Organizations often face challenges in managing and analyzing their data due to the complexity of integrating various data sources, ensuring data consistency, and maintaining real-time data availability. SQL Database in Microsoft Fabric addresses these challenges by providing a unified platform that simplifies data integration, enhances data consistency, and ensures near real-time data availability.

Integrate with mirroring

One of the key features of SQL Database in Microsoft Fabric is its ability to mirror databases from Azure SQL Database directly into Fabric’s OneLake.

n today’s fast-paced tech world, understanding AI is essential for enhancing applications and staying competitive. SQL Database in Fabric is key to this transformation, offering a robust platform for integrating AI. With capabilities like Natural Language to SQL, code completion, quick actions, and intelligent insights, it empowers users to harness AI, and boost application performance.

These tools enable the creation of intelligent, responsive, and efficient applications that meet modern user demands.

Use Copilot for SQL database in Fabric

Microsoft Copilot is integrated with SQL database in Fabric, enhancing SQL management and troubleshooting. It boosts productivity by offering natural language to SQL conversion and self-help for users.

Copilot can automatically correct T-SQL code errors as they occur. By sharing context with the active query tab, Copilot offers helpful suggestions to fix SQL query errors seamlessly. You can also generate T-SQL queries by asking questions in natural language.

With the natural language to SQL capability, which translates natural language queries into SQL within the query editor in Fabric portal, database interactions become more intuitive. This integration allows Copilot to answer questions based on your database context, as Copilot is schema-aware.

n a database, users have access to several capabilities aimed at safeguarding sensitive information. These security measures are capable of securing or masking data from users or roles without proper authorization, ensuring data protection across both the database and the SQL analytics endpoints. This ensures a smooth and secure user experience, with no need for changes to the existing applications.

Understand security capabilities

Users who are often well-versed in the SQL engine and adept at using T-SQL, find databases in Microsoft Fabric easy to use.

This is because SQL Database in Microsoft Fabric is powered by the same SQL engine they’re familiar with, enabling them to perform complex queries and data manipulations. The SQL engine’s wide range of security features further allows for sophisticated security mechanism at the database level.

To create a new SQL database in Fabric, you need a new or existing workspace. Start by navigating to the Fabric portal and selecting Databases. Under the New section, select the SQL database tile. Enter a name for your new database and select Create.

To help you get started, there are three useful tiles under Build your database. The Sample data option allows you to import the AdventureWorksLT sample data into your empty database. The T-SQL option provides a web-editor for writing T-SQL to create database objects like schemas, tables, and views. The Connection strings option displays the SQL database connection string needed for connecting with SQL Server Management Studio or other external tools.

Query a SQL Database

You can query a SQL database in Fabric using similar tools available for Azure SQL Database, with the added convenience of a web-based editor in the Fabric portal. This provides an end-to-end, integrated product that simplifies analytics and fosters collaboration.

SQL Database in Microsoft Fabric is a versatile and developer-friendly transactional database built on the foundation of Azure SQL Database. It allows for the creation and management of operational databases within the Fabric environment.

Differently than Azure SQL Database, which is a Platform as a Service (PaaS), SQL Database in Microsoft Fabric is a Software as a Service (SaaS). This means that users can enjoy a low-maintenance solution, allowing them to focus even more on their core business activities.

One of its capabilities is the automatic replication of data into OneLake and conversion to Parquet in near real-time, which facilitates analytics without the need for complex ETL processes. This integration ensures that data is always up-to-date and accessible for various services within Fabric, such as Spark for analytics, notebooks for data engineering, and Power BI for visualization.

Generative AI models used for content generation are trained on large amounts of data from various sources. The content generated by generative AI models might have a machine learning bias. Machine learning bias happens when an AI model generates biased content due to inaccuracies in the data used for training the model. Ensuring accuracy, relevance, and impartiality in content requires critical thinking skills.

Critical thinking is the ability to analyze, evaluate, and improve your own reasoning. This skill is essential while utilizing generative AI. Applying critical thinking helps to verify, interpret, and improve the content you create and consume.

Critical thinking consists of:

1. Interpretation: Drawing inferences beyond the literal meaning of content generated by AI tools. For example, learners might read a description of a historical period and infer why people behaved the way they did during that time.
2. Analysis: Identify the parts of a whole and their relationships to one another. For example, learners might investigate local environmental factors to determine which are most likely to affect migrating birds.
3. Synthesis: Identify relationships between two or more ideas. For example, learners might be required to compare perspectives from multiple sources.
4. Evaluation: Judging the quality, credibility, or importance of data, ideas, or events. For example, learners might read different accounts of a historical event and determine which ones they find most credible.

Users can produce good quality AI-generated content easily, quickly, and responsibly by using critical thinking. Here are a few steps you can take to ensure you use generative AI tools responsibly.

1. Accuracy check: Double-checking facts for accuracy are essential when using generative AI tools. You can prompt Large Language Models (LLMs) to cite the sources used to generate content for your prompt. It’s important to check the cited sources to ensure they’re current, reliable, and from a reputable website.
2. Ask questions and seek feedback: While creating and consuming generative AI content, ask yourself questions such as: What is the purpose? Who is the intended audience? How reliable are the sources and information? Asking questions and seeking feedback helps improve your understanding of the content.
3. Compare and contrast: Utilize different parameters and descriptions for the same prompt to see if the content generated is relevant and similar. Use critical thinking skills to interpret the results from your prompt. Reflect on your own critical thinking skills and assess how you analyzed and evaluated the different answers.
4. Refer to the content policies: AI tool creators publish guidelines on how to use their tools responsibly. For example, the Microsoft content policy for Image Creator from Microsoft Designer prohibits content generation depicting child exploitation, child sexualization, adult content, human trafficking, self-harm, acts of terrorism, and violence against others. In summary, these guidelines aim to ensure the usage of the Microsoft Image Creator tool while contributing towards cultivating a safer online environment.
5. Legal requirements: Be informed about legislative changes on AI tool use in your work, and disclose the use of AI tools in content generation when required.

Generative AI technology offers numerous applications with the potential to have a positive impact on society. These applications span a wide range, including content creation, chatbots, virtual assistants, predictive analytics, and forecasting. Generative AI provides individuals and organizations with valuable tools to help them efficiently and effectively achieve their goals. By exploring and understanding the practical applications of generative AI tools, you can identify opportunities to incorporate AI into your life and trainings.

Here are some applications of generative AI tools that can be utilized in a training environment:

1. Content creation and design: Generative AI empowers artists, writers, designers, and anyone interested in producing original written, visual, and auditory content. Generative AI can increase artistic capabilities and enable better training content creation.
2. Personalized marketing: Businesses and other organizations can offer instant and accurate responses to customer queries using generative AI. Sales and marketing professionals use generative AI to improve customer engagement and conversion rates and achieve marketing and sales targets.
3. Chatbots and virtual assistants: Businesses and other organizations can offer instant and accurate responses to customer queries using generative AI. Based on the insights gathered from chats, chatbots provide customers with personalized support. These include product recommendations, based on the insights gathered from chats. Instant and timely customer support reduces wait times and increases customer satisfaction and loyalty. Microsoft Copilot can be anyone’s virtual assistant, helping with tasks such as meeting notes, troubleshooting issues, creating reminders, responding to emails, and providing information on the go.
4. Language translation and natural language processing: Generative AI can translate text content in real time. For example, Microsoft Edge can translate web content into over 70 languages, enabling you to read webpages in your preferred language as you browse.
5. Accessibility: Generative AI tools empower diverse linguistic communities, foster inclusivity, and break communication barriers. For example, Immersive Reader offers personalized reading assistance for learners with learning disabilities. In addition, the Speaker Coach feature of Microsoft PowerPoint helps learners enhance their presentation skills.
6. Predictive analytics and forecasting: Educational organizations can use generative AI tools to analyze historical data about learners’ performance or progress to predict dropout risks. Educators can then be notified so that they can intervene early and prevent potential risks.

Microsoft Copilot, previously known as Bing Chat, is a generative AI-powered assistant that enables search, chat, and content creation; all within a single interface. It’s powered by a Large Language Model (LLM), which is responsible for Microsoft Copilot’s extensive functionalities and user experiences. With Microsoft Copilot, you can ask questions and receive comprehensive answers. It also offers a text to image model, which can convert descriptive texts into images providing personalized user interactions.

The LLM’s ability to synthesize text, summarize information, and engage in dialogue makes it highly useful for various applications, including trainings. In this video, you explore how to use Microsoft Copilot in your training sessions.

Large language models (LLMs) are a type of neural network architecture that can process and generate conversational text, write code, abstract information, answer questions, and process text in a myriad of ways. LLMs have been trained on vast amounts of text data and can generate human-like text across a wide range of tasks. GPT is a type of LLM.

Due to extensive training from billions of language samples, including books, articles, and websites, LLMs can perform a variety of natural language tasks, such as:

1. Classification: LLMs can assign predefined labels or categories such as positive, negative, spam, not spam, news, or opinion to texts based on meaning and context. LLMs can even identify the sentiment of a text.
2. Summarization: LLMs can extract the most crucial and relevant information from text, such as news articles, product reviews, and research papers. It can then compose concise and coherent summaries.
3. Translation: LLMs can translate text between various languages while preserving the context and structure of the original text.
4. Content generation: LLMs can create new and original text such as stories, poems, jokes, slogans, and captions from given input or prompts. LLMs can also generate codes in languages like HTML, CSS, JavaScript, and Python.

Generative AI is a term for AI systems that recognize patterns in significant and complex data sets to generate original text, voice, and images based on these patterns. While some AI systems can make predictions based on existing data, generative AI is designed to use the patterns provided to generate entirely new content. As a result, generative AI tools don’t create the same output twice for the same input.

Two types of generative AI models:

1. Natural language generation Natural Language Generation (NLG) is a branch of AI that generates texts like how humans write. NLG supports applications that can process text and speech such as Generative Pretrained Transformer (GPT). GPT, a type of Large language model, can process a given prompt and generate a natural response. A practical example is Microsoft Copilot, which uses this technology to generate relevant and coherent responses.
2. Text to image In text to image, an AI model generates an image based on a text prompt. A text-to-image model like the one in Microsoft Copilot, can generate icons, patterns, illustrations, artwork, imaginary photos, and depictions of 3D objects.