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.

Sign up for GitHub

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

Jump to bottom

[Epic] Fully Utilize Docling V2 Capabilities #374

Open

6 tasks

ktam3 opened this issue Nov 12, 2024 · 0 comments

Assignees

Labels

ktam3 commented Nov 12, 2024 •

edited by khaledsulayman

Loading

Goals:

Hierarchical Chunking
All v2 document types are supported

Tasks:

Phase 1 Code Changes to allow to get through docling
- Chunking Refactor: Always use Context-Aware Chunker #334
- Enable support for docling V2 supported filetypes #353
Phase 2 Parsing hierarchical chunking
- Dependent on Research Team
  Need to test V2 format of docling
- Use Docling v2 hierarchical chunking instead of the existing context-aware chunking implementation #350

ktam3 added the enhancement label

ktam3 assigned aakankshaduggal, bbrowning and khaledsulayman

khaledsulayman changed the title ~~Fully Utilize Docling V2 Capabilities~~ [Epic] Fully Utilize Docling V2 Capabilities

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment