Will this project currently support image and PDF URL parsing functionality?
Will this project currently support image and PDF URL parsing functionality? https://docs.anthropic.com/en/release-notes/api
So far, openAI only supports text, image, or audio inputs. To ensure the compatibility, I would take this as a low priority one.
One thing you can try is to maybe create screenshot of the pdf pages and then use the image input. But not an effective way though, especially for large number of pages.
The recommended way is to use AWS SDK directly to get all features from Amazon Bedrock.
Thank you for your reply. I've noticed that there seems to be a blocking issue with this project—when a non-streaming request is made, other streaming requests get disconnected.