chore: update lance dependency to v10.1.0-beta.2

Cargo.toml

@@ -13,20 +13,20 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"
 
 [workspace.dependencies]
-lance = { "version" = "=10.1.0-beta.1", default-features = false, "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=10.1.0-beta.1", default-features = false, "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=10.1.0-beta.1", default-features = false, "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=10.1.0-beta.2", default-features = false, "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=10.1.0-beta.2", default-features = false, "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=10.1.0-beta.2", default-features = false, "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=10.1.0-beta.2", "tag" = "v10.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
 ahash = "0.8"
 # Note that this one does not include pyarrow
 arrow = { version = "58.0.0", optional = false }

docs/src/python/python.md

@@ -180,21 +180,6 @@ instead of being materialized with the rest of the row.
 
 ::: lancedb.otel.instrument_lancedb_metrics
 
-## Legacy V2 migration
-
-Tables created with the experimental V2 format in LanceDB Node 0.5.x can be
-rewritten with the legacy PyLance reader. In a dedicated environment, install
-LanceDB normally, then install the legacy reader without its obsolete PyArrow
-upper bound and run the migration:
-
-```shell
-pip install lancedb
-pip install --no-deps pylance==0.12.1
-python -m lancedb.legacy_v2 <database-uri>
-```
-
-::: lancedb.legacy_v2.migrate_legacy_v2_tables
-
 ## Exceptions
 
 ::: lancedb.exceptions.MissingValueError

java/pom.xml

@@ -28,7 +28,7 @@
     <properties>
         <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
         <arrow.version>15.0.0</arrow.version>
-        <lance-core.version>10.1.0-beta.1</lance-core.version>
+        <lance-core.version>10.1.0-beta.2</lance-core.version>
         <spotless.skip>false</spotless.skip>
         <spotless.version>2.30.0</spotless.version>
         <spotless.java.googlejavaformat.version>1.7</spotless.java.googlejavaformat.version>

nodejs/src/table.rs

@@ -339,9 +339,7 @@ impl Table {
         let transforms = NewColumnTransform::SqlExpressions(transforms);
         let res = self
             .inner_ref()?
-            .add_columns()
-            .transform(transforms)
-            .execute()
+            .add_columns(transforms, None)
             .await
             .default_error()?;
         Ok(res.into())
@@ -358,9 +356,7 @@ impl Table {
         let transforms = NewColumnTransform::AllNulls(schema);
         let res = self
             .inner_ref()?
-            .add_columns()
-            .transform(transforms)
-            .execute()
+            .add_columns(transforms, None)
             .await
             .default_error()?;
         Ok(res.into())

python/python/lancedb/db.py

@@ -707,9 +707,6 @@ class LanceDBConnection(DBConnection):
         self._namespace_client_properties = namespace_client_properties
         if _inner is not None:
             self._conn = _inner
-            # Native-derived wrappers resolve this in their async reconstruction
-            # path so construction never synchronously re-enters LOOP.
-            self._read_consistency_interval = read_consistency_interval
             self._cached_namespace_client = None
             return
 
@@ -759,14 +756,11 @@ class LanceDBConnection(DBConnection):
         # storage_options.  Also, this class really shouldn't be holding any state
         # beyond _conn.
         self._conn = AsyncConnection(LOOP.run(do_connect()))
-        # Keep property access synchronous so debugger introspection cannot wait on
-        # the background loop while that thread is suspended at a breakpoint.
-        self._read_consistency_interval = read_consistency_interval
         self._cached_namespace_client: Optional[LanceNamespace] = None
 
     @property
     def read_consistency_interval(self) -> Optional[timedelta]:
-        return self._read_consistency_interval
+        return LOOP.run(self._conn.get_read_consistency_interval())
 
     @property
     def session(self) -> Optional[Session]:
@@ -777,16 +771,8 @@ class LanceDBConnection(DBConnection):
         return self._conn.uri
 
     @classmethod
-    def from_inner(
-        cls,
-        inner: LanceDbConnection,
-        read_consistency_interval: Optional[timedelta],
-    ):
-        return cls(
-            None,
-            read_consistency_interval=read_consistency_interval,
-            _inner=inner,
-        )
+    def from_inner(cls, inner: LanceDbConnection):
+        return cls(None, _inner=inner)
 
     def __repr__(self) -> str:
         return f"{self.__class__.__name__}(uri={self._conn.uri!r})"

python/python/lancedb/legacy_v2.py

@@ -1,263 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-"""Recovery utilities for the experimental V2 format used by old Node releases."""
-
-from __future__ import annotations
-
-import argparse
-import asyncio
-import inspect
-import warnings
-from collections.abc import Iterable
-from typing import Any
-
-from packaging.version import Version
-
-import lancedb
-
-__all__ = ["migrate_legacy_v2_tables"]
-
-_LEGACY_LANCE_VERSION = Version("0.12.1")
-_LEGACY_V2_ERROR_MARKERS = (
-    "missing columnencoding encoding description",
-    "missing lance.encodings.columnencoding encoding description",
-    "was missing a columnencoding",
-    "rust future panicked",
-    "panic in async function",
-)
-
-
-def _require_legacy_lance() -> Any:
-    try:
-        import lance
-    except ImportError as error:
-        raise RuntimeError(
-            "Legacy V2 migration requires pylance==0.12.1. Install it in a "
-            "dedicated environment with "
-            "`pip install --no-deps pylance==0.12.1`."
-        ) from error
-
-    version = Version(lance.__version__)
-    if version != _LEGACY_LANCE_VERSION:
-        raise RuntimeError(
-            "Legacy V2 migration requires pylance==0.12.1, but found "
-            f"pylance=={version}. Reinstall it with "
-            "`pip install --no-deps --force-reinstall pylance==0.12.1`."
-        )
-    return lance
-
-
-def _exception_messages(error: BaseException) -> Iterable[str]:
-    seen: set[int] = set()
-    current: BaseException | None = error
-    while current is not None and id(current) not in seen:
-        seen.add(id(current))
-        yield str(current).lower()
-        current = current.__cause__ or current.__context__
-
-
-def _is_legacy_v2_error(error: BaseException) -> bool:
-    return any(
-        marker in message
-        for message in _exception_messages(error)
-        for marker in _LEGACY_V2_ERROR_MARKERS
-    )
-
-
-def _list_table_names(db: Any) -> list[str]:
-    list_tables = getattr(db, "list_tables", None)
-    if list_tables is not None:
-        # The deprecated table_names() API defaults to only ten results.
-        return list(list_tables(limit=None).tables)
-
-    # Compatibility for LanceDB 0.16, which was used by the original script.
-    with warnings.catch_warnings():
-        warnings.simplefilter("ignore", DeprecationWarning)
-        return list(db.table_names())
-
-
-async def _needs_migration(db: Any, table_name: str) -> bool:
-    table = await db.open_table(table_name)
-    try:
-        # One row is enough to load and validate the data-file metadata.
-        await table.query().limit(1).to_arrow()
-    except (KeyboardInterrupt, SystemExit, GeneratorExit):
-        raise
-    except BaseException as error:
-        if _is_legacy_v2_error(error):
-            return True
-        raise
-    return False
-
-
-async def _create_migrated_table(
-    db: Any, table_name: str, reader: Any, storage_format: str
-) -> Any:
-    parameters = inspect.signature(db.create_table).parameters
-    options: dict[str, Any] = {"mode": "overwrite"}
-    if "data_storage_version" in parameters:
-        # LanceDB 0.16 exposed the format as a direct create_table option.
-        options["data_storage_version"] = storage_format
-    else:
-        options["storage_options"] = {"new_table_data_storage_version": storage_format}
-    return await db.create_table(table_name, reader, **options)
-
-
-async def _migrate_table(
-    source_db: Any,
-    destination_db: Any,
-    table_name: str,
-    storage_format: str,
-) -> int:
-    source_table = source_db.open_table(table_name)
-    source_dataset = source_table.to_lance()
-    source_rows = source_dataset.count_rows()
-    reader = source_dataset.scanner().to_reader()
-
-    migrated_table = await _create_migrated_table(
-        destination_db, table_name, reader, storage_format
-    )
-    migrated_rows = await migrated_table.count_rows()
-    if migrated_rows != source_rows:
-        raise RuntimeError(
-            f"Migration of table {table_name!r} wrote {migrated_rows} rows; "
-            f"expected {source_rows}."
-        )
-
-    # Force the current reader to load data-file metadata before reporting success.
-    await migrated_table.query().limit(1).to_arrow()
-    return migrated_rows
-
-
-async def migrate_legacy_v2_tables(
-    uri: str,
-    *,
-    table_name: str | None = None,
-    destination_uri: str | None = None,
-    storage_format: str = "2.0",
-    show_progress: bool = True,
-) -> list[str]:
-    """Migrate tables written with the incompatible experimental V2 format.
-
-    LanceDB Node 0.5.x could enable an experimental data format when an empty
-    table was created and data was added later. Those files panic older modern
-    readers and are rejected by newer readers. This utility streams them through
-    ``pylance==0.12.1`` and rewrites them in a supported format.
-
-    Install the legacy reader in a dedicated environment before running this
-    function::
-
-        pip install lancedb
-        pip install --no-deps pylance==0.12.1
-
-    ``--no-deps`` is required because the legacy wheel declares an obsolete
-    PyArrow upper bound. The migration uses only its dataset scanner and writes
-    through the current LanceDB package.
-
-    This migration is available only for local/OSS databases, including object
-    storage URIs. It is not supported for LanceDB Cloud ``db://`` connections.
-    In-place migration creates a new table version, so old data remains available
-    for recovery until old versions are cleaned up. Table indices are not copied
-    and should be rebuilt after migration.
-
-    Parameters
-    ----------
-    uri : str
-        Source LanceDB database URI.
-    table_name : str, optional
-        Migrate only this table. By default, inspect every table.
-    destination_uri : str, optional
-        Write to another database. By default, migrate in place.
-    storage_format : str, default "2.0"
-        Data storage format for the rewritten tables. Use ``"0.1"`` for
-        compatibility with older LanceDB releases.
-    show_progress : bool, default True
-        Display progress bars while inspecting and migrating tables.
-
-    Returns
-    -------
-    list of str
-        Names of the migrated tables.
-    """
-    if uri.startswith("db://") or (
-        destination_uri is not None and destination_uri.startswith("db://")
-    ):
-        raise ValueError("Legacy V2 migration is supported only for local/OSS tables")
-
-    # Import and validate before opening or modifying any table.
-    _require_legacy_lance()
-
-    source_db = lancedb.connect(uri)
-    async_source_db = await lancedb.connect_async(uri)
-    destination_db = (
-        async_source_db
-        if destination_uri is None or destination_uri == uri
-        else await lancedb.connect_async(destination_uri)
-    )
-
-    if table_name is not None:
-        table_names = [table_name]
-    else:
-        table_names = _list_table_names(source_db)
-
-    inspection: Iterable[str] = table_names
-    if show_progress:
-        from tqdm.auto import tqdm
-
-        inspection = tqdm(table_names, desc="Checking tables")
-
-    tables_to_migrate = [
-        name for name in inspection if await _needs_migration(async_source_db, name)
-    ]
-
-    migration: Iterable[str] = tables_to_migrate
-    if show_progress:
-        from tqdm.auto import tqdm
-
-        migration = tqdm(tables_to_migrate, desc="Migrating tables")
-
-    migrated = []
-    for name in migration:
-        await _migrate_table(source_db, destination_db, name, storage_format)
-        migrated.append(name)
-    return migrated
-
-
-def _parser() -> argparse.ArgumentParser:
-    parser = argparse.ArgumentParser(
-        description="Migrate tables written with the old experimental V2 format."
-    )
-    parser.add_argument("uri", help="source LanceDB database URI")
-    parser.add_argument("--table-name", help="migrate only this table")
-    parser.add_argument("--destination-uri", help="write to another database URI")
-    parser.add_argument(
-        "--storage-format",
-        default="2.0",
-        help='destination data format (default: "2.0"; use "0.1" for compatibility)',
-    )
-    parser.add_argument(
-        "--no-progress", action="store_true", help="disable progress bars"
-    )
-    return parser
-
-
-def main() -> None:
-    args = _parser().parse_args()
-    migrated = asyncio.run(
-        migrate_legacy_v2_tables(
-            args.uri,
-            table_name=args.table_name,
-            destination_uri=args.destination_uri,
-            storage_format=args.storage_format,
-            show_progress=not args.no_progress,
-        )
-    )
-    if migrated:
-        print(f"Migrated {len(migrated)} table(s): {', '.join(migrated)}")
-    else:
-        print("No legacy V2 tables found")
-
-
-if __name__ == "__main__":
-    main()

python/python/lancedb/merge.py

@@ -92,10 +92,8 @@ class LanceMergeInsertBuilder(object):
         self._when_not_matched_by_source_delete = True
         if isinstance(condition, Expr):
             self._when_not_matched_by_source_condition_expr = condition._inner
-            self._when_not_matched_by_source_condition = None
-        else:
+        elif condition is not None:
             self._when_not_matched_by_source_condition = condition
-            self._when_not_matched_by_source_condition_expr = None
         return self
 
     def use_index(self, use_index: bool) -> LanceMergeInsertBuilder:

python/python/lancedb/permutation.py

@@ -226,7 +226,7 @@ class PermutationBuilder:
 
         async def do_execute():
             inner_tbl = await self._async.execute()
-            return await LanceTable.from_inner(inner_tbl)
+            return LanceTable.from_inner(inner_tbl)
 
         return LOOP.run(do_execute())
 

python/python/lancedb/query.py

@@ -2697,7 +2697,7 @@ class LanceHybridQueryBuilder(LanceQueryBuilder):
             self._fts_query.phrase_query(True)
         if self._distance_type:
             self._vector_query.metric(self._distance_type)
-        if self._minimum_nprobes is not None:
+        if self._minimum_nprobes:
             self._vector_query.minimum_nprobes(self._minimum_nprobes)
         if self._maximum_nprobes is not None:
             self._vector_query.maximum_nprobes(self._maximum_nprobes)

python/python/lancedb/table.py

@@ -1595,8 +1595,8 @@ class Table(ABC):
         Prefer this over :meth:`fetch_blobs` for large payloads. ``row_ids`` is
         a ``list[int]`` or a query ``pyarrow.Table`` carrying row identity via
         ``_rowid`` or a ``_lance_row_id`` field on the blob descriptor. Null
-        rows are ``None``. Remote tables require LanceDB Cloud server 0.5.0 or
-        newer.
+        rows are ``None``. Unsupported on LanceDB Cloud, where
+        :meth:`fetch_blobs` returns full bytes instead.
         """
 
     @abstractmethod
@@ -2182,15 +2182,11 @@ class LanceTable(Table):
         return self.name
 
     @classmethod
-    async def from_inner(cls, tbl: LanceDBTable):
-        from .db import AsyncConnection, LanceDBConnection
+    def from_inner(cls, tbl: LanceDBTable):
+        from .db import LanceDBConnection
 
         async_tbl = AsyncTable(tbl)
-        inner_conn = tbl.database()
-        read_consistency_interval = await AsyncConnection(
-            inner_conn
-        ).get_read_consistency_interval()
-        conn = LanceDBConnection.from_inner(inner_conn, read_consistency_interval)
+        conn = LanceDBConnection.from_inner(tbl.database())
         return cls(
             conn,
             async_tbl.name,

python/python/tests/test_db.py

@@ -77,23 +77,6 @@ def test_sync_repr_does_not_use_background_loop(tmp_path, monkeypatch):
     assert repr(table) == f"LanceTable(name='test', _conn={db!r})"
 
 
-def test_read_consistency_interval_does_not_use_background_loop(tmp_path, monkeypatch):
-    from lancedb.background_loop import LOOP
-    from lancedb.db import LanceDBConnection
-
-    consistency_interval = timedelta(seconds=5)
-    db = lancedb.connect(tmp_path, read_consistency_interval=consistency_interval)
-    db_from_inner = LanceDBConnection.from_inner(db._inner, consistency_interval)
-
-    def fail_run(*args, **kwargs):
-        raise AssertionError("properties should not use the Python background loop")
-
-    monkeypatch.setattr(LOOP, "run", fail_run)
-
-    assert db.read_consistency_interval == consistency_interval
-    assert db_from_inner.read_consistency_interval == consistency_interval
-
-
 def test_ingest_pd(tmp_path):
     db = lancedb.connect(tmp_path)
 

python/python/tests/test_hybrid_query.py

@@ -123,19 +123,6 @@ async def test_async_hybrid_query_default_limit(table: AsyncTable):
     assert texts.count("a") == 1
 
