Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
As mentioned here (#5675), a tool for OCR of images was added whose output preserves the text in the format of the source image. Its accuracy is higher than using LLM (Vison) to extract text in band format, with significantly fewer illusions.
Example1:
Extracting the value of loss from a screenshot of a machine learning training and plotting a line graph
2024-06-29.22-09-40.mp4
Example2:
Extract maths questions, give them to multiple LLMs (even non-version ones) to answer, and subsequently aggregate them
2024-06-29.21-27-47.mp4
Type of Change
Please delete options that are not relevant.
How Has This Been Tested?
Created several new workflow tests using this new tool and ran several tests in the workflow using its supported image formats (png/jpg)
Suggested Checklist:
dev/reformat
(backend) andcd web && npx lint-staged
(frontend) to appease the lint godsoptional
I have made corresponding changes to the documentationoptional
I have added tests that prove my fix is effective or that my feature worksoptional
New and existing unit tests pass locally with my changes