Back to Catalog

RAG: Vector Databases and Retrievers

PremiumIntermediateCourse

Master advanced RAG techniques using FAISS, ChromaDB, and modern retrievers while building high-performance search applications with LangChain and LlamaIndex, and Gradio.

Language

  • English

Topic

  • Artificial Intelligence

Industries

  • Information Technology

Skills You Will Learn

  • ChromaDB, Faiss, Generative AI, HNSW, LangChain, RAG

Offered By

  • IBMSkillsNetwork

Estimated Effort

  • 7 hours

Platform

  • SkillsNetwork

Last Update

  • January 20, 2026
About this Course
Master cutting-edge retrieval techniques that power today’s most advanced AI systems. In this course, you’ll explore sophisticated retriever patterns, vector databases, and indexing algorithms used in Retrieval-Augmented Generation (RAG). You’ll build a strong understanding of FAISS, ChromaDB, HNSW indexing, and the mechanics behind scalable similarity search in modern AI applications.
 
After completing this course, you will be able to: 

  • Build RAG applications using vector databases and advanced retrieval patterns
  • Employ the core mechanics of vector databases such as FAISS and ChromaDB and implement indexing algorithms like HNSW
  • Implement advanced retrievers using LlamaIndex and LangChain to improve the quality of LLM responses
  • Develop comprehensive RAG applications by integrating LangChain, FAISS, and interactive user interfaces built with Gradio
  • Differentiate retrieval strategies and assess when to apply each for improved accuracy
  • Use advanced similarity search techniques to optimize retrieval within RAG systems

Through guided labs, you’ll implement advanced retrievers—including self-querying, multi-query, parent document retrievers, and vector-store-backed pipelines—using both LangChain and LlamaIndex. These exercises demonstrate how to significantly improve retrieval accuracy, reduce hallucinations, and deliver high-quality responses from large language models (LLMs).

You’ll bring everything together by building a complete RAG application that integrates FAISS for vector search, an advanced retriever for improved relevance, and a fully interactive Gradio interface. This end-to-end project strengthens your ability to design AI systems that understand context, surface precise information, and serve users in real time.

By the end of the course, you’ll have applied the latest retrieval strategies and database technologies to build production-ready RAG pipelines—skills that directly support careers in AI engineering, search systems, and applied machine learning.

The following skills are required to be successful with this course: 

  • Python programming 
  • Familiarity with vector databases
  • Working knowledge of RAG and Similarity Search 


Course Syllabus



Welcome to the Course

  • Course Introduction
  • Course Overview
  • RAG and Agentic AI Professional Certificate Overview
  • Reading: Helpful Tips for Course Completion

Module 1: Advanced Retrievers for RAG

  • Module Summary and Learning Objectives
  • Work with Advanced Retrievers in LangChain
    • Explore Advanced Retrievers in LangChain: Part 1
    • Explore Advanced Retrievers in LangChain: Part 2
    • Lab: Build a Smarter Search with LangChain Context Retrieval
    • [Optional] Interactive LangChain Lesson Recap Podcast (AI-Powered)
    • Practice Quiz: Work with Advanced Retrievers in LangChain
  • Work with Advanced Retrievers in LlamaIndex
    • Advanced Retrievers in LlamaIndex
    • Lab: Explore Advanced Retrievers in LlamaIndex
    • [Optional] Interactive LlamaIndex Lesson Recap Podcast (AI-Powered)
    • Practice Quiz: Work with Advanced Retrievers in LlamaIndex
  • Module Summary and Evaluation
    • Summary and Highlights: Advanced Retrievers for RAG
    • Reading: Cheat Sheet: Advanced Retrievers for RAG
    • Graded Quiz: Advanced Retrievers for RAG
    • [Optional] Meet and Greet

Module 2: Build a Comprehensive RAG Application

  • Module Summary and Learning Objectives
  • Introduction to FAISS for RAG
    • Introduction to FAISS and How It Compares to ChromaDB
    • Lab: Semantic Similarity with FAISS
    • Reading: Hierarchical Navigable Small World (HNSW)
    • Lab: AI-Powered YouTube Summarizer, QA Tool with RAG, LangChain, FAISS
    • [Optional] Interactive FAISS/HNSW Lesson Recap Podcast (AI-Powered)
    • Practice Quiz: Introduction to FAISS for RAG
  • Module Summary and Evaluation
    • Summary and Highlights: Build a Comprehensive RAG Application
    • Cheat Sheet: Build a Comprehensive RAG Application
    • Graded Quiz: Build a Comprehensive RAG Application

Course Wrap-Up

  • Course Wrap-Up
  • Congratulations and Next Steps
  • Team and Acknowledgments