rename gha task

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

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

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.23.1"
+current_version = "0.24.1"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

.github/workflows/build_linux_wheel/action.yml

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

.github/workflows/build_mac_wheel/action.yml

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

.github/workflows/build_windows_wheel/action.yml

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

.github/workflows/codex-update-lance-dependency.yml

@@ -75,6 +75,13 @@ 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.
 
@@ -84,10 +91,10 @@ 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 "${BRANCH_NAME}" (replace any duplicated hyphens if necessary).
-          6. Stage all relevant files with "git add -A". Commit using the message "chore: update lance dependency to v${VERSION}".
+          6. Stage all relevant files with "git add -A". Commit using the message "${COMMIT_TYPE}: update lance dependency to v${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 "chore: update lance dependency to v${VERSION}". In the body, summarize the dependency bump, clippy/fmt verification, and link the triggering tag (${TAG}).
+          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".
           10. After creating the PR, display the PR URL, "git status --short", and a concise summary of the commands run and their results.
 
           Constraints:

.github/workflows/docs.yml

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

.github/workflows/pypi-publish.yml

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

.github/workflows/python.yml

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

.github/workflows/rust.yml

@@ -48,6 +48,8 @@ jobs:
         run: cargo fmt --all -- --check
       - name: Run clippy
         run: cargo clippy --profile ci --workspace --tests --all-features -- -D warnings
+      - name: Run clippy (without remote feature)
+        run: cargo clippy --profile ci --workspace --tests -- -D warnings
 
   build-no-lock:
     runs-on: ubuntu-24.04
@@ -181,7 +183,7 @@ jobs:
     runs-on: ubuntu-24.04
     strategy:
       matrix:
-        msrv: ["1.78.0"] # This should match up with rust-version in Cargo.toml
+        msrv: ["1.88.0"] # This should match up with rust-version in Cargo.toml
     env:
       # Need up-to-date compilers for kernels
       CC: clang-18
@@ -212,4 +214,6 @@ jobs:
           cargo update -p aws-sdk-sts --precise 1.51.0
           cargo update -p home --precise 0.5.9
       - name: cargo +${{ matrix.msrv }} check
+        env:
+          RUSTUP_TOOLCHAIN: ${{ matrix.msrv }}
         run: cargo check --profile ci --workspace --tests --benches --all-features

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 = "1.78.0"
+rust-version = "1.88.0"
 
 [workspace.dependencies]
-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" }
+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" }
 ahash = "0.8"
 # Note that this one does not include pyarrow
-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"
+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"
 async-trait = "0"
-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"
+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"
 env_logger = "0.11"
-half = { "version" = "2.7.1", default-features = false, features = [
+half = { "version" = "2.6.0", default-features = false, features = [
     "num-traits",
 ] }
 futures = "0"
@@ -59,7 +59,7 @@ rand = "0.9"
 snafu = "0.8"
 url = "2"
 num-traits = "0.2"
-regex = "1.12"
+regex = "1.10"
 lazy_static = "1"
 semver = "1.0.25"
 chrono = "0.4"

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>0.23.1</version>
+    <version>0.24.1</version>
 </dependency>
 ```
 

java/lancedb-core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
       <groupId>com.lancedb</groupId>
       <artifactId>lancedb-parent</artifactId>
-      <version>0.23.1-final.0</version>
+      <version>0.24.1-final.0</version>
       <relativePath>../pom.xml</relativePath>
     </parent>
 

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.23.1-final.0</version>
+    <version>0.24.1-final.0</version>
     <packaging>pom</packaging>
     <name>${project.artifactId}</name>
     <description>LanceDB Java SDK Parent POM</description>

nodejs/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.23.1"
+version = "0.24.1"
 license.workspace = true
 description.workspace = true
 repository.workspace = true

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.23.1",
+	"version": "0.24.1",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",

nodejs/npm/darwin-x64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-x64",
-	"version": "0.23.1",
+	"version": "0.24.1",
 	"os": ["darwin"],
 	"cpu": ["x64"],
 	"main": "lancedb.darwin-x64.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.23.1",
+	"version": "0.24.1",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-musl",
-	"version": "0.23.1",
+	"version": "0.24.1",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-musl.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.23.1",
+	"version": "0.24.1",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-musl",
-	"version": "0.23.1",
+	"version": "0.24.1",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-musl.node",

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

@@ -1,6 +1,6 @@
 {
   "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.23.1",
+  "version": "0.24.1",
   "os": [
     "win32"
   ],

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.23.1",
+	"version": "0.24.1",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@lancedb/lancedb",
-  "version": "0.23.1",
+  "version": "0.24.1",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@lancedb/lancedb",
-      "version": "0.23.1",
+      "version": "0.24.1",
       "cpu": [
         "x64",
         "arm64"

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.23.1",
+  "version": "0.24.1",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.27.0-beta.0"
+current_version = "0.27.1"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

python/CONTRIBUTING.md

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

python/Cargo.toml

@@ -1,28 +1,28 @@
 [package]
 name = "lancedb-python"
-version = "0.27.0-beta.0"
+version = "0.27.1"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true
 repository.workspace = true
 keywords.workspace = true
 categories.workspace = true
-rust-version = "1.75.0"
+rust-version = "1.88.0"
 
 [lib]
 name = "_lancedb"
 crate-type = ["cdylib"]
 
 [dependencies]
-arrow = { version = "57.2", features = ["pyarrow"] }
+arrow = { version = "56.2", 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 = "0.26", features = ["extension-module", "abi3-py39"] }
-pyo3-async-runtimes = { version = "0.26", features = [
+pyo3 = { version = "0.25", features = ["extension-module", "abi3-py310"] }
+pyo3-async-runtimes = { version = "0.25", features = [
     "attributes",
     "tokio-runtime",
 ] }
@@ -32,9 +32,9 @@ snafu.workspace = true
 tokio = { version = "1.40", features = ["sync"] }
 
 [build-dependencies]
-pyo3-build-config = { version = "0.26", features = [
+pyo3-build-config = { version = "0.25", features = [
     "extension-module",
-    "abi3-py39",
+    "abi3-py310",
 ] }
 
 [features]

python/pyproject.toml

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

python/python/lancedb/pydantic.py

@@ -6,7 +6,6 @@
 from __future__ import annotations
 
 import inspect
-import sys
 import types
 from abc import ABC, abstractmethod
 from datetime import date, datetime
@@ -141,14 +140,6 @@ def Vector(
                 raise TypeError("A list of numbers or numpy.ndarray is needed")
             return cls(v)
 
-        if PYDANTIC_VERSION.major < 2:
-
-            @classmethod
-            def __modify_schema__(cls, field_schema: Dict[str, Any]):
-                field_schema["items"] = {"type": "number"}
-                field_schema["maxItems"] = dim
-                field_schema["minItems"] = dim
-
     return FixedSizeList
 
 
@@ -226,26 +217,14 @@ def MultiVector(
         def __get_validators__(cls) -> Generator[Callable, None, None]:
             yield cls.validate
 
-        # For pydantic v1
         @classmethod
-        def validate(cls, v):
-            if not isinstance(v, (list, range)):
-                raise TypeError("A list of vectors is needed")
-            for vec in v:
-                if not isinstance(vec, (list, range, np.ndarray)) or len(vec) != dim:
-                    raise TypeError(f"Each vector must be a list of {dim} numbers")
-            return cls(v)
-
-        if PYDANTIC_VERSION.major < 2:
-
-            @classmethod
-            def __modify_schema__(cls, field_schema: Dict[str, Any]):
-                field_schema["items"] = {
-                    "type": "array",
-                    "items": {"type": "number"},
-                    "minItems": dim,
-                    "maxItems": dim,
-                }
+        def __modify_schema__(cls, field_schema: Dict[str, Any]):
+            field_schema["items"] = {
+                "type": "array",
+                "items": {"type": "number"},
+                "minItems": dim,
+                "maxItems": dim,
+            }
 
     return MultiVectorList
 
@@ -275,35 +254,31 @@ def _py_type_to_arrow_type(py_type: Type[Any], field: FieldInfo) -> pa.DataType:
         return pa.timestamp("us", tz=tz)
     elif getattr(py_type, "__origin__", None) in (list, tuple):
         child = py_type.__args__[0]
-        return pa.list_(_py_type_to_arrow_type(child, field))
+        return _pydantic_list_child_to_arrow(child, field)
     raise TypeError(
         f"Converting Pydantic type to Arrow Type: unsupported type {py_type}."
     )
 
 
-if PYDANTIC_VERSION.major < 2:
-
-    def _pydantic_model_to_fields(model: pydantic.BaseModel) -> List[pa.Field]:
-        return [
-            _pydantic_to_field(name, field) for name, field in model.__fields__.items()
-        ]
-
-else:
-
-    def _pydantic_model_to_fields(model: pydantic.BaseModel) -> List[pa.Field]:
-        return [
-            _pydantic_to_field(name, field)
-            for name, field in model.model_fields.items()
-        ]
+def _pydantic_model_to_fields(model: pydantic.BaseModel) -> List[pa.Field]:
+    return [
+        _pydantic_to_field(name, field) for name, field in model.model_fields.items()
+    ]
 
 
 def _pydantic_type_to_arrow_type(tp: Any, field: FieldInfo) -> pa.DataType:
+    def _safe_issubclass(candidate: Any, base: type) -> bool:
+        try:
+            return issubclass(candidate, base)
+        except TypeError:
+            return False
+
     if inspect.isclass(tp):
-        if issubclass(tp, pydantic.BaseModel):
+        if _safe_issubclass(tp, pydantic.BaseModel):
             # Struct
             fields = _pydantic_model_to_fields(tp)
             return pa.struct(fields)
-        if issubclass(tp, FixedSizeListMixin):
+        if _safe_issubclass(tp, FixedSizeListMixin):
             if getattr(tp, "is_multi_vector", lambda: False)():
                 return pa.list_(pa.list_(tp.value_arrow_type(), tp.dim()))
             # For regular Vector
@@ -311,45 +286,67 @@ def _pydantic_type_to_arrow_type(tp: Any, field: FieldInfo) -> pa.DataType:
     return _py_type_to_arrow_type(tp, field)
 
 
+def _pydantic_list_child_to_arrow(child: Any, field: FieldInfo) -> pa.DataType:
+    unwrapped = _unwrap_optional_annotation(child)
+    if unwrapped is not None:
+        return pa.list_(
+            pa.field("item", _pydantic_type_to_arrow_type(unwrapped, field), True)
+        )
+    return pa.list_(_pydantic_type_to_arrow_type(child, field))
+
+
+def _unwrap_optional_annotation(annotation: Any) -> Any | None:
+    if isinstance(annotation, (_GenericAlias, GenericAlias)):
+        origin = annotation.__origin__
+        args = annotation.__args__
+        if origin == Union:
+            non_none = [arg for arg in args if arg is not type(None)]
+            if len(non_none) == 1 and len(non_none) != len(args):
+                return non_none[0]
+    elif isinstance(annotation, types.UnionType):
+        args = annotation.__args__
+        non_none = [arg for arg in args if arg is not type(None)]
+        if len(non_none) == 1 and len(non_none) != len(args):
+            return non_none[0]
+    return None
+
+
