Merge pull request #49375 from MicrosoftDocs/NEW-genaiops

New genaiops

Author: v-dirichards

learn-pr/paths/operationalize-gen-ai-apps/index.yml

@@ -0,0 +1,34 @@
+### YamlMime:LearningPath
+uid: learn.wwl.operationalize-gen-ai-apps
+metadata:
+  title: Operationalize generative AI applications (GenAIOps)
+  description: Learn how to develop, evaluate, optimize, and deploy generative AI applications (GenAIOps)
+  ms.date: 03/03/2025
+  author: wwlpublish
+  ms.author: madiepev
+  ms.topic: learning-path
+  ms.collection: wwl-ai-copilot
+  ms.custom: [copilot-learning-hub]
+title: Operationalize generative AI applications (GenAIOps) 
+prerequisites: |
+  Before starting this learning path, you should be familiar with fundamental generative AI concepts and services in Azure. Consider completing the [Microsoft Azure AI Fundamentals: Generative AI](/training/paths/introduction-generative-ai/?azure-portal=true) learning path first.
+summary: |
+  To effectively scale generative Artificial Intelligence (AI) applications, you need to manage, deploy, and maintain GenAI apps to ensure their performance, reliability, and continuous improvement in real-world applications.
+iconUrl: /training/achievements/generic-badge.svg
+levels:
+- intermediate
+roles:
+- data-scientist
+- ai-engineer
+products:
+- ai-services
+subjects:
+- artificial-intelligence
+- machine-learning
+- natural-language-processing
+modules:
+- learn.wwl.plan-prepare-genaiops
+- learn.wwl.ai-foundry-sdk
+- learn.evaluate-generative-ai-apps
+trophy:
+  uid: learn.wwl.operationalize-gen-ai-apps.trophy

learn-pr/wwl-data-ai/plan-prepare-genaiops/1-introduction.yml

@@ -0,0 +1,15 @@
+### YamlMime:ModuleUnit
+uid: learn.wwl.plan-prepare-genaiops.introduction
+title: Introduction
+metadata:
+  title: Introduction
+  description: Introduction to code-first development of generative AI applications with Azure AI Foundry.
+  author: madiepev
+  ms.author: madiepev
+  ms.date: 02/21/2025
+  ms.topic: unit
+  ms.collection:
+    - wwl-ai-copilot
+durationInMinutes: 3
+content: |
+  [!include[](includes/1-introduction.md)]

learn-pr/wwl-data-ai/plan-prepare-genaiops/2-use-cases.yml

@@ -0,0 +1,15 @@
+### YamlMime:ModuleUnit
+uid: learn.wwl.plan-prepare-genaiops.use-cases
+title: Explore use cases for GenAIOps
+metadata:
+  title: Explore use cases for GenAIOps
+  description: Explore use cases for GenAIOps.
+  author: madiepev
+  ms.author: madiepev
+  ms.date: 02/21/2025
+  ms.topic: unit
+  ms.collection:
+    - wwl-ai-copilot
+durationInMinutes: 6
+content: |
+  [!include[](includes/2-use-cases.md)]

learn-pr/wwl-data-ai/plan-prepare-genaiops/3-select-model.yml

@@ -0,0 +1,15 @@
+### YamlMime:ModuleUnit
+uid: learn.wwl.plan-prepare-genaiops.select-model
+title: Select the right generative AI model
+metadata:
+  title: Select the right generative AI model
+  description: When building an intelligent app, choosing the right generative AI model requires evaluating factors like task type, precision, performance, and scalability to meet real-world needs.
+  author: madiepev
+  ms.author: madiepev
+  ms.date: 02/21/2025
+  ms.topic: unit
+  ms.collection:
+    - wwl-ai-copilot
+durationInMinutes: 8
+content: |
+  [!include[](includes/3-select-model.md)]

learn-pr/wwl-data-ai/plan-prepare-genaiops/4-lifecycle-overview.yml

@@ -0,0 +1,15 @@
+### YamlMime:ModuleUnit
+uid: learn.wwl.plan-prepare-genaiops.lifecycle-overview
+title: Understand the development lifecycle of a language model application
+metadata:
+  title: Understand the development lifecycle of a language model application
+  description: Understand the development lifecycle of a language model application.
+  author: madiepev
+  ms.author: madiepev
+  ms.date: 02/21/2025
+  ms.topic: unit
+  ms.collection:
+    - wwl-ai-copilot
+durationInMinutes: 7
+content: |
+  [!include[](includes/4-lifecycle-overview.md)]

learn-pr/wwl-data-ai/plan-prepare-genaiops/5-tools-frameworks.yml

@@ -0,0 +1,15 @@
+### YamlMime:ModuleUnit
+uid: learn.wwl.plan-prepare-genaiops.tools-frameworks
+title: Explore available tools and frameworks to implement GenAIOps
+metadata:
+  title: Explore available tools and frameworks to implement GenAIOps
+  description: Explore available tools and frameworks to implement GenAIOps.
+  author: madiepev
+  ms.author: madiepev
+  ms.date: 02/21/2025
+  ms.topic: unit
+  ms.collection:
+    - wwl-ai-copilot
+durationInMinutes: 7
+content: |
+  [!include[](includes/5-tools-frameworks.md)]

learn-pr/wwl-data-ai/plan-prepare-genaiops/6-exercise.yml

@@ -0,0 +1,15 @@
+### YamlMime:ModuleUnit
+uid: learn.wwl.plan-prepare-genaiops.exercise
+title: Exercise - Compare language models from the model catalog
+metadata:
+  title: Exercise - Compare language models from the model catalog
+  description: Compare language models from the model catalog.
+  author: madiepev
+  ms.author: madiepev
+  ms.date: 02/21/2025
+  ms.topic: unit
+  ms.collection:
+    - wwl-ai-copilot
+durationInMinutes: 15
+content: |
+  [!include[](includes/6-exercise.md)]

