Thursday 9 November 2023

My AI talks at ESPC 2023 - Microsoft 365 Copilot experiences, Syntex, Azure OpenAI and more

As the new era of AI is in full swing, I have the privilege of covering some of the hottest topics at the upcoming European SharePoint, Microsoft 365 and Azure Conference 2023 in Amsterdam, Europe’s biggest Microsoft-focused conference. The conference starts on Monday 27 November and I’ll be sharing experiences from the field with Microsoft 365 Copilot, Microsoft Syntex, and “AI with your organisational data” projects using Azure OpenAI. I’ll be delivering three sessions plus an open mic talk on all things Copilot and AI with my good friend Jussi Roine.

In 27 years of working, I don’t remember a time when technology was having a bigger impact on how we work and how economies and societies operate. AI is obviously a huge part of that today, and 12 months on from ChatGPT becoming available it’s a wonderful moment to have 2500+ people together for an event like this. My sessions are just a small part of what will be an amazing conference. As usual, Microsoft are sending senior leadership and product managers to deliver keynotes and product announcements, and the entire session catalog has some amazing speakers delivering content to suit many personas. The conference still has tickets available – see https://www.sharepointeurope.com

The conference site has more, but here's an overview of my sessions with an explainer for each.

    Microsoft 365 Copilot - Experiences from the Field

    Experiences from the Early Access Programme and using Copilot, including a deep-dive on the specific approaches we (Advania/Content+Cloud) believe organisations need to adopt to get Copilot-ready


    Microsoft Syntex Deep-Dive - from AI Document Understanding to Content Governance

    In the Copilot era, Syntex is increasing in relevance rather than decreasing. New capabilities help you get ready for Copilot and extend the reach of AI compared to what Copilot can achieve alone


    Integrate ChatGPT into SPFx and Power Platform solutions with OpenAI and Azure OpenAI

    A technical session with my colleague and fellow MVP Anoop Tatti, where we explore different approaches to using GPT in your applications


    The Captain and the Copilots – Insights Uncovered on Generative AI, Productivity and the Speed of Innovation

    An "Inspire stage" session with Jussi Roine on all that we’ve learnt on Copilots, GPT, and Microsoft’s approach to generative AI

    Conference details

    ESPC is always an amazing event if you're based in Europe - it's not to late to attend and I highly recommend it if you work with Microsoft technoloogies. Here's the link to the conference pricing page

    https://www.sharepointeurope.com/pricing/

    Hopefully see you there!

    Wednesday 18 October 2023

    Building generative AI/ChatGPT on your data solutions - considerations, pitfalls and lessons learnt

    The last article focused on combining organisational data with ChatGPT and Large Language Models, specifically using Microsoft’s 'Azure OpenAI on your data' accelerator which is designed to simplify this. I’ve been focused on the general area of 'AI with your data' (though not the AOI accelerator specifically) for a while now with colleagues, and I don’t think it’s any exaggeration to say that combining generative AI and organisational data will be a big thing for the next few years. The results can be astonishing – we all know what ChatGPT is capable of, but seeing it answer questions and generate content related to an organisation’s clients, products, services, people, and projects rather than its original internet training data immediately shows huge value – providing a “second brain” for employees and supporting many use cases at work. Platform solutions like Microsoft 365 Copilot offer amazing capabilities for core collaboration and productivity, but building your own AI and data solution (often to supplement Copilot) using available building blocks is often the way to go for better results with your data.

    The overall message from my last article (Integrating your data with ChatGPT - exploring Microsoft's "Azure OpenAI on your data" accelerator) was that the tool is a useful accelerator in some respects, but in reality only gets you so far in terms of what you probably need. For AI that gives relevant, accurate, and transparent responses to prompts and queries for real world use cases, the implementors need to understand concepts such as retrieval augmentation (RAG), chunking, vector generation, and more. There are various ways to slice this but here’s one way of thinking of the top-level considerations:

    All of these concepts are inter-related.

    This article tries to help you understand each in more detail, sharing info on our approach and technology selection (for Microsoft-centric solutions) as well as some lessons learnt. I'll finish with some predictions on where the space is going and what I believe will remain important.

    Data platform for Retrieval Augmented Generation

    Retrieval augmentation has emerged as a key concept for combining generative AI with data, representing arguably the first thing to learn about the space. I summarised it in the “RAG and other concepts” section of the last article, so if the concept is new to you, the three bullet points outlined there may help.

    In order to be able to do RAG, you need a platform for your data and it may not be the one where it is currently held. A likely scenario is that data you wish to integrate with AI is spread across multiple platforms rather than conveniently batched up in one place anyway – in our clients, organisational knowledge is often spread across documents in Microsoft 365 (Teams and SharePoint), various data sources in Azure (e.g. structured data in Azure SQL or Cosmos DB, files in Azure BLOBs, perhaps some other flavours too), and some single-purpose SaaS applications. While you *may* have some success going directly to a myriad of platforms like this, there are two fundamental reasons why it’s likely to be difficult:

    • The data in its native form will not be suited to AI – it will not be chunked or represented as vector embeddings, meaning that poor answers are likely to be returned due to issues with relevance and similarity search (both needed by generative AI)
    • Establishing which data source to go to when (across all of the prompts and queries your users might enter) is likely to be difficult, especially when results should be returned in seconds – similarly, responses which combine data from multiple sources will be a challenge if you’re hopping across them

    So, what’s often needed is a vector database which also acts as a data aggregation point. This allows you to run one retrieval operation across the right kind of data for AI, where data from your various sources has already been brought together and converted to embeddings. We favour Azure Cognitive Search in our solutions today since it has lots of connectors, a ready-made indexing platform, and support for vector storage, but as discussed last time many vector database options have sprung up in the AI era - from dedicated vector DBs such as Pinecone, Qdrant and Weaviate, to additions to existing technologies like Azure Cosmos DB (MongoDB flavour), Databricks, and Redis. Microsoft promote Azure Cognitive Search for generative AI applications and it does have some fairly unique capabilities, but we regularly review options in this fast-changing space.

    See the “Generating vector embeddings” section for more on what vectors are why they’re needed in AI solutions.

