Skip to content

DocumentToImageContent component #9263

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
Open
anakin87 opened this issue Apr 17, 2025 · 1 comment
Open

DocumentToImageContent component #9263

anakin87 opened this issue Apr 17, 2025 · 1 comment
Assignees
@sjrl
Labels
P1 High priority, add to the next sprint

Comments

@anakin87
Copy link
Member

We should make an additional component to FileToImageContent called DocumentToImageContent which allows passing of Document objects directly along with specifying the meta field where you'll find the image path.

An additional requirement here is that we should also support looking for a meta field called page_number. In the situation of supporting PDFs we rarely want to send the whole PDF to the vision LLM, but rather a single page (or even maybe a few pages).

Depends on #9258.

@sjrl has background on this.
@sjrl
Copy link
Contributor

sjrl commented Apr 17, 2025 •
edited
Loading

Here are the analogous components that we use in deepset

These could probably be combined so we don't need separate components for the different file types.

@sjrl sjrl mentioned this issue Apr 17, 2025
Open
@julian-risch julian-risch added P2 Medium priority, add to the next sprint if no P1 available P1 High priority, add to the next sprint and removed P2 Medium priority, add to the next sprint if no P1 available labels Apr 17, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@sjrl sjrl

Labels
P1 High priority, add to the next sprint
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@julian-risch @sjrl @anakin87