К содержимому
learnspaceYOUR NEXT CHAPTER
ПРОСТРАНСТВО ОБУЧЕНИЯ
ГлавнаяКаталог курсовМоё обучениеCoursera

Знания без границ

Учитесь у лучших университетов и компаний мира.

Открыть Coursera
Интеграция
Пространство университета
Моё пространствоСтраница курса
↵
ЯЛичный кабинетСтудент
© 2026 LearnSpaceКаждый день — возможность узнать больше.Помощь
Vector Database Foundations and Core Concepts · LearnSpace
Назад в каталог
courseraАнализ данных

Vector Database Foundations and Core Concepts

Курс от Coursera
Средний≈ 14 чАнглийский
О курсеНавыкиПрограммаПреподаватели

О курсе

Vector databases are transforming how machines understand and retrieve information across AI applications. This comprehensive course demystifies vector database technologies, taking you from foundational concepts to advanced implementation techniques. You'll learn to generate high-quality embeddings, calculate sophisticated similarity metrics, and implement efficient vector search algorithms. Through hands-on modules, you'll gain practical skills in converting raw data into meaningful vector representations, evaluating embedding quality, and optimizing search performance. The course covers critical techniques used in semantic search, recommendation systems, and retrieval-augmented generation. Whether you're an aspiring machine learning engineer or a data professional looking to enhance your AI toolkit, you'll develop the expertise to design performant vector search systems. Who this is for: Machine learning engineers, data scientists, and AI professionals eager to master vector database technologies. Basic programming and machine learning familiarity recommended.

Навыки, которые вы освоите

Vector DatabasesPerformance TuningEmbeddingsModel OptimizationAI WorkflowsGenerative AIRetrieval-Augmented GenerationModel EvaluationMachine Learning MethodsMachine LearningDatabase SystemsScalabilityUnstructured Data

Программа курса

6 модулей · 72 учебных материалов

01Grasp Vector DB Basics15 материалов
AI Coach: The Failed SearchDIALOGUEFrom Words to Numbers: What Are Vector Embeddings?ЧтениеHow-To: Visualize a Semantic SearchВидеоHands-On Learning: Articulate the "Why" for a Technical PeerЗадание

Учитесь у экспертов

Professionals from the Industry

Преподаватель курса

Vector Database Foundations and Core Concepts
В каталоге вашей программы

Инвестируйте в себя

Новые знания — в удобное для вас время.

Начать на Coursera

Обучение откроется на Coursera
в новой вкладке

Обучение на Coursera

≈ 14 ч

6 модулей

Язык: Английский

Часть программы вашего университета
Knowledge Check: Core Concepts of Vector SearchЗадание
Why a Single Database Can't Do It AllВидео
A Framework for Database ComparisonЧтение
How-To: Apply the Decision FrameworkВидео
Hands-On Learning: Build a Database Decision MatrixЗадание
Knowledge Check: Database Use Case AnalysisЗадание
The Stakeholder Gauntlet: Beyond "Cool" TechВидео
Crafting a Persuasive Technical PitchЧтение
Justify Your ChoiceDIALOGUE
Hands-On Learning: Draft the "Problem" SlideЗадание
The Stakeholder PitchЗадание
02Embed Everything12 материалов
Why Embeddings Power Modern AIDIALOGUEWhat Are Embeddings? Translating Unstructured DataВидеоChoosing Your Toolkit: A Comparison of Pre-trained ModelsЧтениеHow-To: Build a Batch Embedding Script in PythonВидеоHands-On Learning: Scripting Your First Text EmbedderЛабораторнаяKnowledge Check: Embedding Generation CheckЗаданиеThe High-Stakes Quest for Quality: A Medical Case StudyВидеоDemystifying High-Dimensional Data with t-SNEЧтениеHow to Create and Analyze a t-SNE Plot in Python?ВидеоHands-On Learning: Visualizing and Interpreting a t-SNE PlotЛабораторнаяAI Coaching Session: Defending Your t-SNE InterpretationDIALOGUEBuilding an E-commerce Embedding Pipeline and Quality ReportЗадание
03Measure Vector Similarity11 материалов
Why Choosing the Right Metric is CriticalDIALOGUEUnderstanding Similarity MetricsВидеоCalculating Cosine Similarity in PythonВидеоThe Mathematical Properties of Similarity MetricsЧтениеHands-On Learning: Calculate All Three MetricsЛабораторнаяKnowledge Check: Foundational ConceptsЗаданиеWhy Rankings Diverge: Amazon vs. Oxford?ВидеоAnalyzing and Benchmarking Similarity MetricsЧтениеBuilding a Benchmark NotebookВидеоReflecting on Your AnalysisDIALOGUEBuild a Benchmark NotebookЗадание
04Master ANN Search17 материалов
The Billion-Vector ChallengeDIALOGUEWhen Exact Search Fails: The Limits of Brute ForceВидеоWhat is an ANN Index?ЧтениеYour First Index: Implementing FAISSВидеоHands-On Learning: Build a Basic Vector IndexЛабораторнаяKnowledge Check: ANN FundamentalsЗаданиеGoogle's Quest for High-Recall SearchВидеоDefining Your Metrics: Recall@k and LatencyЧтениеNavigating the Trade-OffDIALOGUEMeasuring Recall and Latency in CodeВидеоHands-On Learning: Benchmark Your IndexЛабораторнаяKnowledge Check: Interpreting Performance ResultsЗаданиеThe RAG Backbone: Why Indexing Matters for Generative AIВидеоA Guide to Tuning Your IndexЧтениеRefining Your Project StrategyDIALOGUEProposing an OptimizationЗаданиеPrototype and Report on an ANN IndexЗадание
05Tune HNSW12 материалов
The Vector Search Balancing ActDIALOGUEWhy Build Quality Matters: The Microsoft Bing StoryВидеоUnderstanding Build-Time Parameters: M and efConstructionЧтениеCode-Along: Constructing an HNSW Index in PythonВидеоEvaluating Your HNSW Tuning StrategyDIALOGUEKnowledge Check: Practice Building an IndexЗаданиеWhat's Your Priority: Speed or Accuracy?DIALOGUEThe User Experience: Amazon's Visual SearchВидеоThe efSearch Parameter and the Recall-Latency Trade-offЧтениеHow to Measure and Plot the Recall-Latency Trade-off?ВидеоHands-On Learning: Charting the Recall-Latency CurveЛабораторнаяJustify Your HNSW ParametersЗадание
06GenAI Literacy: AI-Assisted Embedding Workflows5 материалов
AI Co‑Pilot for Fast Embedding & IndexingDIALOGUEAI-Assisted Development: Patterns and Best PracticesЧтениеAI‑Guided FAISS Indexing: From Prompt to OptimizationЧтениеAI-Augmented Problem SolvingDIALOGUEGraded Quiz: AI-Augmented WorkflowsЗадание