Bump version: 0.27.1 → 0.28.0-beta.0

## Summary

- PR #2957 changed the permutation builder to only select `_rowid` from
the base table, but `Splitter::project()` for hash and calculated splits
replaced the selection entirely, dropping `_rowid`.
- Include `_rowid` in the column selections for hash and calculated
split projections.
- Fix a Python test that queried the permutation table for base table
columns no longer materialized.

Fixes the `test_split_hash`, `test_split_hash_with_discard`,
`test_split_calculated`, `test_shuffle_combined_with_splits`, and
`test_filter_with_splits` failures in `test_permutation.py`.

## Test plan

- [x] `cargo test -p lancedb -- permutation` (22 passed)
- [x] `pytest python/tests/test_permutation.py` (46 passed)
- [x] `npm test __test__/permutation.test.ts` (20 passed)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

---------

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>

.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

@@ -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
@@ -212,9 +212,9 @@ 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"

README.md

@@ -66,7 +66,7 @@ Follow the [Quickstart](https://lancedb.com/docs/quickstart/) doc to set up Lanc
 | Python SDK | https://lancedb.github.io/lancedb/python/python/ |
 | Typescript SDK | https://lancedb.github.io/lancedb/js/globals/ |
 | Rust SDK | https://docs.rs/lancedb/latest/lancedb/index.html |
-| REST API | https://docs.lancedb.com/api-reference/introduction |
+| REST API | https://docs.lancedb.com/api-reference/rest |
 
 ## **Join Us and Contribute**
 

docs/src/embeddings/available_embedding_models/text_embedding_functions/voyageai_embedding.md

@@ -0,0 +1,62 @@
+# VoyageAI Embeddings
+
+Voyage AI provides cutting-edge embedding and rerankers.
+
+
+Using voyageai API requires voyageai package, which can be installed using `pip install voyageai`. Voyage AI embeddings are used to generate embeddings for text data. The embeddings can be used for various tasks like semantic search, clustering, and classification.
+You also need to set the `VOYAGE_API_KEY` environment variable to use the VoyageAI API.
+
+Supported models are:
+
+**Voyage-4 Series (Latest)**
+
+- voyage-4 (1024 dims, general-purpose and multilingual retrieval, 320K batch tokens)
+- voyage-4-lite (1024 dims, optimized for latency and cost, 1M batch tokens)
+- voyage-4-large (1024 dims, best retrieval quality, 120K batch tokens)
+
+**Voyage-3 Series**
+
+- voyage-3
+- voyage-3-lite
+
+**Domain-Specific Models**
+
+- voyage-finance-2
+- voyage-multilingual-2
+- voyage-law-2
+- voyage-code-2
+
+
+Supported parameters (to be passed in `create` method) are:
+
+| Parameter | Type | Default Value | Description |
+|---|---|--------|---------|
+| `name` | `str` | `None` | The model ID of the model to use. Supported base models for Text Embeddings: voyage-4, voyage-4-lite, voyage-4-large, voyage-3, voyage-3-lite, voyage-finance-2, voyage-multilingual-2, voyage-law-2, voyage-code-2 |
+| `input_type` | `str` | `None` | Type of the input text. Default to None. Other options: query, document. |
+| `truncation` | `bool` | `True` | Whether to truncate the input texts to fit within the context length. |
+
+
+Usage Example:
+    
+```python
+    import lancedb
+    from lancedb.pydantic import LanceModel, Vector
+    from lancedb.embeddings import EmbeddingFunctionRegistry
+
+    voyageai = EmbeddingFunctionRegistry
+        .get_instance()
+        .get("voyageai")
+        .create(name="voyage-3")
+
+    class TextModel(LanceModel):
+        text: str = voyageai.SourceField()
+        vector: Vector(voyageai.ndims()) =  voyageai.VectorField()
+
+    data = [ { "text": "hello world" },
+            { "text": "goodbye world" }]
+
+    db = lancedb.connect("~/.lancedb")
+    tbl = db.create_table("test", schema=TextModel, mode="overwrite")
+
+    tbl.add(data)
+```

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>1.0.0-rc.2</lance-core.version>
+        <lance-core.version>1.0.4</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/lancedb/table.ts

@@ -538,35 +538,6 @@ export abstract class Table {
    *
    */
   abstract stats(): Promise<TableStatistics>;
-
-  /**
-   * Get the initial storage options that were passed in when opening this table.
-   *
-   * For dynamically refreshed options (e.g., credential vending), use
-   * {@link Table.latestStorageOptions}.
-   *
-   * Warning: This is an internal API and the return value is subject to change.
-   *
-   * @returns The storage options, or undefined if no storage options were configured.
-   */
-  abstract initialStorageOptions(): Promise<
-    Record<string, string> | null | undefined
-  >;
-
-  /**
-   * Get the latest storage options, refreshing from provider if configured.
-   *
-   * This method is useful for credential vending scenarios where storage options
-   * may be refreshed dynamically. If no dynamic provider is configured, this
-   * returns the initial static options.
-   *
-   * Warning: This is an internal API and the return value is subject to change.
-   *
-   * @returns The storage options, or undefined if no storage options were configured.
-   */
-  abstract latestStorageOptions(): Promise<
-    Record<string, string> | null | undefined
-  >;
 }
 
 export class LocalTable extends Table {
@@ -887,18 +858,6 @@ export class LocalTable extends Table {
     return await this.inner.stats();
   }
 
-  async initialStorageOptions(): Promise<
-    Record<string, string> | null | undefined
-  > {
-    return await this.inner.initialStorageOptions();
-  }
-
-  async latestStorageOptions(): Promise<
-    Record<string, string> | null | undefined
-  > {
-    return await this.inner.latestStorageOptions();
-  }
-
   mergeInsert(on: string | string[]): MergeInsertBuilder {
     on = Array.isArray(on) ? on : [on];
     return new MergeInsertBuilder(this.inner.mergeInsert(on), this.schema());

nodejs/src/table.rs

@@ -166,19 +166,6 @@ impl Table {
         Ok(stats.into())
     }
 
-    #[napi(catch_unwind)]
-    pub async fn initial_storage_options(&self) -> napi::Result<Option<HashMap<String, String>>> {
-        Ok(self.inner_ref()?.initial_storage_options().await)
-    }
-
-    #[napi(catch_unwind)]
-    pub async fn latest_storage_options(&self) -> napi::Result<Option<HashMap<String, String>>> {
-        self.inner_ref()?
-            .latest_storage_options()
-            .await
-            .default_error()
-    }
-
     #[napi(catch_unwind)]
     pub async fn update(
         &self,

