Alice Chambers |
More than 100 million developers will have access to Microsoft Azure artificial intelligence and other industry-leading AI models via a “built-in playground that lets you test different prompts and model parameters, for free, right in GitHub”, according to Thomas Dohmke, CEO of GitHub.
GitHub users will have direct access to Microsoft’s Phi-3 suite of small language models as well as models like OpenAI’s GPT-4o, Meta’s Llama 3.1 and Mistral AI’s Mistral Large 2.
“With GitHub Models, developers can now explore and utilise the latest models along with AI innovations and next-generation frontier models,” said Asha Sharma, corporate vice president of the AI platform at Microsoft, in a recent blog post. “This offering gives every developer the flexibility to choose the best combination of unique capabilities, performance metrics and cost efficiencies. GitHub Models opens the door for developers to experiment with multiple models, simplifying model experimentation and selection across the best of the Azure AI catalogue, quickly comparing models, parameters and prompts.”
Developers will also be able to bring the models into their Codespaces and Microsoft Visual Studio Code environments.
“By making Azure AI an open, modular platform, we aim to help our customers rapidly go from idea to code to cloud,” said Sharma. “With Azure AI on GitHub, developers can do just that by utilising Codespaces to set up a prototype of use the Prompty extension to generate code with GitHub Models directly in Microsoft Visual Studio Code.”
It is also easier for organisations to access GitHub Enterprise through Azure. Firms with an existing Azure subscription can purchase GitHub products via self-service, directly through Microsoft Sales or via Microsoft Cloud Solution Providers and can adjust the number of GitHub seats as needed.
Microsoft plans to expand its integration with GitHub further by bringing Azure AI’s language, vision and multi-modal services to GitHub, as well as Azure AI toolchain elements that will further streamline the AI application development process.