rename gha task

The permutation table was always intended to be a small table of row id
pointers (and split id). However, it was accidentally doing a full
materialization of the base table 🤦

This PR changes the permutation builder to only store row id and split
id.

.bumpversion.toml

@@ -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*)\\.

.github/workflows/build_linux_wheel/action.yml

@@ -3,7 +3,7 @@ name: build-linux-wheel
 description: "Build a manylinux wheel for lance"
 inputs:
   python-minor-version:
-    description: "8, 9, 10, 11, 12"
+    description: "10, 11, 12, 13"
     required: true
   args:
     description: "--release"

.github/workflows/build_mac_wheel/action.yml

@@ -3,7 +3,7 @@ name: build_wheel
 description: "Build a lance wheel"
 inputs:
   python-minor-version:
-    description: "8, 9, 10, 11"
+    description: "10, 11, 12, 13"
     required: true
   args:
     description: "--release"

.github/workflows/build_windows_wheel/action.yml

@@ -3,7 +3,7 @@ name: build_wheel
 description: "Build a lance wheel"
 inputs:
   python-minor-version:
-    description: "8, 9, 10, 11"
+    description: "10, 11, 12, 13, 14"
     required: true
   args:
     description: "--release"

.github/workflows/docs.yml

@@ -41,7 +41,7 @@ jobs:
           sudo apt install -y protobuf-compiler libssl-dev
           rustup update && rustup default
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: "3.10"
           cache: "pip"

.github/workflows/pypi-publish.yml

@@ -44,12 +44,12 @@ jobs:
           fetch-depth: 0
           lfs: true
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
-          python-version: 3.8
+          python-version: "3.10"
       - uses: ./.github/workflows/build_linux_wheel
         with:
-          python-minor-version: 8
+          python-minor-version: 10
           args: "--release --strip ${{ matrix.config.extra_args }}"
           arm-build: ${{ matrix.config.platform == 'aarch64' }}
           manylinux: ${{ matrix.config.manylinux }}
@@ -74,12 +74,12 @@ jobs:
           fetch-depth: 0
           lfs: true
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
-          python-version: 3.12
+          python-version: "3.13"
       - uses: ./.github/workflows/build_mac_wheel
         with:
-          python-minor-version: 8
+          python-minor-version: 10
           args: "--release --strip --target ${{ matrix.config.target }} --features fp16kernels"
       - uses: ./.github/workflows/upload_wheel
         if: startsWith(github.ref, 'refs/tags/python-v')
@@ -95,12 +95,12 @@ jobs:
           fetch-depth: 0
           lfs: true
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
-          python-version: 3.12
+          python-version: "3.13"
       - uses: ./.github/workflows/build_windows_wheel
         with:
-          python-minor-version: 8
+          python-minor-version: 10
           args: "--release --strip"
           vcpkg_token: ${{ secrets.VCPKG_GITHUB_PACKAGES }}
       - uses: ./.github/workflows/upload_wheel

.github/workflows/python.yml

@@ -25,7 +25,7 @@ jobs:
   lint:
     name: "Lint"
     timeout-minutes: 30
-    runs-on: "ubuntu-22.04"
+    runs-on: "ubuntu-24.04"
     defaults:
       run:
         shell: bash
@@ -36,9 +36,9 @@ jobs:
           fetch-depth: 0
           lfs: true
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
-          python-version: "3.12"
+          python-version: "3.13"
       - name: Install ruff
         run: |
           pip install ruff==0.9.9
@@ -61,9 +61,9 @@ jobs:
           fetch-depth: 0
           lfs: true
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
-          python-version: "3.12"
+          python-version: "3.13"
       - name: Install protobuf compiler
         run: |
           sudo apt update
@@ -90,9 +90,9 @@ jobs:
           fetch-depth: 0
           lfs: true
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
-          python-version: "3.12"
+          python-version: "3.13"
           cache: "pip"
       - name: Install protobuf
         run: |
@@ -110,7 +110,7 @@ jobs:
     timeout-minutes: 30
     strategy:
       matrix:
-        python-minor-version: ["9", "12"]
+        python-minor-version: ["10", "13"]
     runs-on: "ubuntu-24.04"
     defaults:
       run:
@@ -126,7 +126,7 @@ jobs:
           sudo apt update
           sudo apt install -y protobuf-compiler
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: 3.${{ matrix.python-minor-version }}
       - uses: ./.github/workflows/build_linux_wheel
@@ -156,9 +156,9 @@ jobs:
           fetch-depth: 0
           lfs: true
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
-          python-version: "3.12"
+          python-version: "3.13"
       - uses: ./.github/workflows/build_mac_wheel
         with:
           args: --profile ci
@@ -185,9 +185,9 @@ jobs:
           fetch-depth: 0
           lfs: true
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
-          python-version: "3.12"
+          python-version: "3.13"
       - uses: ./.github/workflows/build_windows_wheel
         with:
           args: --profile ci
@@ -195,7 +195,7 @@ jobs:
       # Make sure wheels are not included in the Rust cache
       - name: Delete wheels
         run: rm -rf target/wheels
-  pydantic1x:
+  min-deps:
     timeout-minutes: 30
     runs-on: "ubuntu-24.04"
     defaults:
@@ -212,12 +212,11 @@ jobs:
           sudo apt update
           sudo apt install -y protobuf-compiler
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
-          python-version: 3.9
+          python-version: "3.10"
       - name: Install lancedb
         run: |
-          pip install "pydantic<2"
           pip install pyarrow==16
           pip install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests]
           pip install tantivy

Cargo.lock

@@ -4971,7 +4971,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb"
-version = "0.24.0"
+version = "0.24.1"
 dependencies = [
  "ahash",
  "anyhow",
@@ -5050,7 +5050,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-nodejs"
-version = "0.24.0"
+version = "0.24.1"
 dependencies = [
  "arrow-array",
  "arrow-ipc",
@@ -5070,7 +5070,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-python"
-version = "0.27.0"
+version = "0.27.1"
 dependencies = [
  "arrow",
  "async-trait",

docs/src/java/java.md

@@ -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>
 ```
 

java/lancedb-core/pom.xml

@@ -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>
 

java/pom.xml

@@ -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>

nodejs/Cargo.toml

@@ -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

nodejs/npm/darwin-arm64/package.json

@@ -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",

nodejs/npm/darwin-x64/package.json

@@ -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",

nodejs/npm/linux-arm64-gnu/package.json

@@ -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",

nodejs/npm/linux-arm64-musl/package.json

@@ -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",

nodejs/npm/linux-x64-gnu/package.json

@@ -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",

nodejs/npm/linux-x64-musl/package.json

@@ -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",

nodejs/npm/win32-arm64-msvc/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.24.0",
+  "version": "0.24.1",
   "os": [
     "win32"
   ],

nodejs/npm/win32-x64-msvc/package.json

@@ -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",

nodejs/package-lock.json

@@ -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"

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.24.0",
+  "version": "0.24.1",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",

python/CONTRIBUTING.md

@@ -16,7 +16,7 @@ The Python package is a wrapper around the Rust library, `lancedb`. We use
 
 To set up your development environment, you will need to install the following:
 
-1. Python 3.9 or later
+1. Python 3.10 or later
 2. Cargo (Rust's package manager). Use [rustup](https://rustup.rs/) to install.
 3. [protoc](https://grpc.io/docs/protoc-installation/) (Protocol Buffers compiler)
 

python/Cargo.toml

@@ -21,7 +21,7 @@ lance-core.workspace = true
 lance-namespace.workspace = true
 lance-io.workspace = true
 env_logger.workspace = true
-pyo3 = { version = "0.25", features = ["extension-module", "abi3-py39"] }
+pyo3 = { version = "0.25", features = ["extension-module", "abi3-py310"] }
 pyo3-async-runtimes = { version = "0.25", features = [
     "attributes",
     "tokio-runtime",
@@ -34,7 +34,7 @@ tokio = { version = "1.40", features = ["sync"] }
 [build-dependencies]
 pyo3-build-config = { version = "0.25", features = [
     "extension-module",
-    "abi3-py39",
+    "abi3-py310",
 ] }
 
 [features]

python/pyproject.toml

@@ -8,7 +8,7 @@ dependencies = [
     "overrides>=0.7; python_version<'3.12'",
     "packaging",
     "pyarrow>=16",
-    "pydantic>=1.10",
+    "pydantic>=2",
     "tqdm>=4.27.0",
     "lance-namespace>=0.3.2"
 ]
@@ -16,7 +16,7 @@ description = "lancedb"
 authors = [{ name = "LanceDB Devs", email = "dev@lancedb.com" }]
 license = { file = "LICENSE" }
 readme = "README.md"
-requires-python = ">=3.9"
+requires-python = ">=3.10"
 keywords = [
     "data-format",
     "data-science",
@@ -33,10 +33,10 @@ classifiers = [
     "Programming Language :: Python",
     "Programming Language :: Python :: 3",
     "Programming Language :: Python :: 3 :: Only",
-    "Programming Language :: Python :: 3.9",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
     "Topic :: Scientific/Engineering",
 ]
 
@@ -137,4 +137,4 @@ include = [
     "python/lancedb/_lancedb.pyi",
 ]
 exclude = ["python/tests/"]
-pythonVersion = "3.12"
+pythonVersion = "3.13"

python/python/lancedb/pydantic.py

@@ -6,7 +6,6 @@
 from __future__ import annotations
 
 import inspect
-import sys
 import types
 from abc import ABC, abstractmethod
 from datetime import date, datetime
@@ -141,14 +140,6 @@ def Vector(
                 raise TypeError("A list of numbers or numpy.ndarray is needed")
             return cls(v)
 
-        if PYDANTIC_VERSION.major < 2:
