RAG from Scratch: Complete Retrieval-Augmented Generation
«RAG from Scratch: Complete Retrieval-Augmented Generation» è un corso online di RAG e AI engineering di livello intermedio, tenuto da InsightLearn Curated AI su InsightLearn. Il percorso comprende 10 lezioni organizzate in 3 sezioni, per una durata complessiva di 12h 0m. Build RAG pipelines from zero: chunking strategies, embedding models, vector stores, hybrid search, and advanced retrieval patterns.
- Docente: InsightLearn Curated AI
- Categoria: RAG e AI engineering
- Livello: intermedio
- Durata: 12h 0m
- Accesso: gratuito in questa fase di validazione, in cambio di un feedback al termine
- Certificato: certificato di completamento verificabile online
Descrizione del corso
InsightLearn è in fase di sviluppo (work in progress): i contenuti di questa pagina sono pubblicati esclusivamente a fini di verifica e test.
A hands-on deep dive into Retrieval-Augmented Generation. You will implement every component from scratch: document loading and chunking (fixed-size, semantic, recursive), embedding model selection and fine-tuning, vector database integration (Chroma, FAISS, Pinecone), hybrid BM25+dense retrieval, metadata filtering, re-ranking with cross-encoders, query transformation (HyDE, multi-query, step-back), and answer generation with faithfulness grounding. Covers both naive RAG and advanced patterns like CRAG, self-RAG, and adaptive RAG.
Cosa imparerai
- Curated from public resources. Build RAG pipelines from zero: chunking strategies, embedding models, vector stores, hybrid search, and advanced retrieval patterns.
Programma del corso
- Why RAG? LLM limitations and knowledge cutoffs (18 min)
- RAG pipeline architecture overview (22 min)
- Document loading: PDFs, HTML, markdown, databases (25 min)
- Fixed-size vs semantic vs recursive chunking (28 min)
- Embedding models: OpenAI, Cohere, open-source comparison (32 min)
- Multi-vector retrieval and late interaction models (26 min)
- Hybrid search: BM25 + dense vectors (30 min)
- Re-ranking with cross-encoders and Cohere Rerank (27 min)
- Query transformation: HyDE, multi-query, step-back (35 min)
- CRAG, self-RAG, and adaptive RAG patterns (40 min)
Dalle lezioni
Estratto della trascrizione di «Why RAG? LLM limitations and knowledge cutoffs»
Welcome to this lesson of the RBA course from scratch. Complete review of augmented generation. In this session, we will explore RBAs. LLM Limitation Sand Knowledge Qtops. We will start with the fundamental concepts and the theoretical principles of the base. We will then see practical applications and almost practical uses in the world of development. We will analyze concrete elements of RBAs. in the world of development. We will analyze specific examples and the best practices of the sector. At the end of this lesson, you will be able to apply the techniques of UIRB-AG LLM-Limitation-Sand-Knowledge-Kutoff-Snei-Turri-Projecti. We will start with the fundamental concepts and the theoretical principles. We will analyze specific examples and the best practices of the sector.…
Estratto della trascrizione di «RAG pipeline architecture overview»
Welcome to this lecture of the RBA Courses from Scratch. Complete review of augmented generation. In this session, we will explore RBA GPs for virtual architecture. We will start with the fundamental concepts and the basic theoretical principles. We will then see practical applications and practical cases in the world of development. We will analyze concrete elements and the best practices of the sector. At the end of this lesson you will be able to apply autonomously the techniques of R&G for the architecture or for you and your projects. We will start with the fundamental concepts and the basic theoretical principles. We will then see practical applications and almost real uses in the world of development. We will analyze…
Estratto della trascrizione di «Document loading: PDFs, HTML, markdown, databases»
Benvenuto in questa lezione del corso RWG from scratch. Complete retrieva augmented generation. In questa session esclaveremo document loading. PDFs, HTML, Markdown, Database. Inizieremo con i concetti fondamentali e i principi teorici di base. Vedremo poi applicazioni pratiche e casi due reali nel mondo dello sviluppo AI. Analizeremo. and the best practices of the sector. At the end of this lesson, you will be able to apply autonomously the documents and documents of your projects. We will start with the fundamental concepts and the basic principles. We will then see practical applications and almost real-life cases in the world of development. We will analyze concrete examples and the best practices of the sector. See you in the next lesson. This…
Altri corsi di RAG e AI engineering
- Vector Databases in Production: Chroma, FAISS, pgvector
- Agentic AI Patterns: ReAct, Plan-and-Execute, and Multi-Agent
- AI Engineering: Building Production LLM Applications
- AI Safety: Alignment, Red-Teaming, Responsible Deployment
- Fine-Tuning LLMs: LoRA, QLoRA, and Full Fine-Tuning
- Function Calling & Tool Use: Multi-Model Production Patterns
Domande frequenti
Quanto dura il corso RAG from Scratch: Complete Retrieval-Augmented Generation?
Il corso dura 12h 0m in totale, con 10 lezioni suddivise in 3 sezioni, da seguire online al proprio ritmo.
Serve esperienza pregressa?
Il corso è di livello intermedio e non indica requisiti specifici di ingresso.
Il corso rilascia un certificato?
Sì: al completamento del corso ricevi un certificato di completamento verificabile online.