HTTP请求触发的Python脚本的基础结构 [英] Infrastructure for a Python script triggered by a http request
问题描述
我在文档,报价和服务的丛林中迷失了.我对基础架构的外观一无所知,因此将其推向正确的方向将非常有帮助.
I'm a bit lost in the jungle of documentation, offers, and services. I'm clueless on how the infrastructure should look like, and it would be very helpful to get a nudge in the right direction.
我们有一个带有pytorch的python脚本,可以运行预测.该脚本必须从http请求中触发.优选地,要进行预测的样本也必须来自同一请求者.它必须尽快返回预测.
We have a python script with pytorch that runs a prediction. The script has to be triggered from a http request. Preferably, the samples to do a prediction on also has to come from the same requester. It has to return the prediction as fast as possible.
什么是最好/最容易/最快的方法?
What is the best / easiest / fastest way of doing this?
我们现在将脚本放置在Container Registry中.使用Docker容器并将其放置在某处是一种明智的策略吗? Azure Kubernetes服务? Azure容器实例(足够快)吗?触发器,Azure函数还是逻辑应用程序?
We have the script laying in a Container Registry for now. Is using a Docker container and putting it somewhere a smart strategy? Azure Kubernetes Service? Azure Container Instances (is this fast enough)? Trigger, Azure function, or logic app?
谢谢!
推荐答案
由于此问题与机器学习无关,因此我将其移至适当的子论坛以寻求更好的帮助.感谢您在这里的反馈.
Since this issue is not related to Machine Learning, I will move it to the proper sub-forum for better help. Thanks for your feedback here.
此致
雨桐
这篇关于HTTP请求触发的Python脚本的基础结构的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!