-
-            @classmethod
-            def __modify_schema__(cls, field_schema: Dict[str, Any]):
-                field_schema["items"] = {"type": "number"}
-                field_schema["maxItems"] = dim
-                field_schema["minItems"] = dim
-
     return FixedSizeList
 
 
@@ -226,26 +217,14 @@ def MultiVector(
         def __get_validators__(cls) -> Generator[Callable, None, None]:
             yield cls.validate
 
-        # For pydantic v1
         @classmethod
-        def validate(cls, v):
+        def __modify_schema__(cls, field_schema: Dict[str, Any]):
-            if not isinstance(v, (list, range)):
+            field_schema["items"] = {
-                raise TypeError("A list of vectors is needed")
+                "type": "array",
-            for vec in v:
+                "items": {"type": "number"},
-                if not isinstance(vec, (list, range, np.ndarray)) or len(vec) != dim:
+                "minItems": dim,
-                    raise TypeError(f"Each vector must be a list of {dim} numbers")
+                "maxItems": dim,
-            return cls(v)
+            }
-
-        if PYDANTIC_VERSION.major < 2:
-
-            @classmethod
-            def __modify_schema__(cls, field_schema: Dict[str, Any]):
-                field_schema["items"] = {
-                    "type": "array",
-                    "items": {"type": "number"},
-                    "minItems": dim,
-                    "maxItems": dim,
-                }
 
     return MultiVectorList
 
@@ -275,35 +254,31 @@ 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}."
     )
 
 
-if PYDANTIC_VERSION.major < 2:
+def _pydantic_model_to_fields(model: pydantic.BaseModel) -> List[pa.Field]:
-
+    return [
-    def _pydantic_model_to_fields(model: pydantic.BaseModel) -> List[pa.Field]:
+        _pydantic_to_field(name, field) for name, field in model.model_fields.items()
-        return [
+    ]
-            _pydantic_to_field(name, field) for name, field in model.__fields__.items()
-        ]
-
-else:
-
-    def _pydantic_model_to_fields(model: pydantic.BaseModel) -> List[pa.Field]:
-        return [
-            _pydantic_to_field(name, field)
-            for name, field in model.model_fields.items()
-        ]
 
 
 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 +286,67 @@ 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 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))
+            return _pydantic_list_child_to_arrow(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_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):
+    elif 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(
+    elif inspect.isclass(field.annotation):
-        field.annotation, FixedSizeListMixin
+        try:
-    ):
+            if issubclass(field.annotation, FixedSizeListMixin):
-        return field.annotation.nullable()
+                return field.annotation.nullable()
+        except TypeError:
+            return False
     return False
 
 
@@ -446,8 +443,6 @@ class LanceModel(pydantic.BaseModel):
 
     @classmethod
     def safe_get_fields(cls):
-        if PYDANTIC_VERSION.major < 2:
-            return cls.__fields__
         return cls.model_fields
 
     @classmethod
@@ -490,18 +485,8 @@ def get_extras(field_info: FieldInfo, key: str) -> Any:
     return (field_info.field_info.extra or {}).get("json_schema_extra", {}).get(key)
 
 
-if PYDANTIC_VERSION.major < 2:
+def model_to_dict(model: pydantic.BaseModel) -> Dict[str, Any]:
-
+    """
-    def model_to_dict(model: pydantic.BaseModel) -> Dict[str, Any]:
+    Convert a Pydantic model to a dictionary.
-        """
+    """
-        Convert a Pydantic model to a dictionary.
+    return model.model_dump()
-        """
-        return model.dict()
-
-else:
-
-    def model_to_dict(model: pydantic.BaseModel) -> Dict[str, Any]:
-        """
-        Convert a Pydantic model to a dictionary.
-        """
-        return model.model_dump()

python/python/tests/test_pydantic.py

@@ -2,7 +2,6 @@
 # SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
 import json
-import sys
 from datetime import date, datetime
 from typing import List, Optional, Tuple
 
@@ -20,10 +19,6 @@ from pydantic import BaseModel
 from pydantic import Field
 
 
-@pytest.mark.skipif(
