Category: Microsoft
Category Archives: Microsoft
LookUp column shows up as [object Object] for single column in board view
Hi,
I have seen similar questions from this topic, but I couldn’t really apply to my problem.
I have a SharePoint list which one of the lookup columns retrieves data from another list.
This new column [Evaluated Property] allows multiple selection from the LookUp column it originates from.
When viewed in list mode, the multiple selection LookUp columns results are visible (1st picture).
However, when I create a board view, I get [object Object],[object Object].
I figure from other threads here in the discussion group that this can be solved using a JSON custom formatting. However, this did not seem to work. I am unsure how should I do this formatting since I am not familiar with JSON coding.
Did anyone face this same issue and could suggest me how to handle this?
Regards,
Lucca
Hi, I have seen similar questions from this topic, but I couldn’t really apply to my problem. I have a SharePoint list which one of the lookup columns retrieves data from another list. This new column [Evaluated Property] allows multiple selection from the LookUp column it originates from. When viewed in list mode, the multiple selection LookUp columns results are visible (1st picture). However, when I create a board view, I get [object Object],[object Object]. I figure from other threads here in the discussion group that this can be solved using a JSON custom formatting. However, this did not seem to work. I am unsure how should I do this formatting since I am not familiar with JSON coding. Did anyone face this same issue and could suggest me how to handle this? Regards, Lucca Read More
Exchange Hybrid Configuration Wizard error – root element is missing when connecting to 365
Hi Exchange Brain trust,
I have an Exchange 2016 environment where I recently joined a Exchange 2019 server to move everything and eventually decommission 2016 server. Everything is configured manually to match what we currently have in 2016 server – configuration wise, they both are identical now. We don’t have any mailbox on-prem. Its just being used for administration and SMTP relay.
The question is, do we still have to run Hybrid Config Wizard ? The reason I’m asking is, I’m stuck on the following stage with an error I pulled my hair off for hours trying to figure the root cause. Connectivity is all working well.
Any idea would be really appreciated !
Hi Exchange Brain trust, I have an Exchange 2016 environment where I recently joined a Exchange 2019 server to move everything and eventually decommission 2016 server. Everything is configured manually to match what we currently have in 2016 server – configuration wise, they both are identical now. We don’t have any mailbox on-prem. Its just being used for administration and SMTP relay. The question is, do we still have to run Hybrid Config Wizard ? The reason I’m asking is, I’m stuck on the following stage with an error I pulled my hair off for hours trying to figure the root cause. Connectivity is all working well. Any idea would be really appreciated ! Read More
What do sign-in logs to Azure AD Identity Governance – Entitlement Management tell me
BLUF: I’m seeing a few user accounts (members and guests) that are showing up in sign in activity to Azure AD Identity Governance – Entitlement Management…but most other user accounts (members and guests) do not show up with sign-ins against that app, why would I be seeing sign-in logs for that, and what exactly am I seeing?
We have about 50 internal users (members) and 500 external users (guests)…out of those typical sign-ins I mostly see then within the apps that they are utilizing, however there are a few user accounts (members and guests) where I’m seeing sign-in logs specifically to the application name = Azure AD Identity Governance – Entitlement Management. We do have 100+ apps in which we have setup access packages for external users, but I haven’t seen any other sign in activity to apps that they haven’t been given permission to access, this seemed to have started around first of June 2024. I’m just curious as to what I’m actually seeing when I see a user sign-in log showing up for Application = Azure AD Identity Governance – Entitlement Management.
BLUF: I’m seeing a few user accounts (members and guests) that are showing up in sign in activity to Azure AD Identity Governance – Entitlement Management…but most other user accounts (members and guests) do not show up with sign-ins against that app, why would I be seeing sign-in logs for that, and what exactly am I seeing? We have about 50 internal users (members) and 500 external users (guests)…out of those typical sign-ins I mostly see then within the apps that they are utilizing, however there are a few user accounts (members and guests) where I’m seeing sign-in logs specifically to the application name = Azure AD Identity Governance – Entitlement Management. We do have 100+ apps in which we have setup access packages for external users, but I haven’t seen any other sign in activity to apps that they haven’t been given permission to access, this seemed to have started around first of June 2024. I’m just curious as to what I’m actually seeing when I see a user sign-in log showing up for Application = Azure AD Identity Governance – Entitlement Management. Read More
Quick,B00ks Error R6025 – How to Resolve?
