chore(deps): bump snafu from 0.8.9 to 0.9.0

Bumps [snafu](https://github.com/shepmaster/snafu) from 0.8.9 to 0.9.0.
- [Changelog](https://github.com/shepmaster/snafu/blob/main/CHANGELOG.md)
- [Commits](https://github.com/shepmaster/snafu/compare/0.8.9...0.9.0)

---
updated-dependencies:
- dependency-name: snafu
  dependency-version: 0.9.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.27.0-beta.3"
+current_version = "0.29.1-beta.0"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

.github/ISSUE_TEMPLATE/documentation.yml

@@ -18,6 +18,6 @@ body:
       label: Link
       description: >
         Provide a link to the existing documentation, if applicable.
-      placeholder: ex. https://lancedb.com/docs/tables/...
+      placeholder: ex. https://docs.lancedb.com/tables/...
     validations:
       required: false

.github/dependabot.yml

@@ -0,0 +1,23 @@
+version: 2
+
+# Scope: the root Cargo workspace, which produces the Rust binaries we
+# ship to users (the Node.js and Python native extensions). The
+# `rust/lancedb` library crate shares the same lockfile; its consumers
+# pick their own dependency versions, but bumping transitive deps here
+# keeps the binaries we ship current.
+updates:
+  - package-ecosystem: cargo
+    directory: /
+    schedule:
+      interval: weekly
+    open-pull-requests-limit: 10
+    # Only update Cargo.lock, never widen/raise the version requirements in
+    # Cargo.toml. The goal is keeping the lockfile (and the binaries we ship)
+    # current on security fixes, not forcing our library's consumers onto
+    # newer minimum versions.
+    versioning-strategy: lockfile-only
+    groups:
+      rust-minor-patch:
+        update-types:
+          - minor
+          - patch

.github/workflows/build_linux_wheel/action.yml

@@ -23,8 +23,10 @@ runs:
   steps:
     - name: CONFIRM ARM BUILD
       shell: bash
+      env:
+        ARM_BUILD: ${{ inputs.arm-build }}
       run: |
-        echo "ARM BUILD: ${{ inputs.arm-build }}"
+        echo "ARM BUILD: $ARM_BUILD"
     - name: Build x86_64 Manylinux wheel
       if: ${{ inputs.arm-build == 'false' }}
       uses: PyO3/maturin-action@v1

.github/workflows/codex-fix-ci.yml

@@ -45,7 +45,9 @@ jobs:
       - name: Set up Node.js
         uses: actions/setup-node@v4
         with:
-          node-version: 20
+          # pnpm 11 (used by the nodejs install step below) requires
+          # Node >= 22.13; use 24 since 22 hits EOL in October.
+          node-version: 24
 
       - name: Install Codex CLI
         run: npm install -g @openai/codex
@@ -79,10 +81,14 @@ jobs:
           java-version: '11'
           cache: maven
 
+      - name: Setup pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 11.1.1
       - name: Install Node.js dependencies for TypeScript bindings
         run: |
           cd nodejs
-          npm ci
+          pnpm install --frozen-lockfile
 
       - name: Configure git user
         run: |
@@ -137,7 +143,7 @@ jobs:
                - For Rust test failures: Run the specific test with "cargo test -p <crate> <test_name>"
                - For Python test failures: Build with "cd python && maturin develop" then run "pytest <specific_test_file>::<test_name>"
                - For Java test failures: Run "cd java && mvn test -Dtest=<TestClass>#<testMethod>"
-               - For TypeScript test failures: Run "cd nodejs && npm run build && npm test -- --testNamePattern='<test_name>'"
+               - For TypeScript test failures: Run "cd nodejs && pnpm build && pnpm test -- --testNamePattern='<test_name>'"
                - Do NOT run the full test suite - only run the tests that were failing
 
           7. If the additional guidelines are provided, follow them as well.

.github/workflows/dev.yml

@@ -8,6 +8,9 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
 
+permissions:
+  contents: read
+
 jobs:
   labeler:
     permissions:
@@ -15,7 +18,7 @@ jobs:
     name: Label PR
     runs-on: ubuntu-latest
     steps:
-      - uses: srvaroa/labeler@master
+      - uses: srvaroa/labeler@v1
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
   commitlint:
@@ -24,7 +27,7 @@ jobs:
     name: Verify PR title / description conforms to semantic-release
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/setup-node@v3
+      - uses: actions/setup-node@v4
         with:
           node-version: "18"
       # These rules are disabled because Github will always ensure there
@@ -47,7 +50,7 @@ jobs:
 
             ${{ github.event.pull_request.body }}
       - if: failure()
-        uses: actions/github-script@v6
+        uses: actions/github-script@v7
         with:
           script: |
             const message = `**ACTION NEEDED**

.github/workflows/docs.yml

@@ -53,7 +53,7 @@ jobs:
           python -m pip install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ -e .
           python -m pip install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ -r ../docs/requirements.txt
       - name: Set up node
-        uses: actions/setup-node@v3
+        uses: actions/setup-node@v4
         with:
           node-version: 20
           cache: 'npm'
@@ -68,7 +68,7 @@ jobs:
         run: |
           PYTHONPATH=. mkdocs build
       - name: Setup Pages
-        uses: actions/configure-pages@v2
+        uses: actions/configure-pages@v5
       - name: Upload artifact
         uses: actions/upload-pages-artifact@v3
         with:

.github/workflows/java-publish.yml

@@ -19,6 +19,9 @@ on:
     paths:
       - .github/workflows/java-publish.yml
 
+permissions:
+  contents: read
+
 jobs:
   publish:
     name: Build and Publish
@@ -40,7 +43,7 @@ jobs:
           server-username: SONATYPE_USER
           server-password: SONATYPE_TOKEN
           gpg-private-key: ${{ secrets.GPG_PRIVATE_KEY }}
-          gpg-passphrase: ${{ secrets.GPG_PASSPHRASE }}
+          gpg-passphrase: MAVEN_GPG_PASSPHRASE
       - name: Set git config
         run: |
           git config --global user.email "dev+gha@lancedb.com"
@@ -55,10 +58,11 @@ jobs:
           echo "use-agent" >> ~/.gnupg/gpg.conf
           echo "pinentry-mode loopback" >> ~/.gnupg/gpg.conf
           export GPG_TTY=$(tty)
-          ./mvnw --batch-mode -DskipTests -DpushChanges=false -Dgpg.passphrase=${{ secrets.GPG_PASSPHRASE }} deploy -pl lancedb-core -am -P deploy-to-ossrh
+          ./mvnw --batch-mode -DskipTests -DpushChanges=false deploy -pl lancedb-core -am -P deploy-to-ossrh
         env:
           SONATYPE_USER: ${{ secrets.SONATYPE_USER }}
           SONATYPE_TOKEN: ${{ secrets.SONATYPE_TOKEN }}
+          MAVEN_GPG_PASSPHRASE: ${{ secrets.GPG_PASSPHRASE }}
 
   report-failure:
     name: Report Workflow Failure

.github/workflows/java.yml

@@ -24,6 +24,9 @@ on:
       - java/**
       - .github/workflows/java.yml
 
+permissions:
+  contents: read
+
 jobs:
   build-java:
     runs-on: ubuntu-24.04

.github/workflows/license-header-check.yml

@@ -10,6 +10,10 @@ on:
       - nodejs/**
       - java/**
       - .github/workflows/license-header-check.yml
+
+permissions:
+  contents: read
+
 jobs:
   check-licenses:
     runs-on: ubuntu-latest

.github/workflows/nodejs.yml

@@ -7,12 +7,17 @@ on:
   pull_request:
     paths:
       - Cargo.toml
+      - Cargo.lock
+      - rust-toolchain.toml
       - nodejs/**
       - rust/**
       - docs/src/js/**
       - .github/workflows/nodejs.yml
       - docker-compose.yml
 
+permissions:
+  contents: read
+
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
@@ -37,11 +42,17 @@ jobs:
       with:
         fetch-depth: 0
         lfs: true
-    - uses: actions/setup-node@v3
+    - uses: pnpm/action-setup@v4
       with:
-        node-version: 20
-        cache: 'npm'
-        cache-dependency-path: nodejs/package-lock.json
+        version: 11.1.1
+    - uses: actions/setup-node@v4
+      with:
+        # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
+        # in October. The library itself still supports Node >= 18
+        # (see test matrix below).
+        node-version: 24
+        cache: 'pnpm'
+        cache-dependency-path: nodejs/pnpm-lock.yaml
     - uses: actions-rust-lang/setup-rust-toolchain@v1
       with:
         components: rustfmt, clippy
@@ -56,11 +67,13 @@ jobs:
       run: cargo clippy --profile ci --all --all-features -- -D warnings
     - name: Lint Typescript
       run: |
-        npm ci
-        npm run lint-ci
+        pnpm install --frozen-lockfile
+        pnpm lint-ci
     - name: Lint examples
       working-directory: nodejs/examples
-      run: npm ci && npm run lint-ci
+      # The `@lancedb/lancedb` dep points at file:../dist; pnpm errors if
+      # that dir is missing, so create an empty one for lint-only runs.
+      run: mkdir -p ../dist && pnpm install --frozen-lockfile && pnpm lint-ci
   linux:
     name: Linux (NodeJS ${{ matrix.node-version }})
     timeout-minutes: 30
@@ -77,14 +90,18 @@ jobs:
       with:
         fetch-depth: 0
         lfs: true
-    - uses: actions/setup-node@v3
-      name: Setup Node.js 20 for build
+    - uses: pnpm/action-setup@v4
       with:
-        # @napi-rs/cli v3 requires Node >= 20.12 (via @inquirer/prompts@8).
-        # Build always on Node 20; tests run on the matrix version below.
-        node-version: 20
-        cache: 'npm'
-        cache-dependency-path: nodejs/package-lock.json
+        version: 11.1.1
+    - uses: actions/setup-node@v4
+      name: Setup Node.js 24 for build
+      with:
+        # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
+        # in October. Build/install runs on Node 24; tests run on the
+        # matrix version below using direct jest invocation.
+        node-version: 24
+        cache: 'pnpm'
+        cache-dependency-path: nodejs/pnpm-lock.yaml
     - uses: Swatinem/rust-cache@v2
     - name: Install dependencies
       run: |
@@ -92,48 +109,58 @@ jobs:
         sudo apt install -y protobuf-compiler libssl-dev
     - name: Build
       run: |
-        npm ci --include=optional
-        npm run build:debug -- --profile ci
-    - uses: actions/setup-node@v3
+        pnpm install --frozen-lockfile
+        # No `--` separator: pnpm forwards it literally, which would
+        # make napi-rs treat `--profile ci` as a cargo passthrough arg.
+        pnpm build:debug --profile ci
+        pnpm tsc
+    - name: Setup examples
+      working-directory: nodejs/examples
+      run: pnpm install --frozen-lockfile
+    - name: Check docs
+      run: |
+        # We run this as part of the job because the binary needs to be built
+        # first to export the types of the native code.
+        set -e
+        # `pnpm docs` would invoke pnpm's built-in `docs` command, not
+        # the script — use `pnpm run docs`.
+        pnpm run docs
+        if ! git diff --exit-code -- ../ ':(exclude)Cargo.lock'; then
+          echo "Docs need to be updated"
+          echo "Run 'pnpm run docs', fix any warnings, and commit the changes."
+          exit 1
+        fi
+    - uses: actions/setup-node@v4
       name: Setup Node.js ${{ matrix.node-version }} for test
       with:
         node-version: ${{ matrix.node-version }}
-    - name: Compile TypeScript
-      run: npm run tsc
     - name: Setup localstack
       working-directory: .
       run: docker compose up --detach --wait
     - name: Test
       env:
         S3_TEST: "1"
-      run: npm run test
-    - name: Setup examples
-      working-directory: nodejs/examples
-      run: npm ci
+        # Newer @smithy/core uses dynamic ESM imports.
+        NODE_OPTIONS: "--experimental-vm-modules"
+      # Invoke jest directly because pnpm 11 itself requires Node 22+
+      # while the matrix tests on older Node versions.
+      run: npx jest --verbose
     - name: Test examples
       working-directory: ./
       env:
         OPENAI_API_KEY: test
         OPENAI_BASE_URL: http://0.0.0.0:8000
+        NODE_OPTIONS: "--experimental-vm-modules"
       run: |
         python ci/mock_openai.py &
         cd nodejs/examples
-        npm test
-    - name: Check docs
-      run: |
-        # We run this as part of the job because the binary needs to be built
-        # first to export the types of the native code.
-        set -e
-        npm ci
-        npm run docs
-        if ! git diff --exit-code -- ../ ':(exclude)Cargo.lock'; then
-          echo "Docs need to be updated"
-          echo "Run 'npm run docs', fix any warnings, and commit the changes."
-          exit 1
-        fi
+        npx jest --testEnvironment jest-environment-node-single-context --verbose
   macos:
     timeout-minutes: 30
-    runs-on: "macos-14"
+    # macos-15 ships a newer linker; the older macos-14 linker fails to insert
+    # branch islands when the debug cdylib's __text section exceeds the 128 MB
+    # AArch64 B/BL branch range.
+    runs-on: "macos-15"
     defaults:
       run:
         shell: bash
@@ -143,20 +170,28 @@ jobs:
       with:
         fetch-depth: 0
         lfs: true
-    - uses: actions/setup-node@v3
+    - uses: pnpm/action-setup@v4
       with:
-        node-version: 20
-        cache: 'npm'
-        cache-dependency-path: nodejs/package-lock.json
+        version: 11.1.1
+    - uses: actions/setup-node@v4
+      with:
+        # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
+        # in October.
+        node-version: 24
+        cache: 'pnpm'
+        cache-dependency-path: nodejs/pnpm-lock.yaml
+    - uses: dtolnay/rust-toolchain@stable
     - uses: Swatinem/rust-cache@v2
     - name: Install dependencies
       run: |
         brew install protobuf
     - name: Build
       run: |
-        npm ci --include=optional
-        npm run build:debug -- --profile ci
-        npm run tsc
+        pnpm install --frozen-lockfile
+        # No `--` separator: pnpm forwards it literally, which would
+        # make napi-rs treat `--profile ci` as a cargo passthrough arg.
+        pnpm build:debug --profile ci
+        pnpm tsc
     - name: Test
       run: |
-        npm run test
+        pnpm test

.github/workflows/npm-publish.yml

@@ -19,6 +19,7 @@ on:
     paths:
       - .github/workflows/npm-publish.yml
       - Cargo.toml # Change in dependency frequently breaks builds
+      - Cargo.lock
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
@@ -124,7 +125,12 @@ jobs:
             pre_build: |-
               set -e &&
               apt-get update &&
-              apt-get install -y protobuf-compiler pkg-config
+              apt-get install -y protobuf-compiler pkg-config &&
+              # The base image (manylinux2014-cross) sets TARGET_CC to the old
+              # GCC 4.8 cross-compiler. aws-lc-sys checks TARGET_CC before CC,
+              # so it picks up GCC even though the napi-rs image sets CC=clang.
+              # Override to use the image's clang-18 which supports -fuse-ld=lld.
+              export TARGET_CC=clang TARGET_CXX=clang++
           - target: x86_64-unknown-linux-musl
             # This one seems to need some extra memory
             host: ubuntu-2404-8x-x64
@@ -144,9 +150,10 @@ jobs:
               set -e &&
               apt-get update &&
               apt-get install -y protobuf-compiler pkg-config &&
-              # https://github.com/aws/aws-lc-rs/issues/737#issuecomment-2725918627
-              ln -s /usr/aarch64-unknown-linux-gnu/lib/gcc/aarch64-unknown-linux-gnu/4.8.5/crtbeginS.o /usr/aarch64-unknown-linux-gnu/aarch64-unknown-linux-gnu/sysroot/usr/lib/crtbeginS.o &&
-              ln -s /usr/aarch64-unknown-linux-gnu/lib/gcc /usr/aarch64-unknown-linux-gnu/aarch64-unknown-linux-gnu/sysroot/usr/lib/gcc &&
+              export TARGET_CC=clang TARGET_CXX=clang++ &&
+              # The manylinux2014 sysroot has glibc 2.17 headers which lack
+              # AT_HWCAP2 (added in Linux 3.17). Define it for aws-lc-sys.
+              export CFLAGS="$CFLAGS -DAT_HWCAP2=26" &&
               rustup target add aarch64-unknown-linux-gnu
           - target: aarch64-unknown-linux-musl
             host: ubuntu-2404-8x-x64
@@ -164,13 +171,18 @@ jobs:
         working-directory: nodejs
     steps:
       - uses: actions/checkout@v4
+      - name: Setup pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 11.1.1
       - name: Setup node
         uses: actions/setup-node@v4
-        if: ${{ !matrix.settings.docker }}
         with:
-          node-version: 20
-          cache: npm
-          cache-dependency-path: nodejs/package-lock.json
+          # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
+          # in October.
+          node-version: 24
+          cache: pnpm
+          cache-dependency-path: nodejs/pnpm-lock.yaml
       - name: Install
         uses: dtolnay/rust-toolchain@stable
         if: ${{ !matrix.settings.docker }}
@@ -188,7 +200,7 @@ jobs:
             target/
           key: nodejs-${{ matrix.settings.target }}-cargo-${{ matrix.settings.host }}
       - name: Install dependencies
-        run: npm ci
+        run: pnpm install --frozen-lockfile
       - name: Install Zig
         uses: mlugg/setup-zig@v2
         if: ${{ contains(matrix.settings.target, 'musl') }}
@@ -241,7 +253,7 @@ jobs:
       # one to do the upload.
       - name: Make generic artifacts
         if: ${{ matrix.settings.target == 'aarch64-apple-darwin' }}
-        run: npm run tsc
+        run: pnpm tsc
       - name: Upload Generic Artifacts
         if: ${{ matrix.settings.target == 'aarch64-apple-darwin' }}
         uses: actions/upload-artifact@v4
@@ -266,7 +278,7 @@ jobs:
           - target: x86_64-unknown-linux-gnu
             host: ubuntu-latest
           - target: aarch64-unknown-linux-gnu
-            host: buildjet-16vcpu-ubuntu-2204-arm
+            host: ubuntu-2404-8x-arm64
         node:
           - '20'
     runs-on: ${{ matrix.settings.host }}
@@ -276,14 +288,24 @@ jobs:
         working-directory: nodejs
     steps:
       - uses: actions/checkout@v4
-      - name: Setup node
+      - name: Setup pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 11.1.1
+      - name: Setup Node.js 24 for install
+        uses: actions/setup-node@v4
+        with:
+          # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
+          # in October.
+          node-version: 24
+          cache: pnpm
+          cache-dependency-path: nodejs/pnpm-lock.yaml
+      - name: Install dependencies
+        run: pnpm install --frozen-lockfile
+      - name: Setup Node.js ${{ matrix.node }} for test
         uses: actions/setup-node@v4
         with:
           node-version: ${{ matrix.node }}
-          cache: npm
-          cache-dependency-path: nodejs/package-lock.json
-      - name: Install dependencies
-        run: npm ci
       - name: Download artifacts
         uses: actions/download-artifact@v4
         with:
@@ -304,7 +326,9 @@ jobs:
       - name: Move built files
         run: cp dist/native.d.ts dist/native.js dist/*.node lancedb/
       - name: Test bindings
-        run: npm test
+        # Invoke jest directly because pnpm 11 itself requires Node 22+
+        # while the matrix tests on older Node versions.
+        run: npx jest --verbose
   publish:
     name: Publish
     runs-on: ubuntu-latest
@@ -316,15 +340,19 @@ jobs:
       - test-lancedb
     steps:
       - uses: actions/checkout@v4
+      - name: Setup pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 11.1.1
       - name: Setup node
         uses: actions/setup-node@v4
         with:
           node-version: 24
-          cache: npm
-          cache-dependency-path: nodejs/package-lock.json
+          cache: pnpm
+          cache-dependency-path: nodejs/pnpm-lock.yaml
           registry-url: "https://registry.npmjs.org"
       - name: Install dependencies
-        run: npm ci
+        run: pnpm install --frozen-lockfile
       - uses: actions/download-artifact@v4
         with:
           name: nodejs-dist
@@ -344,7 +372,7 @@ jobs:
       - name: Display structure of downloaded files
         run: find dist && find nodejs-artifacts
       - name: Move artifacts
-        run: npx napi artifacts -d nodejs-artifacts
+        run: pnpm exec napi artifacts -d nodejs-artifacts
       - name: List packages
         run: find npm
       - name: Publish

.github/workflows/pypi-publish.yml

@@ -9,14 +9,21 @@ on:
     paths:
       - .github/workflows/pypi-publish.yml
       - Cargo.toml # Change in dependency frequently breaks builds
+      - Cargo.lock
 
 env:
   PIP_EXTRA_INDEX_URL: "https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/"
 
+permissions:
+  contents: read
+
 jobs:
   linux:
     name: Python ${{ matrix.config.platform }} manylinux${{ matrix.config.manylinux }}
     timeout-minutes: 60
+    permissions:
+      id-token: write
+      contents: read
     strategy:
       matrix:
         config:
@@ -56,10 +63,12 @@ jobs:
       - uses: ./.github/workflows/upload_wheel
         if: startsWith(github.ref, 'refs/tags/python-v')
         with:
-          pypi_token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
           fury_token: ${{ secrets.FURY_TOKEN }}
   mac:
     timeout-minutes: 90
+    permissions:
+      id-token: write
+      contents: read
     runs-on: ${{ matrix.config.runner }}
     strategy:
       matrix:
@@ -84,10 +93,12 @@ jobs:
       - uses: ./.github/workflows/upload_wheel
         if: startsWith(github.ref, 'refs/tags/python-v')
         with:
-          pypi_token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
           fury_token: ${{ secrets.FURY_TOKEN }}
   windows:
     timeout-minutes: 60
+    permissions:
+      id-token: write
+      contents: read
     runs-on: windows-latest
     steps:
       - uses: actions/checkout@v4
@@ -106,7 +117,6 @@ jobs:
       - uses: ./.github/workflows/upload_wheel
         if: startsWith(github.ref, 'refs/tags/python-v')
         with:
-          pypi_token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
           fury_token: ${{ secrets.FURY_TOKEN }}
   gh-release:
     if: startsWith(github.ref, 'refs/tags/python-v')

.github/workflows/python.yml

@@ -7,6 +7,8 @@ on:
   pull_request:
     paths:
       - Cargo.toml
+      - Cargo.lock
+      - rust-toolchain.toml
       - python/**
       - rust/**
       - .github/workflows/python.yml
@@ -15,6 +17,9 @@ on:
       - .github/workflows/build_windows_wheel/**
       - .github/workflows/run_tests/**
 
+permissions:
+  contents: read
+
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
@@ -106,7 +111,6 @@ jobs:
       - name: Install
         run: |
           pip install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests,dev,embeddings]
-          pip install tantivy
           pip install mlx
       - name: Doctest
         run: pytest --doctest-modules python/lancedb
@@ -201,7 +205,7 @@ jobs:
       - name: Delete wheels
         run: rm -rf target/wheels
   pydantic1x:
-    timeout-minutes: 30
+    timeout-minutes: 60
     runs-on: "ubuntu-24.04"
     defaults:
       run:
@@ -225,6 +229,5 @@ jobs:
           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
       - name: Run tests
         run: pytest -m "not slow and not s3_test" -x -v --durations=30 python/tests

.github/workflows/rust.yml

@@ -7,9 +7,17 @@ on:
   pull_request:
     paths:
       - Cargo.toml
+      - Cargo.lock
+      - rust-toolchain.toml
+      - deny.toml
       - rust/**
+      - nodejs/Cargo.toml
+      - python/Cargo.toml
       - .github/workflows/rust.yml
 
+permissions:
+  contents: read
+
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
@@ -51,6 +59,17 @@ jobs:
       - name: Run clippy (without remote feature)
         run: cargo clippy --profile ci --workspace --tests -- -D warnings
 
+  deny:
+    # Supply-chain checks: advisories, licenses, banned crates, and source
+    # restrictions. Configuration lives in `deny.toml` at the workspace root.
+    timeout-minutes: 10
+    runs-on: ubuntu-24.04
+    steps:
+      - uses: actions/checkout@v4
+      - uses: EmbarkStudios/cargo-deny-action@v2
+        with:
+          command: check advisories bans licenses sources
+
   build-no-lock:
     runs-on: ubuntu-24.04
     timeout-minutes: 30
@@ -206,14 +225,34 @@ jobs:
       - name: Downgrade  dependencies
         # These packages have newer requirements for MSRV
         run: |
-          cargo update -p aws-sdk-bedrockruntime --precise 1.64.0
-          cargo update -p aws-sdk-dynamodb --precise 1.55.0
-          cargo update -p aws-config --precise 1.5.10
-          cargo update -p aws-sdk-kms --precise 1.51.0
-          cargo update -p aws-sdk-s3 --precise 1.65.0
-          cargo update -p aws-sdk-sso --precise 1.50.0
-          cargo update -p aws-sdk-ssooidc --precise 1.51.0
-          cargo update -p aws-sdk-sts --precise 1.51.0
+          cargo update -p aws-sdk-bedrockruntime --precise 1.77.0
+          cargo update -p aws-sdk-dynamodb --precise 1.68.0
+          cargo update -p aws-config --precise 1.6.0
+          cargo update -p aws-sdk-kms --precise 1.63.0
+          cargo update -p aws-sdk-s3 --precise 1.79.0
+          cargo update -p aws-sdk-sso --precise 1.62.0
+          cargo update -p aws-sdk-ssooidc --precise 1.63.0
+          cargo update -p aws-sdk-sts --precise 1.63.0
+          # aws-runtime/sigv4/credential-types/types and the aws-smithy-*
+          # crates bumped their MSRV to 1.91.1 in late 2026; pin to the last
+          # 1.91.0-compatible versions. The order matters — each downgrade
+          # only succeeds once everything that still pins it at a higher
+          # version has itself been downgraded.
+          cargo update -p aws-runtime --precise 1.5.12
+          cargo update -p aws-types --precise 1.3.9
+          cargo update -p aws-sigv4 --precise 1.3.5
+          cargo update -p aws-credential-types --precise 1.2.8
+          cargo update -p aws-smithy-checksums --precise 0.63.9
+          cargo update -p aws-smithy-runtime --precise 1.9.3
+          cargo update -p aws-smithy-http --precise 0.62.4
+          cargo update -p aws-smithy-eventstream --precise 0.60.12
+          cargo update -p aws-smithy-http-client --precise 1.1.3
+          cargo update -p aws-smithy-observability --precise 0.1.4
+          cargo update -p aws-smithy-query --precise 0.60.8
+          cargo update -p aws-smithy-runtime-api --precise 1.9.1
+          cargo update -p aws-smithy-async --precise 1.2.6
+          cargo update -p aws-smithy-types --precise 1.3.5
+          cargo update -p aws-smithy-xml --precise 0.60.11
           cargo update -p home --precise 0.5.9
       - name: cargo +${{ matrix.msrv }} check
         env:

.github/workflows/update_package_lock_run.yml

@@ -3,6 +3,9 @@ name: Update package-lock.json
 on:
   workflow_dispatch:
 
+permissions:
+  contents: read
+
 jobs:
   publish:
     runs-on: ubuntu-latest

.github/workflows/update_package_lock_run_nodejs.yml

@@ -3,6 +3,9 @@ name: Update NodeJs package-lock.json
 on:
   workflow_dispatch:
 
+permissions:
+  contents: read
+
 jobs:
   publish:
     runs-on: ubuntu-latest

.github/workflows/upload_wheel/action.yml

@@ -2,9 +2,6 @@ name: upload-wheel
 
 description: "Upload wheels to Pypi"
 inputs:
-  pypi_token:
-    required: true
-    description: "release token for the repo"
   fury_token:
     required: true
     description: "release token for the fury repo"
@@ -12,12 +9,6 @@ inputs:
 runs:
   using: "composite"
   steps:
-  - name: Install dependencies
-    shell: bash
-    run: |
-      python -m pip install --upgrade pip
-      pip install twine
-      python3 -m pip install --upgrade pkginfo
   - name: Choose repo
     shell: bash
     id: choose_repo
@@ -27,19 +18,17 @@ runs:
       else
         echo "repo=pypi" >> $GITHUB_OUTPUT
       fi
-  - name: Publish to PyPI
+  - name: Publish to Fury
+    if: steps.choose_repo.outputs.repo == 'fury'
     shell: bash
     env:
       FURY_TOKEN: ${{ inputs.fury_token }}
-      PYPI_TOKEN: ${{ inputs.pypi_token }}
     run: |
-      if [[ ${{ steps.choose_repo.outputs.repo }} == fury ]]; then
-        WHEEL=$(ls target/wheels/lancedb-*.whl 2> /dev/null | head -n 1)
-        echo "Uploading $WHEEL to Fury"
-        curl -f -F package=@$WHEEL https://$FURY_TOKEN@push.fury.io/lancedb/
-      else
-        twine upload --repository ${{ steps.choose_repo.outputs.repo }} \
-          --username __token__ \
-          --password $PYPI_TOKEN \
-          target/wheels/lancedb-*.whl
-      fi
+      WHEEL=$(ls target/wheels/lancedb-*.whl 2> /dev/null | head -n 1)
+      echo "Uploading $WHEEL to Fury"
+      curl -f -F package=@$WHEEL https://$FURY_TOKEN@push.fury.io/lancedb/
+  - name: Publish to PyPI
+    if: steps.choose_repo.outputs.repo == 'pypi'
+    uses: pypa/gh-action-pypi-publish@release/v1
+    with:
+      packages-dir: target/wheels/

AGENTS.md

@@ -17,9 +17,30 @@ Common commands:
 * Run tests: `cargo test --quiet --features remote --tests`
 * Run specific test: `cargo test --quiet --features remote -p <package_name> --test <test_name>`
 * Lint: `cargo clippy --quiet --features remote --tests --examples`
-* Format: `cargo fmt --all`
+* Format Rust: `cargo fmt --all`
+* Format Python: `ruff format .`
+* Lint Python: `ruff check .`
+* Bootstrap Python dev env: `cd python && uv run --extra tests --extra dev maturin develop --extras tests,dev`
+* Run Python tests: `cd python && uv run --extra tests pytest python/tests -vv --durations=10 -m "not slow and not s3_test"`
+* Run specific Python test: `cd python && uv run --extra tests pytest python/tests/<test_file>.py::<test_name> -q`
 
-Before committing changes, run formatting.
+For Python validation, prefer the uv-managed environment declared by `python/uv.lock`.
+Do not treat system `python`, global `pytest`, or missing editable-install errors as
+final blockers; bootstrap or enter the uv environment instead. If `lancedb._lancedb`
+is missing or stale, or if Rust/PyO3 binding code changed, rebuild the Python
+extension with the bootstrap command above before running tests.
+
+Before committing changes, run formatting for every language you touched. At minimum:
+
+* Rust changes: run `cargo fmt --all`.
+* Python changes: run `ruff format .` and `ruff check .` from the repository root,
+  and run targeted tests through `cd python && uv run ...`.
+* TypeScript changes: run the relevant `npm`/`pnpm` lint, format, build, and docs commands in `nodejs`.
+
+Before creating a PR, make sure the PR title follows Conventional Commits, such as
+`fix: support nested field paths in native index creation` or
+`feat(python): add dataset multiprocessing support`. The semantic-release check uses the
+PR title and body as the merge commit message, so a non-conventional PR title will fail CI.
 