-    sys.version_info < (3, 9),
-    reason="using native type alias requires python3.9 or higher",
-)
 def test_pydantic_to_arrow():
     class StructModel(pydantic.BaseModel):
         a: str
@@ -83,10 +78,6 @@ def test_pydantic_to_arrow():
     assert schema == expect_schema
 
 
-@pytest.mark.skipif(
-    sys.version_info < (3, 10),
-    reason="using | type syntax requires python3.10 or higher",
-)
 def test_optional_types_py310():
     class TestModel(pydantic.BaseModel):
         a: str | None
@@ -105,10 +96,233 @@ def test_optional_types_py310():
     assert schema == expect_schema
 
 
-@pytest.mark.skipif(
+def test_optional_structs():
-    sys.version_info > (3, 8),
+    class SplitInfo(pydantic.BaseModel):
-    reason="using native type alias requires python3.9 or higher",
+        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
+
+
+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
+
+
+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
+
+
+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
+
+
+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
+
+
 def test_pydantic_to_arrow_py38():
     class StructModel(pydantic.BaseModel):
         a: str

rust/lancedb/Cargo.toml

@@ -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

rust/lancedb/src/dataloader/permutation/builder.rs

@@ -19,7 +19,7 @@ use crate::{
         split::{SplitStrategy, Splitter, SPLIT_ID_COLUMN},
         util::{rename_column, TemporaryDirectory},
     },
-    query::{ExecutableQuery, QueryBase},
+    query::{ExecutableQuery, QueryBase, Select},
     Error, Result, Table,
 };
 
@@ -27,6 +27,8 @@ 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;
+
 /// Where to store the permutation table
 #[derive(Debug, Clone, Default)]
 enum PermutationDestination {
@@ -167,10 +169,20 @@ 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()),
@@ -232,7 +244,7 @@ impl PermutationBuilder {
     /// Builds the permutation table and stores it in the given database.
     pub async fn build(self) -> Result<Table> {
         // First pass, apply filter and load row ids
-        let mut rows = self.base_table.query().with_row_id();
+        let mut rows = self.base_table.query().select(Select::columns(&[ROW_ID]));
 
         if let Some(filter) = &self.config.filter {
             rows = rows.only_if(filter);
@@ -321,6 +333,47 @@ mod tests {
 
     use super::*;
 
+    #[tokio::test]
+    async fn test_permutation_table_only_stores_row_id_and_split_id() {
+        let temp_dir = tempfile::tempdir().unwrap();
+
+        let db = connect(temp_dir.path().to_str().unwrap())
+            .execute()
+            .await
+            .unwrap();
+
+        let initial_data = lance_datagen::gen_batch()
+            .col("col_a", lance_datagen::array::step::<Int32Type>())
+            .col("col_b", lance_datagen::array::step::<Int32Type>())
+            .into_ldb_stream(RowCount::from(100), BatchCount::from(10));
+        let data_table = db
+            .create_table_streaming("base_tbl", initial_data)
+            .execute()
+            .await
+            .unwrap();
+
+        let permutation_table = PermutationBuilder::new(data_table.clone())
+            .with_split_strategy(
+                SplitStrategy::Sequential {
+                    sizes: SplitSizes::Percentages(vec![0.5, 0.5]),
+                },
+                None,
+            )
+            .with_filter("col_a > 57".to_string())
+            .build()
+            .await
+            .unwrap();
+
+        let schema = permutation_table.schema().await.unwrap();
+        let field_names: Vec<&str> = schema.fields().iter().map(|f| f.name().as_str()).collect();
+        assert_eq!(
+            field_names,
+            vec!["row_id", "split_id"],
+            "Permutation table should only contain row_id and split_id columns, but found: {:?}",
+            field_names,
+        );
+    }
+
     #[tokio::test]
     async fn test_permutation_builder() {
         let temp_dir = tempfile::tempdir().unwrap();
@@ -352,8 +405,6 @@ mod tests {
             .await
             .unwrap();
 
-        println!("permutation_table: {:?}", permutation_table);
-
         // Potentially brittle seed-dependent values below
         assert_eq!(permutation_table.count_rows(None).await.unwrap(), 330);
         assert_eq!(