I’ve encountered Quick-Books Error R6025 recently and I’m not sure how to fix it. It happens randomly when I’m working in Q-B Desktop. What does this error mean, and what steps can I take to resolve it? Any insights or suggestions would be greatly appreciated!
I’ve encountered Quick-Books Error R6025 recently and I’m not sure how to fix it. It happens randomly when I’m working in Q-B Desktop. What does this error mean, and what steps can I take to resolve it? Any insights or suggestions would be greatly appreciated! Read More
Quick-B00ks Error 163 – Need Assistance to Resolve
I’ve encountered Quick-Books Error 163 while trying to [describe the specific action or task you were performing]. Can someone please explain what this error means and provide guidance on how to resolve it? Any help would be greatly appreciated!
I’ve encountered Quick-Books Error 163 while trying to [describe the specific action or task you were performing]. Can someone please explain what this error means and provide guidance on how to resolve it? Any help would be greatly appreciated! Read More
Q-B Error 184 – Seeking Solutions
I’m encountering Quick-B00ks Error 184 when trying to [describe the specific action or task, such as logging in or accessing a particular feature]. Could someone explain the meaning of this error and provide steps to resolve it? Any advice or insights would be greatly appreciated!
I’m encountering Quick-B00ks Error 184 when trying to [describe the specific action or task, such as logging in or accessing a particular feature]. Could someone explain the meaning of this error and provide steps to resolve it? Any advice or insights would be greatly appreciated! Read More
Anywhere365 integrates Azure Communication Services into their Dialogue Cloud Platform
Every day, companies aim to help their customers realize the most value from their products and services. They do this by providing effective service through automated self-service and human assistance with customer service agents. Brands recognize the value of using AI across their omnichannel communication to ensure continuous improvement as well as prompt effective automated and human responses that better serve customers.
Azure Communication Services is Microsoft’s intelligent B2C communication platform offering agent-to-customer and automated communication API/SDKs for independent software vendors (ISVs) to engineer within their customer service offerings. Today we have great news to share; Anywhere365 incorporates Azure Communication Services into its cloud contact center offering alongside integration with Microsoft Teams. The outcome of this helps businesses achieve more with AI-powered intelligent B2C communication solutions.
Founded in 2010, Anywhere365 a Netherland headquartered company, is a fast-growing SaaS communication provider, fully developed on the Microsoft technology, that has successfully expanded globally over the last 14 years. Today more than 2,000 enterprise companies around the world trust their contact center solution, including Rabobank, DHL, Emirates, Founders Insurance Company, KPMG, Mazda, Deloitte, Aldi, Vodafone and Zeiss.
Anywhere365 has integrated Azure Communication Services to power their Dialogue Cloud platform. Incoming calls to the platform are managed by Azure Communication Services Call Automation API, which answers calls, plays audio prompts, and collects audio streams. Calls can then be directed to the appropriate agents based on their availability, using Microsoft Teams or the custom-built Anywhere365 WebAgent. Azure Communication Services also enables audio transcription in real-time using Azure AI services along with Azure OpenAI Models to generate conversation summaries for post-call analysis. Finally, Anywhere365’s Dialogue Studio allows rapid deployment and integration with Microsoft Copilot Studio.
We are excited about Anywhere365’s advancements using Microsoft technology which also includes an embedded contact center within Teams for omnichannel communication that integrates with identify services for secure communication. With it, companies have access to a native embedded contact center in their Teams environment and infrastructure. They can also decrease call handling time and improve customer experience with the use of AI technology, with features such as the ability to summarize voice conversations, translate chat messages, and autofill forms with key data from voice conversations in business apps.
“At Anywhere365, we envision a future where every customer feels heard, understood and valued. We help brands deliver exceptional customer experiences: enhanced engagement, efficient workforce collaboration, AI driven insights, and full omni-channel service experience, leveraging the power of Teams, Azure Communication Services and the Microsoft ecosystem. In addition, Anywhere365’s Agent Assist, powered by Azure OpenAI, helps agents decrease call handling time and improve customer experience” says Will Blench CEO, Anywhere365.
Anywhere365’s contact center solution is available on the Azure Marketplace enabling Microsoft clients to use their corporate discount. Now there is every reason to bring your Microsoft Teams and Azure investment to play with Anywhere365’s contact center solution.
About Azure Communication Services: Azure Communication Services enables ISVs, like Anywhere365, to interact with customers using any channel, augmenting existing customer service platforms with intelligence and automation, and helping customers use Microsoft Teams to access subject matter experts in a company from existing call centers to exceed customer expectations and empower employees.
About Anywhere365: Anywhere365 Dialogue Cloud is a native communication layer on top of Microsoft Teams and its foundational framework, Azure Communication Services. A trusted Microsoft partner, they fully leverage existing investments in the Microsoft ecosystem to streamline communications for an accurate, reliable, customer-centric experience. Their omnichannel capabilities create flexibility and freedom to seamlessly reach customers on any communication channel, facilitating speedy solutions, whilst creating the capacity to handle more requests.
Microsoft Tech Community – Latest Blogs –Read More
Seamless Transition from Workplace by Meta to Microsoft
We understand the challenges and decisions customers may face in finding an enterprise-ready digital workspace that meets your organization’s needs. Microsoft has a market-leading solution for customers impacted by Meta’s closure of Workplace and we will work to help ensure a smooth transition and customized plan to help you manage this change.
Why Microsoft?
Microsoft offers a communications and community solution built upon familiar Microsoft 365 productivity tools and designed to foster collaboration, community, and engagement at scale. We have a robust employee experience platform that deeply integrates with common tools and is backed by Microsoft’s administrative, security, and compliance capabilities.
With Microsoft, you can:
Leverage the unified communications and collaboration solution across Microsoft 365, Microsoft Teams, and Microsoft Viva to enhance workforce productive and employee experiences
Migrate from Workplace by Meta to Microsoft Viva Engage, a leading communication and community platform that includes knowledge management, deep analytics, AI capabilities, and flexible and out-of-the-box events.
Keep all employees connected with Microsoft Teams, the place where over 320 million people chat, meet, call, and collaborate to achieve more together.
Deliver flexible solutions designed for different employee groups like information workers, frontline employees, and remote, hybrid, and dispersed global workforces.
Reduce total cost of ownership and administration of your communication tools through special offers for new and existing Microsoft customers transitioning from Meta.
Ensure data is safe, protected by enterprise-grade security, threat protection, and compliance standards as part of Microsoft Trust.
Tailored Transition Support
Transitioning to a new platform can be daunting. We have support to ensure a seamless switch whether you are an existing Microsoft customer or new to our platform:
Personalized migration plans tailored to your organization’s specific needs.
Special introductory pricing for our Viva Communications offering.
Partner and FastTrack support for managed deployment, adoption, and access.
Training and resources to get your team up to accelerate adoption and ROI.
Ongoing support from our dedicated team of experts.
Next Steps
We hope that Microsoft can support your organization’s goals and the next steps for a successful transition. We are committed to supporting you every step of the way and look forward to welcoming you to the Microsoft 365 community. Learn more about the Microsoft communications solution and contact your account team to get started.
Additional Resources:
Microsoft Communications and Communities plan
Microsoft for Frontline Workers
Microsoft Tech Community – Latest Blogs –Read More
Get the most out of any Teams Rooms meeting with speaker recognition and Copilot
AI-powered speaker recognition technology has now expanded to all Teams Rooms on Windows devices, regardless of the microphone type. This was previously only available with intelligent speaker equipment in the room. Now any Teams Room on Windows can enhance meeting experiences with precise speaker attribution and intelligent insights from Copilot. Everyone can be recognized and get the most from Copilot with our cloud technology, Teams Rooms devices such as Surface Hub 3, and other devices certified from partners.
