apunkt/sqlite-vec
1
0
Fork 0
mirror of https://github.com/asg017/sqlite-vec.git synced 2026-04-25 00:36:56 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Add DiskANN index for vec0 virtual table

Browse source 
Add DiskANN graph-based index: builds a Vamana graph with configurable R
(max degree) and L (search list size, separate for insert/query), supports
int8 quantization with rescore, lazy reverse-edge replacement, pre-quantized
query optimization, and insert buffer reuse. Includes shadow table management,
delete support, KNN integration, compile flag (SQLITE_VEC_ENABLE_DISKANN),
release-demo workflow, fuzz targets, and tests. Fixes rescore int8
quantization bug.
This commit is contained in:
Alex Garcia 2026-03-29 19:46:53 -07:00
parent e2c38f387c
commit 575371d751
23 changed files with 6550 additions and 135 deletions
Download patch file Download diff file Expand all files Collapse all files

20
benchmarks-ann/Makefile
View file

@ -19,9 +19,16 @@ RESCORE_CONFIGS = \
"rescore-bit-os16:type=rescore,quantizer=bit,oversample=16" \
"rescore-int8-os8:type=rescore,quantizer=int8,oversample=8"
ALL_CONFIGS = $(BASELINES) $(RESCORE_CONFIGS) $(IVF_CONFIGS)
# --- 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"
.PHONY: seed ground-truth bench-smoke bench-rescore bench-ivf bench-10k bench-50k bench-100k bench-all \
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 ---
@ -37,7 +44,8 @@ ground-truth: seed
bench-smoke: seed
$(BENCH) --subset-size 5000 -k 10 -n 20 -o runs/smoke \
"brute-float:type=baseline,variant=float" \
"ivf-quick:type=ivf,nlist=16,nprobe=4"
"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 -o runs/rescore \
@ -62,6 +70,12 @@ bench-ivf: seed
$(BENCH) --subset-size 50000 -k 10 -o runs/ivf $(BASELINES) $(IVF_CONFIGS)
$(BENCH) --subset-size 100000 -k 10 -o runs/ivf $(BASELINES) $(IVF_CONFIGS)
# --- DiskANN across sizes ---
bench-diskann: seed
$(BENCH) --subset-size 10000 -k 10 -o runs/diskann $(BASELINES) $(DISKANN_CONFIGS)
$(BENCH) --subset-size 50000 -k 10 -o runs/diskann $(BASELINES) $(DISKANN_CONFIGS)
$(BENCH) --subset-size 100000 -k 10 -o runs/diskann $(BASELINES) $(DISKANN_CONFIGS)
# --- Report ---
report:
@echo "Use: sqlite3 runs/<dir>/results.db 'SELECT * FROM bench_results ORDER BY recall DESC'"