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.27.1"
+current_version = "0.28.0-beta.0"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

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

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.27.1"
+version = "0.28.0-beta.0"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true
@@ -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

@@ -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/_lancedb.pyi

@@ -180,8 +180,6 @@ class Table:
         delete_unverified: Optional[bool] = None,
     ) -> OptimizeStats: ...
     async def uri(self) -> str: ...
-    async def initial_storage_options(self) -> Optional[Dict[str, str]]: ...
-    async def latest_storage_options(self) -> Optional[Dict[str, str]]: ...
     @property
     def tags(self) -> Tags: ...
     def query(self) -> Query: ...

python/python/lancedb/background_loop.py

@@ -22,7 +22,12 @@ class BackgroundEventLoop:
         self.thread.start()
 
     def run(self, future):
-        return asyncio.run_coroutine_threadsafe(future, self.loop).result()
+        concurrent_future = asyncio.run_coroutine_threadsafe(future, self.loop)
+        try:
+            return concurrent_future.result()
+        except BaseException:
+            concurrent_future.cancel()
+            raise
 
 
 LOOP = BackgroundEventLoop()

python/python/lancedb/embeddings/colpali.py

@@ -275,7 +275,7 @@ class ColPaliEmbeddings(EmbeddingFunction):
         """
         Convert image inputs to PIL Images.
         """
-        PIL = attempt_import_or_raise("PIL", "pillow")
+        PIL_Image = attempt_import_or_raise("PIL.Image", "pillow")
         requests = attempt_import_or_raise("requests", "requests")
         images = self.sanitize_input(images)
         pil_images = []
@@ -285,12 +285,12 @@ class ColPaliEmbeddings(EmbeddingFunction):
                     if image.startswith(("http://", "https://")):
                         response = requests.get(image, timeout=10)
                         response.raise_for_status()
-                        pil_images.append(PIL.Image.open(io.BytesIO(response.content)))
+                        pil_images.append(PIL_Image.open(io.BytesIO(response.content)))
                     else:
-                        with PIL.Image.open(image) as im:
+                        with PIL_Image.open(image) as im:
                             pil_images.append(im.copy())
                 elif isinstance(image, bytes):
-                    pil_images.append(PIL.Image.open(io.BytesIO(image)))
+                    pil_images.append(PIL_Image.open(io.BytesIO(image)))
                 else:
                     # Assume it's a PIL Image; will raise if invalid
                     pil_images.append(image)

python/python/lancedb/embeddings/jinaai.py

@@ -77,8 +77,8 @@ class JinaEmbeddings(EmbeddingFunction):
             if isinstance(inputs, list):
                 inputs = inputs
             else:
-                PIL = attempt_import_or_raise("PIL", "pillow")
-                if isinstance(inputs, PIL.Image.Image):
+                PIL_Image = attempt_import_or_raise("PIL.Image", "pillow")
+                if isinstance(inputs, PIL_Image.Image):
                     inputs = [inputs]
         return inputs
 
@@ -89,13 +89,13 @@ class JinaEmbeddings(EmbeddingFunction):
         elif isinstance(image, (str, Path)):
             parsed = urlparse.urlparse(image)
             # TODO handle drive letter on windows.
-            PIL = attempt_import_or_raise("PIL", "pillow")
+            PIL_Image = attempt_import_or_raise("PIL.Image", "pillow")
             if parsed.scheme == "file":
-                pil_image = PIL.Image.open(parsed.path)
+                pil_image = PIL_Image.open(parsed.path)
             elif parsed.scheme == "":
-                pil_image = PIL.Image.open(image if os.name == "nt" else parsed.path)
+                pil_image = PIL_Image.open(image if os.name == "nt" else parsed.path)
             elif parsed.scheme.startswith("http"):
-                pil_image = PIL.Image.open(io.BytesIO(url_retrieve(image)))
+                pil_image = PIL_Image.open(io.BytesIO(url_retrieve(image)))
             else:
                 raise NotImplementedError("Only local and http(s) urls are supported")
             buffered = io.BytesIO()
@@ -103,9 +103,9 @@ class JinaEmbeddings(EmbeddingFunction):
             image_bytes = buffered.getvalue()
             image_dict = {"image": base64.b64encode(image_bytes).decode("utf-8")}
         else:
-            PIL = attempt_import_or_raise("PIL", "pillow")
+            PIL_Image = attempt_import_or_raise("PIL.Image", "pillow")
 
-            if isinstance(image, PIL.Image.Image):
+            if isinstance(image, PIL_Image.Image):
                 buffered = io.BytesIO()
                 image.save(buffered, format="PNG")
                 image_bytes = buffered.getvalue()
@@ -136,9 +136,9 @@ class JinaEmbeddings(EmbeddingFunction):
         elif isinstance(query, (Path, bytes)):
             return [self.generate_image_embedding(query)]
         else:
-            PIL = attempt_import_or_raise("PIL", "pillow")
+            PIL_Image = attempt_import_or_raise("PIL.Image", "pillow")
 
