[Feature Request] Refactor DocumentProcessingToolkit in owl and ExcelToolkit in camel
Opened this issue · 7 comments
Required prerequisites
- I have searched the Issue Tracker and Discussions that this hasn't already been reported. (+1 or comment there if it has.)
- Consider asking first in a Discussion.
Motivation
move DocumentProcessingToolkit to camel, move feature in ExcelToolkit to DocumentProcessingToolkit, mode robust design think consider large file and token limite
Solution
No response
Alternatives
No response
Additional context
No response
hi
thank you, hope this implement soon
who's assigned to this?
hey @GitHoobar , seems this issue is not taken, or would @mahdiidham3837 interested in this?
id love to help here, but slightly unclear on the large file and token limitation, is this because currently large files are not handled well?
hey @JINO-ROHIT , yes the current implementation doesn't support large file well and has low efficiency, like for excel toolkit, we can add support to just extract the naming of rows, or top k first rows to reduce token consume
alrightyy, picking this