Microsoft’s intelligent speaker recognition analyzes the distinct vocal characteristics of each speaker, such as pitch, tone, and speaking style. We think of it as a voiceprint for each participant, akin to a fingerprint for their voice.
There are several benefits to enrolling your voice to enable speaker recognition. Background noise is suppressed so that calls and meetings are easier to hear with noise suppression using voice isolation. Intelligent recap and Copilot are enabled because speakers in meetings are identified and whatever they say is attributed to them in the transcript.
In a hybrid meeting without speaker recognition, the video and audio feeds of participants in the room are assigned to the location (e.g., Conf room 1245) rather than each speaker. This makes it difficult to identify individuals’ contributions, summarize everyone’s perspectives, or address action items.
With speaker recognition, Teams Rooms can identify speakers during live transcription in shared meeting rooms, ensuring clear and precise voice capture for every participant. This allows you to effortlessly track who said what during the meeting through the meeting transcript and to enable intelligent meeting recap and Copilot.
Getting started is easy for IT and individual users
Identifying each speaker is a crucial input for Copilot in Teams. It utilizes the meeting transcript so it can deliver summaries, insights, and action items. End users can easily create a voice profile in the Teams desktop. Go to aka.ms/voiceprofile to quickly set it up.
For organizations, an IT admin needs to enable voice enrollment using Teams meeting policy and PowerShell scripts. For admins to enable an organization’s users and Teams Rooms, there are three easy steps:
Connect to Teams PowerShell
connect-MicrosoftTeams
Enable speaker recognition for the Teams meeting policy that is assigned to your Rooms
Set-CsTeamsMeetingPolicy -Identity MTRRoomsUS -roomAttributeUserOverride Attribute-AllowTranscription $true
Enable enrollment for the Teams meeting policy that is assigned to your users
Set-CsTeamsMeetingPolicy -Identity USUsers -EnrollUserOverride Enabled -AllowTranscription $true
Note: Please replace “-Identity MTRRoomsUS and USUsers” with the correct policy names for which you want to enable this feature. Alternatively, you can use the Global policy.
Get the information and enrollment scripts you need to enable voice profiles, speaker recognition, and the intelligence of Copilot in your organization at Overview of voice and face enrollment – Microsoft Teams | Microsoft Learn.
Even if you are still waiting for approval to use voice and face enrollment, you can turn it on now for the Teams Rooms you have. This will immediately distinguish individuals from the room and help users get the most out of intelligent recaps and Copilot.
Biometric profile security you can count on
We know security and privacy is of the utmost importance for organizations. Microsoft takes our commitment to ensure data security, including biometric profiles, very seriously.
The voice and face data for users is encrypted at rest and in transit and is protected by Microsoft’s security and privacy policies and practices. The voice and face data for users is stored in the same region as their Microsoft Teams data and storage is GDPR compliant. Users can unenroll their voice or face profile at any time. Profiles are automatically deleted when a Teams account is deleted or if not used for one year. Learn more about data handling and retention practices here.
Get started today
We are excited to make this cloud-powered feature available now for all existing microphones first on Teams Rooms on Windows. Later this year, the feature will expand to Teams desktop for bring your own device (BYOD) meeting spaces. Teams Rooms on Android devices will follow in 2025.
While we’re delighted to extend the capability of speaker recognition to more rooms, it’s important to note that the quality may not match that of an intelligent speaker device. Intelligent speakers are designed with multiple microphones to provide high-quality audio, maximizing accuracy in recognition and transcription and boasting an industry-leading reduction of word error rate. In rooms where top-quality transcription and attribution are imperative, it’s worth it to assess the benefits of integrating intelligent speaker hardware certified for Teams. Find devices certified for Teams at aka.ms/teamsdevices.
Use these resources to enable voice profiles, speaker recognition, and Copilot for your organization’s meetings now:
Overview of voice and face enrollment – Microsoft Teams | Microsoft Learn
Manage voice recognition technology controls for an Intelligent Speaker
How users create a digital voice profile in Teams
Microsoft Tech Community – Latest Blogs –Read More
Unified Security Operation Sentinel Vs Defender Tables
I have a question regarding the Unified SOC portal. In the session below, they highlighted one advantage: the ability to use Defender and Sentinel Tables together. However, both the SignInLogs and DeviceLogonEvents tables are already accessible in Sentinel through the Defender connector. Am I missing something, or did they use an incorrect example to demonstrate an advantage that Sentinel already provides?
Unified Security Operations Platform GA launch and exclusive demo
I have a question regarding the Unified SOC portal. In the session below, they highlighted one advantage: the ability to use Defender and Sentinel Tables together. However, both the SignInLogs and DeviceLogonEvents tables are already accessible in Sentinel through the Defender connector. Am I missing something, or did they use an incorrect example to demonstrate an advantage that Sentinel already provides? Unified Security Operations Platform GA launch and exclusive demo Read More
Green screen appears after device has been idle for more than 2 hours (Windows Insider)
My Acer Nitro 5 laptop, running Windows 11 with Insider Program installed, has been idle for a little more than 2 hours and a green screen appeared. The device tried to repair itself, but nothing happens. The Green screen mentions a failure of Windows Insider.
I cannot access Safe Mode or Bios.
What can be done?
My Acer Nitro 5 laptop, running Windows 11 with Insider Program installed, has been idle for a little more than 2 hours and a green screen appeared. The device tried to repair itself, but nothing happens. The Green screen mentions a failure of Windows Insider. I cannot access Safe Mode or Bios.What can be done? Read More
Customizing filters
Hello, i’d like to know if there is a way to group certain contents of cells and filter by that main group. E.g, )please see attached) I’d like to group “Toronto, ON”, “Ottawa, ON”, “Markham, ON …” into “ON”; “Montreal, QC”, “Quebec City, QC” into “QC” and filter by the provinces only. The way I have it now is with an extra column with just the provinces’ names in there. Thank you!
Hello, i’d like to know if there is a way to group certain contents of cells and filter by that main group. E.g, )please see attached) I’d like to group “Toronto, ON”, “Ottawa, ON”, “Markham, ON …” into “ON”; “Montreal, QC”, “Quebec City, QC” into “QC” and filter by the provinces only. The way I have it now is with an extra column with just the provinces’ names in there. Thank you! Read More
Q-B Pay_roll Update Error 557 : How to Fix and get support team ?
Q.B is a robust accounting software widely used by businesses to manage their finances, pay_roll, and other accounting tasks.
Q.B is a robust accounting software widely used by businesses to manage their finances, pay_roll, and other accounting tasks. Read More
Understanding Q.B Error 30159: Causes and get support?
Understand Q_B Error 30159, its causes, and how to get support. This guide provides solutions to resolve the error and maintain smooth pay_roll operations.
Understand Q_B Error 30159, its causes, and how to get support. This guide provides solutions to resolve the error and maintain smooth pay_roll operations. Read More
How to keep link when adjusting color of Column text in a list on sharepoint
Hi there,
so I have set up a list on sharepoint where a users name and their location will be inputted from a 2nd and 3rd list. When entering these I can’t seem to get the colour to change without removing the link. The link is used to allow quick access to update the details of the persons name or the locations details if needed
The code used to change the color is this:
Hi there, so I have set up a list on sharepoint where a users name and their location will be inputted from a 2nd and 3rd list. When entering these I can’t seem to get the colour to change without removing the link. The link is used to allow quick access to update the details of the persons name or the locations details if needed The code used to change the color is this: Read More
New LAPS rights to execute Get-LapsADPassword
Hello,
I’ve implemented the new LAPS into my AD environment, and I am currently trying to give a few support users access to read computer LAPS passwords.
According to the documentation, the CLI command Set-LapsADReadPasswordPermission should grant the necessary permissions, but it only provides rights to a few LAPS-related properties, which is not enough. Users are trying to retrieve passwords via Get-LapsADPassword -Identity $computerName on their machines, and it only works when I give them full control of the OU, which is not an option.
