Advent of 2024, Day 17 – Microsoft Azure AI – Azure OpenAI service

This article is originally published at https://tomaztsql.wordpress.com

In this Microsoft Azure AI series:

1. Dec 01: Microsoft Azure AI – What is Foundry?
2. Dec 02: Microsoft Azure AI – Working with Azure AI Foundry
3. Dec 03: Microsoft Azure AI – Creating project in Azure AI Foundry
4. Dec 04: Microsoft Azure AI – Deployment in Azure AI Foundry
5. Dec 05: Microsoft Azure AI – Deployment parameters in Azure AI Foundry
6. Dec 06: Microsoft Azure AI – AI Services in Azure AI Foundry
7. Dec 07: Microsoft Azure AI – Speech service in AI Services
8. Dec 08: Microsoft Azure AI – Speech Studio in Azure with AI Services
9. Dec 09: Microsoft Azure AI – Speech SDK with Python
10. Dec 10: Microsoft Azure AI – Language and Translation in Azure AI Foundry
11. Dec 11: Microsoft Azure AI – Language and Translation Python SDK
12. Dec 12: Microsoft Azure AI – Vision and Document AI Service
13. Dec 13: Microsoft Azure AI – Vision and Document Python SDK
14. Dec 14: Microsoft Azure AI – Content safety AI service
15. Dec 15: Microsoft Azure AI – Content safety Python SDK
16. Dec 16: Microsoft Azure AI – Fine-tuning a model

Let’s first address the elephant in the room. We have explored the Azure AI Foundry and the we have also Azure OpenAI. So what is the core difference? Let’s take a look:

The services in the back:

• Azure AI Services has much broader AI capabilities and simpler integration into applications and usage of the real world. With mostly pre-build API for all services (face recognition, document recognition, speech recognition, computer vision, image recognition, and more) that will allow better interoperabilty and and connection to machine learning services (Azure Machine Learning Service).
• Azure OpenAI is focusing primarly on OpenAI LLM models (Azure AI services supports many others) and provides great agents for conversations, content tools, RAG and natural language services.

UI:

• Azure AI Foundry (PreviousAzure AI Studio) contains AI Hubs, Hubs contain projects and projects contain AI resources (Search, Computer Vision, Models, etc). Azure OpenAI gives you access to the OpenAI models to use in the Studio as a part of a project.
• Azure OpenAI will give you the endpoints listed in the Azure OpenAI service details. And access to the various AI resources.

GenAI models:

• Models in Azure AI Services offers a variety of AI models and tools that can be fine-tuned, customised and applied (embedded) to your application or service. AI Service also offers many of the pre-trained models that can be used out-of-the-box or even later fine-tuned. Models include variety of services for image analysis, translation, and text analytics
• Models in Azure OpenAI are mainly the OpenAI’s LLMs and along those models are also the tasks one can use to create. From RAG systems. text generation, chat bots, summarisations, also to fine-tuning and some additional customisation. You will also find capabilities for image analysis and video analysis. But in general more limited in comparison to Azure AI Services with the model offerings.

There are also differences when it comes to integration with other azure services but in general it derives from the models each is offering.

Creating Azure OpenAI service, you can create a new by opening Azure OpenAI service in Azure portal.

and once you have the service up and running you will enter to the same UI (interface), that is Azure AI Foundry. Here you will have all the with the API capabilities, playground and other functionalities.

Tomorrow we will look into the Azure AI Project and Azure AI Hub.

All of the code samples will be available on my Github.

Thanks for visiting r-craft.org
This article is originally published at https://tomaztsql.wordpress.com
Please visit source website for post related comments.