Bump version: 0.23.1 → 0.24.0-beta.0

2026-03-26 02:20:40 +00:00 · 2026-01-21 12:21:32 +00:00
70 changed files with 920 additions and 1951 deletions
--- a/.bumpversion.toml
+++ b/.bumpversion.toml
@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.24.1"
+current_version = "0.24.0-beta.0"
 parse = """(?x)
    (?P<major>0|[1-9]\\d*)\\.
    (?P<minor>0|[1-9]\\d*)\\.
--- a/.github/workflows/build_linux_wheel/action.yml
+++ b/.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: "10, 11, 12, 13"
+    description: "8, 9, 10, 11, 12"
    required: true
  args:
    description: "--release"
--- a/.github/workflows/build_mac_wheel/action.yml
+++ b/.github/workflows/build_mac_wheel/action.yml
@@ -3,7 +3,7 @@ name: build_wheel
 description: "Build a lance wheel"
 inputs:
  python-minor-version:
-    description: "10, 11, 12, 13"
+    description: "8, 9, 10, 11"
    required: true
  args:
    description: "--release"
--- a/.github/workflows/build_windows_wheel/action.yml
+++ b/.github/workflows/build_windows_wheel/action.yml
@@ -3,7 +3,7 @@ name: build_wheel
 description: "Build a lance wheel"
 inputs:
  python-minor-version:
-    description: "10, 11, 12, 13, 14"
+    description: "8, 9, 10, 11"
    required: true
  args:
    description: "--release"
--- a/.github/workflows/codex-update-lance-dependency.yml
+++ b/.github/workflows/codex-update-lance-dependency.yml
@@ -75,13 +75,6 @@ jobs:
          VERSION="${VERSION#v}"
          BRANCH_NAME="codex/update-lance-${VERSION//[^a-zA-Z0-9]/-}"

-          # Use "chore" for beta/rc versions, "feat" for stable releases
-          if [[ "${VERSION}" == *beta* ]] || [[ "${VERSION}" == *rc* ]]; then
-            COMMIT_TYPE="chore"
-          else
-            COMMIT_TYPE="feat"
-          fi
-
          cat <<EOF >/tmp/codex-prompt.txt
          You are running inside the lancedb repository on a GitHub Actions runner. Update the Lance dependency to version ${VERSION} and prepare a pull request for maintainers to review.

@@ -91,10 +84,10 @@ jobs:
          3. After clippy succeeds, run "cargo fmt --all" to format the workspace.
          4. Ensure the repository is clean except for intentional changes. Inspect "git status --short" and "git diff" to confirm the dependency update and any required fixes.
          5. Create and switch to a new branch named "${BRANCH_NAME}" (replace any duplicated hyphens if necessary).
-          6. Stage all relevant files with "git add -A". Commit using the message "${COMMIT_TYPE}: update lance dependency to v${VERSION}".
+          6. Stage all relevant files with "git add -A". Commit using the message "chore: update lance dependency to v${VERSION}".
          7. Push the branch to origin. If the branch already exists, force-push your changes.
          8. env "GH_TOKEN" is available, use "gh" tools for github related operations like creating pull request.
-          9. Create a pull request targeting "main" with title "${COMMIT_TYPE}: update lance dependency to v${VERSION}". First, write the PR body to /tmp/pr-body.md using a heredoc (cat <<'EOF' > /tmp/pr-body.md). The body should summarize the dependency bump, clippy/fmt verification, and link the triggering tag (${TAG}). Then run "gh pr create --body-file /tmp/pr-body.md".
+          9. Create a pull request targeting "main" with title "chore: update lance dependency to v${VERSION}". In the body, summarize the dependency bump, clippy/fmt verification, and link the triggering tag (${TAG}).
          10. After creating the PR, display the PR URL, "git status --short", and a concise summary of the commands run and their results.

          Constraints:
--- a/.github/workflows/docs.yml
+++ b/.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@v6
+        uses: actions/setup-python@v5
        with:
          python-version: "3.10"
          cache: "pip"
--- a/.github/workflows/pypi-publish.yml
+++ b/.github/workflows/pypi-publish.yml
@@ -44,12 +44,12 @@ jobs:
          fetch-depth: 0
          lfs: true
      - name: Set up Python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v4
        with:
-          python-version: "3.10"
+          python-version: 3.8
      - uses: ./.github/workflows/build_linux_wheel
        with:
-          python-minor-version: 10
+          python-minor-version: 8
          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@v6
+        uses: actions/setup-python@v4
        with:
-          python-version: "3.13"
+          python-version: 3.12
      - uses: ./.github/workflows/build_mac_wheel
        with:
-          python-minor-version: 10
+          python-minor-version: 8
          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@v6
+        uses: actions/setup-python@v4
        with:
-          python-version: "3.13"
+          python-version: 3.12
      - uses: ./.github/workflows/build_windows_wheel
        with:
-          python-minor-version: 10
+          python-minor-version: 8
          args: "--release --strip"
          vcpkg_token: ${{ secrets.VCPKG_GITHUB_PACKAGES }}
      - uses: ./.github/workflows/upload_wheel
--- a/.github/workflows/python.yml
+++ b/.github/workflows/python.yml
@@ -36,9 +36,9 @@ jobs:
          fetch-depth: 0
          lfs: true
      - name: Set up Python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v5
        with:
-          python-version: "3.13"
+          python-version: "3.12"
      - name: Install ruff
        run: |
          pip install ruff==0.9.9
@@ -61,9 +61,9 @@ jobs:
          fetch-depth: 0
          lfs: true
      - name: Set up Python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v5
        with:
-          python-version: "3.13"
+          python-version: "3.12"
      - name: Install protobuf compiler
        run: |
          sudo apt update
@@ -90,9 +90,9 @@ jobs:
          fetch-depth: 0
          lfs: true
      - name: Set up Python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v5
        with:
-          python-version: "3.13"
+          python-version: "3.12"
          cache: "pip"
      - name: Install protobuf
        run: |
@@ -110,7 +110,7 @@ jobs:
    timeout-minutes: 30
    strategy:
      matrix:
-        python-minor-version: ["10", "13"]
+        python-minor-version: ["9", "12"]
    runs-on: "ubuntu-24.04"
    defaults:
      run:
@@ -126,7 +126,7 @@ jobs:
          sudo apt update
          sudo apt install -y protobuf-compiler
      - name: Set up Python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v5
        with:
          python-version: 3.${{ 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@v6
+        uses: actions/setup-python@v5
        with:
-          python-version: "3.13"
+          python-version: "3.12"
      - 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@v6
+        uses: actions/setup-python@v5
        with:
-          python-version: "3.13"
+          python-version: "3.12"
      - 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@v6
+        uses: actions/setup-python@v5
        with:
-          python-version: "3.10"
+          python-version: 3.9
      - name: Install lancedb
        run: |
          pip install "pydantic<2"
--- a/.github/workflows/rust.yml
+++ b/.github/workflows/rust.yml
@@ -48,8 +48,6 @@ jobs:
        run: cargo fmt --all -- --check
      - name: Run clippy
        run: cargo clippy --profile ci --workspace --tests --all-features -- -D warnings
-      - name: Run clippy (without remote feature)
-        run: cargo clippy --profile ci --workspace --tests -- -D warnings

  build-no-lock:
    runs-on: ubuntu-24.04
@@ -183,7 +181,7 @@ jobs:
    runs-on: ubuntu-24.04
    strategy:
      matrix:
-        msrv: ["1.88.0"] # This should match up with rust-version in Cargo.toml
+        msrv: ["1.78.0"] # This should match up with rust-version in Cargo.toml
    env:
      # Need up-to-date compilers for kernels
      CC: clang-18
@@ -214,6 +212,4 @@ jobs:
          cargo update -p aws-sdk-sts --precise 1.51.0
          cargo update -p home --precise 0.5.9
      - name: cargo +${{ matrix.msrv }} check
-        env:
-          RUSTUP_TOOLCHAIN: ${{ matrix.msrv }}
        run: cargo check --profile ci --workspace --tests --benches --all-features
--- a/Cargo.lock
+++ b/Cargo.lock
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -12,42 +12,42 @@ repository = "https://github.com/lancedb/lancedb"
 description = "Serverless, low-latency vector database for AI applications"
 keywords = ["lancedb", "lance", "database", "vector", "search"]
 categories = ["database-implementations"]
-rust-version = "1.88.0"
+rust-version = "1.78.0"

 [workspace.dependencies]
-lance = { "version" = "=1.0.4", default-features = false, "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=1.0.4", default-features = false, "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=1.0.4", default-features = false, "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=2.0.0-beta.8", default-features = false, "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=2.0.0-beta.8", default-features = false, "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=2.0.0-beta.8", default-features = false, "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
 ahash = "0.8"
 # Note that this one does not include pyarrow
-arrow = { version = "56.2", optional = false }
-arrow-array = "56.2"
-arrow-data = "56.2"
-arrow-ipc = "56.2"
-arrow-ord = "56.2"
-arrow-schema = "56.2"
-arrow-select = "56.2"
-arrow-cast = "56.2"
+arrow = { version = "57.2", optional = false }
+arrow-array = "57.2"
+arrow-data = "57.2"
+arrow-ipc = "57.2"
+arrow-ord = "57.2"
+arrow-schema = "57.2"
+arrow-select = "57.2"
+arrow-cast = "57.2"
 async-trait = "0"
-datafusion = { version = "50.1", default-features = false }
-datafusion-catalog = "50.1"
-datafusion-common = { version = "50.1", default-features = false }
-datafusion-execution = "50.1"
-datafusion-expr = "50.1"
-datafusion-physical-plan = "50.1"
+datafusion = { version = "51.0", default-features = false }
+datafusion-catalog = "51.0"
+datafusion-common = { version = "51.0", default-features = false }
+datafusion-execution = "51.0"
+datafusion-expr = "51.0"
+datafusion-physical-plan = "51.0"
 env_logger = "0.11"
-half = { "version" = "2.6.0", default-features = false, features = [
+half = { "version" = "2.7.1", default-features = false, features = [
    "num-traits",
 ] }
 futures = "0"
@@ -59,7 +59,7 @@ rand = "0.9"
 snafu = "0.8"
 url = "2"
 num-traits = "0.2"
-regex = "1.10"
+regex = "1.12"
 lazy_static = "1"
 semver = "1.0.25"
 chrono = "0.4"
--- a/README.md
+++ b/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/rest |
+| REST API | https://docs.lancedb.com/api-reference/introduction |

 ## **Join Us and Contribute**

--- a/docs/src/embeddings/available_embedding_models/text_embedding_functions/voyageai_embedding.md
+++ b/docs/src/embeddings/available_embedding_models/text_embedding_functions/voyageai_embedding.md
@@ -1,62 +0,0 @@
-# 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)
-```
--- a/docs/src/java/java.md
+++ b/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>0.24.1</version>
+    <version>0.24.0-beta.0</version>
 </dependency>
 ```

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

--- a/java/pom.xml
+++ b/java/pom.xml
@@ -6,7 +6,7 @@

    <groupId>com.lancedb</groupId>
    <artifactId>lancedb-parent</artifactId>
-    <version>0.24.1-final.0</version>
+    <version>0.24.0-beta.0</version>
    <packaging>pom</packaging>
    <name>${project.artifactId}</name>
    <description>LanceDB Java SDK Parent POM</description>
@@ -28,7 +28,7 @@
    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <arrow.version>15.0.0</arrow.version>
-        <lance-core.version>1.0.4</lance-core.version>
+        <lance-core.version>1.0.0-rc.2</lance-core.version>
        <spotless.skip>false</spotless.skip>
        <spotless.version>2.30.0</spotless.version>
        <spotless.java.googlejavaformat.version>1.7</spotless.java.googlejavaformat.version>
--- a/nodejs/Cargo.toml
+++ b/nodejs/Cargo.toml
@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.24.1"
+version = "0.24.0-beta.0"
 license.workspace = true
 description.workspace = true
 repository.workspace = true
--- a/nodejs/npm/darwin-arm64/package.json
+++ b/nodejs/npm/darwin-arm64/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.24.1",
+	"version": "0.24.0-beta.0",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",
--- a/nodejs/npm/darwin-x64/package.json
+++ b/nodejs/npm/darwin-x64/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-x64",
-	"version": "0.24.1",
+	"version": "0.24.0-beta.0",
 	"os": ["darwin"],
 	"cpu": ["x64"],
 	"main": "lancedb.darwin-x64.node",
--- a/nodejs/npm/linux-arm64-gnu/package.json
+++ b/nodejs/npm/linux-arm64-gnu/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.24.1",
+	"version": "0.24.0-beta.0",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",
--- a/nodejs/npm/linux-arm64-musl/package.json
+++ b/nodejs/npm/linux-arm64-musl/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-musl",
-	"version": "0.24.1",
+	"version": "0.24.0-beta.0",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-musl.node",
--- a/nodejs/npm/linux-x64-gnu/package.json
+++ b/nodejs/npm/linux-x64-gnu/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.24.1",
+	"version": "0.24.0-beta.0",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",
--- a/nodejs/npm/linux-x64-musl/package.json
+++ b/nodejs/npm/linux-x64-musl/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-musl",
-	"version": "0.24.1",
+	"version": "0.24.0-beta.0",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-musl.node",
--- a/nodejs/npm/win32-arm64-msvc/package.json
+++ b/nodejs/npm/win32-arm64-msvc/package.json
@@ -1,6 +1,6 @@
 {
  "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.24.1",
+  "version": "0.24.0-beta.0",
  "os": [
    "win32"
  ],
--- a/nodejs/npm/win32-x64-msvc/package.json
+++ b/nodejs/npm/win32-x64-msvc/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.24.1",
+	"version": "0.24.0-beta.0",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",
--- a/nodejs/package-lock.json
+++ b/nodejs/package-lock.json
@@ -1,12 +1,12 @@
 {
  "name": "@lancedb/lancedb",
-  "version": "0.24.1",
+  "version": "0.23.1",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "@lancedb/lancedb",
-      "version": "0.24.1",
+      "version": "0.23.1",
      "cpu": [
        "x64",
        "arm64"
--- a/nodejs/package.json
+++ b/nodejs/package.json
@@ -11,7 +11,7 @@
    "ann"
  ],
  "private": false,
-  "version": "0.24.1",
+  "version": "0.24.0-beta.0",
  "main": "dist/index.js",
  "exports": {
    ".": "./dist/index.js",
--- a/python/.bumpversion.toml
+++ b/python/.bumpversion.toml
@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.28.0-beta.0"
+current_version = "0.27.0-beta.0"
 parse = """(?x)
    (?P<major>0|[1-9]\\d*)\\.