Which properties should they be able to read to get this working? I cannot find this information in the documentation. Is there a way to determine which permissions are required for that CLI command?
Hello,I’ve implemented the new LAPS into my AD environment, and I am currently trying to give a few support users access to read computer LAPS passwords.According to the documentation, the CLI command Set-LapsADReadPasswordPermission should grant the necessary permissions, but it only provides rights to a few LAPS-related properties, which is not enough. Users are trying to retrieve passwords via Get-LapsADPassword -Identity $computerName on their machines, and it only works when I give them full control of the OU, which is not an option.Which properties should they be able to read to get this working? I cannot find this information in the documentation. Is there a way to determine which permissions are required for that CLI command? Read More
How to fix Quick-B00ks Error 6000 1076
Hello everyone,
I’ve been encountering an issue with Quick-B00ks recently and could use some help. Whenever I try to open my company file, I keep getting an error message that says ” Quick-B00ks Error 6000 1076″. I’ve tried restarting my computer and even reinstalling Quick-B00ks, but the problem persists. Does anyone know what might be causing this error and how I can resolve it?
Thank you in advance!
Hello everyone,I’ve been encountering an issue with Quick-B00ks recently and could use some help. Whenever I try to open my company file, I keep getting an error message that says ” Quick-B00ks Error 6000 1076″. I’ve tried restarting my computer and even reinstalling Quick-B00ks, but the problem persists. Does anyone know what might be causing this error and how I can resolve it?Thank you in advance! Read More
Understand the development lifecycle of a large language model (LLM) app
Before understanding how to work with prompt flow, let’s explore the development lifecycle of a Large Language Model (LLM) application.
The lifecycle consists of the following stages:
Initialization: Define the use case and design the solution.Experimentation: Develop a flow and test with a small dataset.Evaluation and refinement: Assess the flow with a larger dataset.Production: Deploy and monitor the flow and application.
During both evaluation and refinement, and production, you might find that your solution needs to be improved. You can revert back to experimentation during which you develop your flow continuously, until you’re satisfied with the results.
Let’s explore each of these phases in more detail.
Initialization
Imagine you want to design and develop an LLM application to classify news articles. Before you start creating anything, you need to define what categories you want as output. You need to understand what a typical news article looks like, how you present the article as input to your application, and how the application generates the desired output.
In other words, during initialization you:
Define the objectiveCollect a sample datasetBuild a basic promptDesign the flow
To design, develop, and test an LLM application, you need a sample dataset that serves as the input. A sample dataset is a small representative subset of the data you eventually expect to parse as input to your LLM application.
When collecting or creating the sample dataset, you should ensure diversity in the data to cover various scenarios and edge cases. You should also remove any privacy sensitive information from the dataset to avoid any vulnerabilities.
Experimentation
You collected a sample dataset of news articles, and decided on which categories you want the articles to be classified into. You designed a flow that takes a news article as input, and uses an LLM to classify the article. To test whether your flow generates the expected output, you run it against your sample dataset.
The experimentation phase is an iterative process during which you (1) run the flow against a sample dataset. You then (2) evaluate the prompt’s performance. If you’re (3) satisfied with the result, you can move on to evaluation and refinement. If you think there’s room for improvement, you can (4) modify the flow by changing the prompt or flow itself.
Evaluation and refinement
When you’re satisfied with the output of the flow that classifies news articles, based on the sample dataset, you can assess the flow’s performance against a larger dataset.
By testing the flow on a larger dataset, you can evaluate how well the LLM application generalizes to new data. During evaluation, you can identify potential bottlenecks or areas for optimization or refinement.
When you edit your flow, you should first run it against a smaller dataset before running it again against a larger dataset. Testing your flow with a smaller dataset allows you to more quickly respond to any issues.
Once your LLM application appears to be robust and reliable in handling various scenarios, you can decide to move the LLM application to production.
Production
Finally, your news article classification application is ready for production.