-            if isinstance(query, PIL.Image.Image):
+            if isinstance(query, PIL_Image.Image):
                 return [self.generate_image_embedding(query)]
             else:
                 raise TypeError(

python/python/lancedb/embeddings/open_clip.py

@@ -71,8 +71,8 @@ class OpenClipEmbeddings(EmbeddingFunction):
         if isinstance(query, str):
             return [self.generate_text_embeddings(query)]
         else:
-            PIL = attempt_import_or_raise("PIL", "pillow")
-            if isinstance(query, PIL.Image.Image):
+            PIL_Image = attempt_import_or_raise("PIL.Image", "pillow")
+            if isinstance(query, PIL_Image.Image):
                 return [self.generate_image_embedding(query)]
             else:
                 raise TypeError("OpenClip supports str or PIL Image as query")
@@ -145,20 +145,20 @@ class OpenClipEmbeddings(EmbeddingFunction):
             return self._encode_and_normalize_image(image)
 
     def _to_pil(self, image: Union[str, bytes]):
-        PIL = attempt_import_or_raise("PIL", "pillow")
+        PIL_Image = attempt_import_or_raise("PIL.Image", "pillow")
         if isinstance(image, bytes):
-            return PIL.Image.open(io.BytesIO(image))
-        if isinstance(image, PIL.Image.Image):
+            return PIL_Image.open(io.BytesIO(image))
+        if isinstance(image, PIL_Image.Image):
             return image
         elif isinstance(image, str):
             parsed = urlparse.urlparse(image)
             # TODO handle drive letter on windows.
             if parsed.scheme == "file":
-                return PIL.Image.open(parsed.path)
+                return PIL_Image.open(parsed.path)
             elif parsed.scheme == "":
-                return PIL.Image.open(image if os.name == "nt" else parsed.path)
+                return PIL_Image.open(image if os.name == "nt" else parsed.path)
             elif parsed.scheme.startswith("http"):
-                return PIL.Image.open(io.BytesIO(url_retrieve(image)))
+                return PIL_Image.open(io.BytesIO(url_retrieve(image)))
             else:
                 raise NotImplementedError("Only local and http(s) urls are supported")
 

python/python/lancedb/embeddings/siglip.py

@@ -56,8 +56,8 @@ class SigLipEmbeddings(EmbeddingFunction):
         if isinstance(query, str):
             return [self.generate_text_embeddings(query)]
         else:
-            PIL = attempt_import_or_raise("PIL", "pillow")
-            if isinstance(query, PIL.Image.Image):
+            PIL_Image = attempt_import_or_raise("PIL.Image", "pillow")
+            if isinstance(query, PIL_Image.Image):
                 return [self.generate_image_embedding(query)]
             else:
                 raise TypeError("SigLIP supports str or PIL Image as query")
@@ -127,21 +127,21 @@ class SigLipEmbeddings(EmbeddingFunction):
             return image_features.cpu().detach().numpy().squeeze()
 
     def _to_pil(self, image: Union[str, bytes, "PIL.Image.Image"]):
-        PIL = attempt_import_or_raise("PIL", "pillow")
-        if isinstance(image, PIL.Image.Image):
+        PIL_Image = attempt_import_or_raise("PIL.Image", "pillow")
+        if isinstance(image, PIL_Image.Image):
             return image.convert("RGB") if image.mode != "RGB" else image
         elif isinstance(image, bytes):
-            return PIL.Image.open(io.BytesIO(image)).convert("RGB")
+            return PIL_Image.open(io.BytesIO(image)).convert("RGB")
         elif isinstance(image, str):
             parsed = urlparse.urlparse(image)
             if parsed.scheme == "file":
-                return PIL.Image.open(parsed.path).convert("RGB")
+                return PIL_Image.open(parsed.path).convert("RGB")
             elif parsed.scheme == "":
                 path = image if os.name == "nt" else parsed.path
-                return PIL.Image.open(path).convert("RGB")
+                return PIL_Image.open(path).convert("RGB")
             elif parsed.scheme.startswith("http"):
                 image_bytes = url_retrieve(image)
-                return PIL.Image.open(io.BytesIO(image_bytes)).convert("RGB")
+                return PIL_Image.open(io.BytesIO(image_bytes)).convert("RGB")
             else:
                 raise NotImplementedError("Only local and http(s) urls are supported")
         else:

python/python/lancedb/embeddings/voyageai.py

@@ -21,6 +21,9 @@ if TYPE_CHECKING:
 
 # Token limits for different VoyageAI models
 VOYAGE_TOTAL_TOKEN_LIMITS = {
+    "voyage-4": 320_000,
+    "voyage-4-lite": 1_000_000,
+    "voyage-4-large": 120_000,
     "voyage-context-3": 32_000,
     "voyage-3.5-lite": 1_000_000,
     "voyage-3.5": 320_000,
@@ -61,7 +64,7 @@ def is_video_path(path: Path) -> bool:
 
 
 def transform_input(input_data: Union[str, bytes, Path]):
-    PIL = attempt_import_or_raise("PIL", "pillow")
+    PIL_Image = attempt_import_or_raise("PIL.Image", "pillow")
     if isinstance(input_data, str):
         if is_valid_url(input_data):
             if is_video_url(input_data):
@@ -70,7 +73,7 @@ def transform_input(input_data: Union[str, bytes, Path]):
                 content = {"type": "image_url", "image_url": input_data}
         else:
             content = {"type": "text", "text": input_data}
-    elif isinstance(input_data, PIL.Image.Image):
+    elif isinstance(input_data, PIL_Image.Image):
         buffered = BytesIO()
         input_data.save(buffered, format="JPEG")
         img_str = base64.b64encode(buffered.getvalue()).decode("utf-8")
@@ -79,7 +82,7 @@ def transform_input(input_data: Union[str, bytes, Path]):
             "image_base64": "data:image/jpeg;base64," + img_str,
         }
     elif isinstance(input_data, bytes):
-        img = PIL.Image.open(BytesIO(input_data))
+        img = PIL_Image.open(BytesIO(input_data))
         buffered = BytesIO()
         img.save(buffered, format="JPEG")
         img_str = base64.b64encode(buffered.getvalue()).decode("utf-8")
@@ -98,7 +101,7 @@ def transform_input(input_data: Union[str, bytes, Path]):
                 "video_base64": video_str,
             }
         else:
-            img = PIL.Image.open(input_data)
+            img = PIL_Image.open(input_data)
             buffered = BytesIO()
             img.save(buffered, format="JPEG")
             img_str = base64.b64encode(buffered.getvalue()).decode("utf-8")
@@ -116,8 +119,8 @@ def sanitize_multimodal_input(inputs: Union[TEXT, IMAGES]) -> List[Any]:
     """
     Sanitize the input to the embedding function.
     """
-    PIL = attempt_import_or_raise("PIL", "pillow")
-    if isinstance(inputs, (str, bytes, Path, PIL.Image.Image)):
+    PIL_Image = attempt_import_or_raise("PIL.Image", "pillow")
+    if isinstance(inputs, (str, bytes, Path, PIL_Image.Image)):
         inputs = [inputs]
     elif isinstance(inputs, list):
         pass  # Already a list, use as-is
@@ -130,7 +133,7 @@ def sanitize_multimodal_input(inputs: Union[TEXT, IMAGES]) -> List[Any]:
             f"Input type {type(inputs)} not allowed with multimodal model."
         )
 
