Skip to content
LeetLLM
Tracks
Intermediate22 lessons

RAG and Search Systems

Learn document ingestion, retrieval, reranking, evaluation, and secure enterprise RAG as one coherent path.

Builders working on search, support bots, internal knowledge assistants, and document QA.

You can design a retrieval pipeline, debug faithfulness failures, and choose vector, lexical, and graph retrieval pieces deliberately.

  1. 1Static to Contextual EmbeddingsTurn token IDs into vectors, learn what nearby usage captures, and see why a word such as charge needs sentence-dependent representations.Core LLM FoundationsMedium25 min
  2. 2Sentence Embeddings & Contrastive LossBuild sentence embeddings with contrastive losses, audit negative labels, and measure retrieval recall, latency, and vector storage.Transformer Deep DivesHard64 min
  3. 3Embedding Similarity & QuantizationCompare vector scores, test shorter prefixes, and measure scalar, product, and binary quantization against retrieval requirements.Transformer Deep DivesHard52 min
  4. 4Dimensionality Reduction for EmbeddingsShrink and inspect embedding indexes without guessing: measure recall while testing PCA, projections, native shortening, and quantization.Applied LLM EngineeringMedium37 min
  5. 5File Ingestion for AITurn PDFs, scans, HTML, and Markdown into faithful evidence records with provenance and quality checks before retrieval.Core LLM FoundationsMedium20 min
  6. 6Chunking StrategiesTurn clean documents into retrieval units that preserve answers, citations, and measurable search quality.Core LLM FoundationsMedium21 min
  7. 7Core Retrieval AlgorithmsBuild and evaluate the evidence-selection stage of a technical-docs assistant with BM25, dense similarity, rank fusion, reranking, and approximate search audits.ML Algorithms & EvaluationMedium29 min
  8. 8Production RAG PipelinesDesign a secure, traceable RAG service around versioned policy evidence, grounded answers, abstention, release gates, and latency budgets.Applied LLM EngineeringMedium32 min
  9. 9Vector DB Internals: HNSW & IVFTrace graph hops, expose an IVF boundary miss, and test why compressed scores, filters, and shard tails can change nearest-neighbor results.Advanced Agents & RetrievalHard53 min
  10. 10Hybrid Search: Dense + SparseUpgrade a permission-safe RAG retriever with BM25, semantic scores, rank fusion, and recall gates for exact codes and paraphrased policy questions.Applied LLM EngineeringMedium32 min
  11. 11Reranking and Cross-Encoders for RAGRank retrieved passages with cross-encoders, measure candidate recall and ordering, and preserve source permissions, text boundaries, and serving budgets.Applied LLM EngineeringMedium33 min
  12. 12RAG Evaluation for Reliable AnswersSeparate evidence support, citation accuracy, relevance, and completeness. Build a small RAG evaluation harness, test misleading answers, and interpret abstention and slice-level results.Applied LLM EngineeringMedium28 min
  13. 13LLM-as-a-Judge EvaluationBuild rubric-based judges, detect unstable preferences, and measure agreement without mistaking a plausible score for ground truth.Applied LLM EngineeringMedium25 min
  14. 14Hallucination Detection & MitigationBuild a structured grounding gate for incident updates, test its failure cases, and distinguish evidence support from consistency, freshness, and real-world truth.Applied LLM EngineeringMedium30 min
  15. 15LLM Observability & MonitoringConnect answer-quality checks to latency, cost, traces, and actionable alerts without confusing missing evidence with a healthy service.Applied LLM EngineeringMedium31 min
  16. 16Advanced RAG: HyDE & Self-RAGCompare query rewriting, HyDE, Self-RAG, and CRAG, then test retrieval coverage, support checks, fallback policy, and added cost on a docs assistant.Advanced Agents & RetrievalHard54 min
  17. 17GraphRAG & Knowledge GraphsBuild source-linked incident graphs, compare local retrieval with community-report search, and test where graph coverage, identity, and authorization can fail.Advanced Agents & RetrievalHard55 min
  18. 18RAG Security & Access ControlStop a signing-key query from exposing a restricted runbook: authorize before export, isolate tenants, and audit the reject path.Advanced Agents & RetrievalHard54 min
  19. 19Model Versioning & DeploymentTurn an evaluated LLM change into an immutable release bundle, promote it through measured traffic, and roll back without losing lineage.Applied LLM EngineeringMedium31 min
  20. 20Semantic Caching & Cost OptimizationTest whether policy answers can be reused across paraphrases within release, access, and freshness boundaries; compare quality, cost, and tail latency before serving hits.Applied LLM EngineeringMedium32 min
  21. 21Capstone: Document QABuild an approved-policy lookup, test citations and refusals, and trace source-bound reviews through a research-job simulation.Portfolio CapstonesHard52 min
  22. 22LLM-Powered Search EngineDesign a permission-aware search pipeline with current evidence, hybrid ranking, auditable citations, checked streaming, and realistic latency and capacity boundaries.System Design CapstonesHard30 min