Giter Club home page Giter Club logo

aca-dapr-openai-workshop's Introduction

Summarizer using Azure Open AI

Open in GitHub Codespaces

Hands-on-guide : https://aka.ms/aca-dapr-workshop

Welcome to this Dapr, Azure Container Apps Workshop. You'll be experimenting with Azure Serverless services in multiple labs to achieve a real world scenario. Don't worry, even if the challenges will increase in difficulty, this is a step by step lab, you will be guided through the whole process.

During this workshop you will have the instructions to complete each steps. It is recommended to search for the answers in provided resources and links before looking at the solutions placed under the 'Toggle solution' panel.

Prerequisites

Before starting this workshop, be sure you have:

  • An existing subscription with owner rights with rights to provision Azure Open AI resources.
    • If you don't have an Azure subscription, create a free account before you begin.
    • You can request access to Azure Open AI here
  • Azure providers should be registerd on your Azure Subscription if not done yet: Microsoft.CognitiveServices, Microsoft.DocumentDB, Microsoft.ContainerRegistry, Microsoft.KeyVault, Microsoft.ServiceBus,Microsoft.Web

Link Summarizer

Link Summarizer is an application designed to demonstrates how to build a, intelligent cloud native application using Dapr, Containers Apps and Open AI. It is composed of multiple microservices.

SummarizeArchitecture

Summarizer Blazor App (Front-end) : A Blazor WebAssembly application that allows to browse all summaries and eventually queue new links to be summarized.

SummarizeWeb

Requests API (Python) : FastAPI leveraging Dapr state management to store / get all requests of summaries. It allows to track and reuse previous summaries eventually generated. When a new completed request is created following processing, it sends a email message to the requestor.

Requests Processor (Python) : A Python application that allows to process summary requests in queue. If no summary has already being provided, it will prompt Azure Open AI to get a new summary. In any case, requests will be tracked using the requests API at the end of the process.

How to install

1. Open the solution using GitHub Codespaces

Open in GitHub Codespaces

2. Review the file at ./infra/setup.sh and set the global variable

export RESOURCE_GROUP=rg-summarizer>
export WORKLOAD_NAME=summarizer
export ENVIRONMENT=dev
export UNIQUE_ID=01

2. Deploy the application

az login
cd infra
./setup.sh

3. Review resources

SummarizeArchitecture

aca-dapr-openai-workshop's People

Contributors

reidav avatar azuredevmuc avatar

Stargazers

Thomas Zühlke avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.