Course Overview
Please note attendees work together in teams of 5 as a minimum and the pricing advertised is per team of 5.
Course Content
This OpenHack enables attendees to add intelligent search capabilities to their applications and services, leveraging artificial intelligence to extract meaningful results from data. This OpenHack simulates a real-world scenario where a travel company needs to uncover data locked up in documents and withdraw insights from that data to make key business decisions. During the “hacking” attendees will focus on:
- 1. exploring ways in which Azure Search can be used as the core of a search solution
- 2. enriching the search solution through integration with Cognitive Services, Azure Machine Learning, and custom code.
Technical Scenarios
- Search – Improving the ability to ingest data from various sources, intelligently sift through that data using core Azure AI services like Azure Search and Cog Services, and then analyze that data
- Data modeling – Create custom ML models that learn from data and continuously improve search
Who should attend
- App Developers
- ML/AI Engineers
- Customers looking to extract insights from vast quantities of diverse data
- Customers looking for intuitive search capabilities to help them find and make sense of relevant information that they need to make key business decisions
Prerequisites
To be successful and get the most out of this OpenHack, it is highly recommended that participants have previous experience with: Tooling Prerequisites To avoid any delays with downloading or installing tooling, have the following ready to go ahead of the OpenHack:
- A modern laptop running Windows 10 (1703 or higher), Mac OSX (10.12 or higher), or one of these Ubuntu versions
- Install your choice of Integrated Development Environment (IDE) software, such as Visual Studio, Visual Studio Code, Eclipse, or IntelliJ [/lnik]. The recommended IDE is Visual Studio Code.
- After installing Visual Studio Code, install the following language-specific extensions for the language you plan to use:
C#- NET Core SDK
- C# Extension for Visual Studio Code
- Node.js
- Python Extension for Visual Studio Code
- After installing the language-specific extensions, install the Azure Functions extension. You will use this in some of the later challenges.
- Most of the operations to create and modify Azure Search entities involve submitting JSON requests to a REST interface. You can write code in your preferred language to do this, or you can use Postman to create and submit collections of REST requests.
Language-Specific Prerequisites
- Recommended that participants have previous experience with knowledge of programing languages including C#, JavaScript, Node.JS or Java.
Course Objectives
By the end of the OpenHack, attendees will have built out a technical solution that is a complete Azure machine learning-based intelligent search infrastructure that can make sense of vast quantities of data (i.e. documents, scanned images, and other digital artifacts).
- AI-Powered Knowledge Mining helps businesses make better decisions through more robust data extraction and analysis
- Improved search functionality to decrease time-to-find relevant data
Outline: OpenHack – AI-Powered Knowledge Mining (OHAIPM)
Challenge 1: A Question of Knowledge
In this challenge, you will…
Learning objectives:
- Create a Q&A Maker knowledge base
- Write code that uses the REST API to query the knowledge base
Challenge 2: The Search Begins
In this challenge, you will…
Learning objectives:
- Create an Azure Search Index
- Use the SDK or REST API to submit a range of search queries using both simple and full syntax
Challenge 3: Expanding the Search
In this challenge, you will…
Learning objectives:
- Add built-in cognitive skills to an Azure Search index to return:
- Key Phrases
- Entities (including links)
- Sentiment (especially reviews)
Challenge 4: Getting the Full Picture
In this challenge, you will…
Learning objectives:
- Add built-in cognitive skills to an Azure Search index to return:
- Image Descriptions and Tags
- OCR extracted Text
Challenge 5: What is the Frequency?
In this challenge, you will…
Learning objectives:
- Create a custom skill to find the top ten most frequent words
Challenge 6: The Search for Relevance
In this challenge, you will…
Learning objectives:
- Add Synonyms
- Implement query suggestions / autocomplete
- Add scoring profiles that boost documents in results.
Challenge 7: Knowledge preservation
In this challenge, you will…
Learning objectives:
- Implement knowledge stores.
Challenge 8: Finding Your Form
In this challenge, you will…
Learning objectives:
- Create a custom skill that calls the Forms Understanding Service
Challenge 9: Use Your Intelligence
In this challenge, you will…
Learning objectives:
- Build a custom skill that consumes a custom machine learning model