Hi ,

Our users are working on projects and need to access their emails. When they add their email to Outlook, they often do not select the “Sign in with this app only” option. This causes a conflict because the other MS account gets added to the “Work or School Account,” leading to issues with the Windows license. The license is supposed to be Enterprise instead of Pro, as we have Microsoft E3 licenses.

My question is, how can I disconnect the other work or school accounts via Intune, using PowerShell or another tool, to avoid having to communicate with all users to disconnect it manually?

Thank you for your assistance.

Best regards,

​Hi ,Our users are working on projects and need to access their emails. When they add their email to Outlook, they often do not select the “Sign in with this app only” option. This causes a conflict because the other MS account gets added to the “Work or School Account,” leading to issues with the Windows license. The license is supposed to be Enterprise instead of Pro, as we have Microsoft E3 licenses.My question is, how can I disconnect the other work or school accounts via Intune, using PowerShell or another tool, to avoid having to communicate with all users to disconnect it manually?Thank you for your assistance.Best regards,   Read More

​

Hi Everone! I’m hoping someone can help me please

I am trying to customise my SharePoint home page with a HTML page. I am looking to keep the sharepoint bar across the top but replace the widgets below with a HTML page with click areas.

I can add a iframe, but this doesnt fill the page.

Example below of what i would like

I already have the HTML file with click locations created.  

Hope someone can help.

Many Thanks

​Hi Everone! I’m hoping someone can help me please I am trying to customise my SharePoint home page with a HTML page. I am looking to keep the sharepoint bar across the top but replace the widgets below with a HTML page with click areas. I can add a iframe, but this doesnt fill the page.Example below of what i would like I already have the HTML file with click locations created.    Hope someone can help. Many Thanks  Read More

​

Good morning!
I’m trying to figure out how to pull the most common trends for a specific team (not numbers). I’ve done this before (a long time ago), but I can’t remember the functions to use. 

​Good morning!I’m trying to figure out how to pull the most common trends for a specific team (not numbers). I’ve done this before (a long time ago), but I can’t remember the functions to use.   Read More

​

At Microsoft Build, we announced the availability of Command R models on Azure AI. Today, we are very excited to announce the addition of two new models from Cohere: 

Cohere Rerank 3 – English 

Cohere Rerank 3 – Multilingual

Cohere Rerank 3 is considered a leading AI model for semantic reranking in search systems.  These models are available as serverless APIs with pay-as-you-go token-based billing. Accessing Cohere’s enterprise-ready language models on Azure AI’s robust infrastructure enables businesses to seamlessly, reliably, and safely incorporate cutting-edge semantic search technology into their applications.  

This integration allows users to leverage the flexibility and scalability of Azure AI, combined with Cohere’s  language models, to deliver superior search results in production. Using Azure’s AI model catalog, and with just a few lines of code, developers can implement Rerank 3 to enhance their existing search systems.   

According to Cohere, Rerank 3 offers state-of-the-art capabilities for enterprise search, including: 

4k context length to significantly improve search quality for longer documents 
Ability to search over multi-aspect and semi-structured data like emails, invoices, JSON documents, code, and tables
Multilingual coverage of 100+ languages 
Improved latency and lower total cost of ownership (TCO)

How Customers Can Enhance Search with Rerank 

Rerank models (compatible with 100+ languages) serve two primary purposes, 

It can be added to existing search systems after an initial dense retrieval stage to improve the relevancy of results, or  

it can be added to retrieval-augmented generation (RAG) systems to increase the relevancy of documents being passed to the generative model (and therefore reduce operating costs). 

Atomicwork, a digital workplace experience platform and longtime Azure customer, has significantly enhanced its IT service management platform with Rerank 3. By integrating the model into their AI digital assistant, Atom AI, Atomicwork saw over 20% in improved search accuracy and relevance, providing faster, more precise answers to complex IT support queries. This integration has streamlined IT operations and boosted productivity across the enterprise.  

“The driving force behind Atomicwork’s digital workplace experience solution is Cohere’s Rerank model and Azure AI Studio, which powers Atom AI, our digital assistant, with the precision and performance required to deliver real-world results. This strategic collaboration underscores our commitment to providing businesses with advanced, secure, and reliable enterprise AI capabilities,” said Vijay Rayapati, CEO of Atomicwork.” 

TD Bank Group, one of the largest banks in North America, recently signed an agreement with Cohere to explore its full suite of large language models (LLMs), including Rerank 3.  

“At TD, we’ve seen the transformative potential of AI to deliver more personalized and intuitive experiences for our customers, colleagues and communities,” said Kirsti Racine, VP, AI Technology Lead, TD. “We’re excited to be working alongside Cohere to explore how its language models perform on Microsoft Azure to help support our innovation journey at the Bank.”  

