We’re excited to partner with GitHub to enable their 100+ million developers to build AI applications directly from GitHub.com with seamless integrations with Codespaces and Microsoft Visual Studio Code.
Microsoft is empowering developers to become AI developers, bringing industry-leading Azure AI models to GitHub’s global community of over 100 million
More than 60,000 organizations use Microsoft Azure Artificial Intelligence Nowadays, it is very common to explore the power of custom AI applications. However, the market is rapidly moving from experimentation to scale and we are seeing more and more developers around the world becoming AI developers. With this natural evolution, the needs of developers and their requirements to access and build with AI models and tools are also transforming.
To support this shift in scale, we are excited to… Partnering with GitHub to empower its 100+ million developers to build AI applications directly from GitHub.com with seamless integrations with Codespaces and Microsoft Visual Studio Code. Our collaboration begins today as we bring Azure Artificial IntelligenceThe leading model selection for developers through GitHub Modelsalong with simple APIs to power responsible, production-ready AI applications.
To learn more about how GitHub models can help you increase experimentation and accelerate your development cycles, all on GitHub, Read the blog from GitHub CEO Thomas Dohmke.
Simplifying AI development
As AI model innovation accelerates, Azure remains committed to offering the leading model selection and greatest model diversity to meet the unique cost, latency, design, and security needs of AI developers. Today, we offer the largest and most comprehensive model library on the market, including the latest models from OpenAI, Meta, Mistral, and Cohere and updates to our own Phi-3 family of small language models. With GitHub Models, developers can now explore and use the latest models alongside AI innovations and next-generation cutting-edge models. This offering gives every developer the flexibility to choose the best combination of unique capabilities, performance metrics, and cost efficiency.
While continued model innovation brings more options, it also brings complexity in selecting the right model for the right scenario. Today, developers have a variety of options for cloud vs. edge, for general purpose vs. specific tasks, and more. On top of that, organizations often need multiple models to enable better quality, lower cost of goods sold, and to address complex use cases for each industry. GitHub Models opens the door for developers to experiment with multiple models, simplifying experimentation and model selection across the best of the Azure AI catalog, quickly comparing models, parameters, and prompts.
By making Azure AI an open and modular platform, our goal is to help our customers quickly move from idea to code to the cloud. With Azure AI on GitHub, developers can do exactly that by using Codespaces to set up a prototype or use the Quick extension to generate code with GitHub models directly in Microsoft Visual Studio Code.
In the coming months, we will further expand our integration, bringing Azure AI language, vision, and multimodal services to GitHub, along with additional elements of the Azure AI toolchain, further streamlining the AI application development process.
Security integration by default
Developers building AI-powered applications want to be confident that their AI applications are trustworthy and secure. GitHub Models gives developers a solid foundation from the start with Azure AI’s built-in security controls.
Azure AI works with model providers and other partners such as Hidden layer to reduce emerging threats, from cybersecurity vulnerabilities to malware and other signs of tampering. And we’ve taken this further in GitHub Models by integrating Azure AI Content Security For the best base models, including Azure OpenAI ServiceLlama and Mistral. Azure AI Content Safety enables built-in, real-time protection against risks such as harmful content generation, copyrighted materials, hallucinations, and new AI-specific attacks such as security leaks and rapid injection attacks.
If developers want to go deeper, they can customize these controls in Azure AI, using assessments to test and monitor their applications to ensure ongoing quality and security.
Simplicity of AI with a single API
The largest selection of models gives developers the widest range of options for the individual applications they are building. But each model naturally comes with increased complexity. To counter this, we are making it incredibly easy for every developer to experiment with a variety of models through Azure AI Model Inference APIWith this single API, GitHub developers can now access a common set of capabilities to compare performance across a diverse set of foundational models in a uniform and consistent manner, easily switching between models to compare performance without changing the underlying code.
He Azure AI Inference SDK provides client libraries in Piton and JavaScript Coming soon with C# and .NET support. This SDK makes it easy to integrate AI into your applications by simplifying common tasks related to authentication, security, and retries in the programming language of your choice. You can get started today with Piton and JavaScript samples.
Optimizing access to GitHub Enterprise through Microsoft Azure
In addition to these new integrations, we’re also making it easier than ever for organizations to access GitHub Enterprise through Azure, combining GitHub’s cloud-native platform with Azure’s robust, enterprise-grade security and scalability.
Organizations with an existing Azure subscription can purchase GitHub products through self-service, directly through Microsoft Sales, or through Microsoft cloud solution providers, and can adjust the number of GitHub seats as needed to ensure efficient usage. Additionally, eligible organizations can take advantage of the Microsoft Azure Consumption Commitment (MACC) and Azure Commitment Discount (ACD).
Companies can now create a GitHub instance directly from Azure Portal and connect your Microsoft ID Sign in with GitHub for easy user management and access control. With an Azure subscription, you have all the tools needed to build an intelligent AI application, including access to the full range of GitHub services such as repositories, actions, advanced security, and Copilot. This makes it incredibly simple and efficient to give developers everything they need to build and deploy AI applications at scale.
We invite you to experience the power of this integrated end-to-end development experience. New customers can explore these capabilities with a GitHub Enterprise 30-day free trial.
We can’t wait to see what you build with GitHub and Azure.
