What is Microsoft Fabric: A beginners guide

Microsoft Fabric is a new SaaS data platform announced in MS Build Conference on May 23, 2023.

As per the official doc

Microsoft Fabric is a unified data platform in the era of AI.  Fabric integrates technologies like Azure Data Factory, Azure Synapse Analytics, and Power BI into a single unified product, empowering data and business professionals alike to unlock the potential of their data and lay the foundation for the era of AI.

To put it simply, Microsoft Fabric simplifies and unifies data operations. From data ingestion to data engineering, data management, machine learning, real time insights and reporting, you can do all in one unified platform.

The Fabric platform is a SaaS service for data and analytical workloads. The platform provides core capabilities of Azure Data Factory, Azure Synapse, and Power BI.

The platform can be used for:

-> Data Ingestion using Data Factory

-> Data Engineering using Synapse

-> Data Science operations using Synapse

-> Data Warehousing using Synapse

-> Real Time Analytics using Synapse

-> Reporting using Power BI

-> Actions using Data Activator (coming soon)

-> Governance using Purview

Why should I care about?

One obvious questions that comes to our mind is why should I care about it? I can anyways go a create a data pipeline today using Azure Data Factory, I can create Spark notebooks on top of Synapse, and create my reports in Power BI. Why should I go and do the same in Fabric?

The answer is: simplicity and unification.

The answer is: It simplifies data collaboration across multiple data professional disciplines

The answer is: It simplifies licensing and purchasing. You don’t have to spin up multiple capacity and infrastructure for your multiple data workloads

The answer is: It simplifies setup and configuration

The answer is: It simplifies data management. No data redundancy or data silos

The answer is: It simplifies data governance

With Microsoft Fabric – a data engineer can create data pipelines to ingest data, using the ingested data, a data warehouse engineer can create data warehouses, an ML engineer using the same data can create models, and an analyst can create data models and Power BI reports – all within the same platform.

Where is my data stored?

All workloads store the data in something new called as “OneLake”. The way we have OneDrive for documents, Microsoft has introduced “OneLake” for data.

OneLake provides a single, unified storage system for data workloads in Fabric. Each tenant has one OneLake provisioned.

There is also a concept of ShortCuts in OneLake which blows away my mind. You can create “shortcuts” of your data in AWS or other clouds right inside OneLake. This means the data stays in the original source and can be used for analytical workloads right through OneLake.

What happens to current Azure analytics solutions?

As per Microsoft they will continue to remain and provide analytical capabilities as a PaaS. Microsoft Fabric simplifies this in the form of SaaS.

Existing Microsoft products such as Azure Synapse Analytics, Azure Data Factory, and Azure Data Explorer will continue to provide a robust, enterprise-grade platform as a service (PaaS) solution for data analytics. Fabric represents an evolution of those offerings in the form of a simplified SaaS solution that can connect to existing PaaS offerings. Customers will be able to upgrade from their current products into Fabric at their own pace.  

How should I get started?

Head to and try a free trial today. The free trial is for 60 days that will allow you to create warehouses, lakehouses, notebooks and more.

If you are an existing Power BI customer with Premium capacity, you can try it right away.

How to enable Fabric in my tenant?

You need to go to Power BI Admin portal and enable it.

Once on the admin portal, you can “enable” the setting for the entire org or specific security group

After 15 mins you will see an icon at the bottom left corner in your fabric portal. Clicking on it will take you to the Fabric home page.

Is Power BI same as Fabric?

Somehow I feel this is same as Power BI.

Yes, the experience, the UI and core components of Power BI portal are the same in Fabric. This means:

-> Workspaces

-> Navigation

-> Collaboration

-> Content Management

-> Admin portal

-> Capacity

will look familiar to you.

However Fabric is an umbrella platform and Power BI is a critical component of it.

What happens after free trial?

Starting June 1 you can start purchasing Fabric capacities from Azure to supercharge your data and analytical workloads.

Any more questions? Feel free to ask here in the comments.