 
-def test_hybrid_query_minimum_nprobes_zero_raises(sync_table: Table):
-    # minimum_nprobes(0) must raise the same validation error a plain vector
-    # query raises, not silently no-op because 0 is falsy.
-    with pytest.raises(ValueError, match="minimum_nprobes must be greater than 0"):
-        (
-            sync_table.search(query_type="hybrid")
-            .vector([0.0, 0.4])
-            .text("dog")
-            .minimum_nprobes(0)
-            .to_arrow()
-        )
-
-
 def test_hybrid_query_distance_range(sync_table: Table):
     reranker = RRFReranker(return_score="all")
     result = (

python/python/tests/test_legacy_v2.py

@@ -1,165 +0,0 @@
-from unittest.mock import AsyncMock, Mock
-
-import pytest
-
-from lancedb import legacy_v2
-
-
-class FakeQuery:
-    def __init__(self, error=None):
-        self.error = error
-
-    def limit(self, _limit):
-        return self
-
-    async def to_arrow(self):
-        if self.error is not None:
-            raise self.error
-        return None
-
-
-class FakeAsyncTable:
-    def __init__(self, rows=2, error=None):
-        self.rows = rows
-        self.error = error
-
-    def query(self):
-        return FakeQuery(self.error)
-
-    async def count_rows(self):
-        return self.rows
-
-
-class FakeDataset:
-    def __init__(self, reader, rows=2):
-        self.reader = reader
-        self.rows = rows
-
-    def count_rows(self):
-        return self.rows
-
-    def scanner(self):
-        scanner = Mock()
-        scanner.to_reader.return_value = self.reader
-        return scanner
-
-
-@pytest.mark.asyncio
-@pytest.mark.parametrize(
-    "message",
-    [
-        "rust future panicked: unknown error",
-        "Panic in async function",
-        "Missing ColumnEncoding encoding description",
-        "Missing lance.encodings.ColumnEncoding encoding description",
-        "the column at index 0 was missing a ColumnEncoding",
-    ],
-)
-async def test_needs_migration_recognizes_legacy_reader_errors(message):
-    db = Mock()
-    db.open_table = AsyncMock(return_value=FakeAsyncTable(error=RuntimeError(message)))
-
-    assert await legacy_v2._needs_migration(db, "legacy")
-
-
-@pytest.mark.asyncio
-async def test_needs_migration_propagates_unrelated_errors():
-    db = Mock()
-    db.open_table = AsyncMock(
-        return_value=FakeAsyncTable(error=RuntimeError("permission denied"))
-    )
-
-    with pytest.raises(RuntimeError, match="permission denied"):
-        await legacy_v2._needs_migration(db, "legacy")
-
-
-@pytest.mark.asyncio
-async def test_migration_streams_and_verifies_rows(monkeypatch):
-    reader = object()
-    source_dataset = FakeDataset(reader)
-    source_table = Mock()
-    source_table.to_lance.return_value = source_dataset
-    source_db = Mock()
-    source_db.list_tables.return_value.tables = ["healthy", "legacy"]
-    source_db.open_table.return_value = source_table
-
-    legacy_error = RuntimeError(
-        "Missing lance.encodings.ColumnEncoding encoding description"
-    )
-    async_source_db = Mock()
-
-    async def open_table(name):
-        if name == "legacy":
-            return FakeAsyncTable(error=legacy_error)
-        return FakeAsyncTable()
-
-    async_source_db.open_table = open_table
-    create_calls = []
-
-    async def create_table(name, data, *, mode, storage_options):
-        create_calls.append((name, data, mode, storage_options))
-        return FakeAsyncTable()
-
-    async_source_db.create_table = create_table
-
-    monkeypatch.setattr(legacy_v2, "_require_legacy_lance", Mock())
-    monkeypatch.setattr(legacy_v2.lancedb, "connect", Mock(return_value=source_db))
-
-    async def connect_async(_uri):
-        return async_source_db
-
-    monkeypatch.setattr(legacy_v2.lancedb, "connect_async", connect_async)
-
-    migrated = await legacy_v2.migrate_legacy_v2_tables("/data/db", show_progress=False)
-
-    assert migrated == ["legacy"]
-    source_db.list_tables.assert_called_once_with(limit=None)
-    assert create_calls == [
-        (
-            "legacy",
-            reader,
-            "overwrite",
-            {"new_table_data_storage_version": "2.0"},
-        )
-    ]
-
-
-def test_list_table_names_supports_legacy_connection():
-    db = Mock(spec=["table_names"])
-    db.table_names.return_value = [f"table_{index}" for index in range(12)]
-
-    assert len(legacy_v2._list_table_names(db)) == 12
-
-
-@pytest.mark.asyncio
-async def test_create_table_uses_legacy_storage_parameter():
-    calls = []
-
-    class LegacyConnection:
-        async def create_table(self, name, data, *, mode, data_storage_version=None):
-            calls.append((name, data, mode, data_storage_version))
-            return FakeAsyncTable()
-
-    reader = object()
-    await legacy_v2._create_migrated_table(LegacyConnection(), "legacy", reader, "0.1")
-
-    assert calls == [("legacy", reader, "overwrite", "0.1")]
-
-
-def test_requires_exact_legacy_lance_version(monkeypatch):
-    fake_lance = Mock(__version__="9.0.0")
-    monkeypatch.setitem(__import__("sys").modules, "lance", fake_lance)
-
-    with pytest.raises(RuntimeError, match="requires pylance==0.12.1"):
-        legacy_v2._require_legacy_lance()
-
-
-@pytest.mark.asyncio
-async def test_cloud_migration_is_rejected_before_dependency_check(monkeypatch):
-    require_lance = Mock()
-    monkeypatch.setattr(legacy_v2, "_require_legacy_lance", require_lance)
-
-    with pytest.raises(ValueError, match="only for local/OSS"):
-        await legacy_v2.migrate_legacy_v2_tables("db://example")
-
-    require_lance.assert_not_called()

python/python/tests/test_permutation.py

@@ -6,7 +6,6 @@ import math
 import pytest
 
 from lancedb import DBConnection, Table, connect
-from lancedb.background_loop import LOOP
 from lancedb.permutation import Permutation, Permutations, permutation_builder
 
 
@@ -32,25 +31,6 @@ def test_split_random_ratios(mem_db):
     assert 65 <= split_1_count <= 75  # ~70% ± tolerance
 
 
-def test_execute_does_not_reenter_background_loop(tmp_path, monkeypatch):
-    import threading
-
-    db = connect(tmp_path)
-    tbl = db.create_table("test_table", pa.table({"x": range(10)}))
-    original_run = LOOP.run
-
-    def fail_on_reentry(future):
-        assert threading.current_thread() is not LOOP.thread
-        return original_run(future)
-
-    monkeypatch.setattr(LOOP, "run", fail_on_reentry)
-
-    permutation_tbl = permutation_builder(tbl).execute()
-
-    assert permutation_tbl.count_rows() == 10
-    assert permutation_tbl._conn.read_consistency_interval is None
-
-
 def test_split_random_counts(mem_db):
     """Test random splitting with absolute counts."""
     tbl = mem_db.create_table(

python/python/tests/test_remote_db.py

@@ -2055,24 +2055,6 @@ def blob_remote_table(*, server_version=Version("0.5.0")):
             request.send_header("phalanx-version", str(server_version))
             request.end_headers()
             request.wfile.write(json.dumps(BLOB_DESCRIBE_RESPONSE).encode())
-        elif request.path.startswith("/v1/table/test/blob/image/"):
-            path = request.path.partition("?")[0]
-            row_id = int(path.split("/")[-2])
-            payload = {10: b"alpha", 20: None, 30: b"gamma"}[row_id]
-            if payload is None:
-                request.send_response(204)
-                request.end_headers()
-                return
-            byte_range = request.headers["Range"].removeprefix("bytes=")
-            start_text, end_text = byte_range.split("-", maxsplit=1)
-            start = int(start_text)
-            end = int(end_text) if end_text else len(payload) - 1
-            chunk = payload[start : end + 1]
-            request.send_response(206)
-            request.send_header("Content-Range", f"bytes {start}-{end}/{len(payload)}")
-            request.send_header("Content-Length", str(len(chunk)))
-            request.end_headers()
-            request.wfile.write(chunk)
         elif request.path == "/v1/table/test/query/":
             content_len = int(request.headers.get("Content-Length", 0))
             body = json.loads(request.rfile.read(content_len))
@@ -2110,21 +2092,8 @@ def test_remote_blob_columns_and_fetch():
         assert table.blob_columns() == ["image"]
         blobs = table.fetch_blobs("image", [10, 20, 30])
         assert blobs.to_pylist() == [b"alpha", None, b"gamma"]
-
-
-def test_remote_blob_files_are_lazy_seekable_handles():
-    with blob_remote_table() as table:
-        files = table.fetch_blob_files("image", [10, 20, 30])
-
-        assert len(files) == 3
-        alpha, null_row, gamma = files
-        assert null_row is None
-        assert alpha is not None
-        assert gamma is not None
-        assert alpha.size() == 5
-        assert alpha.read_range(1, 3) == b"lph"
-        gamma.seek(2)
-        assert gamma.read() == b"mma"
+        with pytest.raises(NotImplementedError, match="Use fetch_blobs for full bytes"):
+            table.fetch_blob_files("image", [10, 20, 30])
 
 
 def test_remote_blob_fetch_accepts_query_table():

python/python/tests/test_table.py

@@ -6,7 +6,6 @@ import os
 import sys
 import threading
 import warnings
-from concurrent.futures import ThreadPoolExecutor
 from datetime import date, datetime, timedelta
 from time import sleep
 from typing import List
@@ -2125,27 +2124,6 @@ def test_delete(mem_db: DBConnection):
     assert table.to_arrow()["id"].to_pylist() == [1]
 