 def _pydantic_to_arrow_type(field: FieldInfo) -> pa.DataType:
     """Convert a Pydantic FieldInfo to Arrow DataType"""
+    unwrapped = _unwrap_optional_annotation(field.annotation)
+    if unwrapped is not None:
+        return _pydantic_type_to_arrow_type(unwrapped, field)
     if isinstance(field.annotation, (_GenericAlias, GenericAlias)):
         origin = field.annotation.__origin__
         args = field.annotation.__args__
 
         if origin is list:
             child = args[0]
-            return pa.list_(_py_type_to_arrow_type(child, field))
-        elif origin == Union:
-            if len(args) == 2 and args[1] is type(None):
-                return _pydantic_type_to_arrow_type(args[0], field)
-    elif sys.version_info >= (3, 10) and isinstance(field.annotation, types.UnionType):
-        args = field.annotation.__args__
-        if len(args) == 2:
-            for typ in args:
-                if typ is type(None):
-                    continue
-                return _py_type_to_arrow_type(typ, field)
+            return _pydantic_list_child_to_arrow(child, field)
     return _pydantic_type_to_arrow_type(field.annotation, field)
 
 
 def is_nullable(field: FieldInfo) -> bool:
     """Check if a Pydantic FieldInfo is nullable."""
+    if _unwrap_optional_annotation(field.annotation) is not None:
+        return True
     if isinstance(field.annotation, (_GenericAlias, GenericAlias)):
         origin = field.annotation.__origin__
         args = field.annotation.__args__
         if origin == Union:
-            if len(args) == 2 and args[1] is type(None):
+            if any(typ is type(None) for typ in args):
                 return True
-    elif sys.version_info >= (3, 10) and isinstance(field.annotation, types.UnionType):
+    elif isinstance(field.annotation, types.UnionType):
         args = field.annotation.__args__
         for typ in args:
             if typ is type(None):
                 return True
-    elif inspect.isclass(field.annotation) and issubclass(
-        field.annotation, FixedSizeListMixin
-    ):
-        return field.annotation.nullable()
+    elif inspect.isclass(field.annotation):
+        try:
+            if issubclass(field.annotation, FixedSizeListMixin):
+                return field.annotation.nullable()
+        except TypeError:
+            return False
     return False
 
 
@@ -446,8 +443,6 @@ class LanceModel(pydantic.BaseModel):
 
     @classmethod
     def safe_get_fields(cls):
-        if PYDANTIC_VERSION.major < 2:
-            return cls.__fields__
         return cls.model_fields
 
     @classmethod
@@ -490,18 +485,8 @@ def get_extras(field_info: FieldInfo, key: str) -> Any:
     return (field_info.field_info.extra or {}).get("json_schema_extra", {}).get(key)
 
 
-if PYDANTIC_VERSION.major < 2:
-
-    def model_to_dict(model: pydantic.BaseModel) -> Dict[str, Any]:
-        """
-        Convert a Pydantic model to a dictionary.
-        """
-        return model.dict()
-
-else:
-
-    def model_to_dict(model: pydantic.BaseModel) -> Dict[str, Any]:
-        """
-        Convert a Pydantic model to a dictionary.
-        """
-        return model.model_dump()
+def model_to_dict(model: pydantic.BaseModel) -> Dict[str, Any]:
+    """
+    Convert a Pydantic model to a dictionary.
+    """
+    return model.model_dump()

python/python/lancedb/query.py

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

python/python/tests/conftest.py

@@ -2,12 +2,27 @@
 # 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:

python/python/tests/test_db.py

@@ -268,6 +268,8 @@ 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]],
@@ -286,10 +288,11 @@ 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", pa.utf8()),
+            pa.field("item", pandas_string_type()),
             pa.field("price", pa.float64()),
         ]
     )
@@ -299,7 +302,7 @@ 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", pa.utf8()),
+            pa.field("item", pandas_string_type()),
             pa.field("price", pa.float64()),
             pa.field("extra", pa.float32()),
         ]
@@ -365,6 +368,8 @@ 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]],
@@ -382,10 +387,11 @@ 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", pa.utf8()),
+            pa.field("item", pandas_string_type()),
             pa.field("price", pa.float64()),
         ]
     )
@@ -595,6 +601,8 @@ 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(
         {
@@ -614,10 +622,11 @@ 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": pa.utf8(),
+            "item": pandas_string_type(),
             "price": pa.float64(),
         }
     )

python/python/tests/test_namespace_integration.py

@@ -26,6 +26,8 @@ import pytest
 from lance_namespace import (
     CreateEmptyTableRequest,
     CreateEmptyTableResponse,
+    DeclareTableRequest,
+    DeclareTableResponse,
     DescribeTableRequest,
     DescribeTableResponse,
     LanceNamespace,
@@ -160,6 +162,19 @@ 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:

python/python/tests/test_pydantic.py

@@ -2,7 +2,6 @@
 # SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
 import json
-import sys
 from datetime import date, datetime
 from typing import List, Optional, Tuple
 
@@ -20,10 +19,6 @@ from pydantic import BaseModel
 from pydantic import Field
 
 
-@pytest.mark.skipif(
-    sys.version_info < (3, 9),
-    reason="using native type alias requires python3.9 or higher",
-)
 def test_pydantic_to_arrow():
     class StructModel(pydantic.BaseModel):
         a: str
@@ -83,10 +78,6 @@ def test_pydantic_to_arrow():
     assert schema == expect_schema
 
 
-@pytest.mark.skipif(
-    sys.version_info < (3, 10),
-    reason="using | type syntax requires python3.10 or higher",
-)
 def test_optional_types_py310():
     class TestModel(pydantic.BaseModel):
         a: str | None
@@ -105,10 +96,233 @@ def test_optional_types_py310():
     assert schema == expect_schema
 
 
-@pytest.mark.skipif(
-    sys.version_info > (3, 8),
-    reason="using native type alias requires python3.9 or higher",
-)
+def test_optional_structs():
+    class SplitInfo(pydantic.BaseModel):
+        start_frame: int
+        end_frame: int
+
+    class TestModel(pydantic.BaseModel):
+        id: str
+        split: SplitInfo | None = None
+
+    schema = pydantic_to_schema(TestModel)
+
+    expect_schema = pa.schema(
+        [
+            pa.field("id", pa.utf8(), False),
+            pa.field(
+                "split",
+                pa.struct(
+                    [
+                        pa.field("start_frame", pa.int64(), False),
+                        pa.field("end_frame", pa.int64(), False),
+                    ]
+                ),
+                True,
+            ),
+        ]
+    )
+    assert schema == expect_schema
+
+
+def test_optional_struct_list_py310():
+    class SplitInfo(pydantic.BaseModel):
+        start_frame: int
+        end_frame: int
+
+    class TestModel(pydantic.BaseModel):
+        id: str
+        splits: list[SplitInfo] | None = None
+
+    schema = pydantic_to_schema(TestModel)
+
+    expect_schema = pa.schema(
+        [
+            pa.field("id", pa.utf8(), False),
+            pa.field(
+                "splits",
+                pa.list_(
+                    pa.struct(
+                        [
+                            pa.field("start_frame", pa.int64(), False),
+                            pa.field("end_frame", pa.int64(), False),
+                        ]
+                    )
+                ),
+                True,
+            ),
+        ]
+    )
+    assert schema == expect_schema
+
+
+def test_nested_struct_list():
+    class SplitInfo(pydantic.BaseModel):
+        start_frame: int
+        end_frame: int
+
+    class TestModel(pydantic.BaseModel):
+        id: str
+        splits: list[SplitInfo]
+
+    schema = pydantic_to_schema(TestModel)
+
+    expect_schema = pa.schema(
+        [
+            pa.field("id", pa.utf8(), False),
+            pa.field(
+                "splits",
+                pa.list_(
+                    pa.struct(
+                        [
+                            pa.field("start_frame", pa.int64(), False),
+                            pa.field("end_frame", pa.int64(), False),
+                        ]
+                    )
+                ),
+                False,
+            ),
+        ]
+    )
+    assert schema == expect_schema
+
+
+def test_nested_struct_list_optional():
+    class SplitInfo(pydantic.BaseModel):
+        start_frame: int
+        end_frame: int
+
+    class TestModel(pydantic.BaseModel):
+        id: str
+        splits: Optional[list[SplitInfo]] = None
+
+    schema = pydantic_to_schema(TestModel)
+
+    expect_schema = pa.schema(