Fabric learning resources (from Microsoft)

To help you get started with Fabric, there are several resources we recommend:

  • Microsoft Fabric learning paths: Experience a high-level tour of Fabric and how to get started.
  • Microsoft Fabric tutorials: Get detailed tutorials with a step-by-step guide on how to create an end-to-end solution in Fabric. These tutorials focus on a few different common patterns including a lakehouse architecture, data warehouse architecture, real-time analytics, and data science projects.
  • Microsoft Fabric documentation: Read Fabric docs to see detailed documentation for all aspects of Fabric.

My personal favorite is this YouTube video by Justyna Lucznik, Principal Group PM for Microsoft Fabric, on Microsoft Mechanics channel.


What is LangChain: A Beginners Guide to developing AI-powered applications


With the recent advancements in technology, there has been an ever-increasing rise in online platforms that are based on Artificial Intelligence. These platforms, such as OpenAI’s ChatGPT, have started a new wave in the world. Just type in a few words and you’ll get an entire database of factual information in one place. You don’t need to do a lot of research like in earlier days. This technology has been useful for students, teachers, digital marketers, content writers, and many more. No wonder that with its release in 2022, it has gained high popularity among the youth and working professionals. 

Moving back a few years, ChatGPT came into the picture because of GPT-3, which is a Large Language Model or LLM released in 2020. To sum up, based on GPT-3, ChatGPT was created. But what is the technology behind GPT-3? Well, it’s simple, it is a Large Language Model that uses deep learning methods to produce human-like content.  

However, it cannot be ignored that it was through ChatGPT that interest in Large Language Models reached the sky. After all, it opened up new doors for everyone around the world. Indeed, LLMs and generative AI weren’t that popular when they were released but after ChatGPT people started showing their interest in this technology. As a result, there have been significant advances in LLMs. 

Historically, it all started with the release of Google’s “sentient” LaMDA. After that, the first open-source LLM “BLOOM” was released. And then OpenAI released their next-generation text embedding GPT 3.5 models. Finally, with these giant leaps in the LLM world, OpenAI released ChatGPT – which directly put LLM into the spotlight.

Around the same time, the LLM wave ushered to the shore another useful framework, which came to be known by the name LangChain. LangChain was released by its creator Harrison Chase in the fall of October 2022.  

An Overview of LangChain – An Open-Source Python Library 

LangChain is an open-source Python library that helps in the creation of LLM-powered AI applications. LangChain is filled with amazing features and tools which are a boon for anyone wishing to develop software out of it.

At the core, the framework of LangChain is built around LLMs. It can be used for chatbots, summarization, Generative Question-Answering, and a lot more!  The primary concept behind the LangChain library revolves around its ability to interconnect different components, allowing the creation of sophisticated applications for Language and Learning Models. The chains consist of multiple components on several modules such as prompt templates, LLMs, agents, memory, etc. 

Apps need to be super smart when it comes to understanding language, and that’s exactly where LangChain comes into the picture. Through the help of LangChain, it has become super easy to connect AI models with different kinds of data sources so that you can get customized natural language processing (NLP) solutions. LangChain helps to develop applications that are powered by a language model, in particular, a Large Language Model.

The technology used behind LangChain is beyond standard API calls as it is a data-aware agentic framework that enables connections with various data sources for a more enhanced and personalized experience. So, whether you’re a developer, a data scientist, or someone who has always been curious about the latest developments in NLP technology, this article has been made for you. Let’s explore how you can unlock the power of this framework in your organization.  

Key Features of LangChain 

LangChain offers the following 6 modules. 

  1. Large Language Models and APIs 

LangChain’s primary component is a Large Language Model (LLM). At the time of writing this article, LangChain supports 20 LLMs. These include OpenAI, Hugging Face models, DeepInfra, Cohere, to name a few. You may take advantage of LLMs’ full potential for a variety of use cases by using the application programming interfaces (APIs) that LangChain offers to access, interact with, and promote smooth interaction with them. For instance, you could develop a chatbot that generates customized trip plans based on the user’s preferences and prior travels. 

