add chunker
This commit is contained in:
+12
@@ -0,0 +1,12 @@
|
||||
from langchain_text_splitter import RecursiveCharacterTextSplitter
|
||||
|
||||
def get_chunks(content, title):
|
||||
splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
|
||||
texts = splitter.split_text(content)
|
||||
return [
|
||||
{
|
||||
"page_content": t,
|
||||
"metadata": {"title": title}
|
||||
}
|
||||
for t in texts
|
||||
]
|
||||
Reference in New Issue
Block a user