Skip to content

feat/chunking by page #3613

Open
Open
@saeedesmaili

Description

@saeedesmaili

It's nice that we have the option to chunk by title, and the multipage_sections=False allows us to consider a page break as a new chunk.

But it would be great to have the option to only chunk by page. So if we have a document as following:

[page 1]
## title
text

## title 2
text
[page 2]
## title 3
text

The chunking by page would split the above document into two chunks (one chunk for each page). I believe it is not possible to achieve this currently.

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions