For learners using the November 2020 webcast series from the Microsoft US Azure team https://aka.ms/azure-knowledge-mining
This training is an updated version of the Azure Learn AI Knowledge Mining Bootcamp that has been retired. The original workshop can be found at https://github.com/Azure/LearnAI-KnowledgeMiningBootcamp
In this course, you will create an enterprise search solution by applying knowledge mining to business documents like contracts, memos, presentations and images. You will use Microsoft Azure AI technology to extract insights from unstructured data and expose the results in a Bot interface.
At the end of this training you will have learned:
- What Azure Cognitive Search is
- How to implement a Cognitive Search Solution
- Why this technology can be useful for any company
- When to use this solution for demos, POCs and other business scenarios
The hands-on labs will teach you how to use Microsoft Azure Cognitive Search combined with Microsoft Cognitive Services for entity recognition, image analysis, text translation and indexed search on enterprise business documents. This approach uses Artificial Intelligence to create an advanced search experience.
In this course we will cover these key concepts:
-
Fundamentals of Azure Cognitive Search and its capabilities
-
Knowledge Mining business scenarios
-
Building an enrichment data pipeline for search using predefined and custom skillsets:
- Text skills like entity recognition, language detection, text manipulation and key phrase extraction
- Image skills like OCR
- Content moderation skills to detect documents with incompliant content
-
Use the enriched data for an advanced search experience for business documents within an enterprise.
-
Expose the knowledge mining solution using a bot interface for document search and consumption.
Intelligent search is relevant to many major industries. Some are listed below.
-
Retail and health care industries employ chat bots with advanced multi-language support capabilities to service their customers.
-
Retail, Housing and Automotive industries for sales/listing.
-
Law firms and legal departments can use this technology to enforce compliance or improve search capabilities.
- Fundamental working knowledge of Azure Portal, Azure Functions and Azure Cognitive Search
- Familiarity with Visual Studio and minimum C# knowledge
- Familiarity with Azure Bots and Microsoft Bot Framework v4
- Familiarity with Postman
If you do not have any of the above pre-requisites, please find below links
- To Read (10 minutes): Visual Studio Tutorial
- To Read (8 minutes): Azure Bot Service Overview
- To Read (4 minutes): Azure Functions Overview
- To Read (10 minutes): Azure Cognitive Search Overview
- To Read (7 minutes): Postman Tutorial
- To Do (30 minutes): C# Quickstart
- To Create: You need a Microsoft Azure account to create the services we use in our solution. You can create a free account, use your MSDN account or any other subscription where you have permission to create services
- To Install: Visual Studio 2019 or later, including the Azure development workload
- To Install: Postman. To call the labs APIs
- To Install: Bot Emulator, use the '.exe' file from release 4.1.0 or newer
- To Install: Git for Windows or any other git app you prefer
Primary Audience: Azure AI Developers, Solution Architects. Secondary Audience: Any professional interested in learning AI.
This content is designed as an intermediate to advanced level course for AI developers and/or architects.
This course, in its full form, is designed to be taught in-person but you can also use the materials in a self-paced fashion. There are assignments and multiple reference links throughout the materials that support the concepts and skills you will learn.
Full Course classroom training: 16 hours
-
Introduction – Presentation overview of Azure Cognitive Search, Cognitive Search, business scenarios and industry specific applications.
-
Architecture – Solution Architecture for building enterprise search solution.
-
Prerequisites - Environment Creation
-
Lab 1 - Indexing Blog Storage
-
Lab 2 - Text Skills
-
Lab 3 – Image Skills
-
Lab 4 - Custom Skills
-
Lab 5 - Build and Integrate a Bot with the Search API
-
Optional lab - Analyzing extracted data with PowerBI
Note: Once you've completed the labs, we recommend deleting the resource group (and all the resources in it) to avoid incurring extra charges, unless you want to use this solution as a tool for demos and POCs.
-
Using Azure-Functions-for-Python to create a Cognitive Search Filtering Custom Skill
-
Start Today! Learn How to Create End-to-End Solutions with Microsoft AI
The LearnAI team had intense participation in the creation of the following new Microsoft certifications and its required tests:
-
- DP-200: Implementing an Azure Data Solution
- DP-201: Designing an Azure Data Solutions
-
- AI-100: Designing and Implementing an Azure AI Solution
-
- DP-100: Designing and Implementing a Data Science Solution on Azure
Click here to learn how Microsoft Cognitive Services handle your data.