 ## Coding tips
 

Cargo.toml

@@ -1,7 +1,5 @@
 [workspace]
 members = ["rust/lancedb", "nodejs", "python"]
-# Python package needs to be built by maturin.
-exclude = ["python"]
 resolver = "2"
 
 [workspace.package]
@@ -15,40 +13,40 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"
 
 [workspace.dependencies]
-lance = { "version" = "=3.0.0-rc.2", default-features = false, "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=3.0.0-rc.2", default-features = false, "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=3.0.0-rc.2", default-features = false, "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=7.0.0-beta.13", default-features = false, "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=7.0.0-beta.13", "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=7.0.0-beta.13", "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=7.0.0-beta.13", "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=7.0.0-beta.13", default-features = false, "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=7.0.0-beta.13", "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=7.0.0-beta.13", "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=7.0.0-beta.13", "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=7.0.0-beta.13", default-features = false, "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=7.0.0-beta.13", "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=7.0.0-beta.13", "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=7.0.0-beta.13", "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=7.0.0-beta.13", "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=7.0.0-beta.13", "tag" = "v7.0.0-beta.13", "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 = "58.0.0", optional = false }
+arrow-array = "58.0.0"
+arrow-data = "58.0.0"
+arrow-ipc = "58.0.0"
+arrow-ord = "58.0.0"
+arrow-schema = "58.0.0"
+arrow-select = "58.0.0"
+arrow-cast = "58.0.0"
 async-trait = "0"
-datafusion = { version = "52.1", default-features = false }
-datafusion-catalog = "52.1"
-datafusion-common = { version = "52.1", default-features = false }
-datafusion-execution = "52.1"
-datafusion-expr = "52.1"
-datafusion-functions = "52.1"
-datafusion-physical-plan = "52.1"
-datafusion-physical-expr = "52.1"
-datafusion-sql = "52.1"
+datafusion = { version = "53.0.0", default-features = false }
+datafusion-catalog = "53.0.0"
+datafusion-common = { version = "53.0.0", default-features = false }
+datafusion-execution = "53.0.0"
+datafusion-expr = "53.0.0"
+datafusion-functions = "53.0.0"
+datafusion-physical-plan = "53.0.0"
+datafusion-physical-expr = "53.0.0"
+datafusion-sql = "53.0.0"
 env_logger = "0.11"
 half = { "version" = "2.7.1", default-features = false, features = [
     "num-traits",
@@ -56,7 +54,7 @@ half = { "version" = "2.7.1", default-features = false, features = [
 futures = "0"
 log = "0.4"
 moka = { version = "0.12", features = ["future"] }
-object_store = "0.12.0"
+object_store = "0.13.2"
 pin-project = "1.0.7"
 rand = "0.9"
 snafu = "0.8"

README.md

@@ -15,7 +15,7 @@
 
 # **The Multimodal AI Lakehouse**
 
-[**How to Install** ](#how-to-install) ✦ [**Detailed Documentation**](https://lancedb.com/docs) ✦ [**Tutorials and Recipes**](https://github.com/lancedb/vectordb-recipes/tree/main) ✦  [**Contributors**](#contributors) 
+[**How to Install** ](#how-to-install) ✦ [**Detailed Documentation**](https://docs.lancedb.com) ✦ [**Tutorials and Recipes**](https://github.com/lancedb/vectordb-recipes/tree/main) ✦  [**Contributors**](#contributors) 
 
 **The ultimate multimodal data platform for AI/ML applications.** 
 
@@ -57,7 +57,7 @@ LanceDB is a central location where developers can build, train and analyze thei
 
 ## **How to Install**:
 
-Follow the [Quickstart](https://lancedb.com/docs/quickstart/) doc to set up LanceDB locally. 
+Follow the [Quickstart](https://docs.lancedb.com/quickstart) doc to set up LanceDB locally. 
 
 **API & SDK:** We also support Python, Typescript and Rust SDKs
 

ci/check_lance_release.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import argparse
+import functools
 import json
 import os
 import re
@@ -26,6 +27,7 @@ SEMVER_RE = re.compile(
 )
 
 
+@functools.total_ordering
 @dataclass(frozen=True)
 class SemVer:
     major: int
@@ -156,7 +158,9 @@ def read_current_version(repo_root: Path) -> str:
 
 
 def determine_latest_tag(tags: Iterable[TagInfo]) -> TagInfo:
-    return max(tags, key=lambda tag: tag.semver)
+    # Stable releases (no prerelease) are always preferred over pre-releases.
+    # Within each group, standard semver ordering applies.
+    return max(tags, key=lambda tag: (not tag.semver.prerelease, tag.semver))
 
 
 def write_outputs(args: argparse.Namespace, payload: dict) -> None:

deny.toml

@@ -0,0 +1,196 @@
+# cargo-deny configuration for LanceDB.
+#
+# Run locally with `cargo deny check`. See
+# https://embarkstudios.github.io/cargo-deny/ for the full reference.
+
+# The set of target triples we care about. cargo-deny will only consider
+# dependencies that are used on at least one of these targets. Keeping this
+# explicit avoids noise from platform-specific crates (e.g. wasm, android,
+# ios) that we never actually ship.
+[graph]
+targets = [
+    "x86_64-unknown-linux-gnu",
+    "aarch64-unknown-linux-gnu",
+    "x86_64-apple-darwin",
+    "aarch64-apple-darwin",
+    "x86_64-pc-windows-msvc",
+    "aarch64-pc-windows-msvc",
+]
+all-features = true
+
+[output]
+feature-depth = 1
+
+# ---------------------------------------------------------------------------
+# Advisories: security vulnerabilities and yanked crates.
+# ---------------------------------------------------------------------------
+[advisories]
+version = 2
+# Fail the check if any crate in the lockfile has been yanked from crates.io.
+# Yanked crates are a signal the author retracted the release (often due to
+# bugs or security issues) and should not be depended on.
+yanked = "deny"
+# Advisory IDs we have explicitly reviewed and chosen to accept. Every
+# entry must include a rationale and, where possible, an upstream issue
+# pointing to a fix. Revisit this list whenever dependencies are updated.
+ignore = [
+    # rsa: Marvin Attack timing side-channel in PKCS#1 v1.5 decryption.
+    # Reached only through opendal → reqsign → rsa. We do not use RSA
+    # decryption in LanceDB ourselves; this is dormant in the signing path.
+    # No fixed release exists upstream as of this writing.
+    # https://rustsec.org/advisories/RUSTSEC-2023-0071
+    { id = "RUSTSEC-2023-0071", reason = "rsa crate via opendal/reqsign; no fixed upstream release" },
+
+    # instant: unmaintained. Pulled in via backoff → instant. Upstream
+    # recommends switching to `web-time`; fix has to come from backoff.
+    # https://rustsec.org/advisories/RUSTSEC-2024-0384
+    { id = "RUSTSEC-2024-0384", reason = "transitive via backoff; waiting on backoff replacement" },
+
+    # paste: unmaintained (author archived the repo). Used transitively by
+    # datafusion and the arrow ecosystem; widespread, no drop-in replacement.
+    # https://rustsec.org/advisories/RUSTSEC-2024-0436
+    { id = "RUSTSEC-2024-0436", reason = "transitive via datafusion; awaiting ecosystem migration" },
+
+    # encoding: unmaintained. Reached through lindera-dictionary, which is
+    # required by the native Lindera tokenizer path. Lindera has not migrated
+    # off this crate yet.
+    # https://rustsec.org/advisories/RUSTSEC-2021-0153
+    { id = "RUSTSEC-2021-0153", reason = "transitive via lindera-dictionary for native Lindera tokenizer" },
+
+    # fast-float: unsound and unmaintained. Reached only through polars-arrow
+    # from the optional Polars integration; replacement requires a Polars
+    # dependency upgrade.
+    # https://rustsec.org/advisories/RUSTSEC-2024-0379
+    { id = "RUSTSEC-2024-0379", reason = "transitive via polars-arrow; waiting on Polars migration" },
+
+    # tantivy: segfault on malformed input due to missing bounds check.
+    # Pulled in via lance for full-text search. We only feed tantivy
+    # documents we construct ourselves, not attacker-controlled bytes.
+    # Tracked for a lance dependency bump.
+    # https://rustsec.org/advisories/RUSTSEC-2025-0003
+    { id = "RUSTSEC-2025-0003", reason = "tantivy via lance; inputs are internally produced, not user-supplied bytes" },
+
+    # backoff: unmaintained. Reached only via async-openai. Replacement
+    # requires async-openai to migrate (or us to drop async-openai).
+    # https://rustsec.org/advisories/RUSTSEC-2025-0012
+    { id = "RUSTSEC-2025-0012", reason = "transitive via async-openai; waiting on upstream migration" },
+
+    # number_prefix: unmaintained. Transitive via indicatif → hf-hub.
+    # No security impact, just maintenance status.
+    # https://rustsec.org/advisories/RUSTSEC-2025-0119
+    { id = "RUSTSEC-2025-0119", reason = "transitive via hf-hub/indicatif; cosmetic formatting crate" },
+
+    # bincode: unmaintained. Reached through lindera and lindera-dictionary,
+    # which are required by the native Lindera tokenizer path. Lindera has not
+    # migrated to another serialization format yet.
+    # https://rustsec.org/advisories/RUSTSEC-2025-0141
+    { id = "RUSTSEC-2025-0141", reason = "transitive via lindera/lindera-dictionary for native Lindera tokenizer" },
+
+    # lru: soundness issue in IterMut. Reached only through aws-sdk-s3 in
+    # LanceDB's dev-dependency graph; LanceDB does not use that iterator
+    # directly. Clearing this requires the AWS SDK chain to update lru.
+    # https://rustsec.org/advisories/RUSTSEC-2026-0002
+    { id = "RUSTSEC-2026-0002", reason = "transitive via aws-sdk-s3 dev-dependency; waiting on AWS SDK lru upgrade" },
+
+    # rustls-webpki 0.101.7 (old major line): name-constraint checks for
+    # URI / wildcard names. Pulled in only via the legacy rustls 0.21 chain
+    # from aws-smithy-http-client. The 0.103 line we actively use is patched.
+    # Clearing the 0.101 copy requires the aws-sdk chain to migrate off
+    # rustls 0.21.
+    # https://rustsec.org/advisories/RUSTSEC-2026-0098
+    # https://rustsec.org/advisories/RUSTSEC-2026-0099
+    { id = "RUSTSEC-2026-0098", reason = "only affects rustls-webpki 0.101 from legacy aws-smithy/rustls 0.21 chain" },
+    { id = "RUSTSEC-2026-0099", reason = "only affects rustls-webpki 0.101 from legacy aws-smithy/rustls 0.21 chain" },
+
+    # rustls-webpki 0.101.7: reachable panic in CRL parsing. Same legacy
+    # rustls 0.21 chain from aws-smithy-http-client as above. The 0.103 line
+    # we actively use is upgraded to 0.103.13 which contains the fix.
+    # https://rustsec.org/advisories/RUSTSEC-2026-0104
+    { id = "RUSTSEC-2026-0104", reason = "only affects rustls-webpki 0.101 from legacy aws-smithy/rustls 0.21 chain" },
+
+    # rand 0.8.5: soundness issue only when ThreadRng reseeds inside a custom
+    # logger. Reached through several transitive chains. LanceDB does not use
+    # rand from a custom logger; upgrade once all pinned chains accept 0.8.6+.
+    # https://rustsec.org/advisories/RUSTSEC-2026-0097
+    { id = "RUSTSEC-2026-0097", reason = "transitive rand 0.8.5; LanceDB does not call ThreadRng from custom logging" },
+]
+
+# ---------------------------------------------------------------------------
+# Licenses: only allow licenses we've reviewed as compatible with Apache-2.0.
+# ---------------------------------------------------------------------------
+[licenses]
+version = 2
+# SPDX identifiers for licenses that are compatible with our Apache-2.0
+# distribution. Additions require legal review.
+allow = [
+    "Apache-2.0",
+    "Apache-2.0 WITH LLVM-exception",
+    "MIT",
+    "BSD-2-Clause",
+    "BSD-3-Clause",
+    "ISC",
+    "Unicode-3.0",
+    "Unicode-DFS-2016",
+    "Zlib",
+    "CC0-1.0",
+    "MPL-2.0",
+    "BSL-1.0",
+    "OpenSSL",
+    # 0BSD ("BSD Zero Clause") is effectively public domain — no attribution
+    # required. Pulled in by `mock_instant`.
+    "0BSD",
+    # bzip2-1.0.6 is the permissive upstream bzip2 license (BSD-like). Pulled
+    # in by `libbz2-rs-sys`, the pure-Rust bzip2 implementation.
+    "bzip2-1.0.6",
+    # CDLA-Permissive-2.0 is a permissive data license used by `webpki-roots`
+    # for the Mozilla CA root bundle. Data-only, distribution-compatible.
+    "CDLA-Permissive-2.0",
+]
+confidence-threshold = 0.8
+# Crates whose license cannot be determined from Cargo metadata but whose
+# license we've manually confirmed from upstream. Keep this list minimal.
+[[licenses.clarify]]
+# polars-arrow-format omits the `license` field in its Cargo.toml, but the
+# upstream repo (pola-rs/polars-arrow-format) is dual-licensed Apache-2.0 OR
+# MIT. See https://github.com/pola-rs/polars-arrow-format/blob/main/LICENSE
+crate = "polars-arrow-format"
+expression = "Apache-2.0 OR MIT"
+license-files = []
+
+# ---------------------------------------------------------------------------
+# Bans: disallow specific crates and flag dependency hygiene issues.
+# ---------------------------------------------------------------------------
+[bans]
+# Warn (not deny) on duplicate versions of the same crate. In a large
+# workspace like this one, duplicates are common and often unavoidable
+# transitively. We surface them to discourage growth, but don't fail CI.
+multiple-versions = "warn"
+# Wildcard version requirements (`foo = "*"`) are a footgun — they let any
+# future release in without review. Ban them outright.
+wildcards = "deny"
+# Internal workspace crates reference each other via `path = "..."`, which
+# cargo-deny sees as a wildcard version. That's fine for private workspace
+# members (not published to crates.io), so allow it specifically for paths.
+allow-wildcard-paths = true
+# Features that, if enabled, should cause the check to fail.
+deny = []
+# Crates to skip when checking for duplicate versions.
+skip = []
+# Similar to `skip`, but also skips the entire transitive subtree.
+skip-tree = []
+
+# ---------------------------------------------------------------------------
+# Sources: restrict where crates can come from.
+# ---------------------------------------------------------------------------
+[sources]
+# Deny any registry other than the ones explicitly listed below.
+unknown-registry = "deny"
+# Deny any git dependency whose host isn't in the allow-list below. This
+# prevents accidental pulls from arbitrary forks.
+unknown-git = "deny"
+allow-registry = ["https://github.com/rust-lang/crates.io-index"]
+# Lance is developed in a sibling repo and pulled as a git dependency until
+# releases are cut to crates.io. Allow that specific host.
+allow-git = [
+    "https://github.com/lance-format/lance",
+]

docker-compose.yml

@@ -1,7 +1,7 @@
 version: "3.9"
 services:
   localstack:
-    image: localstack/localstack:3.3
+    image: localstack/localstack:4.0
     ports:
       - 4566:4566
     environment:

dockerfiles/Dockerfile

@@ -1,27 +1,27 @@
-#Simple base dockerfile that supports basic dependencies required to run lance with FTS and Hybrid Search
-#Usage docker build -t lancedb:latest -f Dockerfile .
-FROM python:3.10-slim-buster
+# Simple base dockerfile that supports basic dependencies required to run lance with FTS and Hybrid Search
+# Usage: docker build -t lancedb:latest -f Dockerfile .
+FROM python:3.12-slim-bookworm
 
-# Install Rust
-RUN apt-get update && apt-get install -y curl build-essential && \
-  curl https://sh.rustup.rs -sSf | sh -s -- -y
-
-# Set the environment variable for Rust
-ENV PATH="/root/.cargo/bin:${PATH}"
-
-# Install protobuf compiler
-RUN apt-get install -y protobuf-compiler && \
+# Install build dependencies in a single layer
+RUN apt-get update && \
+  apt-get install -y --no-install-recommends \
+    curl \
+    build-essential \
+    protobuf-compiler \
+    git \
+    ca-certificates && \
   apt-get clean && \
   rm -rf /var/lib/apt/lists/*
 
-RUN apt-get -y update &&\
-  apt-get -y upgrade && \
-  apt-get -y install git
+# Install Rust (pinned installer, non-interactive)
+RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain stable --profile minimal
 
+# Set the environment variable for Rust
+ENV PATH="/root/.cargo/bin:${PATH}"
 
 # Verify installations
 RUN python --version && \
   rustc --version && \
   protoc --version
 
-RUN pip install tantivy lancedb
+RUN pip install --no-cache-dir lancedb

docs/README.md

@@ -1,6 +1,6 @@
 # LanceDB Documentation
 
-LanceDB docs are available at [lancedb.com/docs](https://lancedb.com/docs).
+LanceDB docs are available at [docs.lancedb.com](https://docs.lancedb.com).
 
 The SDK docs are built and deployed automatically by [Github Actions](../.github/workflows/docs.yml)
 whenever a commit is pushed to the `main` branch. So it is possible for the docs to show

docs/requirements.txt

@@ -1,9 +1,9 @@
-mkdocs==1.5.3
+mkdocs==1.6.1
 mkdocs-jupyter==0.24.1
-mkdocs-material==9.5.3
-mkdocs-autorefs<=1.0
-mkdocstrings[python]==0.25.2
-griffe
-mkdocs-render-swagger-plugin
-pydantic
-mkdocs-redirects
+mkdocs-material==9.6.23
+mkdocs-autorefs>=0.5,<=1.0
+mkdocstrings[python]>=0.24,<1.0
+griffe>=0.40,<1.0
+mkdocs-render-swagger-plugin>=0.1.0
+pydantic>=2.0,<3.0
+mkdocs-redirects>=1.2.0

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>0.27.0-beta.3</version>
+    <version>0.29.1-beta.0</version>
 </dependency>
 ```
 
@@ -57,32 +57,32 @@ LanceNamespace namespaceClient = LanceDbNamespaceClientBuilder.newBuilder()
 
 ## Metadata Operations
 
-### Creating a Namespace
+### Creating a Namespace Path
 
-Namespaces organize tables hierarchically. Create a namespace before creating tables within it:
+Namespace paths organize tables hierarchically. Create the desired namespace path before creating tables within it:
 
 ```java
 import org.lance.namespace.model.CreateNamespaceRequest;
 import org.lance.namespace.model.CreateNamespaceResponse;
 
-// Create a child namespace
+// Create a child namespace path
 CreateNamespaceRequest request = new CreateNamespaceRequest();
 request.setId(Arrays.asList("my_namespace"));
 
 CreateNamespaceResponse response = namespaceClient.createNamespace(request);
 ```
 
-You can also create nested namespaces:
+You can also create nested namespace paths:
 
 ```java
-// Create a nested namespace: parent/child
+// Create a nested namespace path: parent/child
 CreateNamespaceRequest request = new CreateNamespaceRequest();
 request.setId(Arrays.asList("parent_namespace", "child_namespace"));
 
 CreateNamespaceResponse response = namespaceClient.createNamespace(request);
 ```
 
-### Describing a Namespace
+### Describing a Namespace Path
 
 ```java
 import org.lance.namespace.model.DescribeNamespaceRequest;
@@ -95,22 +95,22 @@ DescribeNamespaceResponse response = namespaceClient.describeNamespace(request);
 System.out.println("Namespace properties: " + response.getProperties());
 ```
 
-### Listing Namespaces
+### Listing Namespace Paths
 
 ```java
 import org.lance.namespace.model.ListNamespacesRequest;
 import org.lance.namespace.model.ListNamespacesResponse;
 
-// List all namespaces at root level
+// List all namespace paths at the root level
 ListNamespacesRequest request = new ListNamespacesRequest();
 request.setId(Arrays.asList());  // Empty for root
 
 ListNamespacesResponse response = namespaceClient.listNamespaces(request);
 for (String ns : response.getNamespaces()) {
-    System.out.println("Namespace: " + ns);
+    System.out.println("Namespace path: " + ns);
 }
 
-// List child namespaces under a parent
+// List child namespace paths under a parent path
 ListNamespacesRequest childRequest = new ListNamespacesRequest();
 childRequest.setId(Arrays.asList("parent_namespace"));
 
@@ -123,7 +123,7 @@ ListNamespacesResponse childResponse = namespaceClient.listNamespaces(childReque
 import org.lance.namespace.model.ListTablesRequest;
 import org.lance.namespace.model.ListTablesResponse;
 
-// List tables in a namespace
+// List tables in a namespace path
 ListTablesRequest request = new ListTablesRequest();
 request.setId(Arrays.asList("my_namespace"));
 
@@ -133,7 +133,7 @@ for (String table : response.getTables()) {
 }
 ```
 
-### Dropping a Namespace
+### Dropping a Namespace Path
 
 ```java
 import org.lance.namespace.model.DropNamespaceRequest;
@@ -175,7 +175,7 @@ DropTableResponse response = namespaceClient.dropTable(request);
 
 ### Creating a Table
 
-Tables are created within a namespace by providing data in Apache Arrow IPC format:
+Tables are created within a namespace path by providing data in Apache Arrow IPC format:
 
 ```java
 import org.lance.namespace.LanceNamespace;
@@ -242,7 +242,7 @@ try (BufferAllocator allocator = new RootAllocator();
     }
     byte[] tableData = out.toByteArray();
 
-    // Create table in a namespace
+    // Create a table in a namespace path
     CreateTableRequest request = new CreateTableRequest();
     request.setId(Arrays.asList("my_namespace", "my_table"));
     CreateTableResponse response = namespaceClient.createTable(request, tableData);

docs/src/js/README.md

@@ -34,7 +34,7 @@ const results = await table.vectorSearch([0.1, 0.3]).limit(20).toArray();
 console.log(results);
 ```
 
-The [quickstart](https://lancedb.com/docs/quickstart/basic-usage/) contains more complete examples.
+The [quickstart](https://docs.lancedb.com/quickstart/) contains more complete examples.
 
 ## Development
 

docs/src/js/_media/CONTRIBUTING.md

@@ -12,20 +12,22 @@ Typescript.
 * `src/`: Rust bindings source code
 * `lancedb/`: Typescript package source code
 * `__test__/`: Unit tests
-* `examples/`: An npm package with the examples shown in the documentation
+* `examples/`: A pnpm package with the examples shown in the documentation
 
 ## Development environment
 
 To set up your development environment, you will need to install the following:
 
-1. Node.js 14 or later
-2. Rust's package manager, Cargo. Use [rustup](https://rustup.rs/) to install.
-3. [protoc](https://grpc.io/docs/protoc-installation/) (Protocol Buffers compiler)
+1. Node.js 22 or later (required by pnpm 11)
+2. [pnpm](https://pnpm.io/installation) 11 or later (or run via `corepack enable`,
+   which uses the `packageManager` field in `package.json`)
+3. Rust's package manager, Cargo. Use [rustup](https://rustup.rs/) to install.
+4. [protoc](https://grpc.io/docs/protoc-installation/) (Protocol Buffers compiler)
 
 Initial setup:
 
 ```shell
-npm install
+pnpm install
 ```
 
 ### Commit Hooks
@@ -39,38 +41,38 @@ pre-commit install
 
 ## Development
 
-Most common development commands can be run using the npm scripts.
+Most common development commands can be run using the pnpm scripts.
 
 Build the package
 
 ```shell
-npm install
-npm run build
+pnpm install
+pnpm build
 ```
 
 Lint:
 
 ```shell
-npm run lint
+pnpm lint
 ```
 
 Format and fix lints:
 
 ```shell
-npm run lint-fix
+pnpm lint-fix
 ```
 
 Run tests:
 
 ```shell
-npm test
+pnpm test
 ```
 
 To run a single test:
 
 ```shell
 # Single file: table.test.ts
-npm test -- table.test.ts
+pnpm test -- table.test.ts
 # Single test: 'merge insert' in table.test.ts
-npm test -- table.test.ts --testNamePattern=merge\ insert
+pnpm test -- table.test.ts --testNamePattern=merge\ insert
 ```

docs/src/js/classes/Connection.md

@@ -61,8 +61,8 @@ sharing the same data, deletion, and index files.
 * **options.sourceVersion?**: `number`
     The version of the source table to clone.
 
-* **options.targetNamespace?**: `string`[]
-    The namespace for the target table (defaults to root namespace).
+* **options.targetNamespacePath?**: `string`[]
+    The namespace path for the target table (defaults to root namespace).
 
 #### Returns
 
@@ -116,13 +116,13 @@ Creates a new empty Table
 
 `Promise`<[`Table`](Table.md)>
 
-#### createEmptyTable(name, schema, namespace, options)
+#### createEmptyTable(name, schema, namespacePath, options)
 
 ```ts
 abstract createEmptyTable(
    name,
    schema,
-   namespace?,
+   namespacePath?,
    options?): Promise<Table>
 ```
 
@@ -136,8 +136,8 @@ Creates a new empty Table
 * **schema**: [`SchemaLike`](../type-aliases/SchemaLike.md)
     The schema of the table
 
-* **namespace?**: `string`[]
-    The namespace to create the table in (defaults to root namespace)
+* **namespacePath?**: `string`[]
+    The namespace path to create the table in (defaults to root namespace)
 
 * **options?**: `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
     Additional options
@@ -148,12 +148,39 @@ Creates a new empty Table
 
 ***
 
-### createTable()
-
-#### createTable(options, namespace)
+### createNamespace()
 
 ```ts
-abstract createTable(options, namespace?): Promise<Table>
+abstract createNamespace(namespacePath, options?): Promise<CreateNamespaceResponse>
+```
+
+Create a new namespace at the given path.
+
+#### Parameters
+
+* **namespacePath**: `string`[]
+    The namespace path to create.
+
+* **options?**: `Partial`&lt;[`CreateNamespaceOptions`](../interfaces/CreateNamespaceOptions.md)&gt;
+    Creation `mode`
+    ("create" | "exist_ok" | "overwrite") and optional `properties`
+    to attach to the namespace.
+
+#### Returns
+
+`Promise`&lt;[`CreateNamespaceResponse`](../interfaces/CreateNamespaceResponse.md)&gt;
+
+The properties of the
+  created namespace and an optional transaction id.
+
+***
+
+### createTable()
+
+#### createTable(options, namespacePath)
+
+```ts
+abstract createTable(options, namespacePath?): Promise<Table>
 ```
 
 Creates a new Table and initialize it with new data.
@@ -163,8 +190,8 @@ Creates a new Table and initialize it with new data.
 * **options**: `object` & `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
     The options object.
 
