When a nullable scalar field has no inverted index, the forward filter path
fails to handle null values from Arrow's filter evaluation:
1. get_forward_bit(): BooleanArray::operator[] returns nullopt for null entries,
which is_filtered() treats as "no filter" (not filtered), letting null docs
through. Fix: use value_or(false) to treat null as "not matched".
2. is_matched_by_forward_filter(): reads BooleanScalar.value without checking
is_valid, which is UB for null scalars. Fix: check is_valid first.
Closes#409
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
- Set unique WORKING_DIRECTORY per test binary via cc_test()/cuda_test() to prevent filesystem path conflicts when running tests in parallel. Each test runs in ${CMAKE_BINARY_DIR}/test_tmp/${test_name}/.
- Enable parallel ctest execution in the unittest target with ProcessorCount-based --parallel flag (defaults to NPROC - 1).
- Set TEST_BINARY_DIR environment variable for crash recovery tests so they can locate helper binaries from isolated working directories.
- Update LocateDataGenerator() and LocateOptimizeGenerator() to search TEST_BINARY_DIR and TEST_BINARY_DIR/bin for helper executables.
Rewrite file/path handling to use std::filesystem and UTF-8-safe helpers.
Switch Windows file open/create paths to wide-char APIs, replace manual
separator concatenation with PathJoin, and enable RocksDB UTF-8 filenames.
Also add UTF-8 path coverage for file IO, version manager recovery, and
collection open/flush/reopen flows.
fixes#328
Problem:
SQ8 metadata (squared_sum, sum) was computed from pre-rounded float
values, causing mismatch with actual stored int8 values. On asymmetric
datasets (e.g. OpenAI 1536D where |x_min| >> x_max), this leads to
severe recall drop.
Solution:
Move std::round before accumulating squared_sum and sum.
Co-authored-by: rayx <rui.xing@alibaba-inc.com>
* support ios build
* fix: ci
* fix: update build_ios.sh
* fix: pr
* fix: cmake minimum version
* fix: cmake minimum version
* fix: cmake minimum version in ci
* fix: add all test in ci
* fix: ci
* init branch
Add GitHub Actions release workflow for C API
add release linux-arm64
remove c api version
refact some code
add api reference
* feat(c-api): add nullable/doc-result APIs for agency migration (#234)
* Flattened index parameters structure
* refact c api code
* remove RAII guard
* refact use opaque pointer pattern
* refact version info
* refact use pure opaque pointers
* use typedef instead of enum
* fix set_last_error
* fix build yml
* fix doc.h
* remove wheel exclude
* fix c msvc link
* remove release yml
* fix c link libstdc++
* fix c link libgcc
---------
Co-authored-by: Donny/강동윤 <kdy.1997.dev@gmail.com>
* feat: add Python 3.13 and 3.14 support
- Add Python 3.13 and 3.14 classifiers to pyproject.toml
- Add cp313 and cp314 cibuildwheel build targets
- Add Python 3.13 and 3.14 to CI test matrix
- Enable allow-prereleases for setup-python (required for 3.14 alpha)
Signed-off-by: Maxime Grenu <maxime.grenu@gmail.com>
* ci: retrigger (flaky Int4SquaredEuclideanMetric tolerance on linux-x64)
Signed-off-by: Maxime Grenu <maxime.grenu@gmail.com>
* fix: widen Int4 distance matrix test tolerance from 1e-4 to 5e-4
Int4 quantization uses only 16 levels per dimension (vs 256 for Int8),
resulting in larger rounding errors in distance computations. The
previous 1e-4 absolute tolerance was too tight and caused flaky
failures (observed diff: 1.22e-4 on values ~523.77). The Int8 test
already has this EXPECT_NEAR commented out, relying solely on the
relative IsAlmostEqual check.
Signed-off-by: Maxime Grenu <maxime.grenu@gmail.com>
* fix: remove allow-prereleases flag for Python 3.14
Python 3.14 is now a stable release (v3.14.3, released Oct 2025),
so allow-prereleases: true is no longer needed in setup-python.
Signed-off-by: Maxime Kawawa-Beaudan <maxkb@meta.com>
Signed-off-by: Maxime Grenu <maxime.grenu@gmail.com>
---------
Signed-off-by: Maxime Grenu <maxime.grenu@gmail.com>
Signed-off-by: Maxime Kawawa-Beaudan <maxkb@meta.com>