  1. Prompts Templates 

The primary input to an LLM is prompt. It takes effort to come up with the right prompt for the desired output. Once the prompt is built you may use it as a template for other tasks. With LangChain it becomes quite easy to manage prompts with prompt templates. LangChain provides several classes and methods to construct and manage the prompts easily. 

  1. Chains 

To create complex applications, you need to combine multiple components together. LangChain provides interfaces for building chains. For example: you may use a PromptTemplate component with a memory component to create a chatbot. Another example, if you want to ask a followup questions to a bot, you may require a SimpleSequentialChain. Chains can also be used to add context to the conversation.  

  1. Indexes 

LLMs by default do not have contextual information (your business or domain specific information). You can use LangChain Indexes to load your company documents and use specific LangChain classes for a question and answering task. 

  1. Memory 

By default LLMs and chat models are stateless. They don’t remember the previous state. So if you build an application where you require to remember the previous conversation you need memory. LangChain provides interfaces for storing short term and long term memory. 

  1. Agents 

LLMs have limited knowledge. Ex: Open AI ChatGpt is trained with data till Sep 2021. What if you need current knowledge? That’s where LangChain Agents come into play. The following agents can help with our applications: Google Search, Wikipedia lookup, calculators 

Installation and Setup of LangChain 

  1. You need Python on your system to setup and build applications using LangChain. 
  1. Then you using pip, you will install LangChain. Open your terminal and type: 
pip install langchain 

This command will install LangChain and all its dependencies. 

  1. While LangChain can connect to 20+ LLMs, in this example I have used OpenAI. To install OpenAI in your system, type: 
pip install openai 
  1. Once OpenAI SDK is installed you need to get its key. You may put the key in a .env file and load in your Python code 
import os  
from dotenv import load_dotenv  
import openai  

import langchain  

from langchain.llms import OpenAI 


openai.api_key = os.getenv("OPENAI_API_KEY")

  1. Now you can use LangChain to interact with OpenAI with this sample code 
llm = OpenAI(temperature=0.9) 
text = "What would be a good company name for a company that makes colorful socks?" 


3 Application Examples of LangChain 

With the help of LangChain, you can create complex applications by leveraging a large language model (LLM). LangChain may be utilized to construct a wide range of applications across various industries thanks to its adaptability, customization opportunities, and powerful components.

Examples of applications that make substantial use of LangChain include the following: 

  1. Text Summarization (Data Augmented Generation) 

Do you remember writing precis in school? It was indeed a tricky task. To summarize a long text into a tiny paragraph is a tiresome and time-taking process because one has to read the entire text for hours just to find a gist. But we don’t have to worry about that anymore, because with LangChain we can easily summarize lengthy texts in a short amount of time.

You can create tools using LangChain that effectively manages text summarizing chores. Your application will be able to produce precise and succinct summaries of lengthy texts by utilizing strong language models like ChatGPT, enabling your customers to rapidly understand the core ideas of complicated publications. 

  1. Question Answering 

Building applications with question-answering features is another application for LangChain. By integrating with a large language model, your application can receive user-inputted text data and extract relevant answers from a variety of sources, such as Wikipedia, Notion, or Apify Actors.  Users looking for fast and dependable information on various subjects can find great value in this feature. 

  1. Chatbots (Language Model) 

Chatbots came into fashion a long time ago, but ever since ChatGPT, they have gained quite a popularity. As a result, the need to build such useful tools has reason among coders as well. Those days are long gone where one had to write huge codes on their own to build applications. With the advent of LangChain, this task has become super easy.

Your chatbot applications may offer a more organic and interesting user experience by utilizing LangChain’s framework and components. The language model will produce context-aware responses when users interact with your chatbots for general discussion, support questions, or other particular objectives. 

These application examples are just a few instances of how LangChain may be used to create robust and adaptable apps. Understanding the advantages of various language models can help you develop creative solutions that are tailored to the requirements of your users. 


In conclusion, the framework and modules provided by LangChain streamline the development procedure, enabling programmers to take advantage of language models’ full potential and produce sophisticated, data-aware applications.  

