Build your own copilots with Azure AI Studio
HTML-код
- Опубликовано: 13 май 2024
- Build, test, deploy, and monitor your generative AI apps at scale from one place with Azure AI Studio. Access models in the Azure OpenAI service from Meta, NVIDIA and Microsoft Research, as well hundreds of open-source models. Integrate your own data across multiple data sets to ground your model, which is made easier through direct integration with OneLake in Microsoft Fabric. It uses shortcuts to let you bring in virtualized data sets across your data estate without having to move them.
Use Azure AI Studio for full lifecycle development from a unified playground for prompt engineering, to pre-built Azure AI skills to build multi-modal applications, using language, vision, and speech, as well as Search, which includes hybrid with semantic ranking for more precise information retrieval. Test your AI applications for quality and safety with built-in evaluation, and use a prompt flow tool for custom orchestration, as well as overarching controls with Responsible AI content filters for safety. Seth Juarez, Principal Program Manager for Azure AI, gives you an overview of Azure AI Studio.
► QUICK LINKS:
00:00 - Build your own copilots in Azure AI Studio
01:52 - Copilot app running as a chatbot
03:53 - Retrieval augmented generation grounded on your data
04:54 - Experiment with prompts: Multi-modality
06:47 - Advanced capabilities: Prompt flow
08:58 - Ensure quality and safety of responses
10:09 - Wrap up
► Link References
Start using Azure AI Studio today at ai.azure.com
Check out our QuickStart guides at aka.ms/LearnAIStudio
► 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 RUclips: / 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
#Copilot #GenerativeAI #GPT #OpenAI 
Наука
Loved it. This was already presented in MS-Build 2023, but this was more detailed. So thank you very much.
Thank you - Glad it was helpful!
Much improved presentation compared to MS-Build
Thanks Microsoft Mechanics team, and love you Seth!
Excellent content as always Seth.
How do you deploy a chatbot outside of the playground? You show a chatbot on a website and how to build it within the playground but don't show how to put it on a website. How is this done?
same question here
Did you find anything?
Most likely develop a chatbox outside and connect it to the API end point provided.
This is mind-blowing 🤯
Can you build GPTs like you can with ChatGPT Plus?
gpt-4 is not part of the models available. Is an application required?
Looks great!
Thanks, Jason!
would be interested in seeing some testing data as examples 🙏 that'd be super helpful
How to create indexes out of new blob storage data? Eg. stream vs batch?
Awesome 👏
How do I use the model that I customized in the Copilot Studio? Is there an integration between the Azure AI Studio and the Copilot Studio?
Thank you
On my end I don't have gpt4 as an option. I also don't have vector search and only has keyword search. Is this because I'm on free version of Azure? Super new to this. Would appreciate if anyone has answers.
So whats the difference bewteen using openai from azure portal and like this ?
The playground part is similar, but AI Studio has access to more models, data source integration, RAG orchestration using visual prompt flows, content filtering, system prompt samples, and more.
💥💥
Wow. Great stuff. MS makes this technology usable.
❤️❤️❤️❤️❤️
Is this free or paid?
For a 🧠👀 to all link Done new come all system and sinc to all team