-    if not all(isinstance(x, (str, bytes, Path, PIL.Image.Image)) for x in inputs):
+    if not all(isinstance(x, (str, bytes, Path, PIL_Image.Image)) for x in inputs):
         raise ValueError("Each input should be either str, bytes, Path or Image.")
 
     return [transform_input(i) for i in inputs]
@@ -167,6 +170,9 @@ class VoyageAIEmbeddingFunction(EmbeddingFunction):
     name: str
         The name of the model to use. List of acceptable models:
 
+            * voyage-4 (1024 dims, general-purpose and multilingual retrieval)
+            * voyage-4-lite (1024 dims, optimized for latency and cost)
+            * voyage-4-large (1024 dims, best retrieval quality)
             * voyage-context-3
             * voyage-3.5
             * voyage-3.5-lite
@@ -215,6 +221,9 @@ class VoyageAIEmbeddingFunction(EmbeddingFunction):
     _FLEXIBLE_DIM_MODELS: ClassVar[list] = ["voyage-multimodal-3.5"]
     _VALID_DIMENSIONS: ClassVar[list] = [256, 512, 1024, 2048]
     text_embedding_models: list = [
+        "voyage-4",
+        "voyage-4-lite",
+        "voyage-4-large",
         "voyage-3.5",
         "voyage-3.5-lite",
         "voyage-3",
@@ -252,6 +261,9 @@ class VoyageAIEmbeddingFunction(EmbeddingFunction):
         elif self.name == "voyage-code-2":
             return 1536
         elif self.name in [
+            "voyage-4",
+            "voyage-4-lite",
+            "voyage-4-large",
             "voyage-context-3",
             "voyage-3.5",
             "voyage-3.5-lite",

python/python/lancedb/pydantic.py

@@ -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
 
 

python/python/lancedb/table.py

@@ -2222,37 +2222,6 @@ class LanceTable(Table):
     def uri(self) -> str:
         return LOOP.run(self._table.uri())
 
-    def initial_storage_options(self) -> Optional[Dict[str, str]]:
-        """Get the initial storage options that were passed in when opening this table.
-
-        For dynamically refreshed options (e.g., credential vending), use
-        :meth:`latest_storage_options`.
-
-        Warning: This is an internal API and the return value is subject to change.
-
-        Returns
-        -------
-        Optional[Dict[str, str]]
-            The storage options, or None if no storage options were configured.
-        """
-        return LOOP.run(self._table.initial_storage_options())
-
-    def latest_storage_options(self) -> Optional[Dict[str, str]]:
-        """Get the latest storage options, refreshing from provider if configured.
-
-        This method is useful for credential vending scenarios where storage options
-        may be refreshed dynamically. If no dynamic provider is configured, this
-        returns the initial static options.
-
-        Warning: This is an internal API and the return value is subject to change.
-
-        Returns
-        -------
-        Optional[Dict[str, str]]
-            The storage options, or None if no storage options were configured.
-        """
-        return LOOP.run(self._table.latest_storage_options())
-
     def create_scalar_index(
         self,
         column: str,
@@ -3655,37 +3624,6 @@ class AsyncTable:
         """
         return await self._inner.uri()
 
-    async def initial_storage_options(self) -> Optional[Dict[str, str]]:
-        """Get the initial storage options that were passed in when opening this table.
-
-        For dynamically refreshed options (e.g., credential vending), use
-        :meth:`latest_storage_options`.
-
-        Warning: This is an internal API and the return value is subject to change.
-
-        Returns
-        -------
-        Optional[Dict[str, str]]
-            The storage options, or None if no storage options were configured.
-        """
-        return await self._inner.initial_storage_options()
-
-    async def latest_storage_options(self) -> Optional[Dict[str, str]]:
-        """Get the latest storage options, refreshing from provider if configured.
-
-        This method is useful for credential vending scenarios where storage options
-        may be refreshed dynamically. If no dynamic provider is configured, this
-        returns the initial static options.
-
-        Warning: This is an internal API and the return value is subject to change.
-
-        Returns
-        -------
-        Optional[Dict[str, str]]
-            The storage options, or None if no storage options were configured.
-        """
-        return await self._inner.latest_storage_options()
-
     async def add(
         self,
         data: DATA,

python/python/tests/test_embeddings_slow.py

@@ -517,19 +517,36 @@ def test_ollama_embedding(tmp_path):
 @pytest.mark.skipif(
     os.environ.get("VOYAGE_API_KEY") is None, reason="VOYAGE_API_KEY not set"
 )
-def test_voyageai_embedding_function():
-    voyageai = get_registry().get("voyageai").create(name="voyage-3", max_retries=0)
+@pytest.mark.parametrize(
+    "model_name,expected_dims",
+    [
+        ("voyage-3", 1024),
+        ("voyage-4", 1024),
+        ("voyage-4-lite", 1024),
+        ("voyage-4-large", 1024),
+    ],
+)
+def test_voyageai_embedding_function(model_name, expected_dims, tmp_path):
+    """Integration test for VoyageAI text embedding models with real API calls."""
+    voyageai = get_registry().get("voyageai").create(name=model_name, max_retries=0)
 
     class TextModel(LanceModel):
         text: str = voyageai.SourceField()
         vector: Vector(voyageai.ndims()) = voyageai.VectorField()
 
     df = pd.DataFrame({"text": ["hello world", "goodbye world"]})
-    db = lancedb.connect("~/lancedb")
+    db = lancedb.connect(tmp_path)
     tbl = db.create_table("test", schema=TextModel, mode="overwrite")
 
     tbl.add(df)
     assert len(tbl.to_pandas()["vector"][0]) == voyageai.ndims()
+    assert voyageai.ndims() == expected_dims, (
+        f"{model_name} should have {expected_dims} dimensions"
+    )
+
+    # Test search functionality
+    result = tbl.search("hello").limit(1).to_pandas()
+    assert result["text"][0] == "hello world"
 
 
 @pytest.mark.slow

python/python/tests/test_permutation.py

@@ -438,11 +438,15 @@ def test_filter_with_splits(mem_db):
     row_count = permutation_tbl.count_rows()
     assert row_count == 67
 
-    data = permutation_tbl.search(None).to_arrow().to_pydict()
+    # Verify the permutation table only contains row_id and split_id
+    assert set(permutation_tbl.schema.names) == {"row_id", "split_id"}
+
+    row_ids = permutation_tbl.search(None).to_arrow().to_pydict()["row_id"]
+    data = tbl.take_row_ids(row_ids).to_arrow().to_pydict()
     categories = data["category"]
 
     # All categories should be A or B
-    assert all(cat in ["A", "B"] for cat in categories)
+    assert all(cat in ("A", "B") for cat in categories)
 
 
 def test_filter_with_shuffle(mem_db):

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(
-    sys.version_info > (3, 8),
-    reason="using native type alias requires python3.9 or higher",
-)
+def test_optional_structs():
+    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
+
+
+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

python/python/tests/test_remote_db.py

@@ -8,7 +8,7 @@ import http.server
 import json
 import threading
 import time
-from unittest.mock import MagicMock
+from unittest.mock import MagicMock, patch
 import uuid
 from packaging.version import Version
 
@@ -1203,3 +1203,22 @@ async def test_header_provider_overrides_static_headers():
         extra_headers={"X-API-Key": "static-key", "X-Extra": "extra-value"},
     ) as db:
         await db.table_names()
+
+
+@pytest.mark.parametrize("exception", [KeyboardInterrupt, SystemExit, GeneratorExit])
+def test_background_loop_cancellation(exception):
+    """Test that BackgroundEventLoop.run() cancels the future on interrupt."""
+    from lancedb.background_loop import BackgroundEventLoop
+
+    mock_future = MagicMock()
+    mock_future.result.side_effect = exception()
+
+    with (
+        patch.object(BackgroundEventLoop, "__init__", return_value=None),
+        patch("asyncio.run_coroutine_threadsafe", return_value=mock_future),
+    ):
+        loop = BackgroundEventLoop()
+        loop.loop = MagicMock()
+        with pytest.raises(exception):
+            loop.run(None)
+        mock_future.cancel.assert_called_once()

python/python/tests/test_voyageai_embeddings.py

@@ -0,0 +1,108 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+"""Unit tests for VoyageAI embedding function.
+
+These tests verify model registration and configuration without requiring API calls.
+"""
+
+import pytest
+from unittest.mock import MagicMock, patch
+
+from lancedb.embeddings import get_registry
+
+
+@pytest.fixture(autouse=True)
+def reset_voyageai_client():
+    """Reset VoyageAI client before and after each test to avoid state pollution."""
+    from lancedb.embeddings.voyageai import VoyageAIEmbeddingFunction
+
+    VoyageAIEmbeddingFunction.client = None
+    yield
+    VoyageAIEmbeddingFunction.client = None
+
+
+class TestVoyageAIModelRegistration:
+    """Tests for VoyageAI model registration and configuration."""
+
+    @pytest.fixture
+    def mock_voyageai_client(self):
+        """Mock VoyageAI client to avoid API calls."""
+        with patch.dict("os.environ", {"VOYAGE_API_KEY": "test-key"}):
+            with patch("lancedb.embeddings.voyageai.attempt_import_or_raise") as mock:
+                mock_client = MagicMock()
+                mock_voyageai = MagicMock()
+                mock_voyageai.Client.return_value = mock_client
+                mock.return_value = mock_voyageai
+                yield mock_client
+
+    def test_voyageai_registered(self):
+        """Test that VoyageAI is registered in the embedding function registry."""
+        registry = get_registry()
+        assert registry.get("voyageai") is not None
+
+    @pytest.mark.parametrize(
+        "model_name,expected_dims",
+        [
+            # Voyage-4 series (all 1024 dims)
+            ("voyage-4", 1024),
+            ("voyage-4-lite", 1024),
+            ("voyage-4-large", 1024),
+            # Voyage-3 series
+            ("voyage-3", 1024),
+            ("voyage-3-lite", 512),
+            # Domain-specific models
+            ("voyage-finance-2", 1024),
+            ("voyage-multilingual-2", 1024),
+            ("voyage-law-2", 1024),
+            ("voyage-code-2", 1536),
+            # Multimodal
+            ("voyage-multimodal-3", 1024),
+        ],
+    )
+    def test_model_dimensions(self, model_name, expected_dims, mock_voyageai_client):
+        """Test that each model returns the correct dimensions."""
+        registry = get_registry()
+        func = registry.get("voyageai").create(name=model_name)
+        assert func.ndims() == expected_dims, (
+            f"Model {model_name} should have {expected_dims} dimensions"
+        )
+
+    def test_unsupported_model_raises_error(self, mock_voyageai_client):
+        """Test that unsupported models raise ValueError."""
+        registry = get_registry()
+        func = registry.get("voyageai").create(name="unsupported-model")
+        with pytest.raises(ValueError, match="not supported"):
+            func.ndims()
+
+    @pytest.mark.parametrize(
+        "model_name",
+        [
+            "voyage-4",
+            "voyage-4-lite",
+            "voyage-4-large",
+        ],
+    )
+    def test_voyage4_models_are_text_models(self, model_name, mock_voyageai_client):
+        """Test that voyage-4 models are classified as text models (not multimodal)."""
+        registry = get_registry()
+        func = registry.get("voyageai").create(name=model_name)
+        assert not func._is_multimodal_model(model_name), (
+            f"{model_name} should be a text model, not multimodal"
+        )
+
+    def test_voyage4_models_in_text_embedding_list(self, mock_voyageai_client):
+        """Test that voyage-4 models are in the text_embedding_models list."""
+        registry = get_registry()
+        func = registry.get("voyageai").create(name="voyage-4")
+        assert "voyage-4" in func.text_embedding_models
+        assert "voyage-4-lite" in func.text_embedding_models
+        assert "voyage-4-large" in func.text_embedding_models
+
+    def test_voyage4_models_not_in_multimodal_list(self, mock_voyageai_client):
+        """Test that voyage-4 models are NOT in the multimodal_embedding_models list."""
+        registry = get_registry()
+        func = registry.get("voyageai").create(name="voyage-4")
+        assert "voyage-4" not in func.multimodal_embedding_models
+        assert "voyage-4-lite" not in func.multimodal_embedding_models
+        assert "voyage-4-large" not in func.multimodal_embedding_models

python/src/table.rs

@@ -502,20 +502,6 @@ impl Table {
         future_into_py(self_.py(), async move { inner.uri().await.infer_error() })
     }
 