 
-def test_concurrent_deletes_are_thread_safe(mem_db: DBConnection):
-    num_workers = 8
-    table = mem_db.create_table(
-        "my_table", data=[{"id": row_id} for row_id in range(num_workers)]
-    )
-    barrier = threading.Barrier(num_workers)
-
-    def delete(row_id: int):
-        barrier.wait()
-        return table.delete(f"id = {row_id}")
-
-    with ThreadPoolExecutor(max_workers=num_workers) as pool:
-        results = list(pool.map(delete, range(num_workers)))
-
-    assert all(result.num_deleted_rows == 1 for result in results)
-    assert sorted(result.version for result in results) == list(
-        range(2, num_workers + 2)
-    )
-    assert table.count_rows() == 0
-
-
 def test_delete_expr(mem_db: DBConnection):
     table = mem_db.create_table(
         "my_table",
@@ -2386,29 +2364,6 @@ def test_merge_insert_by_source_delete_expr(mem_db: DBConnection):
     assert table.to_arrow().sort_by("a") == expected
 
 
-def test_merge_insert_by_source_delete_reconfigure(mem_db: DBConnection):
-    # Calling when_not_matched_by_source_delete() again with no condition must
-    # widen the delete to unconditional, not keep the earlier condition around.
-    table = mem_db.create_table(
-        "my_table",
-        data=pa.table({"a": [1, 2, 3], "b": ["a", "b", "c"]}),
-    )
-    new_data = pa.table({"a": [2, 4], "b": ["x", "z"]})
-
-    merge_insert_res = (
-        table.merge_insert("a")
-        .when_matched_update_all()
-        .when_not_matched_insert_all()
-        .when_not_matched_by_source_delete("a > 2")
-        .when_not_matched_by_source_delete()
-        .execute(new_data)
-    )
-    assert merge_insert_res.num_deleted_rows == 2
-
-    expected = pa.table({"a": [2, 4], "b": ["x", "z"]})
-    assert table.to_arrow().sort_by("a") == expected
-
-
 @pytest.mark.asyncio
 async def test_merge_insert_by_source_delete_expr_async(
     mem_db_async: AsyncConnection,

python/src/table.rs

@@ -426,11 +426,9 @@ pub struct PyBlobFile {
 impl PyBlobFile {
     fn read_bytes(self_: PyRef<'_, Self>) -> PyResult<Py<PyBytes>> {
         let inner = self_.inner.clone();
-        let py = self_.py();
-        let bytes = py
-            .detach(move || block_on(async move { inner.read().await }))
+        let bytes = block_on(async move { inner.read().await })
             .map_err(|e| PyRuntimeError::new_err(format!("blob read failed: {e}")))?;
-        Ok(PyBytes::new(py, bytes.as_ref()).unbind())
+        Ok(PyBytes::new(self_.py(), bytes.as_ref()).unbind())
     }
 
     pub fn read(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
@@ -446,32 +444,24 @@ impl PyBlobFile {
 
     fn close(self_: PyRef<'_, Self>) -> PyResult<()> {
         let inner = self_.inner.clone();
-        self_
-            .py()
-            .detach(move || block_on(async move { inner.close().await }))
+        block_on(async move { inner.close().await })
             .map_err(|e| PyRuntimeError::new_err(format!("blob close failed: {e}")))
     }
 
     fn is_closed(self_: PyRef<'_, Self>) -> bool {
         let inner = self_.inner.clone();
-        self_
-            .py()
-            .detach(move || block_on(async move { inner.is_closed().await }))
+        block_on(async move { inner.is_closed().await })
     }
 
     fn seek(self_: PyRef<'_, Self>, position: u64) -> PyResult<()> {
         let inner = self_.inner.clone();
-        self_
-            .py()
-            .detach(move || block_on(async move { inner.seek(position).await }))
+        block_on(async move { inner.seek(position).await })
             .map_err(|e| PyRuntimeError::new_err(format!("blob seek failed: {e}")))
     }
 
     fn tell(self_: PyRef<'_, Self>) -> PyResult<u64> {
         let inner = self_.inner.clone();
-        self_
-            .py()
-            .detach(move || block_on(async move { inner.tell().await }))
+        block_on(async move { inner.tell().await })
             .map_err(|e| PyRuntimeError::new_err(format!("blob tell failed: {e}")))
     }
 
@@ -485,20 +475,16 @@ impl PyBlobFile {
             .checked_add(length as u64)
             .ok_or_else(|| PyValueError::new_err("offset + length overflowed"))?;
         let inner = self_.inner.clone();
-        let py = self_.py();
-        let bytes = py
-            .detach(move || block_on(async move { inner.read_range(offset..end).await }))
+        let bytes = block_on(async move { inner.read_range(offset..end).await })
             .map_err(|e| PyRuntimeError::new_err(format!("blob read_range failed: {e}")))?;
-        Ok(PyBytes::new(py, bytes.as_ref()).unbind())
+        Ok(PyBytes::new(self_.py(), bytes.as_ref()).unbind())
     }
 
     fn read_up_to(self_: PyRef<'_, Self>, length: usize) -> PyResult<Py<PyBytes>> {
         let inner = self_.inner.clone();
-        let py = self_.py();
-        let bytes = py
-            .detach(move || block_on(async move { inner.read_up_to(length).await }))
-            .map_err(|e| PyRuntimeError::new_err(format!("blob read_up_to failed: {e}")))?;
-        Ok(PyBytes::new(py, bytes.as_ref()).unbind())
+        let bytes = block_on(async move { inner.read_up_to(length).await })
+            .map_err(|e| PyRuntimeError::new_err(format!("blob read failed: {e}")))?;
+        Ok(PyBytes::new(self_.py(), bytes.as_ref()).unbind())
     }
 }
 
@@ -745,9 +731,6 @@ impl Table {
 
     #[allow(private_interfaces)]
     pub fn delete(self_: PyRef<'_, Self>, condition: PredicateArg) -> PyResult<Bound<'_, PyAny>> {
-        // Do not hold the Python borrow across the await.  The cloned Rust table
-        // handle is thread-safe and allows deletes on the same Python table to
-        // run concurrently without PyO3 reporting "Already borrowed".
         let inner = self_.inner_ref()?.clone();
         future_into_py(self_.py(), async move {
             let result = match &condition {
@@ -1378,12 +1361,7 @@ impl Table {
 
         let inner = self_.inner_ref()?.clone();
         future_into_py(self_.py(), async move {
-            let result = inner
-                .add_columns()
-                .transform(definitions)
-                .execute()
-                .await
-                .infer_error()?;
+            let result = inner.add_columns(definitions, None).await.infer_error()?;
             Ok(AddColumnsResult::from(result))
         })
     }
@@ -1397,12 +1375,7 @@ impl Table {
 
         let inner = self_.inner_ref()?.clone();
         future_into_py(self_.py(), async move {
-            let result = inner
-                .add_columns()
-                .transform(transform)
-                .execute()
-                .await
-                .infer_error()?;
+            let result = inner.add_columns(transform, None).await.infer_error()?;
             Ok(AddColumnsResult::from(result))
         })
     }

rust/lancedb/Cargo.toml

@@ -49,8 +49,8 @@ lance-namespace = { workspace = true }
 lance-namespace-impls = { workspace = true }
 metrics = { workspace = true, optional = true }
 metrics-util = { workspace = true, optional = true }
-# Pin the transitive GooseFS SDK until the 0.1.6 compile break is fixed upstream.
-goosefs-sdk = { version = "=0.1.5", optional = true }
+# Keep the direct dependency aligned with the version required by OpenDAL.
+goosefs-sdk = { version = "=0.1.8", optional = true }
 moka = { workspace = true }
 pin-project = { workspace = true }
 tokio = { version = "1.23", features = ["rt-multi-thread", "sync"] }

rust/lancedb/src/blob.rs

@@ -9,7 +9,6 @@
 //!
 //! Blob tables require Lance file format >= 2.2 and stable row ids at create.
 
