🔹 2. TextSplitter(文本切块器)
| 功能 | 将长文档切成小块(便于向量化) |
| 推荐类 |
RecursiveCharacterTextSplitter(优先) |示例:
python 复制编辑 from langchain.text_splitter import RecursiveCharacterTextSplitter splitter = RecursiveCharacterTextSplitter( chunk_size=500, chunk_overlap=50 ) chunks = splitter.split_documents(docs)
✅ Best Practice:chunk_size 通常设置为 300–800,overlap 设置为 10–100,依任务灵活调整