Hybrid Retrieval Systems
Build hybrid retrieval systems combining BM25 sparse search with dense vector embeddings using reciprocal rank fusion for superior semantic search performance.
8 min readConcept
Tagged with
search
Explore machine learning concepts related to search. Clear explanations and practical insights.
7
Concepts Found
Concepts Related to search
BM25 Algorithm
Master the BM25 algorithm, the probabilistic ranking function powering Elasticsearch and Lucene for keyword-based document retrieval and search systems.
11 min readConcept
ANN Algorithms Comparison
Compare all approximate nearest neighbor algorithms side-by-side: HNSW, IVF-PQ, LSH, Annoy, and ScaNN. Find the best approach for your use case.
9 min readConcept
HNSW: Hierarchical Navigable Small World
Interactive visualization of HNSW - the graph-based algorithm that powers modern vector search with logarithmic complexity.
7 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.
8 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.
8 min readConcept
Multi-Vector Late Interaction
Explore ColBERT and other multi-vector retrieval models that use fine-grained token-level matching for superior search quality.
8 min readConcept