-* **namespace?**: `string`[]
-    The namespace to create the table in (defaults to root namespace)
+* **namespacePath?**: `string`[]
+    The namespace path to create the table in (defaults to root namespace)
 
 ##### Returns
 
@@ -197,13 +224,13 @@ Creates a new Table and initialize it with new data.
 
 `Promise`&lt;[`Table`](Table.md)&gt;
 
-#### createTable(name, data, namespace, options)
+#### createTable(name, data, namespacePath, options)
 
 ```ts
 abstract createTable(
    name,
    data,
-   namespace?,
+   namespacePath?,
    options?): Promise<Table>
 ```
 
@@ -218,8 +245,8 @@ Creates a new Table and initialize it with new data.
     Non-empty Array of Records
     to be inserted into the table
 
-* **namespace?**: `string`[]
-    The namespace to create the table in (defaults to root namespace)
+* **namespacePath?**: `string`[]
+    The namespace path to create the table in (defaults to root namespace)
 
 * **options?**: `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
     Additional options
@@ -230,6 +257,29 @@ Creates a new Table and initialize it with new data.
 
 ***
 
+### describeNamespace()
+
+```ts
+abstract describeNamespace(namespacePath): Promise<DescribeNamespaceResponse>
+```
+
+Describe a namespace, returning its properties.
+
+#### Parameters
+
+* **namespacePath**: `string`[]
+    The namespace path to describe, in
+    parent → child order, e.g. `["analytics", "sales"]`.
+
+#### Returns
+
+`Promise`&lt;[`DescribeNamespaceResponse`](../interfaces/DescribeNamespaceResponse.md)&gt;
+
+The namespace's properties
+  (may be undefined if the namespace has none).
+
+***
+
 ### display()
 
 ```ts
@@ -247,15 +297,15 @@ Return a brief description of the connection
 ### dropAllTables()
 
 ```ts
-abstract dropAllTables(namespace?): Promise<void>
+abstract dropAllTables(namespacePath?): Promise<void>
 ```
 
 Drop all tables in the database.
 
 #### Parameters
 
-* **namespace?**: `string`[]
-    The namespace to drop tables from (defaults to root namespace).
+* **namespacePath?**: `string`[]
+    The namespace path to drop tables from (defaults to root namespace).
 
 #### Returns
 
@@ -263,10 +313,40 @@ Drop all tables in the database.
 
 ***
 
+### dropNamespace()
+
+```ts
+abstract dropNamespace(namespacePath, options?): Promise<DropNamespaceResponse>
+```
+
+Drop a namespace.
+
+Use `behavior: "cascade"` to also drop everything contained in the
+namespace (sub-namespaces and tables). The default `"restrict"`
+behavior refuses to drop a non-empty namespace.
+
+#### Parameters
+
+* **namespacePath**: `string`[]
+    The namespace path to drop.
+
+* **options?**: `Partial`&lt;[`DropNamespaceOptions`](../interfaces/DropNamespaceOptions.md)&gt;
+    `mode` ("skip" | "fail"
+    for missing-namespace handling) and `behavior` ("restrict" | "cascade").
+
+#### Returns
+
+`Promise`&lt;[`DropNamespaceResponse`](../interfaces/DropNamespaceResponse.md)&gt;
+
+Any properties returned by
+  the server and an optional transaction id.
+
+***
+
 ### dropTable()
 
 ```ts
-abstract dropTable(name, namespace?): Promise<void>
+abstract dropTable(name, namespacePath?): Promise<void>
 ```
 
 Drop an existing table.
@@ -276,8 +356,8 @@ Drop an existing table.
 * **name**: `string`
     The name of the table to drop.
 
-* **namespace?**: `string`[]
-    The namespace of the table (defaults to root namespace).
+* **namespacePath?**: `string`[]
+    The namespace path of the table (defaults to root namespace).
 
 #### Returns
 
@@ -299,12 +379,42 @@ Return true if the connection has not been closed
 
 ***
 
+### listNamespaces()
+
+```ts
+abstract listNamespaces(namespacePath?, options?): Promise<ListNamespacesResponse>
+```
+
+List the immediate child namespaces under the given parent.
+
+Results may be paginated. To retrieve subsequent pages, pass the
+`pageToken` returned by a previous call.
+
+#### Parameters
+
+* **namespacePath?**: `string`[]
+    The parent namespace path. Defaults
+    to the root namespace if omitted.
+
+* **options?**: `Partial`&lt;[`ListNamespacesOptions`](../interfaces/ListNamespacesOptions.md)&gt;
+    Pagination options
+    (`pageToken`, `limit`).
+
+#### Returns
+
+`Promise`&lt;[`ListNamespacesResponse`](../interfaces/ListNamespacesResponse.md)&gt;
+
+Child namespace names and
+  an optional token for fetching the next page.
+
+***
+
 ### openTable()
 
 ```ts
 abstract openTable(
    name,
-   namespace?,
+   namespacePath?,
    options?): Promise<Table>
 ```
 
@@ -315,8 +425,8 @@ Open a table in the database.
 * **name**: `string`
     The name of the table
 
-* **namespace?**: `string`[]
-    The namespace of the table (defaults to root namespace)
+* **namespacePath?**: `string`[]
+    The namespace path of the table (defaults to root namespace)
 
 * **options?**: `Partial`&lt;[`OpenTableOptions`](../interfaces/OpenTableOptions.md)&gt;
     Additional options
@@ -327,6 +437,39 @@ Open a table in the database.
 
 ***
 
+### renameTable()
+
+```ts
+abstract renameTable(
+   currentName,
+   newName,
+   options?): Promise<void>
+```
+
+Rename a table.
+
+Currently only supported by LanceDB Cloud. Local OSS connections and
+namespace-backed connections (via [connectNamespace](../functions/connectNamespace.md)) reject with
+a "not supported" error.
+
+#### Parameters
+
+* **currentName**: `string`
+    The current name of the table.
+
+* **newName**: `string`
+    The new name for the table.
+
+* **options?**: [`RenameTableOptions`](../interfaces/RenameTableOptions.md)
+    Optional namespace paths. When
+    `newNamespacePath` is omitted the table stays in `namespacePath`.
+
+#### Returns
+
+`Promise`&lt;`void`&gt;
+
+***
+
 ### tableNames()
 
 #### tableNames(options)
@@ -349,10 +492,10 @@ Tables will be returned in lexicographical order.
 
 `Promise`&lt;`string`[]&gt;
 
-#### tableNames(namespace, options)
+#### tableNames(namespacePath, options)
 
 ```ts
-abstract tableNames(namespace?, options?): Promise<string[]>
+abstract tableNames(namespacePath?, options?): Promise<string[]>
 ```
 
 List all the table names in this database.
@@ -361,8 +504,8 @@ Tables will be returned in lexicographical order.
 
 ##### Parameters
 
-* **namespace?**: `string`[]
-    The namespace to list tables from (defaults to root namespace)
+* **namespacePath?**: `string`[]
+    The namespace path to list tables from (defaults to root namespace)
 
 * **options?**: `Partial`&lt;[`TableNamesOptions`](../interfaces/TableNamesOptions.md)&gt;
     options to control the

docs/src/js/classes/Query.md

@@ -343,6 +343,30 @@ This is useful for pagination.
 
 ***
 
+### orderBy()
+
+```ts
+orderBy(ordering): this
+```
+
+Sort the results by the specified column(s).
+
+#### Parameters
+
+* **ordering**: [`ColumnOrdering`](../interfaces/ColumnOrdering.md) \| [`ColumnOrdering`](../interfaces/ColumnOrdering.md)[]
+
+#### Returns
+
+`this`
+
+This query builder.
+
+#### Inherited from
+
+`StandardQueryBase.orderBy`
+
+***
+
 ### outputSchema()
 
 ```ts

docs/src/js/classes/Scannable.md

@@ -0,0 +1,173 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / Scannable
+
+# Class: Scannable
+
+A data source that can be scanned as a stream of Arrow `RecordBatch`es.
+
+`Scannable` wraps the schema + optional row count + rescannable flag and
+a callback that yields batches one at a time. It is passed to consumers
+(e.g. `Table.add`, `createTable`, `mergeInsert` — follow-up work) that
+need to pull data without materializing the full dataset in JS memory.
+
+Batches cross the JS↔Rust boundary as Arrow IPC Stream messages; a fresh
+writer serializes each batch, and the Rust side decodes it with
+`arrow_ipc::reader::StreamReader`. One batch is in flight at a time.
+
+## Properties
+
+### numRows
+
+```ts
+readonly numRows: null | number;
+```
+
+***
+
+### rescannable
+
+```ts
+readonly rescannable: boolean;
+```
+
+***
+
+### schema
+
+```ts
+readonly schema: Schema<any>;
+```
+
+## Methods
+
+### fromFactory()
+
+```ts
+static fromFactory(
+   schema,
+   factory,
+   opts): Promise<Scannable>
+```
+
+Build a Scannable from an explicit schema and a factory that returns a
+fresh batch iterator on each call.
+
+The factory is invoked once per scan. Each iterator yields
+`RecordBatch`es matching the declared schema. Use this when you need
+direct control over the pull loop — for example, to wrap a streaming
+source whose batches are produced lazily.
+
+#### Parameters
+
+* **schema**: `Schema`&lt;`any`&gt;
+    The Arrow schema of the produced batches.
+
+* **factory**
+    Called at the start of each scan to produce a batch
+    iterator. Must be idempotent when `rescannable` is true.
+
+* **opts**: [`ScannableOptions`](../interfaces/ScannableOptions.md) = `{}`
+    Optional hints. `rescannable` defaults to `true`; set to
+    `false` if calling `factory()` twice would not reproduce the same data.
+
+#### Returns
+
+`Promise`&lt;[`Scannable`](Scannable.md)&gt;
+
+***
+
+### fromIterable()
+
+```ts
+static fromIterable(
+   schema,
+   iter,
+   opts): Promise<Scannable>
+```
+
+Build a Scannable from an iterable of `RecordBatch`es. `rescannable`
+defaults to `false`. Pass an explicit schema so the consumer can
+validate before any batch is pulled.
+
+`opts.rescannable: true` is honest for replayable iterables (Arrays,
+Sets, or custom iterables whose `[Symbol.iterator]()` returns a fresh
+iterator each call). It is rejected for one-shot iterables (generators,
+async generators, or already-an-iterator inputs) because their
+`[Symbol.iterator]()` returns the same exhausted object on the second
+scan. For replayable sources outside this shape, use
+`fromFactory(schema, () => createIter(), { rescannable: true })`.
+
+Note: when `opts.rescannable` is `true`, the constructor calls
+`[Symbol.iterator]()` once on the input to perform the structural check.
+
+#### Parameters
+
+* **schema**: `Schema`&lt;`any`&gt;
+
+* **iter**: `Iterable`&lt;`RecordBatch`&lt;`any`&gt;&gt; \| `AsyncIterable`&lt;`RecordBatch`&lt;`any`&gt;&gt;
+
+* **opts**: [`ScannableOptions`](../interfaces/ScannableOptions.md) = `{}`
+
+#### Returns
+
+`Promise`&lt;[`Scannable`](Scannable.md)&gt;
+
+***
+
+### fromRecordBatchReader()
+
+```ts
+static fromRecordBatchReader(reader, opts): Promise<Scannable>
+```
+
+Build a Scannable from an Arrow `RecordBatchReader`. A reader can only
+be consumed once; `rescannable` defaults to `false`.
+
+The reader must already be opened (via `.open()`) so its `.schema` is
+populated. `RecordBatchReader.from(...)` returns an unopened reader.
+
+`opts.rescannable: true` is rejected because `RecordBatchReader` is a
+self-iterator (its `[Symbol.iterator]()` returns itself), and this
+constructor does not call `reader.reset()` between scans, so a second
+scan would always see an exhausted reader. For genuinely replayable
+sources, use
+`fromFactory(schema, () => openReader(), { rescannable: true })`,
+which mints a fresh reader on each scan.
+
+#### Parameters
+
+* **reader**: `RecordBatchReader`&lt;`any`&gt;
+
+* **opts**: [`ScannableOptions`](../interfaces/ScannableOptions.md) = `{}`
+
+#### Returns
+
+`Promise`&lt;[`Scannable`](Scannable.md)&gt;
+
+***
+
+### fromTable()
+
+```ts
+static fromTable(table, opts): Promise<Scannable>
+```
+
+Build a Scannable from an in-memory Arrow `Table`. Always rescannable;
+the table's batches are replayed on each scan.
+
+The table's row count is authoritative: `opts.numRows` must either be
+omitted or equal to `table.numRows`. `opts.rescannable` of `false` is
+rejected because in-memory Tables are always rescannable.
+
+#### Parameters
+
+* **table**: `Table`&lt;`any`&gt;
+
+* **opts**: [`ScannableOptions`](../interfaces/ScannableOptions.md) = `{}`
+
+#### Returns
+
+`Promise`&lt;[`Scannable`](Scannable.md)&gt;

docs/src/js/classes/Table.md

@@ -71,11 +71,12 @@ Add new columns with defined values.
 
 #### Parameters
 
-* **newColumnTransforms**: [`AddColumnsSql`](../interfaces/AddColumnsSql.md)[]
-    pairs of column names and
-    the SQL expression to use to calculate the value of the new column. These
-    expressions will be evaluated for each row in the table, and can
-    reference existing columns in the table.
+* **newColumnTransforms**: `Field`<`any`> \| `Field`<`any`>[] \| `Schema`<`any`> \| [`AddColumnsSql`](../interfaces/AddColumnsSql.md)[]
+    Either:
+    - An array of objects with column names and SQL expressions to calculate values
+    - A single Arrow Field defining one column with its data type (column will be initialized with null values)
+    - An array of Arrow Fields defining columns with their data types (columns will be initialized with null values)
+    - An Arrow Schema defining columns with their data types (columns will be initialized with null values)
 
 #### Returns
 
@@ -484,19 +485,7 @@ Modeled after ``VACUUM`` in PostgreSQL.
  - Prune: Removes old versions of the dataset
  - Index: Optimizes the indices, adding new data to existing indices
 
- Experimental API
- ----------------
-
- The optimization process is undergoing active development and may change.
- Our goal with these changes is to improve the performance of optimization and
- reduce the complexity.
-
- That being said, it is essential today to run optimize if you want the best
- performance.  It should be stable and safe to use in production, but it our
- hope that the API may be simplified (or not even need to be called) in the
- future.
-
- The frequency an application shoudl call optimize is based on the frequency of
+ The frequency an application should call optimize is based on the frequency of
  data modifications.  If data is frequently added, deleted, or updated then
  optimize should be run frequently.  A good rule of thumb is to run optimize if
  you have added or modified 100,000 or more records or run more than 20 data
@@ -512,6 +501,34 @@ Modeled after ``VACUUM`` in PostgreSQL.
 
 ***
 
+### prewarmData()
+
+```ts
+abstract prewarmData(columns?): Promise<void>
+```
+
+Prewarm one or more columns of data in the table.
+
+#### Parameters
+
+* **columns?**: `string`[]
+    The columns to prewarm. If undefined, all columns are prewarmed.
+    This will load the column data into the page cache so that future queries that
+    read those columns avoid the initial cold-start latency.  This call initiates
+    prewarming and returns once the request is accepted; the warming itself may
+    continue in the background.  Calling it on already-prewarmed columns is a
+    no-op on the server.
+    Prewarming is generally useful for columns used in filters or projections.
+    Large columns (e.g. high-dimensional vectors or binary data) may not be
+    practical to prewarm.
+    This feature is currently only supported on remote tables.
+
+#### Returns
+
+`Promise`&lt;`void`&gt;
+
+***
+
 ### prewarmIndex()
 
 ```ts
@@ -673,6 +690,74 @@ of the given query
 
 ***
 
+### setLsmWriteSpec()
+
+```ts
+abstract setLsmWriteSpec(spec): Promise<void>
+```
+
+Install an [LsmWriteSpec](../interfaces/LsmWriteSpec.md) on this table, selecting Lance's MemWAL
+LSM-style write path for future `mergeInsert` calls.
+
+`LsmWriteSpec` chooses one of three sharding strategies via `specType`:
+
+- `"bucket"` — hash-bucket writes by the single-column unenforced primary
+  key (`column` and `numBuckets` required).
+- `"identity"` — shard by the raw value of a scalar `column`.
+- `"unsharded"` — route every write to a single shard.
+
+All variants require the table to have an unenforced primary key
+([Table#setUnenforcedPrimaryKey](Table.md#setunenforcedprimarykey)); bucket sharding additionally
+requires it to be the single column being bucketed.
+
+#### Parameters
+
+* **spec**: [`LsmWriteSpec`](../interfaces/LsmWriteSpec.md)
+    The sharding spec to install.
+
+#### Returns
+
+`Promise`&lt;`void`&gt;
+
+#### Example
+
+```ts
+await table.setUnenforcedPrimaryKey("id");
+await table.setLsmWriteSpec({
+  specType: "bucket",
+  column: "id",
+  numBuckets: 16,
+  maintainedIndexes: ["id_idx"],
+});
+```
+
+***
+
+### setUnenforcedPrimaryKey()
+
+```ts
+abstract setUnenforcedPrimaryKey(columns): Promise<void>
+```
+
+Set the unenforced primary key for this table to a single column.
+
+"Unenforced" means LanceDB does not check uniqueness on writes; the
+column is recorded in the schema as the primary key for use by features
+such as `merge_insert`. Only single-column primary keys are supported,
+and the key cannot be changed once set.
+
+#### Parameters
+
+* **columns**: `string` \| `string`[]
+    The primary key column. A one-element
+    array is also accepted; passing more than one column is rejected.
+
+#### Returns
+
+`Promise`&lt;`void`&gt;
+
+***
+
 ### stats()
 
 ```ts
@@ -776,6 +861,23 @@ Return the table as an arrow table
 
 ***
 
+### unsetLsmWriteSpec()
+
+```ts
+abstract unsetLsmWriteSpec(): Promise<void>
+```
+
+Remove the [LsmWriteSpec](../interfaces/LsmWriteSpec.md) from this table, reverting to the standard
+`mergeInsert` write path.
+
+Errors if no spec is currently set.
+
+#### Returns
+
+`Promise`&lt;`void`&gt;
+
+***
+
 ### update()
 
 #### update(opts)

docs/src/js/classes/VectorQuery.md

@@ -498,6 +498,30 @@ This is useful for pagination.
 
 ***
 
+### orderBy()
+
+```ts
+orderBy(ordering): this
+```
+
+Sort the results by the specified column(s).
+
+#### Parameters
+
+* **ordering**: [`ColumnOrdering`](../interfaces/ColumnOrdering.md) \| [`ColumnOrdering`](../interfaces/ColumnOrdering.md)[]
+
+#### Returns
+
+`this`
+
+This query builder.
+
+#### Inherited from
+
+`StandardQueryBase.orderBy`
+
+***
+
 ### outputSchema()
 
 ```ts

docs/src/js/functions/connectNamespace.md

@@ -0,0 +1,131 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / connectNamespace
+
+# Function: connectNamespace()
+
+## connectNamespace(implName, config, options)
+
+```ts
+function connectNamespace(
+   implName,
+   config,
+   options?): Promise<Connection>
+```
+
+Connect to a LanceDB database through a namespace.
+
+Unlike [connect](connect.md), which routes by URI scheme (local path vs.
+`db://` cloud), `connectNamespace` always returns a namespace-backed
+connection. The `implName` selects the namespace implementation:
+
+- `"dir"` — directory namespace, configured with [DirNamespaceConfig](../interfaces/DirNamespaceConfig.md).
+- `"rest"` — remote REST catalog, configured with [RestNamespaceConfig](../interfaces/RestNamespaceConfig.md).
+- Any other string — full module path for a custom implementation,
+  configured with a free-form string-keyed `properties` map.
+
+### Parameters
+
+* **implName**: `"dir"`
+
+* **config**: [`DirNamespaceConfig`](../interfaces/DirNamespaceConfig.md)
+
+* **options?**: `Partial`&lt;[`ConnectNamespaceOptions`](../interfaces/ConnectNamespaceOptions.md)&gt;
+
+### Returns
+
+`Promise`&lt;[`Connection`](../classes/Connection.md)&gt;
+
+### Examples
+
+```ts
+const db = await connectNamespace("dir", { root: "/path/to/db" });
+await db.createTable("users", [{ id: 1 }]);
+```
+
+```ts
+const db = await connectNamespace("rest", {
+  uri: "https://catalog.example.com",
+  headers: { "x-api-key": process.env.CATALOG_KEY ?? "" },
+});
+```
+
+```ts
+const db = await connectNamespace("my.custom.Namespace", {
+  endpoint: "...",
+});
+```
+
+## connectNamespace(implName, config, options)
+
+```ts
+function connectNamespace(
+   implName,
+   config,
+   options?): Promise<Connection>
+```
+
+Connect through the built-in REST namespace.
+
+Configured with [RestNamespaceConfig](../interfaces/RestNamespaceConfig.md). See the function-level
+documentation above for the full surface, examples, and how this
+relates to [connect](connect.md).
+
+### Parameters
+
+* **implName**: `"rest"`
+
+* **config**: [`RestNamespaceConfig`](../interfaces/RestNamespaceConfig.md)
+
+* **options?**: `Partial`&lt;[`ConnectNamespaceOptions`](../interfaces/ConnectNamespaceOptions.md)&gt;
+
+### Returns
+
+`Promise`&lt;[`Connection`](../classes/Connection.md)&gt;
+
+### Example
+
+```ts
+const db = await connectNamespace("rest", {
+  uri: "https://catalog.example.com",
+  headers: { "x-api-key": process.env.CATALOG_KEY ?? "" },
+});
+```
+
+## connectNamespace(implName, properties, options)
+
+```ts
+function connectNamespace(
+   implName,
+   properties,
+   options?): Promise<Connection>
+```
+
+Connect through a custom namespace implementation by full module path,
+configured with a free-form string-keyed `properties` map. Use the
+typed overloads above for the built-in `"dir"` and `"rest"` impls.
+
+See the function-level documentation above for examples and how this
+relates to [connect](connect.md).
+
+### Parameters
+
+* **implName**: `string`
+
+* **properties**: `Record`&lt;`string`, `string`&gt;
+
+* **options?**: `Partial`&lt;[`ConnectNamespaceOptions`](../interfaces/ConnectNamespaceOptions.md)&gt;
+
+### Returns
+
+`Promise`&lt;[`Connection`](../classes/Connection.md)&gt;
+
+### Example
+
+```ts
+const db = await connectNamespace("my.custom.Namespace", {
+  endpoint: "...",
+});
+```

docs/src/js/globals.md

@@ -32,6 +32,7 @@
 - [PhraseQuery](classes/PhraseQuery.md)
 - [Query](classes/Query.md)
 - [QueryBase](classes/QueryBase.md)
+- [Scannable](classes/Scannable.md)
 - [Session](classes/Session.md)
 - [StaticHeaderProvider](classes/StaticHeaderProvider.md)
 - [Table](classes/Table.md)
@@ -50,11 +51,19 @@
 - [AlterColumnsResult](interfaces/AlterColumnsResult.md)
 - [ClientConfig](interfaces/ClientConfig.md)
 - [ColumnAlteration](interfaces/ColumnAlteration.md)
+- [ColumnOrdering](interfaces/ColumnOrdering.md)
 - [CompactionStats](interfaces/CompactionStats.md)
+- [ConnectNamespaceOptions](interfaces/ConnectNamespaceOptions.md)
 - [ConnectionOptions](interfaces/ConnectionOptions.md)
+- [CreateNamespaceOptions](interfaces/CreateNamespaceOptions.md)
+- [CreateNamespaceResponse](interfaces/CreateNamespaceResponse.md)
 - [CreateTableOptions](interfaces/CreateTableOptions.md)
 - [DeleteResult](interfaces/DeleteResult.md)
+- [DescribeNamespaceResponse](interfaces/DescribeNamespaceResponse.md)
+- [DirNamespaceConfig](interfaces/DirNamespaceConfig.md)
 - [DropColumnsResult](interfaces/DropColumnsResult.md)
+- [DropNamespaceOptions](interfaces/DropNamespaceOptions.md)
+- [DropNamespaceResponse](interfaces/DropNamespaceResponse.md)
 - [ExecutableQuery](interfaces/ExecutableQuery.md)
 - [FragmentStatistics](interfaces/FragmentStatistics.md)
 - [FragmentSummaryStats](interfaces/FragmentSummaryStats.md)
@@ -69,13 +78,19 @@
 - [IvfFlatOptions](interfaces/IvfFlatOptions.md)
 - [IvfPqOptions](interfaces/IvfPqOptions.md)
 - [IvfRqOptions](interfaces/IvfRqOptions.md)
+- [ListNamespacesOptions](interfaces/ListNamespacesOptions.md)
+- [ListNamespacesResponse](interfaces/ListNamespacesResponse.md)
+- [LsmWriteSpec](interfaces/LsmWriteSpec.md)
 - [MergeResult](interfaces/MergeResult.md)
 - [OpenTableOptions](interfaces/OpenTableOptions.md)
 - [OptimizeOptions](interfaces/OptimizeOptions.md)
 - [OptimizeStats](interfaces/OptimizeStats.md)
 - [QueryExecutionOptions](interfaces/QueryExecutionOptions.md)
 - [RemovalStats](interfaces/RemovalStats.md)
+- [RenameTableOptions](interfaces/RenameTableOptions.md)
+- [RestNamespaceConfig](interfaces/RestNamespaceConfig.md)
 - [RetryConfig](interfaces/RetryConfig.md)
+- [ScannableOptions](interfaces/ScannableOptions.md)
 - [ShuffleOptions](interfaces/ShuffleOptions.md)
 - [SplitCalculatedOptions](interfaces/SplitCalculatedOptions.md)
 - [SplitHashOptions](interfaces/SplitHashOptions.md)
@@ -90,6 +105,7 @@
 - [UpdateResult](interfaces/UpdateResult.md)
 - [Version](interfaces/Version.md)
 - [WriteExecutionOptions](interfaces/WriteExecutionOptions.md)
+- [WriteProgress](interfaces/WriteProgress.md)
 
 ## Type Aliases
 
@@ -107,6 +123,7 @@
 
 - [RecordBatchIterator](functions/RecordBatchIterator.md)
 - [connect](functions/connect.md)
+- [connectNamespace](functions/connectNamespace.md)
 - [makeArrowTable](functions/makeArrowTable.md)
 - [packBits](functions/packBits.md)
 - [permutationBuilder](functions/permutationBuilder.md)

docs/src/js/interfaces/AddDataOptions.md

@@ -19,3 +19,39 @@ mode: "append" | "overwrite";
 If "append" (the default) then the new data will be added to the table
 
 If "overwrite" then the new data will replace the existing data in the table.
+
+***
+
+### progress()
+
+```ts
+progress: (progress) => void;
+```
+
+Optional callback invoked periodically with write progress.
+
+The callback is fired once per batch written and once more with
+`done: true` when the write completes. Calls are dispatched
+asynchronously to the JS event loop and never block the write — a slow
+callback will queue events rather than back-pressure the writer.
+
+Errors thrown from the callback are logged with `console.warn` and
+swallowed — they do not abort the write.
+
+#### Parameters
+
+* **progress**: [`WriteProgress`](WriteProgress.md)
+
+#### Returns
+
+`void`
+
+#### Example
+
+```ts
+await table.add(data, {
+  progress: (p) => {
+    console.log(`${p.outputRows}/${p.totalRows ?? "?"} rows`);
+  },
+});
+```

docs/src/js/interfaces/ClientConfig.md

@@ -53,3 +53,18 @@ optional tlsConfig: TlsConfig;
 ```ts
 optional userAgent: string;
 ```
+
+***
+
+### userId?
+
+```ts
+optional userId: string;
+```
+
+User identifier for tracking purposes.
+
+This is sent as the `x-lancedb-user-id` header in requests to LanceDB Cloud/Enterprise.
+It can be set directly, or via the `LANCEDB_USER_ID` environment variable.
+Alternatively, set `LANCEDB_USER_ID_ENV_KEY` to specify another environment
+variable that contains the user ID value.

docs/src/js/interfaces/ColumnOrdering.md

@@ -0,0 +1,31 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / ColumnOrdering
+
+# Interface: ColumnOrdering
+
+## Properties
+
+### ascending?
+
+```ts
+optional ascending: boolean;
+```
+
+***
+
+### columnName
+
+```ts
+columnName: string;
+```
+
+***
+
+### nullsFirst?
+
+```ts
+optional nullsFirst: boolean;
+```

docs/src/js/interfaces/ConnectNamespaceOptions.md

@@ -0,0 +1,54 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / ConnectNamespaceOptions
+
+# Interface: ConnectNamespaceOptions
+
+## Properties
+
+### namespaceClientProperties?
+
+```ts
+optional namespaceClientProperties: Record<string, string>;
+```
+
+Extra properties for the backing namespace client.
+
+***
+
+### readConsistencyInterval?
+
+```ts
+optional readConsistencyInterval: number;
+```
+
+The interval, in seconds, at which to check for updates to the table
+from other processes. If None, then consistency is not checked. For
+performance reasons, this is the default. For strong consistency, set
+this to zero seconds. Then every read will check for updates from other
+processes. As a compromise, you can set this to a non-zero value for
+eventual consistency.
+
+***
+
+### session?
+
+```ts
+optional session: Session;
+```
+
+The session to use for this connection. Holds shared caches and other
+session-specific state.
+
+***
+
+### storageOptions?
+
+```ts
+optional storageOptions: Record<string, string>;
+```
+
+Configuration for object storage. The available options are described
+at https://docs.lancedb.com/storage/

docs/src/js/interfaces/ConnectionOptions.md

@@ -41,6 +41,29 @@ for testing purposes.
 
 ***
 
+### manifestEnabled?
+
+```ts
+optional manifestEnabled: boolean;
+```
+
+(For LanceDB OSS only): use directory namespace manifests as the source
+of truth for table metadata. Existing directory-listed root tables are
+migrated into the manifest on access.
+
+***
+
+### namespaceClientProperties?
+
+```ts
+optional namespaceClientProperties: Record<string, string>;
+```
+
+(For LanceDB OSS only): extra properties for the backing namespace
+client used by manifest-enabled native connections.
+
+***
+
 ### readConsistencyInterval?
 