    (?P<minor>0|[1-9]\\d*)\\.
--- a/python/CONTRIBUTING.md
+++ b/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 3.10 or later
+1. Python 3.9 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)

--- a/python/Cargo.toml
+++ b/python/Cargo.toml
@@ -1,28 +1,28 @@
 [package]
 name = "lancedb-python"
-version = "0.28.0-beta.0"
+version = "0.27.0-beta.0"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true
 repository.workspace = true
 keywords.workspace = true
 categories.workspace = true
-rust-version = "1.88.0"
+rust-version = "1.75.0"

 [lib]
 name = "_lancedb"
 crate-type = ["cdylib"]

 [dependencies]
-arrow = { version = "56.2", features = ["pyarrow"] }
+arrow = { version = "57.2", features = ["pyarrow"] }
 async-trait = "0.1"
 lancedb = { path = "../rust/lancedb", default-features = false }
 lance-core.workspace = true
 lance-namespace.workspace = true
 lance-io.workspace = true
 env_logger.workspace = true
-pyo3 = { version = "0.25", features = ["extension-module", "abi3-py310"] }
-pyo3-async-runtimes = { version = "0.25", features = [
+pyo3 = { version = "0.26", features = ["extension-module", "abi3-py39"] }
+pyo3-async-runtimes = { version = "0.26", features = [
    "attributes",
    "tokio-runtime",
 ] }
@@ -32,9 +32,9 @@ snafu.workspace = true
 tokio = { version = "1.40", features = ["sync"] }

 [build-dependencies]
-pyo3-build-config = { version = "0.25", features = [
+pyo3-build-config = { version = "0.26", features = [
    "extension-module",
-    "abi3-py310",
+    "abi3-py39",
 ] }

 [features]
--- a/python/pyproject.toml
+++ b/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 = ">=3.10"
+requires-python = ">=3.9"
 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 = "3.13"
+pythonVersion = "3.12"
--- a/python/python/lancedb/background_loop.py
+++ b/python/python/lancedb/background_loop.py
@@ -22,12 +22,7 @@ class BackgroundEventLoop:
        self.thread.start()

    def run(self, future):
-        concurrent_future = asyncio.run_coroutine_threadsafe(future, self.loop)
-        try:
-            return concurrent_future.result()
-        except BaseException:
-            concurrent_future.cancel()
-            raise
+        return asyncio.run_coroutine_threadsafe(future, self.loop).result()


 LOOP = BackgroundEventLoop()
--- a/python/python/lancedb/embeddings/colpali.py
+++ b/python/python/lancedb/embeddings/colpali.py
@@ -275,7 +275,7 @@ class ColPaliEmbeddings(EmbeddingFunction):
        """
        Convert image inputs to PIL Images.
        """
-        PIL_Image = attempt_import_or_raise("PIL.Image", "pillow")
+        PIL = attempt_import_or_raise("PIL", "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)
--- a/python/python/lancedb/embeddings/jinaai.py
+++ b/python/python/lancedb/embeddings/jinaai.py
@@ -77,8 +77,8 @@ class JinaEmbeddings(EmbeddingFunction):
            if isinstance(inputs, list):
                inputs = inputs
            else:
-                PIL_Image = attempt_import_or_raise("PIL.Image", "pillow")
-                if isinstance(inputs, PIL_Image.Image):
+                PIL = attempt_import_or_raise("PIL", "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_Image = attempt_import_or_raise("PIL.Image", "pillow")
+            PIL = attempt_import_or_raise("PIL", "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_Image = attempt_import_or_raise("PIL.Image", "pillow")
+            PIL = attempt_import_or_raise("PIL", "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_Image = attempt_import_or_raise("PIL.Image", "pillow")
+            PIL = attempt_import_or_raise("PIL", "pillow")

-            if isinstance(query, PIL_Image.Image):
+            if isinstance(query, PIL.Image.Image):
                return [self.generate_image_embedding(query)]
            else:
                raise TypeError(
--- a/python/python/lancedb/embeddings/open_clip.py
+++ b/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_Image = attempt_import_or_raise("PIL.Image", "pillow")
-            if isinstance(query, PIL_Image.Image):
+            PIL = attempt_import_or_raise("PIL", "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_Image = attempt_import_or_raise("PIL.Image", "pillow")
+        PIL = attempt_import_or_raise("PIL", "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")

--- a/python/python/lancedb/embeddings/siglip.py
+++ b/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_Image = attempt_import_or_raise("PIL.Image", "pillow")
-            if isinstance(query, PIL_Image.Image):
+            PIL = attempt_import_or_raise("PIL", "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_Image = attempt_import_or_raise("PIL.Image", "pillow")
-        if isinstance(image, PIL_Image.Image):
+        PIL = attempt_import_or_raise("PIL", "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:
--- a/python/python/lancedb/embeddings/voyageai.py
+++ b/python/python/lancedb/embeddings/voyageai.py
@@ -21,9 +21,6 @@ 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,
@@ -64,7 +61,7 @@ def is_video_path(path: Path) -> bool:


 def transform_input(input_data: Union[str, bytes, Path]):
-    PIL_Image = attempt_import_or_raise("PIL.Image", "pillow")
+    PIL = attempt_import_or_raise("PIL", "pillow")
    if isinstance(input_data, str):
        if is_valid_url(input_data):
            if is_video_url(input_data):
@@ -73,7 +70,7 @@ 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")
@@ -82,7 +79,7 @@ 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")
@@ -101,7 +98,7 @@ 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")
@@ -119,8 +116,8 @@ def sanitize_multimodal_input(inputs: Union[TEXT, IMAGES]) -> List[Any]:
    """
    Sanitize the input to the embedding function.
    """
-    PIL_Image = attempt_import_or_raise("PIL.Image", "pillow")
-    if isinstance(inputs, (str, bytes, Path, PIL_Image.Image)):
+    PIL = attempt_import_or_raise("PIL", "pillow")
+    if isinstance(inputs, (str, bytes, Path, PIL.Image.Image)):
        inputs = [inputs]
    elif isinstance(inputs, list):
        pass  # Already a list, use as-is
@@ -133,7 +130,7 @@ 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]
@@ -170,9 +167,6 @@ 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
@@ -221,9 +215,6 @@ 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",
@@ -261,9 +252,6 @@ 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",
--- a/python/python/lancedb/pydantic.py
+++ b/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 _pydantic_list_child_to_arrow(child, field)
+        return pa.list_(_py_type_to_arrow_type(child, field))
    raise TypeError(
        f"Converting Pydantic type to Arrow Type: unsupported type {py_type}."
    )
@@ -298,18 +298,12 @@ 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 _safe_issubclass(tp, pydantic.BaseModel):
+        if issubclass(tp, pydantic.BaseModel):
            # Struct
            fields = _pydantic_model_to_fields(tp)
            return pa.struct(fields)
-        if _safe_issubclass(tp, FixedSizeListMixin):
+        if 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
@@ -317,67 +311,45 @@ 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 _pydantic_list_child_to_arrow(child, field)
+            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_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 any(typ is type(None) for typ in args):
+            if len(args) == 2 and args[1] is type(None):
                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):
-        try:
-            if issubclass(field.annotation, FixedSizeListMixin):
-                return field.annotation.nullable()
-        except TypeError:
-            return False
+    elif inspect.isclass(field.annotation) and issubclass(
+        field.annotation, FixedSizeListMixin
+    ):
+        return field.annotation.nullable()
    return False


--- a/python/python/lancedb/query.py
+++ b/python/python/lancedb/query.py
@@ -961,22 +961,27 @@ class LanceQueryBuilder(ABC):
        >>> query = [100, 100]
        >>> plan = table.search(query).analyze_plan()
        >>> print(plan)  # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
-        AnalyzeExec verbose=true, metrics=[], cumulative_cpu=...
-          TracedExec, metrics=[], cumulative_cpu=...
-            ProjectionExec: expr=[...], metrics=[...], cumulative_cpu=...
-              GlobalLimitExec: skip=0, fetch=10, metrics=[...], cumulative_cpu=...
-                FilterExec: _distance@2 IS NOT NULL,
-                metrics=[output_rows=..., elapsed_compute=...], cumulative_cpu=...
-                  SortExec: TopK(fetch=10), expr=[...],
+        AnalyzeExec verbose=true, elapsed=..., metrics=...
+          TracedExec, elapsed=..., metrics=...
+            ProjectionExec: elapsed=..., expr=[...],
+            metrics=[output_rows=..., elapsed_compute=..., output_bytes=...]
+              GlobalLimitExec: elapsed=..., skip=0, fetch=10,
+              metrics=[output_rows=..., elapsed_compute=..., output_bytes=...]
+                FilterExec: elapsed=..., _distance@2 IS NOT NULL, metrics=[...]
+                  SortExec: elapsed=..., TopK(fetch=10), expr=[...],
                  preserve_partitioning=[...],
-                  metrics=[output_rows=..., elapsed_compute=..., row_replacements=...],
-                  cumulative_cpu=...
-                    KNNVectorDistance: metric=l2,
-                    metrics=[output_rows=..., elapsed_compute=..., output_batches=...],
-                    cumulative_cpu=...
