feat: upgrade Lance to v0.37.0 (#2672)

Change logs:

* https://github.com/lancedb/lance/releases/tag/v0.37.0
* https://github.com/lancedb/lance/releases/tag/v0.36.0
This commit is contained in:
Will Jones
2025-09-23 13:41:47 -07:00
committed by GitHub
parent e921c90c1b
commit 1ab60fae7f
7 changed files with 109 additions and 60 deletions

View File

@@ -1470,10 +1470,7 @@ class Table(ABC):
be deleted unless they are at least 7 days old. If delete_unverified is True
then these files will be deleted regardless of their age.
retrain: bool, default False
If True, retrain the vector indices, this would refine the IVF clustering
and quantization, which may improve the search accuracy. It's faster than
re-creating the index from scratch, so it's recommended to try this first,
when the data distribution has changed significantly.
This parameter is no longer used and is deprecated.
Experimental API
----------------
@@ -2835,10 +2832,7 @@ class LanceTable(Table):
be deleted unless they are at least 7 days old. If delete_unverified is True
then these files will be deleted regardless of their age.
retrain: bool, default False
If True, retrain the vector indices, this would refine the IVF clustering
and quantization, which may improve the search accuracy. It's faster than
re-creating the index from scratch, so it's recommended to try this first,
when the data distribution has changed significantly.
This parameter is no longer used and is deprecated.
Experimental API
----------------
@@ -4298,10 +4292,7 @@ class AsyncTable:
be deleted unless they are at least 7 days old. If delete_unverified is True
then these files will be deleted regardless of their age.
retrain: bool, default False
If True, retrain the vector indices, this would refine the IVF clustering
and quantization, which may improve the search accuracy. It's faster than
re-creating the index from scratch, so it's recommended to try this first,
when the data distribution has changed significantly.
This parameter is no longer used and is deprecated.
Experimental API
----------------
@@ -4324,10 +4315,19 @@ class AsyncTable:
cleanup_since_ms: Optional[int] = None
if cleanup_older_than is not None:
cleanup_since_ms = round(cleanup_older_than.total_seconds() * 1000)
if retrain:
import warnings
warnings.warn(
"The 'retrain' parameter is deprecated and will be removed in a "
"future version.",
DeprecationWarning,
)
return await self._inner.optimize(
cleanup_since_ms=cleanup_since_ms,
delete_unverified=delete_unverified,
retrain=retrain,
)
async def list_indices(self) -> Iterable[IndexConfig]:

View File

@@ -591,12 +591,11 @@ impl Table {
}
/// Optimize the on-disk data by compacting and pruning old data, for better performance.
#[pyo3(signature = (cleanup_since_ms=None, delete_unverified=None, retrain=None))]
#[pyo3(signature = (cleanup_since_ms=None, delete_unverified=None))]
pub fn optimize(
self_: PyRef<'_, Self>,
cleanup_since_ms: Option<u64>,
delete_unverified: Option<bool>,
retrain: Option<bool>,
) -> PyResult<Bound<'_, PyAny>> {
let inner = self_.inner_ref()?.clone();
let older_than = if let Some(ms) = cleanup_since_ms {
@@ -632,10 +631,9 @@ impl Table {
.prune
.unwrap();
inner
.optimize(lancedb::table::OptimizeAction::Index(match retrain {
Some(true) => OptimizeOptions::retrain(),
_ => OptimizeOptions::default(),
}))
.optimize(lancedb::table::OptimizeAction::Index(
OptimizeOptions::default(),
))
.await
.infer_error()?;
Ok(OptimizeStats {