šļø KD-Trees & Ball-Trees
Exact nearest-neighbor search with space-partitioning trees ā rigorous and immediately practical.
šļø Approximate Nearest Neighbor Search
HNSW, IVF, and LSH ā the three dominant families of approximate nearest-neighbor / vector search.
šļø Tokenization Algorithms
BPE, WordPiece, and Unigram LM ā the subword tokenizers that power virtually every modern LLM.
šļø Matrix Ops, Attention O(nĀ²) & Sparse Formats
Matrix multiplication complexity, attention's O(nĀ²) wall, and the sparse formats that scale it.
šļø Beam Search & Constrained Decoding
Theory, math, and algorithms of beam search and constrained decoding for LLM generation.
šļø Graph Algorithms for KG & GraphRAG
How graph algorithms power knowledge graphs and GraphRAG retrieval in production LLM systems.
šļø State Machines & DAGs for Agents (LangGraph)
Designing LangGraph agent systems grounded in finite-state-machine and DAG theory.
šļø Streaming & Caching Data Structures
LRU/LFU caches, Bloom filters, count-min sketch, and reservoir sampling for bounded-memory systems.
šļø š® ANN Search (Practice)
Interactive practice for ANN Search ā a live in-browser Python exercise.
šļø š® Beam Search (Practice)
Interactive practice for Beam Search & Constrained Decoding ā a live in-browser Python exercise.
šļø š® GraphRAG (Practice)
Interactive practice for Graph Algorithms for KG & GraphRAG ā a live in-browser Python exercise.
šļø š® KD-Trees (Practice)
Interactive practice for KD-Trees & Ball-Trees ā a live in-browser Python exercise.
šļø š® Matrix/Attention (Practice)
Interactive practice for Matrix Ops & Attention ā a live in-browser Python exercise.
šļø š® Agent DAGs (Practice)
Interactive practice for State Machines & DAGs for Agents ā a live in-browser Python exercise.
šļø š® Streaming/Caching (Practice)
Interactive practice for Streaming & Caching Data Structures ā a live in-browser Python exercise.
šļø š® Tokenization (Practice)
Interactive practice for Tokenization Algorithms ā a live in-browser Python exercise.