12 videos
9:35
In this video, we'll walk through how to call Azure AI Document Intelligence using the REST API. We'll look at the process of extracting data from images and PDF scans, showing you how to work with the service directly without relying on a specific language SDK.
5:42
In this video, we'll walk through how to incorporate Azure AI Translation into a Fabric Data Lake solution. We'll explore how to use Fabric's embedded Synapse ML features to leverage Azure AI services directly in Spark notebooks, showing you how to enrich and transform your data using Language AI Services with a Python Jupyter notebook.
15:31
In this video, we'll walk through how to build a Document Intelligence solution inside Microsoft Fabric that uses Azure AI to pull text from scanned documents. We'll show you how to ingest that data into a Data Lake using a Spark Notebook and Synapse ML.
19:11
In this video, we'll walk through how to take a machine learning model and turn it into a working web service. We'll start by setting up the necessary resources in Azure, then move into the ML Studio to create a compute cluster and train our model. We'll cover the full process, from uploading data and training the model all the way through registering it and deploying it to a REST endpoint, finishing up by showing you how to test the endpoint and fetch the necessary authentication token.
6:23
In this video, we'll walk through the steps to export a model from Microsoft Fabric and import it into an Azure Machine Learning workspace. We'll look at how to deploy it to a real-time inference endpoint and test it both within Azure ML and from Postman, so you can start leveraging those Azure features right away.
8:16
In this video, we'll explore Azure Machine Learning's Model Catalog and walk through how to pick a pre-trained model from top providers. We'll guide you through the steps of deploying it on Azure's computing services and accessing it via a REST API.
11:34
In this video we'll explore how to enrich image data for Power BI analysis using Azure AI Vision. We'll walk through generating descriptive metadata for images and then see how to incorporate that data into a Power BI solution, following along with a live code demo.
13:48
In this video, we'll walk through how to take an AI model built in the cloud and get it running on an iPhone. We'll start by exploring the Azure Portal to set up our Vision project, then move through the steps of testing and exporting the model. We'll cover how to package it for CoreML and walk through the Xcode project setup, ending with a look at running the final result directly on a device.
10:50
In this video, we'll walk through how to create an Azure AI Custom Vision model to detect if a product has been accurately packaged. We'll start by setting up the necessary Azure resources, then move into importing and tagging images of the products. From there, we'll train the model, review its performance, and test it to see how well it identifies packaging defects.
8:43
In this video we'll explore how to use Azure OpenAI Services from a Fabric Jupyter notebook to automatically summarize large collections of user review data. We'll walk through the process of prompt engineering, securely storing secrets in Azure Key Vault, and reading and writing data to Delta tables in a Fabric Lakehouse.
10:58
In this video, we'll walk through how to use Azure AI Search integrated vector embeddings to index documents for Retrieval Augmented Generation. We'll create a new Azure AI Vector index, populate it with PDF data, and build a Streamlit Python application to interact with an OpenAI LLM using Azure AI Search as the data source.
33:16
In this video, we'll build an end-to-end NFL analytics reference architecture in Microsoft Fabric using NFLVerse data. We'll walk through downloading the data locally, setting up a Fabric workspace and Lakehouse, and transforming raw files into curated Gold star schemas. Then, we'll deploy a Power BI semantic model and compare two different Fabric Data Agent patterns to see how they handle natural language analytics. Finally, we'll test the agents in Microsoft 365 Copilot, run evaluations, and walk through the development loop for improving AI-powered analytics quality.