chore: update lance dependency to v2.0.0-rc.4

fix: support pydantic list of structs or optional struct (#2953 )
Closes #2950 *This code is generated by codex-gpt5.2*
2026-09-09 14:52:25 +00:00 · 2026-01-29 16:22:24 +00:00 · 2026-01-28 21:08:18 -08:00 · 2026-01-28 09:02:59 +05:30 · 2026-01-26 23:39:18 +00:00 · 2026-01-26 23:38:50 +00:00
36 changed files with 1230 additions and 1125 deletions
@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.24.0"
+current_version = "0.24.1"
 parse = """(?x)
    (?P<major>0|[1-9]\\d*)\\.
    (?P<minor>0|[1-9]\\d*)\\.
@@ -48,6 +48,8 @@ jobs:
        run: cargo fmt --all -- --check
      - name: Run clippy
        run: cargo clippy --profile ci --workspace --tests --all-features -- -D warnings
+      - name: Run clippy (without remote feature)
+        run: cargo clippy --profile ci --workspace --tests -- -D warnings

  build-no-lock:
    runs-on: ubuntu-24.04
@@ -181,7 +183,7 @@ jobs:
    runs-on: ubuntu-24.04
    strategy:
      matrix:
-        msrv: ["1.78.0"] # This should match up with rust-version in Cargo.toml
+        msrv: ["1.88.0"] # This should match up with rust-version in Cargo.toml
    env:
      # Need up-to-date compilers for kernels
      CC: clang-18
@@ -212,4 +214,6 @@ jobs:
          cargo update -p aws-sdk-sts --precise 1.51.0
          cargo update -p home --precise 0.5.9
      - name: cargo +${{ matrix.msrv }} check
+        env:
+          RUSTUP_TOOLCHAIN: ${{ matrix.msrv }}
        run: cargo check --profile ci --workspace --tests --benches --all-features
@@ -12,23 +12,23 @@ repository = "https://github.com/lancedb/lancedb"
 description = "Serverless, low-latency vector database for AI applications"
 keywords = ["lancedb", "lance", "database", "vector", "search"]
 categories = ["database-implementations"]
-rust-version = "1.78.0"
+rust-version = "1.88.0"

 [workspace.dependencies]
-lance = { "version" = "=2.0.0-rc.1", default-features = false, "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=2.0.0-rc.1", default-features = false, "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=2.0.0-rc.1", default-features = false, "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=2.0.0-rc.4", default-features = false, "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=2.0.0-rc.4", "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=2.0.0-rc.4", "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=2.0.0-rc.4", "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=2.0.0-rc.4", default-features = false, "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=2.0.0-rc.4", "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=2.0.0-rc.4", "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=2.0.0-rc.4", "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=2.0.0-rc.4", default-features = false, "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=2.0.0-rc.4", "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=2.0.0-rc.4", "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=2.0.0-rc.4", "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=2.0.0-rc.4", "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=2.0.0-rc.4", "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
 ahash = "0.8"
 # Note that this one does not include pyarrow
 arrow = { version = "57.2", optional = false }
@@ -47,7 +47,7 @@ datafusion-execution = "51.0"
 datafusion-expr = "51.0"
 datafusion-physical-plan = "51.0"
 env_logger = "0.11"
-half = { "version" = "2.7.1", default-features = false, features = [
+half = { "version" = "2.6.0", default-features = false, features = [
    "num-traits",
 ] }
 futures = "0"
@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
 <dependency>
    <groupId>com.lancedb</groupId>
    <artifactId>lancedb-core</artifactId>