+        [
+            pa.field("id", pa.utf8(), False),
+            pa.field(
+                "splits",
+                pa.list_(
+                    pa.struct(
+                        [
+                            pa.field("start_frame", pa.int64(), False),
+                            pa.field("end_frame", pa.int64(), False),
+                        ]
+                    )
+                ),
+                True,
+            ),
+        ]
+    )
+    assert schema == expect_schema
+
+
+def test_nested_struct_list_optional_items():
+    class SplitInfo(pydantic.BaseModel):
+        start_frame: int
+        end_frame: int
+
+    class TestModel(pydantic.BaseModel):
+        id: str
+        splits: list[Optional[SplitInfo]]
+
+    schema = pydantic_to_schema(TestModel)
+
+    expect_schema = pa.schema(
+        [
+            pa.field("id", pa.utf8(), False),
+            pa.field(
+                "splits",
+                pa.list_(
+                    pa.field(
+                        "item",
+                        pa.struct(
+                            [
+                                pa.field("start_frame", pa.int64(), False),
+                                pa.field("end_frame", pa.int64(), False),
+                            ]
+                        ),
+                        True,
+                    )
+                ),
+                False,
+            ),
+        ]
+    )
+    assert schema == expect_schema
+
+
+def test_nested_struct_list_optional_container_and_items():
+    class SplitInfo(pydantic.BaseModel):
+        start_frame: int
+        end_frame: int
+
+    class TestModel(pydantic.BaseModel):
+        id: str
+        splits: Optional[list[Optional[SplitInfo]]] = None
+
+    schema = pydantic_to_schema(TestModel)
+
+    expect_schema = pa.schema(
+        [
+            pa.field("id", pa.utf8(), False),
+            pa.field(
+                "splits",
+                pa.list_(
+                    pa.field(
+                        "item",
+                        pa.struct(
+                            [
+                                pa.field("start_frame", pa.int64(), False),
+                                pa.field("end_frame", pa.int64(), False),
+                            ]
+                        ),
+                        True,
+                    )
+                ),
+                True,
+            ),
+        ]
+    )
+    assert schema == expect_schema
+
+
+def test_nested_struct_list_optional_items_pep604():
+    class SplitInfo(pydantic.BaseModel):
+        start_frame: int
+        end_frame: int
+
+    class TestModel(pydantic.BaseModel):
+        id: str
+        splits: list[SplitInfo | None]
+
+    schema = pydantic_to_schema(TestModel)
+
+    expect_schema = pa.schema(
+        [
+            pa.field("id", pa.utf8(), False),
+            pa.field(
+                "splits",
+                pa.list_(
+                    pa.field(
+                        "item",
+                        pa.struct(
+                            [
+                                pa.field("start_frame", pa.int64(), False),
+                                pa.field("end_frame", pa.int64(), False),
+                            ]
+                        ),
+                        True,
+                    )
+                ),
+                False,
+            ),
+        ]
+    )
+    assert schema == expect_schema
+
+
 def test_pydantic_to_arrow_py38():
     class StructModel(pydantic.BaseModel):
         a: str

python/python/tests/test_util.py

@@ -528,12 +528,19 @@ 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": pa.large_utf8()
-                if isinstance(data, pl.DataFrame)
-                else pa.string(),
+                "text": text_type,
                 "vector": pa.list_(pa.float32(), 10),
             }
         )

python/src/arrow.rs

@@ -10,7 +10,8 @@ use arrow::{
 use futures::stream::StreamExt;
 use lancedb::arrow::SendableRecordBatchStream;
 use pyo3::{
-    exceptions::PyStopAsyncIteration, pyclass, pymethods, Bound, Py, PyAny, PyRef, PyResult, Python,
+    exceptions::PyStopAsyncIteration, pyclass, pymethods, Bound, PyAny, PyObject, PyRef, PyResult,
+    Python,
 };
 use pyo3_async_runtimes::tokio::future_into_py;
 
@@ -35,11 +36,8 @@ impl RecordBatchStream {
 #[pymethods]
 impl RecordBatchStream {
     #[getter]
-    pub fn schema(&self, py: Python) -> PyResult<Py<PyAny>> {
-        (*self.schema)
-            .clone()
-            .into_pyarrow(py)
-            .map(|obj| obj.unbind())
+    pub fn schema(&self, py: Python) -> PyResult<PyObject> {
+        (*self.schema).clone().into_pyarrow(py)
     }
 
     pub fn __aiter__(self_: PyRef<'_, Self>) -> PyRef<'_, Self> {
@@ -55,12 +53,7 @@ impl RecordBatchStream {
                 .next()
                 .await
                 .ok_or_else(|| PyStopAsyncIteration::new_err(""))?;
-            #[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)
+            Python::with_gil(|py| inner_next.infer_error()?.to_pyarrow(py))
         })
     }
 }

python/src/connection.rs

@@ -12,7 +12,7 @@ use pyo3::{
     exceptions::{PyRuntimeError, PyValueError},
     pyclass, pyfunction, pymethods,
     types::{PyDict, PyDictMethods},
-    Bound, FromPyObject, Py, PyAny, PyRef, PyResult, Python,
+    Bound, FromPyObject, Py, PyAny, PyObject, 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<Py<PyAny>>,
+        storage_options_provider: Option<PyObject>,
         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<Py<PyAny>>,
+        storage_options_provider: Option<PyObject>,
         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<Py<PyAny>>,
+        storage_options_provider: Option<PyObject>,
         index_cache_size: Option<u32>,
         location: Option<String>,
     ) -> PyResult<Bound<'_, PyAny>> {
@@ -307,7 +307,6 @@ 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)?;
@@ -328,7 +327,8 @@ impl Connection {
         let py = self_.py();
         future_into_py(py, async move {
             use lance_namespace::models::CreateNamespaceRequest;
-            let mode_enum = mode.and_then(|m| match m.to_lowercase().as_str() {
+            // Mode is now a string field
+            let mode_str = 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()),
@@ -340,12 +340,11 @@ impl Connection {
                 } else {
                     Some(namespace)
                 },
-                mode: mode_enum,
+                mode: mode_str,
                 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)?;
@@ -365,12 +364,13 @@ impl Connection {
         let py = self_.py();
         future_into_py(py, async move {
             use lance_namespace::models::DropNamespaceRequest;
-            let mode_enum = mode.and_then(|m| match m.to_uppercase().as_str() {
+            // Mode and Behavior are now string fields
+            let mode_str = mode.and_then(|m| match m.to_uppercase().as_str() {
                 "SKIP" => Some("Skip".to_string()),
                 "FAIL" => Some("Fail".to_string()),
                 _ => None,
             });
-            let behavior_enum = behavior.and_then(|b| match b.to_uppercase().as_str() {
+            let behavior_str = behavior.and_then(|b| match b.to_uppercase().as_str() {
                 "RESTRICT" => Some("Restrict".to_string()),
                 "CASCADE" => Some("Cascade".to_string()),
                 _ => None,
@@ -381,12 +381,11 @@ impl Connection {
                 } else {
                     Some(namespace)
                 },
-                mode: mode_enum,
-                behavior: behavior_enum,
+                mode: mode_str,
+                behavior: behavior_str,
                 ..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)?;
@@ -414,7 +413,6 @@ 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)?;
@@ -445,7 +443,6 @@ 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)?;

python/src/error.rs

@@ -40,34 +40,31 @@ impl<T> PythonErrorExt<T> for std::result::Result<T, LanceError> {
                     request_id,
                     source,
                     status_code,
-                } => {
-                    #[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,
+                } => 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,
                             request_id,
                             status_code.map(|s| s.as_u16()),
-                        ))?;
+                        )?;
+                        err.setattr(intern!(py, "__cause__"), cause_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))
-                    })
-                }
+                    Err(PyErr::from_value(err))
+                }),
                 LanceError::Retry {
                     request_id,
                     request_failures,
@@ -78,37 +75,33 @@ impl<T> PythonErrorExt<T> for std::result::Result<T, LanceError> {
                     max_read_failures,
                     source,
                     status_code,
-                } =>
-                {
-                    #[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()),
-                        )?;
+                } => 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(),
             },
         }

python/src/header.rs

@@ -12,7 +12,6 @@ pub struct PyHeaderProvider {
 
 impl Clone for PyHeaderProvider {
     fn clone(&self) -> Self {
-        #[allow(deprecated)]
         Python::with_gil(|py| Self {
             provider: self.provider.clone_ref(py),
         })
@@ -26,7 +25,6 @@ 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");

python/src/permutation.rs

@@ -19,7 +19,7 @@ use pyo3::{
     exceptions::PyRuntimeError,
     pyclass, pymethods,
     types::{PyAnyMethods, PyDict, PyDictMethods, PyType},
-    Bound, Py, PyAny, PyRef, PyRefMut, PyResult, Python,
+    Bound, PyAny, PyRef, PyRefMut, PyResult, Python,
 };
 use pyo3_async_runtimes::tokio::future_into_py;
 
@@ -281,12 +281,7 @@ impl PyPermutationReader {
         let reader = slf.reader.clone();
         future_into_py(slf.py(), async move {
             let schema = reader.output_schema(selection).await.infer_error()?;
-            #[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)
+            Python::with_gil(|py| schema.to_pyarrow(py))
         })
     }
 

python/src/query.rs

@@ -29,7 +29,6 @@ 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;
@@ -454,12 +453,7 @@ impl Query {
         let inner = self_.inner.clone();
         future_into_py(self_.py(), async move {
             let schema = inner.output_schema().await.infer_error()?;
-            #[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)
+            Python::with_gil(|py| schema.to_pyarrow(py))
         })
     }
 
@@ -538,12 +532,7 @@ impl TakeQuery {
         let inner = self_.inner.clone();
         future_into_py(self_.py(), async move {
             let schema = inner.output_schema().await.infer_error()?;
-            #[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)
+            Python::with_gil(|py| schema.to_pyarrow(py))
         })
     }
 
@@ -638,12 +627,7 @@ impl FTSQuery {
         let inner = self_.inner.clone();
         future_into_py(self_.py(), async move {
             let schema = inner.output_schema().await.infer_error()?;
-            #[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)
+            Python::with_gil(|py| schema.to_pyarrow(py))
         })
     }
 
@@ -822,12 +806,7 @@ impl VectorQuery {
         let inner = self_.inner.clone();
         future_into_py(self_.py(), async move {
             let schema = inner.output_schema().await.infer_error()?;
-            #[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)
+            Python::with_gil(|py| schema.to_pyarrow(py))
         })
     }
 

python/src/storage_options.rs

@@ -17,12 +17,11 @@ use pyo3::types::PyDict;
 /// Internal wrapper around a Python object implementing StorageOptionsProvider
 pub struct PyStorageOptionsProvider {
     /// The Python object implementing fetch_storage_options()
-    inner: Py<PyAny>,
+    inner: PyObject,
 }
 
 impl Clone for PyStorageOptionsProvider {
     fn clone(&self) -> Self {
-        #[allow(deprecated)]
         Python::with_gil(|py| Self {
             inner: self.inner.clone_ref(py),
         })
@@ -30,8 +29,7 @@ impl Clone for PyStorageOptionsProvider {
 }
 
 impl PyStorageOptionsProvider {
-    pub fn new(obj: Py<PyAny>) -> PyResult<Self> {
-        #[allow(deprecated)]
+    pub fn new(obj: PyObject) -> PyResult<Self> {
         Python::with_gil(|py| {
             // Verify the object has a fetch_storage_options method
             if !obj.bind(py).hasattr("fetch_storage_options")? {
@@ -39,9 +37,7 @@ impl PyStorageOptionsProvider {
                     "StorageOptionsProvider must implement fetch_storage_options() method",
                 ));
             }
-            Ok(Self {
-                inner: obj.clone_ref(py),
-            })
+            Ok(Self { inner: obj })
         })
     }
 }
@@ -64,7 +60,6 @@ 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
@@ -124,7 +119,6 @@ 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);
@@ -149,7 +143,7 @@ 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: Py<PyAny>,
+    py_obj: PyObject,
 ) -> PyResult<Arc<dyn StorageOptionsProvider>> {
     let py_provider = PyStorageOptionsProvider::new(py_obj)?;
     Ok(Arc::new(PyStorageOptionsProviderWrapper::new(py_provider)))

python/src/table.rs

@@ -21,7 +21,7 @@ use pyo3::{
     exceptions::{PyKeyError, PyRuntimeError, PyValueError},
     pyclass, pymethods,
     types::{IntoPyDict, PyAnyMethods, PyDict, PyDictMethods},
-    Bound, FromPyObject, Py, PyAny, PyRef, PyResult, Python,
+    Bound, FromPyObject, PyAny, PyRef, PyResult, Python,
 };
 use pyo3_async_runtimes::tokio::future_into_py;
 
@@ -287,12 +287,7 @@ impl Table {
         let inner = self_.inner_ref()?.clone();
         future_into_py(self_.py(), async move {
             let schema = inner.schema().await.infer_error()?;
-            #[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)
+            Python::with_gil(|py| schema.to_pyarrow(py))
         })
     }
 
@@ -442,7 +437,6 @@ 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)?;
@@ -473,7 +467,6 @@ 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)?;
@@ -528,7 +521,6 @@ 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()
@@ -880,7 +872,6 @@ 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 {

rust/lancedb/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.23.1"
+version = "0.24.1"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true

rust/lancedb/src/connection.rs

@@ -36,10 +36,42 @@ 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::StorageOptionsProvider;
+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));
+}
 
 /// A builder for configuring a [`Connection::table_names`] operation
 pub struct TableNamesBuilder {
@@ -246,16 +278,14 @@ 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_options = self
+        let store_params = 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());
-        store_options.insert(key.into(), value.into());
+        merge_storage_options(store_params, [(key.into(), value.into())]);
         self
     }
 
@@ -269,19 +299,17 @@ impl<const HAS_DATA: bool> CreateTableBuilder<HAS_DATA> {
         mut self,
         pairs: impl IntoIterator<Item = (impl Into<String>, impl Into<String>)>,
     ) -> Self {
-        let store_options = self
+        let store_params = 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());
-
-        for (key, value) in pairs {
-            store_options.insert(key.into(), value.into());
-        }
+        let updates = pairs
+            .into_iter()
+            .map(|(key, value)| (key.into(), value.into()));
+        merge_storage_options(store_params, updates);
         self
     }
 
@@ -318,23 +346,21 @@ 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 storage_options = self
+        let store_params = 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);
-
-        storage_options.insert(
-            OPT_NEW_TABLE_V2_MANIFEST_PATHS.to_string(),
-            if use_v2_manifest_paths {
-                "true".to_string()
-            } else {
-                "false".to_string()
-            },
+        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)],
         );
         self
     }
@@ -344,19 +370,19 @@ 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 storage_options = self
+        let store_params = 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);
-
-        storage_options.insert(
-            OPT_NEW_TABLE_STORAGE_VERSION.to_string(),
-            data_storage_version.to_string(),
+        merge_storage_options(
+            store_params,
+            [(
+                OPT_NEW_TABLE_STORAGE_VERSION.to_string(),
+                data_storage_version.to_string(),
+            )],
         );
         self
     }
@@ -381,13 +407,14 @@ 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 {
-        self.request
+        let store_params = self
+            .request
             .write_options
             .lance_write_params
             .get_or_insert(Default::default())
             .store_params
-            .get_or_insert(Default::default())
-            .storage_options_provider = Some(provider);
+            .get_or_insert(Default::default());
+        set_storage_options_provider(store_params, provider);
         self
     }
 }
@@ -450,15 +477,13 @@ 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 storage_options = self
+        let store_params = self
             .request
             .lance_read_params
             .get_or_insert(Default::default())
             .store_options
-            .get_or_insert(Default::default())
-            .storage_options
             .get_or_insert(Default::default());
-        storage_options.insert(key.into(), value.into());
+        merge_storage_options(store_params, [(key.into(), value.into())]);
         self
     }
 
@@ -472,18 +497,16 @@ impl OpenTableBuilder {
         mut self,
         pairs: impl IntoIterator<Item = (impl Into<String>, impl Into<String>)>,
     ) -> Self {
-        let storage_options = self
+        let store_params = self
             .request
             .lance_read_params
             .get_or_insert(Default::default())
             .store_options
-            .get_or_insert(Default::default())
-            .storage_options
             .get_or_insert(Default::default());
-
-        for (key, value) in pairs {
-            storage_options.insert(key.into(), value.into());
-        }
+        let updates = pairs
+            .into_iter()
+            .map(|(key, value)| (key.into(), value.into()));
+        merge_storage_options(store_params, updates);
         self
     }
 
@@ -507,12 +530,13 @@ 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 {
-        self.request
+        let store_params = self
+            .request
             .lance_read_params
             .get_or_insert(Default::default())
             .store_options
-            .get_or_insert(Default::default())
-            .storage_options_provider = Some(provider);
+            .get_or_insert(Default::default());
+        set_storage_options_provider(store_params, provider);
         self
     }
 
@@ -868,6 +892,10 @@ 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 {
@@ -1051,11 +1079,27 @@ 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 options = RemoteDatabaseOptions::parse_from_map(&self.request.options)?;
+        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 region = options.region.ok_or_else(|| Error::InvalidInput {
             message: "A region is required when connecting to LanceDb Cloud".to_string(),
@@ -1277,8 +1321,6 @@ 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};
@@ -1302,6 +1344,23 @@ 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() {
@@ -1526,18 +1585,27 @@ mod tests {
 
     #[tokio::test]
     async fn drop_table() {
-        let tmp_dir = tempdir().unwrap();
+        let tc = new_test_connection().await.unwrap();
+        let db = tc.connection;
 
-        let uri = tmp_dir.path().to_str().unwrap();
-        let db = connect(uri).execute().await.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 { .. }),
+            ));
+        }
 
-        // 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();
+        let schema = Arc::new(Schema::new(vec![Field::new("x", DataType::Int32, false)]));
+        db.create_empty_table("table1", schema.clone())
+            .execute()
+            .await
+            .unwrap();
         db.drop_table("table1", &[]).await.unwrap();
 
         let tables = db.table_names().execute().await.unwrap();

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::StorageOptionsProvider;
+use lance_io::object_store::{StorageOptionsAccessor, StorageOptionsProvider};
 use lance_table::io::commit::commit_handler_from_url;
 use object_store::local::LocalFileSystem;
 use snafu::ResultExt;
@@ -356,7 +356,13 @@ impl ListingDatabase {
                     .clone()
                     .unwrap_or_else(|| Arc::new(lance::session::Session::default()));
                 let os_params = ObjectStoreParams {
-                    storage_options: Some(options.storage_options.clone()),
+                    storage_options_accessor: if options.storage_options.is_empty() {
+                        None
+                    } else {
+                        Some(Arc::new(StorageOptionsAccessor::with_static_options(
+                            options.storage_options.clone(),
+                        )))
+                    },
                     ..Default::default()
                 };
                 let (object_store, base_path) = ObjectStore::from_uri_and_params(
@@ -492,7 +498,13 @@ impl ListingDatabase {
 
     async fn drop_tables(&self, names: Vec<String>) -> Result<()> {
         let object_store_params = ObjectStoreParams {
-            storage_options: Some(self.storage_options.clone()),
+            storage_options_accessor: if self.storage_options.is_empty() {
+                None
+            } else {
+                Some(Arc::new(StorageOptionsAccessor::with_static_options(
+                    self.storage_options.clone(),
+                )))
+            },
             ..Default::default()
         };
         let mut uri = self.uri.clone();
@@ -541,7 +553,7 @@ impl ListingDatabase {
             .lance_write_params
             .as_ref()
             .and_then(|p| p.store_params.as_ref())
-            .and_then(|sp| sp.storage_options.as_ref());
+            .and_then(|sp| sp.storage_options());
 
         let storage_version_override = storage_options
             .and_then(|opts| opts.get(OPT_NEW_TABLE_STORAGE_VERSION))
@@ -592,21 +604,20 @@ 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() {
-            let storage_options = write_params
+        if !self.storage_options.is_empty() || self.storage_options_provider.is_some() {
+            let store_params = write_params
                 .store_params
-                .get_or_insert_with(Default::default)
-                .storage_options
                 .get_or_insert_with(Default::default);
-            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();
+            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));
         }
 
         write_params.data_storage_version = self
@@ -892,7 +903,13 @@ impl Database for ListingDatabase {
         validate_table_name(&request.target_table_name)?;
 
         let storage_params = ObjectStoreParams {
-            storage_options: Some(self.storage_options.clone()),
+            storage_options_accessor: if self.storage_options.is_empty() {
+                None
+            } else {
+                Some(Arc::new(StorageOptionsAccessor::with_static_options(
+                    self.storage_options.clone(),
+                )))
+            },
             ..Default::default()
         };
         let read_params = ReadParams {
@@ -956,25 +973,28 @@ 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() {
-            let storage_options = request
+        if !self.storage_options.is_empty() || self.storage_options_provider.is_some() {
+            let store_params = 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);
-            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();
+            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));
         }
 
         // Some ReadParams are exposed in the OpenTableBuilder, but we also
@@ -1881,7 +1901,9 @@ mod tests {
         let write_options = WriteOptions {
             lance_write_params: Some(lance::dataset::WriteParams {
                 store_params: Some(lance::io::ObjectStoreParams {
-                    storage_options: Some(storage_options),
+                    storage_options_accessor: Some(Arc::new(
+                        StorageOptionsAccessor::with_static_options(storage_options),
+                    )),
                     ..Default::default()
                 }),
                 ..Default::default()
@@ -1955,7 +1977,9 @@ mod tests {
         let write_options = WriteOptions {
             lance_write_params: Some(lance::dataset::WriteParams {
                 store_params: Some(lance::io::ObjectStoreParams {
-                    storage_options: Some(storage_options),
+                    storage_options_accessor: Some(Arc::new(
+                        StorageOptionsAccessor::with_static_options(storage_options),
+                    )),
                     ..Default::default()
                 }),
                 ..Default::default()

rust/lancedb/src/database/namespace.rs

@@ -9,14 +9,15 @@ use std::sync::Arc;
 use async_trait::async_trait;
 use lance_namespace::{
     models::{
-        CreateNamespaceRequest, CreateNamespaceResponse, DeclareTableRequest,
-        DescribeNamespaceRequest, DescribeNamespaceResponse, DescribeTableRequest,
-        DropNamespaceRequest, DropNamespaceResponse, DropTableRequest, ListNamespacesRequest,
-        ListNamespacesResponse, ListTablesRequest, ListTablesResponse,
+        CreateEmptyTableRequest, 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};