During production, you:
Optimize the flow that classifies incoming articles for efficiency and effectiveness.Deploy your flow to an endpoint. When you call the endpoint, the flow is triggered to run and the desired output is generated.Monitor the performance of your solution by collecting usage data and end-user feedback. By understanding how the application performs, you can improve the flow whenever necessary.
Explore the complete development lifecycle
Now that you understand each stage of the development lifecycle of an LLM application, you can explore the complete overview:
Before understanding how to work with prompt flow, let’s explore the development lifecycle of a Large Language Model (LLM) application.The lifecycle consists of the following stages: Initialization: Define the use case and design the solution.Experimentation: Develop a flow and test with a small dataset.Evaluation and refinement: Assess the flow with a larger dataset.Production: Deploy and monitor the flow and application.During both evaluation and refinement, and production, you might find that your solution needs to be improved. You can revert back to experimentation during which you develop your flow continuously, until you’re satisfied with the results.Let’s explore each of these phases in more detail.InitializationImagine you want to design and develop an LLM application to classify news articles. Before you start creating anything, you need to define what categories you want as output. You need to understand what a typical news article looks like, how you present the article as input to your application, and how the application generates the desired output.In other words, during initialization you: Define the objectiveCollect a sample datasetBuild a basic promptDesign the flowTo design, develop, and test an LLM application, you need a sample dataset that serves as the input. A sample dataset is a small representative subset of the data you eventually expect to parse as input to your LLM application.When collecting or creating the sample dataset, you should ensure diversity in the data to cover various scenarios and edge cases. You should also remove any privacy sensitive information from the dataset to avoid any vulnerabilities.ExperimentationYou collected a sample dataset of news articles, and decided on which categories you want the articles to be classified into. You designed a flow that takes a news article as input, and uses an LLM to classify the article. To test whether your flow generates the expected output, you run it against your sample dataset. The experimentation phase is an iterative process during which you (1) run the flow against a sample dataset. You then (2) evaluate the prompt’s performance. If you’re (3) satisfied with the result, you can move on to evaluation and refinement. If you think there’s room for improvement, you can (4) modify the flow by changing the prompt or flow itself.Evaluation and refinementWhen you’re satisfied with the output of the flow that classifies news articles, based on the sample dataset, you can assess the flow’s performance against a larger dataset.By testing the flow on a larger dataset, you can evaluate how well the LLM application generalizes to new data. During evaluation, you can identify potential bottlenecks or areas for optimization or refinement.When you edit your flow, you should first run it against a smaller dataset before running it again against a larger dataset. Testing your flow with a smaller dataset allows you to more quickly respond to any issues.Once your LLM application appears to be robust and reliable in handling various scenarios, you can decide to move the LLM application to production.ProductionFinally, your news article classification application is ready for production. During production, you:Optimize the flow that classifies incoming articles for efficiency and effectiveness.Deploy your flow to an endpoint. When you call the endpoint, the flow is triggered to run and the desired output is generated.Monitor the performance of your solution by collecting usage data and end-user feedback. By understanding how the application performs, you can improve the flow whenever necessary.Explore the complete development lifecycleNow that you understand each stage of the development lifecycle of an LLM application, you can explore the complete overview: Read More
Push Notifications Not Working on Edge 126
Hello,
I have a problem on Edge 126. Push notifications suddenly stopped working. When trying to subscribe to notifications I get the following error: `DOMException: Registration failed – push service error`.
I see that it has also impacted other popular websites, like for example Facebook. When trying to enable notifications on Edge, the page just reloads and that’s it. Trying to disable and enable notifications again, doesn’t help. Tried Chrome and Opera and I’m able to subscribe and receive notifications without any issue.
Hello,I have a problem on Edge 126. Push notifications suddenly stopped working. When trying to subscribe to notifications I get the following error: `DOMException: Registration failed – push service error`. I see that it has also impacted other popular websites, like for example Facebook. When trying to enable notifications on Edge, the page just reloads and that’s it. Trying to disable and enable notifications again, doesn’t help. Tried Chrome and Opera and I’m able to subscribe and receive notifications without any issue. Read More