|pages|numbers|key|md|py|js|java|c|cpp|h|php|go|ts|sh|cs|kt|html)$", filename):
+             r".*\.(doc|docx|ppt|pptx|yml|xml|htm|json|csv|txt|ini|xls|xlsx|wps|rtf|hlp|pages|numbers|key|md|py|js|java|c|cpp|h|php|go|ts|sh|cs|kt|html)$", filename):
         return FileType.DOC.value
 
     if re.match(
diff --git a/deepdoc/parser/html_parser.py b/deepdoc/parser/html_parser.py
index 9811d131e..ac2d3ef16 100644
--- a/deepdoc/parser/html_parser.py
+++ b/deepdoc/parser/html_parser.py
@@ -1,4 +1,16 @@
 # -*- coding: utf-8 -*-
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+#
 from rag.nlp import find_codec
 import readability
 import html_text
@@ -8,7 +20,7 @@ def get_encoding(file):
     with open(file,'rb') as f:
         tmp = chardet.detect(f.read())
         return tmp['encoding']
-    
+
 class RAGFlowHtmlParser:
     def __call__(self, fnm, binary=None):
         txt = ""
@@ -18,7 +30,7 @@ class RAGFlowHtmlParser:
         else:
             with open(fnm, "r",encoding=get_encoding(fnm)) as f:
                 txt = f.read()
-            
+
         html_doc = readability.Document(txt)
         title = html_doc.title()
         content = html_text.extract_text(html_doc.summary(html_partial=True))
diff --git a/rag/app/book.py b/rag/app/book.py
index e0a1f9ffb..d969ccf92 100644
--- a/rag/app/book.py
+++ b/rag/app/book.py
@@ -135,7 +135,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
                   for ck in hierarchical_merge(bull, sections, 5)]
     else:
         sections = [s.split("@") for s, _ in sections]
-        sections = [(pr[0], "@" + pr[1]) for pr in sections if len(pr) == 2]
+        sections = [(pr[0], "@" + pr[1]) if len(pr) == 2 else (pr[0], '') for pr in sections ]
         chunks = naive_merge(
             sections, kwargs.get(
                 "chunk_token_num", 256), kwargs.get(