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

Gemini support for PDFs #2304

Open
rjpereira opened this issue Mar 5, 2025 · 3 comments
Open

Gemini support for PDFs #2304

rjpereira opened this issue Mar 5, 2025 · 3 comments

Comments

@rjpereira
Copy link

Apologise if this has been discussed before, but couldn't find any direct reference to the topics.

As I see from the implementation from the Gemini client, it is multimodal, support audio, video and images, but not supporting PDF blobs.
PDFs are directly supported on Gemini API with Part.from_data and respective mime type.

Doesn't seem to be something immediate to support on GeminiClient only as I guess that Message would have to be extended with more "content types".

I would like in first instance to have your opinion if you see any impediment to support PDF content, and if not if there would be someone more familiar with the framework that was interested in collaborating to add the support.

Thanks

@ysolanky
Copy link
Contributor

ysolanky commented Mar 5, 2025

Hello @rjpereira !

We plan on adding support for PDFs and other file types that are supported by Gemini. It is on our roadmap and will be released in the next ~1 week. Thank you for the feature request!

@kepler
Copy link
Contributor

kepler commented Mar 7, 2025

Hi @ysolanky ,

Would this also include support for Claude?

@ysolanky
Copy link
Contributor

Hello @rjpereira and @kepler ! I have a PR out that adds file support for both Gemini and Claude. It will most likely be a part of the release tomorrow!

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

3 participants