    Azure Cognitive Search – a competitive advantage for RAG?
    While just about every data platform under the sun now has a vector database offering (I count three options from Microsoft alone - Azure Cognitive Search and two Cosmos DB options), an interesting consideration comes up in terms of choosing between search index and database architectures for storing vectors (i.e. what I described earlier as your RAG platform). Microsoft quite heavily promote Azure Cognitive Search as being especially suited to “AI on your data” solutions, by virtue of things possible with a search engine but not (easily) with a database. In particular, Cognitive Search offers a hybrid search option which combines both vector and full-text searching in the same query. The benefit of this can be improved accuracy of answers from the AI, stemming from increased relevance of initial results retrieved. The theory (quite logical) is that whereas embeddings are great for finding related concepts, keyword matching/full-text search works better with specialised terms, product codes, dates, names and so on because of the nature of exact matching.

    We use this option in our solutions today and get good results, though without some fairly academic research it’s hard to pin down whether it’s definitively related to what happens in a hybrid search. In Cognitive Search, hybrid entails combining vector search and keyword search but also a re-ranking step based on “deep learning models adapted from Microsoft Bing”, all of which is detailed in a Microsoft article Azure Cognitive Search: Outperforming vector search with hybrid retrieval and ranking capabilities. The article goes some way to explaining Microsoft’s testing, methodology, and results - and therefore their rationale for positioning Azure Cognitive Search as the answer to retrieval augmented generation – all I can say here is that it works for us at the moment, but we’re open minded as to whether this is the only game in town.

    Expertise in your RAG platform of choice is key – and you may need to bring in support or consultancy if Azure Cognitive Search (or your chosen vector database) isn’t a common skill today.

    Chunking

    Chunking refers to the practice of splitting long documents which go beyond the limitations of prompt size, e.g 4000 or 32000 tokens for GPT-4 (a token is around 4 characters of text). Remember that RAG is all about retrieving some data/information to give to the AI in a big long prompt, but the limitations we have today mean that a long document will never fit into the prompt in its entirety. What we need is for the most relevant part(s) of the document to be passed to the AI – and that means the documents need to be split into chunks in the RAG data platform. Additionally, models used to generate vectors have similar limits on the maximum input, so chunking is needed both for storing your data in the right format as well as retrieving it. The cut-off point for a chunk is equivalent to around 6000 words if you’re using the Azure OpenAI embeddings models for vector generation, so chunks need to be smaller than that. You can split your documents into:

    • Fixed-size chunks
    • Variable chunks
    • A hybrid, with some special chunking strategies added (e.g. to deal with specific formats in your documents like tables in PDFs or smart art)

    In our experience, that last point needs some special thought - I expand on it in the later section on “Content tuning”.

    Getting chunking right is vital. I speculated in the last article that some of my poor results with the “Azure OpenAI on your data” accelerator were due to inadequate chunking - there is a chunking mechanism in there, but it’s not used under all circumstances and the parameters used in the chunking script may not have suited my data.

    In terms of existing tools to help you implement chunking, there are various scripts and options out there. The LangChain splitter is a common one and Semantic Kernel, Microsoft’s AI orchestrator library, also has one. Whatever script or approach you use, in most cases you’ll need to integrate it into your indexing/ingestion pipeline so that as documents and data change and need to be re-indexed, the chunking and other steps happen automatically. More on this in the “Content ingestion/indexing” section.

    The following Microsoft documentation is a good read on chunking and related considerations:

    Chunk documents in vector search - Azure Cognitive Search | Microsoft Learn

    Generating vector embeddings

    As touched on earlier, in most cases your AI solution will be much more powerful if your data is converted from its original form (e.g. text in a document) to embeddings. This allows concepts like similarity search, which is where much of the power of ChatGPT and generative AI comes from, in particular the feeling that the AI understands what you’re asking for regardless of the exact words you used. Most classic search solutions rely on keyword matching - a search for the word "dog" will only get results containing “dog". However, cats are somewhat related to dogs - and both are related to household pets. When your information is represented as embeddings, these semantic links and relationships can be understood – enabling AI solutions which use search, classification, recommendations, data visualization and more. The approach can work not just across text, but across other content types like images, audio, and video – different content types can all be converted to embeddings, enabling interesting scenarios like finding images and video related to concepts discussed in a conversation or document.

    Embeddings are created by passing your data (e.g. text inside a document) into an AI model which returns the information as embeddings, i.e. arrays of numbers. OpenAI have this image which nicely represents the process:


     

    Most solutions using Azure OpenAI will generate their embeddings using a model behind the Embeddings API e.g. text-embedding-ada-002. New versions get created as models evolve, and since these use different weights/measures internally the format is different, some care is needed that your embeddings generation matches the AI model you’re querying/prompting against.

    AI orchestration

    When developing AI applications, it quickly becomes apparent that some middleware is needed to do some of the heavy lifting of storing data and calling plugins. LangChain emerged as a popular open source library for this, followed by Semantic Kernel as a Microsoft equivalent. Semantic Kernel provides quite a few valuable functions:

    • Connectors to vector databases – including Azure Cognitive Search, but also Azure PostgreSQL, Chroma, Pinecone, Qdrant, Redis, Sqlite, Weaviate and a couple of others
    • A plugins model – allowing you to call out to other apps and systems from the conversation the user has with the AI. If you heard about ChatGPT plugins (e.g. those for Expedia, Zapier, Slack etc.) then this is the SK equivalent – and since the model provides an abstraction over different plugin architectures, both OpenAI and Azure OpenAI plugins can be used. Importantly, SK also provides some ready-to-go plugins, allowing you to do some common operations easily – calling out to a HTTP API, doing file IO, summarising conversations, getting the current time etc., and also doing some things LLMs aren’t suited to such as math operations
    • Memories – context is crucial in generative AI. The AI needs to understand things previously said in the conversation, so the user can ask contextual questions like “Can you expand on that?” Additionally, SK provides the concept of document memories, enabling the AI to have context of a particular document the user is working with closely. In this case, SK does the work of generating vectors embeddings for documents (e.g. those uploaded by the user in a front-end app), thus joining up several of the concepts discussed here

    The real power of orchestration comes with chaining plugins and functions together in both predetermined and non-predetermined ways. In the latter case, we are allowing the LLM to decide how best to use a set of additional capabilities to meet a certain goal i.e. a request made by a user in a prompt which is extremely interesting. For this to be effective, functions need to be described well so that the AI can decide whether they will be useful. The concept of giving the AI agency to decide which tools from an extended toolkit may be useful for a given task (i.e. beyond what it was initially trained on) has huge potential for organisational use. Consider an insurance company offering home/car/pet insurance policies to a large client base – with the right set of plugins, it would be possible to make complex requests in prompts such as:

    “Find all clients with a total annual contract value in the bottom 50%, and for each generate a personalised e-mail recommending policy extras not currently taken. Upload the draft e-mails to SharePoint and post a summary of client numbers and key themes to the ‘Client Retention’ team in Microsoft Teams to allow review”.

    Such a request could simplify a complex data analysis, content generation, and approval exercise massively, not only reducing effort and cost but potentially bringing in new revenue through the campaign results. The capability is ground-breaking because we are able to approximate human work – taking a fairly open-ended input and establishing the process and tools to get to an outcome, perhaps via certain milestones. This is generative AI supporting automation within the workplace, leveraging GPT’s ability to process data, identify anomalies, establish trends, generate content, and take action via plugins.

    Semantic Kernel is particularly strong in this, with several planner types offered to suit different “thinking approaches”. Simple cases will use the ActionPlanner, with more complex multi-step processes using one of the others:


    See the planner capability in the SK docs for more info.

    Content tuning

    In the Chunking section earlier I touched on some of the complexities of chunking for specific content, such as tables in PDF files. Attention needs to be paid to what’s IN the files you are working with – not all content is created equal, and text in paragraphs is more easily understood by AI than tables, graphs, and other visualisations. Some of the specific examples we’ve run into where the AI did not initially give great answers on include:

    • Tables (in both PDF and Office docs), especially:
      • Long tables spanning multiple pages
      • Tables where some rows are effectively a “sub-header row”
    • Scanned/OCR’d documents where the content is effectively an image
    • HTML content
    • Images
    • Smart art
    • Document structure elements (headings, subheadings etc.) which convey semantics

    We needed to take specific steps to deal with such content, and as mentioned in the last article I think it’s where accelerators like Azure OpenAI on your data can run out of steam. For a production-grade AI platform, you’ll need to establish what you need to solve for in this area and prioritise accordingly - there’s almost no upper limit to how much tuning and content optimisation you could implement. Note also that while I label this “content tuning”, the tuning actually takes place in your platform mechanisms – your content ingestion pipeline and the chunking script/code most specifically. You’re not changing content to suit the AI, because the business will create content as the business needs to. That said, one tactic for special content may to index a modified version of a file rather than the original – so long as you have a mechanism for ongoing ingestion of content created by the business.

    So what are the specific steps you might need to take? A possible toolbox here includes:

    • Modifying chunking to recognise long tables and adopt tactics such as:
    • Create a larger chunk than normal so the entire table fits into one
    • Ensure the table header is repeated every time the table is split
    • Implementing ‘document cracking’ (aka document understanding) using something like:
      • Microsoft Syntex – perhaps to leverage its extraction capabilities with important values inside documents (e.g. contract value, start date, end date, special clauses etc.); this can ensure vital details are indexed properly
      • Azure AI Document Intelligence – similar to Syntex, using the Layout model allows you to crack PDFs or images to text, even if it’s a scanned document where the content is actually an image

    Both of those document cracking approaches (Syntex and Azure Document Intelligence) allow tables to be processed since they understand headers, rows and columns.

    In cases where high value information is expressed in such constructs, be ready to spend time in this area gradually tuning and improving the AI’s understanding of the content. To close, perhaps considering the image helps convey why gen AI needs help in this arena:

    Content ingestion/indexing

    All the previous aspects need to be worked into an indexing pipeline of some sort which can continually ingest data from source platforms - the only exception would be if you’re creating a simple solution based on a one-time upload of some static content, which is certainly more straightforward. Most scenarios, however, require generative AI to work against continually changing data (e.g. new and changing documents in Microsoft 365), and this means ensuring all of your steps to support RAG - in terms of content processing, chunking, embeddings generation and so on - are called as part of an automated pipeline.

    But what triggers the process? You could run on a scheduled basis, but in many cases you can piggyback onto existing content indexing mechanisms which may be scheduled or based on detection of content changes. Another benefit of Azure Cognitive Search as the RAG platform is the support for indexers (see the list of connectors above). In our solutions, to bring GPT capabilities to documents stored in Microsoft 365 we use the SharePoint indexer in Cognitive Search to do the initial gathering, but extend using skillsets to integrate document cracking, chunking, embeddings generation and other steps into the ingestion process. A few considerations come with this, including:

    • The SharePoint indexer is still in preview at the time of writing
    • ACS has certain thresholds of how many indexes and indexers you can have – this varies based on pricing tier, but needs consideration when indexing at scale
    • The SharePoint indexer doesn’t currently deal well with some content scenarios such as deletions and folder renaming – this can lead to content staying in your gen AI platform when it shouldn’t, and missed content and/or broken links in citations

    On the second point, our team have needed to augment the indexer to deal with these shortcomings. On the first, we have some views on challenges Microsoft might be running into with the SharePoint indexer (consider ACS ingesting a Microsoft 365 tenant with 30+ TB of data for example) – and we hope this isn’t one of those cases where Microsoft tech gets pulled without even making it out of preview. Having Cognitive Search index documents in SharePoint is a common scenario for many reasons, not just generative AI – leaving the world to create their own indexing mechanisms would take away a big value-add for Microsoft’s premier search technology.

    Summary

    Today, there’s no such a thing as a genuine turn-key platform for “generative AI on large amounts of your organisational data across different platforms”. On a related note, Microsoft 365 Copilot is amazing for many scenarios (and we had early exposure through the limited Early Access Program), but it’s not the answer to every generative AI use case. Sure, data from other platforms can be integrated via Copilot plugins, but in my view the pattern is better suited to small scale ‘callouts’ to the other systems (e.g. read or write a record) – this isn’t quite the model for “ingest TB of data from different company platforms to work with gen AI”.

