3 Resources To JumpStart Your Azure AI Studio Exploration:
Welcome to the eighth post in my This Week In AI News series. Today, I want to talk about building generative AI applications code-first with the Azure AI platform. What does this mean and how does it help us make the paradigm shift to LLM Ops?
What is LLM Ops?
Traditionally, when we talk about AI applications we were referring to machine learning solutions where we built custom models trained on relatively-finite datasets for our target use case. The deployed AI application would then be used to make predictions.
Today, when we talk about AI applications we typically mean generative AI solutions based on large language models trained on massive datasets. Our focus is then on prompt engineering and fine-tuning these pre-trained models to generate content.
This has led to a paradigm shift from ML Ops to LLM Ops where the end-to-end application development lifecycle looks more like the picture shown below. Building these solutions now requires us to think about 3 phases:
- Ideation - define and build the basic experience
- Augmentation - evaluate and refine for quality
- Operationalization - deploy and use in production
This requires new tools, technologies and processes to streamline developer experiencea in building, testing, deploying & integrating, these apps.
What is Azure AI Studio?
Azure AI Studio tackles this challenge by providing a unified platform that supports the entire workflow from ideation (explore models, engineer prompts) to augmentation (build and manage AI projects) to operationalization (deploy & monitor solutions).
Want to get started exploring the platform? Check out the Azure AI Studio UI - a browser-based experience perfect for low-code developers. But if you're a professional developer, you probably want to have more control over the interactions, and potentially integrate additional libraries or features to enhance your solution. This is where having support for code-first development helps.
What does code-first development mean?
From the Azure AI Studio perspective, this means supporting command-line (CLI) and programmatic (SDK) interactions with the underlying Azure AI platform and resources. In February, the Azure AI team recorded this livestream talk which walks you through the process of building an enterprise copilot AI experience using a code-first approach on Azure AI Studio.
Want a more complete picture of what is involved? Check out my Tech Community Post from last month for a more detailed description of the tools, process, and resources to skill up on this topic. The tweet below has a preview of the post for convenience.
Azure AI Week & AskTheExpert
But there's more. Keep an eye out on Mar 11-15 (next week) as we launch Azure AI Week on #60DaysOfIA - part of a multi-week campaign with events and activities focused on building intelligent apps.
Then join us on March 21 for an #AskTheExpert session we will take your questions live, share demos and discuss the generative AI developer journey!
đ¨ Register Now to attend.
This is an exciting time for developers, data scientists and entrepreneurs to go from ideation to operationalization and build intelligent generative AI experiences code-first! Don't forget to check out the resources below to start skilling up!
3 Resources To JumpStart Your Azure AI Studio Exploration:
Top comments (3)
Love this! đ
Thanks so much - there's a lot more we are working on so stay tuned
Is there any articles on just a simple chatbot using gpt4 that looks at multiple pdf files in a blob storage and then asking questions on the chat to see that it is returning the correct results?
There seems to be so many resources to be included in the AI Project that its unsure which are relevant and the adding AI Search resource, it not being found when adding data on the playground.