zdeveloper commented 2 months ago

Pull Request

Description

Create a docker container for the OCR API

Related Issues

180

Additional Notes

Note first run will take a while to download the huggingface models (1.5GB), I tired to incorporate that into the image building step by using the huggingface cli, sadly I needed an API key for that, will have to delay that for a dedicated story.

RUN pip install "huggingface_hub[cli]"
RUN huggingface-cli download microsoft/trocr-large-printed

Checklist

to test the container, build and run with the following commands

docker build -t ocr .
docker run -p 8000:8000 ocr

then access on http://localhost:8000/docs

Please review and complete the following checklist before submitting your pull request:

[ ] I have ensured that the pull request is of a manageable size, allowing it to be reviewed within a single session.
[ ] I have reviewed my changes to ensure they are clear, concise, and well-documented.
[ ] I have updated the documentation, if applicable.
[ ] I have added or updated test cases to cover my changes, if applicable.
[ ] I have minimized the number of reviewers to include only those essential for the review.
[ ] I have notified teammates in the review thread to build awareness.

Checklist for Reviewers

Please review and complete the following checklist during the review process:

[ ] The code follows best practices and conventions.
[ ] The changes implement the desired functionality or fix the reported issue.
[ ] The tests cover the new changes and pass successfully.
[ ] Any potential edge cases or error scenarios have been considered.

schreiaj commented 2 months ago

For bundling the model weights into the Docker image - you could use the cache_dir into a local directory and then copy that in as part of the docker build step with a simple COPY command. As best as I can tell this does not violate any terms of service with HuggingFace.