Build your own private ChatGPT style app with enterprise-ready architecture

Рет қаралды 14,204

Күн бұрын

For enterprise-grade architecture, data privacy, and control, build your own private ChatGPT style app using OpenAI GPT models with the Azure AI services. You can start with open-source samples for design and the user interface along with Azure containers or Azure App Service, then customize what it can do with Azure AI Studio. Importantly, to ensure its enterprise-ready with the right security and scale considerations in place, Azure Landing Zones provide the architectural best practices for apps like this. Landing Zone Accelerators simplify deployment for dedicated app-level subscriptions and scoped security and broader policies. Layering these recommendations and approaches helps ensure that your ChatGPT style private app meets enterprise requirements.
Microsoft Azure expert, Matt McSpirit, shares how to build your own private ChatGPT-style apps and make them enterprise-ready using Azure Landing Zones.
► QUICK LINKS:
00:00 - Build your own private ChatGPT
00:43 - Benefits of building your own private chat experience
02:07 - Use an open source ChatGPT-style app sample
03:16 - Connect your ChatGPT-style experiences
04:12 - Enhance chat experience with Azure AI Studio
04:45 - Architecture and security with Azure Services
06:44 - Landing Zone configuration and accelerators
07:49 - Wrap Up
► Link References:
Go to the Azure OpenAI Landing Zone at aka.ms/OpenAILZ
Get ChatBot UI open-source code in GitHub at aka.ms/GitHubChatBotUI
To use Bicep templates, go to aka.ms/LZ
Check out Landing Zone accelerators at aka.ms/LZAccelerators
Watch our show on Azure AI Studio at aka.ms/AIStudioMechanics
Watch our show on Azure Landing Zones at aka.ms/LandingZoneMechanics
► Unfamiliar with Microsoft Mechanics?
As Microsoft's official video series for IT, you can watch and share valuable content and demos of current and upcoming tech from the people who build it at Microsoft.
• Subscribe to our KZfaq: / microsoftmechanicsseries
• Talk with other IT Pros, join us on the Microsoft Tech Community: techcommunity.microsoft.com/t...
• Watch or listen from anywhere, subscribe to our podcast: microsoftmechanics.libsyn.com...
► Keep getting this insider knowledge, join us on social:
• Follow us on Twitter: / msftmechanics
• Share knowledge on LinkedIn: / microsoft-mechanics
• Enjoy us on Instagram: / msftmechanics
• Loosen up with us on TikTok: / msftmechanics
#ChatGPT #Copilot #OpenAI #AzureAI

Пікірлер: 10

@realmckaywrigley 4 ай бұрын

Thank you for featuring Chatbot UI and here's to open-source!

@nicky_rads 4 ай бұрын

Wow, awesome ! Having a chat not trained on your own data is great

@fallinginthed33p 4 ай бұрын

When will Mistral models be available for this?

@alexchandler6122 4 ай бұрын

What's the difference between this and Microsoft Copilot Studio?

@MSFTMechanics 4 ай бұрын

This would be a pro code option using Azure services for the backend, connectivity, and logic tiers of your app. Copilot Studio is a nice low code option.

@mad056 4 ай бұрын

The chatbot-ui project uses Supabase - so technically its not fully internal and you would be storing info with a third party?

@DeployJeremy 4 ай бұрын

We only suggest this as the front end as a proof of concept, then you would use the Azure Landing Zone guidance for the connection, logic and backend tiers.

@realmckaywrigley 4 ай бұрын

We currently use Supabase as the default backend, though this can be replaced with anything. We're working on improving this so that the core repo is less opinionated so that people can more easily bring their own backend.

@mad056 4 ай бұрын

@@realmckaywrigley that would be great, I haven't had much time to review the full code so did not get a chance to see how replaceable the backend is