Tag Archives: SharePoint

Legal IT

Retrieval Augmented Generation

Leave a comment

In previous articles, we talked about generative AI, its benefits, and the risks that it comes with. One such risks is the fact that generative AI can hallucinate. It also doesn’t have access to the information you keep professionally. Retrieval augmented generation (RAG) addresses both issues. In this article, we answer the following questions: What is retrieval augmented generation? What are the benefits? And how can you use retrieval augmented generation with Copilot & SharePoint?

What is retrieval augmented generation?

Wikipedia defines retrieval augmented generation (or RAG) as “a technique that enables large language models (LLMs) to retrieve and incorporate new information. With RAG, LLMs do not respond to user queries until they refer to a specified set of documents. These documents supplement information from the LLM’s pre-existing training data. This allows LLMs to use domain-specific and/or updated information that is not available in the training data. For example, this helps LLM-based chatbots access internal company data or generate responses based on authoritative sources. RAG improves large language models (LLMs) by incorporating information retrieval before generating responses.”

In other words, RAG enhances large language models by connecting them to external knowledge sources. Instead of relying solely on the information the model learned during training, RAG first retrieves relevant documents or data from a database, or your knowledge base. It then uses that retrieved information to generate more accurate and up-to-date responses.

The basic idea is simple: when you ask a question, the system searches through a collection of documents (like company files, research papers, or websites) to find relevant information. Then it feeds both your question and those retrieved documents to the language model. The model uses this context to produce an answer that’s grounded in your specific data rather than just its own general training knowledge. So, those are the three steps of retrieval augmented generation:

  • Retrieval: When a user asks a question, the RAG system searches an external knowledge base (like a company’s specific documents) for relevant information.
  • Augmentation: The retrieved information is then added to the original prompt, creating an “augmented” request.
  • Generation: The large language model (LLM) then generates a response based on this augmented prompt, using the external data to provide a more specific and accurate answer.

This approach solves several common problems with standard LLMs. It reduces hallucinations because the model a) bases its answers on actual retrieved text, b) allows the system to access current information beyond the model’s training cutoff date, and c) lets you use domain-specific knowledge without having to retrain the entire model. RAG is particularly useful for applications like customer support systems that need company-specific information. It is also useful for research assistants that work with scientific literature, or in any scenario where you need accurate answers based on a particular knowledge base.

Now, when you start researching retrieval augmented generation, you will often encounter the terms pipes or pipelines. It refers to the processing steps that transform a user’s query into a final response. They’re essentially the workflow or data flow that connects different components of the RAG system. The “pipe” metaphor comes from Unix pipes, where data flows from one process to another.

Different RAG implementations can have varying pipeline architectures. Some are simple with just query, retrieve, and generate stages. Others are complex with multiple retrieval steps, feedback loops, or parallel processing paths.

What are the benefits?

RAG offers several benefits that make it attractive for real-world applications.

The fact that it offers access to current and specific information is perhaps the most obvious advantage. Since the model retrieves information from your own database or documents, it can work with data that’s a) more recent than its training cutoff or b) with highly specialized knowledge that wasn’t in its original training data. This means companies can get accurate answers about their latest policies, recent research papers, or proprietary information. Depending on how you set it up, for law firms it can have access to your legal documentation, your knowledge base, your case files and/or documents.

As mentioned in the introduction, reduced hallucinations are another major benefit. When language models generate answers purely from their training, they sometimes confidently state incorrect information. RAG grounds the model’s responses in actual retrieved documents. This makes it cite or base its answers on real sources rather than just making things up. The result is that its output is more reliable and trustworthy.

Another significant is cost-effectiveness. With RAG you don’t need to fine-tune or retrain large language models every time your information changes. Instead, you simply update your document database, and the RAG system will retrieve the new information. This is far cheaper and faster than retraining models. After all, that requires substantial computational resources and technical expertise.

RAG also addresses the issues of transparency and traceability because you can see which documents the system retrieved to answer a question. This makes it easier to verify answers, debug problems, and build trust with users who can check the sources themselves.