-                      LanceRead: uri=..., projection=[vector], ...
-                      metrics=[output_rows=..., elapsed_compute=...,
-                      bytes_read=..., iops=..., requests=...], cumulative_cpu=...
+                  metrics=[output_rows=..., elapsed_compute=...,
+                  output_bytes=..., row_replacements=...]
+                    KNNVectorDistance: elapsed=..., metric=l2,
+                    metrics=[output_rows=..., elapsed_compute=...,
+                    output_bytes=..., output_batches=...]
+                      LanceRead: elapsed=..., uri=..., projection=[vector],
+                      num_fragments=..., range_before=None, range_after=None,
+                      row_id=true, row_addr=false,
+                      full_filter=--, refine_filter=--,
+                      metrics=[output_rows=..., elapsed_compute=..., output_bytes=...,
+                      fragments_scanned=..., ranges_scanned=1, rows_scanned=1,
+                      bytes_read=..., iops=..., requests=..., task_wait_time=...]

        Returns
        -------
--- a/python/python/tests/conftest.py
+++ b/python/python/tests/conftest.py
@@ -2,27 +2,12 @@
 # SPDX-FileCopyrightText: Copyright The LanceDB Authors

 from datetime import timedelta
-
 from lancedb.db import AsyncConnection, DBConnection
 import lancedb
 import pytest
 import pytest_asyncio


-def pandas_string_type():
-    """Return the PyArrow string type that pandas uses for string columns.
-
-    pandas 3.0+ uses large_string for string columns, pandas 2.x uses string.
-    """
-    import pandas as pd
-    import pyarrow as pa
-
-    version = tuple(int(x) for x in pd.__version__.split(".")[:2])
-    if version >= (3, 0):
-        return pa.large_utf8()
-    return pa.utf8()
-
-
 # Use an in-memory database for most tests.
@pytest.fixture
 def mem_db() -> DBConnection:
--- a/python/python/tests/test_db.py
+++ b/python/python/tests/test_db.py
@@ -268,8 +268,6 @@ async def test_create_table_from_iterator_async(mem_db_async: lancedb.AsyncConne


 def test_create_exist_ok(tmp_db: lancedb.DBConnection):
-    from conftest import pandas_string_type
-
    data = pd.DataFrame(
        {
            "vector": [[3.1, 4.1], [5.9, 26.5]],
@@ -288,11 +286,10 @@ def test_create_exist_ok(tmp_db: lancedb.DBConnection):
    assert tbl.schema == tbl2.schema
    assert len(tbl) == len(tbl2)

-    # pandas 3.0+ uses large_string, pandas 2.x uses string
    schema = pa.schema(
        [
            pa.field("vector", pa.list_(pa.float32(), list_size=2)),
-            pa.field("item", pandas_string_type()),
+            pa.field("item", pa.utf8()),
            pa.field("price", pa.float64()),
        ]
    )
@@ -302,7 +299,7 @@ def test_create_exist_ok(tmp_db: lancedb.DBConnection):
    bad_schema = pa.schema(
        [
            pa.field("vector", pa.list_(pa.float32(), list_size=2)),
-            pa.field("item", pandas_string_type()),
+            pa.field("item", pa.utf8()),
            pa.field("price", pa.float64()),
            pa.field("extra", pa.float32()),
        ]
@@ -368,8 +365,6 @@ async def test_create_mode_async(tmp_db_async: lancedb.AsyncConnection):

@pytest.mark.asyncio
 async def test_create_exist_ok_async(tmp_db_async: lancedb.AsyncConnection):
-    from conftest import pandas_string_type
-
    data = pd.DataFrame(
        {
            "vector": [[3.1, 4.1], [5.9, 26.5]],
@@ -387,11 +382,10 @@ async def test_create_exist_ok_async(tmp_db_async: lancedb.AsyncConnection):
    assert tbl.name == tbl2.name
    assert await tbl.schema() == await tbl2.schema()

-    # pandas 3.0+ uses large_string, pandas 2.x uses string
    schema = pa.schema(
        [
            pa.field("vector", pa.list_(pa.float32(), list_size=2)),
-            pa.field("item", pandas_string_type()),
+            pa.field("item", pa.utf8()),
            pa.field("price", pa.float64()),
        ]
    )
@@ -601,8 +595,6 @@ def test_open_table_sync(tmp_db: lancedb.DBConnection):

@pytest.mark.asyncio
 async def test_open_table(tmp_path):
-    from conftest import pandas_string_type
-
    db = await lancedb.connect_async(tmp_path)
    data = pd.DataFrame(
        {
@@ -622,11 +614,10 @@ async def test_open_table(tmp_path):
        )
        is not None
    )
-    # pandas 3.0+ uses large_string, pandas 2.x uses string
    assert await tbl.schema() == pa.schema(
        {
            "vector": pa.list_(pa.float32(), list_size=2),
-            "item": pandas_string_type(),
+            "item": pa.utf8(),
            "price": pa.float64(),
        }
    )
--- a/python/python/tests/test_embeddings_slow.py
+++ b/python/python/tests/test_embeddings_slow.py
@@ -517,36 +517,19 @@ def test_ollama_embedding(tmp_path):
@pytest.mark.skipif(
    os.environ.get("VOYAGE_API_KEY") is None, reason="VOYAGE_API_KEY not set"
 )
-@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)
+def test_voyageai_embedding_function():
+    voyageai = get_registry().get("voyageai").create(name="voyage-3", 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(tmp_path)
+    db = lancedb.connect("~/lancedb")
    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
--- a/python/python/tests/test_namespace_integration.py
+++ b/python/python/tests/test_namespace_integration.py
@@ -26,8 +26,6 @@ import pytest
 from lance_namespace import (
    CreateEmptyTableRequest,
    CreateEmptyTableResponse,
-    DeclareTableRequest,
-    DeclareTableResponse,
    DescribeTableRequest,
    DescribeTableResponse,
    LanceNamespace,
@@ -162,19 +160,6 @@ class TrackingNamespace(LanceNamespace):

        return modified

-    def declare_table(self, request: DeclareTableRequest) -> DeclareTableResponse:
-        """Track declare_table calls and inject rotating credentials."""
-        with self.lock:
-            self.create_call_count += 1
-            count = self.create_call_count
-
-        response = self.inner.declare_table(request)
-        response.storage_options = self._modify_storage_options(
-            response.storage_options, count
-        )
-
-        return response
-
    def create_empty_table(
        self, request: CreateEmptyTableRequest
    ) -> CreateEmptyTableResponse:
--- a/python/python/tests/test_permutation.py
+++ b/python/python/tests/test_permutation.py
@@ -438,15 +438,11 @@ def test_filter_with_splits(mem_db):
    row_count = permutation_tbl.count_rows()
    assert row_count == 67

-    # 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()
+    data = permutation_tbl.search(None).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):
--- a/python/python/tests/test_pydantic.py
+++ b/python/python/tests/test_pydantic.py
@@ -2,6 +2,7 @@
 # SPDX-FileCopyrightText: Copyright The LanceDB Authors

 import json
+import sys
 from datetime import date, datetime
 from typing import List, Optional, Tuple

@@ -19,6 +20,10 @@ 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
@@ -78,6 +83,10 @@ 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
@@ -96,233 +105,10 @@ def test_optional_types_py310():
    assert schema == expect_schema


-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
-
-
+@pytest.mark.skipif(
+    sys.version_info > (3, 8),
+    reason="using native type alias requires python3.9 or higher",
+)
 def test_pydantic_to_arrow_py38():
    class StructModel(pydantic.BaseModel):
        a: str
--- a/python/python/tests/test_remote_db.py
+++ b/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, patch
+from unittest.mock import MagicMock
 import uuid
 from packaging.version import Version

@@ -1203,22 +1203,3 @@ 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()
--- a/python/python/tests/test_util.py
+++ b/python/python/tests/test_util.py
@@ -528,19 +528,12 @@ def test_sanitize_data(
        else:
            expected_schema = schema
    else:
-        from conftest import pandas_string_type
-
-        # polars uses large_string, pandas 3.0+ uses large_string, others use string
-        if isinstance(data, pl.DataFrame):
-            text_type = pa.large_utf8()
-        elif isinstance(data, pd.DataFrame):
-            text_type = pandas_string_type()
-        else:
-            text_type = pa.string()
        expected_schema = pa.schema(
            {
                "id": pa.int64(),
-                "text": text_type,
+                "text": pa.large_utf8()
+                if isinstance(data, pl.DataFrame)
+                else pa.string(),
                "vector": pa.list_(pa.float32(), 10),
            }
        )
--- a/python/python/tests/test_voyageai_embeddings.py
+++ b/python/python/tests/test_voyageai_embeddings.py
@@ -1,108 +0,0 @@
-# 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
--- a/python/src/arrow.rs
+++ b/python/src/arrow.rs
@@ -10,8 +10,7 @@ use arrow::{
 use futures::stream::StreamExt;
 use lancedb::arrow::SendableRecordBatchStream;
 use pyo3::{
-    exceptions::PyStopAsyncIteration, pyclass, pymethods, Bound, PyAny, PyObject, PyRef, PyResult,
-    Python,
+    exceptions::PyStopAsyncIteration, pyclass, pymethods, Bound, Py, PyAny, PyRef, PyResult, Python,
 };
 use pyo3_async_runtimes::tokio::future_into_py;

@@ -36,8 +35,11 @@ impl RecordBatchStream {
 #[pymethods]
 impl RecordBatchStream {
    #[getter]
-    pub fn schema(&self, py: Python) -> PyResult<PyObject> {
-        (*self.schema).clone().into_pyarrow(py)
+    pub fn schema(&self, py: Python) -> PyResult<Py<PyAny>> {
+        (*self.schema)
+            .clone()
+            .into_pyarrow(py)
+            .map(|obj| obj.unbind())
    }

    pub fn __aiter__(self_: PyRef<'_, Self>) -> PyRef<'_, Self> {
@@ -53,7 +55,12 @@ impl RecordBatchStream {
                .next()
                .await
                .ok_or_else(|| PyStopAsyncIteration::new_err(""))?;
-            Python::with_gil(|py| inner_next.infer_error()?.to_pyarrow(py))
+            #[allow(deprecated)]
+            let py_obj: Py<PyAny> = Python::with_gil(|py| -> PyResult<Py<PyAny>> {
+                let bound = inner_next.infer_error()?.to_pyarrow(py)?;
+                Ok(bound.unbind())
+            })?;
+            Ok(py_obj)
        })
    }
 }
--- a/python/src/connection.rs
+++ b/python/src/connection.rs
@@ -12,7 +12,7 @@ use pyo3::{
    exceptions::{PyRuntimeError, PyValueError},
    pyclass, pyfunction, pymethods,
    types::{PyDict, PyDictMethods},
-    Bound, FromPyObject, Py, PyAny, PyObject, PyRef, PyResult, Python,
+    Bound, FromPyObject, Py, PyAny, PyRef, PyResult, Python,
 };
 use pyo3_async_runtimes::tokio::future_into_py;

@@ -114,7 +114,7 @@ impl Connection {
        data: Bound<'_, PyAny>,
        namespace: Vec<String>,
        storage_options: Option<HashMap<String, String>>,
-        storage_options_provider: Option<PyObject>,
+        storage_options_provider: Option<Py<PyAny>>,
        location: Option<String>,
    ) -> PyResult<Bound<'a, PyAny>> {
        let inner = self_.get_inner()?.clone();
@@ -152,7 +152,7 @@ impl Connection {
        schema: Bound<'_, PyAny>,
        namespace: Vec<String>,
        storage_options: Option<HashMap<String, String>>,
-        storage_options_provider: Option<PyObject>,
+        storage_options_provider: Option<Py<PyAny>>,
        location: Option<String>,
    ) -> PyResult<Bound<'a, PyAny>> {
        let inner = self_.get_inner()?.clone();
@@ -187,7 +187,7 @@ impl Connection {
        name: String,
        namespace: Vec<String>,
        storage_options: Option<HashMap<String, String>>,
-        storage_options_provider: Option<PyObject>,
+        storage_options_provider: Option<Py<PyAny>>,
        index_cache_size: Option<u32>,
        location: Option<String>,
    ) -> PyResult<Bound<'_, PyAny>> {
@@ -307,6 +307,7 @@ impl Connection {
                ..Default::default()
            };
            let response = inner.list_namespaces(request).await.infer_error()?;
+            #[allow(deprecated)]
            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
                let dict = PyDict::new(py);
                dict.set_item("namespaces", response.namespaces)?;
@@ -327,8 +328,7 @@ impl Connection {
        let py = self_.py();
        future_into_py(py, async move {
            use lance_namespace::models::CreateNamespaceRequest;
-            // Mode is now a string field
-            let mode_str = mode.and_then(|m| match m.to_lowercase().as_str() {
+            let mode_enum = mode.and_then(|m| match m.to_lowercase().as_str() {
                "create" => Some("Create".to_string()),
                "exist_ok" => Some("ExistOk".to_string()),
                "overwrite" => Some("Overwrite".to_string()),
@@ -340,11 +340,12 @@ impl Connection {
                } else {
                    Some(namespace)
                },
-                mode: mode_str,
+                mode: mode_enum,
                properties,
                ..Default::default()
            };
            let response = inner.create_namespace(request).await.infer_error()?;
+            #[allow(deprecated)]
            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
                let dict = PyDict::new(py);
                dict.set_item("properties", response.properties)?;
@@ -364,13 +365,12 @@ impl Connection {
        let py = self_.py();
        future_into_py(py, async move {
            use lance_namespace::models::DropNamespaceRequest;
-            // Mode and Behavior are now string fields
