Skills › RAG & Vector Search

Advanced RAG

Implement hybrid search, reranking, HyDE, and query routing for production RAG.

0%
Confidence · no data yet
Sign in to track

After this skill you can…

  • Build a hybrid BM25 + dense retrieval pipeline
  • Add a cross-encoder reranker
  • Implement HyDE and query expansion

Watch (10 videos)

Advanced RAG Patterns
Coursera · intermediate hands-on
→ Build robust RAG pipelines for complex queries→ Improve reliability and accuracy of AI models
Advanced RAG 01: Small-to-Big Retrieval with LlamaIndex
Sophia Yang (AI) · advanced hands-on
→ Implement Small-to-Big Retrieval→ Use LlamaIndex for RAG→ Apply Sentence Window Retrieval
Toy Augmented Generation Project to a Production-Ready AI System
codebasics · beginner hands-on
→ Develop a production-ready RAG system→ Deploy a RAG model to the cloud
LLMOPS 02: RAG Analysis & Evaluation Strategy Part-2 | Advanced RAG Pipeline in LLMOPS
Sunny Savita · intermediate hands-on
→ Build a RAG pipeline with LLMOPS→ Deploy a GenAI Document Chat System to AWS ECS
Advanced RAG 06 - RAG Fusion
Sam Witteveen · beginner hands-on
→ Apply reciprocal rank fusion→ Combine search queries
[Graph Neural Nets] Breaking Symmetry Bottlenecks: How Projector-Based Readouts Supercharge GNNs.
AI Podcast Series. Byte Goose AI. · advanced hands-on
→ Implement projector-based readouts→ Supercharge GNNs
Self-RAG Tutorial: How to Make Your AI Fact-Check Itself | Advanced RAG | CampusX
CampusX · beginner hands-on
→ Implement Self-RAG in RAG systems→ Improve fact-checking in AI models
Advanced Agentic RAG And Its Types New Series-Generative AI
Krish Naik · advanced hands-on
→ Build advanced RAG models→ Implement agentic RAG
Advanced RAG: How Corrective RAG (CRAG) Solves Traditional RAG Problems | CampusX
CampusX · intermediate hands-on
→ Implement CRAG to improve RAG response quality→ Evaluate retrieval quality in RAG systems
Advanced RAG 05 - HyDE - Hypothetical Document Embeddings
Sam Witteveen · beginner hands-on
→ Implement HyDE for document embeddings→ Use RAG for information retrieval→ Build agents with LLMs