-    <version>0.24.0</version>
+    <version>0.24.1</version>
 </dependency>
 ```

@@ -8,7 +8,7 @@
    <parent>
      <groupId>com.lancedb</groupId>
      <artifactId>lancedb-parent</artifactId>
-      <version>0.24.0-final.0</version>
+      <version>0.24.1-final.0</version>
      <relativePath>../pom.xml</relativePath>
    </parent>

@@ -6,7 +6,7 @@

    <groupId>com.lancedb</groupId>
    <artifactId>lancedb-parent</artifactId>
-    <version>0.24.0-final.0</version>
+    <version>0.24.1-final.0</version>
    <packaging>pom</packaging>
    <name>${project.artifactId}</name>
    <description>LanceDB Java SDK Parent POM</description>
@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.24.0"
+version = "0.24.1"
 license.workspace = true
 description.workspace = true
 repository.workspace = true
@@ -1520,9 +1520,9 @@ describe("when optimizing a dataset", () => {

  it("delete unverified", async () => {
    const version = await table.version();
-    const versionFile = `${tmpDir.name}/${table.name}.lance/_versions/${String(
-      18446744073709551615n - (BigInt(version) - 1n),
-    ).padStart(20, "0")}.manifest`;
+    const versionFile = `${tmpDir.name}/${table.name}.lance/_versions/${
+      version - 1
+    }.manifest`;
    fs.rmSync(versionFile);

    let stats = await table.optimize({ deleteUnverified: false });
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.24.0",
+	"version": "0.24.1",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-x64",
-	"version": "0.24.0",
+	"version": "0.24.1",
 	"os": ["darwin"],
 	"cpu": ["x64"],
 	"main": "lancedb.darwin-x64.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.24.0",
+	"version": "0.24.1",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-musl",
-	"version": "0.24.0",
+	"version": "0.24.1",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-musl.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.24.0",
+	"version": "0.24.1",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-musl",
-	"version": "0.24.0",
+	"version": "0.24.1",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-musl.node",
@@ -1,6 +1,6 @@
 {
  "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.24.0",
+  "version": "0.24.1",
  "os": [
    "win32"
  ],
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.24.0",
+	"version": "0.24.1",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",
@@ -1,12 +1,12 @@
 {
  "name": "@lancedb/lancedb",
-  "version": "0.24.0",
+  "version": "0.24.1",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "@lancedb/lancedb",
-      "version": "0.24.0",
+      "version": "0.24.1",
      "cpu": [
        "x64",
        "arm64"
@@ -11,7 +11,7 @@
    "ann"
  ],
  "private": false,
-  "version": "0.24.0",
+  "version": "0.24.1",
  "main": "dist/index.js",
  "exports": {
    ".": "./dist/index.js",
@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.27.0"
+current_version = "0.27.1"
 parse = """(?x)
    (?P<major>0|[1-9]\\d*)\\.
    (?P<minor>0|[1-9]\\d*)\\.
@@ -1,13 +1,13 @@
 [package]
 name = "lancedb-python"
-version = "0.27.0"
+version = "0.27.1"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true
 repository.workspace = true
 keywords.workspace = true
 categories.workspace = true
-rust-version = "1.75.0"
+rust-version = "1.88.0"

 [lib]
 name = "_lancedb"
@@ -275,7 +275,7 @@ def _py_type_to_arrow_type(py_type: Type[Any], field: FieldInfo) -> pa.DataType:
        return pa.timestamp("us", tz=tz)
    elif getattr(py_type, "__origin__", None) in (list, tuple):
        child = py_type.__args__[0]
-        return pa.list_(_py_type_to_arrow_type(child, field))
+        return _pydantic_list_child_to_arrow(child, field)
    raise TypeError(
        f"Converting Pydantic type to Arrow Type: unsupported type {py_type}."