    However, with a talented team (or partner), such platforms can be built in a few weeks or months depending on your scope, and many parts of the stack will come from assembly of building blocks which exist already. Without a doubt, lots of the challenges above will be abstracted further in the next year or two – but at the same time, I’ll be surprised if Microsoft or anyone else cracks all parts of the puzzle in a way that works for everyone. Some elements will always be organisation-specific, and priorities will vary. Cost will always be a factor too – budgets will be found for AI projects demonstrating a path to return, but no-one wants to license a hugely expensive product only to find it can’t be easily configured or extended to work with company apps, data, and processes.

    Similarly, no-one wants to spend a year building a platform because the team didn’t know what they were doing or weren’t following developments closely. Being plugged in to the firehose of generative AI changes is vital to avoid missteps and wasted effort. For implementors, I feel this is the new web development or the new databases - solutions of immense value can be built, so relevant expertise will be in demand. Following a series of “AI hacks” and client projects this year, I’m feeling good about how we’re shaping up at Content+Cloud/Advania to respond to this new era.

    More fundamentally, the results we’re seeing from combining GPT (via Azure OpenAI) with our client’s organisational data are hugely encouraging and show the power of generative AI in the workplace. Seeing the AI perform reasoning and answer deep questions over organisational data which came from different platforms and in different formats provides a vision into how AI will power organisations and how work will get done over the next few years. As I keep saying, it’s a magical time.

    Tuesday 5 September 2023

    Integrating your data with ChatGPT - exploring Microsoft's "Azure OpenAI on your data" accelerator

    The idea of combining the power of ChatGPT and LLMs with organisational data has caught the attention of many. It seems to form the basis for many of the conversations I'm having with CIOs and tech leaders at the moment, and with good reason I think. After all, if you could "train" ChatGPT/generative AI everything about your company, your products and services, clients, employees and expertise, past projects and other valuable information, the potential would be huge. If you could further add a sprinkling of the most relevant content on the internet such as the latest industry regulations, analyst reports, or information from accredited suppliers, the potential could be increased further. "Instead of searching and creating, can't I just ask generative AI to give me what I need?" is a common theme of questioning. In my view we're only starting to understand the possibilities and accuracy rates, but in our client projects so far where we've integrated organisational data with ChatGPT, the results are pretty incredible. As one example, being able to ask natural language questions about past projects and get high quality, easy to understand answers, seems to bring out organisational knowledge in a powerful way that helps with decision-making and winning business.  

    There are many approaches to integrating custom data with AI. For most Microsoft-centric organisations, when we talk about ChatGPT it's actually Azure OpenAI which is the starting point for generative AI. This is because it allows safe and controlled use of OpenAI models such as GPT-4, but delivered with all the benefits of trusted Azure such as improved privacy controls, data sovereignty, governance policies, and integration into existing cloud billing. The approach described here revolves around Azure OpenAI and you'll need to have an instance of the service created. 

    Focus of this article
    With this context, this article covers:
    • Core concepts when integrating data with ChatGPT/Azure OpenAI
    • Overview of Azure OpenAI on your data, with a focus on integrating Microsoft 365/SharePoint data in particular
    • The setup process for Azure OpenAI on your data
    • What the solution looks like and findings from testing
    • My thoughts on where the solution fits in combining AI with your data
     

    RAG and other concepts in integrating data with ChatGPT and gen AI

    Stitching together custom data with LLMs requires work. There are several overarching approaches, including training your own model (expensive and complex), fine-tuning an existing model (limited to small pieces of data), to techniques like Retrieval Augmented Generation (or RAG) which essentially combine searching across your dataset - that's the retrieval part - with the answer and content generation we commonly associate with LLMs. RAG is essentially a multi-step process, consisting of at least these steps:

    • Take user prompt and search across a dataset (i.e. your organisational data) for relevant information 
    • Construct a long, detailed prompt for the LLM which includes the fetched data - this is known as grounding
    • Generate a natural language response based on the retrieved information

    The response will therefore feel like ChatGPT has not only been trained on internet data, but your custom company data too. The user does not know or care that a few things have happened under the surface. RAG is essentially the approach used by Microsoft 365 Copilot, where the data being returned in the initial step is from the Microsoft Graph - documents, relationships, meetings, 
    activities, and other data in Microsoft 365.

    In RAG, information is often converted to vectors or embeddings to better support natural language processing.

    Overview - Azure OpenAI on your data  

    To help with the data integration question, Microsoft provide the Azure OpenAI on your data capability (shortened to "AOI on your data" in this article). This is effectively a PaaS accelerator where much of the back-end complexity of integrating LLMs with your data is taken care of. It takes care of creating a back-end data store, allowing your custom data to be ingested, creating embeddings/vectors from your data (at least in some circumstances - more on that later), and allows you to quickly deploy a sample app to provide a basic user interface with some of the useful features you might want (e.g. chat history and citations). It does use resources in your chosen Azure subscription though - you'll either create these at the time of initial config or point to resources you've already provisioned.

    Azure Cognitive Search is a key ingredient

    In Azure OpenAI on your data, the key technology which allows your documents and data to be combined with AI is Azure Cognitive Search. Cognitive Search provides the information store from which the initial information is retrieved, before feeding this into the prompt to ChatGPT/the LLM. Conceptually you can use any queryable data platform in Retrieval Augmented Generation, but it helps a lot if the platform can store vector data. Azure Cognitive Search has been extended with this capability, but know that many vector database options have sprung up in the AI era - from dedicated vector DBs such as Pinecone, Qdrant and Weaviate, to additions to existing technologies like Azure Cosmos DB (MongoDB flavour), Databricks, and Redis. Microsoft promote Azure Cognitive Search for generative AI applications, and it does have some fairly unique capabilities. Azure OpenAI on your data supports the following data sources:

    • Azure BLOBs
    • Files you upload
    • An existing Azure Cognitive Search instance you have (which could hold information you've indexed from lots of sources)

    Needless to say, the last option is the most powerful and flexible, so it's the one we'll look at here. One reason is that Azure Cognitive Search has an array of connectors which will allow you to bring in content quite easily from lots of platforms. These essentially break down as:

    • Native Microsoft connectors:
      • SharePoint Online, Azure SQL, Azure Cosmos DB, Azure MySQL, Azure BLOBs, Files, Tables, Data Lake Gen 2 etc.
    • Third party connectors - there are many, including:
      •  Adobe AEM, Amazon S3, Atlassian, Bentley Connectwise, Box.com, Elasticsearch and lots more - see the ACS connectors gallery
    • Your custom connector:
      • Essentially you can index anything by generating some JSON conforming to a particular structure

    Using the 'existing Cognitive Search' option in Azure OpenAI on your data

    As you might expect, you need an Azure Cognitive Search instance already and to have some data indexed, so if you're experimenting with this you'll need to get one created. If you're interested in "AI on your data" I recommend spending the time on this - it will help you understand how to combine ChatGPT with all sorts of data and platforms.