-use std::ops::Range;
 use std::sync::Arc;
 
 use arrow_array::LargeBinaryArray;
@@ -18,202 +17,10 @@ use arrow_schema::{DataType, Field, Schema};
 use lance::dataset::{BlobRangeRequest as LanceBlobRangeRequest, Dataset, WriteParams};
 use lance_arrow::FieldExt;
 use lance_encoding::version::LanceFileVersion;
-use lance_io::object_store::ObjectStore;
-use object_store::path::Path;
 
 use crate::error::{Error, Result};
 
-/// Seekable handle for one blob value, backed by local storage or a remote
-/// HTTP byte-range endpoint.
-#[derive(Debug)]
-pub struct BlobFile {
-    inner: BlobFileInner,
-}
-
-#[derive(Debug)]
-enum BlobFileInner {
-    Native(lance::dataset::BlobFile),
-    #[cfg(feature = "remote")]
-    Remote(Box<crate::remote::table::blobs::RemoteBlobFile>),
-}
-
-impl From<lance::dataset::BlobFile> for BlobFile {
-    fn from(value: lance::dataset::BlobFile) -> Self {
-        Self {
-            inner: BlobFileInner::Native(value),
-        }
-    }
-}
-
-#[cfg(feature = "remote")]
-impl From<crate::remote::table::blobs::RemoteBlobFile> for BlobFile {
-    fn from(value: crate::remote::table::blobs::RemoteBlobFile) -> Self {
-        Self {
-            inner: BlobFileInner::Remote(Box::new(value)),
-        }
-    }
-}
-
-impl BlobFile {
-    /// Inline reader over a data-file slice.
-    pub fn new_inline(
-        object_store: Arc<ObjectStore>,
-        path: Path,
-        position: u64,
-        size: u64,
-    ) -> Self {
-        lance::dataset::BlobFile::new_inline(object_store, path, position, size).into()
-    }
-
-    /// Dedicated sidecar-file reader.
-    pub fn new_dedicated(object_store: Arc<ObjectStore>, path: Path, size: u64) -> Self {
-        lance::dataset::BlobFile::new_dedicated(object_store, path, size).into()
-    }
-
-    /// Packed reader for a slice in a shared sidecar.
-    pub fn new_packed(
-        object_store: Arc<ObjectStore>,
-        path: Path,
-        position: u64,
-        size: u64,
-    ) -> Self {
-        lance::dataset::BlobFile::new_packed(object_store, path, position, size).into()
-    }
-
-    /// External reader at a resolved object location.
-    pub fn new_external(
-        object_store: Arc<ObjectStore>,
-        path: Path,
-        uri: String,
-        position: u64,
-        size: u64,
-    ) -> Self {
-        lance::dataset::BlobFile::new_external(object_store, path, uri, position, size).into()
-    }
-
-    /// Close the handle.
-    pub async fn close(&self) -> lance_core::Result<()> {
-        match &self.inner {
-            BlobFileInner::Native(file) => file.close().await,
-            #[cfg(feature = "remote")]
-            BlobFileInner::Remote(file) => file.close().await,
-        }
-    }
-
-    /// Whether the handle is closed.
-    pub async fn is_closed(&self) -> bool {
-        match &self.inner {
-            BlobFileInner::Native(file) => file.is_closed().await,
-            #[cfg(feature = "remote")]
-            BlobFileInner::Remote(file) => file.is_closed(),
-        }
-    }
-
-    /// Read a range without moving the cursor.
-    pub async fn read_range(&self, range: Range<u64>) -> lance_core::Result<bytes::Bytes> {
-        match &self.inner {
-            BlobFileInner::Native(file) => file.read_range(range).await,
-            #[cfg(feature = "remote")]
-            BlobFileInner::Remote(file) => file.read_range(range).await,
-        }
-    }
-
-    /// Read ranges without moving the cursor.
-    pub async fn read_ranges(
-        &self,
-        ranges: &[Range<u64>],
-    ) -> lance_core::Result<Vec<bytes::Bytes>> {
-        match &self.inner {
-            BlobFileInner::Native(file) => file.read_ranges(ranges).await,
-            #[cfg(feature = "remote")]
-            BlobFileInner::Remote(file) => file.read_ranges(ranges).await,
-        }
-    }
-
-    /// Read from the cursor to the end.
-    pub async fn read(&self) -> lance_core::Result<bytes::Bytes> {
-        match &self.inner {
-            BlobFileInner::Native(file) => file.read().await,
-            #[cfg(feature = "remote")]
-            BlobFileInner::Remote(file) => file.read().await,
-        }
-    }
-
-    /// Read up to `len` bytes and advance the cursor.
-    pub async fn read_up_to(&self, len: usize) -> lance_core::Result<bytes::Bytes> {
-        match &self.inner {
-            BlobFileInner::Native(file) => file.read_up_to(len).await,
-            #[cfg(feature = "remote")]
-            BlobFileInner::Remote(file) => file.read_up_to(len).await,
-        }
-    }
-
-    /// Move the cursor to `new_cursor`.
-    pub async fn seek(&self, new_cursor: u64) -> lance_core::Result<()> {
-        match &self.inner {
-            BlobFileInner::Native(file) => file.seek(new_cursor).await,
-            #[cfg(feature = "remote")]
-            BlobFileInner::Remote(file) => file.seek(new_cursor).await,
-        }
-    }
-
-    /// Current cursor position.
-    pub async fn tell(&self) -> lance_core::Result<u64> {
-        match &self.inner {
-            BlobFileInner::Native(file) => file.tell().await,
-            #[cfg(feature = "remote")]
-            BlobFileInner::Remote(file) => file.tell().await,
-        }
-    }
-
-    /// Blob length in bytes.
-    pub fn size(&self) -> u64 {
-        match &self.inner {
-            BlobFileInner::Native(file) => file.size(),
-            #[cfg(feature = "remote")]
-            BlobFileInner::Remote(file) => file.size(),
-        }
-    }
-
-    /// Physical byte offset in the data file. `None` on remote handles. The
-    /// Cloud byte-range route does not expose storage layout.
-    pub fn position(&self) -> Option<u64> {
-        match &self.inner {
-            BlobFileInner::Native(file) => Some(file.position()),
-            #[cfg(feature = "remote")]
-            BlobFileInner::Remote(_) => None,
-        }
-    }
-
-    /// Path of the data file holding the blob. `None` on remote handles. The
-    /// Cloud byte-range route does not expose storage layout.
-    pub fn data_path(&self) -> Option<&Path> {
-        match &self.inner {
-            BlobFileInner::Native(file) => Some(file.data_path()),
-            #[cfg(feature = "remote")]
-            BlobFileInner::Remote(_) => None,
-        }
-    }
-
-    /// Native storage layout. `None` on remote handles. The Cloud byte-range
-    /// route does not expose layout.
-    pub fn kind(&self) -> Option<lance_core::datatypes::BlobKind> {
-        match &self.inner {
-            BlobFileInner::Native(file) => Some(file.kind()),
-            #[cfg(feature = "remote")]
-            BlobFileInner::Remote(_) => None,
-        }
-    }
-
-    /// External URI for native handles. Remote handles do not expose storage URIs.
-    pub fn uri(&self) -> Option<&str> {
-        match &self.inner {
-            BlobFileInner::Native(file) => file.uri(),
-            #[cfg(feature = "remote")]
-            BlobFileInner::Remote(_) => None,
-        }
-    }
-}
+pub use lance::dataset::BlobFile;
 
 /// One row-specific blob range read request.
 ///
@@ -457,10 +264,7 @@ pub(crate) async fn take_blob_files_aligned(
 
     let handles = dataset.take_blobs(row_ids, column).await?;
     ensure_all_row_ids_resolved(column, row_ids.len(), handles.len())?;
-    Ok(handles
-        .into_iter()
-        .map(|handle| handle.map(Into::into))
-        .collect())
+    Ok(handles)
 }
 
 #[cfg(test)]

rust/lancedb/src/remote/table.rs

@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
-pub mod blobs;
+mod blobs;
 pub mod insert;
 
 use self::insert::{RemoteWriteExec, WriteOp};
@@ -2939,7 +2939,7 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
 }
 
