CIRED / CIRED/cired.digital

Optimize chunking

Open
#40 0 comments 0 reactions 0 assignees View on GitHub
enhancement
Dominant language
Python
Stars
2
Forks
0
PR merge metrics
No merged PRs in 30d

Description

Default behavior needs investigation:
- Are there nonsense chunks ?
- Do we chunk on chapters / sections / paragraphs ?
- What do we do about images and tables ?

Then optimize, depends on #47

Contributor guide

Open the contributing guide

Research direction

No files or tests are named. Start by investigating the current default chunking behavior and answer how chapters, sections, paragraphs, images, and tables should be handled; review issue #47 before proceeding. Done means the behavior is specified and the chunking approach is optimized accordingly.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
backend
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.