azure openai

Joe Carlyle

Festive Tech Calendar: Adopt AI like a PRO with Azure Essentials

Another year, and another fantastic Festive Tech Calendar. While it wasn’t the first event I participated in, I do think it is my longest running, annual event. I have been a fan since it’s inception and am delighted to see it continue. This year, the team are raising funds for Beatson Cancer Charity. Donations are appreciated via the Just Giving page.

Now, this post is all about Azure AI adoption via the new offering of Azure Essentials. So, we will start off by explaining what that is and why it matters. Over the years, Microsoft has introduced new ways of doing things, new approaches or methods; sometimes these have been simple renames, and sometimes they have been a completely different vision of Azure. Often, they can be confusing regardless. This post aims to help understand Azure Essentials better, using the “tech of the moment” Azure AI.

So – let’s get started. What exactly is Azure Essentials? As we’re working related to AI, let’s set the scene using Copilot…

Copilot for M365 in Teams (please don’t @ me about the structure of that name, I cannot keep up with how to reference Copilot!) was helpful:

Copilot in Azure…not so much:

What you need to take away at this stage is, rather than this being an entirely new thing, it has consolidated existing good work to allow for the consumption of it to be simpler or more refined. At a theory level this seems to make sense, however, we all know the implementation of these things can be very tricky.

With this in mind, how to use or approach Azure Essentials shifts a bit. The first point that struck me was this is most useful for people new to Azure. However, that is not to say it is not useful for those experienced. But if you are new, we have a lot of assumptions that people will know and make use of offerings like CAF and WAF, will reference the Architecture Centre for design guidance, etc. When that is likely not the case.

Centralise core guidance as Azure Essentials is a great idea in my opinion. However, it hasn’t just centralised guidance. Disclosing at this point that I work for a Microsoft Partner. Essentials also includes recommendations for finding a partner, leveraging funding programs, which products are useful, and customer testimonials. This is nice for companies like mine as a marketing/contact channel, but I am not sure if I would define it as “essential”.

What is essential though is how it frames guidance and aligns customers into the right frame of approach in my opinion. The site is a touch confusing on this point though. So the new resource kit is right at the top, it’s the first link on the page. But scenario or use case guidance is further down and brings you elsewhere. Sticking with our original idea regarding AI adoption, there is a use case listed, and this brings you to an Azure Architecture blog from July – this is not what we want…

Whereas if we open the Resource Kit, then check it’s contents, we get a ‘common scenario’ with click through links

Now before we dig in there, one item I noted when researching this was that some messaging implies, or potentially confuses some elements of this with changes to, or improvements upon the Cloud Adoption Framework (CAF). In my opinion, Azure Essentials doesn’t change CAF, it’s not even listed on the What’s New page. However, it is an improvement to how people may be guided to CAF. And anything that brings more people to CAF and allows for efficient and more well governed deployments is a positive to me!

So, what exactly does Essentials recommend then as it’s ideal detail required for AI adoption? Six steps and some learning material. I am delighted to see the inclusion of learning material, its becoming more and more important as the rate of change increases. Let’s have a look at the six steps:

  1. Assess your Azure AI readiness
  2. Explore Azure AI pricing
  3. Prepare your AI environment
  4. Design your AI workloads
  5. Develop Well-Architected AI workloads
  6. Deploy, Manage, and operate your AI workloads

At first glance this looks like a good set to me. I don’t think I would have ranked pricing as high in the sequence, but perhaps it’s important to get that out of the way early! 🙂

The first ask is here is to take an Assessment. The Azure AI readiness assessment focusses on core areas of adoption strategy within your business. It can be a lengthy process, it notes 45 minutes, but if you choose all of the areas available, it will give you 100+ pages of questions to complete to attain your score. Anyone familiar with Azure Well Architected Reviews, or the old Governance Assessment will see the immediate similarities here and understand the usefulness of having something that asks people to think about things in the correct way and offers a score to guide expectations.

Next, it’s pricing. Again, this is tricky for me. To be remotely accurate with pricing, I think you need to have some form of design to then dictate resources, which lead to price. You are then happy, or shocked, and rework your design. Rinse repeat to get to where you need to be. Unfortunately, the link in the resource kit lands you on the default pricing page for Azure, nothing AI specific. So you really are starting at the bottom. Some more AI specific guidance here would be a great inclusion for the next version. For example, this placement link, bring you to the menu item for AI pricing on this page, a small but helpful direction.

Next, we’re onto preparation. A good note on a Landing Zone, but I would have expected as this is Azure Essentials that would link through to some guidance on Landing Zones. We then get two links to Design Architectures for Azure AI in the Architecture Centre. This could be more confusing than helpful, and it’s not the preparation guidance I would expect. This is Azure Essentials, and here is the first AI architecture Visio you see…

My concern here is complexity. I know people may have more interest in using OpenAI models and the whole chat functionality. But I would have gone a different route here. Most likely document based, something that uses one of the more mature services, like Document Intelligence, and a simpler architecture for guidance. Make it easier to see the objective rather than the mountain that is presented above. I don’t think there is actually a perfect set of links here, too many variables and too much information dependent on where the user perception of AI is. Will be very interesting to see how this progresses and it may always require further expertise and information to be properly impactful.

Next, design, one of my favourite areas. No other aspect of Azure excites me like creating the solution design. With a vast platform you start with everything and toil away until you have what works for what is needed. Here we get a note to choose from reference architectures – good point, but which ones? No links are provided, but having said that, there is no single link that works here. The reference architectures are spread out amongst the different products. Next, we get a great link to the AI architecture design overview page. I think I might have switched step 3 and 4 here actually. Doing this first, I believe it gives people a much better starting point to learn from and then understand point 3 more comprehensively. Bookmark this page for your AI adoption journey, it’s like a TOC of what to read for which service/product.

The penultimate step guides us to well architected workloads. The note is simply a note, however the point is valid but I think it should have included this link, as the start point for this step. It’s really useful and helps you quickly jump where you need to with reference to the Well Architected Framework (can anyone else just not call it WAF? Too confusing for me with Web Application Firewall). However the included link, which focusses on Azure OpenAI is good. It has the expected pillar guidance for Well Architected, and it has a comprehensive set of accurate click-through links. I think this step is important and placed in the right place too, so it flows well at this point of the resource kit.

Finally, we have a deploy and manage step. This feels a little bit like the weakest of the six steps. First of all the title is repeated as the first bullet point – not great.

Then it notes we should use best practice – again, no guidance as to what that means. Or how that is practically when it comes to deployment and management. Finally, it links to a guide page regarding responsible use of AI. Responsible use is incredibly important, it is valid when operating AI workloads, but it is useless as a single link for this step. There is a literal AI management page on CAF already that could be used. I have waited until this step to link to this area of CAF, as it hasn’t been updated since the start of 2024, but it has a lot of detail this kit should include, and with an update, would make much more sense than some of the links included.

In conclusion, I think the kit needs some work, a revision so to speak. First, I would tweak the steps to be as follows:

  1. Assess your Azure AI readiness
  2. Develop Well-Architected AI workloads
  3. Design your AI workloads
  4. Prepare your AI environment
  5. Deploy, Manage, and operate your AI workloads
  6. Explore Azure AI pricing

Next, I would rely more heavily on CAF and Architecture Center with context for links, or linking to overview pages with a note to use the links within. Like a ‘further reading’ note or similar. I know it is meant to be Essentials, but let’s give essential guidance rather than minimum perhaps?

Finally, if you want to adopt AI like a Pro – I think Essentials is useful as a sanity check, but you are better investing your time on the already existing items on Learn, CAF and WAF.

Joe Carlyle

Can Azure OpenAI Write This Blog Post?

This is the fear right? Or maybe it’s not a fear, and is a desire for some people, but it’s still not clear what the impact may be. What am I talking about? AI of course; specifically for this post, Azure OpenAI. Now, my idea here is to see what I think of the quality of responses it can give me based on specific prompts to try and tie together a simple blog post. I will pick a topic, an objective for the post, and I will be 100% transparent on what is AI written and what is me – just in case it is not obvious! I will also include the settings being used for my model at the end and whether I adjusted them during.

Ok, let’s get started. My topic is going to be Virtual Network Manager in my usual style of exploration.

What is Azure Virtual Network Manager? Write an opening paragraph for a blog post.

Azure Virtual Network Manager is an essential tool for managing and organizing your cloud-based virtual networks. With virtual networks, you can securely connect and isolate your Azure resources, control traffic flow, and expand your on-premises network into the cloud. However, managing virtual networks can be a challenging task, especially when you have multiple resources and services scattered across different regions. This is where the Azure Virtual Network Manager comes in, offering a centralized and user-friendly interface to help you efficiently manage and monitor your virtual networks. In this blog post, we will take a closer look at the Azure Virtual Network Manager and explore its features and benefits.

