-
Notifications
You must be signed in to change notification settings - Fork 266
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
Add DocQA Tool #330
Add DocQA Tool #330
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
lgtm
'label': table', | ||
'order': 1119, | ||
'caption': [{'Column 1': 'Value 1', 'Column 2': 'Value 2'}, | ||
'summary': 'This table illustrates a trend of ...'}, | ||
], | ||
",document_extraction | ||
"'document_qa' is a tool that can answer any questions about arbitrary documents, presentations, or tables. It's very useful for document QA tasks, you can ask it a specific question or ask it to return a JSON object answering multiple questions about the document.","document_qa(prompt: str, image: numpy.ndarray) -> str: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
would it be better to not use "QA" and instead use "question answering"? i know that changing this would require new benchmarking runs, so no need to address it right now, but maybe for the future.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Like call the tool document_question_answering
instead of document_qa
? I think in this case it's fine, it seems to understand QA pretty well
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM!
Adds a couple things: