asmhatre/spring-ai
1
0
Fork 0
Code Activity

Add vector-stores module: one dataset through VectorStore on pgvector, Redis, Qdrant and Elasticsearch

Browse Source 
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/.
This commit is contained in:
asmhatre
2026-10-09 05:50:01 +00:00
parent 527f4ba7ff
commit 74e6334704
26 changed files with 1065 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
vector-stores/output/04-defaults-that-matter.txt
+7
View File
@@ -0,0 +1,7 @@
pgvector hnsw.ef_search = 40
pgvector index: CREATE INDEX vs_bench_index ON public.vs_bench USING hnsw (embedding vector_cosine_ops)
elasticsearch embedding mapping: "embedding":{"type":"dense_vector","dims":384,"index":true,"similarity":"cosine","index_options":{"type":"bbq_hnsw","m":16,"ef_construction":100,"rescore_vector":{"oversample":3.0}}}
qdrant points_count=30000 indexed_vectors_count=30000
qdrant hnsw_config: "hnsw_config":{"m":16,"ef_construct":100,"full_scan_threshold":10000,"max_indexing_threads":0,"on_disk":false}
qdrant indexing_threshold (KB): 10000
redis num_docs=30000 percent_indexed=1