Retrieval-Augmented Generation and Vector Databases

85 lessons in AI Fundamentals

• Distance to Similarity SortingCode Quiz
• Real-World Use Cases for RAGSlides / Video
• Common RAG Failure ModesSlides / Video
• RAG vs Fine-Tuning Trade-offsSlides / Video
• Vector Database Tools LandscapeSlides / Video
• Evaluating RAG SystemsSlides / Video
• Choosing an Embedding Model for RetrievalSlides / Video
• Chunk Overlap and Context WindowsSlides / Video
• Reranking Retrieved ResultsSlides / Video
• Context Injection and Prompt AugmentationSlides / Video
• Metadata Filtering and Hybrid SearchSlides / Video
• Top-k Retrieval and Result RankingSlides / Video
• Vector Indexing: HNSW and IVFSlides / Video
• Approximate Nearest Neighbor SearchSlides / Video
• Semantic Search vs Keyword SearchSlides / Video
• What a Vector Database IsSlides / Video
• Generating and Storing Document EmbeddingsSlides / Video
• Document Chunking StrategiesSlides / Video
• Indexing vs Query Phase in RAGSlides / Video
• RAG: Retriever Plus GeneratorSlides / Video
• Reranking with a Cross-EncoderCode Quiz
• Chunk-to-Source Mapping for CitationsCode Quiz
• Retrieval Recall@K EvaluationCode Quiz
• Handling Empty Retrieval ResultsCode Quiz
• Embedding Dimension Mismatch BugCode Quiz
• Context Assembly and Budget TruncationCode Quiz
• Vector Quantization and CompressionQuiz
• Retrieval Quality MetricsQuiz
• Top-K Retrieval and ContextQuiz
• Faithfulness and Answer RelevanceQuiz
• Multi-Vector Late-Interaction RetrievalQuiz
• Document Chunking StrategiesQuiz
• Chunk Size and OverlapQuiz
• Embedding Model SelectionQuiz
• Hybrid SearchQuiz
• Exact vs Approximate Trade-offsQuiz
• Indexing and Ingestion PipelineQuiz
• ANN Index StructuresQuiz
• Embedding Dimensionality Trade-offsQuiz
• Common RAG Failure ModesQuiz
• RAG vs Fine-TuningQuiz
• Core RAG Pipeline StagesQuiz
• Grounding and CitationQuiz
• Query Transformation and ExpansionQuiz
• Re-Ranking Retrieved ResultsQuiz
• Metadata Filtering in SearchQuiz
• What a Vector Database IsQuiz
• Approximate Nearest Neighbor SearchQuiz
• Upserting Vectors with MetadataCode Quiz
• Combining BM25 and Vector ScoresCode Quiz
• Reciprocal Rank FusionCode Quiz
• Deduplicating Retrieved ChunksCode Quiz
• Filtering Before vs After SearchCode Quiz
• Similarity Score Threshold FilteringCode Quiz
• HNSW efSearch vs topKCode Quiz
• Maximal Marginal Relevance SelectionCode Quiz
• Embedding a Query via APICode Quiz
• Euclidean (L2) DistanceCode Quiz
• Batch Similarity with MatmulCode Quiz
• Brute-Force Vector SearchCode Quiz
• Normalizing for Cosine SimilarityCode Quiz
• FAISS-style ANN Build & QueryCode Quiz
• Dot Product RankingCode Quiz
• Embedding Model SelectionFlashcard
• Cost and Latency in RAGFlashcard
• Query Transformation and ExpansionFlashcard
• Hybrid Search BasicsFlashcard
• Grounding and Source CitationFlashcard
• Multi-Query and Fusion RetrievalFlashcard
• Popular Vector Database ToolsFlashcard
• Retrieval Failure ModesFlashcard
• Re-ranking Retrieved ResultsFlashcard
• Evaluating RAG SystemsFlashcard
• Indexing vs Query PhaseFlashcard
• Chunk Size and Overlap TradeoffsFlashcard
• RAG Pipeline ArchitectureFlashcard
• IVF and Other ANN Index TypesFlashcard
• Top-K RetrievalFlashcard
• Document Chunking StrategiesFlashcard
• Metadata Filtering in Vector SearchFlashcard
• Vector DB vs Traditional DatabaseFlashcard
• Approximate Nearest Neighbor SearchFlashcard
• Exact vs Approximate SearchFlashcard
• HNSW IndexingFlashcard
• What is a Vector DatabaseFlashcard