Parallelizing Computer Vision 3.2 Read Container

CoreyK-2554 20 Reputation points
2024-04-03T13:53:02.7966667+00:00

Hello,

Our team is using the Computer Vision 3.2 Read container. Is it possible to parallelize the processing of multiple documents/pages within a single container, or would we be required to run concurrent containers equal to the desired number of documents/pages to be run in parallel?

Thanks,

Corey

Azure Computer Vision
Azure Computer Vision
An Azure artificial intelligence service that analyzes content in images and video.
338 questions
{count} votes

Accepted answer
  1. dupammi 7,955 Reputation points Microsoft Vendor
    2024-04-04T04:51:36.62+00:00

    Hi @CoreyK-2554

    Thank you for the question.

    Please refer this doc for several traditional/advanced methods or approaches for parallelism discussed.

    As per the official documentation, it is feasible to parallelize processing of multiple documents/pages in Computer Vision 3.2 Read container. Deploy multiple v3 containers behind a load balancer and let the containers share a universal storage and queue to achieve page level parallelism.

    Currently only Azure Storage and Azure Queue are supported.

    The throughput can be improved, depending on the number of containers that are deployed.

    Refer to the documentation for more information.

    Hope the above approaches and provided information helps.

    Thank you.


    If this answers your query, do click Accept Answer and Yes for was this answer helpful.

    1 person found this answer helpful.
    0 comments No comments

0 additional answers

Sort by: Most helpful