    )
@@ -298,12 +298,18 @@ else:


 def _pydantic_type_to_arrow_type(tp: Any, field: FieldInfo) -> pa.DataType:
+    def _safe_issubclass(candidate: Any, base: type) -> bool:
+        try:
+            return issubclass(candidate, base)
+        except TypeError:
+            return False
+
    if inspect.isclass(tp):
-        if issubclass(tp, pydantic.BaseModel):
+        if _safe_issubclass(tp, pydantic.BaseModel):
            # Struct
            fields = _pydantic_model_to_fields(tp)
            return pa.struct(fields)
-        if issubclass(tp, FixedSizeListMixin):
+        if _safe_issubclass(tp, FixedSizeListMixin):
            if getattr(tp, "is_multi_vector", lambda: False)():
                return pa.list_(pa.list_(tp.value_arrow_type(), tp.dim()))
            # For regular Vector
@@ -311,45 +317,67 @@ def _pydantic_type_to_arrow_type(tp: Any, field: FieldInfo) -> pa.DataType:
    return _py_type_to_arrow_type(tp, field)


+def _pydantic_list_child_to_arrow(child: Any, field: FieldInfo) -> pa.DataType:
+    unwrapped = _unwrap_optional_annotation(child)
+    if unwrapped is not None:
+        return pa.list_(
+            pa.field("item", _pydantic_type_to_arrow_type(unwrapped, field), True)
+        )
+    return pa.list_(_pydantic_type_to_arrow_type(child, field))
+
+
+def _unwrap_optional_annotation(annotation: Any) -> Any | None:
+    if isinstance(annotation, (_GenericAlias, GenericAlias)):
+        origin = annotation.__origin__
+        args = annotation.__args__
+        if origin == Union:
+            non_none = [arg for arg in args if arg is not type(None)]
+            if len(non_none) == 1 and len(non_none) != len(args):
+                return non_none[0]
+    elif sys.version_info >= (3, 10) and isinstance(annotation, types.UnionType):
+        args = annotation.__args__
+        non_none = [arg for arg in args if arg is not type(None)]
+        if len(non_none) == 1 and len(non_none) != len(args):
+            return non_none[0]
+    return None
+
+
 def _pydantic_to_arrow_type(field: FieldInfo) -> pa.DataType:
    """Convert a Pydantic FieldInfo to Arrow DataType"""
+    unwrapped = _unwrap_optional_annotation(field.annotation)
+    if unwrapped is not None:
+        return _pydantic_type_to_arrow_type(unwrapped, field)
    if isinstance(field.annotation, (_GenericAlias, GenericAlias)):
        origin = field.annotation.__origin__
        args = field.annotation.__args__

        if origin is list:
            child = args[0]
-            return pa.list_(_py_type_to_arrow_type(child, field))
-        elif origin == Union:
-            if len(args) == 2 and args[1] is type(None):
-                return _pydantic_type_to_arrow_type(args[0], field)
-    elif sys.version_info >= (3, 10) and isinstance(field.annotation, types.UnionType):
-        args = field.annotation.__args__
-        if len(args) == 2:
-            for typ in args:
-                if typ is type(None):
-                    continue
-                return _py_type_to_arrow_type(typ, field)
+            return _pydantic_list_child_to_arrow(child, field)
    return _pydantic_type_to_arrow_type(field.annotation, field)


 def is_nullable(field: FieldInfo) -> bool:
    """Check if a Pydantic FieldInfo is nullable."""
+    if _unwrap_optional_annotation(field.annotation) is not None:
+        return True
    if isinstance(field.annotation, (_GenericAlias, GenericAlias)):
        origin = field.annotation.__origin__
        args = field.annotation.__args__
        if origin == Union:
-            if len(args) == 2 and args[1] is type(None):
+            if any(typ is type(None) for typ in args):
                return True
    elif sys.version_info >= (3, 10) and isinstance(field.annotation, types.UnionType):
        args = field.annotation.__args__
        for typ in args:
            if typ is type(None):
                return True
-    elif inspect.isclass(field.annotation) and issubclass(
-        field.annotation, FixedSizeListMixin
-    ):
-        return field.annotation.nullable()
+    elif inspect.isclass(field.annotation):
+        try:
+            if issubclass(field.annotation, FixedSizeListMixin):
+                return field.annotation.nullable()
+        except TypeError:
+            return False
    return False


@@ -961,27 +961,22 @@ class LanceQueryBuilder(ABC):
        >>> query = [100, 100]
        >>> plan = table.search(query).analyze_plan()
        >>> print(plan)  # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
-        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=[...],
+        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=[...],
                  preserve_partitioning=[...],
-                  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=...]
+                  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=...

        Returns
        -------
@@ -105,6 +105,253 @@ def test_optional_types_py310():
    assert schema == expect_schema


+@pytest.mark.skipif(
+    sys.version_info < (3, 10),
+    reason="using PEP 604 union types requires python3.10 or higher",
+)
+def test_optional_structs_py310():
+    class SplitInfo(pydantic.BaseModel):
+        start_frame: int
+        end_frame: int
+
+    class TestModel(pydantic.BaseModel):
+        id: str
+        split: SplitInfo | None = None
+
+    schema = pydantic_to_schema(TestModel)
+
+    expect_schema = pa.schema(
+        [
+            pa.field("id", pa.utf8(), False),
+            pa.field(
+                "split",
+                pa.struct(
+                    [
+                        pa.field("start_frame", pa.int64(), False),
+                        pa.field("end_frame", pa.int64(), False),
+                    ]
+                ),
+                True,
+            ),
+        ]
+    )
+    assert schema == expect_schema
+
+
+@pytest.mark.skipif(
+    sys.version_info < (3, 10),
+    reason="using PEP 604 union types requires python3.10 or higher",
+)
+def test_optional_struct_list_py310():
+    class SplitInfo(pydantic.BaseModel):
+        start_frame: int
+        end_frame: int
+
+    class TestModel(pydantic.BaseModel):
+        id: str
+        splits: list[SplitInfo] | None = None
+
+    schema = pydantic_to_schema(TestModel)
+
+    expect_schema = pa.schema(
+        [
+            pa.field("id", pa.utf8(), False),
+            pa.field(
+                "splits",
+                pa.list_(
+                    pa.struct(
+                        [
+                            pa.field("start_frame", pa.int64(), False),
+                            pa.field("end_frame", pa.int64(), False),
+                        ]
+                    )
+                ),
+                True,
+            ),
+        ]
+    )
+    assert schema == expect_schema
+
+
+@pytest.mark.skipif(
+    sys.version_info < (3, 9),
+    reason="using native type alias requires python3.9 or higher",
+)
+def test_nested_struct_list():
+    class SplitInfo(pydantic.BaseModel):
+        start_frame: int
+        end_frame: int
+
+    class TestModel(pydantic.BaseModel):
+        id: str
+        splits: list[SplitInfo]
+
+    schema = pydantic_to_schema(TestModel)
+
+    expect_schema = pa.schema(
+        [
+            pa.field("id", pa.utf8(), False),
+            pa.field(
+                "splits",
+                pa.list_(
+                    pa.struct(
+                        [
+                            pa.field("start_frame", pa.int64(), False),
+                            pa.field("end_frame", pa.int64(), False),
+                        ]
+                    )
+                ),
+                False,
+            ),
+        ]
+    )
+    assert schema == expect_schema
+
+
+@pytest.mark.skipif(
+    sys.version_info < (3, 9),
+    reason="using native type alias requires python3.9 or higher",
+)
+def test_nested_struct_list_optional():
+    class SplitInfo(pydantic.BaseModel):
+        start_frame: int
+        end_frame: int
+
+    class TestModel(pydantic.BaseModel):
+        id: str
+        splits: Optional[list[SplitInfo]] = None
+
+    schema = pydantic_to_schema(TestModel)
+
+    expect_schema = pa.schema(
+        [
+            pa.field("id", pa.utf8(), False),
+            pa.field(
+                "splits",
+                pa.list_(
+                    pa.struct(
+                        [
+                            pa.field("start_frame", pa.int64(), False),
+                            pa.field("end_frame", pa.int64(), False),
+                        ]
+                    )
+                ),
+                True,
+            ),
+        ]
+    )
+    assert schema == expect_schema
+
+
+def test_nested_struct_list_optional_items():
+    class SplitInfo(pydantic.BaseModel):
+        start_frame: int
+        end_frame: int
+
+    class TestModel(pydantic.BaseModel):
+        id: str
+        splits: list[Optional[SplitInfo]]
+
+    schema = pydantic_to_schema(TestModel)
+
+    expect_schema = pa.schema(
+        [
+            pa.field("id", pa.utf8(), False),
+            pa.field(
+                "splits",
+                pa.list_(
+                    pa.field(
+                        "item",
+                        pa.struct(
+                            [
+                                pa.field("start_frame", pa.int64(), False),
+                                pa.field("end_frame", pa.int64(), False),
+                            ]
+                        ),
+                        True,
+                    )
+                ),
+                False,
+            ),
+        ]
+    )
+    assert schema == expect_schema
+
+
+def test_nested_struct_list_optional_container_and_items():
+    class SplitInfo(pydantic.BaseModel):
+        start_frame: int
+        end_frame: int
+
+    class TestModel(pydantic.BaseModel):
+        id: str
+        splits: Optional[list[Optional[SplitInfo]]] = None
+
+    schema = pydantic_to_schema(TestModel)
+
+    expect_schema = pa.schema(
+        [
+            pa.field("id", pa.utf8(), False),
+            pa.field(
+                "splits",
+                pa.list_(
+                    pa.field(
+                        "item",
+                        pa.struct(
+                            [
+                                pa.field("start_frame", pa.int64(), False),
+                                pa.field("end_frame", pa.int64(), False),
+                            ]
+                        ),
+                        True,
+                    )
+                ),
+                True,
+            ),
+        ]
+    )
+    assert schema == expect_schema
+
+
+@pytest.mark.skipif(
+    sys.version_info < (3, 10),
+    reason="using PEP 604 union types requires python3.10 or higher",
+)
+def test_nested_struct_list_optional_items_pep604():
+    class SplitInfo(pydantic.BaseModel):
+        start_frame: int
+        end_frame: int
+
+    class TestModel(pydantic.BaseModel):
+        id: str
+        splits: list[SplitInfo | None]
+
+    schema = pydantic_to_schema(TestModel)
+
+    expect_schema = pa.schema(
+        [
+            pa.field("id", pa.utf8(), False),
+            pa.field(
+                "splits",
+                pa.list_(
+                    pa.field(
+                        "item",
+                        pa.struct(
+                            [
+                                pa.field("start_frame", pa.int64(), False),
+                                pa.field("end_frame", pa.int64(), False),
+                            ]
+                        ),
+                        True,
+                    )
+                ),
+                False,
+            ),
+        ]
+    )
+    assert schema == expect_schema
+
+
@pytest.mark.skipif(
    sys.version_info > (3, 8),
    reason="using native type alias requires python3.9 or higher",
@@ -601,6 +601,7 @@ def test_head():
 def test_query_sync_minimal():
    def handler(body):
        assert body == {
+            "distance_type": "l2",
            "k": 10,
            "prefilter": True,
            "refine_factor": None,
@@ -684,6 +685,7 @@ 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,
@@ -713,6 +715,7 @@ 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,
@@ -835,6 +838,7 @@ def test_query_sync_hybrid():
        else:
            # Vector query
            assert body == {
+                "distance_type": "l2",
                "k": 42,
                "prefilter": True,
                "refine_factor": None,
@@ -1880,13 +1880,8 @@ async def test_optimize_delete_unverified(tmp_db_async: AsyncConnection, tmp_pat
        ],
    )
    version = await table.version()
-    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"
+    path = tmp_path / "test.lance" / "_versions" / f"{version - 1}.manifest"
    os.remove(path)
-
    stats = await table.optimize(delete_unverified=False)
    assert stats.prune.old_versions_removed == 0
    stats = await table.optimize(
@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.24.0"
+version = "0.24.1"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true
@@ -892,6 +892,7 @@ pub struct ConnectBuilder {
    embedding_registry: Option<Arc<dyn EmbeddingRegistry>>,
 }

+#[cfg(feature = "remote")]
 const ENV_VARS_TO_STORAGE_OPTS: [(&str, &str); 1] =
    [("AZURE_STORAGE_ACCOUNT_NAME", "azure_storage_account_name")];

@@ -1,14 +1,22 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors

-use std::{collections::HashMap, sync::Arc};
+use std::{
+    collections::HashMap,
+    sync::{Arc, Mutex},
+};

 use datafusion::prelude::{SessionConfig, SessionContext};
+use datafusion_catalog::streaming::StreamingTable;
+use datafusion_common::DataFusionError;
 use datafusion_execution::{disk_manager::DiskManagerBuilder, runtime_env::RuntimeEnvBuilder};