-    pub fn initial_storage_options(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
-        let inner = self_.inner_ref()?.clone();
-        future_into_py(self_.py(), async move {
-            Ok(inner.initial_storage_options().await)
-        })
-    }
-
-    pub fn latest_storage_options(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
-        let inner = self_.inner_ref()?.clone();
-        future_into_py(self_.py(), async move {
-            inner.latest_storage_options().await.infer_error()
-        })
-    }
-
     pub fn __repr__(&self) -> String {
         match &self.inner {
             None => format!("ClosedTable({})", self.name),

rust/lancedb/src/connection.rs

@@ -251,8 +251,36 @@ impl CreateTableBuilder<false> {
     /// Execute the create table operation
     pub async fn execute(self) -> Result<Table> {
         let parent = self.parent.clone();
-        let table = parent.create_table(self.request).await?;
-        Ok(Table::new(table, parent))
+        let embedding_registry = self.embedding_registry.clone();
+        let request = self.into_request()?;
+        Ok(Table::new_with_embedding_registry(
+            parent.create_table(request).await?,
+            parent,
+            embedding_registry,
+        ))
+    }
+
+    fn into_request(self) -> Result<CreateTableRequest> {
+        if self.embeddings.is_empty() {
+            return Ok(self.request);
+        }
+
+        let CreateTableData::Empty(table_def) = self.request.data else {
+            unreachable!("CreateTableBuilder<false> should always have Empty data")
+        };
+
+        let schema = table_def.schema.clone();
+        let empty_batch = arrow_array::RecordBatch::new_empty(schema.clone());
+
+        let reader = Box::new(std::iter::once(Ok(empty_batch)).collect::<Vec<_>>());
+        let reader = arrow_array::RecordBatchIterator::new(reader.into_iter(), schema);
+        let with_embeddings = WithEmbeddings::new(reader, self.embeddings);
+        let table_definition = with_embeddings.table_definition()?;
+
+        Ok(CreateTableRequest {
+            data: CreateTableData::Empty(table_definition),
+            ..self.request
+        })
     }
 }
 
@@ -1692,4 +1720,128 @@ mod tests {
         let cloned_count = cloned_table.count_rows(None).await.unwrap();
         assert_eq!(source_count, cloned_count);
     }
+
+    #[tokio::test]
+    async fn test_create_empty_table_with_embeddings() {
+        use crate::embeddings::{EmbeddingDefinition, EmbeddingFunction};
+        use arrow_array::{
+            Array, FixedSizeListArray, Float32Array, RecordBatch, RecordBatchIterator, StringArray,
+        };
+        use std::borrow::Cow;
+
+        #[derive(Debug, Clone)]
+        struct MockEmbedding {
+            dim: usize,
+        }
+
+        impl EmbeddingFunction for MockEmbedding {
+            fn name(&self) -> &str {
+                "test_embedding"
+            }
+
+            fn source_type(&self) -> Result<Cow<'_, DataType>> {
+                Ok(Cow::Owned(DataType::Utf8))
+            }
+
+            fn dest_type(&self) -> Result<Cow<'_, DataType>> {
+                Ok(Cow::Owned(DataType::new_fixed_size_list(
+                    DataType::Float32,
+                    self.dim as i32,
+                    true,
+                )))
+            }
+
+            fn compute_source_embeddings(&self, source: Arc<dyn Array>) -> Result<Arc<dyn Array>> {
+                let len = source.len();
+                let values = vec![1.0f32; len * self.dim];
+                let values = Arc::new(Float32Array::from(values));
+                let field = Arc::new(Field::new("item", DataType::Float32, true));
+                Ok(Arc::new(FixedSizeListArray::new(
+                    field,
+                    self.dim as i32,
+                    values,
+                    None,
+                )))
+            }
+
+            fn compute_query_embeddings(&self, _input: Arc<dyn Array>) -> Result<Arc<dyn Array>> {
+                unimplemented!()
+            }
+        }
+
+        let tmp_dir = tempdir().unwrap();
+        let uri = tmp_dir.path().to_str().unwrap();
+        let db = connect(uri).execute().await.unwrap();
+
+        let embed_func = Arc::new(MockEmbedding { dim: 128 });
+        db.embedding_registry()
+            .register("test_embedding", embed_func.clone())
+            .unwrap();
+
+        let schema = Arc::new(Schema::new(vec![Field::new("name", DataType::Utf8, true)]));
+        let ed = EmbeddingDefinition {
+            source_column: "name".to_owned(),
+            dest_column: Some("name_embedding".to_owned()),
+            embedding_name: "test_embedding".to_owned(),
+        };
+
+        let table = db
+            .create_empty_table("test", schema)
+            .mode(CreateTableMode::Overwrite)
+            .add_embedding(ed)
+            .unwrap()
+            .execute()
+            .await
+            .unwrap();
+
+        let table_schema = table.schema().await.unwrap();
+        assert!(table_schema.column_with_name("name").is_some());
+        assert!(table_schema.column_with_name("name_embedding").is_some());
+
+        let embedding_field = table_schema.field_with_name("name_embedding").unwrap();
+        assert_eq!(
+            embedding_field.data_type(),
+            &DataType::new_fixed_size_list(DataType::Float32, 128, true)
+        );
+
+        let input_schema = Arc::new(Schema::new(vec![Field::new("name", DataType::Utf8, true)]));
+        let input_batch = RecordBatch::try_new(
+            input_schema.clone(),
+            vec![Arc::new(StringArray::from(vec![
+                Some("Alice"),
+                Some("Bob"),
+                Some("Charlie"),
+            ]))],
+        )
+        .unwrap();
+
+        let input_reader = Box::new(RecordBatchIterator::new(
+            vec![Ok(input_batch)].into_iter(),
+            input_schema,
+        ));
+
+        table.add(input_reader).execute().await.unwrap();
+
+        let results = table
+            .query()
+            .execute()
+            .await
+            .unwrap()
+            .try_collect::<Vec<_>>()
+            .await
+            .unwrap();
+
+        assert_eq!(results.len(), 1);
+        let batch = &results[0];
+        assert_eq!(batch.num_rows(), 3);
+        assert!(batch.column_by_name("name_embedding").is_some());
+
+        let embedding_col = batch
+            .column_by_name("name_embedding")
+            .unwrap()
+            .as_any()
+            .downcast_ref::<FixedSizeListArray>()
+            .unwrap();
+        assert_eq!(embedding_col.len(), 3);
+    }
 }