A final benefit is referred to as domain adaptability. It means that you can quickly deploy the same base model across different domains or use cases by simply swapping out the document collection it retrieves from. One model can serve medical applications, legal research, or customer support just by changing the underlying knowledge base.

Retrieval augmented generation with Copilot & SharePoint

Interesting for law firms who use Copilot and SharePoint is that Copilot can be used in combination with SharePoint to enable RAG responses. Microsoft has made this integration quite powerful.

How does it work? Microsoft 365 Copilot offers a retrieval API that allows developers to ground generative AI responses in organizational data stored in SharePoint, OneDrive, and Copilot connectors. This means you can build custom AI solutions that retrieve relevant text snippets from SharePoint without needing to replicate or re-index the data elsewhere. The API understands user context and intent, performs query transformations, and returns highly relevant results from your Microsoft 365 content.

This approach offers several advantages for RAG implementations. You don’t need to set up separate vector databases: You can skip the traditional RAG setup that involves embedding, chunking, and indexing documents. The API automatically respects existing access controls and governance policies. This ensures security and compliance. Additionally, you can combine SharePoint data with other Microsoft 365 and third-party sources to create richer, more comprehensive responses.

For personal experimentation

If you would like to first experiment on your own, you can try Google’s new Notebook LM, which implements RAG technology. It’s an AI-powered research and writing assistant that helps users summarize and understand information from uploaded sources or specific websites.

Sources:

 

Legal IT

Microsoft SharePoint Syntex

1 Comment

In this blog post, we will explore Microsoft SharePoint Syntex. We focus on the following questions: What is Microsoft SharePoint Syntex? What can it do? Is Microsoft SharePoint Syntex already available? What are the benefits of Microsoft SharePoint Syntex? And what are the benefits for lawyers?

In the last year, generative AI has been making headlines. (See, e.g., our articles on ChatGPT for lawyers, on Generative AI, and on the dangers of AI). Many software companies have started integrating generative AI into their products and services. Microsoft is no exception. Two of their new generative AI services stand out: CoPilot and SharePoint Syntex. This article is about SharePoint Syntex. Our next article will be about CoPilot.

What is Microsoft SharePoint Syntex?

So, what is Microsoft’s SharePoint Syntex? It is a new product that uses advanced AI and machine teaching to help you capture, manage, and reuse your content more effectively. As the name suggests, it is in essence an add-on feature for SharePoint. (Our blog also has an article on using SharePoint in law firms). Once it is installed, it can be used in some other programs as well. (See below).

Microsoft describes SharePoint Syntex as a content understanding, processing, and compliance service. It uses intelligent document processing, content artificial intelligence (AI), and advanced machine learning. This allows it to automatically and thoughtfully find, organize, and classify documents in your SharePoint libraries, Microsoft Teams, OneDrive for Business, and Exchange. With Syntex, you can automate your content-based processes—capturing the information in your law firm’s documents and transforming that information into working knowledge.

Syntex is the first product from Project Cortex. That is a Microsoft 365 initiative that aims to empower people with knowledge and expertise in the apps they use every day.

What can it do?

Microsoft Syntex offers several services and features to help you enhance the value of your content, build content-centric apps, and manage content at scale. Some of the main services and features are:

Content assembly: You can automatically generate standard repetitive business documents, such as contracts, statements of work, service agreements, letters of consent, and correspondence. You can do all these tasks quicker, more consistently, and with fewer errors in Syntex. You create modern templates based on the documents you use most. You then use those templates to automatically generate new documents using SharePoint lists or user entries as a data source.

Prebuilt document processing: You can use a prebuilt model to save time processing and extracting information from contracts, invoices, or receipts. Prebuilt models are pretrained to recognize common documents and the structured information in the documents. Instead of having to create a new document processing model from scratch, you can use a prebuilt model to jumpstart your document project.

