AI Deploy - Portfolio d'app (EN)

Une collection d'apps d'AI pouvant être facilement déployées avec AI Deploy

Last updated 1st December, 2022.

AI Deploy is in beta. During the beta-testing phase, the infrastructure’s availability and data longevity are not guaranteed. Please do not use this service for applications that are in production, as this phase is not complete.

AI Deploy is covered by OVHcloud Public Cloud Special Conditions.

Objective

AI Deploy allows you to deploy AI apps or models. To test or use the product, you can build on existing AI models.

For example, you can rely on open-source models or apps.

Portfolio of AI apps and models

To test AI Deploy, you can quickly deploy apps based on those proposed in our portfolio.

Quick examples

Owner Task Description Documentation Dockerfile Docker image HTTP port CLI command Usage
OVHcloud Hello world Launch your first API with Flask AI Deploy - Getting started Dockerfile - Hello world priv-registry.gra.training.ai.cloud.ovh.net/ai-deploy-portfolio/ai-deploy-hello-world 5000 ovhai app run --default-http-port 5000 priv-registry.gra.training.ai.cloud.ovh.net/ai-deploy-portfolio/ai-deploy-hello-world API - interact with the API with a curl command or a Python script
OVHcloud EDA and interactive prediction Explore, analyse iris data and do interactive prediction with Streamlit AI Deploy - Tutorial - Deploy an interactive app for EDA and prediction using Streamlit Dockerfile - EDA and prediction on iris data priv-registry.gra.training.ai.cloud.ovh.net/ai-deploy-portfolio/streamlit-eda 8501 ovhai app run --default-http-port 8501 priv-registry.gra.training.ai.cloud.ovh.net/ai-deploy-portfolio/streamlit-eda Web interface - access to the app with the url
OVHcloud Sketch recognition Recognize handwritten digits with Gradio AI Deploy - Tutorial - Deploy a Gradio app for sketch recognition Dockerfile - Sketch recognition priv-registry.gra.training.ai.cloud.ovh.net/ai-deploy-portfolio/gradio-sketch-recognition 8080 (default) ovhai app run priv-registry.gra.training.ai.cloud.ovh.net/ai-deploy-portfolio/gradio-sketch-recognition Web interface - access to the app with the url
OVHcloud Spam classification Classify spam messages with FastAPI AI Deploy - Tutorial - Deploy and call a spam classifier with FastAPI Dockerfile - Spam classifier API priv-registry.gra.training.ai.cloud.ovh.net/ai-deploy-portfolio/fastapi-spam-classification 8000 ovhai app run --default-http-port 8000 priv-registry.gra.training.ai.cloud.ovh.net/ai-deploy-portfolio/fastapi-spam-classification API - interact with the API with <app-url>/docs or curl command
OVHcloud Sentiment analysis Analyse text sentiment with Hugging Face models and Flask AI Deploy - Tutorial - Deploy an app for sentiment analysis with Hugging Face and Flask Dockerfile - Sentiment analysis Hugging Face app priv-registry.gra.training.ai.cloud.ovh.net/ai-deploy-portfolio/flask-sentiment-analysis 5000 ovhai app run --default-http-port 5000 priv-registry.gra.training.ai.cloud.ovh.net/ai-deploy-portfolio/flask-sentiment-analysis Web interface - access to the app with the url

If you want to launch these apps from the OVHcloud control panel:

  1. fill in the name of the docker image in Step 2 - Application to deploy
  2. set the HTTP port in Step 5 - Configure your app

Build you own apps and models to deploy

Below are examples of existing models that can be deployed with AI Deploy. However, you are free to deploy any other AI model or app of your choice.

YOLO

YOLO ('You only look once'), is an Object Detection algorithms family.

References:

DALL-E mini

DALL-E mini is an AI model that can draw images from any text prompt (Text-to-Image).

References:

Stable Diffusion

Stable Diffusion is Text-to-Image model that generates images from text.

References:

EfficientNet

EfficientNet is a family of Image Classification models. There are eight different EfficientNet models (b0 -> b7)

References:

ResNet

ResNet are AI models based residual neural network whose aim is to solve Image Classification tasks.

References:

MobileNet V2

MobileNet are Computer Vision models designed to be used in mobile applications. They are known for their small size and low latency.

References:

GPT-2

GPT-2 is a Text Generation model developed by Open AI.

References:

BERT

Famous NLP models based on BERT can also be deployed for Text Classification for example.

References:

BART

BART-based models can also be deployed for Zero-Shot Classification tasks.

References:

Go further

You can also refer to our GitHub repository to find examples of AI apps to deploy.

You will find all the codes and documentation needed to deploy each app here.

Here are some examples of AI apps we propose:

  • Deploy an app for audio classification task using Streamlit
  • Deploy a web service for YOLOv5 using Flask
  • Deploy a Gradio app for sketch recognition
  • Deploy an app for sentiment analysis with Hugging Face models using Flask
  • Deploy an interactive app for EDA and prediction using Streamlit
  • Deploy and call a spam classifier with FastAPI

Feedback

Please feel free to send us your questions, feedback and suggestions to help our team improve the service on the OVHcloud Discord server


Cette documentation vous a-t-elle été utile ?

N’hésitez pas à nous proposer des suggestions d’amélioration afin de faire évoluer cette documentation.

Images, contenu, structure… N’hésitez pas à nous dire pourquoi afin de la faire évoluer ensemble !

Vos demandes d’assistance ne seront pas traitées par ce formulaire. Pour cela, utilisez le formulaire "Créer un ticket" .

Merci beaucoup pour votre aide ! Vos retours seront étudiés au plus vite par nos équipes..


Ces guides pourraient également vous intéresser...

OVHcloud Community

Accedez à votre espace communautaire. Posez des questions, recherchez des informations, publiez du contenu et interagissez avec d’autres membres d'OVHcloud Community.

Echanger sur OVHcloud Community

Conformément à la Directive 2006/112/CE modifiée, à partir du 01/01/2015, les prix TTC sont susceptibles de varier selon le pays de résidence du client
(par défaut les prix TTC affichés incluent la TVA française en vigueur).