chore: update lance dependency to v2.0.0-rc.1 (#2936)

## Summary
- bump Lance dependencies to v2.0.0-rc.1 (git tag)
- align Arrow/DataFusion/PyO3 versions for the new Lance release
- update Python bindings for PyO3 0.26 (attach API + Py<PyAny>)

## Verification
- `cargo clippy --workspace --tests --all-features -- -D warnings`
- `cargo fmt --all`

## Reference
- https://github.com/lance-format/lance/releases/tag/v2.0.0-rc.1

---------

Co-authored-by: Jack Ye <yezhaoqin@gmail.com>
Co-authored-by: Will Jones <willjones127@gmail.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: BubbleCal <bubble_cal@outlook.com>
This commit is contained in:
LanceDB Robot
2026-01-23 05:14:38 +08:00
committed by GitHub
parent ac07f8068c
commit bd84bba14d
18 changed files with 460 additions and 576 deletions

View File

@@ -961,22 +961,27 @@ class LanceQueryBuilder(ABC):
>>> query = [100, 100]
>>> plan = table.search(query).analyze_plan()
>>> print(plan) # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
AnalyzeExec verbose=true, metrics=[], cumulative_cpu=...
TracedExec, metrics=[], cumulative_cpu=...
ProjectionExec: expr=[...], metrics=[...], cumulative_cpu=...
GlobalLimitExec: skip=0, fetch=10, metrics=[...], cumulative_cpu=...
FilterExec: _distance@2 IS NOT NULL,
metrics=[output_rows=..., elapsed_compute=...], cumulative_cpu=...
SortExec: TopK(fetch=10), expr=[...],
AnalyzeExec verbose=true, elapsed=..., metrics=...
TracedExec, elapsed=..., metrics=...
ProjectionExec: elapsed=..., expr=[...],
metrics=[output_rows=..., elapsed_compute=..., output_bytes=...]
GlobalLimitExec: elapsed=..., skip=0, fetch=10,
metrics=[output_rows=..., elapsed_compute=..., output_bytes=...]
FilterExec: elapsed=..., _distance@2 IS NOT NULL, metrics=[...]
SortExec: elapsed=..., TopK(fetch=10), expr=[...],
preserve_partitioning=[...],
metrics=[output_rows=..., elapsed_compute=..., row_replacements=...],
cumulative_cpu=...
KNNVectorDistance: metric=l2,
metrics=[output_rows=..., elapsed_compute=..., output_batches=...],
cumulative_cpu=...
LanceRead: uri=..., projection=[vector], ...
metrics=[output_rows=..., elapsed_compute=...,
bytes_read=..., iops=..., requests=...], cumulative_cpu=...
metrics=[output_rows=..., elapsed_compute=...,
output_bytes=..., row_replacements=...]
KNNVectorDistance: elapsed=..., metric=l2,
metrics=[output_rows=..., elapsed_compute=...,
output_bytes=..., output_batches=...]
LanceRead: elapsed=..., uri=..., projection=[vector],
num_fragments=..., range_before=None, range_after=None,
row_id=true, row_addr=false,
full_filter=--, refine_filter=--,
metrics=[output_rows=..., elapsed_compute=..., output_bytes=...,
fragments_scanned=..., ranges_scanned=1, rows_scanned=1,
bytes_read=..., iops=..., requests=..., task_wait_time=...]
Returns
-------

View File

@@ -601,7 +601,6 @@ def test_head():
def test_query_sync_minimal():
def handler(body):
assert body == {
"distance_type": "l2",
"k": 10,
"prefilter": True,
"refine_factor": None,
@@ -685,7 +684,6 @@ def test_query_sync_maximal():
def test_query_sync_nprobes():
def handler(body):
assert body == {
"distance_type": "l2",
"k": 10,
"prefilter": True,
"fast_search": True,
@@ -715,7 +713,6 @@ def test_query_sync_nprobes():
def test_query_sync_no_max_nprobes():
def handler(body):
assert body == {
"distance_type": "l2",
"k": 10,
"prefilter": True,
"fast_search": True,
@@ -838,7 +835,6 @@ def test_query_sync_hybrid():
else:
# Vector query
assert body == {
"distance_type": "l2",
"k": 42,
"prefilter": True,
"refine_factor": None,

View File

@@ -1880,8 +1880,13 @@ async def test_optimize_delete_unverified(tmp_db_async: AsyncConnection, tmp_pat
],
)
version = await table.version()
path = tmp_path / "test.lance" / "_versions" / f"{version - 1}.manifest"
assert version == 2
# By removing a manifest file, we make the data files we just inserted unverified
version_name = 18446744073709551615 - (version - 1)
path = tmp_path / "test.lance" / "_versions" / f"{version_name:020}.manifest"
os.remove(path)
stats = await table.optimize(delete_unverified=False)
assert stats.prune.old_versions_removed == 0
stats = await table.optimize(