    Unfortunately the free tier of ACS is not supported for AOI on your data, so you'll need an instance created on at least the 'Basic' tier (£61.05 per month in UK pricing at this time). A good resource for getting started is Create an Azure Cognitive Search service in the portal - the process described there will get you the base service provisioned in Azure. The next step is to connect to some content.

    Indexing content in Microsoft 365/SharePoint Online with the SharePoint indexer

    One popular scenario will be to combine ChatGPT/Azure OpenAI powers with the knowledge contained within documents in Microsoft 365. Sure, it's exactly what Microsoft 365 Copilot will do when it arrives, but for me there are still many reasons to explore going this way - perhaps in addition to adoption of Copilot. For one thing, licensing of all users in an organisation may be a difficult investment case at $30 per user per month - it's unlikely to be something rolled out to the entire organisation for most. In contrast, a tool you stitch together yourself could be - and it could be quite cost effective since there are building blocks like Azure Cognitive Search to support the journey. An AI strategy which combines Microsoft 365 Copilot usage (for those who derive the most value), with a supplementary AI tool which understands organisational data but has no per-user costs, could be a powerful approach to leveraging AI over the next few years. Regarding the latter, Azure Cognitive Search can bring together data from many sources quite easily - meaning it's a good foundation for AI that understands LOTS of how your organisation works. A key benefit is that it can go beyond just data in Microsoft 365. 

    To get set up with Azure Cognitive Search indexing some of your M365/SharePoint content, I recommend following these instructions:

    SharePoint indexer (preview) - Azure Cognitive Search | Microsoft Learn

    Note that there are some technical steps in there since the config is done via Postman and the ACS REST API, but the process doesn't take too long. Once you've done this, it's now time for the fun part - configuring Azure OpenAI on your data and pointing to your Cognitive Search instance. 

    Configuring Azure OpenAI on your data with ACS

    The config steps for this part are done in the Azure AI Studio for your Azure OpenAI instance. As a reminder, you can get to this from the main Azure portal - your OpenAI instance will provide a link. 

    Once there, head into the chat playground and find the "Add your data" tab. Click the "Add a data source" button as shown below:

    In the dropdown which appears, select the Azure Cognitive Search option:


    In the next dialog you're going to point to your Azure Cogntive Search instance by selecting the parent Azure subscription then choosing the ACS service. Note that you also select a specific index within Cognitive Search here - which is why you need all the Cognitive Search config to be in place already using a process like that described above in the "Indexing content in Microsoft 365/SharePoint Online with the SharePoint indexer" section: 

    The next step involves telling ACS how to establish the various bits of data to display in search results. Since the '10 blue links' we associate with search results are always comprised of a title, a URL, a filename and a snippet of content, we need to tell ACS what they should be for the content being indexed. If you were indexing SQL data this might need more thought, but since SharePoint content is a set of files which naturally have these elements the mappings are quite logical. Just use the dropdowns to map each field to the relevant item specified when you created the indexer:

    The final option relates to semantic search in Azure Cognitive Search, which is the ability of ACS to semantically understand relationships between concepts in your data. I'd recommend treating this as an advanced capability that you might not start off with - it's chargeable for one thing, and we've been finding good quality results without it, most likely because vector search is already doing some of this. So, I suggesting skipping past this one for now:  



    The final step is to confirm your settings:

    Once confirmed, you'll be back in the main area of the chat playground with your configuration displayed. Note the "limit responses to your data content" checkbox - this constrains the LLM to only your added data and ignores the core internet data it knows already. Whether you check this or not will depend on the solution you're building (i.e. whether you want both sources involved), but I suggest that you definitely want this during testing at least:

    Config is now complete and we can think about the front-end interface and starting to test. 

    Deploying the sample app front-end

    Azure OpenAI on your data provides a deployable web application which can serve as the front-end. In reality, this isn't something you could deploy to an organisation without further work but it can be useful for testing and/or to accelerate the creation of a real front-end app. To provision it into your Azure subscription, start by finding the "Deploy to" button in the top-right hand corner of the Azure OpenAI Studio:

    Choose your preferred option, but in my case I'm choosing the web app:

    Specify the details for your web app - here's what mine looked like:




    Once the web app has finished deploying, the AOI Studio will display this in the top-right corner:


    Alternatively you can navigate straight in with the URL you specified. When you get there you'll see a basic web app which is talking to your data:


    Looks good! But is it the promised land of ChatGPT and generative AI that truly understands your data? I'll start to answer that here, but there's a lot to consider so I expand on things in the next article - for those working in this space it's worth discussing findings and recommendations in more detail. 

