1.1 | What You'll Learn
This is a 60-75 minute workshop that consists of a series of lab exercises that teach you how to build a production RAG (Retrieval Augmented Generation) based LLM application using Promptflow and Azure AI Studio.
You'll gain hands-on experience with the various steps involved in the end-to-end application development lifecycle from prompt engineering to LLM Ops.
Learning Objectives
By the end of this lab, you should be able to:
- Explain LLMOps - concepts & differentiation from MLOps.
- Explain Prompt Flow - concepts & tools for building LLM Apps.
- Explain Azure AI Studio - features & functionality for streamlining E2E app development.
- Design, run & evaluate RAG apps - using the Promptflow Extension on VS Code
- Deploy, test & use RAG apps - from Azure AI Studio UI (no code experience)
Pre-Requisites
We assume you have familiarity with the following:
- Machine Learning & Generative AI concepts
- Python & Jupyter Notebook programming
- Azure, GitHub & Visual Studio Code tooling
You will need the following to complete the lab:
- Your own laptop (charged) with a modern browser
- A GitHub account with GitHub Codespaces quota.
- An Azure subscription with Azure OpenAI access.
- An Azure AI Search resource with Semantic Ranker enabled.
Dev Environment
You'll make use of the following resources in this workshop:
Code Samples (GitHub Repositories)
- Contoso Chat - source code for the RAG-based LLM app.
- Contoso Web - source code for the Next.js-based Web app.
Developer Tools (local and cloud)
- Visual Studio Code - as the default editor
- Github Codespaces - as the dev container
- Azure AI Studio (Preview) - for AI projects
- Azure ML Studio - for minor configuration
- Azure Portal - for managing Azure resources
- Prompt Flow - for streamlining end-to-end LLM app dev
Azure Resources (Provisioned in Subscription)
- Azure AI Resource - top-level AI resource, provides hosting environment for apps
- Azure AI Project - organize work & save state for AI apps.
- Azure AI Search - full-text search, indexing & information retrieval. (product data)
- Azure OpenAI Service - chat completion & text embedding models. (chat UI, RAG)
- Azure Cosmos DB - globally-distributed multi-model database. (customer data)
- Azure Static Web Apps - optional, deploy Contoso Web application. (chat integration)
===