Building GenAI Apps Learning Badge Path
In this learning path, you'll build a GenAI application with MongoDB's Atlas Vector Search and learn how you can leverage it across a variety of use cases.
This learning path guides you through the foundations of building a GenAI application with MongoDB's Atlas Vector Search. You'll learn what semantic search is and how you can leverage it across a variety of use cases. Then, you'll learn how to build your own chatbot by creating a retrieval augmented generation application with MongoDB and Langchain.
To earn your badge, complete the content in this learning path and then pass the short assessment at the end. You will receive an email with your official Credly badge and digital certificate within 24 hours.
Milestones
-
Learning Badge Content
Introduction to AI and Vector Search
Required
Unit
| Parker Faucher, Katie Redmiles, Emily Pope, Vick Mena30 Minutes
View DetailsLearn about the foundations of AI and how Atlas Vector Search fits in.Using Vector Search for Semantic Search
Required
Unit
| Parker Faucher, Sarah Evans, Vick Mena, John McCambridge, Emily Pope, Harshad Dhavale1.75 Hours
View DetailsLearn all about Atlas Vector Search as you build a semantic search feature. Leverage both Atlas Search and Atlas Vector Search to identify the most relevant search results.Using Atlas Vector Search for RAG Applications
Required
Unit
| Henry Weller, Parker Faucher, Aaron Becker, Emily Pope, Daniel Curran, Manuel Fontan Garcia5 Hours
View DetailsLearn how to implement retrieval-augmented generation (RAG) with MongoDB in your application. Learn what retrieval augmented generation is and set it up using the MongoDB Python driver.Managing Atlas Vector Search Indexes
Required
Unit
| Parker Faucher1.5 Hours
View DetailsLearn how to manage your Atlas Vector Search indexes using the Atlas CLI and MongoDB Shell.Data Ingestion for RAG Applications
Required
Learning Byte
| Manuel Fontan Garcia20 Minutes
View DetailsLearn about the Data Ingestion Pipeline for retrieval-augmented generation (RAG) applications.Building RAG Applications with LlamaIndex and MongoDB
Elective
Learning Byte
| MongoDB University15 Minutes
View DetailsLearn to use LlamaIndex to build a RAG application powered by Atlas Vector Search.MongoDB and GenAI Glossary
Elective
Microcourse
| MongoDB University15 Minutes
View DetailsA guide to key terms and concepts used when building, deploying, and evaluating generative AI applications with MongoDB. -
Learning Badge Assessment
Building GenAI Apps Learning Badge Assessment
Required
Assessment
View DetailsThis assessment will test your knowledge of developing GenAI applications using MongoDB Atlas Vector Search as well as your understanding of semantic search and how to build chatbots with retrieval-augmented generation (RAG), MongoDB, and Langchain.
Welcome! By now, I'm sure you've used intelligent chatbots like Claude or ChatGPT. But, have you ever wanted to build your own? Generative AI can be a powerful tool to leverage for your own projects or business use case, but where should you begin?
Completing this learning badge will give you the skills to build your own GenAI application with MongoDB.
We'll focus on Retrieval Augmented Generation, also known as RAG, as our GenAI app use case.
RAG allows you to build a custom chatbot that responds according to your instructions and based on your own data.
And, even if you've dreamt up another use case, the skills you develop here will aid you in building any GenAI application.
We’ll begin by zooming out and looking at some of the wider components of gen AI. In particular, we’ll learn about the transformer model and how it relates to vector Search.
Next, we'll discuss semantic search, one of the foundations of modern GenAI apps, and how to leverage Atlas Vector Search to build semantic search into your application.
With an understanding of the foundations of GenAI apps, it'll be time to build your own.
You'll learn how to build a custom chatbot with your own data using RAG. We'll show you how to leverage several common frameworks - langchain, microsoft semantic kernel, and llamaindex, to do so.
Finally, we'll dive deeper into a few key areas that will help you as you set up and use your RAG app. We'll show you how to ingest data from many different formats and how to manage your Atlas Vector Search indexes.
At this point in your learning journey, you'll be ready to put your new skills to the test! To earn your badge, simply complete the content in the learning path, and then take the short test at the end. After passing the test, you'll receive an official Credly badge via the email you provided.
Be sure to share your badge on LinkedIn to show off your new skills!
So, are you ready to unlock the power of GenAI and transform your ideas into reality? Let's get started on your journey to becoming a GenAI app developer!