learn-pr/wwl-data-ai/plan-prepare-genaiops/7-knowledge-check.yml

@@ -0,0 +1,49 @@
+### YamlMime:ModuleUnit
+uid: learn.wwl.plan-prepare-genaiops.knowledge-check
+title: Knowledge check
+metadata:
+  title: Knowledge check
+  description: Knowledge check to test your knowledge on grounding models with RAG.
+  author: madiepev
+  ms.author: madiepev
+  ms.date: 02/21/2025
+  ms.topic: unit
+  ms.collection:
+    - wwl-ai-copilot
+durationInMinutes: 3
+content: |
+quiz:
+  questions:
+  - content: "Which of the following best describes GenAIOps?"
+    choices:
+    - content: "GenAIOps is a term used to describe the study of language linguistics and machine operations."
+      isCorrect: false
+      explanation: "Incorrect. GenAIOps doesn't refer to the study of language linguistics and machine operations, but rather to the operational aspects of deploying and maintaining large language models."
+    - content: "GenAIOps focuses primarily on the development of hardware designed for training large language models."
+      isCorrect: false
+      explanation: Incorrect. While hardware development is important, GenAIOps encompasses a broader scope including practices and tools for optimizing, deploying, and maintaining LLMs-based applications."
+    - content: "GenAIOps refers to a set of practices and tools specifically for optimizing, deploying, and maintaining LLMs-based applications."
+      isCorrect: true
+      explanation: "Correct. GenAIOps involves the practices and tools that support the lifecycle of large language models, from optimization and deployment to maintenance and updates."
+  - content: "What is Prompty?"
+    choices:
+    - content: "Prompty is a language agnostic prompt asset class and format for creating prompts and engineering the responses."
+      isCorrect: true
+      explanation: "Correct. Prompty allows for the creation and engineering of prompts in a format that isn't dependent on any specific language, enabling a wide range of applications."
+    - content: "Prompty is a programming language created for writing machine learning algorithms."
+      isCorrect: false
+      explanation: "Incorrect. Prompty isn't a programming language, but rather a format for creating and managing prompts used with large language models."
+    - content: "Prompty is a development tool to create executable flows that link LLMs, prompts, and Python tools through a user-friendly UI."
+      isCorrect: false
+      explanation: "Incorrect. While Prompty facilitates the use of prompts with LLMs, it isn't a tool for creating executable flows or linking Python tools through a UI."
+  - content: "What azd cli command should you use to create all the project resources and deploy the app to Azure?"
+    choices:
+    - content: "`azd up`"
+      isCorrect: true
+      explanation: "Correct. The `azd up` command is used to create all the necessary resources and deploy the application to Azure, streamlining the process into a single step."
+    - content: "`azd deploy`"
+      isCorrect: false
+      explanation: "Incorrect. While `azd deploy` is used for deployment, it doesn't create all the project resources."
+    - content: "`azd auth login`"
+      isCorrect: false
+      explanation: "Incorrect. The `azd auth login` command is used to authenticate with Azure, not to create resources or deploy applications."

learn-pr/wwl-data-ai/plan-prepare-genaiops/8-summary.yml

@@ -0,0 +1,15 @@
+### YamlMime:ModuleUnit
+uid: learn.wwl.plan-prepare-genaiops.summary
+title: Summary
+metadata:
+  title: Summary
+  description: Summary of key learning points on GenAIOps.
+  author: madiepev
+  ms.author: madiepev
+  ms.date: 02/21/2025
+  ms.topic: unit
+  ms.collection:
+    - wwl-ai-copilot
+durationInMinutes: 1
+content: |
+  [!include[](includes/8-summary.md)]

learn-pr/wwl-data-ai/plan-prepare-genaiops/includes/1-introduction.md

@@ -0,0 +1,13 @@
+**Generative Artificial Intelligence** (**GenAI**) applications are transforming the user experience and accelerating adoption of AI tools and solution across consumer and enterprise domains.
+
+Traditional Artificial Intelligence (AI) applications focused on building and deploying machine learning models **from scratch**. Traditional machine learning models were trained on custom datasets with the goal of **generating predictions** that supported decision-making.
+
+Generative AI applications focus on **pretrained language models** based on massive internet-scale text data. These models can be augmented with data (RAG) or **fine-tuned** to execute tasks with the goal of **generating content** in response to user queries or instructions. A generative AI application can focus on text generation like question-answering, text summarization, or translation. Or rich content generation driven by text-based instructions like creating images, audio, video, or code.
+
+The key difference lies in the **use of natural language constructs** as text-based inputs, also known as **prompts**, with **token-based processing**, or completions, that generate stochastic outputs that can vary based on different factors including input prompt, system context, model parameters, and more.
+
+The emergence of generative AI applications is leading to a **paradigm shift** for end-to-end development, where the developer focus shifts from **model generation** (traditional MLOps) to **content generation** using pretrained models (modern GenAIOps).
+
+To build effective GenAI solutions, developers need to select the right models, and also understand how these models fit into the broader operational framework to develop an application. The end-to-end application development of a GenAI solution is also referred to as **Large Language Model Operations** (**LLMOps**), or **GenAI Operations** (**GenAIOps**).
+
+Before going into the technical aspect of preparing a GenAIOps solution, you learn to plan an appropriate use case by exploring various examples and their architectures.