    Testing generative AI on your data

    In short the results from my testing were.....mixed. I put this down to the Azure OpenAI accelerator taking care of some things for you, but for a production-grade solution my view is that you need more control and there's more work to do. Take this how you wish, but for now we are not using the "AOI on your data" accelerator in our client projects at Advania/Content+Cloud which combine generative AI and custom data. We're using similar principles and the very same technologies, but more 'grown-up' approaches based on the Microsoft documentation and other info. More on

    Background - my scenario and data for testing

    As a set of documents to interrogate, I'm using some of Microsoft's earnings reports from recent quarters. I spend quite a bit of time analysing these each quarter to understand Microsoft performance and strategy - they are full of dense information and it would be highly beneficial to be able to ask the AI simple questions and get simple answers, rather than lengthy digestion and interpreting of the contents which I do today. The documents take the format of both PowerPoint documents and Word transcripts from the quarterly earnings calls. I only have a few documents but as I say, they are full of complex information - here they are in the SharePoint document library which ACS is indexing:

    The Word call transcripts look like this:

    The PowerPoint files look like this:

    Results overview

    So let's ask some questions of the data. Initial results seem quite promising, like the answers in this converation thread:

    Looks good! Any solid "generative AI on your data" solution should help you understand how it's finding the answers, and expanding the citation helps me see the source content:

    However, the solution runs into challenges with some requests. Here's an example which I feel should have been answered:

    That's a bit surprising because the answer isn't hard to find in the document set. In a different case, I see a bit of hallucination happening. The data is actually being misunderstood, and an answer is given but it's incorrect. The question I'm asking should again be quite easy to obtain from the documents - total revenue for a specific quarter:

    The reason I know it's incorrect is because the answer is quite easy to find in both the PowerPoint and Word documents. Here it is in the deck for example:

    Expanding the citation starts to explain what's happening here:

    The AI has found something referring to revenue for the quarter, but in fact these numbers relate purely to Intelligent Cloud, one of Microsoft's segments, rather than total revenue. The fact that this part of the discussion in the call transcript relates purely to this has has been misunderstood. This is obviously somewhat concerning. As we combine AI with our data, the need for accuracy and precision tends to increase compared to consumer uses of ChatGPT for example. So why is this happening? Let's consider this and expand out into overall conclusions.

    My high-level conclusions on Azure OpenAI on your data

    My speculation on why AOI on your data doesn't always give great results in these cases comes down to what it does and does not do. Specifically, I put the AI misses above down to the fact that the data is not chunked properly. Sidebar - in the context of AI on your data, "chunking" is a key concept and refers to the practice of splitting long documents which go beyond the limitations of prompt size, e.g 4000 or 32000 tokens for GPT-4 (a token is around 4 characters of text). Clearly, a long document in it's entirety will not fit into the maximum prompt size allowed by LLMs today, so the typical approach involves splitting documents into smaller chunks. Indeed, Microsoft's documentation for AI on your data is explicit in calling out that you might need to do this - the "Ingesting your data into Azure Cognitive Search" section of the AOI on your data documentation (also linked below) discusses this and links to a commonly used 'data preparation' script - however it's something critical you'll need to take care of if you're building any kind of production solution. In some ways, this illustrates the issue with Microsoft's AOI on your data solution today - while it helps in provisioning a starter point for some elements, it doesn't necessarily do the hard bits which you'll need.

    By it's nature, Azure OpenAI is an accelerator which tries to simplify the complex aspects of combining AI with your data, but realistically it cannot take care of everything. Colleagues and I are currently viewing it as a low-code route to AI on your data, and like many low-code solutions there are some trade-offs and you hope you don't run into brick walls. In Power Apps for example, it's possible to break past constraints by calling out to an Azure Function to run custom code or bringing in PCF components to go past out-of-the-box UX controls. In the same way, it's necessary to understand where the boundaries lie with AOI on your data. Let me try to be more specific.

    Where Azure OpenAI on your data helps and where it doesn't

    AOI on your data is helpful in the following ways: 

    • Provisioning a sample web app front-end to Azure App Service - this uses a GitHub sample which isn't a bad starting point, and the solution provisions an App Service and App Service Plan for you. The sample code surfaces capabilities such as SSO auth, chat history and citations, various config options in app settings, and while the UX is very basic it certainly could be extended (the exact sample used is linked below)
    • Provisioning a back-end data store - a Cosmos DB instance used to store chat history, which is configured with 'provisioned throughput' capacity mode (i.e. consumption-based pricing), and the Azure Cognitive Search instance if you're not pointing to an existing one 
    • Hooking up the front-end to the back-end - integrating the sample app to various infrastructure pieces via app config settings - your Cosmos DB, Azure Cognitive Search instance, and your Azure OpenAI instance etc.
    • Helping you connect Azure OpenAI in a basic way to simple custom data sources - as described above, this provides the basics to connect to Azure Blob Storage, the file upload option, and an existing Azure Cognitive Search instance (the approach used in this article)
    However it's less helpful with other things you need:
    • Chunking of your data/content - when you bring an existing Azure Cognitive Search instance, which you'll do for anything other than Azure Blobs or the upload option (e.g. when you want to connect to a wider set of documents in Microsoft 365/SharePoint), the solution will use the data in it's non-chunked form - resulting in potential accuracy challenges
    • Generating vectors/embeddings from your data - this is required to provide similarity search, the capability that allows ChatGPT and generative AI to be so powerful in truly 'understanding' the training data
    • Support for a wide variety of data - the solution supports Word, PowerPoint, PDF and some simple file types (.html, .text, .md) but for anything else you're on your own. Additionally, the processing of these formats is somewhat 'black box' and if it doesn't do the right things for you (e.g. deal with images, graphs, or tables in your PDFs in the right way), it seems there's no control to improve things
    • Aligning with enterprise-grade Azure architecture practices - support here is patchy, and I could imagine some organisations may feel the solution doesn't quite align with their Azure standards and governance. For example, if your Azure OpenAI instance is protected by a vNet and private endpoint, Azure OpenAI on your data can connect to this if you complete an application form but not otherwise. Storage accounts with private endpoints are currently not supported
    Providing a production-grade front-end which you can roll out to the business - in the end, the solution is deploying a sample app, and sample apps aren't meant for production - they are meant as a starting point for development. We've found there's fairly significant coding work to do on this front, and for our client projects (and internal deployment) we choose to use a different GitHub sample as our starting point to this one (there are several around and we've looked at all the major ones)

    In the end, if your goal is to get ChatGPT (by which we really mean Azure OpenAI) talking to your data in Microsoft 365 or Azure, then you'll need to understand some of the deeper mechanics and building blocks involved in creating these solutions. My view is that while AOI on your data takes core of some useful pieces on the journey, those pieces aren't necessarily where the most complexity is. Of course, the capabilities of Azure OpenAI on your data will expand from where they are at the time of writing - there's absolutely no doubt about that. However, my recommendation is to consider the accelerator as the starting point for a technical team to use in a project - either simply as a reference architecture off to the side, or as the basis of a solution they will expand quite significantly. It's a great entry point to the space, but perhaps not the entire solution to providing a solution to the business which combines generative AI and organisational data.   