LangChain’s modular design and thorough documentation increase its adaptability and customizability possibilities. Applications like text summarization, chatbots, and question-and-answer systems can all be created using LangChain, providing quick and precise language processing solutions.

In general, LangChain enables people, developers, and organizations to unleash the power of language, promoting cross-cultural communication, teamwork, and creativity in the digital age. LangChain has indeed taken over the internet ever since it came into being, because of its robust features and easy-to-use technology.  

Power BI Premium Per User license

Power BI Premium Per User (PPU) license

If you ever wanted to try and use capabilities and features provided by Power BI Premium license, now is the time. Starting early Nov 2020 Microsoft Power BI team will be rolling out a new license type in preview. This new license is named: Power BI Premium Per User.

What is Power BI Premium Per User?

In our last post, we touched on two existing Power BI licenses: Power BI Pro and Power BI Premium. If you remember Power BI Premium is a capacity license. If you purchase 1 capacity of this license you can server consumption needs of 450 readers. Read the old post to understand this calculation. But then you have to pay a heft fee of close to $5000 per capacity per month.

Small and mid-size businesses who want to utilize the power of AI, paginated reports, more frequent refreshes, deployment pipelines, and many more features provided by Premium license today got demotivated by just hearing the price.

Power BI Premium per user is a new way to license premium features on a per user basis. With this new license, you get all the capabilities of a pro license along with premium features.

Power BI Pro and Power BI Premium are at the extreme ends of the spectrum. With Power BI Premium per user the gap fills (though only little).

What’s the difference between Power BI Premium and Power BI Premium Per User?

There are some differences. You can check the table below by Microsoft.

Chart comparing the Premium features per user vs. capacity
Source: Microsoft

But there are still report sharing constraints which are outlined in the table below. Example: If you create and share a report in a workspace marked as PPU, a Pro user cannot view/access that report. So you will need all the users to have PPU license to “view” the report.

How sharing works in Power BI with Premium per user
Source: Microsoft

What’s the price for the Power BI Premium per user?

Update: March 10, 2021

Power BI Premium will be priced at $20 per user per month. Isn’t that cheap?

There is no official news on the price by Microsoft. However, the good news is it will be free to use in the preview period.

As per official source: “Premium per user will be uniquely affordable and highly competitive among individual user offerings in the industry

We also don’t know if there will be a min. requirement for the number of PPU licenses.

What’s our thought?

Microsoft clearly says this new license will address the needs to provide a low cost entry point to get access to premium features. However, there will still be more cries than smiles when it comes to users who just need read access. Procuring a Pro or PPU license for them doesn’t make sense even now.

Have more questions?

Head to Microsoft official post on this to know more about scenarios and questions around this.

When is PPU License launching?

Nov 2020 this new license type is launching in public preview. It will be free to use till GA. We are excited to try and let our users and customers know our first hand experience.

Join our list to be the first one to know more about our first hand experience.

Root cause analysis in Power BI

Root cause analysis in Power BI

Microsoft Power BI has some great AI visuals which can provide an in-depth analysis of your data. In our last post we talked about an AI visual – Key Influencer visual. This visual helps in identifying factors that can impact an outcome. In that post, we analyzed what factors influence employee attrition. We also deep-dived into segments and clusters contributing to employee attrition with graphs and charts.

In this post, we will analyze and play with another AI visual – Decomposition tree.

Decomposition tree

The decomposition tree breakdowns a numerical measure into parts and analyzes what factors cause the measure to be high/low.

From Microsoft documentation:

The decomposition tree visual in Power BI lets you visualize data across multiple dimensions. It automatically aggregates data and enables drilling down into your dimensions in any order. It is also an artificial intelligence (AI) visualization, so you can ask it to find the next dimension to drill down into based on certain criteria. This makes it a valuable tool for ad hoc exploration and conducting root cause analysis.


Let’s take a well known example of employee attrition and understand why attrition is high. From the decomposition tree visual we plan to get answers to the following question:

What causes employee attrition to be high?

