Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/nitya/mslearn-contoso-chat
Training materials for running a workshop or training session for the Contoso Chat sample
https://github.com/nitya/mslearn-contoso-chat
azure azure-ai azure-samples generative-ai llmops mslearn promptflow workshop-materials
Last synced: 22 days ago
JSON representation
Training materials for running a workshop or training session for the Contoso Chat sample
- Host: GitHub
- URL: https://github.com/nitya/mslearn-contoso-chat
- Owner: nitya
- License: mit
- Created: 2024-03-15T14:36:53.000Z (8 months ago)
- Default Branch: main
- Last Pushed: 2024-03-18T13:35:19.000Z (8 months ago)
- Last Synced: 2024-10-08T07:15:02.252Z (about 1 month ago)
- Topics: azure, azure-ai, azure-samples, generative-ai, llmops, mslearn, promptflow, workshop-materials
- Homepage: https://nitya.github.io/mslearn-contoso-chat/
- Size: 9.27 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: readme.md
- Contributing: .github/CONTRIBUTING.md
- License: LICENSE
Awesome Lists containing this project
README
# Build Contoso Chat E2E with Azure AI Studio : Guided Projects
This repo contains the instructions and assets required to support a hands-on workshop or training session to build Contoso Chat - an end-to-end custom copilot application using Azure AI Studio and Prompt flow.
The content is structured as a series of **Guided Project** modules using the Microsoft Learn format for convenience. Guided projects focus help you build a solution to a real-world scenario, step-by-step. Each module is designed to be completed in a single session (30 mins), building on the previous module.
## 1 | Introduction
The workshop targets a real-world application, a customer service chat AI ([Contoso Chat](https://github.com/Azure-Samples/contoso-chat)) that implements a **conversational Q&A chatbot** experience for customers visiting their [Contoso Outdoors](https://github.com/Azure-Samples/contoso-web) website. The application sc
![End to End story](./Instructions/Media/contoso-web-app.png)
## 2 | Pre-Requisites
To complete this series of guided projects, you will need:
1. An active GitHub account - [Create a free account](https://github.com/signup)
1. An active Azure subscription - [Create a free account](https://azure.microsoft.com/free/)
1. Approved access to Azure Open AI service - [Request access here](https://aka.ms/oaiapply)Familiarity with these technologies is desirable. Usage experience is a plus.
1. Microsoft Azure Fundamentals - [Refresh your knowledge](https://learn.microsoft.com/en-us/training/courses/az-900t00#course-syllabus)
1. Microsoft Azure AI Fundamentals - [Refresh your knowledge](https://learn.microsoft.com/training/paths/get-started-with-artificial-intelligence-on-azure)
1. Microsoft Azure AI Studio (preview) - [Refresh your knowledge](https://learn.microsoft.com/training/paths/create-custom-copilots-ai-studio/)
1. Using Python & Jupyter Notebooks - [Refresh your knowledge](https://learn.microsoft.com/training/paths/beginner-python/)## 3 | Guided Projects
A _guided project_ is a learning module that guides you through a solution to a real-world use case or challenge. The module format typically involves a _preparation_ step (setup) followed a sequence of _exercises_ (tasks) to build that solution block-by-block. This workshop involves **four** guided projects:
| Project Goal | Description |
|---------|-------------|
| [Setup](./project-1/README.md) | Provision app resources with Azure AI Studio |
| [Ideation](./project-2/README.md) | Build custom copilot function with Prompt flow |
| [Iteration](./project-3/README.md) | Evaluate custom copilot for Responsible AI |
| [Operationalization:](./project-4/README.md) | Deploy copilot API, integrate with chat UI app |
|||## 4 | Related Resources
## 5 | Reporting Issues
If you encounter any issues with the content, please report them by [opening a relevant issue ](https://github.com/nitya/mslearn-contoso-chat/issues/new) in this repository. Please check existing issues to see if the problem has already been reported, to avoid duplication. If so, add any additional information you have as a comment to the existing issue, and track progress there.