-            let mode_str = mode.and_then(|m| match m.to_uppercase().as_str() {
+            let mode_enum = mode.and_then(|m| match m.to_uppercase().as_str() {
                "SKIP" => Some("Skip".to_string()),
                "FAIL" => Some("Fail".to_string()),
                _ => None,
            });
-            let behavior_str = behavior.and_then(|b| match b.to_uppercase().as_str() {
+            let behavior_enum = behavior.and_then(|b| match b.to_uppercase().as_str() {
                "RESTRICT" => Some("Restrict".to_string()),
                "CASCADE" => Some("Cascade".to_string()),
                _ => None,
@@ -381,11 +381,12 @@ impl Connection {
                } else {
                    Some(namespace)
                },
-                mode: mode_str,
-                behavior: behavior_str,
+                mode: mode_enum,
+                behavior: behavior_enum,
                ..Default::default()
            };
            let response = inner.drop_namespace(request).await.infer_error()?;
+            #[allow(deprecated)]
            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
                let dict = PyDict::new(py);
                dict.set_item("properties", response.properties)?;
@@ -413,6 +414,7 @@ impl Connection {
                ..Default::default()
            };
            let response = inner.describe_namespace(request).await.infer_error()?;
+            #[allow(deprecated)]
            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
                let dict = PyDict::new(py);
                dict.set_item("properties", response.properties)?;
@@ -443,6 +445,7 @@ impl Connection {
                ..Default::default()
            };
            let response = inner.list_tables(request).await.infer_error()?;
+            #[allow(deprecated)]
            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
                let dict = PyDict::new(py);
                dict.set_item("tables", response.tables)?;
--- a/python/src/error.rs
+++ b/python/src/error.rs
@@ -40,31 +40,34 @@ impl<T> PythonErrorExt<T> for std::result::Result<T, LanceError> {
                    request_id,
                    source,
                    status_code,
-                } => Python::with_gil(|py| {
-                    let message = err.to_string();
-                    let http_err_cls = py
-                        .import(intern!(py, "lancedb.remote.errors"))?
-                        .getattr(intern!(py, "HttpError"))?;
-                    let err = http_err_cls.call1((
-                        message,
-                        request_id,
-                        status_code.map(|s| s.as_u16()),
-                    ))?;
-
-                    if let Some(cause) = source.source() {
-                        // The HTTP error already includes the first cause. But
-                        // we can add the rest of the chain if there is any more.
-                        let cause_err = http_from_rust_error(
-                            py,
-                            cause,
+                } => {
+                    #[allow(deprecated)]
+                    Python::with_gil(|py| {
+                        let message = err.to_string();
+                        let http_err_cls = py
+                            .import(intern!(py, "lancedb.remote.errors"))?
+                            .getattr(intern!(py, "HttpError"))?;
+                        let err = http_err_cls.call1((
+                            message,
                            request_id,
                            status_code.map(|s| s.as_u16()),
-                        )?;
-                        err.setattr(intern!(py, "__cause__"), cause_err)?;
-                    }
+                        ))?;

-                    Err(PyErr::from_value(err))
-                }),
+                        if let Some(cause) = source.source() {
+                            // The HTTP error already includes the first cause. But
+                            // we can add the rest of the chain if there is any more.
+                            let cause_err = http_from_rust_error(
+                                py,
+                                cause,
+                                request_id,
+                                status_code.map(|s| s.as_u16()),
+                            )?;
+                            err.setattr(intern!(py, "__cause__"), cause_err)?;
+                        }
+
+                        Err(PyErr::from_value(err))
+                    })
+                }
                LanceError::Retry {
                    request_id,
                    request_failures,
@@ -75,33 +78,37 @@ impl<T> PythonErrorExt<T> for std::result::Result<T, LanceError> {
                    max_read_failures,
                    source,
                    status_code,
-                } => Python::with_gil(|py| {
-                    let cause_err = http_from_rust_error(
-                        py,
-                        source.as_ref(),
-                        request_id,
-                        status_code.map(|s| s.as_u16()),
-                    )?;
+                } =>
+                {
+                    #[allow(deprecated)]
+                    Python::with_gil(|py| {
+                        let cause_err = http_from_rust_error(
+                            py,
+                            source.as_ref(),
+                            request_id,
+                            status_code.map(|s| s.as_u16()),
+                        )?;

-                    let message = err.to_string();
-                    let retry_error_cls = py
-                        .import(intern!(py, "lancedb.remote.errors"))?
-                        .getattr("RetryError")?;
-                    let err = retry_error_cls.call1((
-                        message,
-                        request_id,
-                        *request_failures,
-                        *connect_failures,
-                        *read_failures,
-                        *max_request_failures,
-                        *max_connect_failures,
-                        *max_read_failures,
-                        status_code.map(|s| s.as_u16()),
-                    ))?;
+                        let message = err.to_string();
+                        let retry_error_cls = py
+                            .import(intern!(py, "lancedb.remote.errors"))?
+                            .getattr("RetryError")?;
+                        let err = retry_error_cls.call1((
+                            message,
+                            request_id,
+                            *request_failures,
+                            *connect_failures,
+                            *read_failures,
+                            *max_request_failures,
+                            *max_connect_failures,
+                            *max_read_failures,
+                            status_code.map(|s| s.as_u16()),
+                        ))?;

-                    err.setattr(intern!(py, "__cause__"), cause_err)?;
-                    Err(PyErr::from_value(err))
-                }),
+                        err.setattr(intern!(py, "__cause__"), cause_err)?;
+                        Err(PyErr::from_value(err))
+                    })
+                }
                _ => self.runtime_error(),
            },
        }
--- a/python/src/header.rs
+++ b/python/src/header.rs
@@ -12,6 +12,7 @@ pub struct PyHeaderProvider {

 impl Clone for PyHeaderProvider {
    fn clone(&self) -> Self {
+        #[allow(deprecated)]
        Python::with_gil(|py| Self {
            provider: self.provider.clone_ref(py),
        })
@@ -25,6 +26,7 @@ impl PyHeaderProvider {

    /// Get headers from the Python provider (internal implementation)
    fn get_headers_internal(&self) -> Result<HashMap<String, String>, String> {
+        #[allow(deprecated)]
        Python::with_gil(|py| {
            // Call the get_headers method
            let result = self.provider.call_method0(py, "get_headers");
--- a/python/src/permutation.rs
+++ b/python/src/permutation.rs
@@ -19,7 +19,7 @@ use pyo3::{
    exceptions::PyRuntimeError,
    pyclass, pymethods,
    types::{PyAnyMethods, PyDict, PyDictMethods, PyType},
-    Bound, PyAny, PyRef, PyRefMut, PyResult, Python,
+    Bound, Py, PyAny, PyRef, PyRefMut, PyResult, Python,
 };
 use pyo3_async_runtimes::tokio::future_into_py;

@@ -281,7 +281,12 @@ impl PyPermutationReader {
        let reader = slf.reader.clone();
        future_into_py(slf.py(), async move {
            let schema = reader.output_schema(selection).await.infer_error()?;
-            Python::with_gil(|py| schema.to_pyarrow(py))
+            #[allow(deprecated)]
+            let py_obj: Py<PyAny> = Python::with_gil(|py| -> PyResult<Py<PyAny>> {
+                let bound = schema.to_pyarrow(py)?;
+                Ok(bound.unbind())
+            })?;
+            Ok(py_obj)
        })
    }

--- a/python/src/query.rs
+++ b/python/src/query.rs
@@ -29,6 +29,7 @@ use pyo3::types::PyList;
 use pyo3::types::{PyDict, PyString};
 use pyo3::Bound;
 use pyo3::IntoPyObject;
+use pyo3::Py;
 use pyo3::PyAny;
 use pyo3::PyRef;
 use pyo3::PyResult;
@@ -453,7 +454,12 @@ impl Query {
        let inner = self_.inner.clone();
        future_into_py(self_.py(), async move {
            let schema = inner.output_schema().await.infer_error()?;
-            Python::with_gil(|py| schema.to_pyarrow(py))
+            #[allow(deprecated)]
+            let py_obj: Py<PyAny> = Python::with_gil(|py| -> PyResult<Py<PyAny>> {
+                let bound = schema.to_pyarrow(py)?;
+                Ok(bound.unbind())
+            })?;
+            Ok(py_obj)
        })
    }

@@ -532,7 +538,12 @@ impl TakeQuery {
        let inner = self_.inner.clone();
        future_into_py(self_.py(), async move {
            let schema = inner.output_schema().await.infer_error()?;
-            Python::with_gil(|py| schema.to_pyarrow(py))
+            #[allow(deprecated)]
+            let py_obj: Py<PyAny> = Python::with_gil(|py| -> PyResult<Py<PyAny>> {
+                let bound = schema.to_pyarrow(py)?;
+                Ok(bound.unbind())
+            })?;
+            Ok(py_obj)
        })
    }

@@ -627,7 +638,12 @@ impl FTSQuery {
        let inner = self_.inner.clone();
        future_into_py(self_.py(), async move {
            let schema = inner.output_schema().await.infer_error()?;
-            Python::with_gil(|py| schema.to_pyarrow(py))
+            #[allow(deprecated)]
+            let py_obj: Py<PyAny> = Python::with_gil(|py| -> PyResult<Py<PyAny>> {
+                let bound = schema.to_pyarrow(py)?;
+                Ok(bound.unbind())
+            })?;
+            Ok(py_obj)
        })
    }

@@ -806,7 +822,12 @@ impl VectorQuery {
        let inner = self_.inner.clone();
        future_into_py(self_.py(), async move {
            let schema = inner.output_schema().await.infer_error()?;
-            Python::with_gil(|py| schema.to_pyarrow(py))
+            #[allow(deprecated)]
+            let py_obj: Py<PyAny> = Python::with_gil(|py| -> PyResult<Py<PyAny>> {
+                let bound = schema.to_pyarrow(py)?;
+                Ok(bound.unbind())
+            })?;
+            Ok(py_obj)
        })
    }

--- a/python/src/storage_options.rs
+++ b/python/src/storage_options.rs
@@ -17,11 +17,12 @@ use pyo3::types::PyDict;
 /// Internal wrapper around a Python object implementing StorageOptionsProvider
 pub struct PyStorageOptionsProvider {
    /// The Python object implementing fetch_storage_options()
-    inner: PyObject,
+    inner: Py<PyAny>,
 }

 impl Clone for PyStorageOptionsProvider {
    fn clone(&self) -> Self {
+        #[allow(deprecated)]
        Python::with_gil(|py| Self {
            inner: self.inner.clone_ref(py),
        })
@@ -29,7 +30,8 @@ impl Clone for PyStorageOptionsProvider {
 }

 impl PyStorageOptionsProvider {
-    pub fn new(obj: PyObject) -> PyResult<Self> {
+    pub fn new(obj: Py<PyAny>) -> PyResult<Self> {
+        #[allow(deprecated)]
        Python::with_gil(|py| {
            // Verify the object has a fetch_storage_options method
            if !obj.bind(py).hasattr("fetch_storage_options")? {
@@ -37,7 +39,9 @@ impl PyStorageOptionsProvider {
                    "StorageOptionsProvider must implement fetch_storage_options() method",
                ));
            }
-            Ok(Self { inner: obj })
+            Ok(Self {
+                inner: obj.clone_ref(py),
+            })
        })
    }
 }
@@ -60,6 +64,7 @@ impl StorageOptionsProvider for PyStorageOptionsProviderWrapper {
        let py_provider = self.py_provider.clone();

        tokio::task::spawn_blocking(move || {
+            #[allow(deprecated)]
            Python::with_gil(|py| {
                // Call the Python fetch_storage_options method
                let result = py_provider
@@ -119,6 +124,7 @@ impl StorageOptionsProvider for PyStorageOptionsProviderWrapper {
    }

    fn provider_id(&self) -> String {
+        #[allow(deprecated)]
        Python::with_gil(|py| {
            // Call provider_id() method on the Python object
            let obj = self.py_provider.inner.bind(py);
@@ -143,7 +149,7 @@ impl std::fmt::Debug for PyStorageOptionsProviderWrapper {
 /// This is the main entry point for converting Python StorageOptionsProvider objects
 /// to Rust trait objects that can be used by the Lance ecosystem.
