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
Chroma Database Mastery · LearnSpace
Назад в каталог
courseraПрограммирование

Chroma Database Mastery

Курс от Coursera
Средний≈ 14.4 чАнглийский
О курсеНавыкиПрограммаПреподаватели

О курсе

Dive into Chroma, the lightweight vector database transforming how AI applications handle complex data retrieval. This comprehensive course takes you from basic installation to building advanced, production-ready semantic search and RAG (Retrieval-Augmented Generation) systems. You'll progress through hands-on modules covering Chroma setup, data management, embedding integration, and sophisticated query techniques. Learn to configure vector stores, manage collections, integrate with cutting-edge embedding models, and develop APIs that understand meaning—not just keywords. By the end of this course, you'll have built a complete knowledge base project that demonstrates real-world ML engineering skills. Perfect for data scientists, ML engineers, and developers looking to enhance AI applications with intelligent, context-aware search capabilities. Who this is for: Python developers, data scientists, and ML engineers with foundational programming skills who want to implement advanced semantic search and retrieval technologies.

Навыки, которые вы освоите

Vector DatabasesEmbeddingsRetrieval-Augmented GenerationModel EvaluationSoftware InstallationMetadata ManagementDebuggingDocument ManagementLangChainLLM ApplicationData ManagementLarge Language ModelingAI IntegrationsData PipelinesApplied Machine LearningApplication Programming Interface (API)

Программа курса

6 модулей · 69 учебных материалов

01Launch Chroma Fast12 материалов
Your First Step into Vector DatabasesDIALOGUEUnderstanding Chroma: Core ConceptsЧтениеAnatomy of the Chroma Python SDKВидеоInstall Chroma and Launch a Persistent ClientВидео

Учитесь у экспертов

Professionals from the Industry

Преподаватель курса

Chroma Database Mastery
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

≈ 14.4 ч

6 модулей

Язык: Английский

Часть программы вашего университета
Hands-On Learning: Your First Chroma CollectionЛабораторная
Knowledge Check: Setup and ConfigurationЗадание
From Data Silos to Semantic SearchВидео
The Art of Ingestion and QueryingЧтение
How-To: A Full Ingestion and Query LoopВидео
Becoming a "Query Architect"DIALOGUE
Hands-On Learning: Ingesting and Querying the 2k Document SetЛабораторная
Full Chroma Deployment and Query PipelineЗадание
02Manage Data in Chroma16 материалов
The Case for Structured Vector DataDIALOGUEWhat are Documents, Metadata, and Filters in Chroma?ВидеоAnatomy of a Document: Best Practices for MetadataЧтениеAdd a Document with MetadataВидеоHands-On Learning: Ingesting and Tagging DocumentsЛабораторнаяKnowledge Check: Metadata and Filtering ConceptsЗаданиеWhy Use Multiple Collections? Lessons from Retail and FinanceВидеоDesigning a Multi-Collection ArchitectureЧтениеScripting an Ingestion Pipeline in PythonВидеоDialogue with AI Coach: Planning Your ETL Script for Support TicketsDIALOGUEAutomation and Scale: Managing Multiple CollectionsЗаданиеThe Challenge of a Static DatabaseDIALOGUEMastering the Data Lifecycle: Advanced Querying, Updating, and DeletingЧтениеFull Lifecycle Management with PythonВидеоHands-On Learning: Maintaining the Customer Ticket DatabaseЛабораторнаяDynamic Database Management ScriptЗадание
03Integrate Embeddings and Chroma11 материалов
Why Pipeline Reliability MattersDIALOGUEComparing Embedding Models and Chroma CollectionsЧтениеConnecting Embedding Models to a Vector DatabaseВидеоBuilding an Automated Vectorization PipelineВидеоHands-On Learning: Implementing an Auto-Vectorization PipelineЛабораторнаяKnowledge Check: Integration CheckpointsЗаданиеSilent Failures: Preventing AI Integration ErrorsВидеоA Troubleshooting Checklist for Vector PipelinesЧтениеDebugging Silent Vector Dimension MismatchesВидеоArticulating Your Debugging StrategyDIALOGUEDebugging a Failing Vectorization PipelineЗадание
04Build Chroma Search16 материалов
The Problem with Keyword SearchDIALOGUEFrom Keywords to Understanding: The Power of Semantic SearchВидеоThe Core Concepts: Embeddings and Vector DatabasesЧтениеChroma: The Vector Database for Semantic SearchВидеоIndexing Documents with ChromaВидеоHands-On Learning: Build and Query a Chroma CollectionЛабораторнаяKnowledge Check: Embedding Model Evaluation and BenchmarkingЗаданиеObjective Metrics: From Opinion to Production-ReadyВидеоHow to Measure Relevance: MRR & Precision@5 ExplainedЧтениеEvaluating Semantic Search with MRR and Precision@5ВидеоHands-On Learning: Implement Your Evaluation ScriptЛабораторнаяHands-On Learning: Calculating Relevance MetricsЗаданиеFrom Local Script to Global Service: Powering Search with APIsВидеоBuilding a Flask API for Your Search EngineВидеоScenario: "My Search Precision is Low! What Now?"DIALOGUEBuild, Deploy, and Evaluate Your Search APIЗадание
05Boost RAG with Chroma11 материалов
The High Cost of Trusting LLMsDIALOGUEFrom Hallucination to Reality: Grounding AI with RAGВидеоThe RAG Architecture ExplainedЧтениеBuilding a RAG Pipeline with LangChain and ChromaВидеоHands-On Learning: Indexing a Knowledge Base into a Vector StoreЛабораторнаяKnowledge Check: RAG ComponentsЗаданиеThe Principle of Grounding: Building Trustworthy AIВидеоA Framework for Evaluating HallucinationsЧтениеScenario: "Is This Response Grounded?"DIALOGUEHands-On Learning: Generating and Comparing ResponsesЛабораторнаяBuild and Evaluate Your RAG SystemЗадание
06Chroma-Powered Knowledge Base3 материалов
Why This Project MattersЧтениеProject RequirementsЧтениеProject: Chroma‑Powered Knowledge BaseЗадание