Structured and freeform document processing: You can use a structured model to automatically identify field and table values. It works best for structured or semi-structured documents, such as forms and invoices. You can use a freeform model to automatically extract information from unstructured and freeform documents, such as letters and contracts where the information can appear anywhere in the document. Both structured and freeform models use Microsoft Power Apps AI Builder to create and train models within Syntex.

Content AI: You can understand and gather content with AI-powered summarization, translation, auto-assembly, and annotations incorporated into Microsoft 365 and Teams.

Content apps: You can extend and develop content apps with high-volume containers, data, and rich APIs.

Content management: You can analyse and protect content through its lifecycle with AI powered security and compliance, backup/restore and advanced content management.

Is Microsoft SharePoint Syntex already available?

SharePoint Syntex was released on 1 October 2023, and is available in all countries where Microsoft 365 is offered. So, if you are a CICERO LawPack user, you can start using it already. But note that there are some differences in the availability of languages and pricing for SharePoint Syntex in Europe.

SharePoint Syntex supports 21 languages for document understanding models and 63 languages for form processing models. (The article in the Microsoft Tech Community on the availability, which is listed in the sources below, has the full list of supported languages). All languages in which Microsoft 365 is available in Europe are available for Syntex within Europe. This does not mean, however, that all languages are available in all regions. For example, some languages are only available in the US region, such as Arabic, Hebrew, Hindi, Thai, and Vietnamese.

The pricing of SharePoint Syntex depends on the type of licensing and the number of transactions, as well as on the region and currency. There are two options for licensing: per-user and pay-as-you-go. Per-user licensing costs $5 per user per month in the US and allows unlimited usage of Syntex services. The price in EUR may differ depending on the exchange rate and local taxes. Pay-as-you-go licensing charges based on the total number of pages processed by Syntex, with different rates for unstructured, structured, and prebuilt document processing.

According to the Microsoft website, the price of SharePoint Syntex in Belgium is €7,90 per user per month for per-user licensing, and €0,04 per transaction for unstructured document processing, €0,01 per transaction for prebuilt document processing, and €0,04 per transaction for structured and freeform document processing for pay-as-you-go licensing. These prices do not include VAT and may vary depending on the currency exchange rate and the Azure subscription plan. You can find the exact price of SharePoint Syntex in your region and currency on the Microsoft 365 Enterprise Licensing page (listed below in the sources).

What are the benefits of Microsoft SharePoint Syntex?

Microsoft Syntex can help your law firm automate business processes, improve search accuracy, and manage compliance risk. With content AI services and capabilities, you can build content understanding and classification directly into the content management flow. Some of the benefits of using Microsoft Syntex are:

Increased productivity: Your law firm can save time and resources by automating repetitive tasks such as document generation, extraction, classification, tagging, indexing, summarization, translation, etc. You can also access your content faster and easier by using intelligent search capabilities that leverage metadata and AI insights.

Improved quality: You can reduce errors and inconsistencies by using standardized templates, prebuilt models, or custom models that suit your specific needs. You can also ensure that your content is accurate, relevant, and up to date by using AI-powered analytics and feedback mechanisms.

Enhanced security: You can protect your sensitive data by using AI-powered security and compliance features that help you identify risks, apply policies, enforce retention rules, monitor activity, audit changes, etc. You can also backup and restore your content in case of accidental deletion or corruption.

What are the benefits for lawyers?

For lawyers in particular, Microsoft Syntex can offer some additional benefits that can help them streamline their legal workflows, improve their client service, and reduce their liability exposure.

Faster contract review: Lawyers can use prebuilt or custom models to automatically extract key information from contracts such as parties, clauses, terms, dates, amounts, etc. They can also use content assembly to automatically generate contracts based on templates and data sources. This can help them speed up their contract review process, avoid missing important details or deadlines, and ensure consistency across their contracts.

Easier knowledge management: Your law firm can use content AI to automatically summarize, translate, annotate, tag, index their legal documents such as cases, opinions, briefs, memos etc. They can also use intelligent search to quickly find relevant information across their SharePoint libraries or Teams channels. This can help them manage their legal knowledge more effectively, access the information they need when they need it, and share it with their colleagues or clients.

