`MemoryConfig::quantized_index` stores the HNSW index's own copy of the
embeddings as i8 rather than f32. At 100k x 384 that takes the index from
266 to 123 MiB and the whole reopened store from 399 to 256 MiB — 2.72x
to 1.74x the raw vectors, the largest remaining item in the footprint.
Quantised distances are approximate and `ef` cannot compensate, because
the loss is in the distances rather than in the graph: recall@10 tops out
at 0.967 against f32's 0.9995 and does not move between ef=128 and
ef=256. The store already holds the exact embeddings, though, so when the
index is quantised the query path re-scores the candidate pool against
them before fusion. That restores recall (0.9940 vs 0.9945 at ef=64) and
costs about 13% of QPS.
Off by default: it trades query speed for memory and which side is worth
more depends on the deployment. The flag is persisted in `/meta`, so a
reopened store does not silently revert to four times the index memory,
and the sidecar graph is rehydrated into the configured storage.
Also on the CLI as `create --quantized-index`.
Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
The HNSW index keeps its own copy of every vector, which at 100K x 384
f32 is ~146 MiB — the largest single item in the 2.43x footprint now
that the agent stores embeddings once. `Storage::Int8` cuts that copy to
a quarter by scaling each row to i8.
The scale is per row, not global. Unit-length rows in d dimensions have
components around 1/sqrt(d), so a fixed [-1, 1] scale spends fewer than
12 of the 255 levels on a 128-dimensional vector; measured against an
exact ranking that gives 0.35 top-10 overlap. Scaling each row by its
own largest component uses the full range and brings it to 0.99.
Quantised distances still cost recall on their own, and `ef` does not
buy it back because the loss is in the distances rather than the graph:
at N=100K recall@10 tops out at 0.967 against f32's 0.9995. Re-scoring a
wider candidate pool against the exact vectors removes the gap
(0.9940 vs 0.9945 at ef=64) for ~13% of query throughput and ~16% of
build time. That is the intended use, so it is what the test asserts —
against ground truth, not against the f32 index, whose own mistakes a
re-scored search is entitled to get right.
Default is unchanged: `Storage::Float32`, chosen by every existing
constructor. Serialized indexes carry f32 vectors and no storage tag, so
a quantised index is rebuilt rather than loaded; `compact()` keeps the
storage it was given.
The harness grows `--int8` and `--rerank` axes, and reports the storage
in each table header.
Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
MemoryCache held every embedding in two places: a `Vec<Vec<f32>>` and a
flattened copy for the batched kernels, kept in lock-step on every push,
update and compaction. A store loaded from disk therefore carried the corpus
twice, plus one heap allocation per entry.
A new `cache::Embeddings` owns just the flat `[N x dim]` buffer and indexes
into it, so `embeddings[i]` still reads as a `&[f32]` row. The batch kernels
take a `VectorSet` (implemented for both `Embeddings` and `Vec<Vec<f32>>`)
instead of `&[Vec<f32>]`, so their callers and tests are unchanged. Loading no
longer unflattens what it just read.
100k 384-dim entries, reopened from disk: 505 -> 357 MiB, 3.44x -> 2.43x the
raw vectors. Recall (1.0000 at ef=64) and query latency are unchanged.
Rows are now always exactly `dim` long, shorter ones zero-padded. The old
representation allowed ragged rows, which silently misaligned the flattened
copy — every row after a wrong-length embedding — and `update` carried a
comment about falling back to a rebuild to avoid exactly that. It is now
unrepresentable. A record saved without an embedding holds a zero row and is
told apart by its norm, which is what `total_embeddings` now counts.
Measured with a counting allocator rather than RSS: freeing a structure
returns its pages to the allocator's pool, not the OS, so an RSS reading from
inside the process showed the two representations as identical.
Breaking: MemoryCache::embeddings changes type, embeddings_flat is replaced by
flat_embeddings(), rebuild_flat() is a deprecated no-op.
Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
`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]>
Fusion min-max normalises over every keyword match, so hybrid_search asked
BM25 for a ranked list of the whole corpus: a hash insert per posting, then a
sort of every match, then the merge sorted every candidate again to keep k.
- BM25Index::scores returns every match unsorted, accumulated in a dense array
(contributions are strictly positive, so zero means untouched). search() is
built on it with the bounded heap.
