| 123456789101112131415161718192021 |
- from langchain_text_splitters import RecursiveCharacterTextSplitter
- def get_knowledge_splitter():
- """知识库文档分块器"""
- return RecursiveCharacterTextSplitter(
- chunk_size=500,
- chunk_overlap=50,
- separators=["\n\n", "\n", "。", "!", "?", ",", " ", ""],
- length_function=len,
- )
- def get_summary_splitter():
- """摘要分块器 (用于对话记忆)"""
- return RecursiveCharacterTextSplitter(
- chunk_size=1000,
- chunk_overlap=100,
- separators=["\n\n", "\n", "。", " ", ""],
- length_function=len,
- )
|