diff --git a/pilot/out_parser/base.py b/pilot/out_parser/base.py
index 72868cf4d..46a7dde8b 100644
--- a/pilot/out_parser/base.py
+++ b/pilot/out_parser/base.py
@@ -53,9 +53,11 @@ class BaseOutputParser(ABC):
         """
         if data["error_code"] == 0:
             if "vicuna" in CFG.LLM_MODEL:
-                output = data["text"][skip_echo_len + 11:].strip()
+                # output = data["text"][skip_echo_len + 11:].strip()
+                output = data["text"][skip_echo_len:].strip()
             elif "guanaco" in CFG.LLM_MODEL:
-                output = data["text"][skip_echo_len + 14:].replace("<s>", "").strip()
+                # output = data["text"][skip_echo_len + 14:].replace("<s>", "").strip()
+                output = data["text"][skip_echo_len:].replace("<s>", "").strip()
             else:
                 output = data["text"].strip()
 
diff --git a/pilot/scene/chat_knowledge/url/prompt.py b/pilot/scene/chat_knowledge/url/prompt.py
index 96e1ee520..38d5dfe35 100644
--- a/pilot/scene/chat_knowledge/url/prompt.py
+++ b/pilot/scene/chat_knowledge/url/prompt.py
@@ -11,7 +11,7 @@ from pilot.scene.chat_normal.out_parser import NormalChatOutputParser
 
 CFG = Config()
 
-PROMPT_SCENE_DEFINE = """A chat between a curious user and an artificial intelligence assistant, who very familiar with database related knowledge. 
+PROMPT_SCENE_DEFINE = """A chat between a curious human and an artificial intelligence assistant, who very familiar with database related knowledge. 
     The assistant gives helpful, detailed, professional and polite answers to the user's questions. """
 
 
diff --git a/pilot/source_embedding/url_embedding.py b/pilot/source_embedding/url_embedding.py
index 774f6e852..7acfaf961 100644
--- a/pilot/source_embedding/url_embedding.py
+++ b/pilot/source_embedding/url_embedding.py
@@ -5,9 +5,12 @@ from langchain.document_loaders import WebBaseLoader
 from langchain.schema import Document
 from langchain.text_splitter import CharacterTextSplitter
 
+from pilot.configs.config import Config
+from pilot.configs.model_config import KNOWLEDGE_CHUNK_SPLIT_SIZE
 from pilot.source_embedding import SourceEmbedding, register
+from pilot.source_embedding.chn_document_splitter import CHNDocumentSplitter
 
-
+CFG = Config()
 class URLEmbedding(SourceEmbedding):
     """url embedding for read url document."""
 
@@ -22,10 +25,15 @@ class URLEmbedding(SourceEmbedding):
     def read(self):
         """Load from url path."""
         loader = WebBaseLoader(web_path=self.file_path)
-        text_splitor = CharacterTextSplitter(
-            chunk_size=100, chunk_overlap=20, length_function=len
-        )
-        return loader.load_and_split(text_splitor)
+        if CFG.LANGUAGE == "en":
+            text_splitter = CharacterTextSplitter(
+                chunk_size=KNOWLEDGE_CHUNK_SPLIT_SIZE, chunk_overlap=20, length_function=len
+            )
+        else:
+            text_splitter = CHNDocumentSplitter(
+                pdf=True, sentence_size=1000
+            )
+        return loader.load_and_split(text_splitter)
 
     @register
     def data_process(self, documents: List[Document]):