diff --git a/pilot/embedding_engine/markdown_embedding.py b/pilot/embedding_engine/markdown_embedding.py
index 225cdad82..524872d1d 100644
--- a/pilot/embedding_engine/markdown_embedding.py
+++ b/pilot/embedding_engine/markdown_embedding.py
@@ -31,7 +31,7 @@ class MarkdownEmbedding(SourceEmbedding):
         loader = EncodeTextLoader(self.file_path)
 
         if CFG.LANGUAGE == "en":
-            text_splitter = CharacterTextSplitter(
+            text_splitter = RecursiveCharacterTextSplitter(
                 chunk_size=CFG.KNOWLEDGE_CHUNK_SIZE,
                 chunk_overlap=20,
                 length_function=len,
diff --git a/pilot/embedding_engine/pdf_embedding.py b/pilot/embedding_engine/pdf_embedding.py
index 3a47e115e..77ff5f2f3 100644
--- a/pilot/embedding_engine/pdf_embedding.py
+++ b/pilot/embedding_engine/pdf_embedding.py
@@ -4,7 +4,7 @@ from typing import List
 
 from langchain.document_loaders import PyPDFLoader
 from langchain.schema import Document
-from langchain.text_splitter import SpacyTextSplitter, CharacterTextSplitter, RecursiveCharacterTextSplitter
+from langchain.text_splitter import SpacyTextSplitter, RecursiveCharacterTextSplitter
 
 from pilot.configs.config import Config
 from pilot.embedding_engine import SourceEmbedding, register
@@ -34,7 +34,7 @@ class PDFEmbedding(SourceEmbedding):
         #     chunk_overlap=100,
         # )
         if CFG.LANGUAGE == "en":
-            text_splitter = CharacterTextSplitter(
+            text_splitter = RecursiveCharacterTextSplitter(
                 chunk_size=CFG.KNOWLEDGE_CHUNK_SIZE,
                 chunk_overlap=20,
                 length_function=len,
diff --git a/pilot/embedding_engine/ppt_embedding.py b/pilot/embedding_engine/ppt_embedding.py
index 2ddc583f9..c8991c36f 100644
--- a/pilot/embedding_engine/ppt_embedding.py
+++ b/pilot/embedding_engine/ppt_embedding.py
@@ -4,7 +4,7 @@ from typing import List
 
 from langchain.document_loaders import UnstructuredPowerPointLoader
 from langchain.schema import Document
-from langchain.text_splitter import SpacyTextSplitter, CharacterTextSplitter, RecursiveCharacterTextSplitter
+from langchain.text_splitter import SpacyTextSplitter,  RecursiveCharacterTextSplitter
 
 from pilot.configs.config import Config
 from pilot.embedding_engine import SourceEmbedding, register
@@ -32,7 +32,7 @@ class PPTEmbedding(SourceEmbedding):
         #     chunk_overlap=200,
         # )
         if CFG.LANGUAGE == "en":
-            text_splitter = CharacterTextSplitter(
+            text_splitter = RecursiveCharacterTextSplitter(
                 chunk_size=CFG.KNOWLEDGE_CHUNK_SIZE,
                 chunk_overlap=20,
                 length_function=len,
diff --git a/pilot/embedding_engine/url_embedding.py b/pilot/embedding_engine/url_embedding.py
index 273b5e777..587c8d913 100644
--- a/pilot/embedding_engine/url_embedding.py
+++ b/pilot/embedding_engine/url_embedding.py
@@ -3,7 +3,7 @@ from typing import List
 from bs4 import BeautifulSoup
 from langchain.document_loaders import WebBaseLoader
 from langchain.schema import Document
-from langchain.text_splitter import CharacterTextSplitter, SpacyTextSplitter, RecursiveCharacterTextSplitter
+from langchain.text_splitter import SpacyTextSplitter, RecursiveCharacterTextSplitter
 
 from pilot.configs.config import Config
 from pilot.configs.model_config import KNOWLEDGE_CHUNK_SPLIT_SIZE
@@ -27,7 +27,7 @@ class URLEmbedding(SourceEmbedding):
         """Load from url path."""
         loader = WebBaseLoader(web_path=self.file_path)
         if CFG.LANGUAGE == "en":
-            text_splitter = CharacterTextSplitter(
+            text_splitter = RecursiveCharacterTextSplitter(
                 chunk_size=CFG.KNOWLEDGE_CHUNK_SIZE,
                 chunk_overlap=20,
                 length_function=len,
diff --git a/pilot/embedding_engine/word_embedding.py b/pilot/embedding_engine/word_embedding.py
index efb337a9a..0f4732050 100644
--- a/pilot/embedding_engine/word_embedding.py
+++ b/pilot/embedding_engine/word_embedding.py
@@ -4,7 +4,7 @@ from typing import List
 
 from langchain.document_loaders import UnstructuredWordDocumentLoader
 from langchain.schema import Document
-from langchain.text_splitter import CharacterTextSplitter, SpacyTextSplitter, RecursiveCharacterTextSplitter
+from langchain.text_splitter import SpacyTextSplitter, RecursiveCharacterTextSplitter
 
 from pilot.configs.config import Config
 from pilot.embedding_engine import SourceEmbedding, register
@@ -26,7 +26,7 @@ class WordEmbedding(SourceEmbedding):
         """Load from word path."""
         loader = UnstructuredWordDocumentLoader(self.file_path)
         if CFG.LANGUAGE == "en":
-            text_splitter = CharacterTextSplitter(
+            text_splitter = RecursiveCharacterTextSplitter(
                 chunk_size=CFG.KNOWLEDGE_CHUNK_SIZE,
                 chunk_overlap=20,
                 length_function=len,