b4383bb227
perf: pre-allocate collections with known capacity in hot paths
...
- Use with_capacity for chunk_by_source, results, per_entity_traces,
and selected_chunks in assemble() where bound is known
- Pre-allocate tokens/terms vectors in normalize_fts_query and
extract_keywords based on input length
- Pre-allocate neighbor_ids, seen, and ordered in graph expansion
based on relationship count
2026-05-26 20:21:25 +02:00
000852c94c
clippy: adhere to pedantic clippy, uniform test error handling
2026-05-26 20:21:13 +02:00
6a5d631287
chore: remove unused clap dep and fix test_session_table name
...
- Remove clap dependency from retrieval-pipeline (RetrievalStrategy
already has FromStr/Display; evaluations uses clap directly)
- Rename session table from test_session_table to session
2026-05-26 20:14:29 +02:00
17f252e630
release: 1.0.0
...
fix: cargo dist
2026-01-11 20:35:01 +01:00
654add98bc
fix: never block fts, rely on rrf
2025-12-22 22:56:57 +01:00
79ea007b0a
tidying stuff up, dto for search
2025-12-20 22:30:31 +01:00
a090a8c76e
retrieval simplfied
2025-12-09 20:35:42 +01:00
0cb1abc6db
beir-rff
2025-12-08 20:39:12 +01:00
d3fa3be3e5
retrieval: hybrid search, linear fusion
2025-12-04 12:48:59 +01:00
dd881efbf9
benchmarks: ready for hybrid revised
2025-12-03 11:38:07 +01:00
08b1612fcb
refactored to clap, mrr and ndcg
2025-11-28 21:26:51 +01:00
030f0fc17d
evals: v3, ebeddings at the side
...
additional indexes
2025-11-26 15:15:10 +01:00
226b2db43a
retrieval-pipeline: v1
2025-11-19 12:58:27 +01:00
f535df7e61
retrieval-pipeline: v0
2025-11-18 22:46:35 +01:00
Per Stark