@@ -154,7 +155,6 @@ impl Database for LanceNamespaceDatabase {
         table_id.push(request.name.clone());
         let describe_request = DescribeTableRequest {
             id: Some(table_id.clone()),
-            version: None,
             ..Default::default()
         };
 
@@ -205,26 +205,53 @@ impl Database for LanceNamespaceDatabase {
         let mut table_id = request.namespace.clone();
         table_id.push(request.name.clone());
 
-        let create_empty_request = DeclareTableRequest {
+        // 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 {
             id: Some(table_id.clone()),
-            location: None,
-            vend_credentials: None,
             ..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),
-            })?;
+        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 location = create_empty_response
-            .location
-            .ok_or_else(|| Error::Runtime {
-                message: "Table location is missing from create_empty_table response".to_string(),
-            })?;
+                    #[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 native_table = NativeTable::create_from_namespace(
             self.namespace.clone(),
@@ -439,8 +466,6 @@ mod tests {
         // Create a child namespace first
         conn.create_namespace(CreateNamespaceRequest {
             id: Some(vec!["test_ns".into()]),
-            mode: None,
-            properties: None,
             ..Default::default()
         })
         .await
@@ -501,8 +526,6 @@ mod tests {
         // Create a child namespace first
         conn.create_namespace(CreateNamespaceRequest {
             id: Some(vec!["test_ns".into()]),
-            mode: None,
-            properties: None,
             ..Default::default()
         })
         .await
@@ -566,8 +589,6 @@ mod tests {
         // Create a child namespace first
         conn.create_namespace(CreateNamespaceRequest {
             id: Some(vec!["test_ns".into()]),
-            mode: None,
-            properties: None,
             ..Default::default()
         })
         .await
@@ -651,8 +672,6 @@ mod tests {
         // Create a child namespace first
         conn.create_namespace(CreateNamespaceRequest {
             id: Some(vec!["test_ns".into()]),
-            mode: None,
-            properties: None,
             ..Default::default()
         })
         .await
@@ -708,8 +727,6 @@ mod tests {
         // Create a child namespace first
         conn.create_namespace(CreateNamespaceRequest {
             id: Some(vec!["test_ns".into()]),
-            mode: None,
-            properties: None,
             ..Default::default()
         })
         .await
@@ -790,8 +807,6 @@ mod tests {
         // Create a child namespace first
         conn.create_namespace(CreateNamespaceRequest {
             id: Some(vec!["test_ns".into()]),
-            mode: None,
-            properties: None,
             ..Default::default()
         })
         .await
@@ -825,8 +840,6 @@ mod tests {
         // Create a child namespace first
         conn.create_namespace(CreateNamespaceRequest {
             id: Some(vec!["test_ns".into()]),
-            mode: None,
-            properties: None,
             ..Default::default()
         })
         .await

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

@@ -19,7 +19,7 @@ use crate::{
         split::{SplitStrategy, Splitter, SPLIT_ID_COLUMN},
         util::{rename_column, TemporaryDirectory},
     },
-    query::{ExecutableQuery, QueryBase},
+    query::{ExecutableQuery, QueryBase, Select},
     Error, Result, Table,
 };
 
@@ -27,6 +27,8 @@ pub const SRC_ROW_ID_COL: &str = "row_id";
 
 pub const SPLIT_NAMES_CONFIG_KEY: &str = "split_names";
 
+pub const DEFAULT_MEMORY_LIMIT: usize = 100 * 1024 * 1024;
+
 /// Where to store the permutation table
 #[derive(Debug, Clone, Default)]
 enum PermutationDestination {
@@ -167,10 +169,20 @@ impl PermutationBuilder {
         &self,
         data: SendableRecordBatchStream,
     ) -> Result<SendableRecordBatchStream> {
+        let memory_limit = std::env::var("LANCEDB_PERM_BUILDER_MEMORY_LIMIT")
+            .unwrap_or_else(|_| DEFAULT_MEMORY_LIMIT.to_string())
+            .parse::<usize>()
+            .unwrap_or_else(|_| {
+                log::error!(
+                    "Failed to parse LANCEDB_PERM_BUILDER_MEMORY_LIMIT, using default: {}",
+                    DEFAULT_MEMORY_LIMIT
+                );
+                DEFAULT_MEMORY_LIMIT
+            });
         let ctx = SessionContext::new_with_config_rt(
             SessionConfig::default(),
             RuntimeEnvBuilder::new()
-                .with_memory_limit(100 * 1024 * 1024, 1.0)
+                .with_memory_limit(memory_limit, 1.0)
                 .with_disk_manager_builder(
                     DiskManagerBuilder::default()
                         .with_mode(self.config.temp_dir.to_disk_manager_mode()),
@@ -232,7 +244,7 @@ impl PermutationBuilder {
     /// Builds the permutation table and stores it in the given database.
     pub async fn build(self) -> Result<Table> {
         // First pass, apply filter and load row ids
-        let mut rows = self.base_table.query().with_row_id();
+        let mut rows = self.base_table.query().select(Select::columns(&[ROW_ID]));
 
         if let Some(filter) = &self.config.filter {
             rows = rows.only_if(filter);
@@ -321,6 +333,47 @@ mod tests {
 
     use super::*;
 
+    #[tokio::test]
+    async fn test_permutation_table_only_stores_row_id_and_split_id() {
+        let temp_dir = tempfile::tempdir().unwrap();
+
+        let db = connect(temp_dir.path().to_str().unwrap())
+            .execute()
+            .await
+            .unwrap();
+
+        let initial_data = lance_datagen::gen_batch()
+            .col("col_a", lance_datagen::array::step::<Int32Type>())
+            .col("col_b", lance_datagen::array::step::<Int32Type>())
+            .into_ldb_stream(RowCount::from(100), BatchCount::from(10));
+        let data_table = db
+            .create_table_streaming("base_tbl", initial_data)
+            .execute()
+            .await
+            .unwrap();
+
+        let permutation_table = PermutationBuilder::new(data_table.clone())
+            .with_split_strategy(
+                SplitStrategy::Sequential {
+                    sizes: SplitSizes::Percentages(vec![0.5, 0.5]),
+                },
+                None,
+            )
+            .with_filter("col_a > 57".to_string())
+            .build()
+            .await
+            .unwrap();
+
+        let schema = permutation_table.schema().await.unwrap();
+        let field_names: Vec<&str> = schema.fields().iter().map(|f| f.name().as_str()).collect();
+        assert_eq!(
+            field_names,
+            vec!["row_id", "split_id"],
+            "Permutation table should only contain row_id and split_id columns, but found: {:?}",
+            field_names,
+        );
+    }
+
     #[tokio::test]
     async fn test_permutation_builder() {
         let temp_dir = tempfile::tempdir().unwrap();
@@ -352,8 +405,6 @@ mod tests {
             .await
             .unwrap();
 
-        println!("permutation_table: {:?}", permutation_table);
-
         // Potentially brittle seed-dependent values below
         assert_eq!(permutation_table.count_rows(None).await.unwrap(), 330);
         assert_eq!(

rust/lancedb/src/dataloader/permutation/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 % clump_size != 0 {
+            if !is_last && !(batch.num_rows() as u64).is_multiple_of(clump_size) {
                 return Err(Error::Runtime {
                     message: format!(
                         "Expected batch size ({}) to be divisible by clump size ({})",

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

@@ -1,12 +1,9 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
-use std::{
-    iter,
-    sync::{
-        atomic::{AtomicBool, AtomicU64, AtomicUsize, Ordering},
-        Arc,
-    },
+use std::sync::{
+    atomic::{AtomicBool, AtomicU64, AtomicUsize, Ordering},
+    Arc,
 };
 
 use arrow_array::{Array, BooleanArray, RecordBatch, UInt64Array};
@@ -158,7 +155,7 @@ impl Splitter {
                 remaining_in_split
             };
 
-            split_ids.extend(iter::repeat(split_id as u64).take(rows_to_add as usize));
+            split_ids.extend(std::iter::repeat_n(split_id as u64, rows_to_add as usize));
             if done {
                 // Quit early if we've run out of splits
                 break;
@@ -662,7 +659,7 @@ mod tests {
         assert_eq!(split_batch.num_rows(), total_split_sizes as usize);
         let mut expected = Vec::with_capacity(total_split_sizes as usize);