Better compliance and risk management: It is possible to use content management to automatically apply security and compliance policies to their legal documents based on their sensitivity, confidentiality, or retention requirements. Lawyers can also use AI-powered analytics and monitoring to identify potential issues, conflicts, or breaches in their documents and take appropriate actions. This can help them comply with their ethical and legal obligations, protect their client’s interests, and reduce their liability exposure.

 

Sources:

 

Legal IT

Using Teams and SharePoint in Law Firms

2 Comments

Upon request, we will have a closer look in this article at using Teams and SharePoint in law firms. In previous articles, we already talked about running your law practice in the Cloud with law firm management software. We also highlighted how Microsoft 365 was an essential part of that. (It was still called Office 365 at the time). For optimal results for a law firm, Microsoft 365 Business Premium is the recommended solution.

Since the pandemic started, Microsoft has been steadily improving Microsoft Teams. By now, it can be used as the central communication and collaboration hub of your law firm. It consolidates the available Microsoft 365 tools and streamlines business processes by offering team members a centralized location for all files, documents, and firm information. It allows law firms to share critical communications with their clients and their entire team, quickly, efficiently, and securely! It also enables seamless collaboration for all projects, from in-depth cases to day-to-day work by using SharePoint with other Microsoft 365 tools.

Teams as your communication and collaboration hub

You can use Teams as the dashboard from which you coordinate your communications and collaboration. Teams seamlessly integrates with the other Microsoft 365 apps, like Word, Excel, Outlook, SharePoint, but also with apps like Planner or To Do. Outlook allows you to directly access the ‘Conversations’ of the Teams site, so you can manage all your saved emails through the Outlook interface. Teams comes with its own video chat for virtual meetings, which can be recorded and shared. The free MS Bookings app allows to easily set up meetings. But note that integration between Microsoft 365 and your law firm management software is essential. So, make sure this is the case.

One of the main benefits of using the Teams / SharePoint combination lies in its collaboration functionality.  Your team and clients can share documents and collaborate on them, securely and in real time. It is perfectly possible for several people to simultaneously work or comment on the same document. And because this solution is perfectly scalable, it can be used by law firms of any size. Worth noting is also that collaborating on a SharePoint server is more secure than sending documents by email, and therefore a better solution.

Using SharePoint also offers other benefits

It comes with built in version control, where it keeps track of all changes to a document, and where you can see the full history of all versions. Needless to say, it also automatically keeps backups of all those versions.

SharePoint also offer in depth-search functionality. You can perform searches on the full text, but also on meta data. It even comes with optional wiki functionality, and its search and KMS functionalities can be further extended with third party add-ons.

Important is also that it is easy to use Microsoft 365 in a way that is compliant with EU privacy legislation. All law firms that use its software have to do, is choose local European servers as their Microsoft 365 servers. As there are no other intermediate servers involved, you are completely compliant.

Security considerations

in its articles on the annual Legal Technology Survey, Law Technology Today explicitly recommends using cloud-based solutions like Microsoft 365 as it is the most secure solution, both for law firm communications and for file sharing / storage. It notes “Many (if not the majority of) law firms that favor on-premise or hosted solutions to cloud-based platforms will cite security as the reason they refuse to move their data to the cloud. But the truth is, cloud-based solutions are considerably more secure than on-premise or hosted software.”

After all, Microsoft encrypts all data transfers as well as all the stored data, which are encrypted at both disk and file level. In other words, the data you share inside SharePoint is secure, and it is more secure than keeping your data on a local OneDrive. (Microsoft 365 administrators are recommended to switch off synchronisation with a local OneDrive to reap the optimal benefits, including enhanced security, from using the SharePoint & Teams combination).

In short, using Microsoft 365 Premium Business edition offers you a centralized and secure communications and collaboration hub, which maintains client privacy as well as legal compliance. It improves the productivity of your law firm by allowing you to collaborate more effectively, from anywhere you have Internet access.