 #[derive(Serialize, Clone, Debug)]
-pub(crate) struct MergeInsertRequest {
+pub struct MergeInsertRequest {
     on: String,
     when_matched_update_all: bool,
     when_matched_update_all_filt: Option<String>,
@@ -3089,12 +3089,10 @@ mod tests {
             Box::pin(table.delete("false").map_ok(|_| ())),
             Box::pin(
                 table
-                    .add_columns()
-                    .transform(NewColumnTransform::SqlExpressions(vec![(
-                        "x".into(),
-                        "y".into(),
-                    )]))
-                    .execute()
+                    .add_columns(
+                        NewColumnTransform::SqlExpressions(vec![("x".into(), "y".into())]),
+                        None,
+                    )
                     .map_ok(|_| ()),
             ),
             Box::pin(async {
@@ -4302,9 +4300,32 @@ mod tests {
             "fetch_blobs",
         );
 
+        let message = table
+            .fetch_blob_files("image", &[1])
+            .await
+            .unwrap_err()
+            .to_string();
+        assert!(
+            message.contains("fetch_blob_files is not supported on LanceDB Cloud"),
+            "got: {message}"
+        );
+        assert!(
+            !message.contains("Use fetch_blobs"),
+            "old server must not be told to use fetch_blobs, got: {message}"
+        );
+    }
+
+    #[tokio::test]
+    async fn test_blob_files_point_at_fetch_blobs_on_a_blob_capable_server() {
+        let table = Table::new_with_handler_version(
+            "my_table",
+            semver::Version::new(0, 5, 0),
+            |_| -> http::Response<String> { panic!("fetch_blob_files must not reach the server") },
+        );
+
         assert_not_supported_error(
             table.fetch_blob_files("image", &[1]).await.unwrap_err(),
-            "requires LanceDB Cloud server 0.5.0 or newer",
+            "Use fetch_blobs for full bytes",
         );
     }
 
@@ -6390,12 +6411,13 @@ mod tests {
         });
 
         let result = table
-            .add_columns()
-            .transform(NewColumnTransform::SqlExpressions(vec![
-                ("b".into(), "a + 1".into()),
-                ("x".into(), "cast(NULL as int32)".into()),
-            ]))
-            .execute()
+            .add_columns(
+                NewColumnTransform::SqlExpressions(vec![
+                    ("b".into(), "a + 1".into()),
+                    ("x".into(), "cast(NULL as int32)".into()),
+                ]),
+                None,
+            )
             .await
             .unwrap();
 
@@ -7120,12 +7142,10 @@ mod tests {
             }
             "add_columns" => {
                 let _ = table
-                    .add_columns()
-                    .transform(NewColumnTransform::SqlExpressions(vec![(
-                        "c".into(),
-                        "a + 1".into(),
-                    )]))
-                    .execute()
+                    .add_columns(
+                        NewColumnTransform::SqlExpressions(vec![("c".into(), "a + 1".into())]),
+                        None,
+                    )
                     .await;
             }
             "drop_columns" => {
@@ -9883,12 +9903,10 @@ mod tests {
             .await
             .unwrap();
         branch
-            .add_columns()
-            .transform(NewColumnTransform::SqlExpressions(vec![(
-                "b".into(),
-                "a + 1".into(),
-            )]))
-            .execute()
+            .add_columns(
+                NewColumnTransform::SqlExpressions(vec![("b".into(), "a + 1".into())]),
+                None,
+            )
             .await
             .unwrap();
         branch

rust/lancedb/src/remote/table/insert.rs

@@ -33,7 +33,7 @@ use crate::table::{AddResult, MergeResult};
 /// same Arrow-IPC streaming body and error side-channel; only the target
 /// endpoint, query parameters, and parsed result type differ.
 #[derive(Debug, Clone)]
-pub(crate) enum WriteOp {
+pub enum WriteOp {
     /// `add`: stream to `/v1/table/{id}/insert/`, optionally overwriting.
     Insert { overwrite: bool },
     /// `merge_insert`: stream to `/v1/table/{id}/merge_insert/` with the merge
@@ -49,7 +49,7 @@ pub(crate) enum WriteOp {
 /// The parsed server response for a completed write, discriminated by the
 /// operation that produced it.
 #[derive(Debug, Clone)]
-pub(crate) enum WriteResult {
+pub enum WriteResult {
     Add(AddResult),
     Merge(MergeResult),
 }

rust/lancedb/src/table.rs

@@ -3,7 +3,6 @@
 
 //! LanceDB Table APIs
 
-use crate::blob::BlobFile;
 use arrow_array::{LargeBinaryArray, RecordBatch, RecordBatchReader};
 use arrow_schema::{Schema, SchemaRef};
 use async_trait::async_trait;
@@ -13,6 +12,7 @@ use datafusion_physical_plan::ExecutionPlan;
 use datafusion_physical_plan::display::DisplayableExecutionPlan;
 use futures::StreamExt;
 use futures::stream::FuturesUnordered;
+use lance::dataset::BlobFile;
 pub use lance::dataset::ColumnAlteration;
 pub use lance::dataset::NewColumnTransform;
 pub use lance::dataset::ReadParams;
@@ -65,7 +65,6 @@ use crate::utils::{PatchReadParam, PatchWriteParam, resolve_arrow_field_path};
 use self::dataset::DatasetConsistencyWrapper;
 use self::merge::MergeInsertBuilder;
 
-pub mod add_columns;
 mod add_data;
 pub mod branch_merge;
 mod create_index;
@@ -80,7 +79,6 @@ pub mod schema_evolution;
 pub mod update;
 pub mod write_progress;
 use crate::index::waiter::wait_for_index;
-pub use add_columns::AddColumnsBuilder;
 #[cfg(feature = "remote")]
 pub(crate) use add_data::PreprocessingOutput;
 pub use add_data::{AddDataBuilder, AddDataMode, AddResult, NaNVectorBehavior};
@@ -1622,8 +1620,12 @@ impl Table {
     }
 
     /// Add new columns to the table, providing values to fill in.
-    pub fn add_columns(&self) -> AddColumnsBuilder {
-        AddColumnsBuilder::new(self.inner.clone())
+    pub async fn add_columns(
+        &self,
+        transforms: NewColumnTransform,
+        read_columns: Option<Vec<String>>,
+    ) -> Result<AddColumnsResult> {
+        self.inner.add_columns(transforms, read_columns).await
     }
 
     /// Change a column's name or nullability.

