Files
spring-ai/vector-stores/output/10-elasticsearch-index-options.txt
T
asmhatre 74e6334704 Add vector-stores module: one dataset through VectorStore on pgvector, Redis, Qdrant and Elasticsearch
Ingest time, recall@10 against exact search, latency, metadata filtering and running cost, with
the defaults that cost recall reproduced and every figure written to output/.
2026-10-09 05:50:01 +00:00

7 lines
439 B
Plaintext

same 30,000 documents, same queries; only the dense_vector index_options.type differs (the first row is Spring AI's own mapping)
type recall@10 p50 ms filt recall filt p50 ms
bbq_hnsw* 0.472 3.1 0.550 3.0
int8_hnsw 0.967 3.6 0.969 3.2
hnsw 0.997 3.5 1.000 2.9
* default; its full mapping is in 04-defaults-that-matter.txt