What are the top three use cases for Azure Virtual Network Manager? Write a detailed paragraph including bullet points and examples for each.

Azure Virtual Network Manager is a versatile tool that can support various use cases, depending on your organization’s needs. Here are the top three use cases for Azure Virtual Network Manager:

  1. Hybrid Cloud Connectivity: Azure Virtual Network Manager can help organizations establish secure, high-speed connections between their on-premises datacenters and Azure resources. This allows companies to take advantage of the scalability and flexibility of the cloud while maintaining the security and control of their own infrastructure. With Azure Virtual Network Manager, organizations can easily configure VPN gateways, express routes, and other connectivity options to seamlessly integrate their on-premises networks with Azure.

    Examples:
  • Connecting an on-premises Active Directory to Azure to manage identity and access for cloud resources.
  • Extending a corporate LAN to Azure to host applications and services in the cloud.
  • Using Azure as a backup and disaster recovery site for on-premises datacenters.
  1. Multi-Tier Application Architecture: Azure Virtual Network Manager enables organizations to create complex multi-tier application architectures in the cloud, with the ability to isolate and secure different layers of the application. This is done by creating multiple virtual networks, each with its own subnets and security groups. This approach provides better control over network traffic and reduces the risk of security breaches by limiting the attack surface.

    Examples:
  • Hosting a web application in Azure with a separate virtual network for the web server, application server, and database server.
  • Creating a DMZ in Azure to host public-facing services, with a separate virtual network for internal services.
  • Separating development, testing, and production environments into different virtual networks to ensure isolation and security.
  1. Global Network Management: Azure Virtual Network Manager provides a centralized interface to manage virtual networks across different regions and subscriptions. This allows organizations to monitor network traffic, troubleshoot connectivity issues, and optimize network performance from a single location. With Azure Virtual Network Manager, organizations can also implement advanced networking features, such as traffic routing, load balancing, and network security groups.

    Examples:
  • Creating a global load-balancing solution to distribute traffic across multiple regions and availability zones.
  • Implementing Azure Firewall to provide centralized network security management across multiple virtual networks.
  • Enabling Azure Traffic Manager to route traffic to the nearest endpoint based on geographic location or network latency.

What are the current limitations or known issues of Azure Virtual Network Manager? Write a paragraph in the blog post.

While Azure Virtual Network Manager is a powerful tool for managing virtual networks in the cloud, there are some limitations and known issues that organizations should be aware of. Some of the current limitations of Azure Virtual Network Manager include:

  • Limited support for hybrid networking configurations: Currently, Azure Virtual Network Manager has limited support for hybrid networking configurations, which can make it challenging to manage virtual networks that span multiple cloud providers or on-premises datacenters.
  • Limited visibility into network traffic: Azure Virtual Network Manager provides limited visibility into network traffic, which can make it difficult to troubleshoot connectivity issues or monitor network performance.
  • Limited integration with third-party tools: Azure Virtual Network Manager has limited integration with third-party tools, which can make it challenging to implement advanced networking features or security solutions.

    Organizations should carefully evaluate their networking needs and consider these limitations before deploying Azure Virtual Network Manager. However, Microsoft is continually improving the tool and addressing these limitations through updates and new features.

Is there a tutorial or general steps that should be recommended as part of this blog post for people who are interested in now trying Azure Virtual Network Manager? Include high level steps and a link to the appropriate site if possible

Yes, Microsoft offers a comprehensive tutorial on how to set up and manage virtual networks using Azure Virtual Network Manager. Here are the high-level steps for getting started with Azure Virtual Network Manager:

  1. Create a virtual network: The first step is to create a virtual network in Azure. This involves specifying the name, address space, and subnets for your network. You can also configure advanced network settings, such as DNS servers and network security groups.
  2. Create a gateway subnet: If you plan to connect your virtual network to an on-premises network, you need to create a gateway subnet. This subnet is used to deploy a VPN gateway or an ExpressRoute gateway.
  3. Configure VPN or ExpressRoute: Once you have created your virtual network and gateway subnet, you can configure a VPN or ExpressRoute connection to connect your on-premises network to Azure.
  4. Set up network security: Azure Virtual Network Manager provides several tools for securing your virtual network, including network security groups, application security groups, and Azure Firewall. You can use these tools to control inbound and outbound traffic, restrict access to specific resources, and monitor network activity.
  5. Monitor and troubleshoot your network: Azure Virtual Network Manager provides several tools for monitoring and troubleshooting your virtual network, including network performance monitoring, packet capture, and network watcher.