At the end of this post you will have an idea of how to use this visual for exploratory and visual analysis, decomposition of values by factors, and how you can use AI splits to dynamically split and understand the next factor for drill down.

Our final output could look like:

Getting Started

We install the latest version of Power BI Desktop, and click on the decomposition tree visual.

Power BI AI visual – Decomposition tree

You see two input fields “Analyze” and “Explain by”. In the Analyze field we put “Attrition %” and in Explain by we put several other fields say “Overtime”, “Department”, “BusinessTravel”, “MaritalStatus”, “Gender” etc. How to choose these fields in the first place? That’s a tricky question and we will answer this later.

Our decomposition tree when we drag Attrition % looks like:

Decomposition Tree with Attrition % metric

Attrition % overall is 16.12%. Our next step once we have added our metric is to understand:

  1. Which of the factors cause attrition % to be high?
  2. Which of the factors cause attrition % to be low?

Remember we have dragged several fields in “Explain by” section? Let’s click on the “+” sign next to the Attrition % bar.

You see the fields you have dragged. In addition, you see two more fields – High value and Low value.

Exploratory and Ad-hoc analysis

We begin with exploratory analysis by analyzing Attrition % by OverTime. Attrition % is 30.53% if OverTime is Yes. This means when OverTime is high attrition will be high.


Let’s expand this level and understand when OverTime is Yes then what’s the next factor which contributes to attrition%? Let’s explore Marital Status.

Martial Status

Attrition is high among unmarried individuals and these are the ones who over time. Let’s try adding another level to this analysis, say Department.


Unmarried individuals in the Sales department who over time contribute to 65.31% attrition! We can also verify this number by adding tooltips.

Out of 49 employees in Dept Sales with Marital Status Single and OverTime Yes, 32 of them left the company.

What if we start our analysis, not with OverTime? Let’s pick monthly income as the starting factor

Monthly Income

The visual flow is quite different here! Attrition is highest when monthly income is low and in the Sales department when OverTime is High.

With the decomposition tree, you can perform root cause and exploratory analysis by playing with the multiple factors and dimensions. You not only get a deep understanding of what’s happening in your data set, but you can also visually understand the data in a tree format.

AI Analysis

We started analyzing the factors based on our domain knowledge and understanding of the dataset. What was our rationale for choosing OverTime as the starting point of our tree?

The decomposition tree comes with another option to split the tree using AI algorithms. Remember we had two more options in our tree “High value” and “Low value”? It’s time to utilize them.

Let’s start with a blank slate and this time instead of selecting OverTime, let’s select “High value”.

AI Split

As we keep selecting High value at each level of the tree, the algorithm identifies the next level on its own. In the example above the levels chosen were Monthly Income followed by OverTime, Education Field and JobSatisfication. Attrition % is high when monthly income is between 0-2800, and so on.

In AI splits you see a bulb icon next to the level name. Once you hover on the bulb icon you get to see why this level was chosen.

On hovering the bulb icon

You can also select “Low value”. Once you select the low value you will observe that the factor and analysis changes.

A low value split

How to choose fields in “Explain by”?

Should we choose AI split or manual split?

How do we choose the fields in “Explain by”?

The best way to start analyzing the tree is using manual split based on the domain context and your understanding of the data. After 2-3 levels of manual split, you can then split the tree further using AI splits and understand the factors responsible for making a metric high or low.

There’s also a smart alternative to this. You can use “Key Influencer Visual” to understand what factors lead to Attrition = Yes. The visual will provide top factors impacting an outcome (attrition = yes), and you can put those factors in “Explain by” section of the Decomposition tree. When you run key influencer analysis on the employee attrition data set you will get the results as explained and shown in the previous blog post.

Power BI Key Influencer AI visual

You can put Age, OverTime, JobLevel, MonthlyIncome, YearsInCompany and others in the Explain by section of the decomposition tree visual and start drilling down the data.


The decomposition tree is a smart visual to breakdown a numerical measure into components. This AI visual aids in root cause and deeper analysis as shown above. You can perform ad-hoc analysis for the problem in question, understand the breakdown of values using manual and AI splits, and combine it with other Power BI AI visuals to strengthen your analysis.