 pub fn py_object_to_storage_options_provider(
-    py_obj: PyObject,
+    py_obj: Py<PyAny>,
 ) -> PyResult<Arc<dyn StorageOptionsProvider>> {
    let py_provider = PyStorageOptionsProvider::new(py_obj)?;
    Ok(Arc::new(PyStorageOptionsProviderWrapper::new(py_provider)))
--- a/python/src/table.rs
+++ b/python/src/table.rs
@@ -21,7 +21,7 @@ use pyo3::{
    exceptions::{PyKeyError, PyRuntimeError, PyValueError},
    pyclass, pymethods,
    types::{IntoPyDict, PyAnyMethods, PyDict, PyDictMethods},
-    Bound, FromPyObject, PyAny, PyRef, PyResult, Python,
+    Bound, FromPyObject, Py, PyAny, PyRef, PyResult, Python,
 };
 use pyo3_async_runtimes::tokio::future_into_py;

@@ -287,7 +287,12 @@ impl Table {
        let inner = self_.inner_ref()?.clone();
        future_into_py(self_.py(), async move {
            let schema = inner.schema().await.infer_error()?;
-            Python::with_gil(|py| schema.to_pyarrow(py))
+            #[allow(deprecated)]
+            let py_obj: Py<PyAny> = Python::with_gil(|py| -> PyResult<Py<PyAny>> {
+                let bound = schema.to_pyarrow(py)?;
+                Ok(bound.unbind())
+            })?;
+            Ok(py_obj)
        })
    }

@@ -437,6 +442,7 @@ impl Table {
        future_into_py(self_.py(), async move {
            let stats = inner.index_stats(&index_name).await.infer_error()?;
            if let Some(stats) = stats {
+                #[allow(deprecated)]
                Python::with_gil(|py| {
                    let dict = PyDict::new(py);
                    dict.set_item("num_indexed_rows", stats.num_indexed_rows)?;
@@ -467,6 +473,7 @@ impl Table {
        let inner = self_.inner_ref()?.clone();
        future_into_py(self_.py(), async move {
            let stats = inner.stats().await.infer_error()?;
+            #[allow(deprecated)]
            Python::with_gil(|py| {
                let dict = PyDict::new(py);
                dict.set_item("total_bytes", stats.total_bytes)?;
@@ -521,6 +528,7 @@ impl Table {
        let inner = self_.inner_ref()?.clone();
        future_into_py(self_.py(), async move {
            let versions = inner.list_versions().await.infer_error()?;
+            #[allow(deprecated)]
            let versions_as_dict = Python::with_gil(|py| {
                versions
                    .iter()
@@ -872,6 +880,7 @@ impl Tags {
            let tags = inner.tags().await.infer_error()?;
            let res = tags.list().await.infer_error()?;

+            #[allow(deprecated)]
            Python::with_gil(|py| {
                let py_dict = PyDict::new(py);
                for (key, contents) in res {
--- a/rust/lancedb/Cargo.toml
+++ b/rust/lancedb/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.24.1"
+version = "0.24.0-beta.0"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true
--- a/rust/lancedb/src/connection.rs
+++ b/rust/lancedb/src/connection.rs
@@ -36,42 +36,10 @@ use crate::remote::{
 };
 use crate::table::{TableDefinition, WriteOptions};
 use crate::Table;
-use lance::io::ObjectStoreParams;
 pub use lance_encoding::version::LanceFileVersion;
 #[cfg(feature = "remote")]
 use lance_io::object_store::StorageOptions;
-use lance_io::object_store::{StorageOptionsAccessor, StorageOptionsProvider};
-
-fn merge_storage_options(
-    store_params: &mut ObjectStoreParams,
-    pairs: impl IntoIterator<Item = (String, String)>,
-) {
-    let mut options = store_params.storage_options().cloned().unwrap_or_default();
-    for (key, value) in pairs {
-        options.insert(key, value);
-    }
-    let provider = store_params
-        .storage_options_accessor
-        .as_ref()
-        .and_then(|accessor| accessor.provider().cloned());
-    let accessor = if let Some(provider) = provider {
-        StorageOptionsAccessor::with_initial_and_provider(options, provider)
-    } else {
-        StorageOptionsAccessor::with_static_options(options)
-    };
-    store_params.storage_options_accessor = Some(Arc::new(accessor));
-}
-
-fn set_storage_options_provider(
-    store_params: &mut ObjectStoreParams,
-    provider: Arc<dyn StorageOptionsProvider>,
-) {
-    let accessor = match store_params.storage_options().cloned() {
-        Some(options) => StorageOptionsAccessor::with_initial_and_provider(options, provider),
-        None => StorageOptionsAccessor::with_provider(provider),
-    };
-    store_params.storage_options_accessor = Some(Arc::new(accessor));
-}
+use lance_io::object_store::StorageOptionsProvider;

 /// A builder for configuring a [`Connection::table_names`] operation
 pub struct TableNamesBuilder {
@@ -251,36 +219,8 @@ impl CreateTableBuilder<false> {
    /// Execute the create table operation
    pub async fn execute(self) -> Result<Table> {
        let parent = self.parent.clone();
-        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
-        })
+        let table = parent.create_table(self.request).await?;
+        Ok(Table::new(table, parent))
    }
 }

@@ -306,14 +246,16 @@ impl<const HAS_DATA: bool> CreateTableBuilder<HAS_DATA> {
    ///
    /// See available options at <https://lancedb.com/docs/storage/>
    pub fn storage_option(mut self, key: impl Into<String>, value: impl Into<String>) -> Self {
-        let store_params = self
+        let store_options = self
            .request
            .write_options
            .lance_write_params
            .get_or_insert(Default::default())
            .store_params
+            .get_or_insert(Default::default())
+            .storage_options
            .get_or_insert(Default::default());
-        merge_storage_options(store_params, [(key.into(), value.into())]);
+        store_options.insert(key.into(), value.into());
        self
    }

@@ -327,17 +269,19 @@ impl<const HAS_DATA: bool> CreateTableBuilder<HAS_DATA> {
        mut self,
        pairs: impl IntoIterator<Item = (impl Into<String>, impl Into<String>)>,
    ) -> Self {
-        let store_params = self
+        let store_options = self
            .request
            .write_options
            .lance_write_params
            .get_or_insert(Default::default())
            .store_params
+            .get_or_insert(Default::default())
+            .storage_options
            .get_or_insert(Default::default());
-        let updates = pairs
-            .into_iter()
-            .map(|(key, value)| (key.into(), value.into()));
-        merge_storage_options(store_params, updates);
+
+        for (key, value) in pairs {
+            store_options.insert(key.into(), value.into());
+        }
        self
    }

@@ -374,21 +318,23 @@ impl<const HAS_DATA: bool> CreateTableBuilder<HAS_DATA> {
    /// This has no effect in LanceDB Cloud.
    #[deprecated(since = "0.15.1", note = "Use `database_options` instead")]
    pub fn enable_v2_manifest_paths(mut self, use_v2_manifest_paths: bool) -> Self {
-        let store_params = self
+        let storage_options = self
            .request
            .write_options
            .lance_write_params
            .get_or_insert_with(Default::default)
            .store_params
+            .get_or_insert_with(Default::default)
+            .storage_options
            .get_or_insert_with(Default::default);
-        let value = if use_v2_manifest_paths {
-            "true".to_string()
-        } else {
-            "false".to_string()
-        };
-        merge_storage_options(
-            store_params,
-            [(OPT_NEW_TABLE_V2_MANIFEST_PATHS.to_string(), value)],
+
+        storage_options.insert(
+            OPT_NEW_TABLE_V2_MANIFEST_PATHS.to_string(),
+            if use_v2_manifest_paths {
+                "true".to_string()
+            } else {
+                "false".to_string()
+            },
        );
        self
    }
@@ -398,19 +344,19 @@ impl<const HAS_DATA: bool> CreateTableBuilder<HAS_DATA> {
    /// The default is `LanceFileVersion::Stable`.
