Three Resources To Know:
- Explore #60DaysOfIA: Azure AI Week
- Explore: Azure AI Studio Collection
- Explore: Responsible AI Collection
Welcome to the ninth post in my This Week In AI News series. Want to keep up with my weekly posts? Now there's a tag you can follow: 👇🏽
Introduction
In my previous post, I talked about how you can build a copilot experience using Azure AI Studio at a very high level.
By the end of that post, you should have been able to answer three questions:
- What is LLM Ops? (paradigm shift)
- What is Azure AI Studio? (unified platform)
- What is a Copilot? (generative AI app with your data)
The post also linked to a video that walked through the process of building a copilot code-first. But what if you wanted a more hands-on walkthrough of the process with an end-to-end application sample or quickstart templates for popular frameworks? We have you covered!
This week, Azure AI takes the spotlight on the #60DaysOfIA series covering core tools and technologies to build intelligent apps using cloud-native technologies on Azure.
Here's what you can expect to learn:
Day 1️⃣ | End-to-End Contoso Chat Sample
Day 1 kicks off with a 2-part post:
- A kickoff post that describes the driving application scenario, the paradigm shift to LLM Ops, and the "copilot" application experience on Azure.
- A deep-dive into Contoso Chat and end-to-end application sample that teaches you how to build, evaluate, deploy, and test, a RAG-based chat AI application using Azure AI Studio and Prompt flow.
Days 2️⃣-4️⃣: Copilot Quickstart Samples
The figure below shows a high-level architecture diagram for a basic "copilot" application. In this context, a copilot is a generative AI application grounded in your data that allows the user to perform complex tasks or ask questions using conversational chat interface.
Building a copilot requires us to think about two main things:
- Chat Function - developing the chat function that coordinates or orchestrates the many interactions required, to implement the Retrieval Augmented Generation (RAG) pattern shown.
- Chat API - deploying the chat function to a hosted endpoint to expose an API that you can interact with from a chat UI (e.g., Contoso Web application) to deliver conversational user experiences with your products.
In this part of the series, we'll explore three quickstart samples that can jumpstart your own development thinking, using basic Python code (with the Azure AI SDK), or by integrating orchestration tools and popular frameworks like Prompt flow and LangChain
Day 5️⃣: Deploy AI Responsibly
The previous posts focus on Azure Samples that help you build a copilot application on the Azure AI platform with a focus on ideation and augmentation steps of the LLM Ops workflow. They end with deployment to Azure, to expose an API endpoint for integration.
In this final post of our journey we circle back to the first post and revisit the operationalization phase of the LLM Ops story with a focus on 2 aspects:
- Deployment Options - How can we test the deployed endpoint on Azure AI Studio? How can we integrate it with our applications? And are there enterprise-grade examples that show how to containerize and deploy such solutions with cloud-native technologies?
- Responsible AI - How can we ensure that we bring responsible AI practices into the ideation, augmentation and operationalization phases in a meaningful and effective way for generative AI applications? We explore the steps of identifying potential harms, evaluating solutions to assess quality and responsible AI usage, and applying content filters for content safety in production.
Ask The Expert (Mar 21)
Read the series and now you have questions or feedback? Or perhaps you built something interesting and want to share your insights or learn what's next to help you evolve your idea?
We have you covered! Don't forget to join us Mar 21 for an #AskTheExpert where authors from this series will be live to take your questions and share their perspectives on the generative AI development journey.
🚨 Register Now to attend.
Three Resources To Know:
- Explore #60DaysOfIA: Azure AI Week
- Explore: Azure AI Studio Collection
- Explore: Responsible AI Collection
Want to get the latest news, updates, and content on building intelligent apps with Azure? Follow the Azure org right here on dev.to - and subscribe to my This Week in AI series by following the #thisweekinai tag.
Top comments (0)