Vector Search Fundamentals
Learn how to leverage MongoDB Atlas Vector Search to build intelligent, AI-powered search experiences for applications. Explore indexing, embeddings, and retrieval strategies.
|
Upon completion of the Vector Search Fundamentals skill check, you will earn a Credly badge that you are able to share with your network. |
Learning Objectives
Understand Semantic Search
Know how and when to use semantic search to capture the meaning and context behind a query and to improve the relevance of results.
Store Embeddings for Your Data
Capture the meaning and context behind your data by generating embeddings and storing them in MongoDB.
Perform a Vector Search
Implement vector search in your application to retrieve semantically similar data and improve the relevance of the results.
Note: The AI models used this learning content, including LLMs and embedding models, are constantly evolving and may have been updated since its creation.
Who is this Course Good for?
This skill is designed for developers who want to add AI-powered semantic search to their applications using MongoDB. If you are building products where users need to find content based on meaning rather than exact keywords—such as media catalogs, documentation portals, recommendation features, or AI assistants—this Vector Search Fundamentals Skill Badge is for you. It is especially valuable if you already understand basic MongoDB and Atlas Search concepts and now want to learn how to use Vector Search to integrate vector search into real applications. Whether you are experimenting with AI features or planning to productionize semantic search, this skill will help you understand how vector search works, how it fits into MongoDB, and how to apply it to your own workloads.
What to Expect in this Course
In this skill badge, you will learn how to use Vector Search to bring semantic search capabilities into a MongoDB-backed application. The course begins by grounding the problem in a relatable scenario: searching for a movie when you can’t remember the title, only vague details of the plot. Traditional keyword-based search may require you to guess the right phrase and sift through many irrelevant results. In contrast, semantic search lets users describe what they remember—such as “a movie where aliens come to earth in search of resources”—and retrieve results based on meaning rather than exact word matches. You explore how Vector Search enables this type of experience by leveraging AI to interpret the semantics of a query and return related results.
Using a movie catalog application as a running example, you work with movie documents in the sample_mflix database and focus on fields like title and plot. You learn how to generate embeddings for the plot field so that each description is represented as a vector in a high-dimensional space, setting the foundation for vector search. Before you implement the feature, the skill explains how vector search works behind the scenes, including what vectors and dimensions are, how embedding models convert text into numerical vectors, and how those vectors are stored and searched efficiently. You are introduced to core concepts such as Hierarchical Navigable Small World (HNSW) graphs for indexing vectors and nearest neighbor search algorithms that find the most similar vectors for a given query.
With this conceptual understanding in place, you move into implementation. You learn how to define an Atlas Search index that includes a vector field type, and then use the MongoDB aggregation framework with the $vectorSearch stage to query your data based on vector similarity. Step by step, you see how to wire these pieces together so your application can accept a natural-language query, convert it to a vector with an embedding model, and retrieve the most semantically relevant movies from MongoDB. Hands-on labs give you opportunities to practice generating vectors, creating indexes, and writing vector search queries in realistic scenarios. By the end, you will be able to use Vector Search to add AI-driven semantic search to your own applications, with a clear understanding of how it works and how to tune it for your use cases.
Summary of the Course
- Understand the limitations of keyword-based search and why semantic search is valuable for modern applications.
- Explain what vectors, dimensions, and embeddings are and how they relate to Vector Search in MongoDB.
- Generate vector embeddings from text fields using an embedding model to prepare data for vector search.
- Describe how vector indexes based on HNSW graphs and nearest neighbor search power fast, relevant results.
- Create an Atlas Search index that includes a vector field type suitable for vector search workloads.
- Use the MongoDB aggregation framework and the $vectorSearch stage to run semantic search queries.
- Implement a semantic search feature in an application using Vector Search and movie catalog data.
- Build confidence working with MongoDB, AI, and vector search through hands-on labs that mirror real-world scenarios.
Parker Faucher| Senior Software Engineer
Parker is a Senior Software Engineer on the Education team at MongoDB. Prior to joining MongoDB, he helped maintain a world class developer bootcamp that was offered in multiple universities. He is a self taught developer who loves being able to give back to the community that has helped him so much.
Emily Pope | Senior Curriculum Designer
Emily Pope is a Senior Curriculum Designer at MongoDB. She loves learning and loves making it easy for others to learn how and when to use deeply technical products. Recently, she's been creating AI and vector search content for MongoDB University. Before that, she's created learning experiences on databases, computer science, full stack development, and even clinical trial design and analysis. Emily holds an Ed.M. in International Education Policy from Harvard Graduate School of Education and began her career as an English teacher in Turkiye with the Fulbright program.
Joel Lord | Lead, Curriculum Eng/Technologist
Joel Lord is a curriculum engineer at MongoDB who is committed to empowering developers through education and active community involvement. With more than twenty years of experience in software development, developer advocacy, and technical education, he combines extensive expertise with a dedication to making complex topics more understandable.
Holding a Bachelor of Science in computational astrophysics from Université Laval, Joel started his career in web development before he focused on assisting others in their learning journeys. At MongoDB, he develops educational materials designed to equip developers with the skills to build improved applications, drawing on his wide-ranging experience as a speaker at global conferences.
When he is not working, Joel enjoys stargazing in remote camping areas, experimenting with inventive brewing methods in his garage, and offering emotional support to his two cats, who often appear as guests during his Zoom meetings.
Harshad Dhavale | Staff Technical Services Engineer
Harshad Dhavale is a Staff Technical Services Engineer, who has been with MongoDB for over six years. He is a subject matter expert in Atlas Search and Atlas Vector Search, and has made significant contributions in these domains over his tenure. In addition to enablement, he has played a key role in numerous pivotal Atlas Search and Atlas Vector Search initiatives and projects, which have been instrumental in defining the product's trajectory. He is a trusted specialist on all things Search, and enjoys diving deep into complex Search topics.
Henry Weller | Product Manager
Henry Weller is the dedicated Product Manager for Atlas Vector Search, focusing on the query features and scalability of the service, as well as developing best practices for users. He helped launch Atlas Vector Search from Public Preview into GA in 2023, and continues to lead delivery of core features for the service. Henry joined MongoDB in 2022, and was previously a data engineer and backend robotics software engineer.
John McCambridge | Curriculum Engineer
John is a Curriculum Engineer on the University team at MongoDB. Before his work as a Curriculum Engineer, he was an instructor and teaching assistant for coding boot camps at UT (Austin), and UCLA. Additionally, he worked as a QA engineer for a startup called Coder and spent five years at Apple Inc. John is a passionate software engineer and educator who enjoys taking complex topics and making them digestible for the community.
Sarah Evans | Senior Curriculum Engineer
Sarah is a Senior Curriculum Engineer on the Curriculum team at MongoDB. Prior to MongoDB, she taught and developed curricula for developer bootcamps. Sarah has a MAT degree from Columbia University Teachers College and studied Software Engineering at Flatiron School in Chicago, IL.
Katie Redmiles | Instructional Designer
Katie is a Instructional Designer at MongoDB. Before joining the Curriculum team, Katie worked on the University Enablement team developing Learning Bytes and instructional materials for the MongoDB for Academia program. Katie also worked within the Digital Learning Division at the Foreign Service Institute where she honed her skills at developing online learning for a global audience. Katie is passionate about making education accessible and engaging for everyone.
