This project shows how to serve an ONNX-optimized image classification model as a web service with FastAPI, Docker, and Kubernetes.

Overview

Deploying ML models with FastAPI, Docker, and Kubernetes

By: Sayak Paul and Chansung Park

This project shows how to serve an ONNX-optimized image classification model as a RESTful web service with FastAPI, Docker, and Kubernetes (k8s). The idea is to first Dockerize the API and then deploy it on a k8s cluster running on Google Kubernetes Engine (GKE). We do this integration using GitHub Actions.

👋 Note: Even though this project uses an image classification its structure and techniques can be used to serve other models as well.

Deploying the model as a service with k8s

  • We decouple the model optimization part from our API code. The optimization part is available within the notebooks/TF_to_ONNX.ipynb notebook.

  • Then we locally test the API. You can find the instructions within the api directory.

  • To deploy the API, we define our deployment.yaml workflow file inside .github/workflows. It does the following tasks:

    • Looks for any changes in the specified directory. If there are any changes:
    • Builds and pushes the latest Docker image to Google Container Register (GCR).
    • Deploys the Docker container on the k8s cluster running on GKE.

Configurations needed beforehand

  • Create a k8s cluster on GKE. Here's a relevant resource.

  • Create a service account key (JSON) file. It's a good practice to only grant it the roles required for the project. For example, for this project, we created a fresh service account and granted it permissions for the following: Storage Admin, GKE Developer, and GCR Developer.

  • Crete a secret named GCP_CREDENTIALS on your GitHub repository and copy paste the contents of the service account key file into the secret.

  • Configure bucket storage related permissions for the service account:

    $ export PROJECT_ID=<PROJECT_ID>
    $ export ACCOUNT=<ACCOUNT>
    
    $ gcloud -q projects add-iam-policy-binding ${PROJECT_ID} \
        --member=serviceAccount:${ACCOUNT}@${PROJECT_ID}.iam.gserviceaccount.com \
        --role roles/storage.admin
    
    $ gcloud -q projects add-iam-policy-binding ${PROJECT_ID} \
        --member=serviceAccount:${ACCOUNT}@${PROJECT_ID}.iam.gserviceaccount.com \
        --role roles/storage.objectAdmin
    
    gcloud -q projects add-iam-policy-binding ${PROJECT_ID} \
        --member=serviceAccount:${ACCOUNT}@${PROJECT_ID}.iam.gserviceaccount.com \
        --role roles/storage.objectCreator
  • If you're on the main branch already then upon a new push, the worflow defined in .github/workflows/deployment.yaml should automatically run. Here's how the final outputs should look like so (run link):

Notes

  • Since we use CPU-based pods within the k8s cluster, we use ONNX optimizations since they are known to provide performance speed-ups for CPU-based environments. If you are using GPU-based pods then look into TensorRT.
  • We use Kustomize to manage the deployment on k8s.

Querying the API endpoint

From workflow outputs, you should see something like so:

NAME             TYPE           CLUSTER-IP     EXTERNAL-IP     PORT(S)        AGE
fastapi-server   LoadBalancer   xxxxxxxxxx   xxxxxxxxxx        80:30768/TCP   23m
kubernetes       ClusterIP      xxxxxxxxxx     <none>          443/TCP        160m

Note the EXTERNAL-IP corresponding to fastapi-server (iff you have named your service like so). Then cURL it:

curl -X POST -F [email protected] -F with_resize=True -F with_post_process=True http://{EXTERNAL-IP}:80/predict/image

You should get the following output (if you're using the cat.jpg image present in the api directory):

"{\"Label\": \"tabby\", \"Score\": \"0.538\"}"

The request assumes that you have a file called cat.jpg present in your working directory.

TODO (s)

  • Set up logging for the k8s pods.
  • Find a better way to report the latest API endpoint.

Acknowledgements

ML-GDE program for providing GCP credit support.

Comments
  • Feat/locust grpc

    Feat/locust grpc

    @deep-diver currently, the load test runs into:

    Screenshot 2022-04-02 at 10 54 26 AM

    I have ensured https://github.com/sayakpaul/ml-deployment-k8s-fastapi/blob/feat/locust-grpc/locust/grpc/locustfile.py#L49 returns the correct output. But after a few requests, I run into the above problem.

    Also, I should mention that the gRPC client currently does not take care of image resizing which makes it a bit less comparable to the REST client which handles preprocessing as well postprocessing.

    opened by sayakpaul 18
  • Setup TF Serving based deployment

    Setup TF Serving based deployment

    In this new feature, the following works are expected

    • Update the notebook Create a new notebook with the TF Serving prototype based on both gRPC(Ref) and RestAPI(Ref).

    • Update the notebook Update the newly created notebook to check the %%timeit on the TF Serving server locally.

    • Build/Commit docker image based on TF Serving base image using this method.

    • Deploy the built docker image on GKE cluster

    • Check the deployed model's performance with a various scenarios (maybe the same ones applied to ONNX+FastAPI scenarios)

    new feature 
    opened by deep-diver 11
  • Perform load testing with Locust

    Perform load testing with Locust

    Resources:

    • https://towardsdatascience.com/performance-testing-an-ml-serving-api-with-locust-ecd98ab9b7f7
    • https://microsoft.github.io/PartsUnlimitedMRP/pandp/200.1x-PandP-LocustTest.html
    • https://github.com/https-deeplearning-ai/machine-learning-engineering-for-production-public/tree/main/course4/week2-ungraded-labs/C4_W2_Lab_3_Latency_Test_Compose
    opened by sayakpaul 10
  • 4 dockerize

    4 dockerize

    fix

    • move api/utils/requirements.txt to /api
    • add missing dependency python-multipart to the requirements.txt

    add

    • Dockerfile

    Closes https://github.com/sayakpaul/ml-deployment-k8s-fastapi/issues/4

    opened by deep-diver 4
  • Deployment on GKE with GitHub Actions

    Deployment on GKE with GitHub Actions

    Closes https://github.com/sayakpaul/ml-deployment-k8s-fastapi/issues/5, https://github.com/sayakpaul/ml-deployment-k8s-fastapi/issues/7, and https://github.com/sayakpaul/ml-deployment-k8s-fastapi/issues/6.

    opened by sayakpaul 2
  • chore: refactored the colab notebook.

    chore: refactored the colab notebook.

