quantumclaw/clawhdf5
3
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 1 Wiki Activity

feat(agent): build the vector index in parallel by default

Browse Source 
`parallel` joins the agent's default features, so the HNSW bulk build uses the
thread pool: cold index build at 10K records 1152 -> ~380 ms in a same-moment
A/B (the graph is identical either way). Nothing else on the measured paths
changes — ingest, checkpoint, open and steady-state query times are the same
with the feature on or off. Adds rayon to the default dependency set; opt out
with `--no-default-features --features float16,hnsw`.

Harness: `--e2e-only` runs the end-to-end section without the index
benchmarks. Note for anyone comparing numbers: this machine's absolute timings
drifted ~1.5x over a long session, so only same-moment A/B runs are
comparable.

Co-Authored-By: Claude Fable 5.1 <[email protected]>
This commit is contained in:
osobh
2026-09-19 13:52:23 -07:00
co-authored by Claude Fable 5.1
parent 8803d0754b
commit f507803ec1
4 changed files with 12 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CHANGELOG.md
+3 -1
View File
@@ -9,7 +9,9 @@
With the `parallel` feature, planning and pruning run on a thread pool (10K:
388 ms, 100K: ~21 s -> 5.9 s on 16 cores). The graph is deterministic and
identical with or without the feature. `clawhdf5-agent`'s `parallel` feature
now enables it for the agent's index.
enables it for the agent's index and is now **on by default** (adds `rayon`
to the default dependency set; build with `--no-default-features --features
float16,hnsw` to opt out).
- `clawhdf5-ann`: `HnswIndex::search` returned fewer than `k` results — often
none — when the records nearest the query had been deleted: it collected `ef`
candidates, *then* dropped the deleted ones, *then* took `k`. Deleted nodes