    Beyond sample apps - delving deeper into building "AI on your data" solutions

    In the next article, I'll go into more detail on some of the concepts you're likely to need to deal with in building a production "AI on your data" solution, and also some of the Microsoft-centric building blocks which are useful like Semantic Kernel. By the way, I certainly wouldn't want to claim I personally have all the answers - some of the wider thinking described above comes from my talented Advania/Content+Cloud colleagues, and even as a collective we're finding that this is definitely an emerging space where things are moving quickly and there's a lot to learn. Consider this info more as an attempt to share key findings and conclusions perhaps - but if Azure OpenAI on your data on it's own doesn't answer all the questions, in the next article I'll share more thoughts on what might work.

    It truly is an exciting time, and the possibilities of AI with organisational data are huge from our perspective.


    References

    Wednesday 12 July 2023

    My real-world Microsoft Syntex demo videos - and a note on Copilot

    I've written quite a lot about Microsoft Syntex AI on this blog and spoken about it at various conferences, and my firm view is that while the arrival of ChatGPT and Microsoft Copilots changes many aspects of how we work, neither fundamentally change the value Syntex can bring to an organisation. I recently gave a talk with the snappy title "AI choices for apps and automation in 2023 - understanding AI Builder, Azure Cognitive Services, Microsoft Syntex, and Azure OpenAI" at the excellent European Power Platform Conference in Dublin, and as you might infer, this covered Syntex alongside other options in the Microsoft AI toolbox. Along with some other fun conversations, I had feedback from a couple of attendees along the lines of "those Syntex demos are great, how could we show our colleagues?" - so this prompted me to get the videos narrated and uploaded to YouTube. Here's a shot from the conference by the way, it was a great event:


    You can find these videos below. If you watch them, I'd suggest that listening to the voiceover or enabling captions will give you a better understanding of what's being shown. But while we're here, I think it's worth expanding on the the relevance of Syntex today - does Syntex get disintermediated by ChatGPT and Microsoft 365 Copilot, given their ability to directly answer questions of your documents and data?

    Syntex in the era of ChatGPT and Microsoft Copilots

    AI has always had a wide variety of tools and approaches, but for many it's more confusing than ever now - notably, I find some execs are conflating ChatGPT with AI in general, rather than seeing a broader pictire. Regarding Microsoft Syntex, it's certainly true to say generative AI like ChatGPT didn't exist a couple of years ago when Syntex was introduced - the AI landscape has truly changed dramatically in that time. So it's entirely valid to question how things fit together and whether the newer technologies remove the need.

    In short, neither of those technologies diminish the value Syntex AI can add to a business - if anything, they will be increasingly used together, as Microsoft have shown with the Syntex plugin for Microsoft 365 Copilot.  

    Syntex has unique capabilities when it comes to understanding what's in your documents and allowing you to derive insights and automate processes in which they are involved. Because Syntex is trained  specifically by a human on a representative set of your key documents (machine teaching, not machine learning) - it builds a greater understanding of the different variations, and ultimately a more granular comprehension of your documents. If you want to reliably detect (i.e. classify) which documents are which in your Microsoft 365 tenant - and this is powerful because contracts, board packs, proposals, statements of work, order forms, purchase orders, receipts, safety reports, risk assessments etc. are all very different documents used in different ways - Syntex is the technology to do that. Syntex is also the technology to extract the most relevant info from your documents, thus helping you to unlock data trapped inside documents and automate processes. The possibilities are endless, and Microsoft 365 and SharePoint have evolved to be an intelligent platform capable of so much more than simply allowing documents to be thrown in there.

    The examples below try to give a flavour of this. They are both real-world scenarios from either inside my company (Advania/Content+Cloud) or work we've done with clients. While not shown in these videos, we also have a few more examples - such as implementing Syntex in the insurance industry to understand insurance policy documents and accelerate approvals. One powerful aspect of Syntex is that because it's AI rather than OCR (which looks for content in a specific place in the page or document, such as would be the case for invoices from one company), the AI has more intelligence and allows for a lot of variation within instances of the document. Consistency or uniformity between the documents is not necessarily required. 

    Both videos have 1-2 mins of context setting before the demo starts.

    Example 1: Syntex fundamentals - accelerating our SOW process

    In this first example, we look at Microsoft Syntex AI fundamentals in a real-world process - bringing automation to our client engagement process at Advania/Content+Cloud. We run a lot of projects for our clients, and in each a Statement of Work is created to describe the work, it's scope, the project costs, and more. Syntex helps accelerate the weekly pipeline review of upcoming projects and creation of the engagement documentation. Take a look:




    Example 2: More advanced Syntex - automating a risk assessment process

    Where the first example focuses on identifying Statement of Work documents in our tenant and analysing the documents to understand the project pipeline, this next example relates to risk assessments - in this case, AI is used to automate the first pass of documents received by subcontractors. Syntex reads the documents and if certain information is not found, it automatically rejects the submission and e-mails the subcontractor - attaching the original document along with a message detailing the missing information. A Power BI analytics dashboard provides insights on the process and overall compliance levels. In this case, Syntex AI is taking the burden off a human team and ensuring they focus on the more complex/higher risk cases:



    Summary

    Hopefully those videos give you more insight into how Microsoft Syntex works and how it gets used in practice. As more emerges on Microsoft 365 Copilot (still not expected until end 2023 for General Availability), it's becoming increasingly clear that it is designed to work alongside Syntex rather than replace it. Any time a lower level of understanding of your documents is required than is supported by Microsoft 365 Copilot - and there will be many such scenarios as you pursue your AI and automation goals - Syntex will still be needed to provide that in-depth, process specific capability. Copilot will be able to call into Syntex if you have it, unlocking more scenarios such as asking questions of a document or asking Copilot to summarise the document based on Syntex capabilities. In other words, another example of the "better together" product story that Microsoft work hard on. 