         for (i, size) in expected_split_sizes.iter().enumerate() {
-            expected.extend(iter::repeat(i as u64).take(*size as usize));
+            expected.extend(std::iter::repeat_n(i as u64, *size as usize));
         }
         let expected = Arc::new(UInt64Array::from(expected)) as Arc<dyn Array>;
 

rust/lancedb/src/index/vector.rs

@@ -297,10 +297,10 @@ impl IvfPqIndexBuilder {
 }
 
 pub(crate) fn suggested_num_sub_vectors(dim: u32) -> u32 {
-    if dim % 16 == 0 {
+    if dim.is_multiple_of(16) {
         // Should be more aggressive than this default.
         dim / 16
-    } else if dim % 8 == 0 {
+    } else if dim.is_multiple_of(8) {
         dim / 8
     } else {
         log::warn!(

rust/lancedb/src/lib.rs

@@ -51,24 +51,19 @@
 //! - `s3://bucket/path/to/database` or `gs://bucket/path/to/database` - database on cloud object store
 //! - `db://dbname` - Lance Cloud
 //!
-//! You can also use [`ConnectOptions`] to configure the connection to the database.
+//! You can also use [`ConnectBuilder`] 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")
-//!     .aws_creds(AwsCredential {
-//!         key_id: "some_key".to_string(),
-//!         secret_key: "some_secret".to_string(),
-//!         token: None,
-//!     })
+//!     .storage_options([
+//!         ("aws_access_key_id", "some_key"),
+//!         ("aws_secret_access_key", "some_secret"),
+//!     ])
 //!     .execute()
 //!     .await
 //!     .unwrap();
 //! # });
-//! # }
 //! ```
 //!
 //! LanceDB uses [arrow-rs](https://github.com/apache/arrow-rs) to define schema, data types and array itself.

rust/lancedb/src/remote/db.rs

@@ -1718,8 +1718,6 @@ mod tests {
             let namespace = vec!["test_ns".to_string()];
             conn.create_namespace(CreateNamespaceRequest {
                 id: Some(namespace.clone()),
-                mode: None,
-                properties: None,
                 ..Default::default()
             })
             .await
@@ -1745,8 +1743,6 @@ mod tests {
             let list_response = conn
                 .list_tables(ListTablesRequest {
                     id: Some(namespace.clone()),
-                    page_token: None,
-                    limit: None,
                     ..Default::default()
                 })
                 .await
@@ -1758,8 +1754,6 @@ mod tests {
             let list_response = namespace_client
                 .list_tables(ListTablesRequest {
                     id: Some(namespace.clone()),
-                    page_token: None,
-                    limit: None,
                     ..Default::default()
                 })
                 .await
@@ -1800,8 +1794,6 @@ 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
@@ -1827,8 +1819,6 @@ mod tests {
             let list_response = conn
                 .list_tables(ListTablesRequest {
                     id: Some(namespace.clone()),
-                    page_token: None,
-                    limit: None,
                     ..Default::default()
                 })
                 .await

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;
+use lance_io::object_store::{LanceNamespaceStorageOptionsProvider, StorageOptionsAccessor};
 use lance_namespace::models::{
     QueryTableRequest as NsQueryTableRequest, QueryTableRequestColumns,
     QueryTableRequestFullTextQuery, QueryTableRequestVector, StringFtsQuery,
@@ -1425,9 +1425,7 @@ impl Table {
             })
             .collect::<Vec<_>>();
 
-        let unioned = UnionExec::try_new(projected_plans).map_err(|e| Error::Runtime {
-            message: format!("Failed to build union plan: {e}"),
-        })?;
+        let unioned = Arc::new(UnionExec::new(projected_plans));
         // We require 1 partition in the final output
         let repartitioned = RepartitionExec::try_new(
             unioned,
@@ -1668,18 +1666,14 @@ 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,
-            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 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 dataset = builder
             .with_read_params(params)
@@ -1883,7 +1877,13 @@ impl NativeTable {
         let store_params = params
             .store_params
             .get_or_insert_with(ObjectStoreParams::default);
-        store_params.storage_options_provider = Some(storage_options_provider);
+        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));
 
         // Patch the params if we have a write store wrapper
         let params = match write_store_wrapper.clone() {
@@ -2059,7 +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 % 2 != 0 {
+        if num_bits.is_some_and(|num_bits| num_bits == 4) && !suggested.is_multiple_of(2) {
             // num_sub_vectors must be even when 4 bits are used
             suggested + 1
         } else {
@@ -2349,7 +2349,7 @@ impl NativeTable {
                 };
 
                 // Convert select to columns list
-                let columns: Option<Box<QueryTableRequestColumns>> = match &vq.base.select {
+                let columns = match &vq.base.select {
                     Select::All => None,
                     Select::Columns(cols) => Some(Box::new(QueryTableRequestColumns {
                         column_names: Some(cols.clone()),
@@ -2407,7 +2407,6 @@ 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()
                 })
             }
@@ -2426,7 +2425,7 @@ impl NativeTable {
                     .map(|f| self.filter_to_sql(f))
                     .transpose()?;
 
-                let columns: Option<Box<QueryTableRequestColumns>> = match &q.select {
+                let columns = match &q.select {
                     Select::All => None,
                     Select::Columns(cols) => Some(Box::new(QueryTableRequestColumns {
                         column_names: Some(cols.clone()),
@@ -2470,18 +2469,10 @@ 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()
                 })
             }
@@ -3244,7 +3235,7 @@ impl BaseTable for NativeTable {
             .get()
             .await
             .ok()
-            .and_then(|dataset| dataset.storage_options().cloned())
+            .and_then(|dataset| dataset.initial_storage_options().cloned())
     }
 
     async fn index_stats(&self, index_name: &str) -> Result<Option<IndexStatistics>> {
@@ -3409,7 +3400,6 @@ pub struct FragmentSummaryStats {
 #[cfg(test)]
 #[allow(deprecated)]
 mod tests {
-    use std::iter;
     use std::sync::atomic::{AtomicBool, Ordering};
     use std::sync::Arc;
     use std::time::Duration;
@@ -4026,7 +4016,7 @@ mod tests {
                 schema.clone(),
                 vec![
                     Arc::new(Int32Array::from_iter_values(offset..(offset + 10))),
-                    Arc::new(Int32Array::from_iter_values(iter::repeat(age).take(10))),
+                    Arc::new(Int32Array::from_iter_values(std::iter::repeat_n(age, 10))),
                 ],
             )],
             schema,
@@ -5154,15 +5144,16 @@ 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!(column_names, Some(vec!["id".to_string()]));
+        assert_eq!(
+            ns_request
+                .columns
+                .as_ref()
+                .and_then(|c| c.column_names.as_ref()),
+            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());
@@ -5199,16 +5190,17 @@ 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!(column_names, Some(vec!["id".to_string()]));
+        assert_eq!(
+            ns_request
+                .columns
+                .as_ref()
+                .and_then(|c| c.column_names.as_ref()),
+            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

rust/lancedb/src/table/dataset.rs

@@ -100,8 +100,7 @@ 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::VersionNumber(target_ver) => version != target_ver,
-                    refs::Ref::Tag(_) => true, // Always checkout for tags
+                    refs::Ref::Tag(_) => true,           // Always checkout for tags
                 };
 
                 if should_checkout {

rust/lancedb/tests/embedding_registry_test.rs

@@ -4,7 +4,6 @@
 use std::{
     borrow::Cow,
     collections::{HashMap, HashSet},
-    iter::repeat,
     sync::Arc,
 };
 
@@ -268,9 +267,10 @@ fn create_some_records() -> Result<impl IntoArrow> {
             schema.clone(),
             vec![
                 Arc::new(Int32Array::from_iter_values(0..TOTAL as i32)),
-                Arc::new(StringArray::from_iter(
-                    repeat(Some("hello world".to_string())).take(TOTAL),
-                )),
+                Arc::new(StringArray::from_iter(std::iter::repeat_n(
+                    Some("hello world".to_string()),
+                    TOTAL,
+                ))),
             ],
         )
         .unwrap()]