Duke University - Operationalizing LLMs on Azure
- Offered byCoursera
Operationalizing LLMs on Azure at Coursera Overview
Duration | 10 hours |
Start from | Start Now |
Total fee | Free |
Mode of learning | Online |
Official Website | Explore Free Course  |
Credential | Certificate |
Operationalizing LLMs on Azure at Coursera Highlights
- Earn a certificate from Coursera
- Learn from industry experts
Operationalizing LLMs on Azure at Coursera Course details
- Gain proficiency in leveraging Azure for deploying and managing Large Language Models (LLMs)
- Develop advanced query crafting skills using Semantic Kernel to optimize interactions with LLMs within the Azure environment
- Acquire hands-on experience in implementing patterns and deploying applications with Retrieval Augmented Generation (RAG)
- This course is designed for individuals at both an intermediate and beginner level, including data scientists, AI enthusiasts, and professionals seeking to harness the power of Azure for Large Language Models (LLMs)
- Tailored for those with foundational programming experience and familiarity with Azure basics, this comprehensive program takes you through a four-week journey. In the first week, you'll delve into Azure's AI services and the Azure portal, gaining insights into large language models, their functionalities, and strategies for risk mitigation. Subsequent weeks cover practical applications, including leveraging Azure Machine Learning, managing GPU quotas, deploying models, and utilizing the Azure OpenAI Service
- As you progress, the course explores nuanced query crafting, Semantic Kernel implementation, and advanced strategies for optimizing interactions with LLMs within the Azure environment
- The final week focuses on architectural patterns, deployment strategies, and hands-on application building using RAG, Azure services, and GitHub Actions workflows
- Whether you're a data professional or AI enthusiast, this course equips you with the skills to deploy, optimize, and build robust large-scale applications leveraging Azure and Large Language Models
Operationalizing LLMs on Azure at Coursera Curriculum
Introduction to LLMOps with Azure
Meet your instructor: Alfredo Deza
About this course
Introduction
Introduction to the Azure Portal
Using Microsoft Learn
Identifying the Azure AI solutions
Introduction to Azure Machine Learning
Introduction to Azure Open AI Service
Summary
Introduction
What are LLMs and how do they work?
Benefits and risks of using LLMs
Mitigating risks of LLMs
Introduction to LLMOps
Summary
Introduction
Discover and evaluate LLMs in Azure
Deployment options for inferencing
What is the Azure AI Content Safety feature?
Azure Machine Learning and Azure Open AI Service differences
Summary
Connect with your instructor
Course structure and discussion etiquette
External lab: Create an Azure account
What is Azure OpenAI Service?
What is Azure Machine Learning?
An introduction to LLMOps
External Lab: Explore Azure Machine Learning Studio
What is Azure Content Safety?
Introduction to LLMOps with Azure
Meet and greet (optional)
LLMs with Azure
Introduction
GPU quotas and availability
Creating a compute resource
Deploying the model
Using the inference API
Summary
Introduction
Getting access to Azure OpenAI Service
Creating an Azure OpenAI Service resource
Deploy an OpenAI model
Using the playground
Summary
Introduction
Using keys and endpoints
Creating a simple Python example
Reviewing usage and quotas
Cleaning up resources
Summary
Azure ML: Create Resources
External lab: Create a compute resource
External lab: Use the Azure OpenAI Service Playground
External lab: Using Azure OpenAI APIs
LLMs with Azure
Extending with Functions and Plugins
Introduction
What is Semantic Kernel?
Using Semantic Kernel with Azure
Using a system prompt
Advanced system prompts
Summary
Introduction
Overview of functions
Defining functions
Using the function with the LLM
Working with errors
Summary
Introduction
Creating a glue function
Consuming function arguments
Using a native function
Overview of a microservice for functions
Using an external microservice API
Summary
External lab: Using Semantic Kernel with Azure
External lab: Using Functions
External lab: Use native functions
Functions and Plugins
Building an End-to-End LLM application in Azure
Introduction
Architectural overview
What is RAG
Overview of Azure AI Search
Automation and deployment with GitHub
Summary
Introduction
Create the Azure resources
Create the embeddings
Create and upload the index
Verifying the embeddings
Using RAG with Azure OpenAI
Summary
Introduction
Application overview
Setting up Azure components
Architectural overview
Using GitHub Actions with Azure
Verifying and troubleshooting deployments
Summary
External lab: Create an Azure AI Search resource
Azure AI Document Intelligence and Azure OpenAI
Introduction to RAG
External lab: Create embeddings in an index
Azure Container Apps
External Lab: Deploy and end-to-end application
Next steps
End-to-end LLM applications
Operationalizing LLMs on Azure at Coursera Admission Process
Important Dates
Other courses offered by Coursera
Student Forum
Anything you would want to ask experts?