Add DiskANN index for vec0 virtual table

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

View file

@ -26,7 +26,7 @@ FUZZ_LDFLAGS ?= $(shell \
echo "-Wl,-ld_classic"; \
fi)
FUZZ_CFLAGS = $(FUZZ_SANITIZERS) -I ../../ -I ../../vendor -DSQLITE_CORE -g $(FUZZ_LDFLAGS)
FUZZ_CFLAGS = $(FUZZ_SANITIZERS) -I ../../ -I ../../vendor -DSQLITE_CORE -DSQLITE_VEC_ENABLE_DISKANN=1 -g $(FUZZ_LDFLAGS)
FUZZ_SRCS = ../../vendor/sqlite3.c ../../sqlite-vec.c
TARGET_DIR = ./targets
@ -115,6 +115,34 @@ $(TARGET_DIR)/ivf_cell_overflow: ivf-cell-overflow.c $(FUZZ_SRCS) | $(TARGET_DIR
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
$(TARGET_DIR)/ivf_rescore: ivf-rescore.c $(FUZZ_SRCS) | $(TARGET_DIR)
$(TARGET_DIR)/diskann_operations: diskann-operations.c $(FUZZ_SRCS) | $(TARGET_DIR)
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
$(TARGET_DIR)/diskann_create: diskann-create.c $(FUZZ_SRCS) | $(TARGET_DIR)
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
$(TARGET_DIR)/diskann_graph_corrupt: diskann-graph-corrupt.c $(FUZZ_SRCS) | $(TARGET_DIR)
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
$(TARGET_DIR)/diskann_deep_search: diskann-deep-search.c $(FUZZ_SRCS) | $(TARGET_DIR)
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
$(TARGET_DIR)/diskann_blob_truncate: diskann-blob-truncate.c $(FUZZ_SRCS) | $(TARGET_DIR)
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
$(TARGET_DIR)/diskann_delete_stress: diskann-delete-stress.c $(FUZZ_SRCS) | $(TARGET_DIR)
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
$(TARGET_DIR)/diskann_buffer_flush: diskann-buffer-flush.c $(FUZZ_SRCS) | $(TARGET_DIR)
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
$(TARGET_DIR)/diskann_int8_quant: diskann-int8-quant.c $(FUZZ_SRCS) | $(TARGET_DIR)
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
$(TARGET_DIR)/diskann_prune_direct: diskann-prune-direct.c $(FUZZ_SRCS) | $(TARGET_DIR)
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
$(TARGET_DIR)/diskann_command_inject: diskann-command-inject.c $(FUZZ_SRCS) | $(TARGET_DIR)
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
FUZZ_TARGETS = vec0_create exec json numpy \
@ -127,6 +155,11 @@ FUZZ_TARGETS = vec0_create exec json numpy \
ivf_create ivf_operations \
ivf_quantize ivf_kmeans ivf_shadow_corrupt \
ivf_knn_deep ivf_cell_overflow ivf_rescore
diskann_operations diskann_create diskann_graph_corrupt \
diskann_deep_search diskann_blob_truncate \
diskann_delete_stress diskann_buffer_flush \
diskann_int8_quant diskann_prune_direct \
diskann_command_inject
all: $(addprefix $(TARGET_DIR)/,$(FUZZ_TARGETS))