BM25 Algorithm for Text Retrieval
Master the BM25 algorithm, the probabilistic ranking function powering Elasticsearch and Lucene for keyword-based document retrieval and search systems.
12 min readConcept
Tagged with
Search
Explore machine learning concepts related to Search. Clear explanations and practical insights.
7
Concepts Found
Concepts Related to Search
Multi-Vector Late Interaction
Explore ColBERT and other multi-vector retrieval models that use fine-grained token-level matching for superior search quality.
12 min readConcept
Hybrid Retrieval Systems
Build hybrid retrieval systems combining BM25 sparse search with dense vector embeddings using reciprocal rank fusion for superior semantic search performance.
10 min readConcept
HNSW vs IVF-PQ vs LSH: Approximate Nearest Neighbor Algorithms Compared
How HNSW, IVF-PQ, and LSH compare for approximate nearest neighbor (ANN) search — recall, latency, memory, build cost, and update characteristics — with Annoy, ScaNN, and DiskANN included for completeness.
15 min readConcept
LSH: Locality Sensitive Hashing
Explore how LSH uses probabilistic hash functions to find similar vectors in sub-linear time, perfect for streaming and high-dimensional data.
10 min readConcept
IVF-PQ: Inverted File with Product Quantization
Learn how IVF-PQ combines clustering and compression to enable billion-scale vector search with minimal memory footprint.
12 min readConcept
HNSW: Hierarchical Navigable Small World
How HNSW navigates a layered proximity graph to find nearest neighbors in logarithmic time — the default in-memory index of modern vector databases.
9 min readConcept