rust/lancedb/src/table/add_columns.rs

@@ -1,161 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-//! Builder for adding columns to a table.
-
-use std::sync::Arc;
-
-use lance::dataset::NewColumnTransform;
-
-use super::BaseTable;
-use super::schema_evolution::AddColumnsResult;
-use crate::{Error, Result};
-
-/// Adds columns to a table. See [`Table::add_columns`](super::Table::add_columns).
-pub struct AddColumnsBuilder {
-    parent: Arc<dyn BaseTable>,
-    transform: Option<NewColumnTransform>,
-    read_columns: Option<Vec<String>>,
-}
-
-impl std::fmt::Debug for AddColumnsBuilder {
-    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
-        f.debug_struct("AddColumnsBuilder")
-            .field("parent", &self.parent)
-            .field("has_transform", &self.transform.is_some())
-            .field("read_columns", &self.read_columns)
-            .finish()
-    }
-}
-
-impl AddColumnsBuilder {
-    pub(crate) fn new(parent: Arc<dyn BaseTable>) -> Self {
-        Self {
-            parent,
-            transform: None,
-            read_columns: None,
-        }
-    }
-
-    /// Set how the new columns' values are produced. Required.
-    pub fn transform(mut self, transform: NewColumnTransform) -> Self {
-        self.transform = Some(transform);
-        self
-    }
-
-    /// Limit which existing columns a [`NewColumnTransform::BatchUDF`] mapper
-    /// receives. Every other transform determines what it reads, so setting
-    /// this alongside one is an error rather than a silent no-op.
-    pub fn read_columns(mut self, columns: impl IntoIterator<Item = impl Into<String>>) -> Self {
-        self.read_columns = Some(columns.into_iter().map(Into::into).collect());
-        self
-    }
-
-    /// Add the columns.
-    pub async fn execute(self) -> Result<AddColumnsResult> {
-        let Self {
-            parent,
-            transform,
-            read_columns,
-        } = self;
-
-        let Some(transform) = transform else {
-            return Err(Error::InvalidInput {
-                message: "add_columns requires a transform".into(),
-            });
-        };
-
-        if read_columns.is_some() && !matches!(transform, NewColumnTransform::BatchUDF(_)) {
-            return Err(Error::InvalidInput {
-                message: "read_columns applies only to a BatchUDF transform; \
-                          every other transform determines what it reads"
-                    .into(),
-            });
-        }
-
-        parent.add_columns(transform, read_columns).await
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use std::sync::Arc;
-
-    use arrow_array::{Int32Array, RecordBatch, record_batch};
-    use arrow_schema::{DataType, Field, Schema};
-    use lance::dataset::{BatchUDF, NewColumnTransform};
-
-    use crate::Table;
-    use crate::connect;
-
-    async fn table_with_two_columns(name: &str) -> Table {
-        let conn = connect("memory://").execute().await.unwrap();
-        let batch = record_batch!(("x", Int32, [1, 2, 3]), ("y", Int32, [10, 20, 30])).unwrap();
-        conn.create_table(name, batch).execute().await.unwrap()
-    }
-
-    #[tokio::test]
-    async fn test_requires_a_transform() {
-        let table = table_with_two_columns("no_transform").await;
-        let err = table.add_columns().execute().await.unwrap_err();
-        assert!(
-            err.to_string().contains("requires a transform"),
-            "got: {err}"
-        );
-    }
-
-    #[tokio::test]
-    async fn test_read_columns_with_sql_expressions_is_rejected() {
-        let table = table_with_two_columns("read_cols_sql").await;
-        let err = table
-            .add_columns()
-            .transform(NewColumnTransform::SqlExpressions(vec![(
-                "doubled".into(),
-                "x * 2".into(),
-            )]))
-            .read_columns(["x"])
-            .execute()
-            .await
-            .unwrap_err();
-        assert!(err.to_string().contains("BatchUDF"), "got: {err}");
-
-        let schema = table.schema().await.unwrap();
-        assert!(
-            schema.field_with_name("doubled").is_err(),
-            "a rejected call must not commit"
-        );
-    }
-
-    #[tokio::test]
-    async fn test_read_columns_limits_what_a_batch_udf_sees() {
-        let table = table_with_two_columns("read_cols_udf").await;
-
-        let output_schema = Arc::new(Schema::new(vec![Field::new("sum", DataType::Int32, true)]));
-        let mapper_schema = output_schema.clone();
-        let udf = BatchUDF {
-            mapper: Box::new(move |batch: &RecordBatch| {
-                assert!(batch.column_by_name("x").is_some());
-                assert!(batch.column_by_name("y").is_none(), "y was not requested");
-                let x = batch["x"].as_any().downcast_ref::<Int32Array>().unwrap();
-                let doubled: Int32Array = x.iter().map(|v| v.map(|v| v * 2)).collect();
-                Ok(RecordBatch::try_new(
-                    mapper_schema.clone(),
-                    vec![Arc::new(doubled)],
-                )?)
-            }),
-            output_schema,
-            result_checkpoint: None,
-        };
-
-        table
-            .add_columns()
-            .transform(NewColumnTransform::BatchUDF(udf))
-            .read_columns(["x"])
-            .execute()
-            .await
-            .unwrap();
-
-        let schema = table.schema().await.unwrap();
-        assert!(schema.field_with_name("sum").is_ok());
-    }
-}

rust/lancedb/src/table/add_data.rs

@@ -576,12 +576,10 @@ mod tests {
 
         // Add a new physical column AFTER the embedding column.
         table
-            .add_columns()
-            .transform(NewColumnTransform::SqlExpressions(vec![(
-                "score".into(),
-                "42.0".into(),
-            )]))
-            .execute()
+            .add_columns(
+                NewColumnTransform::SqlExpressions(vec![("score".into(), "42.0".into())]),
+                None,
+            )
             .await
             .unwrap();
 
@@ -685,9 +683,7 @@ mod tests {
             true,
         )]));
         table
-            .add_columns()
-            .transform(NewColumnTransform::AllNulls(nested_schema))
-            .execute()
+            .add_columns(NewColumnTransform::AllNulls(nested_schema), None)
             .await
             .unwrap();
 

rust/lancedb/src/table/schema_evolution.rs

@@ -193,12 +193,10 @@ mod tests {
 
         // Add a computed column
         let result = table
-            .add_columns()
-            .transform(NewColumnTransform::SqlExpressions(vec![(
-                "doubled".into(),
-                "id * 2".into(),
-            )]))
-            .execute()
+            .add_columns(
+                NewColumnTransform::SqlExpressions(vec![("doubled".into(), "id * 2".into())]),
+                None,
+            )
             .await
             .unwrap();
 
@@ -253,12 +251,13 @@ mod tests {
 
         // Add multiple columns at once
         table
-            .add_columns()
-            .transform(NewColumnTransform::SqlExpressions(vec![
-                ("y".into(), "x + 1".into()),
-                ("z".into(), "x * x".into()),
-            ]))
-            .execute()
+            .add_columns(
+                NewColumnTransform::SqlExpressions(vec![
+                    ("y".into(), "x + 1".into()),
+                    ("z".into(), "x * x".into()),
+                ]),
+                None,
+            )
             .await
             .unwrap();
 
@@ -284,12 +283,10 @@ mod tests {
 
         // Add a column with a constant value
         table
-            .add_columns()
-            .transform(NewColumnTransform::SqlExpressions(vec![(
-                "constant".into(),
-                "42".into(),
-            )]))
-            .execute()
+            .add_columns(
+                NewColumnTransform::SqlExpressions(vec![("constant".into(), "42".into())]),
+                None,
+            )
             .await
             .unwrap();
 
@@ -662,12 +659,10 @@ mod tests {
 
         // Add column increments version
         let add_result = table
-            .add_columns()
-            .transform(NewColumnTransform::SqlExpressions(vec![(
-                "c".into(),
-                "a + b".into(),
-            )]))
-            .execute()
+            .add_columns(
+                NewColumnTransform::SqlExpressions(vec![("c".into(), "a + b".into())]),
+                None,
+            )
             .await
             .unwrap();
         assert!(add_result.version > v1);

rust/lancedb/tests/blob_integration.rs

@@ -9,17 +9,14 @@ use arrow_array::{
 };
 use arrow_schema::{DataType, Field, Fields, Schema};
 use futures::TryStreamExt;
-use lance::Dataset;
 use lance_encoding::version::LanceFileVersion;
 use lancedb::{
     Connection, Error, Result, Table,
     blob::{BlobRangeRequest, blob},
     connect, connect_namespace,
-    database::listing::{
-        ListingDatabaseOptions, NewTableConfig, OPT_NEW_TABLE_ENABLE_STABLE_ROW_IDS,
-    },
+    database::listing::OPT_NEW_TABLE_ENABLE_STABLE_ROW_IDS,
     query::{ExecutableQuery, QueryBase},
-    table::{AddDataMode, CompactionOptions, OptimizeAction, OptimizeStats},
+    table::{AddDataMode, CompactionOptions, OptimizeAction},
 };
 use tempfile::tempdir;
 
@@ -1078,252 +1075,3 @@ async fn fetch_blob_files_aligns_across_fragments_with_nulls_and_dups() -> Resul
     }
     Ok(())
 }
-
-/// Rows exercising the null/empty interleavings from
-/// <https://github.com/lancedb/lancedb/issues/3744>: a payload, a null, a valid
-/// empty value, then payloads whose descriptors a fragment rewrite used to zero.
-fn null_empty_input_batch() -> RecordBatch {
-    let owned = [
-        Some(dedicated_blob_bytes(1)),
-        None,
-        Some(Vec::new()),
-        Some(dedicated_blob_bytes(4)),
-        Some(dedicated_blob_bytes(5)),
-        Some(dedicated_blob_bytes(6)),
-    ];
-    let payloads: Vec<Option<&[u8]>> = owned.iter().map(|payload| payload.as_deref()).collect();
-    binary_input_batch(&[1, 2, 3, 4, 5, 6], &payloads)
-}
-
-/// One `(id, Some((payload length, first byte)))` per live row, or `(id, None)`
-/// for a null blob.  Comparing lengths and first bytes keeps failure output
-/// readable where comparing whole payloads would not.
-type BlobSummary = Vec<(i64, Option<(usize, Option<u8>)>)>;
-
-/// The rows [`null_empty_input_batch`] leaves behind after `id IN (1, 4)` is
-/// deleted: a null, a valid empty value, and the two payloads that follow them.
-fn expected_null_empty_survivors() -> BlobSummary {
-    vec![
-        (2, None),
-        (3, Some((0, None))),
-        (5, Some((DEDICATED_BLOB_LEN, Some(5)))),
-        (6, Some((DEDICATED_BLOB_LEN, Some(6)))),
-    ]
-}
-
-/// `optimize()` only rewrites a fragment when lance's compaction planner selects
-/// it — here because the delete pushes the fragment past
-/// `materialize_deletions_threshold` (0.1 by default; these tests delete 2 of 6
-/// rows). Without this check, a planner or threshold change upstream would leave
-/// both regression tests green while no rewrite happened at all.
-fn assert_compacted(stats: &OptimizeStats) {
-    let metrics = stats
-        .compaction
-        .as_ref()
-        .expect("OptimizeAction::All runs compaction");
-    assert!(
-        metrics.fragments_removed >= 1,
-        "optimize() rewrote no fragment, so this test proves nothing: {metrics:?}"
-    );
-}
-
-fn summarize(rows: &[(i64, Option<Vec<u8>>)]) -> BlobSummary {
-    rows.iter()
-        .map(|(id, payload)| {
-            (
-                *id,
-                payload
-                    .as_ref()
-                    .map(|bytes| (bytes.len(), bytes.first().copied())),
-            )
-        })
-        .collect()
-}
-
-async fn sorted_id_rowid(table: &Table) -> Result<Vec<(i64, u64)>> {
-    let mut pairs = collect_id_rowid(table).await?;
-    pairs.sort_by_key(|(id, _)| *id);
-    Ok(pairs)
-}
-
-/// `{position, size}` descriptors of a legacy v1 blob column, keyed by `id`.
-async fn v1_blob_descriptors(table: &Table) -> Result<Vec<(i64, Option<(u64, u64)>)>> {
-    let batches = table
-        .query()
-        .execute()
-        .await?
-        .try_collect::<Vec<_>>()
-        .await?;
-    let batch = arrow_select::concat::concat_batches(&batches[0].schema(), &batches).unwrap();
-    let ids = batch
-        .column_by_name("id")
-        .unwrap()
-        .as_any()
-        .downcast_ref::<Int64Array>()
-        .unwrap();
-    let descriptors = batch
-        .column_by_name("image")
-        .unwrap()
-        .as_any()
-        .downcast_ref::<StructArray>()
-        .expect("v1 blob column reads back as a descriptor struct");
-    let position = descriptors
-        .column_by_name("position")
-        .unwrap()
-        .as_any()
-        .downcast_ref::<UInt64Array>()
-        .unwrap();
-    let size = descriptors
-        .column_by_name("size")
-        .unwrap()
-        .as_any()
-        .downcast_ref::<UInt64Array>()
-        .unwrap();
-    let mut rows: Vec<(i64, Option<(u64, u64)>)> = (0..batch.num_rows())
-        .map(|row| {
-            let descriptor =
-                (!descriptors.is_null(row)).then(|| (position.value(row), size.value(row)));
-            (ids.value(row), descriptor)
-        })
-        .collect();
-    rows.sort_by_key(|(id, _)| *id);
-    Ok(rows)
-}
-
-/// Payload bytes of every live row of a legacy v1 blob column, keyed by `id`.
-/// [`Table::fetch_blobs`] rejects v1 columns, so read them through lance.
-async fn v1_blob_payloads(dataset_uri: &str, table: &Table) -> Result<Vec<(i64, Option<Vec<u8>>)>> {
-    let pairs = sorted_id_rowid(table).await?;
-    let row_ids: Vec<u64> = pairs.iter().map(|(_, row_id)| *row_id).collect();
-    let dataset = Arc::new(Dataset::open(dataset_uri).await?);
-    let files = dataset.take_blobs(&row_ids, "image").await?;
-    assert_eq!(
-        files.len(),
-        pairs.len(),
-        "take_blobs returned {} handles for {} live rows",
-        files.len(),
-        pairs.len()
-    );
-    let mut rows = Vec::with_capacity(pairs.len());
-    for ((id, _), file) in pairs.iter().zip(files) {
-        let payload = match file {
-            Some(file) => Some(file.read().await?.to_vec()),
-            None => None,
-        };
-        rows.push((*id, payload));
-    }
-    Ok(rows)
-}
-
-/// Length and first byte of every live blob v2 value, keyed by `id`.
-async fn blob_v2_values(table: &Table) -> Result<BlobSummary> {
-    let pairs = sorted_id_rowid(table).await?;
-    let row_ids: Vec<u64> = pairs.iter().map(|(_, row_id)| *row_id).collect();
-    let bytes = table.fetch_blobs("image", &row_ids).await?;
-    Ok(pairs
-        .iter()
-        .enumerate()
-        .map(|(slot, (id, _))| {
-            let value = (!bytes.is_null(slot))
-                .then(|| (bytes.value(slot).len(), bytes.value(slot).first().copied()));
-            (*id, value)
-        })
-        .collect())
-}
-
-/// Regression test for [#3744]: on storage 2.0 (legacy v1 descriptors),
-/// compaction rewrote every payload following a null or empty value in the same
-/// fragment as `{position: 0, size: 0}`, so the payload bytes read back as `b""`
-/// and the new fragment no longer referenced them at all.
-///
-/// [#3744]: https://github.com/lancedb/lancedb/issues/3744
-#[tokio::test]
-async fn optimize_preserves_v1_blob_payloads_with_null_and_empty() -> Result<()> {
-    let tmp = tempdir().unwrap();
-    let db_uri = tmp.path().to_str().unwrap().to_string();
-    let db = connect(&db_uri)
-        .database_options(&ListingDatabaseOptions {
-            new_table_config: NewTableConfig {
-                data_storage_version: Some(LanceFileVersion::V2_0),
-                ..Default::default()
-            },
-            ..Default::default()
-        })
-        .execute()
-        .await?;
-    let legacy = Field::new("image", DataType::LargeBinary, true).with_metadata(
-        std::collections::HashMap::from([("lance-encoding:blob".to_string(), "true".to_string())]),
-    );
-    let schema = Arc::new(Schema::new(vec![
-        Field::new("id", DataType::Int64, false),
-        legacy,
-    ]));
-    let table = db.create_empty_table("t", schema).execute().await?;
-    table.add(null_empty_input_batch()).execute().await?;
-    assert_eq!(
-        storage_format_version(&table).await,
-        LanceFileVersion::V2_0.resolve(),
-        "v1 blob descriptors only exist below storage 2.2"
-    );
-    let dataset_uri = table.uri().await?;
-
-    // Any rewrite triggers it; deleting rows is the shape from the issue.
-    table.delete("id IN (1, 4)").await?;
-    let descriptors_before = v1_blob_descriptors(&table).await?;
-    let before = v1_blob_payloads(&dataset_uri, &table).await?;
-    assert_eq!(
-        summarize(&before),
-        expected_null_empty_survivors(),
-        "test setup no longer produces the null/empty/payload mix"
-    );
-
-    let stats = table.optimize(OptimizeAction::All).await?;
-    assert_compacted(&stats);
-
-    let descriptors_after = v1_blob_descriptors(&table).await?;
-    let after = v1_blob_payloads(&dataset_uri, &table).await?;
-    assert_eq!(
-        summarize(&after),
-        summarize(&before),
-        "optimize() lost blob payloads; descriptors before={descriptors_before:?} after={descriptors_after:?}"
-    );
-    assert!(after == before, "optimize() changed blob payload bytes");
-    Ok(())
-}
-
-/// Regression test for the blob v2 half of [#3744]: compaction rewrote a valid
-/// empty value as null, destroying the null-vs-empty distinction.
-///
-/// [#3744]: https://github.com/lancedb/lancedb/issues/3744
-#[tokio::test]
-async fn optimize_preserves_blob_v2_null_and_empty_distinction() -> Result<()> {
-    let tmp = tempdir().unwrap();
-    let db = connect(tmp.path().to_str().unwrap()).execute().await?;
-    let table = db
-        .create_empty_table("t", blob_table_schema())
-        .execute()
-        .await?;
-    table.add(null_empty_input_batch()).execute().await?;
-    assert!(
-        storage_format_version(&table).await >= LanceFileVersion::V2_2,
-        "blob v2 columns require storage >= 2.2"
-    );
-
-    table.delete("id IN (1, 4)").await?;
-    let before = blob_v2_values(&table).await?;
-    assert_eq!(
-        before,
-        expected_null_empty_survivors(),
-        "test setup no longer produces the null/empty/payload mix"
-    );
-
-    let stats = table.optimize(OptimizeAction::All).await?;
-    assert_compacted(&stats);
-
-    assert_eq!(
-        blob_v2_values(&table).await?,
-        before,
-        "optimize() changed blob v2 values"
-    );
-    Ok(())
-}