Replies: 1 comment
-
@harskuma did you find a workaround ? |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Hi everyone,
I’m currently using Docling’s HybridChunker for chunking PDF documents. I understand that it follows hierarchical chunking, which generally works well. However, I’ve noticed that some chunks end up being too small, especially for PDFs.
To address this, I’ve already tried:
Setting
max_tokens
to control chunk size.merge_peers=True
Despite these adjustments, I’m still seeing some very small chunks in the output.
Is there any other approach or parameter tweak that could help ensure more consistent chunk sizes, while still maintaining the hierarchical structure?
Would appreciate any suggestions or insights!
Beta Was this translation helpful? Give feedback.
All reactions