Simple web app example serving a PyTorch model using streamlit and FastAPI

Overview

streamlit-fastapi-model-serving

Simple example of usage of streamlit and FastAPI for ML model serving described on this blogpost and PyConES 2020 video.

When developing simple APIs that serve machine learning models, it can be useful to have both a backend (with API documentation) for other applications to call and a frontend for users to experiment with the functionality.

In this example, we serve an image semantic segmentation model using FastAPI for the backend service and streamlit for the frontend service. docker-compose orchestrates the two services and allows communication between them.

To run the example in a machine running Docker and docker-compose, run:

docker-compose build
docker-compose up

To visit the FastAPI documentation of the resulting service, visit http://localhost:8000 with a web browser.
To visit the streamlit UI, visit http://localhost:8501.

Logs can be inspected via:

docker-compose logs

Deployment

To deploy the app, one option is deployment on Heroku (with Dockhero). To do so:

  • rename docker-compose.yml to dockhero-compose.yml
  • create an app (we refer to its name as <my-app>) on a Heroku account
  • install locally the Heroku CLI, and enable the Dockhero plugin with heroku plugins:install dockhero
  • add to the app the DockHero add-on (and with a plan allowing enough RAM to run the model!)
  • in a command line enter heroku dh:compose up -d --app <my-app> to deploy the app
  • to find the address of the app on the web, enter heroku dh:open --app <my-app>
  • to visualize the api, visit the address adding port 8000/docs, e.g. http://dockhero-<named-assigned-to-my-app>-12345.dockhero.io:8000/docs(not https)
  • visit the address adding :8501 to visit the streamlit interface
  • logs are accessible via heroku logs -p dockhero --app <my-app>

Debugging

To modify and debug the app, development in containers can be useful (and kind of fun!).

Reusable utilities for FastAPI

Reusable utilities for FastAPI Documentation: https://fastapi-utils.davidmontague.xyz Source Code: https://github.com/dmontagu/fastapi-utils FastAPI i

David Montague 1.3k Jan 04, 2023
Fastapi-ml-template - Fastapi ml template with python

FastAPI ML Template Run Web API Local $ sh run.sh # poetry run uvicorn app.mai

Yuki Okuda 29 Nov 20, 2022
FastAPI interesting concepts.

fastapi_related_stuffs FastAPI interesting concepts. FastAPI version :- 0.70 Python3 version :- 3.9.x Steps Test Django Like settings export FASTAPI_S

Mohd Mujtaba 3 Feb 06, 2022
Hook Slinger acts as a simple service that lets you send, retry, and manage event-triggered POST requests, aka webhooks

Hook Slinger acts as a simple service that lets you send, retry, and manage event-triggered POST requests, aka webhooks. It provides a fully self-contained docker image that is easy to orchestrate, m

Redowan Delowar 96 Jan 02, 2023
MQTT FastAPI Wrapper With Python

mqtt-fastapi-wrapper Quick start Create mosquitto.conf with the following content: ➜ /tmp cat mosquitto.conf persistence false allow_anonymous true

Vitalii Kulanov 3 May 09, 2022
A simple example of deploying FastAPI as a Zeit Serverless Function

FastAPI Zeit Now Deploy a FastAPI app as a Zeit Serverless Function. This repo deploys the FastAPI SQL Databases Tutorial to demonstrate how a FastAPI

Paul Weidner 26 Dec 21, 2022
Flask-vs-FastAPI - Understanding Flask vs FastAPI Web Framework. A comparison of two different RestAPI frameworks.

Flask-vs-FastAPI Understanding Flask vs FastAPI Web Framework. A comparison of two different RestAPI frameworks. IntroductionIn Flask is a popular mic

Mithlesh Navlakhe 1 Jan 01, 2022
Prometheus exporter for metrics from the MyAudi API

Prometheus Audi Exporter This Prometheus exporter exports metrics that it fetches from the MyAudi API. Usage Checkout submodules Install dependencies

Dieter Maes 7 Dec 19, 2022
Fetching Cryptocurrency Prices from Coingecko and Displaying them on Grafana

cryptocurrency-prices-grafana Fetching Cryptocurrency Prices from Coingecko and Displaying them on Grafana About This stack consists of: Prometheus (t

Ruan Bekker 7 Aug 01, 2022
The template for building scalable web APIs based on FastAPI, Tortoise ORM and other.

FastAPI and Tortoise ORM. Powerful but simple template for web APIs w/ FastAPI (as web framework) and Tortoise-ORM (for working via database without h

prostomarkeloff 95 Jan 08, 2023
Cache-house - Caching tool for python, working with Redis single instance and Redis cluster mode

Caching tool for python, working with Redis single instance and Redis cluster mo

Tural 14 Jan 06, 2022
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
Complete Fundamental to Expert Codes of FastAPI for creating API's

FastAPI FastAPI is a modern, fast (high-performance), web framework for building APIs with Python 3 based on standard Python type hints. The key featu

Pranav Anand 1 Nov 28, 2021
API written using Fast API to manage events and implement a leaderboard / badge system.

Open Food Facts Events API written using Fast API to manage events and implement a leaderboard / badge system. Installation To run the API locally, ru

Open Food Facts 5 Jan 07, 2023
Ansible Inventory Plugin, created to get hosts from HTTP API.

ansible-ws-inventory-plugin Ansible Inventory Plugin, created to get hosts from HTTP API. Features: Database compatible with MongoDB and Filesystem (J

Carlos Neto 0 Feb 05, 2022
implementation of deta base for FastAPIUsers

FastAPI Users - Database adapter for Deta Base Ready-to-use and customizable users management for FastAPI Documentation: https://fastapi-users.github.

2 Aug 15, 2022
A rate limiter for Starlette and FastAPI

SlowApi A rate limiting library for Starlette and FastAPI adapted from flask-limiter. Note: this is alpha quality code still, the API may change, and

Laurent Savaete 562 Jan 01, 2023
Hyperlinks for pydantic models

Hyperlinks for pydantic models In a typical web application relationships between resources are modeled by primary and foreign keys in a database (int

Jaakko Moisio 10 Apr 18, 2022
Prometheus exporter for Starlette and FastAPI

starlette_exporter Prometheus exporter for Starlette and FastAPI. The middleware collects basic metrics: Counter: starlette_requests_total Histogram:

Steve Hillier 225 Jan 05, 2023
A set of demo of deploying a Machine Learning Model in production using various methods

Machine Learning Model in Production This git is for those who have concern about serving your machine learning model to production. Overview The tuto

Vo Van Tu 53 Sep 14, 2022