    You didn't think Microsoft were going to cannibalise one of their own products unnecessarily did you? :)

    Monday 17 April 2023

    Manage Azure OpenAI and ChatGPT/GPT-4 costs

    In my last post I showed how to get started with Azure OpenAI, the service which is effectively "Microsoft-hosted ChatGPT" but also includes other OpenAI models. In particular I showed how to integrate ChatGPT with the Power Platform via a custom connector that talks to your instance in Azure. If you're doing anything with Azure OpenAI it's a good idea to monitor costs, particularly if the service will be open to a few consumers - it's not the cheapest Azure service, and costs could accumulate quickly in some usage patterns. The good news is that it is possible to monitor Azure OpenAI costs just like any other Azure service - this means using Azure Cost Management, and you just need to the right configuration to zero in on this service in particular. As with any Azure service it's not possible to put a hard limit in place by default - you could with some custom automation, but only if you implement that. 

    What you can do of course, is use Azure Cost Management to implement a Budget which will notify you when costs are passing defined thresholds. This can alert an operations team that consumption is higher than expected, at which point some investigation and/or intervention action can occur. With many Azure services this is better than shutting down production use, which would leave teams scrambling to work out why a critical process is not working.

    This article focuses on how to put such a Budget and alerting mechanism in place. 

    Indeed, that's one of the benefits of using Microsoft's Azure OpenAI instead of the API provided by the OpenAI organisation - in addition to the service meeting all usual Azure standards related to security, support for private networking, regional support, and compliance, you can work with Azure OpenAI through regular Azure service conventions and management tools too. 

    Creating an Azure Budget to monitor Azure OpenAI costs

    If you've ever created an Azure Budget to monitor another service, the process is no different - it's simply a question of finding the right filter for Azure OpenAI. An important note on this:

    Potential challenge - Azure OpenAI options may not appear in the filter list
    Something you may run into (I did) when creating a Budget for Azure OpenAI is that there are no relevent filters in the filters list - meaning it's not available for selection. Part of this is expected - if you try to filter on 'ServiceName' expecting to see an option for OpenAI, you won't since it falls under Azure Cognitive Services (and the documentation helpfully calls this out). However, sometimes you won't see anything specific to OpenAI - in particular, when trying to configure the filter for your budget using attributes such as ServiceName, Product, Meter, MeterCategory, MeterSubcategory etc. If this happens, most likely it's because you are trying to create the Budget at a scope which has no OpenAI usage yet. Filters are dynamically created based on usage, so you may need to incur some (and wait a few hours) before your Budget can be created. One option could be to raise the Budget scope (e.g. create at the subscription level rather than resource group) if you have usage elsewhere in your organisation. Either way, once you have valid usage at the scope you're creating for you should see the options in the list.

    I provide valid filters you can use below. 

    Given the varying scopes a Budget can be created at, there are a couple of ways to do it. The process I outline below creates it at the subscription level (i.e. covering all resource groups in that sub) - but creating at the RG level or the overarching management group level are alternatives,

    The process

    We start by heading into Cost Management in the Azure portal, and then into 'Budgets'.

    Once there, hit the 'Add' button to create a new one. The key step is to add a filter for one of the Azure OpenAI fields - in the image below I'm using MeterSubCategory = Azure OpenAI, but there are several possible options (detailed below):

    From there, enter the other details you require from your budget - for example the amount and frequency:
    On the next page, define the alert conditions - for example in the image below, I'm asking to be alerted both when Azure forecasts we'll hit 80% of the budget and when the actual spend hits 80%:
     
    That's it - your budget should now be created and Azure will start monitoring shortly. The key thing is really understanding what to filter on for Azure OpenAI. There are some options here in fact, so let's explore them.

    How granularly do you want to manage costs? Filter options relevant to Azure OpenAI 

    Depending on how granular you want to get with monitoring specific Azure OpenAI usage, the following filter options could be used in your Azure Budget:

    Filter Effect
    MeterSubCategory = 'Azure OpenAI' Monitor all OpenAI usage
    Product = 'Azure OpenAI - Text-Davinci' Monitor the specified model only (Text-Davinci in this case)
    Meter = 'Text-Davinci Tokens' I believe filtering on this will allow you to monitor specified model consumption only (as opposed to model training, which would have a different value)
    Service Family = 'AI + Machine Learning' [Slightly different but including for completeness] - this would allow you to monitor ALL AI usage, including Azure Cognitive Services

    In short, you can configure your Azure Budget with varying degrees of granularity. In most cases you probably want to use "MeterSubCategory = 'Azure OpenAI'" to measure all Azure OpenAI usage, but hopefully that gives you a sense of the other options.

    Using Azure Cost Analysis to monitor OpenAI usage

    Creating an Azure budget will help you become aware if costs are beyond what is expected (via the alerts), but sometimes you just want to do some ad-hoc analysis of what's happening. This can be done by heading into the 'Cost analysis' area:

    Now go into the 'Services' view (still in preview at the time of writing):


    In the list of services displayed. if you expand Azure Cognitive Services you'll find your OpenAI usage listed there:


    As ever, you can use the controls in Cost Analysis to change the period so you can compare costs for different periods to establish trends.

    Sometimes Excel is better though. Cost analysis will also let you download an Excel file, and the image below shows what your line(s) for Azure OpenAI will look like - see the highlighted row:

    As a final note on this, you can configure these Excel files to be automatically generated on a schedule and copied to an Azure BLOB storage container you have. This is done in the 'Exports' area - if you need more detail, I covered how to do it for Microsoft Syntex costs in my Syntex Pay As You Go - how it helps and how to use it article and the process is exactly the same. This will save you the job of manually generating Excel files, and can form the basis of departmental cross-charging, weekly/monthly analysis, or any number of similar FinOps scenarios.

    Summary

    Creating an Azure budget to monitor costs is likely to be an essential step for any organisation starting to work with Azure OpenAI, whether it's for ChatGPT or something else. One of the benefits of Azure hosting is that all the typical service constructs apply, including Cost Management functionality like Azure Budgets. Defining the correct filter is the key step, and if you don't see options in the list then my suggestion is to reference the explanation in the highlighted box above.

    In addition to cost management, you may wish to monitor other aspects of usage such as the number of calls made and how many tokens are used. See the 'Monitoring Azure OpenAI services' link below for more information on this.
    Useful documentation pages