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
AI Memory Systems: Production RAG Pipelines with n8n · LearnSpace
Назад в каталог
courseraАнализ данных

AI Memory Systems: Production RAG Pipelines with n8n

Курс от LearnKartS
Начальный≈ 6.6 чАнглийский
О курсеНавыкиПрограммаПреподаватели

О курсе

What if your AI could search your own documents and respond with context it actually understands? That is exactly what you will build here. This course teaches you to build AI memory systems using RAG, the retrieval architecture behind intelligent document search, enterprise knowledge bases, and AI-driven support tools. Here is what you will mainly build: AI Memory & Retrieval Foundations: Understand why AI loses context, how RAG retrieves the right information before responding, & how vector embeddings enable semantic search. You will also compare traditional RAG with agent-based RAG. A Working RAG Knowledge Base: Ingest PDFs, store OpenAI embeddings in Supabase with pgvector, & build a live query pipeline using GPT-4o mini with a fallback handler for unanswerable queries. Multimodal RAG with Gemini Vision: Use OCR and Gemini Vision to extract context from images, store image embeddings, and query visual content through semantic search. Built for professionals across any function who want AI that works with real organizational data. Over 200,000 professionals across 160+ LearnKartS courses have already built these skills. Start building yours now.

Навыки, которые вы освоите

EmbeddingsVector DatabasesRetrieval-Augmented GenerationData PipelinesOpenAI APIGenerative AI AgentsMachine LearningLarge Language ModelingMultimodal PromptsSemantic WebAI WorkflowsDatabase ManagementApplication Programming Interface (API)Google GeminiWorkflow ManagementNatural Language ProcessingGenerative AIPrompt EngineeringAutomationAgentic Workflows

Программа курса

3 модулей · 47 учебных материалов

01RAG Systems, Embeddings & Vector Databases14 материалов

AI Memory, RAG, and Embeddings Fundamentals

Why Agents Forget: Understanding the Memory ProblemВидеоWhat is RAG and How It WorksВидеоHow Embeddings Work: Turning Text into VectorsВидеоCheckpoint QuizЗадание

Учитесь у экспертов

Nikhil Agarwal

Преподаватель курса

LearnKartS

Преподаватель курса

AI Memory Systems: Production RAG Pipelines with n8n
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

≈ 6.6 ч

3 модулей

Язык: Английский

Часть программы вашего университета
Building AI Memory SystemsDIALOGUE

RAG Systems, Vector Databases, and AI Retrieval Pipelines

SQL vs NoSQL & Introduction to Vector DatabasesВидео Supabase, Vector Storage & Document ProcessingВидеоComplete RAG Pipeline & Similarity Search ВидеоFallback Handling: When the AI Does Not Know the AnswerВидеоTraditional RAG vs Agent-Based RAGВидеоCommon RAG Failure Modes and How to Debug ThemВидеоProficiency QuizЗаданиеBuilding Production RAG SystemsDIALOGUEResources: Memory-Systems-and-RAGЧтение
02Supabase, Vector Databases & End-to-End RAG Systems18 материалов

Supabase & pgvector: Database Concepts for AI Memory Systems

Databases, SQL vs NoSQL & PostgreSQL BasicsВидеоSupabase Features & Vector Database ConceptsВидеоSemantic Search, Embeddings & Full RAG PipelineВидеоCheckpoint QuizЗадание

End-to-End RAG System Setup using Supabase and n8n

Project intro, RAG concept & full pipeline walkthroughВидеоDEMO: Superbase account setup, project creation & connecting credentials to n8nВидеоDEMO: SQL editor - creating the RAG table, enabling vector extension & building the indexВидеоDEMO: Similarity search function, ingest webhook & PDF loader node setupВидеоDEMO: Text splitter, OpenAI embeddings, ingest summary code node & respond webhookВидеоCheckpoint QuizЗаданиеRAG Pipeline Setup and Document IngestionDIALOGUEResource: Real-AI-Apps-StartЧтение

RAG Query Pipeline, PDF Uploads & End-to-End Testing in n8n

DEMO: Building the upload form with AI, fixing CORS, live server & first PDF upload testВидеоDEMO: Query pipeline - webhook setup & parse/validate question code nodeВидеоDEMO: Retrieval QA chain, GPT-4o mini, vector store retriever & how the query flow worksВидеоFallback & debug handler, live query test & project wrap-upВидеоProficiency QuizЗаданиеResources: Rag_knowledge_base_guideЧтение
03Multimodal RAG with OCR, Vision Models & Vector Search15 материалов

OCR, Vision Models, and Multimodal RAG Workflows

Introduction to Multimodal RAG & Image UnderstandingВидеоExtracting Text and Context from ImagesВидеоOCR, Vision Models & AI-Based Image ProcessingВидеоDEMO: Setting Up Gemini Vision and OpenAI Vector WorkflowsВидеоDEMO: Image Embeddings, Chunking & Vector ConversionВидеоCheckpoint QuizЗаданиеBuilding Multimodal RAG SystemsDIALOGUE

Multimodal RAG Pipeline with Vector Search and Image Queries

DEMO: Storing Embeddings in Vector DatabasesВидеоDEMO: Semantic Search for Images and Multimodal QueriesВидеоDEMO: Building the Complete Multimodal RAG PipelineВидеоDEMO: Testing AI Responses with Image-Based QuestionsВидеоOptimization, Real Use Cases & Final Project Wrap-UpВидеоProficiency QuizЗадание
Resource : RAG Multimodal KB (Gemini vision + OpenAI vectors)Чтение
SummaryВидео