 

Sources:

 

Legal IT

Office 365 and SharePoint for Lawyers

Leave a comment

The vast majority of lawyers use the Microsoft Office suite. It comes in different versions, and Microsoft encourages everyone to switch to Office 365. If you have not yet switched to Office 365, it may be useful to consider this. For law firms, it is advisable to switch to Office 365 Business Premium because SharePoint is also included. In this article we give some more explanation.

Office 365 is the subscription version of Microsoft’s Office suite. It is marketed as a service (rather than a product) that ensures you always have the most up-to-date modern productivity tools from Microsoft. It includes all the Office desktop apps that CICERO LawPack users are familiar with, like Word, Outlook, PowerPoint, and Excel. It also comes with extra online storage and cloud-connected features that let you collaborate on files in real time. With a subscription, you’ll always have the latest features, fixes, and security updates along with ongoing tech support at no extra cost.

Office 2016 and Office 2019 on the other hand are sold as a one-time purchase. They don’t have the level of cloud integration that offers all the real time collaboration features Office 365 does. When a new version is released, you have to buy the new version, and often that means there are many new features at once to get familiar with. With a subscription version like Office 365, you get smaller updates several times a year that are included in the subscription price. This subscription model clearly appeals to customers: as of October 2018, Office 365 has 155 million active users worldwide, and each month three million more are added.

One of the reasons CICERO LawPack is moving its customers to Office 365 Business Premium is that it comes with SharePoint. SharePoint is a web-based collaborative platform that integrates with Microsoft Office. It was launched in 2001 and is primarily sold as a document management and storage system. It has 190 million users across 200,000 customer organizations. SharePoint offers the following functionalities:

  • Enterprise content and document management: SharePoint allows for storage, retrieval, searching, archiving, tracking, management, and reporting on electronic documents and records. It also provides search and ‘graph’ functionality. SharePoint’s integration with Office 365 allows for collaborative real-time editing and encrypted/information rights managed synchronization.
  • Intranet: A SharePoint intranet (or intranet portal) is a way to centralize access to enterprise information and applications. It is a tool that helps an organization manage its internal communications, applications and information more easily (e.g. via tools such as wikis).
  • Collaborative software: SharePoint contains team collaboration groupware capabilities, including project scheduling (integrated with Outlook and Project), social collaboration, shared mailboxes, and project related document storage and collaboration. Groupware in SharePoint is based around the concept of a “Team Site”.
  • File hosting service (personal cloud): OneDrive for Business allows storage and synchronization of an individual’s personal documents, as well as public/private file sharing of those documents.
  • Custom web applications: SharePoint’s custom development capabilities provide an additional layer of services that allow rapid prototyping of integrated (typically line-of-business) web applications.

To structure and manage content, SharePoint works with:

  • Pages, which are free-form pages that can be edited in a browser.
  • Web parts and app parts are components (also known as portlets) that can be inserted into Pages. They are used to display information from both SharePoint and third-party applications.
  • Lists, libraries, and content: A SharePoint library stores and displays files and folders, while a SharePoint list stores and displays data items. Each item in a library or list is a content item. Content Types are definitions (or types) of items. SharePoint allows you to create your own definitions based on the built-in ones (like, e.g., Contacts, Appointments, Documents, and Folders).
  • Sites: A SharePoint Site is a collection of pages, lists, libraries, apps, configurations, features, content types, and sub-sites. Examples of Site templates in SharePoint include collaboration (team) sites, wikis, blank sites, and publishing sites.

If you use software for your office management, it is probably software based on Cloud technologies. In that case, it is possible that your data and documents are located on two different Cloud platforms: the software for your office management and the corresponding database are on your software provider’s Cloud solution, while all your documents are in a separate SharePoint DB instead of on a normal file server. This means that you can benefit from all the advantages of SharePoint: all documents are searchable; you can share documents instead of having to e-mail them (which is much safer), and once a document is shared you have access to all the real-time collaboration functionalities; it comes with access and version management, etc. The fact that the documents and data are on separate platforms also provides a safer and faster solution.

 

Sources: