Enterprise RAG (Retrieval-Augmented Generation) Frameworks
Published 7/2026
MP4 | Video: h264, 1920×1080 | Audio: AAC, 44.1 KHz, 2 Ch
Language: English | Duration: 1h 42m | Size: 1.46 GB
Build scalable, governed RAG systems using hybrid retrieval, vector databases, LangChain, LlamaIndex, and GraphRAG.
What you’ll learn
Design end-to-end RAG pipelines separating offline data indexing from online query execution.
Process heterogeneous enterprise documents using layout-aware parsing and robust extraction methods.
Implement semantic, fixed-size, and parent-document chunking strategies for optimal retrieval.
Deploy hybrid retrieval systems combining dense vector search and BM25 sparse lexical retrieval.
Apply cross-encoder reranking to elevate precision and filter irrelevant context before generation.
Utilize advanced patterns including HyDE, multi-query expansion, and GraphRAG for complex queries.
Enforce document-level access control, metadata filtering, and PII redaction inside the vector store.
Evaluate RAG systems using context precision, recall, and the RAGAS framework with LLM judges.
Requirements
Basic understanding of large language models (LLMs) and natural language processing concepts.
Familiarity with Python programming and API integrations.
Fundamental knowledge of database operations; prior vector database experience is beneficial but not strictly required.
Description
“This course contains the use of artificial intelligence.”
Large language models inherently struggle with frozen parametric knowledge, causing enterprise-critical data staleness and hallucination. Scaling generative AI safely and accurately requires more than prompt engineering; it demands a highly governed, cost-efficient retrieval architecture. This course provides a definitive engineering blueprint for designing, deploying, and operating Retrieval-Augmented Generation (RAG) systems in strict production environments.
Course Overview and Architectural Scope
This curriculum dissects the end-to-end RAG architecture, explicitly separating the offline indexing pipeline from the online query execution path. Participants will learn how to parse heterogeneous enterprise documents, implement semantic and structure-aware chunking, and utilize vector databases for scalable approximate nearest neighbor (ANN) search. The program details advanced retrieval mechanics, demonstrating how to fuse dense semantic embeddings with sparse lexical search and optimize results using cross-encoder reranking to maximize context precision.
What is Hybrid Retrieval in RAG?
Hybrid retrieval combines dense semantic vector search with sparse lexical search, such as BM25, and merges the results using Reciprocal Rank Fusion. This approach ensures high recall for both broad conceptual queries and exact alphanumeric keyword matches, significantly improving overall context relevance for the language model.
How does Agentic RAG differ from standard RAG?
Standard RAG uses a fixed, linear pipeline for embedding, retrieval, and generation. Agentic RAG introduces an iterative reasoning loop where a language model autonomously routes queries, selects tools, evaluates retrieved context, and decides if multiple retrieval steps are necessary before synthesizing a final answer.
What are RAG guardrails and access controls?
RAG guardrails are pre-filtering and post-generation validation checks that prevent unauthorized data leakage and hallucinations. Enterprise access control inside RAG requires attaching identity metadata to document chunks during ingestion, ensuring the vector database only retrieves information the user is explicitly authorized to view.
Executive Architecture Briefing and Operational Value
Framed as a high-signal technical briefing, this course bridges the gap between local prototypes and scalable production. Modules progress systematically through ingestion optimization, advanced query expansion patterns (including HyDE and step-back prompting), and complex graph-based architectures like GraphRAG. Crucially, the final sections focus on production operations: implementing LangChain and LlamaIndex orchestration, enforcing document-level data governance, tracking cost and latency, and utilizing the RAGAS framework for continuous, quantitative evaluation.
Current Industry Landscape
This curriculum is fully updated for the 2025/2026 enterprise AI landscape, encompassing modern contextual retrieval strategies, hybrid index scaling, and LLM-as-a-judge evaluation frameworks.
Compliance Disclosure: This course contains the use of artificial intelligence tools to enhance structural formatting and transcript accessibility.
Who this course is for
AI Engineers and Data Scientists building generative AI applications and retrieval pipelines.
Software Architects responsible for designing scalable, secure enterprise machine learning architectures.
Technical Product Managers overseeing AI application integrations, data governance, and LLM deployment lifecycles.
CENTPSREFRRETAGEVAKJAJHEGENRTGTATTN
you must be registered member to see linkes Register Now