FromZero2AI
← Back to Courses
Advanced~12 hours8 lessons

Advanced RAG Patterns

Go beyond basic retrieval. Master chunking strategies, hybrid search, re-ranking, query transformation, and production-grade RAG evaluation.

By Bishwambhar Sen • Last updated

What you'll build: a production-grade query pipeline with hybrid re-ranking
Start Course

Curriculum

Module A: Better Retrieval
3 lessons

Lesson 1: Chunking Strategies That Actually Work

Fixed-size, recursive character, semantic, and document-aware chunking — learn how chunk size and overlap directly impact retrieval quality, with experiments to prove it.

70 min

Lesson 2: Hybrid Search: Semantic + BM25 Keyword

Combine dense vector search with sparse BM25 keyword matching using Reciprocal Rank Fusion (RRF). Understand when hybrid beats pure semantic and how to tune the alpha weight.

75 min

Lesson 3: Re-ranking with Cross-Encoders

Use a cross-encoder model to re-score retrieved candidates and surface the truly most relevant chunks. Covers Cohere Rerank API and local sentence-transformers re-rankers.

60 min
Recommended Watch

What is Retrieval-Augmented Generation (RAG)?

How RAG combines retrieval with generation to ground LLM responses in factual, up-to-date information.

IBM Technology6:59
Module B: Query Engineering
3 lessons

Lesson 4: Query Transformation & HyDE

Rewrite ambiguous user queries before retrieval using step-back prompting and Hypothetical Document Embeddings (HyDE) — closing the gap between what users ask and what documents say.

65 min

Lesson 5: Multi-Query & Step-Back Retrieval

Generate multiple query variations from a single user question and merge the retrieved sets. Use step-back questions to retrieve broader context for narrow queries.

55 min

Lesson 6: Contextual Compression & Filtering

Filter retrieved chunks down to only the sentences that answer the query, using LLM-based extractive compression. Reduce token costs while improving answer quality.

50 min
Recommended Watch

Advanced RAG Techniques

Multi-query retrieval, re-ranking, and hybrid search strategies for production-grade RAG pipelines.

Sam Witteveen20:23
Module C: Evaluation & Production
2 lessons

Lesson 7: Evaluating RAG Pipelines with RAGAS

Measure faithfulness, answer relevancy, context precision, and context recall using the RAGAS framework. Build a golden dataset and run automated eval across pipeline variants.

75 min

Lesson 8: Capstone — Production RAG Pipeline

Build a production-grade RAG system that combines hybrid search, re-ranking, and contextual compression, evaluated end-to-end with RAGAS on a real document corpus.

120 min
Recommended Watch

Evaluating RAG Pipelines

Metrics and frameworks for evaluating RAG system quality — retrieval precision, faithfulness, and relevance.

DeepLearning.AI11:47

Course Quiz

5 questions · ~5 min · Pass 4/5 to unlock your badge

Start Quiz →