    Just added a text cell explaining why it's better to include the preprocessing function in the final exported model. Also, added a cell to show if the TF and ONNX outputs match with np.testing.assert_allclose().

    opened by sayakpaul 2
Owner
Sayak Paul
ML Engineer at @carted | One PR at a time
Sayak Paul
Keycloak integration for Python FastAPI

FastAPI Keycloak Integration Documentation Introduction Welcome to fastapi-keycloak. This projects goal is to ease the integration of Keycloak (OpenID

Code Specialist 113 Dec 31, 2022
Basic fastapi blockchain - An api based blockchain with full functionality

Basic fastapi blockchain - An api based blockchain with full functionality

1 Nov 27, 2021
:rocket: CLI tool for FastAPI. Generating new FastAPI projects & boilerplates made easy.

Project generator and manager for FastAPI. Source Code: View it on Github Features 🚀 Creates customizable project boilerplate. Creates customizable a

Yagiz Degirmenci 1k Jan 02, 2023
FastAPI IPyKernel Sandbox

FastAPI IPyKernel Sandbox This repository is a light-weight FastAPI project that is meant to provide a wrapper around IPyKernel interactions. It is in

Nick Wold 2 Oct 25, 2021
A dynamic FastAPI router that automatically creates CRUD routes for your models

⚡ Create CRUD routes with lighting speed ⚡ A dynamic FastAPI router that automatically creates CRUD routes for your models

Adam Watkins 950 Jan 08, 2023
Easily integrate socket.io with your FastAPI app 🚀

fastapi-socketio Easly integrate socket.io with your FastAPI app. Installation Install this plugin using pip: $ pip install fastapi-socketio Usage To

Srdjan Stankovic 210 Dec 23, 2022
Prometheus exporter for several chia node statistics

prometheus-chia-exporter Prometheus exporter for several chia node statistics It's assumed that the full node, the harvester and the wallet run on the

30 Sep 19, 2022
Adds simple SQLAlchemy support to FastAPI

FastAPI-SQLAlchemy FastAPI-SQLAlchemy provides a simple integration between FastAPI and SQLAlchemy in your application. It gives access to useful help

Michael Freeborn 465 Jan 07, 2023
Opentracing support for Starlette and FastApi

Starlette-OpenTracing OpenTracing support for Starlette and FastApi. Inspired by: Flask-OpenTracing OpenTracing implementations exist for major distri

Rene Dohmen 63 Dec 30, 2022
Formatting of dates and times in Flask templates using moment.js.

Flask-Moment This extension enhances Jinja2 templates with formatting of dates and times using moment.js. Quick Start Step 1: Initialize the extension

Miguel Grinberg 358 Nov 28, 2022
FastAPI Auth Starter Project

This is a template for FastAPI that comes with authentication preconfigured.

Oluwaseyifunmi Oyefeso 6 Nov 13, 2022
Generate modern Python clients from OpenAPI

openapi-python-client Generate modern Python clients from OpenAPI 3.x documents. This generator does not support OpenAPI 2.x FKA Swagger. If you need

Triax Technologies 558 Jan 07, 2023
FastAPI framework plugins

Plugins for FastAPI framework, high performance, easy to learn, fast to code, ready for production fastapi-plugins FastAPI framework plugins Cache Mem

RES 239 Dec 28, 2022
Mixer -- Is a fixtures replacement. Supported Django, Flask, SqlAlchemy and custom python objects.

The Mixer is a helper to generate instances of Django or SQLAlchemy models. It's useful for testing and fixture replacement. Fast and convenient test-

Kirill Klenov 871 Dec 25, 2022
Farlimit - FastAPI rate limit with python

FastAPIRateLimit Contributing is F&E (free&easy) Y Usage pip install farlimit N

omid 27 Oct 06, 2022
FastAPI-PostgreSQL-Celery-RabbitMQ-Redis bakcend with Docker containerization

FastAPI - PostgreSQL - Celery - Rabbitmq backend This source code implements the following architecture: All the required database endpoints are imple

Juan Esteban Aristizabal 54 Nov 26, 2022
Ready-to-use and customizable users management for FastAPI

FastAPI Users Ready-to-use and customizable users management for FastAPI Documentation: https://fastapi-users.github.io/fastapi-users/ Source Code: ht

FastAPI Users 2.3k Dec 30, 2022
🐞 A debug toolbar for FastAPI based on the original django-debug-toolbar. 🐞

Debug Toolbar 🐞 A debug toolbar for FastAPI based on the original django-debug-toolbar. 🐞 Swagger UI & GraphQL are supported. Documentation: https:/

Dani 74 Dec 30, 2022
Asynchronous event dispatching/handling library for FastAPI and Starlette

fastapi-events An event dispatching/handling library for FastAPI, and Starlette. Features: straightforward API to emit events anywhere in your code ev

Melvin 238 Jan 07, 2023
Dead-simple mailer micro-service for static websites

Mailer Dead-simple mailer micro-service for static websites A free and open-source software alternative to contact form services such as FormSpree, to

Romain Clement 42 Dec 21, 2022