Vector DB Foundations, Embeddings & Search Algorithms

"Grasp Vector DB Basics" is an intermediate course for machine learning practitioners and data professionals looking to understand the technology powering modern semantic search and AI applications. In an era where keyword search is no longer enough, this course builds a strong conceptual foundation, explaining how vector databases store and retrieve vector representations, how similarity-based retrieval differs from traditional database querying, and how these capabilities enable applications such as semantic search and recommendation. You will transition from foundational theory to practical analysis, learning to explain what vector databases are, why their ability to understand relationships is a game-changer, and how to compare them against traditional databases. Through scenario-based assignments, you will build and defend a decision framework for choosing the right database and justify your choice to stakeholders. By the end, you will be equipped to analyze use cases and articulate the strategic value of vector databases.

Master ANN Search is an intermediate-level course designed for machine learning engineers and AI practitioners tasked with building high-speed, large-scale vector search systems. As datasets grow into the millions, traditional brute-force search methods become impossibly slow. This course provides the practical skills to overcome this challenge using Approximate Nearest Neighbor (ANN) algorithms. You will get hands-on experience implementing industry-standard libraries like FAISS and Annoy to build and prototype powerful vector indexes. Through a series of expert-led videos, readings, and ungraded labs, you will move beyond basic implementation to master the art of performance evaluation. You will learn to measure and analyze the critical trade-off between retrieval accuracy (recall) and speed (latency), benchmarking your solutions against brute-force search to quantify their effectiveness. The course culminates in a final project where you will optimize an index for a 100k vector dataset, mirroring the real-world job task of balancing performance for applications like Retrieval-Augmented Generation (RAG) or recommendation engines. By the end, you’ll be equipped to not just use ANN, but to strategically deploy it. You will need to be familiar with Python programming, data structures, and basic machine learning concepts. Familiarity with vectors is a plus.

Measure Vector Similarity: Cosine, Dot-Product, and Euclidean Distance is an intermediate course for machine learning engineers and data scientists looking to master how similarity metrics impact information retrieval, recommendation systems, and classification tasks. In a world where the right comparison can mean the difference between a successful product recommendation and a flawed medical insight, choosing the correct metric is critical. This course moves beyond theory and provides direct, hands-on experience. You will learn to calculate and implement cosine similarity, dot-product, and Euclidean distance using Python and NumPy. Through practical examples inspired by real-world applications at companies like Amazon and in healthcare research, you will analyze how each metric uniquely influences vector ranking and search precision. The course culminates in a capstone project where you will build a benchmark notebook to rigorously compare the performance of these metrics on a sample dataset—a portfolio-ready project that proves your ability to make informed, data-driven decisions in machine learning applications. You will need to have basic Python programming skills, familiarity with NumPy, and foundational knowledge of linear algebra (vectors, dot products).

Tune HNSW is an intermediate-level course designed for machine learning practitioners and AI engineers looking to master the art of vector search optimization. In modern AI applications, finding the right balance between search accuracy (recall) and speed (latency) is critical, but traditional methods often fall short. This course provides a focused, hands-on deep dive into the Hierarchical Navigable Small World (HNSW) algorithm, empowering you to build and tune high-performance vector indices. To get the most out of this course, you should have a foundational understanding of key concepts. Prerequisites include familiarity with vector embeddings and basic Python programming. Prior experience with machine learning concepts is also helpful, as it will provide the context needed to master the practical trade-offs of performance tuning. You will move from theory to practice, learning how to strategically manipulate the core HNSW parameters—efConstruction, M, and efSearch—to meet specific project requirements. Through expert-led videos, practical readings, and a code-along lab, you'll learn to build an HNSW index from scratch. You will then systematically analyze the performance trade-offs by charting a precision-latency curve. The course culminates in a final project where you'll justify your tuning decisions for a simulated real-world scenario, creating a portfolio-ready demonstration of your ability to optimize vector search for applications ranging from low-latency chatbots to high-recall visual search engines.

"Understand RAG Basics" is an intermediate course for developers and data scientists who want to build more powerful and trustworthy AI applications. While Large Language Models (LLMs) are revolutionary, they often lack specific, up-to-date knowledge and can hallucinate answers. This 2-hour course provides the fundamental solution: Retrieval-Augmented Generation (RAG). You will need to be familiar with basic Python, API, and LLMs. You will also need Python and a code editor like VS Code installed locally. Focused on practical application, this course transitions from theory to execution. You will begin by learning to diagram the core components of a RAG architecture (the retriever, the generator, and the vector database) to understand its data flow. Then, you will translate that knowledge into a functioning application. Through a hands-on project that mirrors a real-world job task, you will use Python to build a minimal RAG pipeline, complete with a local vector store, to successfully ground an LLM with external facts. By the end, you'll be able to build intelligent systems that provide accurate, context-aware answers derived from your own data.

In the world of AI-powered search, relevance is everything. Go beyond the limits of pure keyword or vector search in Blend Hybrid Search, an intermediate course for developers and ML engineers. You will learn to build a state-of-the-art search system by combining the precision of keyword matching (like BM25) with the semantic power of dense vectors. This course provides a complete, hands-on framework for optimizing search performance using open-source tools as our implementation example. You won't just build a hybrid search function; you will master the art of tuning it. Through a project-driven approach, you will learn to systematically adjust weighting parameters and use the industry-standard NDCG metric to objectively measure and prove the impact of your changes. You will leave with a reusable evaluation script and a data-driven methodology for squeezing the maximum relevance from any search application.

Embed Everything is an intermediate-level course designed for machine learning practitioners and Python developers who want to master the art of converting unstructured data into powerful numerical representations. In a world where data is king, its value is often locked away in complex formats like product descriptions, images, and documents. This course provides the key to unlocking that value. You will learn to build a complete, scalable embedding pipeline from the ground up. Through practical, hands-on labs and expert-led video lessons, you'll apply state-of-the-art pre-trained models to transform raw text and images into meaningful vector embeddings. But creating embeddings is only half the battle. You will also master the crucial skill of evaluation, using powerful visualization techniques like t-SNE and nearest-neighbor analysis to verify that your embeddings capture the true semantic meaning of your data. By the end of this course, you will have written a production-style Python script to batch-process a large dataset, a skill directly applicable to real-world scenarios like Walmart's semantic search engine. Intermediate Python and basic ML skills required. Experience with NumPy and scikit-learn is beneficial.