    #[deprecated(since = "0.15.1", note = "Use `database_options` instead")]
    pub fn data_storage_version(mut self, data_storage_version: LanceFileVersion) -> Self {
-        let store_params = self
+        let storage_options = self
            .request
            .write_options
            .lance_write_params
            .get_or_insert_with(Default::default)
            .store_params
+            .get_or_insert_with(Default::default)
+            .storage_options
            .get_or_insert_with(Default::default);
-        merge_storage_options(
-            store_params,
-            [(
-                OPT_NEW_TABLE_STORAGE_VERSION.to_string(),
-                data_storage_version.to_string(),
-            )],
+
+        storage_options.insert(
+            OPT_NEW_TABLE_STORAGE_VERSION.to_string(),
+            data_storage_version.to_string(),
        );
        self
    }
@@ -435,14 +381,13 @@ impl<const HAS_DATA: bool> CreateTableBuilder<HAS_DATA> {
    /// This allows tables to automatically refresh cloud storage credentials
    /// when they expire, enabling long-running operations on remote storage.
    pub fn storage_options_provider(mut self, provider: Arc<dyn StorageOptionsProvider>) -> Self {
-        let store_params = self
-            .request
+        self.request
            .write_options
            .lance_write_params
            .get_or_insert(Default::default())
            .store_params
-            .get_or_insert(Default::default());
-        set_storage_options_provider(store_params, provider);
+            .get_or_insert(Default::default())
+            .storage_options_provider = Some(provider);
        self
    }
 }
@@ -505,13 +450,15 @@ impl OpenTableBuilder {
    ///
    /// See available options at <https://lancedb.com/docs/storage/>
    pub fn storage_option(mut self, key: impl Into<String>, value: impl Into<String>) -> Self {
-        let store_params = self
+        let storage_options = self
            .request
            .lance_read_params
            .get_or_insert(Default::default())
            .store_options
+            .get_or_insert(Default::default())
+            .storage_options
            .get_or_insert(Default::default());
-        merge_storage_options(store_params, [(key.into(), value.into())]);
+        storage_options.insert(key.into(), value.into());
        self
    }

@@ -525,16 +472,18 @@ impl OpenTableBuilder {
        mut self,
        pairs: impl IntoIterator<Item = (impl Into<String>, impl Into<String>)>,
    ) -> Self {
-        let store_params = self
+        let storage_options = self
            .request
            .lance_read_params
            .get_or_insert(Default::default())
            .store_options
+            .get_or_insert(Default::default())
+            .storage_options
            .get_or_insert(Default::default());
-        let updates = pairs
-            .into_iter()
-            .map(|(key, value)| (key.into(), value.into()));
-        merge_storage_options(store_params, updates);
+
+        for (key, value) in pairs {
+            storage_options.insert(key.into(), value.into());
+        }
        self
    }

@@ -558,13 +507,12 @@ impl OpenTableBuilder {
    /// This allows tables to automatically refresh cloud storage credentials
    /// when they expire, enabling long-running operations on remote storage.
    pub fn storage_options_provider(mut self, provider: Arc<dyn StorageOptionsProvider>) -> Self {
-        let store_params = self
-            .request
+        self.request
            .lance_read_params
            .get_or_insert(Default::default())
            .store_options
-            .get_or_insert(Default::default());
-        set_storage_options_provider(store_params, provider);
+            .get_or_insert(Default::default())
+            .storage_options_provider = Some(provider);
        self
    }

@@ -920,10 +868,6 @@ pub struct ConnectBuilder {
    embedding_registry: Option<Arc<dyn EmbeddingRegistry>>,
 }

-#[cfg(feature = "remote")]
-const ENV_VARS_TO_STORAGE_OPTS: [(&str, &str); 1] =
-    [("AZURE_STORAGE_ACCOUNT_NAME", "azure_storage_account_name")];
-
 impl ConnectBuilder {
    /// Create a new [`ConnectOptions`] with the given database URI.
    pub fn new(uri: &str) -> Self {
@@ -1107,27 +1051,11 @@ impl ConnectBuilder {
        self
    }

-    #[cfg(feature = "remote")]
-    fn apply_env_defaults(
-        env_var_to_remote_storage_option: &[(&str, &str)],
-        options: &mut HashMap<String, String>,
-    ) {
-        for (env_key, opt_key) in env_var_to_remote_storage_option {
-            if let Ok(env_value) = std::env::var(env_key) {
-                if !options.contains_key(*opt_key) {
-                    options.insert((*opt_key).to_string(), env_value);
-                }
-            }
-        }
-    }
-
    #[cfg(feature = "remote")]
    fn execute_remote(self) -> Result<Connection> {
        use crate::remote::db::RemoteDatabaseOptions;

-        let mut merged_options = self.request.options.clone();
-        Self::apply_env_defaults(&ENV_VARS_TO_STORAGE_OPTS, &mut merged_options);
-        let options = RemoteDatabaseOptions::parse_from_map(&merged_options)?;
+        let options = RemoteDatabaseOptions::parse_from_map(&self.request.options)?;

        let region = options.region.ok_or_else(|| Error::InvalidInput {
            message: "A region is required when connecting to LanceDb Cloud".to_string(),
@@ -1349,6 +1277,8 @@ mod test_utils {

 #[cfg(test)]
 mod tests {
+    use std::fs::create_dir_all;
+
    use crate::database::listing::{ListingDatabaseOptions, NewTableConfig};
    use crate::query::QueryBase;
    use crate::query::{ExecutableQuery, QueryExecutionOptions};
@@ -1372,23 +1302,6 @@ mod tests {
        assert_eq!(tc.connection.uri(), tc.uri);
    }

-    #[cfg(feature = "remote")]
-    #[test]
-    fn test_apply_env_defaults() {
-        let env_key = "TEST_APPLY_ENV_DEFAULTS_ENVIRONMENT_VARIABLE_ENV_KEY";
-        let env_val = "TEST_APPLY_ENV_DEFAULTS_ENVIRONMENT_VARIABLE_ENV_VAL";
-        let opts_key = "test_apply_env_defaults_environment_variable_opts_key";
-        std::env::set_var(env_key, env_val);
-
-        let mut options = HashMap::new();
-        ConnectBuilder::apply_env_defaults(&[(env_key, opts_key)], &mut options);
-        assert_eq!(Some(&env_val.to_string()), options.get(opts_key));
-
-        options.insert(opts_key.to_string(), "EXPLICIT-VALUE".to_string());
-        ConnectBuilder::apply_env_defaults(&[(env_key, opts_key)], &mut options);
-        assert_eq!(Some(&"EXPLICIT-VALUE".to_string()), options.get(opts_key));
-    }
-
    #[cfg(not(windows))]
    #[tokio::test]
    async fn test_connect_relative() {
@@ -1613,27 +1526,18 @@ mod tests {

    #[tokio::test]
    async fn drop_table() {
-        let tc = new_test_connection().await.unwrap();
-        let db = tc.connection;
+        let tmp_dir = tempdir().unwrap();

-        if tc.is_remote {
-            // All the typical endpoints such as s3:///, file-object-store:///, etc. treat drop_table
-            // as idempotent.
-            assert!(db.drop_table("invalid_table", &[]).await.is_ok());
-        } else {
-            // The behavior of drop_table when using a file:/// endpoint differs from all other
-            // object providers, in that it returns an error when deleting a non-existent table.
-            assert!(matches!(
-                db.drop_table("invalid_table", &[]).await,
-                Err(crate::Error::TableNotFound { .. }),
-            ));
-        }
+        let uri = tmp_dir.path().to_str().unwrap();
+        let db = connect(uri).execute().await.unwrap();

-        let schema = Arc::new(Schema::new(vec![Field::new("x", DataType::Int32, false)]));
-        db.create_empty_table("table1", schema.clone())
-            .execute()
-            .await
-            .unwrap();
+        // drop non-exist table
+        assert!(matches!(
+            db.drop_table("invalid_table", &[]).await,
+            Err(crate::Error::TableNotFound { .. }),
+        ));
+
+        create_dir_all(tmp_dir.path().join("table1.lance")).unwrap();
        db.drop_table("table1", &[]).await.unwrap();

        let tables = db.table_names().execute().await.unwrap();
@@ -1720,128 +1624,4 @@ 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);
-    }
 }
--- a/rust/lancedb/src/database/listing.rs
+++ b/rust/lancedb/src/database/listing.rs
@@ -12,7 +12,7 @@ use lance::dataset::{builder::DatasetBuilder, ReadParams, WriteMode};
 use lance::io::{ObjectStore, ObjectStoreParams, WrappingObjectStore};
 use lance_datafusion::utils::StreamingWriteSource;
 use lance_encoding::version::LanceFileVersion;
-use lance_io::object_store::{StorageOptionsAccessor, StorageOptionsProvider};
+use lance_io::object_store::StorageOptionsProvider;
 use lance_table::io::commit::commit_handler_from_url;
 use object_store::local::LocalFileSystem;
 use snafu::ResultExt;
@@ -356,13 +356,7 @@ impl ListingDatabase {
                    .clone()
                    .unwrap_or_else(|| Arc::new(lance::session::Session::default()));
                let os_params = ObjectStoreParams {
-                    storage_options_accessor: if options.storage_options.is_empty() {
-                        None
-                    } else {
-                        Some(Arc::new(StorageOptionsAccessor::with_static_options(
-                            options.storage_options.clone(),
-                        )))
-                    },
+                    storage_options: Some(options.storage_options.clone()),
                    ..Default::default()
                };
                let (object_store, base_path) = ObjectStore::from_uri_and_params(
@@ -498,13 +492,7 @@ impl ListingDatabase {

    async fn drop_tables(&self, names: Vec<String>) -> Result<()> {
        let object_store_params = ObjectStoreParams {
-            storage_options_accessor: if self.storage_options.is_empty() {
-                None
-            } else {
-                Some(Arc::new(StorageOptionsAccessor::with_static_options(
-                    self.storage_options.clone(),
-                )))
-            },
+            storage_options: Some(self.storage_options.clone()),
            ..Default::default()
        };
        let mut uri = self.uri.clone();
@@ -553,7 +541,7 @@ impl ListingDatabase {
            .lance_write_params
            .as_ref()
            .and_then(|p| p.store_params.as_ref())
-            .and_then(|sp| sp.storage_options());
+            .and_then(|sp| sp.storage_options.as_ref());

        let storage_version_override = storage_options
            .and_then(|opts| opts.get(OPT_NEW_TABLE_STORAGE_VERSION))
@@ -604,20 +592,21 @@ impl ListingDatabase {
        // will cause a new connection to be created, and that connection will
        // be dropped from the cache when python GCs the table object, which
        // confounds reuse across tables.
-        if !self.storage_options.is_empty() || self.storage_options_provider.is_some() {
-            let store_params = write_params
+        if !self.storage_options.is_empty() {
+            let storage_options = write_params
                .store_params
+                .get_or_insert_with(Default::default)
+                .storage_options
                .get_or_insert_with(Default::default);
-            let mut storage_options = store_params.storage_options().cloned().unwrap_or_default();
-            if !self.storage_options.is_empty() {
-                self.inherit_storage_options(&mut storage_options);
-            }
-            let accessor = if let Some(ref provider) = self.storage_options_provider {
-                StorageOptionsAccessor::with_initial_and_provider(storage_options, provider.clone())
-            } else {
-                StorageOptionsAccessor::with_static_options(storage_options)
-            };
-            store_params.storage_options_accessor = Some(Arc::new(accessor));
+            self.inherit_storage_options(storage_options);
+        }
+
+        // Set storage options provider if available
+        if self.storage_options_provider.is_some() {
+            write_params
+                .store_params
+                .get_or_insert_with(Default::default)
+                .storage_options_provider = self.storage_options_provider.clone();
        }

        write_params.data_storage_version = self
@@ -903,13 +892,7 @@ impl Database for ListingDatabase {
        validate_table_name(&request.target_table_name)?;

        let storage_params = ObjectStoreParams {
-            storage_options_accessor: if self.storage_options.is_empty() {
-                None
-            } else {
-                Some(Arc::new(StorageOptionsAccessor::with_static_options(
-                    self.storage_options.clone(),
-                )))
-            },
+            storage_options: Some(self.storage_options.clone()),
            ..Default::default()
        };
        let read_params = ReadParams {
@@ -973,28 +956,25 @@ impl Database for ListingDatabase {
        // will cause a new connection to be created, and that connection will
        // be dropped from the cache when python GCs the table object, which
        // confounds reuse across tables.
