vmulq_s16(diff, diff) produced int16 results, but diff can be up to
255 for int8 vectors (-128 vs 127), and 255^2 = 65025 overflows
int16 (max 32767). This caused NaN/wrong results for int8 vectors
with large differences.
Fix: use vmull_s16 (widening multiply) to produce int32 results
directly, avoiding the intermediate int16 overflow.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The binary quantizer uses D/8 for buffer sizes and memset, which
truncates for non-multiple-of-8 dimensions, causing OOB writes.
Rather than using ceiling division, enforce the constraint at
table creation time with a clear parse error.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
sqlite3_column_blob() returns NULL for zero-length blobs or on OOM.
Several call sites in rescore KNN and DiskANN node/vector read passed
the result directly to memcpy without checking, risking NULL deref on
corrupt or empty databases. IVF already had proper NULL checks.
Adds corruption regression tests that truncate shadow table blobs and
verify the query errors cleanly instead of crashing.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
vec0Update_UpdateVectorColumn writes to flat chunk blobs but does not
update DiskANN graph or IVF index structures, silently corrupting KNN
results. Now returns a clear error for these index types. Rescore
UPDATE is unaffected — it already has a full implementation that
updates both quantized chunks and float vectors.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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.
Rename SQLITE_VEC_ENABLE_IVF to SQLITE_VEC_EXPERIMENTAL_IVF_ENABLE and
flip the default from 1 to 0. IVF tests are automatically skipped when
the build flag is not set.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add inverted file (IVF) index type: partitions vectors into clusters via
k-means, quantizes to int8, and scans only the nearest nprobe partitions at
query time. Includes shadow table management, insert/delete, KNN integration,
compile flag (SQLITE_VEC_ENABLE_IVF), fuzz targets, and tests. Removes
superseded ivf-benchmarks/ directory.
Add approximate nearest neighbor infrastructure to vec0: shared distance
dispatch (vec0_distance_full), flat index type with parser, NEON-optimized
cosine/Hamming for float32/int8, amalgamation script, and benchmark suite
(benchmarks-ann/) with ground-truth generation and profiling tools. Remove
unused vec_npy_each/vec_static_blobs code, fix missing stdint.h include.
vec0Update_Delete_ClearMetadata's long-text branch runs a DELETE via
sqlite3_step, which returns SQLITE_DONE (101) on success. The code
checked for failure but never normalized the success case to SQLITE_OK.
The function's epilogue returned SQLITE_DONE as-is, which the caller
(vec0Update_Delete) treated as an error, aborting the DELETE scan and
silently leaving rows behind.
- Normalize rc to SQLITE_OK after successful sqlite3_step in ClearMetadata
- Move sqlite3_finalize before the rc check (cleanup on all paths)
- Add test_delete_by_metadata_with_long_text regression test
- Update test_deletes snapshot (row 3 now correctly deleted)
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add rescore index type: stores full-precision float vectors in a rowid-keyed
shadow table, quantizes to int8 for fast initial scan, then rescores top
candidates with original vectors. Includes config parser, shadow table
management, insert/delete support, KNN integration, compile flag
(SQLITE_VEC_ENABLE_RESCORE), fuzz targets, and tests.
Add approximate nearest neighbor infrastructure to vec0: shared distance
dispatch (vec0_distance_full), flat index type with parser, NEON-optimized
cosine/Hamming for float32/int8, amalgamation script, and benchmark suite
(benchmarks-ann/) with ground-truth generation and profiling tools. Remove
unused vec_npy_each/vec_static_blobs code, fix missing stdint.h include.
When a row is deleted from a vec0 virtual table, the rowid slot in
_chunks.rowids and vector data in _vector_chunksNN.vectors are now
zeroed out (previously left as stale data, tracked in #54). When all
rows in a chunk are deleted (validity bitmap all zeros), the chunk and
its associated vector/metadata shadow table rows are reclaimed.
- Add vec0Update_Delete_ClearRowid to zero the rowid blob slot
- Add vec0Update_Delete_ClearVectors to zero all vector blob slots
- Add vec0Update_Delete_DeleteChunkIfEmpty to detect and delete
fully-empty chunks from _chunks, _vector_chunksNN, _metadatachunksNN
- Fix missing rc check in ClearMetadata loop (bug: errors were silently
ignored)
- Fix vec0_new_chunk to explicitly set _rowid_ on shadow table INSERTs
(SHADOW_TABLE_ROWID_QUIRK: "rowid PRIMARY KEY" without INTEGER type
is not a true rowid alias, causing blob_open failures after chunk
delete+recreate cycles)
- Add 13 new tests covering rowid/vector zeroing, chunk reclamation,
metadata/auxiliary/partition/text-PK/int8/bit variants, and
page_count shrinkage verification
- Add vec0-delete-completeness fuzz target
- Update snapshots for new delete zeroing behavior
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Document three classes of undefined behavior found by UBSAN:
function pointer type mismatches, misaligned f32 reads, and
float-to-integer overflow in vec_quantize_int8.
Improve vec-mismatch fuzzer to cover all error-path cleanup patterns:
type mismatches, dimension mismatches, single-arg functions, and
both text and blob inputs.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Targeted fuzzer for two-argument vector functions (vec_distance_*,
vec_add, vec_sub) that binds a valid JSON vector as arg1 and fuzz
data as arg2. This exercises the error path in ensure_vector_match()
where the first vector parses successfully (with sqlite3_free cleanup)
but the second fails, triggering the buggy aCleanup(a) call on line
1031 of sqlite-vec.c (should be aCleanup(*a)).
The fuzzer catches this immediately — ASAN reports "bad-free" when
sqlite3_free is called on a stack address.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Deduplicates exec(), vec0_shadow_table_contents(), _f32(), _i64(), and
_int8() helpers that were copied across six test files.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Baseline tests protecting non-DiskANN chunk-based insert and delete
behavior: vector round-trips, auto rowids, text primary keys, delete
validity, reinsert after delete, dimension/type validation, and v_info
snapshot.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Extends the vec0 tokenizer to recognize '(', ')', and ',' as
single-character tokens, preparing for DiskANN index option parsing.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add test-only wrappers behind SQLITE_VEC_TEST compile flag to expose
static distance functions for unit testing. Includes tests for
distance_l2_sqr_float (4 cases), distance_cosine_float (3 cases),
and distance_hamming (4 cases). Print active SIMD flags at test start.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add SQLITE_EMPTY tests for non-vector column inputs (primary key,
partition key, unknown types) and SQLITE_ERROR tests for zero
dimensions and empty brackets. Tighten existing error assertions
from rc != SQLITE_OK to exact expected return codes.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Expand sqlite-vec-internal.h with scanner/tokenizer types, vector column
definition types, and parser function declarations
- Fix min_idx declaration to match actual C signature (add candidates,
bTaken, k_used params)
- Compile test-unit with -DSQLITE_CORE and link vendor/sqlite3.c so
sqlite3 API functions (sqlite3_strnicmp, sqlite3_mprintf, etc.) resolve
- Add unit tests for vec0_token_next, Vec0Scanner, and
vec0_parse_vector_column
- Fix Rust build.rs to define SQLITE_CORE and compile vendor/sqlite3.c
- Fix Rust min_idx FFI signature and wrapper to match actual C function
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* initial pass at PARTITION KEY support.
* Initial pass, allow auxiliary columns on vec0 virtual tables
* update TODO
* Initial pass at metadata filtering
* unit tests
* gha this PR branch
* fixup tests
* doc internal
* fix tests, KNN/rowids in
* define SQLITE_INDEX_CONSTRAINT_OFFSET
* whoops
* update tests, syrupy, use uv
* un ignore pyproject.toml
* dot
* tests/
* type error?
* win: .exe, update error name
* try fix macos python, paren around expr?
* win bash?
* dbg :(
* explicit error
* op
* dbg win
* win ./tests/.venv/Scripts/python.exe
* block UPDATEs on partition key values for now
* test this branch
* accidentally removved "partition key type mistmatch" block during merge
* typo ugh
* bruv
* start aux snapshots
* drop aux shadow table on destroy
* enforce column types
* block WHERE constraints on auxiliary columns in KNN queries
* support delete
* support UPDATE on auxiliary columns
* test this PR
* dont inline that
* test-metadata.py
* memzero text buffer
* stress test
* more snpashot tests
* rm double/int32, just float/int64
* finish type checking
* long text support
* DELETE support
* UPDATE support
* fix snapshot names
* drop not-used in eqp
* small fixes
* boolean comparison handling
* ensure error is raised when long string constraint
* new version string for beta builds
* typo whoops
* ann-filtering-benchmark directory
* test-case
* updates
* fix aux column error when using non-default rowid values, needs test
* refactor some text knn filtering
* rowids blob read only on text metadata filters
* refactor
* add failing test causes for non eq text knn
* text knn NE
* test cases diff
* GT
* text knn GT/GE fixes
* text knn LT/LE
* clean
* vtab_in handling
* unblock aux failures for now
* guard sqlite3_vtab_in
* else in guard?
* fixes and tests
* add broken shadow table test
* rename _metadata_chunksNN shadown table to _metadatachunksNN, for proper shadowName detection
* _metadata_text_NN shadow tables to _metadatatextNN
* SQLITE_VEC_VERSION_MAJOR SQLITE_VEC_VERSION_MINOR and SQLITE_VEC_VERSION_PATCH in sqlite-vec.h
* _info shadow table
* forgot to update aux snapshot?
* fix aux tests
* initial work on l1
* l1 int8 neon implementation
* tweak l1 int8 and add test
* broken overflow still
* some progress on l1
* change to i32 instead of i64
* remove comment
* ignore poetry stuff
* unrolled l1 int8 and format
* remove comments
