Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[REQUEST] How to split chunks without cutting the table in half? #466

Open
QuangTQV opened this issue Nov 5, 2024 · 1 comment
Open
Labels
enhancement New feature or request

Comments

@QuangTQV
Copy link

QuangTQV commented Nov 5, 2024

Reference Issues

No response

Summary

The table is already very difficult to read for LLM, but when chunking it also loses the integrity of the table (the table is divided into many parts) causing LLM illusion, for example in pdf, word, how to fix it?

Basic Example

for example pdf has a lot of tables, chunking will split the table into many parts, losing the context of the table

Drawbacks

None

Additional information

No response

@vap0rtranz
Copy link

Docs the Docling file handler solve this problem?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

2 participants