mirror of
https://github.com/asg017/sqlite-vec.git
synced 2026-04-25 08:46:49 +02:00
f2c9fb8f08
Infrastructure improvements: - Fix benchmarks-ann Makefile: type=baseline -> type=vec0-flat (baseline was never a valid INDEX_REGISTRY key) - Add DiskANN + text primary key test: insert, KNN, delete, KNN - Add rescore + text primary key test: insert, KNN, delete, KNN - Add WAL concurrency test: reader sees snapshot isolation while writer has an open transaction, KNN works on reader's snapshot Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
85 lines
2.9 KiB
Makefile
85 lines
2.9 KiB
Makefile
BENCH = python bench.py
|
|
BASE_DB = cohere1m/base.db
|
|
EXT = ../dist/vec0
|
|
|
|
# --- Baseline (brute-force) configs ---
|
|
BASELINES = \
|
|
"brute-float:type=vec0-flat,variant=float" \
|
|
"brute-int8:type=vec0-flat,variant=int8" \
|
|
"brute-bit:type=vec0-flat,variant=bit"
|
|
|
|
# --- IVF configs ---
|
|
IVF_CONFIGS = \
|
|
"ivf-n32-p8:type=ivf,nlist=32,nprobe=8" \
|
|
"ivf-n128-p16:type=ivf,nlist=128,nprobe=16" \
|
|
"ivf-n512-p32:type=ivf,nlist=512,nprobe=32"
|
|
|
|
RESCORE_CONFIGS = \
|
|
"rescore-bit-os8:type=rescore,quantizer=bit,oversample=8" \
|
|
"rescore-bit-os16:type=rescore,quantizer=bit,oversample=16" \
|
|
"rescore-int8-os8:type=rescore,quantizer=int8,oversample=8"
|
|
|
|
# --- DiskANN configs ---
|
|
DISKANN_CONFIGS = \
|
|
"diskann-R48-binary:type=diskann,R=48,L=128,quantizer=binary" \
|
|
"diskann-R72-binary:type=diskann,R=72,L=128,quantizer=binary" \
|
|
"diskann-R72-int8:type=diskann,R=72,L=128,quantizer=int8" \
|
|
"diskann-R72-L256:type=diskann,R=72,L=256,quantizer=binary"
|
|
|
|
ALL_CONFIGS = $(BASELINES) $(RESCORE_CONFIGS) $(IVF_CONFIGS) $(DISKANN_CONFIGS)
|
|
|
|
.PHONY: seed ground-truth bench-smoke bench-rescore bench-ivf bench-diskann bench-10k bench-50k bench-100k bench-all \
|
|
report clean
|
|
|
|
# --- Data preparation ---
|
|
seed:
|
|
$(MAKE) -C cohere1m
|
|
|
|
ground-truth: seed
|
|
python ground_truth.py --subset-size 10000
|
|
python ground_truth.py --subset-size 50000
|
|
python ground_truth.py --subset-size 100000
|
|
|
|
# --- Quick smoke test ---
|
|
bench-smoke: seed
|
|
$(BENCH) --subset-size 5000 -k 10 -n 20 --dataset cohere1m -o runs \
|
|
"brute-float:type=vec0-flat,variant=float" \
|
|
"ivf-quick:type=ivf,nlist=16,nprobe=4" \
|
|
"diskann-quick:type=diskann,R=48,L=64,quantizer=binary"
|
|
|
|
bench-rescore: seed
|
|
$(BENCH) --subset-size 10000 -k 10 --dataset cohere1m -o runs \
|
|
$(RESCORE_CONFIGS)
|
|
|
|
|
|
# --- Standard sizes ---
|
|
bench-10k: seed
|
|
$(BENCH) --subset-size 10000 -k 10 --dataset cohere1m -o runs $(ALL_CONFIGS)
|
|
|
|
bench-50k: seed
|
|
$(BENCH) --subset-size 50000 -k 10 --dataset cohere1m -o runs $(ALL_CONFIGS)
|
|
|
|
bench-100k: seed
|
|
$(BENCH) --subset-size 100000 -k 10 --dataset cohere1m -o runs $(ALL_CONFIGS)
|
|
|
|
bench-all: bench-10k bench-50k bench-100k
|
|
|
|
# --- IVF across sizes ---
|
|
bench-ivf: seed
|
|
$(BENCH) --subset-size 10000 -k 10 --dataset cohere1m -o runs $(BASELINES) $(IVF_CONFIGS)
|
|
$(BENCH) --subset-size 50000 -k 10 --dataset cohere1m -o runs $(BASELINES) $(IVF_CONFIGS)
|
|
$(BENCH) --subset-size 100000 -k 10 --dataset cohere1m -o runs $(BASELINES) $(IVF_CONFIGS)
|
|
|
|
# --- DiskANN across sizes ---
|
|
bench-diskann: seed
|
|
$(BENCH) --subset-size 10000 -k 10 --dataset cohere1m -o runs $(BASELINES) $(DISKANN_CONFIGS)
|
|
$(BENCH) --subset-size 50000 -k 10 --dataset cohere1m -o runs $(BASELINES) $(DISKANN_CONFIGS)
|
|
$(BENCH) --subset-size 100000 -k 10 --dataset cohere1m -o runs $(BASELINES) $(DISKANN_CONFIGS)
|
|
|
|
# --- Report ---
|
|
report:
|
|
@echo "Use: sqlite3 runs/cohere1m/<size>/results.db 'SELECT run_id, config_name, status, recall FROM runs JOIN run_results USING(run_id)'"
|
|
|
|
# --- Cleanup ---
|
|
clean:
|
|
rm -rf runs/
|