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!(

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

@@ -12,6 +12,8 @@ use datafusion_common::hash_utils::create_hashes;
 use futures::{StreamExt, TryStreamExt};
 use lance_arrow::SchemaExt;
 
+use lance_core::ROW_ID;
+
 use crate::{
     arrow::{SendableRecordBatchStream, SimpleRecordBatchStream},
     dataloader::{
@@ -360,11 +362,15 @@ impl Splitter {
 
     pub fn project(&self, query: Query) -> Query {
         match &self.strategy {
-            SplitStrategy::Calculated { calculation } => query.select(Select::Dynamic(vec![(
-                SPLIT_ID_COLUMN.to_string(),
-                calculation.clone(),
-            )])),
-            SplitStrategy::Hash { columns, .. } => query.select(Select::Columns(columns.clone())),
+            SplitStrategy::Calculated { calculation } => query.select(Select::Dynamic(vec![
+                (SPLIT_ID_COLUMN.to_string(), calculation.clone()),
+                (ROW_ID.to_string(), ROW_ID.to_string()),
+            ])),
+            SplitStrategy::Hash { columns, .. } => {
+                let mut cols = columns.clone();
+                cols.push(ROW_ID.to_string());
+                query.select(Select::Columns(cols))
+            }
             _ => query,
         }
     }

rust/lancedb/src/remote/table.rs

@@ -1493,14 +1493,6 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
         None
     }
 
-    async fn initial_storage_options(&self) -> Option<HashMap<String, String>> {
-        None
-    }
-
-    async fn latest_storage_options(&self) -> Result<Option<HashMap<String, String>>> {
-        Ok(None)
-    }
-
     async fn stats(&self) -> Result<TableStatistics> {
         let request = self
             .client

rust/lancedb/src/table.rs

@@ -79,10 +79,11 @@ use self::merge::MergeInsertBuilder;
 
 pub mod datafusion;
 pub(crate) mod dataset;
+pub mod delete;
 pub mod merge;
-
 use crate::index::waiter::wait_for_index;
 pub use chrono::Duration;
+pub use delete::DeleteResult;
 use futures::future::{join_all, Either};
 pub use lance::dataset::optimize::CompactionOptions;
 pub use lance::dataset::refs::{TagContents, Tags as LanceTags};
@@ -446,15 +447,6 @@ pub struct AddResult {
     pub version: u64,
 }
 
-#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, Default)]
-pub struct DeleteResult {
-    // The commit version associated with the operation.
-    // A version of `0` indicates compatibility with legacy servers that do not return
-    /// a commit version.
-    #[serde(default)]
-    pub version: u64,
-}
-
 #[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, Default)]
 pub struct MergeResult {
     // The commit version associated with the operation.
@@ -611,17 +603,7 @@ pub trait BaseTable: std::fmt::Display + std::fmt::Debug + Send + Sync {
     /// Get the table URI (storage location)
     async fn uri(&self) -> Result<String>;
     /// Get the storage options used when opening this table, if any.
-    #[deprecated(since = "0.25.0", note = "Use initial_storage_options() instead")]
     async fn storage_options(&self) -> Option<HashMap<String, String>>;
-    /// Get the initial storage options that were passed in when opening this table.
-    ///
-    /// For dynamically refreshed options (e.g., credential vending), use [`Self::latest_storage_options`].
-    async fn initial_storage_options(&self) -> Option<HashMap<String, String>>;
-    /// Get the latest storage options, refreshing from provider if configured.
-    ///
-    /// Returns `Ok(Some(options))` if storage options are available (static or refreshed),
-    /// `Ok(None)` if no storage options were configured, or `Err(...)` if refresh failed.
-    async fn latest_storage_options(&self) -> Result<Option<HashMap<String, String>>>;
     /// Poll until the columns are fully indexed. Will return Error::Timeout if the columns
     /// are not fully indexed within the timeout.
     async fn wait_for_index(
@@ -1338,32 +1320,10 @@ impl Table {
     /// Get the storage options used when opening this table, if any.
     ///
     /// Warning: This is an internal API and the return value is subject to change.
-    #[deprecated(since = "0.25.0", note = "Use initial_storage_options() instead")]
     pub async fn storage_options(&self) -> Option<HashMap<String, String>> {
-        #[allow(deprecated)]
         self.inner.storage_options().await
     }
 
-    /// Get the initial storage options that were passed in when opening this table.
-    ///
-    /// For dynamically refreshed options (e.g., credential vending), use [`Self::latest_storage_options`].
-    ///
-    /// Warning: This is an internal API and the return value is subject to change.
-    pub async fn initial_storage_options(&self) -> Option<HashMap<String, String>> {
-        self.inner.initial_storage_options().await
-    }
-
-    /// Get the latest storage options, refreshing from provider if configured.
-    ///
-    /// This method is useful for credential vending scenarios where storage options
-    /// may be refreshed dynamically. If no dynamic provider is configured, this
-    /// returns the initial static options.
-    ///
-    /// Warning: This is an internal API and the return value is subject to change.
-    pub async fn latest_storage_options(&self) -> Result<Option<HashMap<String, String>>> {
-        self.inner.latest_storage_options().await
-    }
-
     /// Get statistics about an index.
     /// Returns None if the index does not exist.
     pub async fn index_stats(
@@ -3110,11 +3070,8 @@ impl BaseTable for NativeTable {
 