 use datafusion_expr::col;
+use datafusion_physical_plan::{
+    stream::RecordBatchStreamAdapter, streaming::PartitionStream,
+    SendableRecordBatchStream as DataFusionRecordBatchStream,
+};
 use futures::TryStreamExt;
 use lance_core::ROW_ID;
-use lance_datafusion::exec::SessionContextExt;

 use crate::{
    arrow::{SendableRecordBatchStream, SendableRecordBatchStreamExt, SimpleRecordBatchStream},
@@ -27,6 +35,51 @@ pub const SRC_ROW_ID_COL: &str = "row_id";

 pub const SPLIT_NAMES_CONFIG_KEY: &str = "split_names";

+pub const DEFAULT_MEMORY_LIMIT: usize = 100 * 1024 * 1024;
+
+struct OneShotPartitionStream {
+    schema: arrow_schema::SchemaRef,
+    stream: Mutex<Option<DataFusionRecordBatchStream>>,
+}
+
+impl OneShotPartitionStream {
+    fn new(schema: arrow_schema::SchemaRef, stream: DataFusionRecordBatchStream) -> Self {
+        Self {
+            schema,
+            stream: Mutex::new(Some(stream)),
+        }
+    }
+}
+
+impl PartitionStream for OneShotPartitionStream {
+    fn schema(&self) -> &arrow_schema::SchemaRef {
+        &self.schema
+    }
+
+    fn execute(&self, _ctx: Arc<datafusion_execution::TaskContext>) -> DataFusionRecordBatchStream {
+        self.stream
+            .lock()
+            .ok()
+            .and_then(|mut stream| stream.take())
+            .unwrap_or_else(|| {
+                Box::pin(RecordBatchStreamAdapter::new(
+                    Arc::clone(&self.schema),
+                    futures::stream::empty::<
+                        std::result::Result<arrow_array::RecordBatch, DataFusionError>,
+                    >(),
+                ))
+            })
+    }
+}
+
+impl std::fmt::Debug for OneShotPartitionStream {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        f.debug_struct("OneShotPartitionStream")
+            .field("schema", &self.schema)
+            .finish()
+    }
+}
+
 /// Where to store the permutation table
 #[derive(Debug, Clone, Default)]
 enum PermutationDestination {
@@ -167,10 +220,20 @@ impl PermutationBuilder {
        &self,
        data: SendableRecordBatchStream,
    ) -> Result<SendableRecordBatchStream> {
+        let memory_limit = std::env::var("LANCEDB_PERM_BUILDER_MEMORY_LIMIT")
+            .unwrap_or_else(|_| DEFAULT_MEMORY_LIMIT.to_string())
+            .parse::<usize>()
+            .unwrap_or_else(|_| {
+                log::error!(
+                    "Failed to parse LANCEDB_PERM_BUILDER_MEMORY_LIMIT, using default: {}",
+                    DEFAULT_MEMORY_LIMIT
+                );
+                DEFAULT_MEMORY_LIMIT
+            });
        let ctx = SessionContext::new_with_config_rt(
            SessionConfig::default(),
            RuntimeEnvBuilder::new()
-                .with_memory_limit(100 * 1024 * 1024, 1.0)
+                .with_memory_limit(memory_limit, 1.0)
                .with_disk_manager_builder(
                    DiskManagerBuilder::default()
                        .with_mode(self.config.temp_dir.to_disk_manager_mode()),
@@ -178,12 +241,17 @@ impl PermutationBuilder {
                .build_arc()
                .unwrap(),
        );
-        let df = ctx
-            .read_one_shot(data.into_df_stream())
-            .map_err(|e| Error::Other {
-                message: format!("Failed to setup sort by split id: {}", e),
-                source: Some(e.into()),
-            })?;
+        let df_stream = data.into_df_stream();
+        let schema = df_stream.schema();
+        let partition = Arc::new(OneShotPartitionStream::new(schema.clone(), df_stream));
+        let table = StreamingTable::try_new(schema, vec![partition]).map_err(|e| Error::Other {
+            message: format!("Failed to create streaming table: {}", e),
+            source: Some(e.into()),
+        })?;
+        let df = ctx.read_table(Arc::new(table)).map_err(|e| Error::Other {
+            message: format!("Failed to setup sort by split id: {}", e),
+            source: Some(e.into()),
+        })?;
        let df_stream = df
            .sort_by(vec![col(SPLIT_ID_COLUMN)])
            .map_err(|e| Error::Other {
@@ -171,7 +171,7 @@ impl Shuffler {
            // This is kind of an annoying limitation but if we allow runt clumps from batches then
            // clumps will get unaligned and we will mess up the clumps when we do the in-memory
            // shuffle step.  If this is a problem we can probably figure out a better way to do this.