-        if !self.storage_options.is_empty() || self.storage_options_provider.is_some() {
-            let store_params = request
+        if !self.storage_options.is_empty() {
+            let storage_options = request
                .lance_read_params
                .get_or_insert_with(Default::default)
                .store_options
+                .get_or_insert_with(Default::default)
+                .storage_options
                .get_or_insert_with(Default::default);
-            let mut storage_options = store_params.storage_options().cloned().unwrap_or_default();
-            if !self.storage_options.is_empty() {
-                self.inherit_storage_options(&mut storage_options);
-            }
-            // Preserve request-level provider if no connection-level provider exists
-            let request_provider = store_params
-                .storage_options_accessor
-                .as_ref()
-                .and_then(|a| a.provider().cloned());
-            let provider = self.storage_options_provider.clone().or(request_provider);
-            let accessor = if let Some(provider) = provider {
-                StorageOptionsAccessor::with_initial_and_provider(storage_options, provider)
-            } else {
-                StorageOptionsAccessor::with_static_options(storage_options)
-            };
-            store_params.storage_options_accessor = Some(Arc::new(accessor));
+            self.inherit_storage_options(storage_options);
+        }
+
+        // Set storage options provider if available
+        if self.storage_options_provider.is_some() {
+            request
+                .lance_read_params
+                .get_or_insert_with(Default::default)
+                .store_options
+                .get_or_insert_with(Default::default)
+                .storage_options_provider = self.storage_options_provider.clone();
        }

        // Some ReadParams are exposed in the OpenTableBuilder, but we also
@@ -1901,9 +1881,7 @@ mod tests {
        let write_options = WriteOptions {
            lance_write_params: Some(lance::dataset::WriteParams {
                store_params: Some(lance::io::ObjectStoreParams {
-                    storage_options_accessor: Some(Arc::new(
-                        StorageOptionsAccessor::with_static_options(storage_options),
-                    )),
+                    storage_options: Some(storage_options),
                    ..Default::default()
                }),
                ..Default::default()
@@ -1977,9 +1955,7 @@ mod tests {
        let write_options = WriteOptions {
            lance_write_params: Some(lance::dataset::WriteParams {
                store_params: Some(lance::io::ObjectStoreParams {
-                    storage_options_accessor: Some(Arc::new(
-                        StorageOptionsAccessor::with_static_options(storage_options),
-                    )),
+                    storage_options: Some(storage_options),
                    ..Default::default()
                }),
                ..Default::default()
--- a/rust/lancedb/src/database/namespace.rs
+++ b/rust/lancedb/src/database/namespace.rs
@@ -9,15 +9,14 @@ use std::sync::Arc;
 use async_trait::async_trait;
 use lance_namespace::{
    models::{
-        CreateEmptyTableRequest, CreateNamespaceRequest, CreateNamespaceResponse,
-        DeclareTableRequest, DescribeNamespaceRequest, DescribeNamespaceResponse,
-        DescribeTableRequest, DropNamespaceRequest, DropNamespaceResponse, DropTableRequest,
-        ListNamespacesRequest, ListNamespacesResponse, ListTablesRequest, ListTablesResponse,
+        CreateNamespaceRequest, CreateNamespaceResponse, DeclareTableRequest,
+        DescribeNamespaceRequest, DescribeNamespaceResponse, DescribeTableRequest,
+        DropNamespaceRequest, DropNamespaceResponse, DropTableRequest, ListNamespacesRequest,
+        ListNamespacesResponse, ListTablesRequest, ListTablesResponse,
    },
    LanceNamespace,
 };
 use lance_namespace_impls::ConnectBuilder;
-use log::warn;

 use crate::database::ReadConsistency;
 use crate::error::{Error, Result};
@@ -155,6 +154,7 @@ impl Database for LanceNamespaceDatabase {
        table_id.push(request.name.clone());
        let describe_request = DescribeTableRequest {
            id: Some(table_id.clone()),
+            version: None,
            ..Default::default()
        };

@@ -205,53 +205,26 @@ impl Database for LanceNamespaceDatabase {
        let mut table_id = request.namespace.clone();
        table_id.push(request.name.clone());

-        // Try declare_table first, falling back to create_empty_table for backwards
-        // compatibility with older namespace clients that don't support declare_table
-        let declare_request = DeclareTableRequest {
+        let create_empty_request = DeclareTableRequest {
            id: Some(table_id.clone()),
+            location: None,
+            vend_credentials: None,
            ..Default::default()
        };

-        let location = match self.namespace.declare_table(declare_request).await {
-            Ok(response) => response.location.ok_or_else(|| Error::Runtime {
-                message: "Table location is missing from declare_table response".to_string(),
-            })?,
-            Err(e) => {
-                // Check if the error is "not supported" and try create_empty_table as fallback
-                let err_str = e.to_string().to_lowercase();
-                if err_str.contains("not supported") || err_str.contains("not implemented") {
-                    warn!(
-                        "declare_table is not supported by the namespace client, \
-                        falling back to deprecated create_empty_table. \
-                        create_empty_table is deprecated and will be removed in Lance 3.0.0. \
-                        Please upgrade your namespace client to support declare_table."
-                    );
-                    #[allow(deprecated)]
-                    let create_empty_request = CreateEmptyTableRequest {
-                        id: Some(table_id.clone()),
-                        ..Default::default()
-                    };
+        let create_empty_response = self
+            .namespace
+            .declare_table(create_empty_request)
+            .await
+            .map_err(|e| Error::Runtime {
+                message: format!("Failed to declare table: {}", e),
+            })?;

-                    #[allow(deprecated)]
-                    let create_response = self
-                        .namespace
-                        .create_empty_table(create_empty_request)
-                        .await
-                        .map_err(|e| Error::Runtime {
-                            message: format!("Failed to create empty table: {}", e),
-                        })?;
-
-                    create_response.location.ok_or_else(|| Error::Runtime {
-                        message: "Table location is missing from create_empty_table response"
-                            .to_string(),
-                    })?
-                } else {
-                    return Err(Error::Runtime {
-                        message: format!("Failed to declare table: {}", e),
-                    });
-                }
-            }
-        };
+        let location = create_empty_response
+            .location
+            .ok_or_else(|| Error::Runtime {
+                message: "Table location is missing from create_empty_table response".to_string(),
+            })?;

        let native_table = NativeTable::create_from_namespace(
            self.namespace.clone(),
@@ -466,6 +439,8 @@ mod tests {
        // Create a child namespace first
        conn.create_namespace(CreateNamespaceRequest {
            id: Some(vec!["test_ns".into()]),
+            mode: None,
+            properties: None,
            ..Default::default()
        })
        .await
@@ -526,6 +501,8 @@ mod tests {
        // Create a child namespace first
        conn.create_namespace(CreateNamespaceRequest {
            id: Some(vec!["test_ns".into()]),
+            mode: None,
+            properties: None,
            ..Default::default()
        })
        .await
@@ -589,6 +566,8 @@ mod tests {
        // Create a child namespace first
        conn.create_namespace(CreateNamespaceRequest {
            id: Some(vec!["test_ns".into()]),
+            mode: None,
+            properties: None,
            ..Default::default()
        })
        .await
@@ -672,6 +651,8 @@ mod tests {
        // Create a child namespace first
        conn.create_namespace(CreateNamespaceRequest {
            id: Some(vec!["test_ns".into()]),
+            mode: None,
+            properties: None,
            ..Default::default()
        })
        .await
@@ -727,6 +708,8 @@ mod tests {
        // Create a child namespace first
        conn.create_namespace(CreateNamespaceRequest {
            id: Some(vec!["test_ns".into()]),
+            mode: None,
+            properties: None,
            ..Default::default()
        })
        .await
@@ -807,6 +790,8 @@ mod tests {
        // Create a child namespace first
        conn.create_namespace(CreateNamespaceRequest {
            id: Some(vec!["test_ns".into()]),
+            mode: None,
+            properties: None,
            ..Default::default()
        })
        .await
@@ -840,6 +825,8 @@ mod tests {
        // Create a child namespace first
        conn.create_namespace(CreateNamespaceRequest {
            id: Some(vec!["test_ns".into()]),
+            mode: None,
+            properties: None,
            ..Default::default()
        })
        .await
--- a/rust/lancedb/src/dataloader/permutation/builder.rs
+++ b/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, Select},
+    query::{ExecutableQuery, QueryBase},
    Error, Result, Table,
 };

@@ -27,8 +27,6 @@ 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 {
@@ -169,20 +167,10 @@ 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(memory_limit, 1.0)
+                .with_memory_limit(100 * 1024 * 1024, 1.0)
                .with_disk_manager_builder(
                    DiskManagerBuilder::default()
                        .with_mode(self.config.temp_dir.to_disk_manager_mode()),
@@ -244,7 +232,7 @@ 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().select(Select::columns(&[ROW_ID]));
+        let mut rows = self.base_table.query().with_row_id();

        if let Some(filter) = &self.config.filter {
            rows = rows.only_if(filter);
@@ -333,47 +321,6 @@ 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();
@@ -405,6 +352,8 @@ 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!(
--- a/rust/lancedb/src/dataloader/permutation/shuffle.rs
+++ b/rust/lancedb/src/dataloader/permutation/shuffle.rs
@@ -171,7 +171,7 @@ impl Shuffler {
            // This is kind of an annoying limitation but if we allow runt clumps from batches then
            // clumps will get unaligned and we will mess up the clumps when we do the in-memory
            // shuffle step.  If this is a problem we can probably figure out a better way to do this.
-            if !is_last && !(batch.num_rows() as u64).is_multiple_of(clump_size) {
+            if !is_last && batch.num_rows() as u64 % clump_size != 0 {
                return Err(Error::Runtime {
                    message: format!(
                        "Expected batch size ({}) to be divisible by clump size ({})",
--- a/rust/lancedb/src/dataloader/permutation/split.rs
+++ b/rust/lancedb/src/dataloader/permutation/split.rs
@@ -1,9 +1,12 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors

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

 use arrow_array::{Array, BooleanArray, RecordBatch, UInt64Array};
@@ -12,8 +15,6 @@ 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::{
@@ -157,7 +158,7 @@ impl Splitter {
                remaining_in_split
            };

-            split_ids.extend(std::iter::repeat_n(split_id as u64, rows_to_add as usize));
+            split_ids.extend(iter::repeat(split_id as u64).take(rows_to_add as usize));
            if done {
                // Quit early if we've run out of splits
                break;
@@ -362,15 +363,11 @@ 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()),
-                (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))
-            }
+            SplitStrategy::Calculated { calculation } => query.select(Select::Dynamic(vec![(
+                SPLIT_ID_COLUMN.to_string(),
+                calculation.clone(),
+            )])),
+            SplitStrategy::Hash { columns, .. } => query.select(Select::Columns(columns.clone())),
            _ => query,
        }
    }
@@ -665,7 +662,7 @@ mod tests {
        assert_eq!(split_batch.num_rows(), total_split_sizes as usize);
        let mut expected = Vec::with_capacity(total_split_sizes as usize);
        for (i, size) in expected_split_sizes.iter().enumerate() {
-            expected.extend(std::iter::repeat_n(i as u64, *size as usize));
+            expected.extend(iter::repeat(i as u64).take(*size as usize));
        }
        let expected = Arc::new(UInt64Array::from(expected)) as Arc<dyn Array>;

--- a/rust/lancedb/src/index/vector.rs
+++ b/rust/lancedb/src/index/vector.rs
@@ -297,10 +297,10 @@ impl IvfPqIndexBuilder {
 }

 pub(crate) fn suggested_num_sub_vectors(dim: u32) -> u32 {
-    if dim.is_multiple_of(16) {
+    if dim % 16 == 0 {
        // Should be more aggressive than this default.
        dim / 16
-    } else if dim.is_multiple_of(8) {
+    } else if dim % 8 == 0 {
        dim / 8
    } else {
        log::warn!(
--- a/rust/lancedb/src/lib.rs
+++ b/rust/lancedb/src/lib.rs
@@ -51,19 +51,24 @@
 //! - `s3://bucket/path/to/database` or `gs://bucket/path/to/database` - database on cloud object store
 //! - `db://dbname` - Lance Cloud
 //!
-//! You can also use [`ConnectBuilder`] to configure the connection to the database.
+//! You can also use [`ConnectOptions`] to configure the connection to the database.
 //!
 //! ```rust
+//! # #[cfg(feature = "aws")]
+//! # {
+//! use object_store::aws::AwsCredential;
 //! # tokio::runtime::Runtime::new().unwrap().block_on(async {
 //! let db = lancedb::connect("data/sample-lancedb")
-//!     .storage_options([
-//!         ("aws_access_key_id", "some_key"),
-//!         ("aws_secret_access_key", "some_secret"),
-//!     ])
+//!     .aws_creds(AwsCredential {
+//!         key_id: "some_key".to_string(),
+//!         secret_key: "some_secret".to_string(),
+//!         token: None,
+//!     })
 //!     .execute()
 //!     .await
 //!     .unwrap();
 //! # });
+//! # }
 //! ```
 //!