- merge_vector_keyword partitions out its top k (select_nth) and orders only
those, with the same score-then-id order.
- Both hybrid paths use scores().
Rankings are identical (equivalence tests for both changes). p50 0.24 -> 0.07
ms (1K), 2.1 -> 0.49 ms (10K), 23 -> 4.65 ms (100K).
The harness gains --fusion-study, which measured the alternative — capping the
keyword pool — and found it changes the top-10 for most queries (overlap
0.83-0.92, different #1 for 10-35%) for only a 2x saving. Not adopted.
Co-Authored-By: Claude Fable 5.1 <[email protected]>
open() marked the HNSW index dirty, so the first search of every session
rebuilt it from scratch — 36 s at 100K records with the (better, slower)
heuristic build. First query after open is now 1.7 / 15 / 159 ms at
1K / 10K / 100K; what remains is the one-off keyword index build.
- clawhdf5-ann: HnswIndex::graph_to_bytes / from_graph_bytes serialize the
graph only (levels, tombstones, adjacency as u32, CRC32). The existing HDF5
serializer embeds a full copy of every vector, which would double a store
that already holds them. Loading validates everything — counts, levels vs
layer count, connection limits, every neighbour id and the layer it must
exist on — so a damaged graph, or a hostile one with a valid checksum, is an
error rather than an out-of-bounds walk during search.
- clawhdf5-agent: each checkpoint writes the graph to <store>.h5.ann (synced,
atomic, before the .h5) and records a fresh generation id in /meta. open()
loads the sidecar only if its generation matches that checkpoint; missing,
stale, damaged or mismatched sidecars are ignored and the index rebuilt.
Records appended through WAL replay join the loaded index incrementally; a
replayed Update or Tombstone invalidates it. snapshot() copies it. Only an
index that exactly mirrors the cache is saved; otherwise a stale sidecar is
removed.
- ensure_hnsw_fresh inserts records appended since the last sync instead of
rebuilding, so save_batch no longer marks the whole index dirty.
- CheckpointMeta { wal_applied, ann_generation } with *_with_meta build/write/
read functions; the *_with_mark ones delegate.
- Harness reports the one-off cold index build separately from the first query
after a reopen.
Co-Authored-By: Claude Fable 5.1 <[email protected]>
Neighbours were selected as the plain closest-M, for both a new node's links
and back-link pruning. On clustered data every link of a node inside a tight
cluster then goes to that same cluster, so clusters become islands a search
entering elsewhere can never reach: recall@10 was 0.87 / 0.67 / 0.31 at
1K / 10K / 100K (384-dim) and flat in ef. Uniform random data — all the
existing tests used — does not show it.
Implement the HNSW paper's Algorithm 4 with keepPrunedConnections: accept a
candidate only if it is closer to the node than to every neighbour already
accepted, then fill spare slots with the closest rejected ones. Recall@10 at
ef=64 is now 1.00 / 1.00 / 0.98 and rises with ef; uniform data improves
slightly. Build is ~3.5x slower at 10K (extra distance evaluations), to be
recovered by the distance-kernel work. The needless rayon fan-out over <=33
distances in prune_connections is gone.
Tests: a clustered-data recall test for bulk build and incremental insert
(scores 0.43 with the old selection), and a unit test of the selection rule.
Harness gains --uniform and --ann-only; before/after in BENCHMARKS.md.
Co-Authored-By: Claude Fable 5.1 <[email protected]>
New clawhdf5-bench binary `search_harness`, the measurement baseline for the
search hot-path work. On deterministic clustered 384-dim data it reports HNSW
build time and, per ef, recall@10 against an exact scan, QPS and p50/p99; and
for HDF5Memory: ingest, checkpoint, open, first-query-after-open and
steady-state hybrid_search latency at 1K/10K (and 100K with --full). Optional
JSON output for tracking.
Baseline recorded in BENCHMARKS.md. It shows two problems: HNSW recall@10 does
not respond to ef and falls from 0.87 (1K) to 0.31 (100K) on clustered data,
and end-to-end hybrid_search is ~1000x slower than its vector stage because
every query rebuilds BM25 and rewrites the .h5 file.
Co-Authored-By: Claude Fable 5.1 <[email protected]>