     /// Delete rows from the table
     async fn delete(&self, predicate: &str) -> Result<DeleteResult> {
-        let mut dataset = self.dataset.get_mut().await?;
-        dataset.delete(predicate).await?;
-        Ok(DeleteResult {
-            version: dataset.version().version,
-        })
+        // Delegate to the submodule implementation
+        delete::execute_delete(self, predicate).await
     }
 
     async fn tags(&self) -> Result<Box<dyn Tags + '_>> {
@@ -3263,10 +3220,6 @@ impl BaseTable for NativeTable {
     }
 
     async fn storage_options(&self) -> Option<HashMap<String, String>> {
-        self.initial_storage_options().await
-    }
-
-    async fn initial_storage_options(&self) -> Option<HashMap<String, String>> {
         self.dataset
             .get()
             .await
@@ -3274,11 +3227,6 @@ impl BaseTable for NativeTable {
             .and_then(|dataset| dataset.initial_storage_options().cloned())
     }
 
-    async fn latest_storage_options(&self) -> Result<Option<HashMap<String, String>>> {
-        let dataset = self.dataset.get().await?;
-        Ok(dataset.latest_storage_options().await?.map(|o| o.0))
-    }
-
     async fn index_stats(&self, index_name: &str) -> Result<Option<IndexStatistics>> {
         let stats = match self
             .dataset

rust/lancedb/src/table/delete.rs

@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+use serde::{Deserialize, Serialize};
+
+use super::NativeTable;
+use crate::Result;
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, Default)]
+pub struct DeleteResult {
+    // The commit version associated with the operation.
+    // A version of `0` indicates compatibility with legacy servers that do not return
+    /// a commit version.
+    #[serde(default)]
+    pub version: u64,
+}
+
+/// Internal implementation of the delete logic
+///
+/// This logic was moved from NativeTable::delete to keep table.rs clean.
+pub(crate) async fn execute_delete(table: &NativeTable, predicate: &str) -> Result<DeleteResult> {
+    // We access the dataset from the table. Since this is in the same module hierarchy (super),
+    // and 'dataset' is pub(crate), we can access it.
+    let mut dataset = table.dataset.get_mut().await?;
+
+    // Perform the actual delete on the Lance dataset
+    dataset.delete(predicate).await?;
+
+    // Return the result with the new version
+    Ok(DeleteResult {
+        version: dataset.version().version,
+    })
+}
+
+#[cfg(test)]
+mod tests {
+    use crate::connect;
+    use arrow_array::{record_batch, Int32Array, RecordBatch, RecordBatchIterator};
+    use arrow_schema::{DataType, Field, Schema};
+    use std::sync::Arc;
+
+    use crate::query::ExecutableQuery;
+    use futures::TryStreamExt;
+    #[tokio::test]
+    async fn test_delete_simple() {
+        let conn = connect("memory://").execute().await.unwrap();
+
+        // 1. Create a table with values 0 to 9
+        let schema = Arc::new(Schema::new(vec![Field::new("i", DataType::Int32, false)]));
+        let batch = RecordBatch::try_new(
+            schema.clone(),
+            vec![Arc::new(Int32Array::from_iter_values(0..10))],
+        )
+        .unwrap();
+
+        let table = conn
+            .create_table(
+                "test_delete",
+                RecordBatchIterator::new(vec![Ok(batch)], schema),
+            )
+            .execute()
+            .await
+            .unwrap();
+
+        // 2. Verify initial state
+        assert_eq!(table.count_rows(None).await.unwrap(), 10);
+
+        // 3. Execute Delete (removes values > 5)
+        table.delete("i > 5").await.unwrap();
+
+        // 4. Verify results
+        assert_eq!(table.count_rows(None).await.unwrap(), 6); // 0, 1, 2, 3, 4, 5 remain
+
+        // 5. Verify specific data consistency
+        let batches = table
+            .query()
+            .execute()
+            .await
+            .unwrap()
+            .try_collect::<Vec<_>>()
+            .await
+            .unwrap();
+        let batch = &batches[0];
+        let array = batch
+            .column(0)
+            .as_any()
+            .downcast_ref::<Int32Array>()
+            .unwrap();
+
+        // Ensure no value > 5 exists
+        for val in array.iter() {
+            assert!(val.unwrap() <= 5);
+        }
+    }
+    #[tokio::test]
+    async fn rows_removed_schema_same() {
+        let conn = connect("memory://").execute().await.unwrap();
+        let batch = record_batch!(
+            ("id", Int32, [1, 2, 3, 4, 5]),
+            ("name", Utf8, ["a", "b", "c", "d", "e"])
+        )
+        .unwrap();
+        let original_schema = batch.schema();
+
+        let table = conn
+            .create_table(
+                "test_delete_all",
+                RecordBatchIterator::new(vec![Ok(batch)], original_schema.clone()),
+            )
+            .execute()
+            .await
+            .unwrap();
+
+        table.delete("true").await.unwrap();
+
+        assert_eq!(table.count_rows(None).await.unwrap(), 0);
+
+        let current_schema = table.schema().await.unwrap();
+        //check if the original schema is the same as current
+        assert_eq!(current_schema, original_schema);
+    }
+
+    #[tokio::test]
+    async fn test_delete_false_increments_version() {
+        let conn = connect("memory://").execute().await.unwrap();
+
+        // Create a table with 5 rows
+        let batch = record_batch!(("id", Int32, [1, 2, 3, 4, 5])).unwrap();
+
+        let schema = batch.schema();
+
+        let table = conn
+            .create_table(
+                "test_delete_noop",
+                RecordBatchIterator::new(vec![Ok(batch)], schema),
+            )
+            .execute()
+            .await
+            .unwrap();
+
+        // Capture the initial state (Rows = 5, Version = 1)
+        let initial_rows = table.count_rows(None).await.unwrap();
+        let initial_version = table.version().await.unwrap();
+
+        assert_eq!(initial_rows, 5);
+        table.delete("false").await.unwrap();
+
+        // Rows should still be 5
+        let current_rows = table.count_rows(None).await.unwrap();
+        assert_eq!(
+            current_rows, initial_rows,
+            "Data should not change when predicate is false"
+        );
+
+        // version check
+        let current_version = table.version().await.unwrap();
+        assert!(
+            current_version > initial_version,
+            "Table version must increment after delete operation"
+        );
+    }
+}