mirror of
https://github.com/langchain-ai/docs.git
synced 2026-08-27 02:41:59 -04:00
13 lines
410 B
Plaintext
13 lines
410 B
Plaintext
```python
|
|
from langchain_text_splitters import RecursiveCharacterTextSplitter
|
|
|
|
text_splitter = RecursiveCharacterTextSplitter(
|
|
chunk_size=1000, # chunk size (characters)
|
|
chunk_overlap=200, # chunk overlap (characters)
|
|
add_start_index=True, # track index in original document
|
|
)
|
|
all_splits = text_splitter.split_documents(docs)
|
|
|
|
print(f"Split blog post into {len(all_splits)} sub-documents.")
|
|
```
|