    For more detailed instructions on how to use Azure Virtual Network Manager, check out the official Microsoft tutorial: https://docs.microsoft.com/en-us/azure/virtual-network/tutorial-create-virtual-network.

Based on your previous responses do you think there is anything else that is important to know about Virtual Network Manager? Write a closing paragraph with a call to action to get in touch if you have any questions

In conclusion, Azure Virtual Network Manager is a powerful tool that can help organizations manage and secure their virtual networks in the cloud. With Azure Virtual Network Manager, organizations can establish secure connections between their on-premises and cloud-based resources, create complex multi-tier application architectures, and manage virtual networks across different regions and subscriptions. While there are some limitations and known issues with the tool, Microsoft is continually improving it with updates and new features.

If you have any questions about how to use Azure Virtual Network Manager or want to learn more about how it can support your organization’s networking needs, don’t hesitate to get in touch. Our team of experts is always available to help you navigate the complexities of cloud networking and find the best solutions for your business.

Let’s start with the settings used, I started with these and didn’t change them at all during the process:

engine="35t", (gpt35-turbo)
temperature=0.8,
max_tokens=800,
top_p=0.95,
frequency_penalty=0,
presence_penalty=0

Overall, I think it has the basics nearly correct. However, it has very little personalisation, it obviously speak to no real experience, and is essentially a modified read of the Docs pages. So I am pretty confident that at no point in near future could it be used to write an entire post that I would be happy with publishing. However, where a post calls for something more generic, like known issues, or intros, it could definitely be used as a starting point.

I am interest to see if a GPT4 model would make a huge difference, but for this style of work, I am not sure. Also, I could of course edit the temperature or top p, but I am unsure as to whether that impact again would be noticeable enough.

In conclusion, Azure OpenAI can definitely write a blog post – I am just not sure it’s a blog post I would be happy with!

Joe Carlyle

Where to Start – NLP with Azure OpenAI

I think without a doubt, one of the most talked about subjects at the moment is AI. Mass usage of OpenAI’s ChatGPT service exploded onto the scene this year, and we haven’t looked back. However, starting at such a broad scale of possibilities can be daunting. This post aims to simplify things down a bit, by looking at one single use case.

In this instance, I am going to take the Natural Language Processing capability offered by Azure OpenAI and have a GPT model summarise a piece of text for me. I completed sample lab files for this as part of a Microsoft Learn course, and I am reusing the Python here with some tweaks of mine!

All of the code for this solution is on Github here – https://github.com/wedoazure/sumo

The idea is that we take a text file, in my code I am using the first chapter from ‘Sherlock Holmes – The Hound of the Baskervilles’, but feel free to use whatever txt file you like, and send it to Azure OpenAI and ask for it to be summarised.

The app itself is command line based, very simple. It reads your text file, then sends a chat completion prompt to the Open AI model asking it to summarise your text.

The model then responds with a fixed length summary based on your input of word count and temperature.

The ability to adjust both is something I have added as my little variation. I had a couple of reasons for changing this up, but mostly built on the fact that your opinion of the output is important. For an example, read the actual text you want summarised, then have the app do it. Is the summary accurate? Is it a bit short, is it a bit too stiff? Change things up! Here is a 50 word summary at a temp of 0.5 versus 0.9 for the same txt file.

Sherlock Holmes and Dr. Watson examine a visitor’s stick, deducing that its owner is a country practitioner who walks a lot and has likely received a presentation from a hospital. The visitor, Dr. James Mortimer, arrives and confirms their deductions. He seeks Holmes’ assistance with a serious and extraordinary problem.

50 words at 0.5 temp

Dr. James Mortimer visits Sherlock Holmes and asks for his assistance with a mysterious problem. Through analyzing a stick left by a previous visitor, Holmes deduces that Dr. Mortimer is a country practitioner who used to work at Charing Cross Hospital. Dr. Mortimer confirms this and reveals that he has a strange case involving the curse of the Baskervilles.

50 words at 0.9 temp

As you can see, these are very different outputs, I personally prefer the response at 0.9, as I am summarising a work of fiction. However, if it was a financial report, you may need a lot less creativity and therefore force a lower temp. Similarly, you may want more words, or less, depending on your scope.

And that’s it! Short and sweet, using a single use case, minimal effort but impactful and useful outcome. I am sure I may make more tweaks, adding more advanced file input is definitely on the list. Let me know if you have any questions!