One last note: to get the best of the output and results from this visual, you may want to convert numerical attributes like age, income, etc into categorical values (or bins – Example above: monthly income is broken down into 0-2800, 2800-5000 etc. bins).

PS: AI splits in the decomposition tree comes with two analysis mode: absolute and relative. We will cover this in detail in next blog post.

Next steps

If you are looking to explore the possibility of applying AI in your dataset or looking to evaluate the use of Power BI in your organization, don’t hesitate to contact us today.

Power BI Embedded Licensing

In our last post we talked about Power BI Pro and Power BI Premium. To recap, Power BI Pro is a per use license and is more towards content creation and consumption. On the other hand, Power BI Premium is a capacity license and is more for content consumption.

Rather than assigning a Pro license to every individual in your org, you can assign a premium capacity to a workspace to support large number of content viewers.

In this post we will tackle another Power BI offering – Power BI Embedded.

Power BI Embedded

Power BI Embedded is a Microsoft Azure service that lets independent software vendors (ISVs) and developers quickly embed visuals, reports, and dashboards into an application. This embedding is done through a capacity-based, hourly metered model.


Power BI Embedded is an offering by Microsoft where you can embed Power BI visuals, reports, and dashboards in a custom application or in associated Microsoft Services like Teams or SharePoint Online.

How does Power BI Embedded look like in reality?

Ok, here’s a screenshot of a Power BI report embedded inside a custom application. By custom application I mean an application which is not It can be a plain vanilla website or a WordPress website or can be a heavy application with Reporting and Analytics section.

In the screenshot below, the sections highlighted in red are part of the custom application. The “SALES PERFORMANCE REPORT” or the part highlighted in green is the Power BI report securely embedded in the application.

You can embed a visual, report, dashboard and Q&A. We have used “report” as a general content for embedding. But the description apply to any of the contents.

How can I embed a Power BI report?

There are 3 ways to embed a Power BI report.

  1. Publish to web. Simplest (and not secure) way of embedding is publishing your Power BI report to web for public access. Note: Anyone with the URL will have access to your report.
  2. No-code Embedding – Simplest and secure. This approach gives you a secure URL to the Power BI report which you can put in your application. However, this will prompt you for Org authentication.
  3. Custom Embedding using JavaScript SDK. This gives you full power of embedding capabilities. You can read more about how to embed using JavaScript SDK in our other blog post.

What licensing do I need to support Power BI Embedding?

Now, that’s a tricky question. For embedding you can choose – P SKU, EM SKU or A SKU.

The licensing to go for really depends on your specific scenario. The general answer to choosing the SKU is “where” the content will be consumed.

  • Choose A SKU if the Power BI content will be consumed in a custom application
  • Choose EM SKU if the Power BI content will be consumed in Teams or SharePoint online (SPO).
  • Choose P SKU if the Power BI content will be consumed in a custom application or Teams or SPO.

**You can even choose a P SKU if you are an enterprise or a Large ISV.

The P SKU is an umbrella SKU which not only gives embedding capabilities but additional feature sets including large read users, AI features, and other enterprise features.

Typically, enterprises go with P SKUs.

How are P, EM and A SKUs different in terms of performance?

Here’s a quick summary of each of the SKUs node performance:

Image source: Microsoft

So an A4 node is same as a P1 node in terms of performance.

It is generally suggested to start with A1 to test and benchmark your capacities, and then take necessary steps to increase the capacity.

Is Power BI Embedded free to use?

No. For production workloads you have to choose from either of the licensing types. For dev workloads, yes you can embed without purchasing a capacity. However, you may hit the token limits and reports may not render.

Next steps?

If you have any questions on this or want to explore Power BI for your organization, do contact us today.

Quick URLs for further reading

Power BI Embedded Capacity:

Developer Samples:

Power BI Embedded Playground:

I hope this post provides some understanding on Power BI Embedded, licensing and consideration for choosing this type of offering.