Skip to content
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.

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

Cookbook for DSPy with multimodal support #1721

Closed
Ranking666 opened this issue Oct 30, 2024 · 8 comments
Closed

Cookbook for DSPy with multimodal support #1721

Ranking666 opened this issue Oct 30, 2024 · 8 comments
Assignees

Comments

@Ranking666
Copy link

Are there any examples that support local multimodal large models? Including data format, model loading method

@pavan4
Copy link

pavan4 commented Oct 30, 2024

Check #1495

@Ranking666
Copy link
Author

Is there a complete example?

@isaacbmiller
Copy link
Collaborator

For now there isn't a great cookbook. MMMU.ipynb shows the basics.

I am working on a better cookbook. If there is something in particular you want to see let me know and I can see how to fit it in

@isaacbmiller isaacbmiller changed the title DSPy with multimodal support Cookbook for DSPy with multimodal support Nov 1, 2024
@isaacbmiller isaacbmiller self-assigned this Nov 1, 2024
@thiccvitalik
Copy link

An example with a list of input images, where the list size can vary, would be great.

@isaacbmiller
Copy link
Collaborator

What's the downstream use case here? (Not disagreeing just curious)

@thiccvitalik
Copy link

My use case is multi-page PDFs where the number of pages can vary, so I can’t predetermine a fixed number of input images (I convert multiple pages to a single image, but this still requires a flexible list size).

@jkpjkpjkp
Copy link

jkpjkpjkp commented Dec 13, 2024

hi! am very curious about the followups on this one. did you solve it?

upd: i found this '#1801' and '#1763', the former being a work-in-progress and the latter handles the list case. will try them out. cheers~

upd2: pr/1801 worked like a charm. 1763 has issues when merged into latest.

@okhat
Copy link
Collaborator

okhat commented Dec 17, 2024

@jkpjkpjkp You don't need any PRs for multi-modal support now. It's merged in the library.

@okhat okhat closed this as completed Dec 17, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

6 participants