Exploring AI Development and Management: A Journey through Contoso Chat and LLM Ops
In this blog, we'll navigate through the world of AI models, exploring Contoso Chat, Prompt Engineering, limitations of Prompt Engineering, and Large Language Models. We'll introduce tools like the RAG Pattern and Azure AI Studio that can boost AI responses and system performance. Ready to dive into the intricacies of AI development and management? Join us!Journey Series for Generative AI Application Architecture - Foundation
At Build last year, Microsoft CTO Kevin Scott proposed Copilot Stack to provide problem-solving ideas for Generative AI applications. Based on the Coplit Stack, community have developed many frameworks in the past year, such as Semantic Kernel, AutoGen, and LangChain. These frameworks are more biased toward front-end applications, and enterprises need a better engineering solution. This series hopes to give you some ideas based on Microsoft Cloud and related frameworks and tools.Building your own copilot – yes, but how? (Part 1 of 2)
Are you interested in building your own AI co-pilot? Check out the first of a two-part blog post from Carlotta Castelluccio that covers the basics of creating a virtual assistant that can help you with tasks like scheduling, email management, and more. Learn about the tools and technologies involved, including Microsoft's Bot Framework and Language Understanding Intelligent Service (LUIS). Whether you're a software developer or just curious about the possibilities of AI, this post is a great introduction to building your own co-pilot.
DocAider: Automated Documentation Maintenance for Open-source GitHub Repositories
Code–level documentation of a software system provides explanations of the code functionality and usages. Documentation is crucial for giving clear insights into the code for end–users and future developers. However, creating and updating documentation manually is a demanding task, requiring significant resources and labour. With the advancement of generative AI, there is a potential to reduce human labour in documentation tasks significantly. We propose DocAider, an automation tool powered by GPT–4 that integrates the processes of documentation generation and update. DocAider can generate comprehensive and structured documentation in markdown format and update it in response to any changes made in pull requests. The mission of DocAider is to reduce developers’ burden on maintaining documentation for GitHub repositories.Deploying GPT-4o AI Chat app on Azure via Azure AI Services – a step-by-step guide
Are you ready to revolutionize your business with cutting-edge AI technology? Dive into our comprehensive step-by-step guide on deploying a GPT-4o AI Chat app using Azure AI Services. Discover how to harness the power of advanced natural language processing to create interactive, human-like chat experiences. From setting up your Azure account to deploying your AI model and customizing your chat app, this guide covers it all. Unleash the potential of AI in your business and stay ahead of the curve with the latest advancements from Microsoft Azure. Don’t miss out on this opportunity to transform your workflows and elevate customer interactions to new heights!Building your own copilot – yes, but how? (Part 2 of 2)
With the term copilot we refer to a virtual assistant solution hosted in the Cloud, using an LLM as a chat engine, which is fed with business data and custom prompts and eventually integrated with 3 rd party services and plugins. In the first blog of this series, we covered how to build a copilot on custom data using low code tools and Azure out-of-the-box features. In this blog post we’ll focus on developer tools and code-first experience.