 ```ts
@@ -89,4 +112,4 @@ optional storageOptions: Record<string, string>;
 
 (For LanceDB OSS only): configuration for object storage.
 
-The available options are described at https://lancedb.com/docs/storage/
+The available options are described at https://docs.lancedb.com/storage/

docs/src/js/interfaces/CreateNamespaceOptions.md

@@ -0,0 +1,27 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / CreateNamespaceOptions
+
+# Interface: CreateNamespaceOptions
+
+## Properties
+
+### mode?
+
+```ts
+optional mode: "overwrite" | "create" | "exist_ok";
+```
+
+Creation mode.
+
+***
+
+### properties?
+
+```ts
+optional properties: Record<string, string>;
+```
+
+Properties to set on the new namespace.

docs/src/js/interfaces/CreateNamespaceResponse.md

@@ -0,0 +1,23 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / CreateNamespaceResponse
+
+# Interface: CreateNamespaceResponse
+
+## Properties
+
+### properties?
+
+```ts
+optional properties: Record<string, string>;
+```
+
+***
+
+### transactionId?
+
+```ts
+optional transactionId: string;
+```

docs/src/js/interfaces/CreateTableOptions.md

@@ -97,4 +97,4 @@ Configuration for object storage.
 Options already set on the connection will be inherited by the table,
 but can be overridden here.
 
-The available options are described at https://lancedb.com/docs/storage/
+The available options are described at https://docs.lancedb.com/storage/

docs/src/js/interfaces/DescribeNamespaceResponse.md

@@ -0,0 +1,15 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / DescribeNamespaceResponse
+
+# Interface: DescribeNamespaceResponse
+
+## Properties
+
+### properties?
+
+```ts
+optional properties: Record<string, string>;
+```

docs/src/js/interfaces/DirNamespaceConfig.md

@@ -0,0 +1,47 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / DirNamespaceConfig
+
+# Interface: DirNamespaceConfig
+
+Configuration for the built-in directory namespace (`"dir"`).
+
+The directory namespace stores tables under a single root path (local
+filesystem or object storage URI). See
+[https://docs.lancedb.com/namespaces](https://docs.lancedb.com/namespaces) for the documented surface;
+less-common knobs live under [DirNamespaceConfig.extraProperties](DirNamespaceConfig.md#extraproperties).
+
+## Properties
+
+### extraProperties?
+
+```ts
+optional extraProperties: Record<string, string>;
+```
+
+Additional raw properties passed verbatim to the namespace
+implementation (e.g. `storage.*`, `credential_vendor.*`). Typed
+fields above take precedence on key collision.
+
+***
+
+### manifestEnabled?
+
+```ts
+optional manifestEnabled: boolean;
+```
+
+Whether to maintain a namespace manifest at the root. Required for
+child namespaces. Defaults to true on the impl side.
+
+***
+
+### root
+
+```ts
+root: string;
+```
+
+Root path or URI containing the LanceDB tables.

docs/src/js/interfaces/DropNamespaceOptions.md

@@ -0,0 +1,27 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / DropNamespaceOptions
+
+# Interface: DropNamespaceOptions
+
+## Properties
+
+### behavior?
+
+```ts
+optional behavior: "restrict" | "cascade";
+```
+
+Refuse to drop if non-empty (restrict) or drop recursively (cascade).
+
+***
+
+### mode?
+
+```ts
+optional mode: "fail" | "skip";
+```
+
+Whether to skip if the namespace doesn't exist, or fail.

docs/src/js/interfaces/DropNamespaceResponse.md

@@ -0,0 +1,23 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / DropNamespaceResponse
+
+# Interface: DropNamespaceResponse
+
+## Properties
+
+### properties?
+
+```ts
+optional properties: Record<string, string>;
+```
+
+***
+
+### transactionId?
+
+```ts
+optional transactionId: string[];
+```

docs/src/js/interfaces/ListNamespacesOptions.md

@@ -0,0 +1,27 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / ListNamespacesOptions
+
+# Interface: ListNamespacesOptions
+
+## Properties
+
+### limit?
+
+```ts
+optional limit: number;
+```
+
+An optional limit to the number of results to return.
+
+***
+
+### pageToken?
+
+```ts
+optional pageToken: string;
+```
+
+Token from a previous response for pagination.

docs/src/js/interfaces/ListNamespacesResponse.md

@@ -0,0 +1,23 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / ListNamespacesResponse
+
+# Interface: ListNamespacesResponse
+
+## Properties
+
+### namespaces
+
+```ts
+namespaces: string[];
+```
+
+***
+
+### pageToken?
+
+```ts
+optional pageToken: string;
+```

docs/src/js/interfaces/LsmWriteSpec.md

@@ -0,0 +1,64 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / LsmWriteSpec
+
+# Interface: LsmWriteSpec
+
+Specification selecting Lance's MemWAL LSM-style write path for
+`mergeInsert`.
+
+`specType` is `"bucket"`, `"identity"`, or `"unsharded"`. For `"bucket"`,
+`column` and `numBuckets` are required; for `"identity"`, `column` is
+required.
+
+## Properties
+
+### column?
+
+```ts
+optional column: string;
+```
+
+Bucket and identity variants: the sharding column.
+
+***
+
+### maintainedIndexes?
+
+```ts
+optional maintainedIndexes: string[];
+```
+
+Names of indexes the MemWAL should keep up to date during writes.
+
+***
+
+### numBuckets?
+
+```ts
+optional numBuckets: number;
+```
+
+Bucket variant: the number of buckets, in `[1, 1024]`.
+
+***
+
+### specType
+
+```ts
+specType: "bucket" | "identity" | "unsharded";
+```
+
+One of `"bucket"`, `"identity"`, or `"unsharded"`.
+
+***
+
+### writerConfigDefaults?
+
+```ts
+optional writerConfigDefaults: Record<string, string>;
+```
+
+Default `ShardWriter` configuration recorded in the MemWAL index.

docs/src/js/interfaces/OpenTableOptions.md

@@ -42,4 +42,4 @@ Configuration for object storage.
 Options already set on the connection will be inherited by the table,
 but can be overridden here.
 
-The available options are described at https://lancedb.com/docs/storage/
+The available options are described at https://docs.lancedb.com/storage/

docs/src/js/interfaces/OptimizeOptions.md

@@ -37,3 +37,12 @@ tbl.optimize({cleanupOlderThan: new Date()});
 ```ts
 deleteUnverified: boolean;
 ```
+
+Because they may be part of an in-progress transaction, files newer than
+7 days old are not deleted by default. If you are sure that there are no
+in-progress transactions, then you can set this to true to delete all
+files older than `cleanupOlderThan`.
+
+**WARNING**: This should only be set to true if you can guarantee that
+no other process is currently working on this dataset. Otherwise the
+dataset could be put into a corrupted state.

docs/src/js/interfaces/RenameTableOptions.md

@@ -0,0 +1,29 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / RenameTableOptions
+
+# Interface: RenameTableOptions
+
+## Properties
+
+### namespacePath?
+
+```ts
+optional namespacePath: string[];
+```
+
+The namespace path of the table being renamed. Defaults to the root
+namespace (`[]`) when omitted.
+
+***
+
+### newNamespacePath?
+
+```ts
+optional newNamespacePath: string[];
+```
+
+The namespace path to move the table to as part of the rename. When
+omitted the table stays in `namespacePath`.

docs/src/js/interfaces/RestNamespaceConfig.md

@@ -0,0 +1,47 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / RestNamespaceConfig
+
+# Interface: RestNamespaceConfig
+
+Configuration for the built-in REST namespace (`"rest"`).
+
+The REST namespace talks to a remote catalog server over HTTP. See
+[https://docs.lancedb.com/namespaces](https://docs.lancedb.com/namespaces) for the documented surface;
+less-common knobs (TLS, metrics) live under
+[RestNamespaceConfig.extraProperties](RestNamespaceConfig.md#extraproperties).
+
+## Properties
+
+### extraProperties?
+
+```ts
+optional extraProperties: Record<string, string>;
+```
+
+Additional raw properties passed verbatim to the namespace
+implementation (e.g. `tls.*`, `ops_metrics_enabled`, `delimiter`).
+Typed fields above take precedence on key collision.
+
+***
+
+### headers?
+
+```ts
+optional headers: Record<string, string>;
+```
+
+HTTP headers forwarded with each request. Keys are passed through
+as-is (e.g. `"x-api-key"`, `"Authorization"`).
+
+***
+
+### uri
+
+```ts
+uri: string;
+```
+
+Catalog endpoint URL.

docs/src/js/interfaces/ScannableOptions.md

@@ -0,0 +1,29 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / ScannableOptions
+
+# Interface: ScannableOptions
+
+## Properties
+
+### numRows?
+
+```ts
+optional numRows: number;
+```
+
+Hint about the number of rows. Not validated against the stream.
+
+***
+
+### rescannable?
+
+```ts
+optional rescannable: boolean;
+```
+
+Whether the source can be scanned more than once. Defaults to `true` for
+`fromTable` / `fromFactory` and `false` for `fromIterable` /
+`fromRecordBatchReader`.

docs/src/js/interfaces/WriteProgress.md

@@ -0,0 +1,84 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / WriteProgress
+
+# Interface: WriteProgress
+
+Progress snapshot for a write operation, delivered to the `progress`
+callback passed to [Table.add](../classes/Table.md#add).
+
+## Properties
+
+### activeTasks
+
+```ts
+activeTasks: number;
+```
+
+Number of parallel write tasks currently in flight.
+
+***
+
+### done
+
+```ts
+done: boolean;
+```
+
+`true` for the final callback; `false` otherwise.
+
+***
+
+### elapsedSeconds
+
+```ts
+elapsedSeconds: number;
+```
+
+Wall-clock seconds since the write started.
+
+***
+
+### outputBytes
+
+```ts
+outputBytes: number;
+```
+
+Number of bytes written so far.
+
+***
+
+### outputRows
+
+```ts
+outputRows: number;
+```
+
+Number of rows written so far.
+
+***
+
+### totalRows?
+
+```ts
+optional totalRows: number;
+```
+
+Total rows expected, when the input source reports it.
+
+Always set on the final callback (the one with `done: true`), falling
+back to the actual number of rows written when the source could not
+report a row count up front.
+
+***
+
+### totalTasks
+
+```ts
+totalTasks: number;
+```
+
+Total number of parallel write tasks (the write parallelism).

docs/src/js/namespaces/embedding/classes/EmbeddingFunction.md

@@ -52,7 +52,7 @@ new EmbeddingFunction<T, M>(): EmbeddingFunction<T, M>
 ### computeQueryEmbeddings()
 
 ```ts
-computeQueryEmbeddings(data): Promise<number[] | Float32Array | Float64Array>
+computeQueryEmbeddings(data): Promise<number[] | Uint8Array | Float32Array | Float64Array>
 ```
 
 Compute the embeddings for a single query
@@ -63,7 +63,7 @@ Compute the embeddings for a single query
 
 #### Returns
 
-`Promise`&lt;`number`[] \| `Float32Array` \| `Float64Array`&gt;
+`Promise`&lt;`number`[] \| `Uint8Array` \| `Float32Array` \| `Float64Array`&gt;
 
 ***
 

docs/src/js/namespaces/embedding/classes/TextEmbeddingFunction.md

@@ -37,7 +37,7 @@ new TextEmbeddingFunction<M>(): TextEmbeddingFunction<M>
 ### computeQueryEmbeddings()
 
 ```ts
-computeQueryEmbeddings(data): Promise<number[] | Float32Array | Float64Array>
+computeQueryEmbeddings(data): Promise<number[] | Uint8Array | Float32Array | Float64Array>
 ```
 
 Compute the embeddings for a single query
@@ -48,7 +48,7 @@ Compute the embeddings for a single query
 
 #### Returns
 
-`Promise`&lt;`number`[] \| `Float32Array` \| `Float64Array`&gt;
+`Promise`&lt;`number`[] \| `Uint8Array` \| `Float32Array` \| `Float64Array`&gt;
 
 #### Overrides
 

docs/src/js/type-aliases/IntoVector.md

@@ -7,5 +7,10 @@
 # Type Alias: IntoVector
 
 ```ts
-type IntoVector: Float32Array | Float64Array | number[] | Promise<Float32Array | Float64Array | number[]>;
+type IntoVector:
+  | Float32Array
+  | Float64Array
+  | Uint8Array
+  | number[]
+  | Promise<Float32Array | Float64Array | Uint8Array | number[]>;
 ```

docs/src/python/python.md

@@ -36,6 +36,20 @@ is also an [asynchronous API client](#connections-asynchronous).
 
 ::: lancedb.table.Tags
 
+## Expressions
+
+Type-safe expression builder for filters and projections. Use these instead
+of raw SQL strings with [where][lancedb.query.LanceQueryBuilder.where] and
+[select][lancedb.query.LanceQueryBuilder.select].
+
+::: lancedb.expr.Expr
+
+::: lancedb.expr.col
+
+::: lancedb.expr.lit
+
+::: lancedb.expr.func
+
 ## Querying (Synchronous)
 
 ::: lancedb.query.Query
@@ -80,11 +94,11 @@ is also an [asynchronous API client](#connections-asynchronous).
 
 ## Full text search
 
-::: lancedb.fts.create_index
+Use [lancedb.table.Table.create_fts_index][] for the synchronous API or
+[lancedb.table.AsyncTable.create_index][] with [lancedb.index.FTS][] for the
+asynchronous API.
 
-::: lancedb.fts.populate_index
-
-::: lancedb.fts.search_index
+::: lancedb.index.FTS
 
 ## Utilities
 
@@ -152,6 +166,12 @@ lists the indices that LanceDb supports.
 
 ::: lancedb.index.IvfFlat
 
+::: lancedb.index.IvfSq
+
+::: lancedb.index.IvfRq
+
+::: lancedb.index.HnswFlat
+
 ::: lancedb.table.IndexStatistics
 
 ## Querying (Asynchronous)

java/README.md

@@ -1,4 +1,4 @@
-# LanceDB Java SDK
+# LanceDB Java Enterprise Client
 
 ## Configuration and Initialization
 

java/lancedb-core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
       <groupId>com.lancedb</groupId>
       <artifactId>lancedb-parent</artifactId>
-      <version>0.27.0-beta.3</version>
+      <version>0.29.1-beta.0</version>
       <relativePath>../pom.xml</relativePath>
     </parent>
 
@@ -56,21 +56,21 @@
         <dependency>
             <groupId>org.apache.logging.log4j</groupId>
             <artifactId>log4j-slf4j2-impl</artifactId>
-            <version>2.24.3</version>
+            <version>2.25.3</version>
             <scope>test</scope>
         </dependency>
 
         <dependency>
             <groupId>org.apache.logging.log4j</groupId>
             <artifactId>log4j-core</artifactId>
-            <version>2.24.3</version>
+            <version>2.25.3</version>
             <scope>test</scope>
         </dependency>
 
         <dependency>
             <groupId>org.apache.logging.log4j</groupId>
             <artifactId>log4j-api</artifactId>
-            <version>2.24.3</version>
+            <version>2.25.3</version>
             <scope>test</scope>
         </dependency>
     </dependencies>

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.27.0-beta.3</version>
+    <version>0.29.1-beta.0</version>
     <packaging>pom</packaging>
     <name>${project.artifactId}</name>
     <description>LanceDB Java SDK Parent POM</description>
@@ -28,7 +28,7 @@
     <properties>
         <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
         <arrow.version>15.0.0</arrow.version>
-        <lance-core.version>3.1.0-beta.2</lance-core.version>
+        <lance-core.version>7.0.0-beta.13</lance-core.version>
         <spotless.skip>false</spotless.skip>
         <spotless.version>2.30.0</spotless.version>
         <spotless.java.googlejavaformat.version>1.7</spotless.java.googlejavaformat.version>
@@ -111,7 +111,7 @@
             <plugin>
                 <groupId>org.apache.maven.plugins</groupId>
                 <artifactId>maven-source-plugin</artifactId>
-                <version>2.2.1</version>
+                <version>3.3.1</version>
                 <executions>
                     <execution>
                         <id>attach-sources</id>
@@ -124,7 +124,7 @@
             <plugin>
                 <groupId>org.apache.maven.plugins</groupId>
                 <artifactId>maven-javadoc-plugin</artifactId>
-                <version>2.9.1</version>
+                <version>3.11.2</version>
                 <executions>
                     <execution>
                         <id>attach-javadocs</id>
@@ -178,15 +178,15 @@
             <plugins>
                 <plugin>
                     <artifactId>maven-clean-plugin</artifactId>
-                    <version>3.1.0</version>
+                    <version>3.4.1</version>
                 </plugin>
                 <plugin>
                     <artifactId>maven-resources-plugin</artifactId>
-                    <version>3.0.2</version>
+                    <version>3.3.1</version>
                 </plugin>
                 <plugin>
                     <artifactId>maven-compiler-plugin</artifactId>
-                    <version>3.8.1</version>
+                    <version>3.14.0</version>
                     <configuration>
                         <compilerArgs>
                             <arg>-h</arg>
@@ -205,11 +205,11 @@
                 </plugin>
                 <plugin>
                     <artifactId>maven-jar-plugin</artifactId>
-                    <version>3.0.2</version>
+                    <version>3.4.2</version>
                 </plugin>
                 <plugin>
                     <artifactId>maven-install-plugin</artifactId>
-                    <version>2.5.2</version>
+                    <version>3.1.3</version>
                 </plugin>
                 <plugin>
                     <groupId>com.diffplug.spotless</groupId>
@@ -327,7 +327,7 @@
                     <plugin>
                         <groupId>org.apache.maven.plugins</groupId>
                         <artifactId>maven-gpg-plugin</artifactId>
-                        <version>1.5</version>
+                        <version>3.2.7</version>
                         <executions>
                             <execution>
                                 <id>sign-artifacts</id>

nodejs/AGENTS.md

@@ -3,11 +3,11 @@ The core Rust library is in the `../rust/lancedb` directory, the rust binding
 code is in the `src/` directory and the typescript bindings are in
 the `lancedb/` directory.
 
-Whenever you change the Rust code, you will need to recompile: `npm run build`.
+Whenever you change the Rust code, you will need to recompile: `pnpm build`.
 
 Common commands:
-* Build: `npm run build`
-* Lint: `npm run lint`
-* Fix lints: `npm run lint-fix`
-* Test: `npm test`
-* Run single test file: `npm test __test__/arrow.test.ts`
+* Build: `pnpm build`
+* Lint: `pnpm lint`
+* Fix lints: `pnpm lint-fix`
+* Test: `pnpm test`
+* Run single test file: `pnpm test __test__/arrow.test.ts`

nodejs/CONTRIBUTING.md

@@ -12,20 +12,22 @@ Typescript.
 * `src/`: Rust bindings source code
 * `lancedb/`: Typescript package source code
 * `__test__/`: Unit tests
-* `examples/`: An npm package with the examples shown in the documentation
+* `examples/`: A pnpm package with the examples shown in the documentation
 
 ## Development environment
 
 To set up your development environment, you will need to install the following:
 
-1. Node.js 14 or later
-2. Rust's package manager, Cargo. Use [rustup](https://rustup.rs/) to install.
-3. [protoc](https://grpc.io/docs/protoc-installation/) (Protocol Buffers compiler)
+1. Node.js 22 or later (required by pnpm 11)
+2. [pnpm](https://pnpm.io/installation) 11 or later (or run via `corepack enable`,
+   which uses the `packageManager` field in `package.json`)
+3. Rust's package manager, Cargo. Use [rustup](https://rustup.rs/) to install.
+4. [protoc](https://grpc.io/docs/protoc-installation/) (Protocol Buffers compiler)
 
 Initial setup:
 
 ```shell
-npm install
+pnpm install
 ```
 
 ### Commit Hooks
@@ -39,38 +41,38 @@ pre-commit install
 
 ## Development
 
-Most common development commands can be run using the npm scripts.
+Most common development commands can be run using the pnpm scripts.
 
 Build the package
 
 ```shell
-npm install
-npm run build
+pnpm install
+pnpm build
 ```
 
 Lint:
 
 ```shell
-npm run lint
+pnpm lint
 ```
 
 Format and fix lints:
 
 ```shell
-npm run lint-fix
+pnpm lint-fix
 ```
 
 Run tests:
 
 ```shell
-npm test
+pnpm test
 ```
 
 To run a single test:
 
 ```shell
 # Single file: table.test.ts
-npm test -- table.test.ts
+pnpm test -- table.test.ts
 # Single test: 'merge insert' in table.test.ts
-npm test -- table.test.ts --testNamePattern=merge\ insert
+pnpm test -- table.test.ts --testNamePattern=merge\ insert
 ```

nodejs/Cargo.toml

@@ -1,7 +1,8 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.27.0-beta.3"
+version = "0.29.1-beta.0"
+publish = false
 license.workspace = true
 description.workspace = true
 repository.workspace = true
@@ -15,22 +16,25 @@ crate-type = ["cdylib"]
 async-trait.workspace = true
 arrow-ipc.workspace = true
 arrow-array.workspace = true
+arrow-buffer = "58.0.0"
+half.workspace = true
 arrow-schema.workspace = true
 env_logger.workspace = true
 futures.workspace = true
 lancedb = { path = "../rust/lancedb", default-features = false }
+lance-namespace.workspace = true
 napi = { version = "3.8.3", default-features = false, features = [
     "napi9",
     "async"
 ] }
 napi-derive = "3.5.2"
 # Prevent dynamic linking of lzma, which comes from datafusion
-lzma-sys = { version = "*", features = ["static"] }
+lzma-sys = { version = "0.1", features = ["static"] }
 log.workspace = true
 
-# Workaround for build failure until we can fix it.
-aws-lc-sys = "=0.28.0"
-aws-lc-rs = "=1.13.0"
+# Pin to resolve build failures; update periodically for security patches.
+aws-lc-sys = "=0.40.0"
+aws-lc-rs = "=1.16.3"
 
 [build-dependencies]
 napi-build = "2.3.1"

nodejs/README.md

@@ -30,7 +30,7 @@ const results = await table.vectorSearch([0.1, 0.3]).limit(20).toArray();
 console.log(results);
 ```
 
-The [quickstart](https://lancedb.com/docs/quickstart/basic-usage/) contains more complete examples.
+The [quickstart](https://docs.lancedb.com/quickstart/) contains more complete examples.
 
 ## Development
 

nodejs/__test__/arrow.test.ts

@@ -63,6 +63,7 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       tableFromIPC,
       DataType,
       Dictionary,
+      Uint8: ArrowUint8,
       // biome-ignore lint/suspicious/noExplicitAny: <explanation>
     } = <any>arrow;
     type Schema = ApacheArrow["Schema"];
@@ -362,6 +363,38 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
         ).toEqual(new Float64().toString());
       });
 
+      it("will infer FixedSizeList<Float32> from Float32Array values", async function () {
+        const table = makeArrowTable([
+          { id: "a", vector: new Float32Array([0.1, 0.2, 0.3]) },
+          { id: "b", vector: new Float32Array([0.4, 0.5, 0.6]) },
+        ]);
+
+        expect(DataType.isFixedSizeList(table.getChild("vector")?.type)).toBe(
+          true,
+        );
+        const vectorType = table.getChild("vector")?.type;
+        expect(vectorType.listSize).toBe(3);
+        expect(vectorType.children[0].type.toString()).toEqual(
+          new Float32().toString(),
+        );
+      });
+
+      it("will infer FixedSizeList<Uint8> from Uint8Array values", async function () {
+        const table = makeArrowTable([
+          { id: "a", vector: new Uint8Array([1, 2, 3]) },
+          { id: "b", vector: new Uint8Array([4, 5, 6]) },
+        ]);
+
+        expect(DataType.isFixedSizeList(table.getChild("vector")?.type)).toBe(
+          true,
+        );
+        const vectorType = table.getChild("vector")?.type;
+        expect(vectorType.listSize).toBe(3);
+        expect(vectorType.children[0].type.toString()).toEqual(
+          new ArrowUint8().toString(),
+        );
+      });
+
       it("will use dictionary encoded strings if asked", async function () {
         const table = makeArrowTable([{ str: "hello" }]);
         expect(DataType.isUtf8(table.getChild("str")?.type)).toBe(true);

nodejs/__test__/connection.test.ts

@@ -4,7 +4,7 @@
 import { readdirSync } from "fs";
 import { Field, Float64, Schema } from "apache-arrow";
 import * as tmp from "tmp";
-import { Connection, Table, connect } from "../lancedb";
+import { Connection, Table, connect, connectNamespace } from "../lancedb";
 import { LocalTable } from "../lancedb/table";
 
 describe("when connecting", () => {
@@ -47,6 +47,14 @@ describe("given a connection", () => {
     await db.close();
     expect(db.isOpen()).toBe(false);
     await expect(db.tableNames()).rejects.toThrow("Connection is closed");
+    await expect(db.renameTable("a", "b")).rejects.toThrow(
+      "Connection is closed",
+    );
+  });
+
+  it("should report renameTable as unsupported on an OSS connection", async () => {
+    await db.createTable("a", [{ id: 1 }]);
+    await expect(db.renameTable("a", "b")).rejects.toThrow(/not supported/);
   });
   it("should be able to create a table from an object arg `createTable(options)`, or args `createTable(name, data, options)`", async () => {
     let tbl = await db.createTable("test", [{ id: 1 }, { id: 2 }]);
@@ -306,3 +314,186 @@ describe("clone table functionality", () => {
     ).rejects.toThrow("Deep clone is not yet implemented");
   });
 });
+
+describe("namespaces", () => {
+  let tmpDir: tmp.DirResult;
+  let db: Connection;
+
+  beforeEach(async () => {
+    tmpDir = tmp.dirSync({ unsafeCleanup: true });
+    // The local DirectoryNamespace backend only supports child namespaces
+    // when manifest mode is enabled (see lance-namespace-impls/src/dir.rs).
+    db = await connect(tmpDir.name, {
+      // biome-ignore lint/style/useNamingConvention: opaque backend property key, must match Rust
+      namespaceClientProperties: { manifest_enabled: "true" },
+    });
+  });
+  afterEach(() => tmpDir.removeCallback());
+
+  it("should create and describe a namespace", async () => {
+    await db.createNamespace(["myns"]);
+    const desc = await db.describeNamespace(["myns"]);
+    expect(desc).toBeDefined();
+  });
+
+  it("should list namespaces created at the root", async () => {
+    await db.createNamespace(["alpha"]);
+    await db.createNamespace(["beta"]);
+    const list = await db.listNamespaces();
+    expect(list.namespaces).toEqual(expect.arrayContaining(["alpha", "beta"]));
+  });
+
+  it("should list child namespaces under a parent", async () => {
+    await db.createNamespace(["parent"]);
+    await db.createNamespace(["parent", "child"]);
+    const list = await db.listNamespaces(["parent"]);
+    expect(list.namespaces).toContain("child");
+  });
+
+  it("should drop a namespace", async () => {
+    await db.createNamespace(["ephemeral"]);
+    await db.dropNamespace(["ephemeral"]);
+    const list = await db.listNamespaces();
+    expect(list.namespaces).not.toContain("ephemeral");
+  });
+
+  it("should raise an error on any namespace op after close", async () => {
+    await db.close();
+    await expect(db.describeNamespace(["foo"])).rejects.toThrow(
+      "Connection is closed",
+    );
+    await expect(db.listNamespaces()).rejects.toThrow("Connection is closed");
+    await expect(db.createNamespace(["foo"])).rejects.toThrow(
+      "Connection is closed",
+    );
+    await expect(db.dropNamespace(["foo"])).rejects.toThrow(
+      "Connection is closed",
+    );
+  });
+
+  it("should raise an understandable error when describing a non-existent namespace", async () => {
+    await expect(db.describeNamespace(["does-not-exist"])).rejects.toThrow(
+      /not found/i,
+    );
+  });
+
+  it("should raise an error when creating a namespace that already exists", async () => {
+    await db.createNamespace(["dup"]);
+    await expect(db.createNamespace(["dup"])).rejects.toThrow();
+  });
+
+  it("should reject an unrecognized createNamespace mode with a clear error", async () => {
+    await expect(
+      // biome-ignore lint/suspicious/noExplicitAny: deliberately bypass TS to test runtime validation
+      db.createNamespace(["x"], { mode: "frobnicate" as any }),
+    ).rejects.toThrow(/Invalid mode 'frobnicate'/);
+  });
+
+  it("should reject an unrecognized dropNamespace mode with a clear error", async () => {
+    await db.createNamespace(["x"]);
+    await expect(
+      // biome-ignore lint/suspicious/noExplicitAny: deliberately bypass TS to test runtime validation
+      db.dropNamespace(["x"], { mode: "frobnicate" as any }),
+    ).rejects.toThrow(/Invalid mode 'frobnicate'/);
+  });
+
+  it("should reject an unrecognized dropNamespace behavior with a clear error", async () => {
+    await db.createNamespace(["x"]);
+    await expect(
+      // biome-ignore lint/suspicious/noExplicitAny: deliberately bypass TS to test runtime validation
+      db.dropNamespace(["x"], { behavior: "frobnicate" as any }),
+    ).rejects.toThrow(/Invalid behavior 'frobnicate'/);
+  });
+});
+
+describe("connectNamespace", () => {
+  let tmpDir: tmp.DirResult;
+  beforeEach(() => {
+    tmpDir = tmp.dirSync({ unsafeCleanup: true });
+  });
+  afterEach(() => tmpDir.removeCallback());
+
+  it("connects via the dir implementation and supports table ops", async () => {
+    const db = await connectNamespace("dir", { root: tmpDir.name });
+    await db.createTable("users", [{ id: 1 }, { id: 2 }]);
+    await expect(db.tableNames()).resolves.toContain("users");
+  });
+
+  it("throws a clear error when implName is empty", async () => {
+    await expect(connectNamespace("", {})).rejects.toThrow(
+      "implName must be a non-empty string",
+    );
+  });
+
+  it("throws when the namespace implementation is unknown", async () => {
+    await expect(connectNamespace("not-a-real-impl", {})).rejects.toThrow();
+  });
+
+  it("passes storage options through to the namespace", async () => {
+    const db = await connectNamespace(
+      "dir",
+      { root: tmpDir.name },
+      { storageOptions: { newTableDataStorageVersion: "stable" } },
+    );
+    await db.createTable("plumbing", [{ id: 1 }]);
+    await expect(db.tableNames()).resolves.toContain("plumbing");
+  });
+
+  it("supports child namespaces when manifestEnabled is true on the dir config", async () => {
+    const writer = await connectNamespace("dir", {
+      root: tmpDir.name,
+      manifestEnabled: true,
+    });
+    await writer.createNamespace(["analytics"]);
+    await writer.createTable("orders", [{ id: 1 }, { id: 2 }], ["analytics"]);
+    await writer.close();
+
+    const reader = await connectNamespace("dir", {
+      root: tmpDir.name,
+      manifestEnabled: true,
+    });
+    await expect(reader.tableNames(["analytics"])).resolves.toContain("orders");
+    const orders = await reader.openTable("orders", ["analytics"]);
+    await expect(orders.countRows()).resolves.toBe(2);
+  });
+
+  it("merges extraProperties into the dir config and is overridden by typed fields", async () => {
+    // Two observable assertions:
+    // - Typed `root` overrides extraProperties.root: createTable would fail
+    //   under the bogus path if the override didn't happen.
+    // - extraProperties.manifest_enabled="false" is honored end-to-end. Child
+    //   namespaces require manifest mode (default true), so explicitly
+    //   disabling it via extraProperties must make createNamespace reject. If
+    //   extraProperties pass-through were silently broken, the default would
+    //   let createNamespace succeed.
+    const db = await connectNamespace("dir", {
+      root: tmpDir.name,
+      extraProperties: {
+        root: "/should/be/overridden",
+        // biome-ignore lint/style/useNamingConvention: backend property key
+        manifest_enabled: "false",
+      },
+    });
+    await db.createTable("base", [{ id: 1 }]);
+    await expect(db.tableNames()).resolves.toContain("base");
+    await expect(db.createNamespace(["analytics"])).rejects.toThrow();
+  });
+
+  it("flows unknown top-level keys through when implName is dynamic (no silent drop)", async () => {
+    // Routes via the third overload because `impl` is `string`, not the
+    // literal `"dir"`. The dispatcher still notices the runtime value is
+    // "dir", but unknown keys like `manifest_enabled` must not be silently
+    // dropped during the conversion.
+    //
+    // Asserting a *negative* outcome (manifest disabled -> createNamespace
+    // rejects) is required for observability, since the backend default for
+    // `manifest_enabled` is true.
+    const impl: string = "dir";
+    const db = await connectNamespace(impl, {
+      root: tmpDir.name,
+      // biome-ignore lint/style/useNamingConvention: backend property key
+      manifest_enabled: "false",
+    });
+    await expect(db.createNamespace(["mixed"])).rejects.toThrow();
+  });
+});

nodejs/__test__/query.test.ts

@@ -109,3 +109,209 @@ describe("Query outputSchema", () => {
     expect(schema.fields.length).toBe(3);
   });
 });
+
+describe("Query orderBy", () => {
+  let tmpDir: tmp.DirResult;
+  let table: Table;
+
+  beforeEach(async () => {
+    tmpDir = tmp.dirSync({ unsafeCleanup: true });
+    const db = await connect(tmpDir.name);
+
+    // Create table with numeric data for sorting
+    const schema = new Schema([
+      new Field("id", new Int64(), true),
+      new Field("score", new Float32(), true),
+      new Field("name", new Utf8(), true),
+    ]);
+
+    const data = makeArrowTable(
+      [
+        { id: 1n, score: 3.5, name: "charlie" },
+        { id: 2n, score: 1.2, name: "alice" },
+        { id: 3n, score: 2.8, name: "bob" },
+        { id: 4n, score: 0.5, name: "david" },
+        { id: 5n, score: 4.1, name: "eve" },
+      ],
+      { schema },
+    );
+    table = await db.createTable("test", data);
+  });
+
+  afterEach(() => {
+    tmpDir.removeCallback();
+  });
+
+  it("should sort by single column ascending", async () => {
+    const results = await table
+      .query()
+      .orderBy({ columnName: "score", ascending: true, nullsFirst: false })
+      .toArray();
+
+    expect(results.length).toBe(5);
+    // Verify ascending order
+    expect(results[0].score).toBeCloseTo(0.5, 0.001);
+    expect(results[1].score).toBeCloseTo(1.2, 0.001);
+    expect(results[2].score).toBeCloseTo(2.8, 0.001);
+    expect(results[3].score).toBeCloseTo(3.5, 0.001);
+    expect(results[4].score).toBeCloseTo(4.1, 0.001);
+  });
+
+  it("should sort by single column descending", async () => {
+    const results = await table
+      .query()
+      .orderBy({ columnName: "score", ascending: false, nullsFirst: false })
+      .toArray();
+
+    expect(results.length).toBe(5);
+    // Verify descending order
+    expect(results[0].score).toBeCloseTo(4.1, 0.001);
+    expect(results[1].score).toBeCloseTo(3.5, 0.001);
+    expect(results[2].score).toBeCloseTo(2.8, 0.001);
+    expect(results[3].score).toBeCloseTo(1.2, 0.001);
+    expect(results[4].score).toBeCloseTo(0.5, 0.001);
+  });
+
+  it("should use ascending as default direction", async () => {
+    const results = await table
+      .query()
+      .orderBy({ columnName: "score" })
+      .toArray();
+
+    expect(results.length).toBe(5);
+    // Verify ascending order (default)
+    expect(results[0].score).toBeCloseTo(0.5, 0.001);
+    expect(results[1].score).toBeCloseTo(1.2, 0.001);
+    expect(results[2].score).toBeCloseTo(2.8, 0.001);
+    expect(results[3].score).toBeCloseTo(3.5, 0.001);
+    expect(results[4].score).toBeCloseTo(4.1, 0.001);
+  });
+
+  it("should sort by string column", async () => {
+    const results = await table
+      .query()
+      .orderBy({ columnName: "name" })
+      .toArray();
+
+    expect(results.length).toBe(5);
+    // Verify alphabetical order
+    expect(results[0].name).toBe("alice");
+    expect(results[1].name).toBe("bob");
+    expect(results[2].name).toBe("charlie");
+    expect(results[3].name).toBe("david");
+    expect(results[4].name).toBe("eve");
+  });
+
+  it("should support method chaining with where", async () => {
+    const results = await table
+      .query()
+      .where("score > 2.0")
+      .orderBy({ columnName: "score" })
+      .toArray();
+    expect(results.length).toBe(3);
+    // Verify filtered and sorted
+    expect(results[0].score).toBeCloseTo(2.8, 0.001);
+    expect(results[1].score).toBeCloseTo(3.5, 0.001);
+    expect(results[2].score).toBeCloseTo(4.1, 0.001);
+  });
+
+  it("should support method chaining with limit", async () => {
+    const results = await table
+      .query()
+      .orderBy({ columnName: "score", ascending: false })
+      .limit(3)
+      .toArray();
+
+    expect(results.length).toBe(3);
+    // Verify top 3 in descending order
+    expect(results[0].score).toBeCloseTo(4.1, 0.001);
+    expect(results[1].score).toBeCloseTo(3.5, 0.001);
+    expect(results[2].score).toBeCloseTo(2.8, 0.001);
+  });
+
+  it("should support method chaining with offset", async () => {
+    const results = await table
+      .query()
+      .orderBy({ columnName: "score" })
+      .offset(2)
+      .limit(2)
+      .toArray();
+
+    expect(results.length).toBe(2);
+    // Verify results skip first 2 and take next 2
+    expect(results[0].score).toBeCloseTo(2.8, 0.001);
+    expect(results[1].score).toBeCloseTo(3.5, 0.001);
+  });
+
+  it("should support method chaining with select", async () => {
+    const results = await table
+      .query()
+      .orderBy({ columnName: "name" })
+      .select(["name", "score"])
+      .toArray();
+
+    expect(results.length).toBe(5);
+    // Verify only selected columns are present
+    expect(Object.keys(results[0])).toEqual(["name", "score"]);
+    expect(Object.keys(results[4])).toEqual(["name", "score"]);
+    // Verify sorted by name
+    expect(results[0].name).toBe("alice");
+    expect(results[4].name).toBe("eve");
+  });
+
+  it("should support complex method chaining", async () => {
+    const results = await table
+      .query()
+      .where("score > 1.0")
+      .orderBy({ columnName: "score", ascending: false })
+      .limit(3)
+      .select(["id", "score", "name"])
+      .toArray();
+
+    expect(results.length).toBe(3);
+    // Verify filtered, sorted, limited, and projected
+    expect(results[0].score).toBeCloseTo(4.1, 0.001);
+    expect(results[1].score).toBeCloseTo(3.5, 0.001);
+    expect(results[2].score).toBeCloseTo(2.8, 0.001);
+    expect(Object.keys(results[0])).toEqual(["id", "score", "name"]);
+  });
+
+  it("should support multi-column ordering and null placement", async () => {
+    const schema = new Schema([
+      new Field("group", new Int64(), true),
+      new Field("score", new Float32(), true),
+      new Field("name", new Utf8(), true),
+    ]);
+
+    const data = makeArrowTable(
+      [
+        { group: 1n, score: null, name: "z" },
+        { group: 1n, score: 1.0, name: "b" },
+        { group: 1n, score: 1.0, name: "a" },
+        { group: 2n, score: 0.5, name: "c" },
+      ],
+      { schema },
+    );
+    const nullTable = await (await connect(tmpDir.name)).createTable(
+      "test_multi_order",
+      data,
+      { mode: "overwrite" },
+    );
+
+    const results = await nullTable
+      .query()
+      .orderBy([
+        { columnName: "group", ascending: true, nullsFirst: false },
+        { columnName: "score", ascending: true, nullsFirst: true },
+        { columnName: "name", ascending: true, nullsFirst: false },
+      ])
+      .toArray();
+
+    expect(results.map((r) => [r.group, r.score, r.name])).toEqual([
+      [1n, null, "z"],
+      [1n, 1.0, "a"],
+      [1n, 1.0, "b"],
+      [2n, 0.5, "c"],
+    ]);
+  });
+});

nodejs/__test__/remote.test.ts

@@ -617,4 +617,68 @@ describe("remote connection", () => {
       );
     });
   });
+
+  describe("renameTable", () => {
+    async function captureRenameRequest(
+      call: (db: Connection) => Promise<void>,
+    ): Promise<{ url: string; body: Record<string, unknown> }> {
+      let captured: { url: string; body: Record<string, unknown> } | undefined;
+      await withMockDatabase((req, res) => {
+        let raw = "";
+        req.on("data", (chunk) => {
+          raw += chunk;
+        });
+        req.on("end", () => {
+          captured = {
+            url: req.url ?? "",
+            body: raw ? JSON.parse(raw) : {},
+          };
+          res.writeHead(200, { "Content-Type": "application/json" }).end("");
+        });
+      }, call);
+      if (!captured) {
+        throw new Error("mock server never saw a request");
+      }
+      return captured;
+    }
+
+    it("sends rename request for a table in the root namespace", async () => {
+      const { url, body } = await captureRenameRequest(async (db) => {
+        await db.renameTable("table1", "table2");
+      });
+      expect(url).toBe("/v1/table/table1/rename/");
+      // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
+      expect(body).toEqual({ new_table_name: "table2" });
+    });
+
+    it("omits new_namespace when only the current namespace is supplied", async () => {
+      // Safe-default check: passing namespacePath alone must not send
+      // `new_namespace`, so the server keeps the table in its current
+      // namespace instead of silently moving it to root.
+      const { url, body } = await captureRenameRequest(async (db) => {
+        await db.renameTable("table1", "table2", {
+          namespacePath: ["ns1"],
+        });
+      });
+      expect(url).toBe("/v1/table/ns1$table1/rename/");
+      // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
+      expect(body).toEqual({ new_table_name: "table2" });
+    });
+
+    it("includes new_namespace in the body for a cross-namespace rename", async () => {
+      const { url, body } = await captureRenameRequest(async (db) => {
+        await db.renameTable("table1", "table2", {
+          namespacePath: ["ns1"],
+          newNamespacePath: ["ns2"],
+        });
+      });
+      expect(url).toBe("/v1/table/ns1$table1/rename/");
+      expect(body).toEqual({
+        // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
+        new_table_name: "table2",
+        // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
+        new_namespace: ["ns2"],
+      });
+    });
+  });
 });

nodejs/__test__/rerankers.test.ts

@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
+import { spawn } from "node:child_process";
+import * as path from "node:path";
 import { RecordBatch } from "apache-arrow";
 import * as tmp from "tmp";
 import { Connection, Index, Table, connect, makeArrowTable } from "../lancedb";
@@ -76,4 +78,91 @@ describe("rerankers", function () {
 
     expect(result).toHaveLength(2);
   });
+
+  it("does not keep process alive after rerank query", async function () {
+    const script = `
+import * as lancedb from "./dist/index.js";
+import * as os from "node:os";
+import * as path from "node:path";
+import * as fs from "node:fs/promises";
+
+const dir = await fs.mkdtemp(path.join(os.tmpdir(), "lancedb-rerank-exit-"));
+const db = await lancedb.connect(dir);
+const table = await db.createTable("test", [{ text: "hello", vector: [1, 2, 3] }], {
+  mode: "overwrite",
+});
+await table.createIndex("text", { config: lancedb.Index.fts() });
+await table.waitForIndex(["text_idx"], 30);
+
+const reranker = await lancedb.rerankers.RRFReranker.create();
+await table
+  .query()
+  .nearestTo([1, 2, 3])
+  .fullTextSearch("hello")
+  .rerank(reranker)
+  .toArray();
+
+table.close();
+db.close();
+`;
+
+    await new Promise<void>((resolve, reject) => {
+      const child = spawn(
+        process.execPath,
+        ["--input-type=module", "-e", script],
+        {
+          cwd: path.resolve(__dirname, ".."),
+          stdio: ["ignore", "pipe", "pipe"],
+        },
+      );
+
+      let stdout = "";
+      let stderr = "";
+
+      child.stdout.on("data", (chunk) => {
+        stdout += chunk.toString();
+      });
+
+      child.stderr.on("data", (chunk) => {
+        stderr += chunk.toString();
+      });
+
+      const timeout = setTimeout(() => {
+        child.kill();
+        reject(
+          new Error(
+            `child process did not exit in time\nstdout:\n${stdout}\nstderr:\n${stderr}`,
+          ),
+        );
+      }, 20_000);
+
+      child.on("error", (err) => {
+        clearTimeout(timeout);
+        reject(err);
+      });
+
+      child.on("exit", (code, signal) => {
+        clearTimeout(timeout);
+        if (signal !== null) {
+          reject(
+            new Error(
+              `child process exited with signal ${signal}\nstdout:\n${stdout}\nstderr:\n${stderr}`,
+            ),
+          );
+          return;
+        }
+
+        if (code !== 0) {
+          reject(
+            new Error(
+              `child process exited with code ${code}\nstdout:\n${stdout}\nstderr:\n${stderr}`,
+            ),
+          );
+          return;
+        }
+
+        resolve();
+      });
+    });
+  });
 });

nodejs/__test__/scannable.test.ts

@@ -0,0 +1,438 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+import {
+  Field,
+  Float16,
+  Int32,
+  type RecordBatch,
+  RecordBatchReader,
+  Schema,
+  tableToIPC,
+} from "apache-arrow";
+import { makeArrowTable, makeEmptyTable } from "../lancedb/arrow";
+import { Scannable } from "../lancedb/scannable";
+
+function makeTable() {
+  return makeArrowTable(
+    [
+      { id: 1, name: "a" },
+      { id: 2, name: "b" },
+      { id: 3, name: "c" },
+    ],
+    { vectorColumns: {} },
+  );
+}
+
+async function makeReader(): Promise<RecordBatchReader> {
+  // `RecordBatchReader.from()` returns an unopened reader; `.schema` is only
+  // populated after `.open()`. Opening sync readers is synchronous.
+  const reader = RecordBatchReader.from(tableToIPC(makeTable()));
+  return reader.open() as RecordBatchReader;
+}
+
+describe("Scannable", () => {
+  describe("fromTable", () => {
+    test("reflects schema, numRows, and defaults rescannable=true", async () => {
+      const table = makeTable();
+      const scannable = await Scannable.fromTable(table);
+
+      expect(scannable.schema).toBe(table.schema);
+      expect(scannable.numRows).toBe(table.numRows);
+      expect(scannable.rescannable).toBe(true);
+    });
+
+    test("throws when opts.numRows does not match table.numRows", async () => {
+      await expect(
+        Scannable.fromTable(makeTable(), { numRows: 42 }),
+      ).rejects.toThrow(/does not match table\.numRows/);
+    });
+
+    test("throws when opts.rescannable is false", async () => {
+      await expect(
+        Scannable.fromTable(makeTable(), { rescannable: false }),
+      ).rejects.toThrow(/always rescannable/);
+    });
+  });
+
+  describe("fromRecordBatchReader", () => {
+    test("reflects schema and defaults numRows=null, rescannable=false", async () => {
+      const reader = await makeReader();
+      const scannable = await Scannable.fromRecordBatchReader(reader);
+
+      expect(scannable.schema).toBe(reader.schema);
+      expect(scannable.numRows).toBeNull();
+      expect(scannable.rescannable).toBe(false);
+    });
+
+    test("honors numRows override", async () => {
+      const scannable = await Scannable.fromRecordBatchReader(
+        await makeReader(),
+        { numRows: 3 },
+      );
+
+      expect(scannable.numRows).toBe(3);
+      expect(scannable.rescannable).toBe(false);
+    });
+
+    test("rescannable: false explicit does not throw", async () => {
+      const reader = await makeReader();
+      const scannable = await Scannable.fromRecordBatchReader(reader, {
+        rescannable: false,
+      });
+      expect(scannable.rescannable).toBe(false);
+    });
+
+    test("throws when opts.rescannable is true", async () => {
+      const reader = await makeReader();
+      await expect(
+        Scannable.fromRecordBatchReader(reader, { rescannable: true }),
+      ).rejects.toThrow(/does not accept rescannable/);
+    });
+
+    test("throws when opts.rescannable is true even alongside numRows", async () => {
+      const reader = await makeReader();
+      await expect(
+        Scannable.fromRecordBatchReader(reader, {
+          numRows: 3,
+          rescannable: true,
+        }),
+      ).rejects.toThrow(/does not accept rescannable/);
+    });
+  });
+
+  describe("fromIterable", () => {
+    test("accepts a sync iterable of batches", async () => {
+      const table = makeTable();
+      const scannable = await Scannable.fromIterable(
+        table.schema,
+        table.batches,
+      );
+
+      expect(scannable.schema).toBe(table.schema);
+      expect(scannable.numRows).toBeNull();
+      expect(scannable.rescannable).toBe(false);
+    });
+
+    test("accepts an async iterable of batches", async () => {
+      const table = makeTable();
+      async function* generator(): AsyncGenerator<RecordBatch> {
+        for (const batch of table.batches) {
+          yield batch;
+        }
+      }
+
+      const scannable = await Scannable.fromIterable(table.schema, generator());
+      expect(scannable.schema).toBe(table.schema);
+      expect(scannable.rescannable).toBe(false);
+    });
+
+    describe("rescannable: true detection", () => {
+      // Replayable inputs: [Symbol.iterator]() / [Symbol.asyncIterator]()
+      // returns a fresh iterator each call. Must NOT throw.
+
+      test("Array passes (fresh ArrayIterator each call)", async () => {
+        const table = makeTable();
+        const scannable = await Scannable.fromIterable(
+          table.schema,
+          table.batches,
+          { rescannable: true },
+        );
+        expect(scannable.rescannable).toBe(true);
+      });
+
+      test("Set passes (fresh SetIterator each call)", async () => {
+        const table = makeTable();
+        const set = new Set<RecordBatch>(table.batches);
+        const scannable = await Scannable.fromIterable(table.schema, set, {
+          rescannable: true,
+        });
+        expect(scannable.rescannable).toBe(true);
+      });
+
+      test("custom Iterable returning a fresh iterator passes", async () => {
+        const table = makeTable();
+        const replayable: Iterable<RecordBatch> = {
+          [Symbol.iterator]() {
+            return table.batches[Symbol.iterator]();
+          },
+        };
+        const scannable = await Scannable.fromIterable(
+          table.schema,
+          replayable,
+          { rescannable: true },
+        );
+        expect(scannable.rescannable).toBe(true);
+      });
+
+      test("object with generator method passes (fresh generator each call)", async () => {
+        const table = makeTable();
+        const replayable: Iterable<RecordBatch> = {
+          *[Symbol.iterator]() {
+            for (const batch of table.batches) yield batch;
+          },
+        };
+        const scannable = await Scannable.fromIterable(
+          table.schema,
+          replayable,
+          { rescannable: true },
+        );
+        expect(scannable.rescannable).toBe(true);
+      });
+
+      test("empty Array passes (replayable degenerate case)", async () => {
+        const schema = makeTable().schema;
+        const scannable = await Scannable.fromIterable(
+          schema,
+          [] as RecordBatch[],
+          { rescannable: true },
+        );
+        expect(scannable.rescannable).toBe(true);
+      });
+
+      // One-shot inputs: [Symbol.iterator]() / [Symbol.asyncIterator]()
+      // returns the same object, or the input is already-an-iterator.
+      // Must throw with a /one-shot/ message.
+
+      test("sync generator throws", async () => {
+        const table = makeTable();
+        function* generator(): Generator<RecordBatch> {
+          for (const batch of table.batches) yield batch;
+        }
+        await expect(
+          Scannable.fromIterable(table.schema, generator(), {
+            rescannable: true,
+          }),
+        ).rejects.toThrow(/one-shot/);
+      });
+
+      test("async generator throws", async () => {
+        const table = makeTable();
+        async function* generator(): AsyncGenerator<RecordBatch> {
+          for (const batch of table.batches) yield batch;
+        }
+        await expect(
+          Scannable.fromIterable(table.schema, generator(), {
+            rescannable: true,
+          }),
+        ).rejects.toThrow(/one-shot/);
+      });
+
+      test("empty generator throws (one-shot degenerate case)", async () => {
+        const schema = makeTable().schema;
+        function* generator(): Generator<RecordBatch> {
+          // intentionally empty; yields nothing.
+        }
+        await expect(
+          Scannable.fromIterable(schema, generator(), { rescannable: true }),
+        ).rejects.toThrow(/one-shot/);
+      });
+
+      test("custom self-iterator throws", async () => {
+        const table = makeTable();
+        const batches = table.batches;
+        let i = 0;
+        const oneShot: Iterable<RecordBatch> & Iterator<RecordBatch> = {
+          [Symbol.iterator]() {
+            return this;
+          },
+          next() {
+            if (i >= batches.length) {
+              return { done: true, value: undefined };
+            }
+            return { done: false, value: batches[i++] };
+          },
+        };
+        await expect(
+          Scannable.fromIterable(table.schema, oneShot, { rescannable: true }),
+        ).rejects.toThrow(/one-shot/);
+      });
+
+      test("Array.values() (IterableIterator) throws", async () => {
+        const table = makeTable();
+        const iter = table.batches.values();
+        await expect(
+          Scannable.fromIterable(table.schema, iter, { rescannable: true }),
+        ).rejects.toThrow(/one-shot/);
+      });
+
+      test("raw iterator (only `.next`) throws", async () => {
+        const table = makeTable();
+        const batches = table.batches;
+        let i = 0;
+        const rawIter = {
+          next(): IteratorResult<RecordBatch> {
+            if (i >= batches.length) {
+              return { done: true, value: undefined };
+            }
+            return { done: false, value: batches[i++] };
+          },
+        };
+        await expect(
+          Scannable.fromIterable(
+            table.schema,
+            rawIter as unknown as Iterable<RecordBatch>,
+            { rescannable: true },
+          ),
+        ).rejects.toThrow(/one-shot/);
+      });
+
+      // Edge: null/undefined must not crash the detection helper. The
+      // null check belongs to `normalizeIterator` and only fires when a
+      // scan starts.
+
+      test("null input does not crash detection at construction", async () => {
+        const schema = makeTable().schema;
+        await expect(
+          Scannable.fromIterable(
+            schema,
+            null as unknown as Iterable<RecordBatch>,
+            {
+              rescannable: true,
+            },
+          ),
+        ).resolves.toBeDefined();
+      });
+
+      test("undefined input does not crash detection at construction", async () => {
+        const schema = makeTable().schema;
+        await expect(
+          Scannable.fromIterable(
+            schema,
+            undefined as unknown as Iterable<RecordBatch>,
+            { rescannable: true },
+          ),
+        ).resolves.toBeDefined();
+      });
+
+      // Default (rescannable omitted) skips the check entirely, so even
+      // pathological inputs construct without throwing here.
+
+      test("rescannable omitted skips detection entirely (generator passes)", async () => {
+        const table = makeTable();
+        function* generator(): Generator<RecordBatch> {
+          for (const batch of table.batches) yield batch;
+        }
+        const scannable = await Scannable.fromIterable(
+          table.schema,
+          generator(),
+        );
+        expect(scannable.rescannable).toBe(false);
+      });
+
+      test("rescannable: false explicit skips detection entirely (generator passes)", async () => {
+        const table = makeTable();
+        function* generator(): Generator<RecordBatch> {
+          for (const batch of table.batches) yield batch;
+        }
+        const scannable = await Scannable.fromIterable(
+          table.schema,
+          generator(),
+          { rescannable: false },
+        );
+        expect(scannable.rescannable).toBe(false);
+      });
+    });
+  });
+
+  describe("fromFactory", () => {
+    test("defaults rescannable=true and does not invoke the factory eagerly", async () => {
+      const table = makeTable();
+      const factory = jest.fn(() => table.batches);
+
+      const scannable = await Scannable.fromFactory(table.schema, factory);
+
+      expect(scannable.schema).toBe(table.schema);
+      expect(scannable.rescannable).toBe(true);
+      expect(factory).not.toHaveBeenCalled();
+    });
+
+    test("honors rescannable and numRows overrides", async () => {
+      const table = makeTable();
+      const scannable = await Scannable.fromFactory(
+        table.schema,
+        () => table.batches,
+        { numRows: 7, rescannable: false },
+      );
+
+      expect(scannable.numRows).toBe(7);
+      expect(scannable.rescannable).toBe(false);
+    });
+  });
+
+  describe("validation", () => {
+    test("throws when numRows is negative", async () => {
+      await expect(
+        Scannable.fromFactory(makeTable().schema, () => [], { numRows: -1 }),
+      ).rejects.toThrow(/non-negative/);
+    });
+
+    test("throws when numRows is not an integer", async () => {
+      await expect(
+        Scannable.fromFactory(makeTable().schema, () => [], { numRows: 3.5 }),
+      ).rejects.toThrow(/integer/);
+    });
+  });
+
+  describe("native handle", () => {
+    test("exposes a native handle via inner", async () => {
+      const scannable = await Scannable.fromTable(makeTable());
+      expect(scannable.inner).toBeDefined();
+      expect(typeof scannable.inner).toBe("object");
+      expect(scannable.inner).not.toBeNull();
+    });
+  });
+
+  // Schema-variety construction tests. Each asserts that construction
+  // succeeds against a richer Arrow schema, which transitively exercises
+  // schema serialization and the Rust-side `ipc_file_to_schema` for types
+  // beyond flat primitives.
+  describe("schema variety", () => {
+    test("accepts an empty table", async () => {
+      const schema = new Schema([new Field("id", new Int32(), true)]);
+      const table = makeEmptyTable(schema);
+      const scannable = await Scannable.fromTable(table);
+
+      expect(scannable.numRows).toBe(0);
+      expect(scannable.schema).toBe(table.schema);
+    });
+
+    test("accepts nested struct and list columns", async () => {
+      const table = makeArrowTable(
+        [
+          { id: 1, point: { x: 0, y: 0 }, tags: ["a", "b"] },
+          { id: 2, point: { x: 1, y: 2 }, tags: ["c"] },
+        ],
+        { vectorColumns: {} },
+      );
+      const scannable = await Scannable.fromTable(table);
+
+      expect(scannable.schema).toBe(table.schema);
+      expect(scannable.numRows).toBe(2);
+    });
+
+    test("accepts a FixedSizeList (vector) column", async () => {
+      const table = makeArrowTable(
+        [
+          { id: 1, vec: [1, 2, 3] },
+          { id: 2, vec: [4, 5, 6] },
+        ],
+        { vectorColumns: { vec: { type: new Float16() } } },
+      );
+      const scannable = await Scannable.fromTable(table);
+
+      expect(scannable.schema).toBe(table.schema);
+      expect(scannable.numRows).toBe(2);
+    });
+
+    test("accepts a table with many columns", async () => {
+      const row: Record<string, number> = {};
+      for (let i = 0; i < 50; i++) row[`c${i}`] = i;
+      const table = makeArrowTable([row, row], { vectorColumns: {} });
+      const scannable = await Scannable.fromTable(table);
+
+      expect(scannable.schema.fields.length).toBe(50);
+      expect(scannable.numRows).toBe(2);
+    });
+  });
+});

nodejs/__test__/table.test.ts

@@ -103,7 +103,7 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
         },
         numIndices: 0,
         numRows: 3,
-        totalBytes: 24,
+        totalBytes: 44,
       });
     });
 
@@ -115,6 +115,48 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       await expect(table.countRows()).resolves.toBe(1);
     });
 
+    it("should invoke the progress callback", async () => {
+      const events: import("../lancedb").WriteProgress[] = [];
+      await table.add([{ id: 1 }, { id: 2 }, { id: 3 }], {
+        progress: (p) => events.push(p),
+      });
+
+      expect(events.length).toBeGreaterThan(0);
+      const last = events[events.length - 1];
+      expect(last.done).toBe(true);
+      // Earlier callbacks must have done=false.
+      for (const ev of events.slice(0, -1)) {
+        expect(ev.done).toBe(false);
+      }
+      // outputRows reflects the rows added in this call, not table size.
+      expect(last.outputRows).toBe(3);
+      // The input source (an array) reports a row count, so totalRows is set.
+      expect(last.totalRows).toBe(3);
+      // outputRows is monotonic.
+      for (let i = 1; i < events.length; i++) {
+        expect(events[i].outputRows).toBeGreaterThanOrEqual(
+          events[i - 1].outputRows,
+        );
+      }
+    });
+
+    it("should swallow errors thrown from the progress callback", async () => {
+      const warn = jest
+        .spyOn(console, "warn")
+        .mockImplementation(() => undefined);
+      try {
+        const res = await table.add([{ id: 1 }, { id: 2 }], {
+          progress: () => {
+            throw new Error("callback bomb");
+          },
+        });
+        expect(res.version).toBeGreaterThan(0);
+        expect(warn).toHaveBeenCalled();
+      } finally {
+        warn.mockRestore();
+      }
+    });
+
     it("should let me close the table", async () => {
       expect(table.isOpen()).toBe(true);
       table.close();
@@ -1259,6 +1301,98 @@ describe("schema evolution", function () {
     expect(await table.schema()).toEqual(expectedSchema);
   });
 
+  it("can add columns with schema for explicit data types", async function () {
+    const con = await connect(tmpDir.name);
+    const table = await con.createTable("vectors", [
+      { id: 1n, vector: [0.1, 0.2] },
+    ]);
+
+    // Define schema for new columns with explicit data types
+    // Note: All columns must be nullable when using addColumns with Schema
+    // because they are initially populated with null values
+    const newColumnsSchema = new Schema([
+      new Field("price", new Float64(), true),
+      new Field("category", new Utf8(), true),
+      new Field("rating", new Int32(), true),
+    ]);
+
+    const result = await table.addColumns(newColumnsSchema);
+    expect(result).toHaveProperty("version");
+    expect(result.version).toBe(2);
+
+    const expectedSchema = new Schema([
+      new Field("id", new Int64(), true),
+      new Field(
+        "vector",
+        new FixedSizeList(2, new Field("item", new Float32(), true)),
+        true,
+      ),
+      new Field("price", new Float64(), true),
+      new Field("category", new Utf8(), true),
+      new Field("rating", new Int32(), true),
+    ]);
+    expect(await table.schema()).toEqual(expectedSchema);
+
+    // Verify that new columns are populated with null values
+    const results = await table.query().toArray();
+    expect(results).toHaveLength(1);
+    expect(results[0].price).toBeNull();
+    expect(results[0].category).toBeNull();
+    expect(results[0].rating).toBeNull();
+  });
+
+  it("can add a single column using Field", async function () {
+    const con = await connect(tmpDir.name);
+    const table = await con.createTable("vectors", [
+      { id: 1n, vector: [0.1, 0.2] },
+    ]);
+
+    // Add a single field
+    const priceField = new Field("price", new Float64(), true);
+    const result = await table.addColumns(priceField);
+    expect(result).toHaveProperty("version");
+    expect(result.version).toBe(2);
+
+    const expectedSchema = new Schema([
+      new Field("id", new Int64(), true),
+      new Field(
+        "vector",
+        new FixedSizeList(2, new Field("item", new Float32(), true)),
+        true,
+      ),
+      new Field("price", new Float64(), true),
+    ]);
+    expect(await table.schema()).toEqual(expectedSchema);
+  });
+
+  it("can add multiple columns using array of Fields", async function () {
+    const con = await connect(tmpDir.name);
+    const table = await con.createTable("vectors", [
+      { id: 1n, vector: [0.1, 0.2] },
+    ]);
+
+    // Add multiple fields as array
+    const fields = [
+      new Field("price", new Float64(), true),
+      new Field("category", new Utf8(), true),
+    ];
+    const result = await table.addColumns(fields);
+    expect(result).toHaveProperty("version");
+    expect(result.version).toBe(2);
+
+    const expectedSchema = new Schema([
+      new Field("id", new Int64(), true),
+      new Field(
+        "vector",
+        new FixedSizeList(2, new Field("item", new Float32(), true)),
+        true,
+      ),
+      new Field("price", new Float64(), true),
+      new Field("category", new Utf8(), true),
+    ]);
+    expect(await table.schema()).toEqual(expectedSchema);
+  });
+
   it("can alter the columns in the schema", async function () {
     const con = await connect(tmpDir.name);
     const schema = new Schema([
@@ -1778,6 +1912,25 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       expect(results.length).toBe(3);
     });
 
+    test("prewarmData errors on local tables", async () => {
+      const db = await connect(tmpDir.name);
+      const data = [
+        { text: "alpha", vector: [0.1, 0.2, 0.3] },
+        { text: "beta", vector: [0.4, 0.5, 0.6] },
+      ];
+      const table = await db.createTable("prewarm_data_test", data);
+
+      // prewarmData is only supported on remote tables. We verify the call
+      // is wired through napi and surfaces the expected error for both
+      // arg shapes (undefined and string[]).
+      await expect(table.prewarmData()).rejects.toThrow(
+        "prewarm_data is currently only supported on remote tables",
+      );
+      await expect(table.prewarmData(["text"])).rejects.toThrow(
+        "prewarm_data is currently only supported on remote tables",
+      );
+    });
+
     test("full text index on list", async () => {
       const db = await connect(tmpDir.name);
       const data = [
@@ -2204,3 +2357,163 @@ describe("when creating an empty table", () => {
     expect((actualSchema.fields[1].type as Float64).precision).toBe(2);
   });
 });
+
+// Ensure we can create float32 arrays without using Arrow
+// by utilizing native JS TypedArray support
+//
+// https://github.com/lancedb/lancedb/issues/3115
+describe("when creating a table with Float32Array vectors", () => {
+  let tmpDir: tmp.DirResult;
+  beforeEach(() => {
+    tmpDir = tmp.dirSync({ unsafeCleanup: true });
+  });
+  afterEach(() => {
+    tmpDir.removeCallback();
+  });
+
+  it("should persist Float32Array as FixedSizeList<Float32> in the LanceDB schema", async () => {
+    const db = await connect(tmpDir.name);
+    const table = await db.createTable("test", [
+      { id: "a", vector: new Float32Array([0.1, 0.2, 0.3]) },
+      { id: "b", vector: new Float32Array([0.4, 0.5, 0.6]) },
+    ]);
+
+    const schema = await table.schema();
+    const vectorField = schema.fields.find((f) => f.name === "vector");
+    expect(vectorField).toBeDefined();
+    expect(vectorField!.type).toBeInstanceOf(FixedSizeList);
+
+    const fsl = vectorField!.type as FixedSizeList;
+    expect(fsl.listSize).toBe(3);
+    expect(fsl.children[0].type.typeId).toBe(Type.Float);
+    // precision: HALF=0, SINGLE=1, DOUBLE=2
+    expect((fsl.children[0].type as Float32).precision).toBe(1);
+  });
+});
+
+describe("setUnenforcedPrimaryKey", () => {
+  let tmpDir: tmp.DirResult;
+
+  beforeEach(() => {
+    tmpDir = tmp.dirSync({ unsafeCleanup: true });
+  });
+  afterEach(() => tmpDir.removeCallback());
+
+  it("sets a single-column primary key (string or one-element array)", async () => {
+    const conn = await connect(tmpDir.name);
+    const schema = new arrow.Schema([
+      new arrow.Field("id", new arrow.Int64(), false),
+    ]);
+    const t1 = await conn.createEmptyTable("t1", schema);
+    await t1.setUnenforcedPrimaryKey("id");
+
+    const t2 = await conn.createEmptyTable("t2", schema);
+    await t2.setUnenforcedPrimaryKey(["id"]);
+  });
+
+  it("rejects a compound primary key", async () => {
+    const conn = await connect(tmpDir.name);
+    const table = await conn.createEmptyTable(
+      "t",
+      new arrow.Schema([
+        new arrow.Field("id", new arrow.Int64(), false),
+        new arrow.Field("name", new arrow.Utf8(), false),
+      ]),
+    );
+    await expect(
+      table.setUnenforcedPrimaryKey(["id", "name"]),
+    ).rejects.toThrow();
+  });
+
+  it("rejects changing the primary key once set", async () => {
+    const conn = await connect(tmpDir.name);
+    const table = await conn.createEmptyTable(
+      "t",
+      new arrow.Schema([
+        new arrow.Field("id", new arrow.Int64(), false),
+        new arrow.Field("name", new arrow.Utf8(), false),
+      ]),
+    );
+    await table.setUnenforcedPrimaryKey("id");
+    await expect(table.setUnenforcedPrimaryKey("name")).rejects.toThrow();
+    await expect(table.setUnenforcedPrimaryKey("id")).rejects.toThrow();
+  });
+});
+
+describe("setLsmWriteSpec / unsetLsmWriteSpec", () => {
+  let tmpDir: tmp.DirResult;
+
+  beforeEach(() => {
+    tmpDir = tmp.dirSync({ unsafeCleanup: true });
+  });
+  afterEach(() => tmpDir.removeCallback());
+
+  async function makeTable(conn: Connection): Promise<Table> {
+    return await conn.createEmptyTable(
+      "t",
+      new arrow.Schema([new arrow.Field("id", new arrow.Int64(), false)]),
+    );
+  }
+
+  it("installs and removes a bucket spec", async () => {
+    const conn = await connect(tmpDir.name);
+    const table = await makeTable(conn);
+
+    await table.setUnenforcedPrimaryKey("id");
+    await table.setLsmWriteSpec({
+      specType: "bucket",
+      column: "id",
+      numBuckets: 4,
+    });
+    await table.unsetLsmWriteSpec();
+    // A second unset errors — there is no spec left to remove.
+    await expect(table.unsetLsmWriteSpec()).rejects.toThrow();
+    // A fresh spec can be installed after unset.
+    await table.setLsmWriteSpec({
+      specType: "bucket",
+      column: "id",
+      numBuckets: 8,
+    });
+  });
+
+  it("installs an unsharded spec", async () => {
+    const conn = await connect(tmpDir.name);
+    const table = await makeTable(conn);
+
+    await table.setUnenforcedPrimaryKey("id");
+    await table.setLsmWriteSpec({ specType: "unsharded" });
+    await table.unsetLsmWriteSpec();
+  });
+
+  it("installs an identity spec", async () => {
+    const conn = await connect(tmpDir.name);
+    const table = await makeTable(conn);
+
+    await table.setUnenforcedPrimaryKey("id");
+    await table.setLsmWriteSpec({ specType: "identity", column: "id" });
+    await table.unsetLsmWriteSpec();
+  });
+
+  it("rejects an invalid spec", async () => {
+    const conn = await connect(tmpDir.name);
+    const table = await makeTable(conn);
+
+    await table.setUnenforcedPrimaryKey("id");
+    // num_buckets out of range.
+    await expect(
+      table.setLsmWriteSpec({
+        specType: "bucket",
+        column: "id",
+        numBuckets: 0,
+      }),
+    ).rejects.toThrow();
+    // Column mismatch.
+    await expect(
+      table.setLsmWriteSpec({
+        specType: "bucket",
+        column: "missing",
+        numBuckets: 4,
+      }),
+    ).rejects.toThrow();
+  });
+});

nodejs/__test__/vector_types.test.ts

@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+import * as tmp from "tmp";
+
+import { type Table, connect } from "../lancedb";
+import {
+  Field,
+  FixedSizeList,
+  Float32,
+  Int64,
+  Schema,
+  makeArrowTable,
+} from "../lancedb/arrow";
+
+describe("Vector query with different typed arrays", () => {
+  let tmpDir: tmp.DirResult;
+
+  afterEach(() => {
+    tmpDir?.removeCallback();
+  });
+
+  async function createFloat32Table(): Promise<Table> {
+    tmpDir = tmp.dirSync({ unsafeCleanup: true });
+    const db = await connect(tmpDir.name);
+    const schema = new Schema([
+      new Field("id", new Int64(), true),
+      new Field(
+        "vec",
+        new FixedSizeList(2, new Field("item", new Float32())),
+        true,
+      ),
+    ]);
+    const data = makeArrowTable(
+      [
+        { id: 1n, vec: [1.0, 0.0] },
+        { id: 2n, vec: [0.0, 1.0] },
+        { id: 3n, vec: [1.0, 1.0] },
+      ],
+      { schema },
+    );
+    return db.createTable("test_f32", data);
+  }
+
+  it("should search with Float32Array (baseline)", async () => {
+    const table = await createFloat32Table();
+    const results = await table
+      .query()
+      .nearestTo(new Float32Array([1.0, 0.0]))
+      .limit(1)
+      .toArray();
+
+    expect(results.length).toBe(1);
+    expect(Number(results[0].id)).toBe(1);
+  });
+
+  it("should search with number[] (backward compat)", async () => {
+    const table = await createFloat32Table();
+    const results = await table
+      .query()
+      .nearestTo([1.0, 0.0])
+      .limit(1)
+      .toArray();
+
+    expect(results.length).toBe(1);
+    expect(Number(results[0].id)).toBe(1);
+  });
+
+  it("should search with Float64Array via raw path", async () => {
+    const table = await createFloat32Table();
+    const results = await table
+      .query()
+      .nearestTo(new Float64Array([1.0, 0.0]))
+      .limit(1)
+      .toArray();
+
+    expect(results.length).toBe(1);
+    expect(Number(results[0].id)).toBe(1);
+  });
+
+  it("should add multiple query vectors with Float64Array", async () => {
+    const table = await createFloat32Table();
+    const results = await table
+      .query()
+      .nearestTo(new Float64Array([1.0, 0.0]))
+      .addQueryVector(new Float64Array([0.0, 1.0]))
+      .limit(2)
+      .toArray();
+
+    expect(results.length).toBeGreaterThanOrEqual(2);
+  });
+
+  // Float16Array is only available in Node 22+; not in TypeScript's standard lib yet
+  const float16ArrayCtor = (globalThis as unknown as Record<string, unknown>)
+    .Float16Array as (new (values: number[]) => unknown) | undefined;
+  const hasFloat16 = float16ArrayCtor !== undefined;
+  const f16it = hasFloat16 ? it : it.skip;
+
+  f16it("should search with Float16Array via raw path", async () => {
+    const table = await createFloat32Table();
+    const results = await table
+      .query()
+      .nearestTo(new float16ArrayCtor!([1.0, 0.0]) as Float32Array)
+      .limit(1)
+      .toArray();
+
+    expect(results.length).toBe(1);
+    expect(Number(results[0].id)).toBe(1);
+  });
+});

nodejs/examples/filtering.test.ts

@@ -38,5 +38,14 @@ test("filtering examples", async () => {
     // --8<-- [start:sql_search]
     await tbl.query().where("id = 10").limit(10).toArray();
     // --8<-- [end:sql_search]
+
+    // --8<-- [start:orderby_search]
+    await tbl
+      .query()
+      .where("id > 10")
+      .orderBy({ columnName: "id", ascending: false })
+      .limit(5)
+      .toArray();
+    // --8<-- [end:orderby_search]
   });
 });

nodejs/examples/package.json

@@ -11,16 +11,17 @@
     "test": "node --experimental-vm-modules node_modules/.bin/jest --testEnvironment jest-environment-node-single-context --verbose",
     "lint": "biome check *.ts && biome format *.ts",
     "lint-ci": "biome ci .",
-    "lint-fix": "biome check --write *.ts && npm run format",
+    "lint-fix": "biome check --write *.ts && pnpm format",
     "format": "biome format --write *.ts"
   },
   "author": "Lance Devs",
   "license": "Apache-2.0",
+  "packageManager": "pnpm@11.1.1",
   "dependencies": {
-    "@huggingface/transformers": "^3.0.2",
+    "@huggingface/transformers": "3.0.2",
     "@lancedb/lancedb": "file:../dist",
-    "openai": "^4.29.2",
-    "sharp": "^0.33.5"
+    "openai": "4.29.2",
+    "sharp": "0.33.5"
   },
   "devDependencies": {
     "@biomejs/biome": "^1.7.3",

nodejs/examples/pnpm-workspace.yaml

@@ -0,0 +1,13 @@
+# Block resolution of versions less than 24h old (Shai-Hulud window).
+# This is the pnpm 11 default but pinned here so it's visible to
+# reviewers and survives a future pnpm major flipping the default.
+minimumReleaseAge: 1440
+
+# Fail install if a transitive dep tries to run an unapproved script.
+strictDepBuilds: true
+
+allowBuilds:
+  '@biomejs/biome': true
+  onnxruntime-node: true
+  protobufjs: true
+  sharp: true

nodejs/lancedb/arrow.ts

@@ -20,6 +20,8 @@ import {
   Float32,
   Float64,
   Int,
+  Int8,
+  Int16,
   Int32,
   Int64,
   LargeBinary,
@@ -35,6 +37,8 @@ import {
   Timestamp,
   Type,
   Uint8,
+  Uint16,
+  Uint32,
   Utf8,
   Vector,
   makeVector as arrowMakeVector,
@@ -113,8 +117,9 @@ export type TableLike =
 export type IntoVector =
   | Float32Array
   | Float64Array
+  | Uint8Array
   | number[]
-  | Promise<Float32Array | Float64Array | number[]>;
+  | Promise<Float32Array | Float64Array | Uint8Array | number[]>;
 
 export type MultiVector = IntoVector[];
 
@@ -122,14 +127,48 @@ export function isMultiVector(value: unknown): value is MultiVector {
   return Array.isArray(value) && isIntoVector(value[0]);
 }
 
+// Float16Array is not in TypeScript's standard lib yet; access dynamically
+type Float16ArrayCtor = new (
+  ...args: unknown[]
+) => { buffer: ArrayBuffer; byteOffset: number; byteLength: number };
+const float16ArrayCtor = (globalThis as unknown as Record<string, unknown>)
+  .Float16Array as Float16ArrayCtor | undefined;
+
 export function isIntoVector(value: unknown): value is IntoVector {
   return (
     value instanceof Float32Array ||
     value instanceof Float64Array ||
+    value instanceof Uint8Array ||
+    (float16ArrayCtor !== undefined && value instanceof float16ArrayCtor) ||
     (Array.isArray(value) && !Array.isArray(value[0]))
   );
 }
 
+/**
+ * Extract the underlying byte buffer and data type from a typed array
+ * for passing to the Rust NAPI layer without precision loss.
+ */
+export function extractVectorBuffer(
+  vector: Float32Array | Float64Array | Uint8Array,
+): { data: Uint8Array; dtype: string } | null {
+  if (float16ArrayCtor !== undefined && vector instanceof float16ArrayCtor) {
+    return {
+      data: new Uint8Array(vector.buffer, vector.byteOffset, vector.byteLength),
+      dtype: "float16",
+    };
+  }
+  if (vector instanceof Float64Array) {
+    return {
+      data: new Uint8Array(vector.buffer, vector.byteOffset, vector.byteLength),
+      dtype: "float64",
+    };
+  }
+  if (vector instanceof Uint8Array && !(vector instanceof Float32Array)) {
+    return { data: vector, dtype: "uint8" };
+  }
+  return null;
+}
+
 export function isArrowTable(value: object): value is TableLike {
   if (value instanceof ArrowTable) return true;
   return "schema" in value && "batches" in value;
@@ -529,7 +568,8 @@ function isObject(value: unknown): value is Record<string, unknown> {
     !(value instanceof Date) &&
     !(value instanceof Set) &&
     !(value instanceof Map) &&
-    !(value instanceof Buffer)
+    !(value instanceof Buffer) &&
+    !ArrayBuffer.isView(value)
   );
 }
 
@@ -588,6 +628,13 @@ function inferType(
     return new Bool();
   } else if (value instanceof Buffer) {
     return new Binary();
+  } else if (ArrayBuffer.isView(value) && !(value instanceof DataView)) {
+    const info = typedArrayToArrowType(value);
+    if (info !== undefined) {
+      const child = new Field("item", info.elementType, true);
+      return new FixedSizeList(info.length, child);
+    }
+    return undefined;
   } else if (Array.isArray(value)) {
     if (value.length === 0) {
       return undefined; // Without any values we can't infer the type
@@ -746,6 +793,32 @@ function makeListVector(lists: unknown[][]): Vector<unknown> {
   return listBuilder.finish().toVector();
 }
 
+/**
+ * Map a JS TypedArray instance to the corresponding Arrow element DataType
+ * and its length. Returns undefined if the value is not a recognized TypedArray.
+ */
+function typedArrayToArrowType(
+  value: ArrayBufferView,
+): { elementType: DataType; length: number } | undefined {
+  if (value instanceof Float32Array)
+    return { elementType: new Float32(), length: value.length };
+  if (value instanceof Float64Array)
+    return { elementType: new Float64(), length: value.length };
+  if (value instanceof Uint8Array)
+    return { elementType: new Uint8(), length: value.length };
+  if (value instanceof Uint16Array)
+    return { elementType: new Uint16(), length: value.length };
+  if (value instanceof Uint32Array)
+    return { elementType: new Uint32(), length: value.length };
+  if (value instanceof Int8Array)
+    return { elementType: new Int8(), length: value.length };
+  if (value instanceof Int16Array)
+    return { elementType: new Int16(), length: value.length };
+  if (value instanceof Int32Array)
+    return { elementType: new Int32(), length: value.length };
+  return undefined;
+}
+
 /** Helper function to convert an Array of JS values to an Arrow Vector */
 function makeVector(
   values: unknown[],
@@ -814,6 +887,16 @@ function makeVector(
       "makeVector cannot infer the type if all values are null or undefined",
     );
   }
+  if (ArrayBuffer.isView(sampleValue) && !(sampleValue instanceof DataView)) {
+    const info = typedArrayToArrowType(sampleValue);
+    if (info !== undefined) {
+      const fslType = new FixedSizeList(
+        info.length,
+        new Field("item", info.elementType, true),
+      );
+      return vectorFromArray(values, fslType);
+    }
+  }
   if (Array.isArray(sampleValue)) {
     // Default Arrow inference doesn't handle list types
     return makeListVector(values as unknown[][]);
@@ -1208,6 +1291,18 @@ export async function fromRecordBatchToBuffer(
   return Buffer.from(await writer.toUint8Array());
 }
 
+/**
+ * Create a buffer containing a single record batch using the Arrow IPC Stream
+ * serialization. Each call produces a self-contained Stream message (schema +
+ * batch + EOS) suitable for incremental decode by `arrow_ipc::reader::StreamReader`.
+ */
+export async function fromRecordBatchToStreamBuffer(
+  batch: RecordBatch,
+): Promise<Buffer> {
+  const writer = RecordBatchStreamWriter.writeAll([batch]);
+  return Buffer.from(await writer.toUint8Array());
+}
+
 /**
  * Serialize an Arrow Table into a buffer using the Arrow IPC Stream serialization
  *

nodejs/lancedb/connection.ts

@@ -16,6 +16,18 @@ import {
 } from "./arrow";
 import { EmbeddingFunctionConfig, getRegistry } from "./embedding/registry";
 import { Connection as LanceDbConnection } from "./native";
+import type {
+  CreateNamespaceResponse,
+  DescribeNamespaceResponse,
+  DropNamespaceResponse,
+  ListNamespacesResponse,
+} from "./native";
+export type {
+  CreateNamespaceResponse,
+  DescribeNamespaceResponse,
+  DropNamespaceResponse,
+  ListNamespacesResponse,
+};
 import { sanitizeTable } from "./sanitize";
 import { LocalTable, Table } from "./table";
 
@@ -42,7 +54,7 @@ export interface CreateTableOptions {
    * Options already set on the connection will be inherited by the table,
    * but can be overridden here.
    *
-   * The available options are described at https://lancedb.com/docs/storage/
+   * The available options are described at https://docs.lancedb.com/storage/
    */
   storageOptions?: Record<string, string>;
 
@@ -78,7 +90,7 @@ export interface OpenTableOptions {
    * Options already set on the connection will be inherited by the table,
    * but can be overridden here.
    *
-   * The available options are described at https://lancedb.com/docs/storage/
+   * The available options are described at https://docs.lancedb.com/storage/
    */
   storageOptions?: Record<string, string>;
   /**
@@ -110,6 +122,41 @@ export interface TableNamesOptions {
   /** An optional limit to the number of results to return. */
   limit?: number;
 }
+
+export interface ListNamespacesOptions {
+  /** Token from a previous response for pagination. */
+  pageToken?: string;
+  /** An optional limit to the number of results to return. */
+  limit?: number;
+}
+
+export interface CreateNamespaceOptions {
+  /** Creation mode. */
+  mode?: "create" | "exist_ok" | "overwrite";
+  /** Properties to set on the new namespace. */
+  properties?: Record<string, string>;
+}
+
+export interface DropNamespaceOptions {
+  /** Whether to skip if the namespace doesn't exist, or fail. */
+  mode?: "skip" | "fail";
+  /** Refuse to drop if non-empty (restrict) or drop recursively (cascade). */
+  behavior?: "restrict" | "cascade";
+}
+
+export interface RenameTableOptions {
+  /**
+   * The namespace path of the table being renamed. Defaults to the root
+   * namespace (`[]`) when omitted.
+   */
+  namespacePath?: string[];
+  /**
+   * The namespace path to move the table to as part of the rename. When
+   * omitted the table stays in `namespacePath`.
+   */
+  newNamespacePath?: string[];
+}
+
 /**
  * A LanceDB Connection that allows you to open tables and create new ones.
  *
@@ -166,25 +213,25 @@ export abstract class Connection {
    * List all the table names in this database.
    *
    * Tables will be returned in lexicographical order.
-   * @param {string[]} namespace - The namespace to list tables from (defaults to root namespace)
+   * @param {string[]} namespacePath - The namespace path to list tables from (defaults to root namespace)
    * @param {Partial<TableNamesOptions>} options - options to control the
    * paging / start point
    *
    */
   abstract tableNames(
-    namespace?: string[],
+    namespacePath?: string[],
     options?: Partial<TableNamesOptions>,
   ): Promise<string[]>;
 
   /**
    * Open a table in the database.
    * @param {string} name - The name of the table
-   * @param {string[]} namespace - The namespace of the table (defaults to root namespace)
+   * @param {string[]} namespacePath - The namespace path of the table (defaults to root namespace)
    * @param {Partial<OpenTableOptions>} options - Additional options
    */
   abstract openTable(
     name: string,
-    namespace?: string[],
+    namespacePath?: string[],
     options?: Partial<OpenTableOptions>,
   ): Promise<Table>;
 
@@ -193,7 +240,7 @@ export abstract class Connection {
    * @param {object} options - The options object.
    * @param {string} options.name - The name of the table.
    * @param {Data} options.data - Non-empty Array of Records to be inserted into the table
-   * @param {string[]} namespace - The namespace to create the table in (defaults to root namespace)
+   * @param {string[]} namespacePath - The namespace path to create the table in (defaults to root namespace)
    *
    */
   abstract createTable(
@@ -201,7 +248,7 @@ export abstract class Connection {
       name: string;
       data: Data;
     } & Partial<CreateTableOptions>,
-    namespace?: string[],
+    namespacePath?: string[],
   ): Promise<Table>;
   /**
    * Creates a new Table and initialize it with new data.
@@ -220,13 +267,13 @@ export abstract class Connection {
    * @param {string} name - The name of the table.
    * @param {Record<string, unknown>[] | TableLike} data - Non-empty Array of Records
    * to be inserted into the table
-   * @param {string[]} namespace - The namespace to create the table in (defaults to root namespace)
+   * @param {string[]} namespacePath - The namespace path to create the table in (defaults to root namespace)
    * @param {Partial<CreateTableOptions>} options - Additional options
    */
   abstract createTable(
     name: string,
     data: Record<string, unknown>[] | TableLike,
-    namespace?: string[],
+    namespacePath?: string[],
     options?: Partial<CreateTableOptions>,
   ): Promise<Table>;
 
@@ -245,28 +292,91 @@ export abstract class Connection {
    * Creates a new empty Table
    * @param {string} name - The name of the table.
    * @param {Schema} schema - The schema of the table
-   * @param {string[]} namespace - The namespace to create the table in (defaults to root namespace)
+   * @param {string[]} namespacePath - The namespace path to create the table in (defaults to root namespace)
    * @param {Partial<CreateTableOptions>} options - Additional options
    */
   abstract createEmptyTable(
     name: string,
     schema: import("./arrow").SchemaLike,
-    namespace?: string[],
+    namespacePath?: string[],
     options?: Partial<CreateTableOptions>,
   ): Promise<Table>;
 
   /**
    * Drop an existing table.
    * @param {string} name The name of the table to drop.
-   * @param {string[]} namespace The namespace of the table (defaults to root namespace).
+   * @param {string[]} namespacePath The namespace path of the table (defaults to root namespace).
    */
-  abstract dropTable(name: string, namespace?: string[]): Promise<void>;
+  abstract dropTable(name: string, namespacePath?: string[]): Promise<void>;
 
   /**
    * Drop all tables in the database.
-   * @param {string[]} namespace The namespace to drop tables from (defaults to root namespace).
+   * @param {string[]} namespacePath The namespace path to drop tables from (defaults to root namespace).
    */
-  abstract dropAllTables(namespace?: string[]): Promise<void>;
+  abstract dropAllTables(namespacePath?: string[]): Promise<void>;
+
+  /**
+   * Describe a namespace, returning its properties.
+   *
+   * @param {string[]} namespacePath - The namespace path to describe, in
+   *   parent → child order, e.g. `["analytics", "sales"]`.
+   * @returns {Promise<DescribeNamespaceResponse>} The namespace's properties
+   *   (may be undefined if the namespace has none).
+   */
+  abstract describeNamespace(
+    namespacePath: string[],
+  ): Promise<DescribeNamespaceResponse>;
+
+  /**
+   * List the immediate child namespaces under the given parent.
+   *
+   * Results may be paginated. To retrieve subsequent pages, pass the
+   * `pageToken` returned by a previous call.
+   *
+   * @param {string[]} namespacePath - The parent namespace path. Defaults
+   *   to the root namespace if omitted.
+   * @param {Partial<ListNamespacesOptions>} options - Pagination options
+   *   (`pageToken`, `limit`).
+   * @returns {Promise<ListNamespacesResponse>} Child namespace names and
+   *   an optional token for fetching the next page.
+   */
+  abstract listNamespaces(
+    namespacePath?: string[],
+    options?: Partial<ListNamespacesOptions>,
+  ): Promise<ListNamespacesResponse>;
+
+  /**
+   * Create a new namespace at the given path.
+   *
+   * @param {string[]} namespacePath - The namespace path to create.
+   * @param {Partial<CreateNamespaceOptions>} options - Creation `mode`
+   *   ("create" | "exist_ok" | "overwrite") and optional `properties`
+   *   to attach to the namespace.
+   * @returns {Promise<CreateNamespaceResponse>} The properties of the
+   *   created namespace and an optional transaction id.
+   */
+  abstract createNamespace(
+    namespacePath: string[],
+    options?: Partial<CreateNamespaceOptions>,
+  ): Promise<CreateNamespaceResponse>;
+
+  /**
+   * Drop a namespace.
+   *
+   * Use `behavior: "cascade"` to also drop everything contained in the
+   * namespace (sub-namespaces and tables). The default `"restrict"`
+   * behavior refuses to drop a non-empty namespace.
+   *
+   * @param {string[]} namespacePath - The namespace path to drop.
+   * @param {Partial<DropNamespaceOptions>} options - `mode` ("skip" | "fail"
+   *   for missing-namespace handling) and `behavior` ("restrict" | "cascade").
+   * @returns {Promise<DropNamespaceResponse>} Any properties returned by
+   *   the server and an optional transaction id.
+   */
+  abstract dropNamespace(
+    namespacePath: string[],
+    options?: Partial<DropNamespaceOptions>,
+  ): Promise<DropNamespaceResponse>;
 
   /**
    * Clone a table from a source table.
@@ -279,7 +389,7 @@ export abstract class Connection {
    * @param {string} targetTableName - The name of the target table to create.
    * @param {string} sourceUri - The URI of the source table to clone from.
    * @param {object} options - Clone options.
-   * @param {string[]} options.targetNamespace - The namespace for the target table (defaults to root namespace).
+   * @param {string[]} options.targetNamespacePath - The namespace path for the target table (defaults to root namespace).
    * @param {number} options.sourceVersion - The version of the source table to clone.
    * @param {string} options.sourceTag - The tag of the source table to clone.
    * @param {boolean} options.isShallow - Whether to perform a shallow clone (defaults to true).
@@ -288,12 +398,30 @@ export abstract class Connection {
     targetTableName: string,
     sourceUri: string,
     options?: {
-      targetNamespace?: string[];
+      targetNamespacePath?: string[];
       sourceVersion?: number;
       sourceTag?: string;
       isShallow?: boolean;
     },
   ): Promise<Table>;
+
+  /**
+   * Rename a table.
+   *
+   * Currently only supported by LanceDB Cloud. Local OSS connections and
+   * namespace-backed connections (via {@link connectNamespace}) reject with
+   * a "not supported" error.
+   *
+   * @param {string} currentName - The current name of the table.
+   * @param {string} newName - The new name for the table.
+   * @param {RenameTableOptions} options - Optional namespace paths. When
+   *   `newNamespacePath` is omitted the table stays in `namespacePath`.
+   */
+  abstract renameTable(
+    currentName: string,
+    newName: string,
+    options?: RenameTableOptions,
+  ): Promise<void>;
 }
 
 /** @hideconstructor */
@@ -319,25 +447,25 @@ export class LocalConnection extends Connection {
   }
 
   async tableNames(
-    namespaceOrOptions?: string[] | Partial<TableNamesOptions>,
+    namespacePathOrOptions?: string[] | Partial<TableNamesOptions>,
     options?: Partial<TableNamesOptions>,
   ): Promise<string[]> {
-    // Detect if first argument is namespace array or options object
-    let namespace: string[] | undefined;
+    // Detect if first argument is namespacePath array or options object
+    let namespacePath: string[] | undefined;
     let tableNamesOptions: Partial<TableNamesOptions> | undefined;
 
-    if (Array.isArray(namespaceOrOptions)) {
-      // First argument is namespace array
-      namespace = namespaceOrOptions;
+    if (Array.isArray(namespacePathOrOptions)) {
+      // First argument is namespacePath array
+      namespacePath = namespacePathOrOptions;
       tableNamesOptions = options;
     } else {
       // First argument is options object (backwards compatibility)
-      namespace = undefined;
-      tableNamesOptions = namespaceOrOptions;
+      namespacePath = undefined;
+      tableNamesOptions = namespacePathOrOptions;
     }
 
     return this.inner.tableNames(
-      namespace ?? [],
+      namespacePath ?? [],
       tableNamesOptions?.startAfter,
       tableNamesOptions?.limit,
     );
@@ -345,12 +473,12 @@ export class LocalConnection extends Connection {
 
   async openTable(
     name: string,
-    namespace?: string[],
+    namespacePath?: string[],
     options?: Partial<OpenTableOptions>,
   ): Promise<Table> {
     const innerTable = await this.inner.openTable(
       name,
-      namespace ?? [],
+      namespacePath ?? [],
       cleanseStorageOptions(options?.storageOptions),
       options?.indexCacheSize,
     );
@@ -362,7 +490,7 @@ export class LocalConnection extends Connection {
     targetTableName: string,
     sourceUri: string,
     options?: {
-      targetNamespace?: string[];
+      targetNamespacePath?: string[];
       sourceVersion?: number;
       sourceTag?: string;
       isShallow?: boolean;
@@ -371,7 +499,7 @@ export class LocalConnection extends Connection {
     const innerTable = await this.inner.cloneTable(
       targetTableName,
       sourceUri,
-      options?.targetNamespace ?? [],
+      options?.targetNamespacePath ?? [],
       options?.sourceVersion ?? null,
       options?.sourceTag ?? null,
       options?.isShallow ?? true,
@@ -406,42 +534,42 @@ export class LocalConnection extends Connection {
     nameOrOptions:
       | string
       | ({ name: string; data: Data } & Partial<CreateTableOptions>),
-    dataOrNamespace?: Record<string, unknown>[] | TableLike | string[],
-    namespaceOrOptions?: string[] | Partial<CreateTableOptions>,
+    dataOrNamespacePath?: Record<string, unknown>[] | TableLike | string[],
+    namespacePathOrOptions?: string[] | Partial<CreateTableOptions>,
     options?: Partial<CreateTableOptions>,
   ): Promise<Table> {
     if (typeof nameOrOptions !== "string" && "name" in nameOrOptions) {
-      // First overload: createTable(options, namespace?)
+      // First overload: createTable(options, namespacePath?)
       const { name, data, ...createOptions } = nameOrOptions;
-      const namespace = dataOrNamespace as string[] | undefined;
-      return this._createTableImpl(name, data, namespace, createOptions);
+      const namespacePath = dataOrNamespacePath as string[] | undefined;
+      return this._createTableImpl(name, data, namespacePath, createOptions);
     }
 
-    // Second overload: createTable(name, data, namespace?, options?)
+    // Second overload: createTable(name, data, namespacePath?, options?)
     const name = nameOrOptions;
-    const data = dataOrNamespace as Record<string, unknown>[] | TableLike;
+    const data = dataOrNamespacePath as Record<string, unknown>[] | TableLike;
 
-    // Detect if third argument is namespace array or options object
-    let namespace: string[] | undefined;
+    // Detect if third argument is namespacePath array or options object
+    let namespacePath: string[] | undefined;
     let createOptions: Partial<CreateTableOptions> | undefined;
 
-    if (Array.isArray(namespaceOrOptions)) {
-      // Third argument is namespace array
-      namespace = namespaceOrOptions;
+    if (Array.isArray(namespacePathOrOptions)) {
+      // Third argument is namespacePath array
+      namespacePath = namespacePathOrOptions;
       createOptions = options;
     } else {
       // Third argument is options object (backwards compatibility)
-      namespace = undefined;
-      createOptions = namespaceOrOptions;
+      namespacePath = undefined;
+      createOptions = namespacePathOrOptions;
     }
 
-    return this._createTableImpl(name, data, namespace, createOptions);
+    return this._createTableImpl(name, data, namespacePath, createOptions);
   }
 
   private async _createTableImpl(
     name: string,
     data: Data,
-    namespace?: string[],
+    namespacePath?: string[],
     options?: Partial<CreateTableOptions>,
   ): Promise<Table> {
     if (data === undefined) {
@@ -455,7 +583,7 @@ export class LocalConnection extends Connection {
       name,
       buf,
       mode,
-      namespace ?? [],
+      namespacePath ?? [],
       storageOptions,
     );
 
@@ -465,21 +593,21 @@ export class LocalConnection extends Connection {
   async createEmptyTable(
     name: string,
     schema: import("./arrow").SchemaLike,
-    namespaceOrOptions?: string[] | Partial<CreateTableOptions>,
+    namespacePathOrOptions?: string[] | Partial<CreateTableOptions>,
     options?: Partial<CreateTableOptions>,
   ): Promise<Table> {
-    // Detect if third argument is namespace array or options object
-    let namespace: string[] | undefined;
+    // Detect if third argument is namespacePath array or options object
+    let namespacePath: string[] | undefined;
     let createOptions: Partial<CreateTableOptions> | undefined;
 
-    if (Array.isArray(namespaceOrOptions)) {
-      // Third argument is namespace array
-      namespace = namespaceOrOptions;
+    if (Array.isArray(namespacePathOrOptions)) {
+      // Third argument is namespacePath array
+      namespacePath = namespacePathOrOptions;
       createOptions = options;
     } else {
       // Third argument is options object (backwards compatibility)
-      namespace = undefined;
-      createOptions = namespaceOrOptions;
+      namespacePath = undefined;
+      createOptions = namespacePathOrOptions;
     }
 
     let mode: string = createOptions?.mode ?? "create";
@@ -502,18 +630,70 @@ export class LocalConnection extends Connection {
       name,
       buf,
       mode,
-      namespace ?? [],
+      namespacePath ?? [],
       storageOptions,
     );
     return new LocalTable(innerTable);
   }
 
-  async dropTable(name: string, namespace?: string[]): Promise<void> {
-    return this.inner.dropTable(name, namespace ?? []);
+  async dropTable(name: string, namespacePath?: string[]): Promise<void> {
+    return this.inner.dropTable(name, namespacePath ?? []);
   }
 
-  async dropAllTables(namespace?: string[]): Promise<void> {
-    return this.inner.dropAllTables(namespace ?? []);
+  async dropAllTables(namespacePath?: string[]): Promise<void> {
+    return this.inner.dropAllTables(namespacePath ?? []);
+  }
+
+  describeNamespace(
+    namespacePath: string[],
+  ): Promise<DescribeNamespaceResponse> {
+    return this.inner.describeNamespace(namespacePath);
+  }
+
+  listNamespaces(
+    namespacePath?: string[],
+    options?: Partial<ListNamespacesOptions>,
+  ): Promise<ListNamespacesResponse> {
+    return this.inner.listNamespaces(
+      namespacePath ?? [],
+      options?.pageToken,
+      options?.limit,
+    );
+  }
+
+  createNamespace(
+    namespacePath: string[],
+    options?: Partial<CreateNamespaceOptions>,
+  ): Promise<CreateNamespaceResponse> {
+    return this.inner.createNamespace(
+      namespacePath,
+      options?.mode,
+      options?.properties,
+    );
+  }
+
+  dropNamespace(
+    namespacePath: string[],
+    options?: Partial<DropNamespaceOptions>,
+  ): Promise<DropNamespaceResponse> {
+    return this.inner.dropNamespace(
+      namespacePath,
+      options?.mode,
+      options?.behavior,
+    );
+  }
+
+  async renameTable(
+    currentName: string,
+    newName: string,
+    options?: RenameTableOptions,
+  ): Promise<void> {
+    return this.inner.renameTable(
+      currentName,
+      newName,
+      options?.namespacePath ?? [],
+      options?.newNamespacePath,
+    );
   }
 }
 

nodejs/lancedb/index.ts

@@ -8,6 +8,7 @@ import {
 } from "./connection";
 
 import {
+  ConnectNamespaceOptions,
   ConnectionOptions,
   Connection as LanceDbConnection,
   JsHeaderProvider as NativeJsHeaderProvider,
@@ -22,6 +23,7 @@ export { JsHeaderProvider as NativeJsHeaderProvider } from "./native.js";
 export {
   AddColumnsSql,
   ConnectionOptions,
+  ConnectNamespaceOptions,
   IndexStatistics,
   IndexConfig,
   ClientConfig,
@@ -62,6 +64,14 @@ export {
   CreateTableOptions,
   TableNamesOptions,
   OpenTableOptions,
+  ListNamespacesOptions,
+  CreateNamespaceOptions,
+  DropNamespaceOptions,
+  ListNamespacesResponse,
+  CreateNamespaceResponse,
+  DropNamespaceResponse,
+  DescribeNamespaceResponse,
+  RenameTableOptions,
 } from "./connection";
 
 export { Session } from "./native.js";
@@ -73,6 +83,7 @@ export {
   VectorQuery,
   TakeQuery,
   QueryExecutionOptions,
+  ColumnOrdering,
   FullTextSearchOptions,
   RecordBatchIterator,
   FullTextQuery,
@@ -103,6 +114,8 @@ export {
   UpdateOptions,
   OptimizeOptions,
   Version,
+  WriteProgress,
+  LsmWriteSpec,
   ColumnAlteration,
 } from "./table";
 
@@ -117,6 +130,7 @@ export { MergeInsertBuilder, WriteExecutionOptions } from "./merge";
 
 export * as embedding from "./embedding";
 export { permutationBuilder, PermutationBuilder } from "./permutation";
+export { Scannable, ScannableOptions } from "./scannable";
 export * as rerankers from "./rerankers";
 export {
   SchemaLike,
@@ -293,3 +307,197 @@ export async function connect(
   );
   return new LocalConnection(nativeConn);
 }
+
+/**
+ * Configuration for the built-in directory namespace (`"dir"`).
+ *
+ * The directory namespace stores tables under a single root path (local
+ * filesystem or object storage URI). See
+ * {@link https://docs.lancedb.com/namespaces} for the documented surface;
+ * less-common knobs live under {@link DirNamespaceConfig.extraProperties}.
+ */
+export interface DirNamespaceConfig {
+  /** Root path or URI containing the LanceDB tables. */
+  root: string;
+  /**
+   * Whether to maintain a namespace manifest at the root. Required for
+   * child namespaces. Defaults to true on the impl side.
+   */
+  manifestEnabled?: boolean;
+  /**
+   * Additional raw properties passed verbatim to the namespace
+   * implementation (e.g. `storage.*`, `credential_vendor.*`). Typed
+   * fields above take precedence on key collision.
+   */
+  extraProperties?: Record<string, string>;
+}
+
+/**
+ * Configuration for the built-in REST namespace (`"rest"`).
+ *
+ * The REST namespace talks to a remote catalog server over HTTP. See
+ * {@link https://docs.lancedb.com/namespaces} for the documented surface;
+ * less-common knobs (TLS, metrics) live under
+ * {@link RestNamespaceConfig.extraProperties}.
+ */
+export interface RestNamespaceConfig {
+  /** Catalog endpoint URL. */
+  uri: string;
+  /**
+   * HTTP headers forwarded with each request. Keys are passed through
+   * as-is (e.g. `"x-api-key"`, `"Authorization"`).
+   */
+  headers?: Record<string, string>;
+  /**
+   * Additional raw properties passed verbatim to the namespace
+   * implementation (e.g. `tls.*`, `ops_metrics_enabled`, `delimiter`).
+   * Typed fields above take precedence on key collision.
+   */
+  extraProperties?: Record<string, string>;
+}
+
+function dirConfigToProperties(
+  config: DirNamespaceConfig,
+): Record<string, string> {
+  // Spread the whole input so that unknown keys (e.g. a raw `manifest_enabled`
+  // passed via the dynamic-impl path) flow through instead of being dropped.
+  // Typed transformations layer on top.
+  const { manifestEnabled, extraProperties, ...rest } = config;
+  const properties: Record<string, string> = {
+    ...(extraProperties ?? {}),
+    ...(rest as Record<string, string>),
+  };
+  if (manifestEnabled !== undefined) {
+    properties.manifest_enabled = String(manifestEnabled);
+  }
+  return properties;
+}
+
+function restConfigToProperties(
+  config: RestNamespaceConfig,
+): Record<string, string> {
+  const { headers, extraProperties, ...rest } = config;
+  const properties: Record<string, string> = {
+    ...(extraProperties ?? {}),
+    ...(rest as Record<string, string>),
+  };
+  if (headers) {
+    for (const [name, value] of Object.entries(headers)) {
+      properties[`headers.${name}`] = value;
+    }
+  }
+  return properties;
+}
+
+/**
+ * Connect to a LanceDB database through a namespace.
+ *
+ * Unlike {@link connect}, which routes by URI scheme (local path vs.
+ * `db://` cloud), `connectNamespace` always returns a namespace-backed
+ * connection. The `implName` selects the namespace implementation:
+ *
+ * - `"dir"` — directory namespace, configured with {@link DirNamespaceConfig}.
+ * - `"rest"` — remote REST catalog, configured with {@link RestNamespaceConfig}.
+ * - Any other string — full module path for a custom implementation,
+ *   configured with a free-form string-keyed `properties` map.
+ *
+ * @example Typed dir namespace
+ * ```ts
+ * const db = await connectNamespace("dir", { root: "/path/to/db" });
+ * await db.createTable("users", [{ id: 1 }]);
+ * ```
+ *
+ * @example Typed REST namespace with auth headers
+ * ```ts
+ * const db = await connectNamespace("rest", {
+ *   uri: "https://catalog.example.com",
+ *   headers: { "x-api-key": process.env.CATALOG_KEY ?? "" },
+ * });
+ * ```
+ *
+ * @example Custom implementation with raw properties
+ * ```ts
+ * const db = await connectNamespace("my.custom.Namespace", {
+ *   endpoint: "...",
+ * });
+ * ```
+ */
+export function connectNamespace(
+  implName: "dir",
+  config: DirNamespaceConfig,
+  options?: Partial<ConnectNamespaceOptions>,
+): Promise<Connection>;
+/**
+ * Connect through the built-in REST namespace.
+ *
+ * Configured with {@link RestNamespaceConfig}. See the function-level
+ * documentation above for the full surface, examples, and how this
+ * relates to {@link connect}.
+ *
+ * @example
+ * ```ts
+ * const db = await connectNamespace("rest", {
+ *   uri: "https://catalog.example.com",
+ *   headers: { "x-api-key": process.env.CATALOG_KEY ?? "" },
+ * });
+ * ```
+ */
+export function connectNamespace(
+  implName: "rest",
+  config: RestNamespaceConfig,
+  options?: Partial<ConnectNamespaceOptions>,
+): Promise<Connection>;
+/**
+ * Connect through a custom namespace implementation by full module path,
+ * configured with a free-form string-keyed `properties` map. Use the
+ * typed overloads above for the built-in `"dir"` and `"rest"` impls.
+ *
+ * See the function-level documentation above for examples and how this
+ * relates to {@link connect}.
+ *
+ * @example
+ * ```ts
+ * const db = await connectNamespace("my.custom.Namespace", {
+ *   endpoint: "...",
+ * });
+ * ```
+ */
+export function connectNamespace(
+  implName: string,
+  properties: Record<string, string>,
+  options?: Partial<ConnectNamespaceOptions>,
+): Promise<Connection>;
+export async function connectNamespace(
+  implName: string,
+  configOrProperties:
+    | DirNamespaceConfig
+    | RestNamespaceConfig
+    | Record<string, string>,
+  options?: Partial<ConnectNamespaceOptions>,
+): Promise<Connection> {
+  let properties: Record<string, string>;
+  if (implName === "dir") {
+    properties = dirConfigToProperties(
+      configOrProperties as DirNamespaceConfig,
+    );
+  } else if (implName === "rest") {
+    properties = restConfigToProperties(
+      configOrProperties as RestNamespaceConfig,
+    );
+  } else {
+    properties = configOrProperties as Record<string, string>;
+  }
+
+  const finalOptions: ConnectNamespaceOptions = (options ??
+    {}) as ConnectNamespaceOptions;
+  finalOptions.storageOptions = cleanseStorageOptions(
+    finalOptions.storageOptions,
+  );
+
+  const nativeConn = await LanceDbConnection.newWithNamespace(
+    implName,
+    properties,
+    finalOptions,
+  );
+  return new LocalConnection(nativeConn);
+}

nodejs/lancedb/query.ts

@@ -5,6 +5,7 @@ import {
   Table as ArrowTable,
   type IntoVector,
   RecordBatch,
+  extractVectorBuffer,
   fromBufferToRecordBatch,
   fromRecordBatchToBuffer,
   tableFromIPC,
@@ -78,6 +79,12 @@ export interface QueryExecutionOptions {
   timeoutMs?: number;
 }
 
+export interface ColumnOrdering {
+  columnName: string;
+  ascending?: boolean;
+  nullsFirst?: boolean;
+}
+
 /**
  * Options that control the behavior of a full text search
  */
@@ -416,6 +423,21 @@ export class StandardQueryBase<
     return this;
   }
 
+  /**
+   * Sort the results by the specified column(s).
+   * @returns This query builder.
+   */
+  orderBy(ordering: ColumnOrdering | ColumnOrdering[]): this {
+    const orderings = Array.isArray(ordering) ? ordering : [ordering];
+    const normalized = orderings.map((o) => ({
+      columnName: o.columnName,
+      ascending: o.ascending ?? true,
+      nullsFirst: o.nullsFirst ?? false,
+    }));
+    this.doCall((inner) => inner.orderBy(normalized));
+    return this;
+  }
+
   /**
    * Skip searching un-indexed data. This can make search faster, but will miss
    * any data that is not yet indexed.
@@ -661,10 +683,8 @@ export class VectorQuery extends StandardQueryBase<NativeVectorQuery> {
       const res = (async () => {
         try {
           const v = await vector;
-          const arr = Float32Array.from(v);
-          //
           // biome-ignore lint/suspicious/noExplicitAny: we need to get the `inner`, but js has no package scoping
-          const value: any = this.addQueryVector(arr);
+          const value: any = this.addQueryVector(v);
           const inner = value.inner as
             | NativeVectorQuery
             | Promise<NativeVectorQuery>;
@@ -676,7 +696,12 @@ export class VectorQuery extends StandardQueryBase<NativeVectorQuery> {
       return new VectorQuery(res);
     } else {
       super.doCall((inner) => {
-        inner.addQueryVector(Float32Array.from(vector));
+        const raw = Array.isArray(vector) ? null : extractVectorBuffer(vector);
+        if (raw) {
+          inner.addQueryVectorRaw(raw.data, raw.dtype);
+        } else {
+          inner.addQueryVector(Float32Array.from(vector as number[]));
+        }
       });
       return this;
     }
@@ -765,14 +790,23 @@ export class Query extends StandardQueryBase<NativeQuery> {
    * a default `limit` of 10 will be used.  @see {@link Query#limit}
    */
   nearestTo(vector: IntoVector): VectorQuery {
+    const callNearestTo = (
+      inner: NativeQuery,
+      resolved: Float32Array | Float64Array | Uint8Array | number[],
+    ): NativeVectorQuery => {
+      const raw = Array.isArray(resolved)
+        ? null
+        : extractVectorBuffer(resolved);
+      if (raw) {
+        return inner.nearestToRaw(raw.data, raw.dtype);
+      }
+      return inner.nearestTo(Float32Array.from(resolved as number[]));
+    };
+
     if (this.inner instanceof Promise) {
       const nativeQuery = this.inner.then(async (inner) => {
-        if (vector instanceof Promise) {
-          const arr = await vector.then((v) => Float32Array.from(v));
-          return inner.nearestTo(arr);
-        } else {
-          return inner.nearestTo(Float32Array.from(vector));
-        }
+        const resolved = vector instanceof Promise ? await vector : vector;
+        return callNearestTo(inner, resolved);
       });
       return new VectorQuery(nativeQuery);
     }
@@ -780,10 +814,8 @@ export class Query extends StandardQueryBase<NativeQuery> {
       const res = (async () => {
         try {
           const v = await vector;
-          const arr = Float32Array.from(v);
-          //
           // biome-ignore lint/suspicious/noExplicitAny: we need to get the `inner`, but js has no package scoping
-          const value: any = this.nearestTo(arr);
+          const value: any = this.nearestTo(v);
           const inner = value.inner as
             | NativeVectorQuery
             | Promise<NativeVectorQuery>;
@@ -794,7 +826,7 @@ export class Query extends StandardQueryBase<NativeQuery> {
       })();
       return new VectorQuery(res);
     } else {
-      const vectorQuery = this.inner.nearestTo(Float32Array.from(vector));
+      const vectorQuery = callNearestTo(this.inner, vector);
       return new VectorQuery(vectorQuery);
     }
   }

nodejs/lancedb/scannable.ts

@@ -0,0 +1,274 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+import {
+  Table as ArrowTable,
+  RecordBatch,
+  RecordBatchReader,
+  Schema,
+} from "apache-arrow";
+import {
+  fromRecordBatchToStreamBuffer,
+  fromTableToBuffer,
+  makeEmptyTable,
+} from "./arrow";
+import { NapiScannable } from "./native.js";
+
+export interface ScannableOptions {
+  /** Hint about the number of rows. Not validated against the stream. */
+  numRows?: number;
+  /**
+   * Whether the source can be scanned more than once. Defaults to `true` for
+   * `fromTable` / `fromFactory` and `false` for `fromIterable` /
+   * `fromRecordBatchReader`.
+   */
+  rescannable?: boolean;
+}
+
+/**
+ * A data source that can be scanned as a stream of Arrow `RecordBatch`es.
+ *
+ * `Scannable` wraps the schema + optional row count + rescannable flag and
+ * a callback that yields batches one at a time. It is passed to consumers
+ * (e.g. `Table.add`, `createTable`, `mergeInsert` — follow-up work) that
+ * need to pull data without materializing the full dataset in JS memory.
+ *
+ * Batches cross the JS↔Rust boundary as Arrow IPC Stream messages; a fresh
+ * writer serializes each batch, and the Rust side decodes it with
+ * `arrow_ipc::reader::StreamReader`. One batch is in flight at a time.
+ */
+export class Scannable {
+  readonly schema: Schema;
+  readonly numRows: number | null;
+  readonly rescannable: boolean;
+
+  /** @hidden */
+  private readonly native: NapiScannable;
+
+  private constructor(
+    native: NapiScannable,
+    schema: Schema,
+    numRows: number | null,
+    rescannable: boolean,
+  ) {
+    this.native = native;
+    this.schema = schema;
+    this.numRows = numRows;
+    this.rescannable = rescannable;
+  }
+
+  /** @hidden Access the native handle for passing through to Rust consumers. */
+  get inner(): NapiScannable {
+    return this.native;
+  }
+
+  /**
+   * Build a Scannable from an explicit schema and a factory that returns a
+   * fresh batch iterator on each call.
+   *
+   * The factory is invoked once per scan. Each iterator yields
+   * `RecordBatch`es matching the declared schema. Use this when you need
+   * direct control over the pull loop — for example, to wrap a streaming
+   * source whose batches are produced lazily.
+   *
+   * @param schema - The Arrow schema of the produced batches.
+   * @param factory - Called at the start of each scan to produce a batch
+   *   iterator. Must be idempotent when `rescannable` is true.
+   * @param opts - Optional hints. `rescannable` defaults to `true`; set to
+   *   `false` if calling `factory()` twice would not reproduce the same data.
+   */
+  static async fromFactory(
+    schema: Schema,
+    factory: () =>
+      | AsyncIterable<RecordBatch>
+      | Iterable<RecordBatch>
+      | AsyncIterator<RecordBatch>
+      | Iterator<RecordBatch>,
+    opts: ScannableOptions = {},
+  ): Promise<Scannable> {
+    const numRows = opts.numRows ?? null;
+    if (numRows != null && !Number.isInteger(numRows)) {
+      throw new TypeError("numRows must be an integer");
+    }
+    const rescannable = opts.rescannable ?? true;
+
+    let iter: AsyncIterator<RecordBatch> | Iterator<RecordBatch> | null = null;
+    const getNextBatch = async (isStart: boolean): Promise<Buffer | null> => {
+      // `isStart` is true on the first pull of every new scan_as_stream.
+      // Drop any cached iterator so factory() is re-invoked for the next scan
+      if (isStart) {
+        iter = null;
+      }
+      if (iter === null) {
+        iter = normalizeIterator(factory());
+      }
+      const result = await iter.next();
+      if (result.done) {
+        iter = null;
+        return null;
+      }
+      return fromRecordBatchToStreamBuffer(result.value);
+    };
+
+    const schemaBuf = await fromTableToBuffer(makeEmptyTable(schema));
+    const native = new NapiScannable(
+      schemaBuf,
+      numRows,
+      rescannable,
+      getNextBatch,
+    );
+    return new Scannable(native, schema, numRows, rescannable);
+  }
+
+  /**
+   * Build a Scannable from an in-memory Arrow `Table`. Always rescannable;
+   * the table's batches are replayed on each scan.
+   *
+   * The table's row count is authoritative: `opts.numRows` must either be
+   * omitted or equal to `table.numRows`. `opts.rescannable` of `false` is
+   * rejected because in-memory Tables are always rescannable.
+   */
+  static async fromTable(
+    table: ArrowTable,
+    opts: ScannableOptions = {},
+  ): Promise<Scannable> {
+    if (opts.numRows != null && opts.numRows !== table.numRows) {
+      throw new TypeError(
+        `opts.numRows (${opts.numRows}) does not match table.numRows (${table.numRows}). ` +
+          `The table's row count is authoritative; omit numRows or pass the matching value.`,
+      );
+    }
+    if (opts.rescannable === false) {
+      throw new TypeError(
+        `fromTable does not accept rescannable: false. ` +
+          `In-memory Arrow Tables are always rescannable; omit the option or pass true.`,
+      );
+    }
+    return Scannable.fromFactory(table.schema, () => table.batches, {
+      numRows: table.numRows,
+      rescannable: true,
+    });
+  }
+
+  /**
+   * Build a Scannable from an iterable of `RecordBatch`es. `rescannable`
+   * defaults to `false`. Pass an explicit schema so the consumer can
+   * validate before any batch is pulled.
+   *
+   * `opts.rescannable: true` is honest for replayable iterables (Arrays,
+   * Sets, or custom iterables whose `[Symbol.iterator]()` returns a fresh
+   * iterator each call). It is rejected for one-shot iterables (generators,
+   * async generators, or already-an-iterator inputs) because their
+   * `[Symbol.iterator]()` returns the same exhausted object on the second
+   * scan. For replayable sources outside this shape, use
+   * `fromFactory(schema, () => createIter(), { rescannable: true })`.
+   *
+   * Note: when `opts.rescannable` is `true`, the constructor calls
+   * `[Symbol.iterator]()` once on the input to perform the structural check.
+   */
+  static async fromIterable(
+    schema: Schema,
+    iter: AsyncIterable<RecordBatch> | Iterable<RecordBatch>,
+    opts: ScannableOptions = {},
+  ): Promise<Scannable> {
+    if (opts.rescannable === true && isOneShotIterable(iter)) {
+      throw new TypeError(
+        `fromIterable: rescannable: true is not honest for one-shot iterables ` +
+          `(generators, async generators, or iterators where [Symbol.iterator]() ` +
+          `returns the same object). The source would be exhausted after the first scan. ` +
+          `Use fromFactory(schema, () => createIter(), { rescannable: true }) for sources ` +
+          `where each call mints a fresh iterator.`,
+      );
+    }
+    return Scannable.fromFactory(schema, () => iter, {
+      numRows: opts.numRows,
+      rescannable: opts.rescannable ?? false,
+    });
+  }
+
+  /**
+   * Build a Scannable from an Arrow `RecordBatchReader`. A reader can only
+   * be consumed once; `rescannable` defaults to `false`.
+   *
+   * The reader must already be opened (via `.open()`) so its `.schema` is
+   * populated. `RecordBatchReader.from(...)` returns an unopened reader.
+   *
+   * `opts.rescannable: true` is rejected because `RecordBatchReader` is a
+   * self-iterator (its `[Symbol.iterator]()` returns itself), and this
+   * constructor does not call `reader.reset()` between scans, so a second
+   * scan would always see an exhausted reader. For genuinely replayable
+   * sources, use
+   * `fromFactory(schema, () => openReader(), { rescannable: true })`,
+   * which mints a fresh reader on each scan.
+   */
+  static async fromRecordBatchReader(
+    reader: RecordBatchReader,
+    opts: ScannableOptions = {},
+  ): Promise<Scannable> {
+    if (opts.rescannable === true) {
+      throw new TypeError(
+        `fromRecordBatchReader does not accept rescannable: true. ` +
+          `RecordBatchReader is a self-iterator (its [Symbol.iterator]() ` +
+          `returns itself) and would be exhausted after the first scan. ` +
+          `Use fromFactory(schema, () => openReader(), { rescannable: true }) ` +
+          `for sources where each call mints a fresh reader.`,
+      );
+    }
+    return Scannable.fromFactory(reader.schema, () => reader, {
+      numRows: opts.numRows,
+      rescannable: false,
+    });
+  }
+}
+
+function normalizeIterator<T>(
+  source: AsyncIterable<T> | Iterable<T> | AsyncIterator<T> | Iterator<T>,
+): AsyncIterator<T> | Iterator<T> {
+  if (source == null) {
+    throw new TypeError("Scannable factory returned null/undefined");
+  }
+  if (
+    typeof (source as AsyncIterable<T>)[Symbol.asyncIterator] === "function"
+  ) {
+    return (source as AsyncIterable<T>)[Symbol.asyncIterator]();
+  }
+  if (typeof (source as Iterable<T>)[Symbol.iterator] === "function") {
+    return (source as Iterable<T>)[Symbol.iterator]();
+  }
+  // Already an iterator (has `.next`).
+  if (typeof (source as Iterator<T>).next === "function") {
+    return source as Iterator<T>;
+  }
+  throw new TypeError("Scannable factory returned a non-iterable value");
+}
+
+// A "self-iterator" returns the same object from `[Symbol.iterator]()` /
+// `[Symbol.asyncIterator]()`. Generators behave this way, so they exhaust
+// after one pass. Replayable iterables (Array, Set, custom) return a fresh
+// iterator each call. Detection mirrors `normalizeIterator`'s ordering so
+// classification matches scan-time behavior.
+function isOneShotIterable(
+  source: AsyncIterable<unknown> | Iterable<unknown>,
+): boolean {
+  // null/undefined are not one-shot in any meaningful sense; let
+  // `normalizeIterator` raise the actual error at scan time.
+  if (source == null) return false;
+  const ref = source as unknown;
+  if (
+    typeof (source as AsyncIterable<unknown>)[Symbol.asyncIterator] ===
+    "function"
+  ) {
+    const it = (source as AsyncIterable<unknown>)[
+      Symbol.asyncIterator
+    ]() as unknown;
+    return it === ref;
+  }
+  if (typeof (source as Iterable<unknown>)[Symbol.iterator] === "function") {
+    const it = (source as Iterable<unknown>)[Symbol.iterator]() as unknown;
+    return it === ref;
+  }
+  // Already-an-iterator (has `.next` but no `Symbol.iterator`) is by
+  // definition one-shot.
+  if (typeof (source as { next?: unknown }).next === "function") return true;
+  return false;
+}

nodejs/lancedb/table.ts

@@ -5,12 +5,15 @@ import {
   Table as ArrowTable,
   Data,
   DataType,
+  Field,
   IntoVector,
   MultiVector,
   Schema,
   dataTypeToJson,
   fromDataToBuffer,
+  fromTableToBuffer,
   isMultiVector,
+  makeEmptyTable,
   tableFromIPC,
 } from "./arrow";
 
@@ -43,6 +46,33 @@ import { sanitizeType } from "./sanitize";
 import { IntoSql, toSQL } from "./util";
 export { IndexConfig } from "./native";
 
+/**
+ * Progress snapshot for a write operation, delivered to the `progress`
+ * callback passed to {@link Table.add}.
+ */
+export interface WriteProgress {
+  /** Number of rows written so far. */
+  outputRows: number;
+  /** Number of bytes written so far. */
+  outputBytes: number;
+  /**
+   * Total rows expected, when the input source reports it.
+   *
+   * Always set on the final callback (the one with `done: true`), falling
+   * back to the actual number of rows written when the source could not
+   * report a row count up front.
+   */
+  totalRows?: number;
+  /** Wall-clock seconds since the write started. */
+  elapsedSeconds: number;
+  /** Number of parallel write tasks currently in flight. */
+  activeTasks: number;
+  /** Total number of parallel write tasks (the write parallelism). */
+  totalTasks: number;
+  /** `true` for the final callback; `false` otherwise. */
+  done: boolean;
+}
+
 /**
  * Options for adding data to a table.
  */
@@ -53,6 +83,28 @@ export interface AddDataOptions {
    * If "overwrite" then the new data will replace the existing data in the table.
    */
   mode: "append" | "overwrite";
+
+  /**
+   * Optional callback invoked periodically with write progress.
+   *
+   * The callback is fired once per batch written and once more with
+   * `done: true` when the write completes. Calls are dispatched
+   * asynchronously to the JS event loop and never block the write — a slow
+   * callback will queue events rather than back-pressure the writer.
+   *
+   * Errors thrown from the callback are logged with `console.warn` and
+   * swallowed — they do not abort the write.
+   *
+   * @example
+   * ```ts
+   * await table.add(data, {
+   *   progress: (p) => {
+   *     console.log(`${p.outputRows}/${p.totalRows ?? "?"} rows`);
+   *   },
+   * });
+   * ```
+   */
+  progress: (progress: WriteProgress) => void;
 }
 
 export interface UpdateOptions {
@@ -84,6 +136,16 @@ export interface OptimizeOptions {
    * tbl.optimize({cleanupOlderThan: new Date()});
    */
   cleanupOlderThan: Date;
+  /**
+   * Because they may be part of an in-progress transaction, files newer than
+   * 7 days old are not deleted by default. If you are sure that there are no
+   * in-progress transactions, then you can set this to true to delete all
+   * files older than `cleanupOlderThan`.
+   *
+   * **WARNING**: This should only be set to true if you can guarantee that
+   * no other process is currently working on this dataset. Otherwise the
+   * dataset could be put into a corrupted state.
+   */
   deleteUnverified: boolean;
 }
 
@@ -93,6 +155,27 @@ export interface Version {
   metadata: Record<string, string>;
 }
 
+/**
+ * Specification selecting Lance's MemWAL LSM-style write path for
+ * `mergeInsert`.
+ *
+ * `specType` is `"bucket"`, `"identity"`, or `"unsharded"`. For `"bucket"`,
+ * `column` and `numBuckets` are required; for `"identity"`, `column` is
+ * required.
+ */
+export interface LsmWriteSpec {
+  /** One of `"bucket"`, `"identity"`, or `"unsharded"`. */
+  specType: "bucket" | "identity" | "unsharded";
+  /** Bucket and identity variants: the sharding column. */
+  column?: string;
+  /** Bucket variant: the number of buckets, in `[1, 1024]`. */
+  numBuckets?: number;
+  /** Names of indexes the MemWAL should keep up to date during writes. */
+  maintainedIndexes?: string[];
+  /** Default `ShardWriter` configuration recorded in the MemWAL index. */
+  writerConfigDefaults?: Record<string, string>;
+}
+
 /**
  * A Table is a collection of Records in a LanceDB Database.
  *
@@ -272,6 +355,25 @@ export abstract class Table {
    */
   abstract prewarmIndex(name: string): Promise<void>;
 
+  /**
+   * Prewarm one or more columns of data in the table.
+   *
+   * @param columns The columns to prewarm. If undefined, all columns are prewarmed.
+   *
+   * This will load the column data into the page cache so that future queries that
+   * read those columns avoid the initial cold-start latency.  This call initiates
+   * prewarming and returns once the request is accepted; the warming itself may
+   * continue in the background.  Calling it on already-prewarmed columns is a
+   * no-op on the server.
+   *
+   * Prewarming is generally useful for columns used in filters or projections.
+   * Large columns (e.g. high-dimensional vectors or binary data) may not be
+   * practical to prewarm.
+   *
+   * This feature is currently only supported on remote tables.
+   */
+  abstract prewarmData(columns?: string[]): Promise<void>;
+
   /**
    * Waits for asynchronous indexing to complete on the table.
    *
@@ -381,15 +483,16 @@ export abstract class Table {
   abstract vectorSearch(vector: IntoVector | MultiVector): VectorQuery;
   /**
    * Add new columns with defined values.
-   * @param {AddColumnsSql[]} newColumnTransforms pairs of column names and
-   * the SQL expression to use to calculate the value of the new column. These
-   * expressions will be evaluated for each row in the table, and can
-   * reference existing columns in the table.
+   * @param {AddColumnsSql[] | Field | Field[] | Schema} newColumnTransforms Either:
+   *   - An array of objects with column names and SQL expressions to calculate values
+   *   - A single Arrow Field defining one column with its data type (column will be initialized with null values)
+   *   - An array of Arrow Fields defining columns with their data types (columns will be initialized with null values)
+   *   - An Arrow Schema defining columns with their data types (columns will be initialized with null values)
    * @returns {Promise<AddColumnsResult>} A promise that resolves to an object
    * containing the new version number of the table after adding the columns.
    */
   abstract addColumns(
-    newColumnTransforms: AddColumnsSql[],
+    newColumnTransforms: AddColumnsSql[] | Field | Field[] | Schema,
   ): Promise<AddColumnsResult>;
 
   /**
@@ -416,6 +519,54 @@ export abstract class Table {
    * containing the new version number of the table after dropping the columns.
    */
   abstract dropColumns(columnNames: string[]): Promise<DropColumnsResult>;
+  /**
+   * Set the unenforced primary key for this table to a single column.
+   *
+   * "Unenforced" means LanceDB does not check uniqueness on writes; the
+   * column is recorded in the schema as the primary key for use by features
+   * such as `merge_insert`. Only single-column primary keys are supported,
+   * and the key cannot be changed once set.
+   * @param {string | string[]} columns The primary key column. A one-element
+   * array is also accepted; passing more than one column is rejected.
+   * @returns {Promise<void>}
+   */
+  abstract setUnenforcedPrimaryKey(columns: string | string[]): Promise<void>;
+  /**
+   * Install an {@link LsmWriteSpec} on this table, selecting Lance's MemWAL
+   * LSM-style write path for future `mergeInsert` calls.
+   *
+   * `LsmWriteSpec` chooses one of three sharding strategies via `specType`:
+   *
+   * - `"bucket"` — hash-bucket writes by the single-column unenforced primary
+   *   key (`column` and `numBuckets` required).
+   * - `"identity"` — shard by the raw value of a scalar `column`.
+   * - `"unsharded"` — route every write to a single shard.
+   *
+   * All variants require the table to have an unenforced primary key
+   * ({@link Table#setUnenforcedPrimaryKey}); bucket sharding additionally
+   * requires it to be the single column being bucketed.
+   * @param {LsmWriteSpec} spec The sharding spec to install.
+   * @returns {Promise<void>}
+   * @example
+   * ```ts
+   * await table.setUnenforcedPrimaryKey("id");
+   * await table.setLsmWriteSpec({
+   *   specType: "bucket",
+   *   column: "id",
+   *   numBuckets: 16,
+   *   maintainedIndexes: ["id_idx"],
+   * });
+   * ```
+   */
+  abstract setLsmWriteSpec(spec: LsmWriteSpec): Promise<void>;
+  /**
+   * Remove the {@link LsmWriteSpec} from this table, reverting to the standard
+   * `mergeInsert` write path.
+   *
+   * Errors if no spec is currently set.
+   * @returns {Promise<void>}
+   */
+  abstract unsetLsmWriteSpec(): Promise<void>;
   /** Retrieve the version of the table */
 
   abstract version(): Promise<number>;
@@ -501,19 +652,7 @@ export abstract class Table {
    *  - Index: Optimizes the indices, adding new data to existing indices
    *
    *
-   *  Experimental API
-   *  ----------------
-   *
-   *  The optimization process is undergoing active development and may change.
-   *  Our goal with these changes is to improve the performance of optimization and
-   *  reduce the complexity.
-   *
-   *  That being said, it is essential today to run optimize if you want the best
-   *  performance.  It should be stable and safe to use in production, but it our
-   *  hope that the API may be simplified (or not even need to be called) in the
-   *  future.
-   *
-   *  The frequency an application shoudl call optimize is based on the frequency of
+   *  The frequency an application should call optimize is based on the frequency of
    *  data modifications.  If data is frequently added, deleted, or updated then
    *  optimize should be run frequently.  A good rule of thumb is to run optimize if
    *  you have added or modified 100,000 or more records or run more than 20 data
@@ -615,7 +754,20 @@ export class LocalTable extends Table {
     const schema = await this.schema();
 
     const buffer = await fromDataToBuffer(data, undefined, schema);
-    return await this.inner.add(buffer, mode);
+    // Wrap the user callback so a thrown error doesn't surface as an
+    // unhandled exception (the callback fires from a napi threadsafe
+    // function — exceptions there crash the process).
+    const userProgress = options?.progress;
+    const progress = userProgress
+      ? (p: WriteProgress) => {
+          try {
+            userProgress(p);
+          } catch (e) {
+            console.warn("Table.add progress callback threw:", e);
+          }
+        }
+      : undefined;
+    return await this.inner.add(buffer, mode, progress);
   }
 
   async update(
@@ -708,6 +860,10 @@ export class LocalTable extends Table {
     await this.inner.prewarmIndex(name);
   }
 
+  async prewarmData(columns?: string[]): Promise<void> {
+    await this.inner.prewarmData(columns);
+  }
+
   async waitForIndex(
     indexNames: string[],
     timeoutSeconds: number,
@@ -806,9 +962,40 @@ export class LocalTable extends Table {
   // TODO: Support BatchUDF
 
   async addColumns(
-    newColumnTransforms: AddColumnsSql[],
+    newColumnTransforms: AddColumnsSql[] | Field | Field[] | Schema,
   ): Promise<AddColumnsResult> {
-    return await this.inner.addColumns(newColumnTransforms);
+    // Handle single Field -> convert to array of Fields
+    if (newColumnTransforms instanceof Field) {
+      newColumnTransforms = [newColumnTransforms];
+    }
+
+    // Handle array of Fields -> convert to Schema
+    if (
+      Array.isArray(newColumnTransforms) &&
+      newColumnTransforms.length > 0 &&
+      newColumnTransforms[0] instanceof Field
+    ) {
+      const fields = newColumnTransforms as Field[];
+      newColumnTransforms = new Schema(fields);
+    }
+
+    // Handle Schema -> use schema-based approach
+    if (newColumnTransforms instanceof Schema) {
+      const schema = newColumnTransforms;
+      // Convert schema to buffer using Arrow IPC format
+      const emptyTable = makeEmptyTable(schema);
+      const schemaBuf = await fromTableToBuffer(emptyTable);
+      return await this.inner.addColumnsWithSchema(schemaBuf);
+    }
+
+    // Handle SQL expressions (existing functionality)
+    if (Array.isArray(newColumnTransforms)) {
+      return await this.inner.addColumns(
+        newColumnTransforms as AddColumnsSql[],
+      );
+    }
+
+    throw new Error("Invalid input type for addColumns");
   }
 
   async alterColumns(
@@ -841,6 +1028,19 @@ export class LocalTable extends Table {
     return await this.inner.dropColumns(columnNames);
   }
 
+  async setUnenforcedPrimaryKey(columns: string | string[]): Promise<void> {
+    const cols = typeof columns === "string" ? [columns] : columns;
+    return await this.inner.setUnenforcedPrimaryKey(cols);
+  }
+
+  async setLsmWriteSpec(spec: LsmWriteSpec): Promise<void> {
+    return await this.inner.setLsmWriteSpec(spec);
+  }
+
+  async unsetLsmWriteSpec(): Promise<void> {
+    return await this.inner.unsetLsmWriteSpec();
+  }
+
   async version(): Promise<number> {
     return await this.inner.version();
   }

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.27.0-beta.3",
+	"version": "0.29.1-beta.0",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.27.0-beta.3",
+	"version": "0.29.1-beta.0",
 	"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": "0.27.0-beta.3",
+	"version": "0.29.1-beta.0",
 	"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": "0.27.0-beta.3",
+	"version": "0.29.1-beta.0",
 	"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": "0.27.0-beta.3",
+	"version": "0.29.1-beta.0",
 	"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": "0.27.0-beta.3",
+  "version": "0.29.1-beta.0",
   "os": [
     "win32"
   ],

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.27.0-beta.3",
+	"version": "0.29.1-beta.0",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.27.0-beta.3",
+  "version": "0.29.1-beta.0",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",
@@ -38,15 +38,15 @@
     "url": "https://github.com/lancedb/lancedb"
   },
   "devDependencies": {
-    "@aws-sdk/client-dynamodb": "^3.33.0",
-    "@aws-sdk/client-kms": "^3.33.0",
-    "@aws-sdk/client-s3": "^3.33.0",
+    "@aws-sdk/client-dynamodb": "3.1003.0",
+    "@aws-sdk/client-kms": "3.1003.0",
+    "@aws-sdk/client-s3": "3.1003.0",
     "@biomejs/biome": "^1.7.3",
     "@jest/globals": "^29.7.0",
-    "@napi-rs/cli": "^3.5.1",
+    "@napi-rs/cli": "3.5.1",
     "@types/axios": "^0.14.0",
     "@types/jest": "^29.1.2",
-    "@types/node": "^22.7.4",
+    "@types/node": "22.7.4",
     "@types/tmp": "^0.2.6",
     "apache-arrow-15": "npm:apache-arrow@15.0.0",
     "apache-arrow-16": "npm:apache-arrow@16.0.0",
@@ -57,9 +57,9 @@
     "shx": "^0.3.4",
     "tmp": "^0.2.3",
     "ts-jest": "^29.1.2",
-    "typedoc": "^0.26.4",
-    "typedoc-plugin-markdown": "^4.2.1",
-    "typescript": "^5.5.4",
+    "typedoc": "0.26.4",
+    "typedoc-plugin-markdown": "4.2.1",
+    "typescript": "5.5.4",
     "typescript-eslint": "^7.1.0"
   },
   "ava": {
@@ -68,16 +68,16 @@
   "engines": {
     "node": ">= 18"
   },
+  "packageManager": "pnpm@11.1.1",
   "cpu": ["x64", "arm64"],
   "os": ["darwin", "linux", "win32"],
   "scripts": {
     "artifacts": "napi artifacts",
     "build:debug": "napi build --platform --dts ../lancedb/native.d.ts --js ../lancedb/native.js --output-dir lancedb",
-    "postbuild:debug": "shx mkdir -p dist && shx cp lancedb/*.node dist/",
+    "postbuild:debug": "shx mkdir -p dist && shx cp lancedb/*.node dist/ && node -e \"require('fs').writeFileSync('dist/package.json', JSON.stringify({name:'@lancedb/lancedb',type:'commonjs'}))\"",
     "build:release": "napi build --platform --release --dts ../lancedb/native.d.ts --js ../lancedb/native.js --output-dir dist",
-    "postbuild:release": "shx mkdir -p dist && shx cp lancedb/*.node dist/",
-    "build": "npm run build:debug && npm run tsc",
-    "build-release": "npm run build:release && npm run tsc",
+    "build": "pnpm build:debug && pnpm tsc",
+    "build-release": "pnpm build:release && pnpm tsc",
     "tsc": "tsc -b",
     "posttsc": "shx cp lancedb/native.d.ts dist/native.d.ts",
     "lint-ci": "biome ci .",
@@ -87,7 +87,7 @@
     "lint-fix": "biome check --write . && biome format --write .",
     "prepublishOnly": "napi prepublish -t npm",
     "test": "jest --verbose",
-    "integration": "S3_TEST=1 npm run test",
+    "integration": "S3_TEST=1 pnpm test",
     "universal": "napi universalize",
     "version": "napi version"
   },
@@ -95,8 +95,8 @@
     "reflect-metadata": "^0.2.2"
   },
   "optionalDependencies": {
-    "@huggingface/transformers": "^3.0.2",
-    "openai": "^4.29.2"
+    "@huggingface/transformers": "3.0.2",
+    "openai": "4.29.2"
   },
   "peerDependencies": {
     "apache-arrow": ">=15.0.0 <=18.1.0"

nodejs/pnpm-workspace.yaml

@@ -0,0 +1,18 @@
+# Flat node_modules layout. The @napi-rs/cli build step fails to locate
+# the cdylib artifact under pnpm's isolated layout; the hoisted linker
+# mirrors npm's structure and unblocks the native build.
+nodeLinker: hoisted
+
+# Block resolution of versions less than 24h old (Shai-Hulud window).
+# This is the pnpm 11 default but pinned here so it's visible to
+# reviewers and survives a future pnpm major flipping the default.
+minimumReleaseAge: 1440
+
+# Fail install if a transitive dep tries to run an unapproved script.
+strictDepBuilds: true
+
+allowBuilds:
+  '@biomejs/biome': true
+  onnxruntime-node: true
+  protobufjs: true
+  sharp: true