Blog

During production, you want to optimize and deploy your flow. Finally, you want to monitor your flows to understand when improving your flows is necessary.

You can optimize your flow by using variants, you can deploy your flow to an endpoint, and you can monitor your flow by evaluating key metrics.

Explore variants

Prompt flow variants are versions of a tool node with distinct settings. Currently, variants are only supported in the LLM tool, where a variant can represent a different prompt content or connection setting. Variants allow users to customize their approach for specific tasks, like, summarizing news articles.

Some benefits of using variants are:

• Enhance the quality of your LLM generation: Creating diverse variants of an LLM node helps find the best prompt and settings for high-quality content.
• Save time and effort: Variants allow for easy management and comparison of different prompt versions, streamlining historical tracking and reducing the effort in prompt tuning.
• Boost productivity: They simplify the optimization of LLM nodes, enabling quicker creation and management of variations, leading to better results in less time.
• Facilitate easy comparison: Variants enable side-by-side result comparisons, aiding in choosing the most effective variant based on data-driven decisions.

infrastructure services

When you create a Large Language Model (LLM) application with prompt flow, you first need to configure any necessary connections and runtimes.

Explore connections

Whenever you want your flow to connect to external data source, service, or API, you need your flow to be authorized to communicate with that external service. When you create a connection, you configure a secure link between prompt flow and external services, ensuring seamless and safe data communication.

Depending on the type of connection you create, the connection securely stores the endpoint, API key, or credentials necessary for prompt flow to communicate with the external service. Any necessary secrets aren’t exposed to users, but instead are stored in an Azure Key Vault.

By setting up connections, users can easily reuse external services necessary for tools in their flows.

hrms

To create a Large Language Model (LLM) application with prompt flow, you need to understand prompt flow’s core components.

Understand a flow

Prompt flow is a feature within Azure Machine Learning that allows you to author flows. Flows are executable workflows often consist of three parts:

1. Inputs: Represent data passed into the flow. Can be different data types like strings, integers, or boolean.
2. Nodes: Represent tools that perform data processing, task execution, or algorithmic operations.
3. Outputs: Represent the data produced by the flow.

Similar to a pipeline, a flow can consist of multiple nodes that can use the flow’s inputs or any output generated by another node. You can add a node to a flow by choosing one of the available types of tools.

Explore the tools available in prompt flow

Three common tools are:

• LLM tool: Enables custom prompt creation utilizing Large Language Models.
• Python tool: Allows the execution of custom Python scripts.
• Prompt tool: Prepares prompts as strings for complex scenarios or integration with other tools.

Each tool is an executable unit with a specific function. You can use a tool to perform tasks like summarizing text, or making an API call. You can use multiple tools within one flow and use a tool multiple times.

financial

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:

1. Initialization: Define the use case and design the solution.
2. Experimentation: Develop a flow and test with a small dataset.
3. Evaluation and refinement: Assess the flow with a larger dataset.
4. 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.

feature

In addition to Azure SQL services, Azure data services are available for other popular relational database systems, including MySQL, MariaDB, and PostgreSQL. The primary reason for these services is to enable organizations that use them in on-premises apps to move to Azure quickly, without making significant changes to their applications.

What are MySQL, MariaDB, and PostgreSQL?

MySQL, MariaDB, and PostgreSQL are relational database management systems that are tailored for different specializations.

MySQL started life as a simple-to-use open-source database management system. It’s the leading open source relational database for Linux, Apache, MySQL, and PHP (LAMP) stack apps. It’s available in several editions; Community, Standard, and Enterprise. The Community edition is available free-of-charge, and has historically been popular as a database management system for web applications, running under Linux. Versions are also available for Windows. Standard edition offers higher performance, and uses a different technology for storing data. Enterprise edition provides a comprehensive set of tools and features, including enhanced security, availability, and scalability. The Standard and Enterprise editions are the versions most frequently used by commercial organizations, although these versions of the software aren’t free.

MariaDB is a newer database management system, created by the original developers of MySQL. The database engine has since been rewritten and optimized to improve performance. One notable feature of MariaDB is its built-in support for temporal data. A table can hold several versions of data, enabling an application to query the data as it appeared at some point in the past.

PostgreSQL is a hybrid relational-object database. You can store data in relational tables, but a PostgreSQL database also enables you to store custom data types, with their own non-relational properties. The database management system is extensible; you can add code modules to the database, which can be run by queries. Another key feature is the ability to store and manipulate geometric data, such as lines, circles, and polygons.

PostgreSQL has its own query language called pgsql. This language is a variant of the standard relational query language, SQL, with features that enable you to write stored procedures that run inside the database.

erp

Azure SQL is a collective term for a family of Microsoft SQL Server based database services in Azure. Specific Azure SQL services include:

• SQL Server on Azure Virtual Machines (VMs) – A virtual machine running in Azure with an installation of SQL Server. The use of a VM makes this option an infrastructure-as-a-service (IaaS) solution that virtualizes hardware infrastructure for compute, storage, and networking in Azure; making it a great option for “lift and shift” migration of existing on-premises SQL Server installations to the cloud.
• Azure SQL Managed Instance – A platform-as-a-service (PaaS) option that provides near-100% compatibility with on-premises SQL Server instances while abstracting the underlying hardware and operating system. The service includes automated software update management, backups, and other maintenance tasks, reducing the administrative burden of supporting a database server instance.
• Azure SQL Database – A fully managed, highly scalable PaaS database service that is designed for the cloud. This service includes the core database-level capabilities of on-premises SQL Server, and is a good option when you need to create a new application in the cloud.
• Azure SQL Edge – A SQL engine that is optimized for Internet-of-things (IoT) scenarios that need to work with streaming time-series data.

digital transformation

You’ve decided to implement self-service password reset (SSPR) in Microsoft Entra ID for your organization. You want to start using SSPR for a group of 20 users in the marketing department as a trial deployment. If everything works well, you’ll enable SSPR for your whole organization.

In this unit, you’ll learn how to enable SSPR in Microsoft Entra ID.

Prerequisites

Before you start to configure SSPR, you need a:

• Microsoft Entra organization: This organization must have at least a P1 or P2 trial license enabled.
• Microsoft Entra account with Authentication Policy Administrator role: You’ll use this account to set up SSPR.
• Non-administrative user account: You’ll use this account to test SSPR. It’s important that this account isn’t an administrator, because Microsoft Entra imposes extra requirements on administrative accounts for SSPR. This user, and all user accounts, must have a valid license to use SSPR.
• Security group with which to test the configuration: The non-administrative user account must be a member of this group. You’ll use this security group to limit who you roll SSPR out to.

Scope of SSPR rollout

There are three settings for the Self-service password reset enabled property:

• None: No users in the Microsoft Entra organization can use SSPR. This value is the default.
• Selected: Only the members of the specified security group can use SSPR. You can use this option to enable SSPR for a targeted group of users who can test it and verify that it works as expected. When you’re ready to roll it out broadly, set the property to Enabled so that all users have access to SSPR.
• All: All users in the Microsoft Entra organization can use SSPR.

data analytics

You’ve been asked to assess ways to reduce help-desk costs in your retail organization. You’ve noticed that the support staff spends a lot of their time resetting passwords for users. Users often complain about delays with this process, and these delays impact their productivity. You want to understand how you can configure Azure to allow users to manage their own passwords.

In this unit, you’ll learn how self-service password reset (SSPR) works in Microsoft Entra ID.

Why use SSPR?

In Microsoft Entra ID, any user can change their password if they’re already signed in. But if they’re not signed in, forgot their password, or it’s expired, they’ll need to reset their password. With SSPR, users can reset their passwords in a web browser or from a Windows sign-in screen to regain access to Azure, Microsoft 365, and any other application that uses Microsoft Entra ID for authentication.

SSPR reduces the load on administrators because users can fix password problems themselves without having to call the help desk. Also, it minimizes the productivity impact of a forgotten or expired password. Users don’t have to wait until an administrator is available to reset their password.

cyber security

Use the CIA Triad model

The CIA Triad is a fundamental model in information security that represents three core principles: confidentiality, integrity, and availability.

• Confidentiality ensures that only authorized individuals can access sensitive information. This principle includes measures like encryption and access controls to protect data from unauthorized access.
• Integrity maintains the accuracy and completeness of data. This principle means protecting data from alterations or tampering by unauthorized users, which ensures that the information remains reliable.
• Availability ensures that information and resources are accessible to authorized users when needed. This principle includes maintaining systems and networks to prevent downtime and ensure continuous access to data.

Some ways that the triad principles can help ensure security and reliability include:

• Data protection: Protect sensitive data from breaches by taking advantage of the CIA Triad, which ensures privacy and compliance with regulations.
• Business continuity: Ensure data integrity and availability to maintain business operations and avoid downtime.
• Customer trust: Implement the CIA Triad to build trust with customers and stakeholders by demonstrating a commitment to data securit

crm

Cloud management establishes effective operations for your Azure cloud estate. Successful operations require clear responsibilities and processes across all management areas.

Ready your Azure cloud operations

1. Identify management responsibilities. Cloud management spans compliance, security, resource management, deployment, development, monitoring, cost, reliability, and performance. Distinguish between central responsibilities for your entire Azure estate and workload-specific responsibilities for individual applications.
2. Establish operations teams. Choose centralized management for smaller organizations or shared management for diverse workloads. Form dedicated teams for platform tasks and specialized workload teams, then assign owners for each responsibility area.
3. Document operational procedures. Create standardized procedures for change management, deployments, and disaster recovery. Develop step-by-step guides for daily tasks and Azure scenarios, storing runbooks in a central repository accessible during incidents.
4. Manage daily operations. Establish 24/7 support through global teams or on-call rotations with automated alerts. Automate repetitive tasks using Azure capabilities to reduce errors and focus teams on strategic work.
5. Improve continuously. Conduct weekly reviews of metrics, incidents, changes, and risks. Address resource sprawl and technical debt while developing skills through Microsoft credentials and Azure training resources.

contact