 //! LanceDB uses [arrow-rs](https://github.com/apache/arrow-rs) to define schema, data types and array itself.
--- a/rust/lancedb/src/remote/db.rs
+++ b/rust/lancedb/src/remote/db.rs
@@ -1718,6 +1718,8 @@ mod tests {
            let namespace = vec!["test_ns".to_string()];
            conn.create_namespace(CreateNamespaceRequest {
                id: Some(namespace.clone()),
+                mode: None,
+                properties: None,
                ..Default::default()
            })
            .await
@@ -1743,6 +1745,8 @@ mod tests {
            let list_response = conn
                .list_tables(ListTablesRequest {
                    id: Some(namespace.clone()),
+                    page_token: None,
+                    limit: None,
                    ..Default::default()
                })
                .await
@@ -1754,6 +1758,8 @@ mod tests {
            let list_response = namespace_client
                .list_tables(ListTablesRequest {
                    id: Some(namespace.clone()),
+                    page_token: None,
+                    limit: None,
                    ..Default::default()
                })
                .await
@@ -1794,6 +1800,8 @@ mod tests {
            let namespace = vec!["multi_table_ns".to_string()];
            conn.create_namespace(CreateNamespaceRequest {
                id: Some(namespace.clone()),
+                mode: None,
+                properties: None,
                ..Default::default()
            })
            .await
@@ -1819,6 +1827,8 @@ mod tests {
            let list_response = conn
                .list_tables(ListTablesRequest {
                    id: Some(namespace.clone()),
+                    page_token: None,
+                    limit: None,
                    ..Default::default()
                })
                .await
--- a/rust/lancedb/src/table.rs
+++ b/rust/lancedb/src/table.rs
@@ -40,7 +40,7 @@ use lance_index::vector::pq::PQBuildParams;
 use lance_index::vector::sq::builder::SQBuildParams;
 use lance_index::DatasetIndexExt;
 use lance_index::IndexType;
-use lance_io::object_store::{LanceNamespaceStorageOptionsProvider, StorageOptionsAccessor};
+use lance_io::object_store::LanceNamespaceStorageOptionsProvider;
 use lance_namespace::models::{
    QueryTableRequest as NsQueryTableRequest, QueryTableRequestColumns,
    QueryTableRequestFullTextQuery, QueryTableRequestVector, StringFtsQuery,
@@ -79,11 +79,10 @@ 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};
@@ -447,6 +446,15 @@ 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.
@@ -1417,7 +1425,9 @@ impl Table {
            })
            .collect::<Vec<_>>();

-        let unioned = Arc::new(UnionExec::new(projected_plans));
+        let unioned = UnionExec::try_new(projected_plans).map_err(|e| Error::Runtime {
+            message: format!("Failed to build union plan: {e}"),
+        })?;
        // We require 1 partition in the final output
        let repartitioned = RepartitionExec::try_new(
            unioned,
@@ -1658,14 +1668,18 @@ impl NativeTable {

        // Use DatasetBuilder::from_namespace which automatically fetches location
        // and storage options from the namespace
-        let builder = DatasetBuilder::from_namespace(namespace_client.clone(), table_id)
-            .await
-            .map_err(|e| match e {
-                lance::Error::Namespace { source, .. } => Error::Runtime {
-                    message: format!("Failed to get table info from namespace: {:?}", source),
-                },
-                source => Error::Lance { source },
-            })?;
+        let builder = DatasetBuilder::from_namespace(
+            namespace_client.clone(),
+            table_id,
+            false, // Don't ignore namespace storage options
+        )
+        .await
+        .map_err(|e| match e {
+            lance::Error::Namespace { source, .. } => Error::Runtime {
+                message: format!("Failed to get table info from namespace: {:?}", source),
+            },
+            source => Error::Lance { source },
+        })?;

        let dataset = builder
            .with_read_params(params)
@@ -1869,13 +1883,7 @@ impl NativeTable {
        let store_params = params
            .store_params
            .get_or_insert_with(ObjectStoreParams::default);
-        let accessor = match store_params.storage_options().cloned() {
-            Some(options) => {
-                StorageOptionsAccessor::with_initial_and_provider(options, storage_options_provider)
-            }
-            None => StorageOptionsAccessor::with_provider(storage_options_provider),
-        };
-        store_params.storage_options_accessor = Some(Arc::new(accessor));
+        store_params.storage_options_provider = Some(storage_options_provider);

        // Patch the params if we have a write store wrapper
        let params = match write_store_wrapper.clone() {
@@ -2051,7 +2059,7 @@ impl NativeTable {
            return provided;
        }
        let suggested = suggested_num_sub_vectors(dim);
-        if num_bits.is_some_and(|num_bits| num_bits == 4) && !suggested.is_multiple_of(2) {
+        if num_bits.is_some_and(|num_bits| num_bits == 4) && suggested % 2 != 0 {
            // num_sub_vectors must be even when 4 bits are used
            suggested + 1
        } else {
@@ -2341,7 +2349,7 @@ impl NativeTable {
                };

                // Convert select to columns list
-                let columns = match &vq.base.select {
+                let columns: Option<Box<QueryTableRequestColumns>> = match &vq.base.select {
                    Select::All => None,
                    Select::Columns(cols) => Some(Box::new(QueryTableRequestColumns {
                        column_names: Some(cols.clone()),
@@ -2399,6 +2407,7 @@ impl NativeTable {
                    with_row_id: Some(vq.base.with_row_id),
                    bypass_vector_index: Some(!vq.use_index),
                    full_text_query,
+                    version: None,
                    ..Default::default()
                })
            }
@@ -2417,7 +2426,7 @@ impl NativeTable {
                    .map(|f| self.filter_to_sql(f))
                    .transpose()?;

-                let columns = match &q.select {
+                let columns: Option<Box<QueryTableRequestColumns>> = match &q.select {
                    Select::All => None,
                    Select::Columns(cols) => Some(Box::new(QueryTableRequestColumns {
                        column_names: Some(cols.clone()),
@@ -2461,10 +2470,18 @@ impl NativeTable {
                    columns,
                    prefilter: Some(q.prefilter),
                    offset: q.offset.map(|o| o as i32),
+                    ef: None,
+                    refine_factor: None,
+                    distance_type: None,
+                    nprobes: None,
                    vector_column: None, // No vector column for plain queries
                    with_row_id: Some(q.with_row_id),
                    bypass_vector_index: Some(true), // No vector index for plain queries
                    full_text_query,
+                    version: None,
+                    fast_search: None,
+                    lower_bound: None,
+                    upper_bound: None,
                    ..Default::default()
                })
            }
@@ -3070,8 +3087,11 @@ impl BaseTable for NativeTable {

    /// Delete rows from the table
    async fn delete(&self, predicate: &str) -> Result<DeleteResult> {
-        // Delegate to the submodule implementation
-        delete::execute_delete(self, predicate).await
+        let mut dataset = self.dataset.get_mut().await?;
+        dataset.delete(predicate).await?;
+        Ok(DeleteResult {
+            version: dataset.version().version,
+        })
    }

    async fn tags(&self) -> Result<Box<dyn Tags + '_>> {
@@ -3224,7 +3244,7 @@ impl BaseTable for NativeTable {
            .get()
            .await
            .ok()
-            .and_then(|dataset| dataset.initial_storage_options().cloned())
+            .and_then(|dataset| dataset.storage_options().cloned())
    }

    async fn index_stats(&self, index_name: &str) -> Result<Option<IndexStatistics>> {
@@ -3389,6 +3409,7 @@ pub struct FragmentSummaryStats {
 #[cfg(test)]
 #[allow(deprecated)]
 mod tests {
+    use std::iter;
    use std::sync::atomic::{AtomicBool, Ordering};
    use std::sync::Arc;
    use std::time::Duration;
@@ -4005,7 +4026,7 @@ mod tests {
                schema.clone(),
                vec![
                    Arc::new(Int32Array::from_iter_values(offset..(offset + 10))),
-                    Arc::new(Int32Array::from_iter_values(std::iter::repeat_n(age, 10))),
+                    Arc::new(Int32Array::from_iter_values(iter::repeat(age).take(10))),
                ],
            )],
            schema,
@@ -5133,16 +5154,15 @@ mod tests {
        let any_query = AnyQuery::VectorQuery(vq);
        let ns_request = table.convert_to_namespace_query(&any_query).unwrap();

+        let column_names = ns_request
+            .columns
+            .as_ref()
+            .and_then(|cols| cols.column_names.clone());
+
        assert_eq!(ns_request.k, 10);
        assert_eq!(ns_request.offset, Some(5));
        assert_eq!(ns_request.filter, Some("id > 0".to_string()));
-        assert_eq!(
-            ns_request
-                .columns
-                .as_ref()
-                .and_then(|c| c.column_names.as_ref()),
-            Some(&vec!["id".to_string()])
-        );
+        assert_eq!(column_names, Some(vec!["id".to_string()]));
        assert_eq!(ns_request.vector_column, Some("vector".to_string()));
        assert_eq!(ns_request.distance_type, Some("l2".to_string()));
        assert!(ns_request.vector.single_vector.is_some());
@@ -5179,17 +5199,16 @@ mod tests {
        let any_query = AnyQuery::Query(q);
        let ns_request = table.convert_to_namespace_query(&any_query).unwrap();

+        let column_names = ns_request
+            .columns
+            .as_ref()
+            .and_then(|cols| cols.column_names.clone());
+
        // Plain queries should pass an empty vector
        assert_eq!(ns_request.k, 20);
        assert_eq!(ns_request.offset, Some(5));
        assert_eq!(ns_request.filter, Some("id > 5".to_string()));
-        assert_eq!(
-            ns_request
-                .columns
-                .as_ref()
-                .and_then(|c| c.column_names.as_ref()),
-            Some(&vec!["id".to_string()])
-        );
+        assert_eq!(column_names, Some(vec!["id".to_string()]));
        assert_eq!(ns_request.with_row_id, Some(true));
        assert_eq!(ns_request.bypass_vector_index, Some(true));
        assert!(ns_request.vector_column.is_none()); // No vector column for plain queries
--- a/rust/lancedb/src/table/dataset.rs
+++ b/rust/lancedb/src/table/dataset.rs
@@ -100,7 +100,8 @@ impl DatasetRef {
                let should_checkout = match &target_ref {
                    refs::Ref::Version(_, Some(target_ver)) => version != target_ver,
                    refs::Ref::Version(_, None) => true, // No specific version, always checkout
-                    refs::Ref::Tag(_) => true,           // Always checkout for tags
+                    refs::Ref::VersionNumber(target_ver) => version != target_ver,
+                    refs::Ref::Tag(_) => true, // Always checkout for tags
                };

                if should_checkout {
--- a/rust/lancedb/src/table/delete.rs
+++ b/rust/lancedb/src/table/delete.rs
@@ -1,161 +0,0 @@
-// 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"
-        );
-    }
-}
--- a/rust/lancedb/tests/embedding_registry_test.rs
+++ b/rust/lancedb/tests/embedding_registry_test.rs
@@ -4,6 +4,7 @@
 use std::{
    borrow::Cow,
    collections::{HashMap, HashSet},
+    iter::repeat,
    sync::Arc,
 };

@@ -267,10 +268,9 @@ fn create_some_records() -> Result<impl IntoArrow> {
            schema.clone(),
            vec![
                Arc::new(Int32Array::from_iter_values(0..TOTAL as i32)),
-                Arc::new(StringArray::from_iter(std::iter::repeat_n(
-                    Some("hello world".to_string()),
-                    TOTAL,
-                ))),
+                Arc::new(StringArray::from_iter(
+                    repeat(Some("hello world".to_string())).take(TOTAL),
+                )),
            ],
        )
        .unwrap()]