-            if !is_last && batch.num_rows() as u64 % clump_size != 0 {
+            if !is_last && !(batch.num_rows() as u64).is_multiple_of(clump_size) {
                return Err(Error::Runtime {
                    message: format!(
                        "Expected batch size ({}) to be divisible by clump size ({})",
@@ -1,12 +1,9 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors

-use std::{
-    iter,
-    sync::{
-        atomic::{AtomicBool, AtomicU64, AtomicUsize, Ordering},
-        Arc,
-    },
+use std::sync::{
+    atomic::{AtomicBool, AtomicU64, AtomicUsize, Ordering},
+    Arc,
 };

 use arrow_array::{Array, BooleanArray, RecordBatch, UInt64Array};
@@ -158,7 +155,7 @@ impl Splitter {
                remaining_in_split
            };

-            split_ids.extend(iter::repeat(split_id as u64).take(rows_to_add as usize));
+            split_ids.extend(std::iter::repeat_n(split_id as u64, rows_to_add as usize));
            if done {
                // Quit early if we've run out of splits
                break;
@@ -662,7 +659,7 @@ mod tests {
        assert_eq!(split_batch.num_rows(), total_split_sizes as usize);
        let mut expected = Vec::with_capacity(total_split_sizes as usize);
        for (i, size) in expected_split_sizes.iter().enumerate() {
-            expected.extend(iter::repeat(i as u64).take(*size as usize));
+            expected.extend(std::iter::repeat_n(i as u64, *size as usize));
        }
        let expected = Arc::new(UInt64Array::from(expected)) as Arc<dyn Array>;

@@ -297,10 +297,10 @@ impl IvfPqIndexBuilder {
 }

 pub(crate) fn suggested_num_sub_vectors(dim: u32) -> u32 {
-    if dim % 16 == 0 {
+    if dim.is_multiple_of(16) {
        // Should be more aggressive than this default.
        dim / 16
-    } else if dim % 8 == 0 {
+    } else if dim.is_multiple_of(8) {
        dim / 8
    } else {
        log::warn!(
@@ -468,9 +468,7 @@ impl<S: HttpSend> RemoteTable<S> {
        self.apply_query_params(&mut body, &query.base)?;

        // Apply general parameters, before we dispatch based on number of query vectors.
-        if let Some(distance_type) = query.distance_type {
-            body["distance_type"] = serde_json::json!(distance_type);
-        }
+        body["distance_type"] = serde_json::json!(query.distance_type.unwrap_or_default());
        // In 0.23.1 we migrated from `nprobes` to `minimum_nprobes` and `maximum_nprobes`.
        // Old client / new server: since minimum_nprobes is missing, fallback to nprobes
        // New client / old server: old server will only see nprobes, make sure to set both
@@ -2232,6 +2230,7 @@ mod tests {
            let body: serde_json::Value = serde_json::from_slice(body).unwrap();
            let mut expected_body = serde_json::json!({
                "prefilter": true,
+                "distance_type": "l2",
                "nprobes": 20,
                "minimum_nprobes": 20,
                "maximum_nprobes": 20,
@@ -1425,8 +1425,9 @@ impl Table {
            })
            .collect::<Vec<_>>();

-        let unioned = UnionExec::try_new(projected_plans).map_err(|err| Error::Runtime {
-            message: err.to_string(),
+        let unioned = UnionExec::try_new(projected_plans).map_err(|e| Error::Other {
+            message: format!("Failed to union query plans: {}", e),
+            source: Some(e.into()),
        })?;
        // We require 1 partition in the final output
        let repartitioned = RepartitionExec::try_new(
@@ -2061,7 +2062,7 @@ impl NativeTable {
            return provided;
        }
        let suggested = suggested_num_sub_vectors(dim);
-        if num_bits.is_some_and(|num_bits| num_bits == 4) && suggested % 2 != 0 {
+        if num_bits.is_some_and(|num_bits| num_bits == 4) && !suggested.is_multiple_of(2) {
            // num_sub_vectors must be even when 4 bits are used
            suggested + 1
        } else {
@@ -3402,7 +3403,6 @@ pub struct FragmentSummaryStats {
 #[cfg(test)]
 #[allow(deprecated)]
 mod tests {
-    use std::iter;
    use std::sync::atomic::{AtomicBool, Ordering};