Enterprises of any size and in any industry can leverage Rerank to enhance their search capabilities across countless scenarios, including:  

Legacy search improvement: Improve results from legacy lexical or semantic tools 

Customer support search: Enable self-serve across complex customer support docs 

Multilingual search: Understand meaning and relevance across over 100 languages 

RAG: Retrieve most relevant answers across heterogenous enterprise data sources 

Command R+, Cohere’s flagship generative model which is also available on Azure AI, is purpose-built to work well with Rerank within a RAG system. Together, they are capable of serving the most demanding enterprise workloads in production. 

Boosting Search Quality for 100+ Languages with a Single Line of Code 

Established keyword-based search systems are deeply ingrained within a company’s information architecture, and switching to a vector database for embedding-based search is often impractical. This is where Cohere Rerank can help, providing a seamless bridge between traditional keyword-based search and the power of semantic search.  

Accessible through Azure AI Studio’s Cohere Rerank endpoint, our model computes a relevance score for a set of text documents compared to a given user query. This approach consistently yields superior search results, especially for complex and domain-specific queries, compared to traditional embedding-based semantic search. 

Why Azure AI for Cohere Rerank models? 

Cohere Rerank models are now available as serverless APIs through Models as a Service (MaaS), which is now Generally Available. This enables enterprise-scale workloads with ease. 

Network Isolation for Inferencing: Protect your data from public network access. 

Expanded Regional Availability: Access from multiple regions. 

Data Privacy and Security: Robust measures to ensure data protection. 

Quick Endpoint Provisioning: Set up a rerank endpoint in AI Studio in seconds. 

Azure AI ensures seamless integration, enhanced security, and rapid deployment for your AI needs. 

How to deploy Cohere Rerank 3 models on Azure AI studio? 

Prerequisites:  

If you don’t have an Azure subscription, get one here: https://azure.microsoft.com/en-us/pricing/purchase-options/pay-as-you-go  

Familiarize yourself with Azure AI Model Catalog  

Create an Azure  AI Studio hub and project. Make sure you pick East US, West US3, South Central US, West US, North Central US, East US 2 or Sweden Central as the Azure region for the hub.  

Create a deployment to obtain the inference API and key:  

Open the model card in the model catalog on Azure AI Studio.  

Click on Deploy and select the Pay-as-you-go option.  

Subscribe to the Marketplace offer and deploy. You can also review the API pricing at this step.  

You should land on the deployment page that shows you the API and key in less than a minute. 

These steps are outlined in detail in the product documentation. 

Please check some samples to get started – LangChain, Web Requests, Cohere Client   

FAQ

What does it cost to use Cohere Rerank on Azure?  

You are billed based on the number of prompt and completions tokens. You can review the pricing on the Cohere  offer in the Azure Marketplace offer details tab when deploying the model. You can also find the pricing on the Azure Marketplace.  

Are the Cohere models’ region specific on Azure?  

 Command R/R+/Embed/Rerank models are available as serverless API endpoints.   

These endpoints can be created in Azure AI Studio projects or Azure Machine Learning workspaces. Cross-regional support for these endpoints is available in the following regions in the US: East US, East US 2 , West US3, South Central US, West US, North Central US, Sweden Central 

Do I require GPU capacity quota in my Azure subscription to deploy Cohere Rerank models?  

Cohere mdodels are available through MaaS as serverless API endpoints. You don’t require GPU capacity quota in your Azure subscription to deploy these models.  

Cohere models are listed on the Azure Marketplace. Can I purchase and use these models directly from Azure Marketplace?  

Azure Marketplace is our foundation for commercial transactions for models built on or built for Azure. The Azure Marketplace enables the purchasing and billing of Mistral models. However, model discoverability occurs in both Azure Marketplace and the Azure AI model catalog. Meaning you can search and find Cohere models in both the Azure Marketplace and Azure AI Model Catalog.   

If you search for Cohere Rerank 3 in Azure Marketplace, you can subscribe to the offer before being redirected to the Azure AI Model Catalog in Azure AI Studio where you can complete subscribing and can deploy the model.   

If you search for Cohere Rerank 3 in the Azure AI Model Catalog, you can subscribe and deploy the model from the Azure AI Model Catalog without starting from the Azure Marketplace. The Azure Marketplace still tracks the underlying commerce flow.   

Given that Cohere models are billed through the Azure Marketplace, does it retire my Azure consumption commitment (aka MACC)? 

Yes, Cohere models are “Azure benefit eligible” Marketplace offers, which indicates MACC eligibility. Learn more about MACC here: https://learn.microsoft.com/en-us/marketplace/azure-consumption-commitment-benefit  

Is my inference data shared with Cohere?  

No, Microsoft does not share the content of any inference request or response data with any model provider.   

Microsoft acts as the data processor for prompts and outputs sent to and generated by a model deployed for pay-as-you-go inferencing (MaaS). Microsoft doesn’t share these prompts and outputs with the model provider, and Microsoft doesn’t use these prompts and outputs to train or improve Microsoft’s, the model providers, or any third party’s models.  Read more on data, security and privacy for Models-as-a-Service.  

Are there rate limits for the Cohere models on Azure?  

Cohere models come with 400 K tokens per minute and 1 K requests per minute limit. Reach out to Azure customer support if this doesn’t suffice.  

Can I use MaaS models in any Azure subscription types?  

Customers can use MaaS models in all Azure subsection types with a valid payment method, except for the CSP (Cloud Solution Provider) program. Free or trial Azure subscriptions are not supported.  

​Microsoft Tech Community – Latest Blogs –Read More 

As AI transforms the way we work, business leaders around the world are exploring ways to implement AI solutions. And technology professionals are looking to quickly build their AI skills to benefit their careers, projects, and teams.  

At the same time, organizations are confronting a skills gap. In fact, according to the 2024 Work Trend Index Annual Report from Microsoft and LinkedIn, 55% of leaders report that they’re concerned about having enough talent to fill roles in the year ahead and 76% of professionals say that they need AI skills to remain competitive. The good news is that Microsoft Learn offers skill-building resources, opportunities, and solutions to meet these critical needs.  

Business leaders and professionals care about AI skills.

To accelerate AI transformation, we recommend a skills-first approach—emphasizing skills and competencies, in addition to degrees and job histories. We suggest focusing on skill building for your whole organization:  

Take a structured approach. Begin with basic AI concepts as technical teams build the skills to onboard Microsoft Copilot experiences and create AI apps. Help business users understand how to use AI in their work, and help ensure that those in technical roles have the skills to design, build, and deploy solutions to address your organization’s unique business scenarios.  

Upskill across every role. Beyond IT, everyone in your organization plays a key role in company-wide AI adoption. To help develop, deploy, and make the best use of new AI solutions, upskill your entire workforce. 

Work with a trusted partner. Start with the AI learning hub on Microsoft Learn, which offers training to accelerate your AI transformation. With Microsoft Learn, business leaders can get the skills to craft strategic AI plans, technical teams can learn to create and implement AI applications with Microsoft AI solutions, and business users can make the most of new AI skills to supercharge their productivity.  

A skills-first approach to AI leads to skill building for every role, with Microsoft Learn as a trusted partner.

Discover the latest industry insights around AI skills in our recently published position paper Accelerate AI transformation with skill building, which highlights the experiences of customers and partners who are running AI skill-building initiatives. Offering practical guidance, it expands on key ways that you can drive successful AI transformation in your organization.  

Learn Microsoft AI with our new blog series 

Today, we’re launching “Get AI ready,” our new AI-focused series of blog posts exploring perspectives and opportunities to acquire critical AI skills. In this series, we share insights, learning experiences, resources, and ideas for individuals and organizations as we all navigate the world of AI skill building.  

Plus, we share how we’re refreshing our training offerings—and how we’re using AI to improve them—so you know that you can learn the latest skills in the most productive way. We understand the challenges, uncertainties, and benefits that come with AI, and we’re creating this series to help you find what you need to skill up for success. 

Wondering what to expect? Here’s a sneak peek into future posts:  

Deep dives into AI learning journey resources from Microsoft Learn 

Real-world AI skill-building success stories and best practices from individuals and organizations 

Microsoft as customer zero for AI adoption and what we’ve learned about skilling up our own employees 

How to foster a culture of AI learning and innovation 

How to prove your AI skills with Microsoft Credentials 

No matter where you are on your AI learning journey, Microsoft Learn meets you there with the resources you need to build and validate your skills—and we’re there for individuals, teams, and organizations alike. 

Coming next: Get AI ready: Build technical skills with the Copilot learning hub 

Stay tuned for our next post! We’ll explore the new Copilot learning hub on Microsoft Learn, created for technology professionals and filled with helpful resources tailored to specific job roles and career goals. It’s where you can find what you need to develop the technical skills to put Microsoft Copilot to work for you. In the post, we’ll include insider information from the team that creates these resources. Spoiler alert: Expect tips and tricks on how to choose your perfect Copilot experience and make the most of it to help boost your efficiency and productivity.  

Stay tuned for our next post in the blog series: Build technical skills with the Copilot learning hub.

From initial AI skill building across every role, to making the most of Copilot at your desk each day—and beyond—we look forward to sharing this AI learning journey with you as we help close the skills gap together. 

Follow us on X and LinkedIn, and make sure you’re subscribed to The Spark, our LinkedIn newsletter. 

​Microsoft Tech Community – Latest Blogs –Read More