    use std::sync::Arc;
    use std::time::Duration;
@@ -4019,7 +4019,7 @@ mod tests {
                schema.clone(),
                vec![
                    Arc::new(Int32Array::from_iter_values(offset..(offset + 10))),
-                    Arc::new(Int32Array::from_iter_values(iter::repeat(age).take(10))),
+                    Arc::new(Int32Array::from_iter_values(std::iter::repeat_n(age, 10))),
                ],
            )],
            schema,
@@ -100,8 +100,8 @@ impl DatasetRef {
                let should_checkout = match &target_ref {
                    refs::Ref::Version(_, Some(target_ver)) => version != target_ver,
                    refs::Ref::Version(_, None) => true, // No specific version, always checkout
+                    refs::Ref::Tag(_) => true,           // Always checkout for tags
                    refs::Ref::VersionNumber(target_ver) => version != target_ver,
-                    refs::Ref::Tag(_) => true, // Always checkout for tags
                };

                if should_checkout {
@@ -4,7 +4,6 @@
 use std::{
    borrow::Cow,
    collections::{HashMap, HashSet},
-    iter::repeat,
    sync::Arc,
 };

@@ -268,9 +267,10 @@ fn create_some_records() -> Result<impl IntoArrow> {
            schema.clone(),
            vec![
                Arc::new(Int32Array::from_iter_values(0..TOTAL as i32)),
-                Arc::new(StringArray::from_iter(
-                    repeat(Some("hello world".to_string())).take(TOTAL),
-                )),
+                Arc::new(StringArray::from_iter(std::iter::repeat_n(
+                    Some("hello world".to_string()),
+                    TOTAL,
+                ))),
            ],
        )
        .unwrap()]
Author	SHA1	Message	Date
lancedb automation	054d09abe9	chore: update lance dependency to v2.0.0-rc.4	2026-01-29 16:22:24 +00:00
Lei Xu	ad51e2dd1f	fix: support pydantic list of structs or optional struct (#2953 ) Closes #2950 This code is generated by codex-gpt5.2	2026-01-28 21:08:18 -08:00
Weston Pace	e9e904783c	feat: allow the permutation builder memory limit to be configured by env var (#2946 ) Running into issues with DF sorting again. This will at least allow the memory limit to be set large to bypass problems.	2026-01-28 09:02:59 +05:30
Lance Release	8500b16eca	Bump version: 0.24.1-beta.0 → 0.24.1	2026-01-26 23:39:18 +00:00
Lance Release	57e7282342	Bump version: 0.24.0 → 0.24.1-beta.0	2026-01-26 23:38:50 +00:00
Lance Release	cc5f8070d7	Bump version: 0.27.1-beta.0 → 0.27.1	2026-01-26 23:38:24 +00:00
Lance Release	dc0fb01f6b	Bump version: 0.27.0 → 0.27.1-beta.0	2026-01-26 23:38:23 +00:00
LanceDB Robot	94b7781551	feat: update lance dependency to v1.0.4 (#2944 ) ## Summary - bump Lance dependencies to v1.0.4 - run `cargo clippy --workspace --tests --all-features -- -D warnings` - run `cargo fmt --all` ## Testing - `cargo clippy --workspace --tests --all-features -- -D warnings` ## Reference - https://github.com/lance-format/lance/releases/tag/v1.0.4	2026-01-26 15:37:28 -08:00
Jack Ye	7bf020b3d5	chore: fix clippy when remote flag is not set (#2943 ) Also add a step in CI to ensure this does not happen in the future	2026-01-26 13:59:31 -08:00
LanceDB Robot	12a98479dc	chore: update lance dependency to v1.0.4-rc.1 (#2942 ) ## Summary - bump Lance dependencies to v1.0.4-rc.1 - verified `cargo clippy --workspace --tests --all-features -- -D warnings` - ran `cargo fmt --all` ## References - https://github.com/lance-format/lance/releases/tag/v1.0.4-rc.1	2026-01-26 12:17:22 -08:00
Jack Ye	e4552e577a	chore(revert): revert update lance dependency to v2.0.0-rc.1 (#2936 ) (#2941 ) This reverts commit `bd84bba14d`, so that we can bump version to 1.0.4-rc.1	2026-01-26 11:13:59 -08:00
Will Jones	f979a902ad	ci(rust): fix MSRV check (#2940 ) Realized our MSRV check was inert because `rust-toolchain.toml` was overriding the Rust version. We set the `RUSTUP_TOOLCHAIN` environment variable, which overrides that. Also needed to update to MSRV 1.88 (due to dependencies like Lance and DataFusion) and fix some clippy warnings.	2026-01-23 15:57:09 -08:00