chore: update lance dependency to v8.0.0-beta.7

2026-08-26 16:08:43 +00:00 · 2026-06-08 20:51:28 +00:00
258 changed files with 3583 additions and 33767 deletions
@@ -1,20 +0,0 @@
-{
-  "name": "lancedb",
-  "interface": {
-    "displayName": "LanceDB"
-  },
-  "plugins": [
-    {
-      "name": "lancedb",
-      "source": {
-        "source": "local",
-        "path": "./plugins/lancedb"
-      },
-      "policy": {
-        "installation": "AVAILABLE",
-        "authentication": "ON_INSTALL"
-      },
-      "category": "Developer Tools"
-    }
-  ]
-}
@@ -5,7 +5,3 @@ This directory contains repo-scoped code agent skills for the LanceDB project.
 Each skill is a folder that contains a required `SKILL.md` and optional bundled resources.

 Codex discovers skills from `.agents/skills` in the current working directory and parent directories.
-
-The `lancedb` skill lives in the `plugins/lancedb` plugin (see `plugins/lancedb/skills/lancedb`)
-so it can be installed via the plugin marketplaces (`.claude-plugin/marketplace.json` and
-`.agents/plugins/marketplace.json`); the `lancedb` entry here is a symlink into that plugin.
@@ -1 +0,0 @@
-../../plugins/lancedb/skills/lancedb
@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.37.1-beta.0"
+current_version = "0.30.1-beta.2"
 parse = """(?x)
    (?P<major>0|[1-9]\\d*)\\.
    (?P<minor>0|[1-9]\\d*)\\.
@@ -23,8 +23,6 @@ allow_dirty = true
 commit = true
 message = "Bump version: {current_version} → {new_version}"
 commit_args = ""
-# bump-my-version >=1.4.0 rejects pre_commit_hooks containing shell syntax unless opted in.
-allow_shell_hooks = true

 # Java maven files
 pre_commit_hooks = [
@@ -75,13 +73,6 @@ filename = "nodejs/Cargo.toml"
 replace = "\nversion = \"{new_version}\""
 search = "\nversion = \"{current_version}\""

-# The Python package takes its version from here (pyproject.toml declares
-# `dynamic = ["version"]`, so maturin reads it out of the crate manifest).
-[[tool.bumpversion.files]]
-filename = "python/Cargo.toml"
-replace = "\nversion = \"{new_version}\""
-search = "\nversion = \"{current_version}\""
-
 # Java documentation
 [[tool.bumpversion.files]]
 filename = "docs/src/java/java.md"
@@ -1,19 +0,0 @@
-{
-  "name": "lancedb",
-  "owner": {
-    "name": "LanceDB"
-  },
-  "description": "LanceDB plugins for Claude Code.",
-  "plugins": [
-    {
-      "name": "lancedb",
-      "source": "./plugins/lancedb",
-      "description": "Write, review, debug, and document LanceDB pipelines in Python and TypeScript that work across local LanceDB OSS tables and remote LanceDB Enterprise/Cloud tables.",
-      "version": "0.1.0",
-      "author": {
-        "name": "LanceDB"
-      },
-      "category": "development"
-    }
-  ]
-}
@@ -27,31 +27,19 @@ runs:
          # Extract failed job names
          FAILED_JOBS=$(echo "$JOB_RESULTS" | jq -r 'to_entries | map(select(.value.result == "failure")) | map(.key) | join(", ")')

-          TITLE="$WORKFLOW_NAME Failed ($FAILED_JOBS)"
-
-          # This action now also runs on nightly schedules, so a breakage that
-          # persists for a few days would otherwise file one issue per night.
-          # Comment on the open report instead when one already exists.
-          EXISTING=$(gh issue list --state open --label ci --limit 100 --json number,title \
-            | jq -r --arg title "$TITLE" 'map(select(.title == $title)) | .[0].number // empty')
-
-          if [ -n "$EXISTING" ]; then
-            gh issue comment "$EXISTING" --body "Failed again: $RUN_URL"
-            echo "Commented on existing issue #$EXISTING"
-          else
-            gh issue create \
-              --title "$TITLE" \
-              --body "The workflow **$WORKFLOW_NAME** failed during execution.
+          # Create issue with workflow name, failed jobs, and run URL
+          gh issue create \
+            --title "$WORKFLOW_NAME Failed ($FAILED_JOBS)" \
+            --body "The workflow **$WORKFLOW_NAME** failed during execution.

        **Failed jobs:** $FAILED_JOBS

        **Run URL:** $RUN_URL

        Please investigate the failed jobs and address any issues." \
-              --label "ci"
+            --label "ci"

-            echo "Issue created successfully"
-          fi
+          echo "Issue created successfully"
        else
          echo "No job failures detected, skipping issue creation"
        fi
@@ -18,14 +18,6 @@ inputs:
    description: "The manylinux version to build for"
    required: false
    default: "2_17"
-  package-name:
-    description: "Override [project] name in python/pyproject.toml (e.g. 'lancedb-compat'). Default keeps 'lancedb'."
-    required: false
-    default: "lancedb"
-  rustflags:
-    description: "RUSTFLAGS for the build container, as a single whitespace-free token (e.g. '-Ctarget-cpu=x86-64-v2'). Empty leaves RUSTFLAGS unset, keeping the defaults from .cargo/config.toml."
-    required: false
-    default: ""
 runs:
  using: "composite"
  steps:
@@ -35,18 +27,6 @@ runs:
        ARM_BUILD: ${{ inputs.arm-build }}
      run: |
        echo "ARM BUILD: $ARM_BUILD"
-    - name: Patch package name for variant build
-      if: ${{ inputs.package-name != 'lancedb' }}
-      shell: bash
-      env:
-        PACKAGE_NAME: ${{ inputs.package-name }}
-      run: |
-        # Swap the [project] name so this build produces e.g. lancedb-compat
-        # wheels. The package still installs files under the lancedb/
-        # namespace -- import lancedb still works after pip install.
-        sed -i.bak 's/^name = "lancedb"$/name = "'"$PACKAGE_NAME"'"/' python/pyproject.toml
-        rm -f python/pyproject.toml.bak
-        grep '^name = ' python/pyproject.toml
    - name: Build x86_64 Manylinux wheel
      if: ${{ inputs.arm-build == 'false' }}
      uses: PyO3/maturin-action@v1
@@ -54,16 +34,15 @@ runs:
        maturin-version: "1.12.4"
        command: build
        working-directory: python
-        docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/' -e PROTOC=/usr/local/bin/protoc ${{ inputs.rustflags != '' && format('-e RUSTFLAGS={0}', inputs.rustflags) || '' }}"
+        docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/'"
        target: x86_64-unknown-linux-gnu
        manylinux: ${{ inputs.manylinux }}
        args: ${{ inputs.args }}
        before-script-linux: |
          set -e
-          curl -fsSL https://github.com/protocolbuffers/protobuf/releases/download/v24.4/protoc-24.4-linux-x86_64.zip -o /tmp/protoc.zip
-          unzip /tmp/protoc.zip -d /usr/local
-          rm /tmp/protoc.zip
-          /usr/local/bin/protoc --version
+          curl -L https://github.com/protocolbuffers/protobuf/releases/download/v24.4/protoc-24.4-linux-$(uname -m).zip > /tmp/protoc.zip \
+            && unzip /tmp/protoc.zip -d /usr/local \
+            && rm /tmp/protoc.zip
    - name: Build Arm Manylinux Wheel
      if: ${{ inputs.arm-build == 'true' }}
      uses: PyO3/maturin-action@v1
@@ -71,14 +50,13 @@ runs:
        maturin-version: "1.12.4"
        command: build
        working-directory: python
-        docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/' -e PROTOC=/usr/local/bin/protoc ${{ inputs.rustflags != '' && format('-e RUSTFLAGS={0}', inputs.rustflags) || '' }}"
+        docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/'"
        target: aarch64-unknown-linux-gnu
        manylinux: ${{ inputs.manylinux }}
        args: ${{ inputs.args }}
        before-script-linux: |
          set -e
-          yum install -y clang
-          curl -fsSL https://github.com/protocolbuffers/protobuf/releases/download/v24.4/protoc-24.4-linux-aarch_64.zip -o /tmp/protoc.zip
-          unzip /tmp/protoc.zip -d /usr/local
-          rm /tmp/protoc.zip
-          /usr/local/bin/protoc --version
+          yum install -y clang \
+            && curl -L https://github.com/protocolbuffers/protobuf/releases/download/v24.4/protoc-24.4-linux-aarch_64.zip > /tmp/protoc.zip \
+            && unzip /tmp/protoc.zip -d /usr/local \
+            && rm /tmp/protoc.zip
@@ -6,6 +6,7 @@ on:
      # We don't publish pre-releases for Rust. Crates.io is just a source
      # distribution, so we don't need to publish pre-releases.
      - "v*-beta*"
+      - "*-v*" # for example, python-vX.Y.Z

 env:
  # This env var is used by Swatinem/rust-cache@v2 for the cache
@@ -24,7 +25,7 @@ jobs:
    # Only runs on tags that matches the make-release action
    if: startsWith(github.ref, 'refs/tags/v')
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
      - uses: Swatinem/rust-cache@v2
        with:
          workspaces: rust
@@ -46,7 +47,7 @@ jobs:
      contents: read
      issues: write
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
      - uses: ./.github/actions/create-failure-issue
        with:
          job-results: ${{ toJSON(needs) }}
@@ -36,14 +36,14 @@ jobs:
          echo "guidelines = ${{ inputs.guidelines }}"

      - name: Checkout Repo
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
        with:
          ref: ${{ inputs.branch }}
          fetch-depth: 0
          persist-credentials: true

      - name: Set up Node.js
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v4
        with:
          # pnpm 11 (used by the nodejs install step below) requires
          # Node >= 22.13; use 24 since 22 hits EOL in October.
@@ -82,7 +82,7 @@ jobs:
          cache: maven

      - name: Setup pnpm
-        uses: pnpm/action-setup@v6
+        uses: pnpm/action-setup@v4
        with:
          version: 11.1.1
      - name: Install Node.js dependencies for TypeScript bindings
@@ -30,13 +30,13 @@ jobs:
          echo "tag = ${{ inputs.tag || 'latest' }}"

      - name: Checkout Repo LanceDB
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
        with:
          fetch-depth: 0
          persist-credentials: true

      - name: Set up Node.js
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v4
        with:
          node-version: 20

@@ -27,7 +27,7 @@ jobs:
    name: Verify PR title / description conforms to semantic-release
    runs-on: ubuntu-latest
    steps:
-      - uses: actions/setup-node@v6
+      - uses: actions/setup-node@v4
        with:
          node-version: "18"
      # These rules are disabled because Github will always ensure there
@@ -35,7 +35,7 @@ jobs:
    runs-on: ubuntu-24.04
    steps:
      - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
      - name: Install dependencies needed for ubuntu
        run: |
          sudo apt install -y protobuf-compiler libssl-dev
@@ -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@v6
+        uses: actions/setup-node@v4
        with:
          node-version: 20
          cache: 'npm'
@@ -1,85 +0,0 @@
-name: GitHub Release
-
-# All SDKs share one version, so a single `vX.Y.Z` tag produces a single GitHub
-# release covering all of them. The per-package publish workflows (PyPI, NPM,
-# Cargo, Maven) trigger off the same tag independently.
-
-on:
-  push:
-    tags:
-      - "v*"
-
-permissions:
-  contents: read
-
-jobs:
-  gh-release:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: write
-    steps:
-      - uses: actions/checkout@v6
-        with:
-          fetch-depth: 0
-          lfs: true
-      - name: Extract version
-        id: extract_version
-        env:
-          GITHUB_REF: ${{ github.ref }}
-        run: |
-          set -e
-          echo "Extracting tag and version from $GITHUB_REF"
-          if [[ $GITHUB_REF =~ refs/tags/v(.*) ]]; then
-            VERSION=${BASH_REMATCH[1]}
-            TAG=v$VERSION
-            echo "tag=$TAG" >> $GITHUB_OUTPUT
-            echo "version=$VERSION" >> $GITHUB_OUTPUT
-          else
-            echo "Failed to extract version from $GITHUB_REF"
-            exit 1
-          fi
-          echo "Extracted version $VERSION from $GITHUB_REF"
-          if [[ $VERSION =~ beta ]]; then
-            echo "This is a beta release"
-            echo "prerelease=true" >> $GITHUB_OUTPUT
-
-            # Get last release (that is not this one)
-            FROM_TAG=$(git tag --sort='version:refname' \
-              | grep ^v \
-              | grep -vF "$TAG" \
-              | python ci/semver_sort.py v \
-              | tail -n 1)
-          else
-            echo "This is a stable release"
-            echo "prerelease=false" >> $GITHUB_OUTPUT
-            # Get last stable tag (ignore betas)
-            FROM_TAG=$(git tag --sort='version:refname' \
-              | grep ^v \
-              | grep -vF "$TAG" \
-              | grep -v beta \
-              | python ci/semver_sort.py v \
-              | tail -n 1)
-          fi
-          echo "Found from tag $FROM_TAG"
-          echo "from_tag=$FROM_TAG" >> $GITHUB_OUTPUT
-      - name: Create Release Notes
-        id: release_notes
-        uses: mikepenz/release-changelog-builder-action@v4
-        with:
-          configuration: .github/release_notes.json
-          toTag: ${{ steps.extract_version.outputs.tag }}
-          fromTag: ${{ steps.extract_version.outputs.from_tag }}
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      - name: Create GH release
-        uses: softprops/action-gh-release@v2
-        with:
-          # Marking betas as pre-releases keeps them from taking the "Latest"
-          # badge on the releases page.
-          prerelease: ${{ steps.extract_version.outputs.prerelease }}
-          make_latest: ${{ steps.extract_version.outputs.prerelease == 'false' }}
-          tag_name: ${{ steps.extract_version.outputs.tag }}
-          token: ${{ secrets.GITHUB_TOKEN }}
-          generate_release_notes: false
-          name: LanceDB v${{ steps.extract_version.outputs.version }}
-          body: ${{ steps.release_notes.outputs.changelog }}
@@ -32,7 +32,7 @@ jobs:
        working-directory: ./java
    steps:
      - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
      - name: Set up Java 8
        uses: actions/setup-java@v4
        with:
@@ -73,7 +73,7 @@ jobs:
      contents: read
      issues: write
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
      - uses: ./.github/actions/create-failure-issue
        with:
          job-results: ${{ toJSON(needs) }}
@@ -36,7 +36,7 @@ jobs:
        working-directory: ./java
    steps:
      - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
      - name: Set up Java 17
        uses: actions/setup-java@v4
        with:
@@ -19,7 +19,7 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - name: Check out code
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
      - name: Install license-header-checker
        working-directory: /tmp
        run: |
@@ -1,14 +1,13 @@
 name: Create release commit

-# This workflow increments the version, tags it, and pushes it. All SDKs share
-# a single version, so one tag releases all of them.
+# This workflow increments versions, tags the version, and pushes it.
 # When a tag is pushed, another workflow is triggered that creates a GH release
 # and uploads the binaries. This workflow is only for creating the tag.

 # This script will enforce that a minor version is incremented if there are any
-# breaking changes since the last minor increment. A breaking change in any SDK
-# bumps the minor version for all of them. If you wish to bypass this check, you
-# can manually increment the version and push the tag.
+# breaking changes since the last minor increment. However, it isn't able to
+# differentiate between breaking changes in Node versus Python. If you wish to
+# bypass this check, you can manually increment the version and push the tag.
 on:
  workflow_dispatch:
    inputs:
@@ -25,6 +24,16 @@ on:
        options:
          - preview
          - stable
+      python:
+        description: 'Make a Python release'
+        required: true
+        default: true
+        type: boolean
+      other:
+        description: 'Make a Node/Rust/Java release'
+        required: true
+        default: true
+        type: boolean
      bump-minor:
        description: 'Bump minor version'
        required: true
@@ -40,7 +49,7 @@ jobs:
    steps:
      - name: Output Inputs
        run: echo "${{ toJSON(github.event.inputs) }}"
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
          lfs: true
@@ -56,16 +65,29 @@ jobs:
        run: |
          git config user.name 'Lance Release'
          git config user.email 'lance-dev@lancedb.com'
-      - name: Bump version
+      - name: Bump Python version
+        if: ${{ inputs.python }}
+        working-directory: python
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          # Need to get the commit before bumping the version, so we can
+          # determine if there are breaking changes in the next step as well.
+          echo "COMMIT_BEFORE_BUMP=$(git rev-parse HEAD)" >> $GITHUB_ENV
+
+          pip install bump-my-version PyGithub packaging
+          bash ../ci/bump_version.sh ${{ inputs.type }} ${{ inputs.bump-minor }} python-v
+      - name: Bump Node/Rust version
+        if: ${{ inputs.other }}
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        run: |
          pip install bump-my-version PyGithub packaging
-          bash ci/bump_version.sh ${{ inputs.type }} ${{ inputs.bump-minor }}
+          bash ci/bump_version.sh ${{ inputs.type }} ${{ inputs.bump-minor }} v $COMMIT_BEFORE_BUMP
          bash ci/update_lockfiles.sh --amend
      - name: Push new version tag
        if: ${{ !inputs.dry_run }}
-        uses: ad-m/github-push-action@881a6320fdb16eb5318c5054f31c218aec2b324c # v1.3.0
+        uses: ad-m/github-push-action@master
        with:
          # Need to use PAT here too to trigger next workflow. See comment above.
          github_token: ${{ secrets.LANCEDB_RELEASE_TOKEN }}
@@ -38,14 +38,14 @@ jobs:
      CC: gcc-12
      CXX: g++-12
    steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
      with:
        fetch-depth: 0
        lfs: true
-    - uses: pnpm/action-setup@v6
+    - uses: pnpm/action-setup@v4
      with:
        version: 11.1.1
-    - uses: actions/setup-node@v6
+    - 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
@@ -61,11 +61,6 @@ jobs:
        sudo apt update
        sudo apt install -y protobuf-compiler libssl-dev
    - uses: Swatinem/rust-cache@v2
-      with:
-        # Restore everywhere, but only save from main. Per-PR saves are
-        # unreadable outside their own branch anyway, since GitHub scopes
-        # caches to the creating ref.
-        save-if: ${{ github.ref == 'refs/heads/main' }}
    - name: Format Rust
      run: cargo fmt --all -- --check
    - name: Lint Rust
@@ -91,14 +86,14 @@ jobs:
        shell: bash
        working-directory: nodejs
    steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
      with:
        fetch-depth: 0
        lfs: true
-    - uses: pnpm/action-setup@v6
+    - uses: pnpm/action-setup@v4
      with:
        version: 11.1.1
-    - uses: actions/setup-node@v6
+    - 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
@@ -108,11 +103,6 @@ jobs:
        cache: 'pnpm'
        cache-dependency-path: nodejs/pnpm-lock.yaml
    - uses: Swatinem/rust-cache@v2
-      with:
-        # Restore everywhere, but only save from main. Per-PR saves are
-        # unreadable outside their own branch anyway, since GitHub scopes
-        # caches to the creating ref.
-        save-if: ${{ github.ref == 'refs/heads/main' }}
    - name: Install dependencies
      run: |
        sudo apt update
@@ -140,7 +130,7 @@ jobs:
          echo "Run 'pnpm run docs', fix any warnings, and commit the changes."
          exit 1
        fi
-    - uses: actions/setup-node@v6
+    - uses: actions/setup-node@v4
      name: Setup Node.js ${{ matrix.node-version }} for test
      with:
        node-version: ${{ matrix.node-version }}
@@ -176,14 +166,14 @@ jobs:
        shell: bash
        working-directory: nodejs
    steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
      with:
        fetch-depth: 0
        lfs: true
-    - uses: pnpm/action-setup@v6
+    - uses: pnpm/action-setup@v4
      with:
        version: 11.1.1
-    - uses: actions/setup-node@v6
+    - uses: actions/setup-node@v4
      with:
        # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
        # in October.
@@ -192,11 +182,6 @@ jobs:
        cache-dependency-path: nodejs/pnpm-lock.yaml
    - uses: dtolnay/rust-toolchain@stable
    - uses: Swatinem/rust-cache@v2
-      with:
-        # Restore everywhere, but only save from main. Per-PR saves are
-        # unreadable outside their own branch anyway, since GitHub scopes
-        # caches to the creating ref.
-        save-if: ${{ github.ref == 'refs/heads/main' }}
    - name: Install dependencies
      run: |
        brew install protobuf
@@ -10,16 +10,10 @@ permissions:

 on:
  push:
+    branches:
+      - main
    tags:
      - "v*"
-  # The cross-compiled targets (musl especially) break from toolchain and
-  # dependency changes that nothing else in CI catches, and discovering that
-  # mid-release is expensive. A nightly run keeps that signal while dropping
-  # the full 8-target release matrix from all ~90 pushes to main each month.
-  # `report-failure` files an issue when a nightly breaks.
-  schedule:
-    - cron: "0 8 * * *"
-  workflow_dispatch:
  pull_request:
    # This should trigger a dry run (we skip the final publish step)
    paths:
@@ -32,6 +26,73 @@ concurrency:
  cancel-in-progress: true

 jobs:
+  gh-release:
+    if: startsWith(github.ref, 'refs/tags/v')
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          lfs: true
+      - name: Extract version
+        id: extract_version
+        env:
+          GITHUB_REF: ${{ github.ref }}
+        run: |
+          set -e
+          echo "Extracting tag and version from $GITHUB_REF"
+          if [[ $GITHUB_REF =~ refs/tags/v(.*) ]]; then
+            VERSION=${BASH_REMATCH[1]}
+            TAG=v$VERSION
+            echo "tag=$TAG" >> $GITHUB_OUTPUT
+            echo "version=$VERSION" >> $GITHUB_OUTPUT
+          else
+            echo "Failed to extract version from $GITHUB_REF"
+            exit 1
+          fi
+          echo "Extracted version $VERSION from $GITHUB_REF"
+          if [[ $VERSION =~ beta ]]; then
+            echo "This is a beta release"
+
+            # Get last release (that is not this one)
+            FROM_TAG=$(git tag --sort='version:refname' \
+              | grep ^v \
+              | grep -vF "$TAG" \
+              | python ci/semver_sort.py v \
+              | tail -n 1)
+          else
+            echo "This is a stable release"
+            # Get last stable tag (ignore betas)
+            FROM_TAG=$(git tag --sort='version:refname' \
+              | grep ^v \
+              | grep -vF "$TAG" \
+              | grep -v beta \
+              | python ci/semver_sort.py v \
+              | tail -n 1)
+          fi
+          echo "Found from tag $FROM_TAG"
+          echo "from_tag=$FROM_TAG" >> $GITHUB_OUTPUT
+      - name: Create Release Notes
+        id: release_notes
+        uses: mikepenz/release-changelog-builder-action@v4
+        with:
+          configuration: .github/release_notes.json
+          toTag: ${{ steps.extract_version.outputs.tag }}
+          fromTag: ${{ steps.extract_version.outputs.from_tag }}
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+      - name: Create GH release
+        uses: softprops/action-gh-release@v2
+        with:
+          prerelease: ${{ contains('beta', github.ref) }}
+          tag_name: ${{ steps.extract_version.outputs.tag }}
+          token: ${{ secrets.GITHUB_TOKEN }}
+          generate_release_notes: false
+          name: Node/Rust LanceDB v${{ steps.extract_version.outputs.version }}
+          body: ${{ steps.release_notes.outputs.changelog }}
+
  build-lancedb:
    strategy:
      fail-fast: false
@@ -40,18 +101,9 @@ jobs:
          - target: aarch64-apple-darwin
            host: macos-latest
            features: fp16kernels
-            pre_build: |-
-              brew install protobuf
-              # Fat LTO (the workspace default in .cargo/config.toml) is
-              # single-threaded and is the peak-memory step of the build. On
-              # this runner it accounted for ~111 of the job's ~113 minutes,
-              # making it the critical path of the entire publish pipeline.
-              # ThinLTO parallelizes it across the runner's cores, for a few
-              # percent of runtime performance.
-              export CARGO_PROFILE_RELEASE_LTO=thin
-              export CARGO_PROFILE_RELEASE_CODEGEN_UNITS=16
+            pre_build: brew install protobuf
          - target: x86_64-pc-windows-msvc
-            host: windows-2025
+            host: windows-latest
            features: ","
            pre_build: |-
              choco install --no-progress protoc ninja nasm
@@ -59,21 +111,12 @@ jobs:
              # There is an issue where choco doesn't add nasm to the path
              export PATH="$PATH:/c/Program Files/NASM"
              nasm -v
-              # See the ThinLTO note on aarch64-apple-darwin above. Keeping
-              # peak memory down is also what lets this run on the standard
-              # 4-core runner: the 8-core larger runner was only needed to
-              # stop fat LTO from OOMing rustc-LLVM.
-              export CARGO_PROFILE_RELEASE_LTO=thin
-              export CARGO_PROFILE_RELEASE_CODEGEN_UNITS=16
          - target: aarch64-pc-windows-msvc
-            host: windows-2025
+            host: windows-latest
            features: ","
            pre_build: |-
                choco install --no-progress protoc
                rustup target add aarch64-pc-windows-msvc
-                # See the ThinLTO note on aarch64-apple-darwin above.
-                export CARGO_PROFILE_RELEASE_LTO=thin
-                export CARGO_PROFILE_RELEASE_CODEGEN_UNITS=16
          - target: x86_64-unknown-linux-gnu
            host: ubuntu-latest
            features: fp16kernels
@@ -127,13 +170,13 @@ jobs:
      run:
        working-directory: nodejs
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
      - name: Setup pnpm
-        uses: pnpm/action-setup@v6
+        uses: pnpm/action-setup@v4
        with:
          version: 11.1.1
      - name: Setup node
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v4
        with:
          # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
          # in October.
@@ -146,49 +189,16 @@ jobs:
        with:
          toolchain: stable
          targets: ${{ matrix.settings.target }}
-      # These builds were entirely uncached: the old key was static, so
-      # `actions/cache` (which only writes on a miss) could never refresh it,
-      # and the multi-GB whole-`target/` copy it tried to store never fit the
-      # repo's cache budget, so no entry was ever saved. rust-cache prunes
-      # `target/` to dependency artifacts and keys on Cargo.lock plus the rustc
-      # version, which both fixes the key and keeps entries a sane size.
-      #
-      # This caches dependency *compilation* only. The LTO link of the cdylib
-      # re-runs regardless, since the local crate changes every time, so the
-      # win is larger on the non-LTO jobs than here.
-      - name: Cache cargo (native builds)
-        uses: Swatinem/rust-cache@v2
-        if: ${{ !matrix.settings.docker }}
+      - name: Cache cargo
+        uses: actions/cache@v4
        with:
-          # The release profile and per-target dirs differ from what the test
-          # workflows cache, so these need to be separate entries.
-          key: release-${{ matrix.settings.target }}
-          # Only the nightly run on main writes, so tag and PR runs restore a
-          # warm entry without every dependabot PR writing its own (which would
-          # be unreadable elsewhere anyway, since GitHub scopes caches to the
-          # creating ref). The nightly cadence also keeps entries inside
-          # GitHub's 7-day eviction window, which a tag-only trigger would not.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
-      # Docker builds can use rust-cache too. `target/` already lives on the
-      # host because the whole workspace is bind-mounted into the container, and
-      # rust-cache's prune and save run host-side, so they can manage it -- which
-      # is what keeps the entry to dependency artifacts rather than a multi-GB
-      # copy of everything.
-      #
-      # Two differences from the native builds. The container's CARGO_HOME is
-      # bind-mounted from `.cargo-cache` rather than the host's ~/.cargo, so that
-      # has to be cached explicitly. And the key is derived from the *host* rustc
-      # version, which is not the compiler that produced these artifacts; that is
-      # safe because cargo fingerprints the real compiler and rebuilds on a
-      # mismatch, it just means a base-image toolchain bump costs one cold build
-      # instead of invalidating the key.
-      - name: Cache cargo (docker builds)
-        uses: Swatinem/rust-cache@v2
-        if: ${{ matrix.settings.docker }}
-        with:
-          key: docker-${{ matrix.settings.target }}
-          cache-directories: .cargo-cache
-          save-if: ${{ github.ref == 'refs/heads/main' }}
+          path: |
+            ~/.cargo/registry/index/
+            ~/.cargo/registry/cache/
+            ~/.cargo/git/db/
+            .cargo-cache
+            target/
+          key: nodejs-${{ matrix.settings.target }}-cargo-${{ matrix.settings.host }}
      - name: Install dependencies
        run: pnpm install --frozen-lockfile
      - name: Install Zig
@@ -206,13 +216,9 @@ jobs:
        if: ${{ matrix.settings.docker }}
        with:
          image: ${{ matrix.settings.docker }}
-          # All three mounts must live under `.cargo-cache`, which is what the
-          # cache step above saves. Previously the registry mounts pointed at
-          # `.cargo/...`, a path nothing cached, so the container re-downloaded
-          # the whole crate registry on every run.
          options: "--user 0:0 -v ${{ github.workspace }}/.cargo-cache/git/db:/usr/local/cargo/git/db \
-                    -v ${{ github.workspace }}/.cargo-cache/registry/cache:/usr/local/cargo/registry/cache \
-                    -v ${{ github.workspace }}/.cargo-cache/registry/index:/usr/local/cargo/registry/index \
+                    -v ${{ github.workspace }}/.cargo/registry/cache:/usr/local/cargo/registry/cache \
+                    -v ${{ github.workspace }}/.cargo/registry/index:/usr/local/cargo/registry/index \
                    -v ${{ github.workspace }}:/build -w /build/nodejs"
          run: |
            set -e
@@ -224,16 +230,6 @@ jobs:
              --js ../lancedb/native.js \
              --strip \
              --output-dir dist/
-      # The container runs as root (`--user 0:0`), so everything it wrote to the
-      # mounted cache dirs is root-owned. rust-cache's post step runs as the
-      # runner user and has to both read these and delete from them while
-      # pruning, so hand them back before it runs.
-      - name: Take ownership of docker build output
-        if: ${{ matrix.settings.docker }}
-        run: |
-          sudo chown -R "$(id -u):$(id -g)" \
-            "${{ github.workspace }}/.cargo-cache" \
-            "${{ github.workspace }}/target"
      - name: Build
        run: |
          ${{ matrix.settings.pre_build }}
@@ -247,17 +243,8 @@ jobs:
              --output-dir dist/
        if: ${{ !matrix.settings.docker }}
        shell: bash
-      # The standard Windows runners have ~14 GB free, and a release `target/`
-      # for this workspace is a large fraction of that. Report the remaining
-      # headroom so a build that only just fits is visible before a dependency
-      # bump turns it into a failed release. `always()` so the numbers are
-      # still there when the build is what ran out of space.
-      - name: Report disk headroom
-        if: always()
-        run: df -h
-        shell: bash
      - name: Upload artifact
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v4
        with:
          name: lancedb-${{ matrix.settings.target }}
          path: nodejs/dist/*.node
@@ -269,7 +256,7 @@ jobs:
        run: pnpm tsc
      - name: Upload Generic Artifacts
        if: ${{ matrix.settings.target == 'aarch64-apple-darwin' }}
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v4
        with:
          name: nodejs-dist
          path: |
@@ -300,13 +287,13 @@ jobs:
        shell: bash
        working-directory: nodejs
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
      - name: Setup pnpm
-        uses: pnpm/action-setup@v6
+        uses: pnpm/action-setup@v4
        with:
          version: 11.1.1
      - name: Setup Node.js 24 for install
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v4
        with:
          # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
          # in October.
@@ -316,18 +303,18 @@ jobs:
      - name: Install dependencies
        run: pnpm install --frozen-lockfile
      - name: Setup Node.js ${{ matrix.node }} for test
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v4
        with:
          node-version: ${{ matrix.node }}
      - name: Download artifacts
-        uses: actions/download-artifact@v8
+        uses: actions/download-artifact@v4
        with:
          name: lancedb-${{ matrix.settings.target }}
          path: nodejs/dist/
          # For testing purposes:
          # run-id: 13982782871
          # github-token: ${{ secrets.GITHUB_TOKEN }} # token with actions:read permissions on target repo
-      - uses: actions/download-artifact@v8
+      - uses: actions/download-artifact@v4
        with:
          name: nodejs-dist
          path: nodejs/dist
@@ -352,13 +339,13 @@ jobs:
    needs:
      - test-lancedb
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
      - name: Setup pnpm
-        uses: pnpm/action-setup@v6
+        uses: pnpm/action-setup@v4
        with:
          version: 11.1.1
      - name: Setup node
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v4
        with:
          node-version: 24
          cache: pnpm
@@ -366,14 +353,14 @@ jobs:
          registry-url: "https://registry.npmjs.org"
      - name: Install dependencies
        run: pnpm install --frozen-lockfile
-      - uses: actions/download-artifact@v8
+      - uses: actions/download-artifact@v4
        with:
          name: nodejs-dist
          path: nodejs/dist
          # For testing purposes:
          # run-id: 13982782871
          # github-token: ${{ secrets.GITHUB_TOKEN }} # token with actions:read permissions on target repo
-      - uses: actions/download-artifact@v8
+      - uses: actions/download-artifact@v4
        name: Download arch-specific binaries
        with:
          pattern: lancedb-*
@@ -406,14 +393,12 @@ jobs:
    name: Report Workflow Failure
    runs-on: ubuntu-latest
    needs: [build-lancedb, test-lancedb, publish]
-    # Nightly runs are the only thing watching the cross-compiled targets now,
-    # so they have to report failures too or the signal is silently lost.
-    if: always() && failure() && (startsWith(github.ref, 'refs/tags/v') || github.event_name == 'schedule')
+    if: always() && failure() && startsWith(github.ref, 'refs/tags/v')
    permissions:
      contents: read
      issues: write
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
      - uses: ./.github/actions/create-failure-issue
        with:
          job-results: ${{ toJSON(needs) }}
@@ -3,7 +3,7 @@ name: PyPI Publish
 on:
  push:
    tags:
-      - 'v*'
+      - 'python-v*'
  pull_request:
    # This should trigger a dry run (we skip the final publish step)
    paths:
@@ -20,15 +20,9 @@ env:
 permissions:
  contents: read

-# Without this, a force-push to a PR leaves the previous run going -- including
-# a ~74 minute Windows job and a billed arm64 wheel build.
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
 jobs:
  linux:
-    name: Python ${{ matrix.config.package_name }} ${{ matrix.config.platform }} manylinux${{ matrix.config.manylinux }}
+    name: Python ${{ matrix.config.platform }} manylinux${{ matrix.config.manylinux }}
    timeout-minutes: 60
    strategy:
      matrix:
@@ -37,28 +31,11 @@ jobs:
            manylinux: "2_28"
            extra_args: "--features fp16kernels"
            runner: ubuntu-22.04
-            package_name: "lancedb"
-            rustflags: ""
          # For successful fat LTO builds, we need a large runner to avoid OOM errors.
          - platform: aarch64
            manylinux: "2_28"
            extra_args: "--features fp16kernels"
            runner: ubuntu-2404-8x-arm64
-            package_name: "lancedb"
-            rustflags: ""
-          # `lancedb-compat`: pre-Haswell-friendly variant for x86_64 hosts
-          # without AVX2 (Sandy Bridge / Ivy Bridge / Westmere on Intel,
-          # Bulldozer / Piledriver / Steamroller on AMD). Compiled at the
-          # `x86-64-v2` baseline; runtime SIMD dispatch in lance-linalg
-          # picks the appropriate tier (scalar / AVX / AVX+FMA / AVX2+FMA
-          # / AVX-512) at load time. Same import as `lancedb` -- conflicts
-          # at install time, so users pick one.
-          - platform: x86_64
-            manylinux: "2_28"
-            extra_args: ""
-            runner: ubuntu-22.04
-            package_name: "lancedb-compat"
-            rustflags: "-Ctarget-cpu=x86-64-v2"
    runs-on: ${{ matrix.config.runner }}
    steps:
      - uses: actions/checkout@v6
@@ -75,13 +52,11 @@ jobs:
          args: "--release --strip ${{ matrix.config.extra_args }}"
          arm-build: ${{ matrix.config.platform == 'aarch64' }}
          manylinux: ${{ matrix.config.manylinux }}
-          package-name: ${{ matrix.config.package_name }}
-          rustflags: ${{ matrix.config.rustflags }}
      - uses: actions/upload-artifact@v7
-        if: startsWith(github.ref, 'refs/tags/v')
+        if: startsWith(github.ref, 'refs/tags/python-v')
        with:
-          name: wheels-linux-${{ matrix.config.package_name }}-${{ matrix.config.platform }}-${{ matrix.config.manylinux }}
-          path: target/wheels/*.whl
+          name: wheels-linux-${{ matrix.config.platform }}-${{ matrix.config.manylinux }}
+          path: target/wheels/lancedb-*.whl
          if-no-files-found: error
  mac:
    timeout-minutes: 90
@@ -107,7 +82,7 @@ jobs:
          python-minor-version: 10
          args: "--release --strip --target ${{ matrix.config.target }} --features fp16kernels"
      - uses: actions/upload-artifact@v7
-        if: startsWith(github.ref, 'refs/tags/v')
+        if: startsWith(github.ref, 'refs/tags/python-v')
        with:
          name: wheels-mac-${{ matrix.config.target }}
          path: target/wheels/lancedb-*.whl
@@ -128,26 +103,19 @@ jobs:
        uses: actions/setup-python@v6
        with:
          python-version: "3.13"
-      # NOTE: caching cargo here would be a no-op. This workflow only runs on
-      # tags and PRs, and GitHub only lets a run restore caches from its own ref
-      # or the default branch -- so with no run on main there is nothing that
-      # can populate an entry the release build would be allowed to read. Fixing
-      # this needs a main/nightly trigger (which would also catch wheel-build
-      # breakage before a release); the ~74 minutes here is otherwise dominated
-      # by the fat-LTO link, which no cache avoids.
      - uses: ./.github/workflows/build_windows_wheel
        with:
          python-minor-version: 10
          args: "--release --strip"
      - uses: actions/upload-artifact@v7
-        if: startsWith(github.ref, 'refs/tags/v')
+        if: startsWith(github.ref, 'refs/tags/python-v')
        with:
          name: wheels-windows
          path: target/wheels/lancedb-*.whl
          if-no-files-found: error
  publish:
    name: Publish wheels
-    if: startsWith(github.ref, 'refs/tags/v')
+    if: startsWith(github.ref, 'refs/tags/python-v')
    needs: [linux, mac, windows]
    runs-on: ubuntu-latest
    permissions:
@@ -177,7 +145,7 @@ jobs:
          FURY_TOKEN: ${{ secrets.FURY_TOKEN }}
        run: |
          shopt -s nullglob
-          WHEELS=(target/wheels/*.whl)
+          WHEELS=(target/wheels/lancedb-*.whl)
          if [[ ${#WHEELS[@]} -eq 0 ]]; then
            echo "No wheels found in target/wheels/" >&2
            exit 1
@@ -196,6 +164,72 @@ jobs:
        uses: pypa/gh-action-pypi-publish@release/v1
        with:
          packages-dir: target/wheels/
+  gh-release:
+    if: startsWith(github.ref, 'refs/tags/python-v')
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          fetch-depth: 0
+          lfs: true
+      - name: Extract version
+        id: extract_version
+        env:
+          GITHUB_REF: ${{ github.ref }}
+        run: |
+          set -e
+          echo "Extracting tag and version from $GITHUB_REF"
+          if [[ $GITHUB_REF =~ refs/tags/python-v(.*) ]]; then
+            VERSION=${BASH_REMATCH[1]}
+            TAG=python-v$VERSION
+            echo "tag=$TAG" >> $GITHUB_OUTPUT
+            echo "version=$VERSION" >> $GITHUB_OUTPUT
+          else
+            echo "Failed to extract version from $GITHUB_REF"
+            exit 1
+          fi
+          echo "Extracted version $VERSION from $GITHUB_REF"
+          if [[ $VERSION =~ beta ]]; then
+            echo "This is a beta release"
+
+            # Get last release (that is not this one)
+            FROM_TAG=$(git tag --sort='version:refname' \
+              | grep ^python-v \
+              | grep -vF "$TAG" \
+              | python ci/semver_sort.py python-v \
+              | tail -n 1)
+          else
+            echo "This is a stable release"
+            # Get last stable tag (ignore betas)
+            FROM_TAG=$(git tag --sort='version:refname' \
+              | grep ^python-v \
+              | grep -vF "$TAG" \
+              | grep -v beta \
+              | python ci/semver_sort.py python-v \
+              | tail -n 1)
+          fi
+          echo "Found from tag $FROM_TAG"
+          echo "from_tag=$FROM_TAG" >> $GITHUB_OUTPUT
+      - name: Create Python Release Notes
+        id: python_release_notes
+        uses: mikepenz/release-changelog-builder-action@v4
+        with:
+          configuration: .github/release_notes.json
+          toTag: ${{ steps.extract_version.outputs.tag }}
+          fromTag: ${{ steps.extract_version.outputs.from_tag }}
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+      - name: Create Python GH release
+        uses: softprops/action-gh-release@v2
+        with:
+          prerelease: ${{ contains('beta', github.ref) }}
+          tag_name: ${{ steps.extract_version.outputs.tag }}
+          token: ${{ secrets.GITHUB_TOKEN }}
+          generate_release_notes: false
+          name: Python LanceDB v${{ steps.extract_version.outputs.version }}
+          body: ${{ steps.python_release_notes.outputs.changelog }}
  report-failure:
    name: Report Workflow Failure
    runs-on: ubuntu-latest
@@ -203,7 +237,7 @@ jobs:
    permissions:
      contents: read
      issues: write
-    if: always() && failure() && startsWith(github.ref, 'refs/tags/v')
+    if: always() && failure() && startsWith(github.ref, 'refs/tags/python-v')
    steps:
      - uses: actions/checkout@v6
      - uses: ./.github/actions/create-failure-issue
@@ -41,7 +41,7 @@ jobs:
        shell: bash
        working-directory: python
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
          lfs: true
@@ -66,7 +66,7 @@ jobs:
        shell: bash
        working-directory: python
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
          lfs: true
@@ -95,7 +95,7 @@ jobs:
        shell: bash
        working-directory: python
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
          lfs: true
@@ -108,15 +108,6 @@ jobs:
        run: |
          sudo apt update
          sudo apt install -y protobuf-compiler
-      # `pip install -e .` builds the extension with maturin, which is most of
-      # this job's ~33 minutes. It had no Rust cache, so every dependency was
-      # recompiled from scratch on every run.
-      - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
      - 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]
@@ -135,7 +126,7 @@ jobs:
        shell: bash
        working-directory: python
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
          lfs: true
@@ -169,7 +160,7 @@ jobs:
        shell: bash
        working-directory: python
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
          lfs: true
@@ -177,14 +168,6 @@ jobs:
        uses: actions/setup-python@v6
        with:
          python-version: "3.13"
-      # maturin runs cargo natively on macOS (docker is Linux-only), so the host
-      # target dir is cacheable. This job had no Rust cache.
-      - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
      - uses: ./.github/workflows/build_mac_wheel
        with:
          args: --profile ci
@@ -206,7 +189,7 @@ jobs:
        shell: bash
        working-directory: python
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
          lfs: true
@@ -214,14 +197,6 @@ jobs:
        uses: actions/setup-python@v6
        with:
          python-version: "3.13"
-      # maturin runs cargo natively on Windows (docker is Linux-only), so the
-      # host target dir is cacheable. This job had no Rust cache at all and so
-      # rebuilt every dependency from scratch on every run.
-      - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. The repo sits at
-          # GitHub's cache cap, so per-PR saves just evict main's entries.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
      - uses: ./.github/workflows/build_windows_wheel
        with:
          args: --profile ci
@@ -237,7 +212,7 @@ jobs:
        shell: bash
        working-directory: python
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
          lfs: true
@@ -249,14 +224,6 @@ jobs:
        uses: actions/setup-python@v6
        with:
          python-version: "3.10"
-      # As with Doctest, `pip install -e .` compiles the extension and this job
-      # had no Rust cache, which is most of its ~37 minutes.
-      - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
      - name: Install lancedb
        run: |
          pip install "pydantic<2"
@@ -40,7 +40,7 @@ jobs:
      CC: clang-18
      CXX: clang++-18
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
          lfs: true
@@ -48,11 +48,6 @@ jobs:
        with:
          components: rustfmt, clippy
      - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
      - name: Install dependencies
        run: |
          sudo apt update
@@ -70,7 +65,7 @@ jobs:
    timeout-minutes: 10
    runs-on: ubuntu-24.04
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
      - uses: EmbarkStudios/cargo-deny-action@v2
        with:
          command: check advisories bans licenses sources
@@ -83,7 +78,7 @@ jobs:
      CC: clang
      CXX: clang++
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
      # Building without a lock file often requires the latest Rust version since downstream
      # dependencies may have updated their minimum Rust version.
      - uses: actions-rust-lang/setup-rust-toolchain@v1
@@ -94,11 +89,6 @@ jobs:
        run: rm -f Cargo.lock
      - uses: rui314/setup-mold@v1
      - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
      - name: Install dependencies
        run: |
          sudo apt update
@@ -108,7 +98,7 @@ jobs:
          cargo build --profile ci --benches --all-features --tests

  linux:
-    timeout-minutes: 60
+    timeout-minutes: 30
    # To build all features, we need more disk space than is available
    # on the free OSS github runner. This is mostly due to the the
    # sentence-transformers feature.
@@ -123,16 +113,11 @@ jobs:
      CXX: clang++-18
      GH_TOKEN: ${{ secrets.SOPHON_READ_TOKEN }}
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
          lfs: true
      - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
      - name: Install dependencies
        run: |
          sudo apt update
@@ -140,26 +125,10 @@ jobs:
      - uses: rui314/setup-mold@v1
      - name: Make Swap
        run: |
-          swapfile=/swapfile
-          min_swap_bytes=$((15 * 1024 * 1024 * 1024))
-          active_swap_bytes="$(sudo swapon --show=NAME,SIZE --bytes --noheadings | awk '$1 == "/swapfile" { print $2 }')"
-          if [ -n "$active_swap_bytes" ]; then
-            if [ "$active_swap_bytes" -ge "$min_swap_bytes" ]; then
-              echo "/swapfile is already active with enough space; skipping swap creation"
-              exit 0
-            fi
-            echo "/swapfile is already active but smaller than 16G; using /mnt/lancedb-swapfile"
-            swapfile=/mnt/lancedb-swapfile
-          fi
-          if sudo swapon --show=NAME --noheadings | grep -Fxq "$swapfile"; then
-            echo "$swapfile is already active; skipping swap creation"
-            exit 0
-          fi
-          sudo rm -f "$swapfile"
-          sudo fallocate -l 16G "$swapfile"
-          sudo chmod 600 "$swapfile"
-          sudo mkswap "$swapfile"
-          sudo swapon "$swapfile"
+          sudo fallocate -l 16G /swapfile
+          sudo chmod 600 /swapfile
+          sudo mkswap /swapfile
+          sudo swapon /swapfile
      - name: Build
        run: cargo build --profile ci --all-features --tests --locked --examples
      - name: Run feature tests
@@ -173,7 +142,7 @@ jobs:
        run: CARGO_ARGS="--profile ci" make -C ./lancedb remote-tests

  macos:
-    timeout-minutes: 60
+    timeout-minutes: 30
    strategy:
      matrix:
        mac-runner: ["macos-14", "macos-15"]
@@ -183,18 +152,13 @@ jobs:
        shell: bash
        working-directory: rust
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
          lfs: true
      - name: CPU features
        run: sysctl -a | grep cpu
      - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
      - name: Install dependencies
        run: brew install protobuf
      - name: Run tests
@@ -207,32 +171,20 @@ jobs:
          cargo test --profile ci --features $ALL_FEATURES --locked

  windows:
+    runs-on: windows-2022
    strategy:
-      fail-fast: false
      matrix:
-        include:
-          - target: x86_64-pc-windows-msvc
-            runner: windows-2022
-          # windows-11-arm is a standard runner, so it is free on public repos.
-          # Running natively lets the aarch64 tests actually execute -- this
-          # job used to cross-compile them and then skip the test step, paying
-          # full codegen and link cost for a compile check.
-          - target: aarch64-pc-windows-msvc
-            runner: windows-11-arm
-    runs-on: ${{ matrix.runner }}
+        target:
+          - x86_64-pc-windows-msvc
+          - aarch64-pc-windows-msvc
    defaults:
      run:
        working-directory: rust/lancedb
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
      - name: Set target
        run: rustup target add ${{ matrix.target }}
      - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
      - name: Install Protoc v21.12
        run: choco install --no-progress protoc
      - name: Build
@@ -240,12 +192,11 @@ jobs:
          $env:VCPKG_ROOT = $env:VCPKG_INSTALLATION_ROOT
          cargo build --profile ci --features aws,remote --tests --locked --target ${{ matrix.target }}
      - name: Run tests
+        # Can only run tests when target matches host
+        if: ${{ matrix.target == 'x86_64-pc-windows-msvc' }}
        run: |
          $env:VCPKG_ROOT = $env:VCPKG_INSTALLATION_ROOT
-          # `--target` has to match the build step above. Without it cargo uses
-          # target/ci/ rather than target/<triple>/ci/ and rebuilds the entire
-          # dependency graph a second time.
-          cargo test --profile ci --features aws,remote --locked --target ${{ matrix.target }}
+          cargo test --profile ci --features aws,remote --locked

  msrv:
    # Check the minimum supported Rust version
@@ -259,7 +210,7 @@ jobs:
      CC: clang-18
      CXX: clang++-18
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
        with:
          submodules: true
      - name: Install dependencies
@@ -271,11 +222,6 @@ jobs:
        with:
          toolchain: ${{ matrix.msrv }}
      - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
      - name: Downgrade  dependencies
        # These packages have newer requirements for MSRV
        run: |
@@ -11,7 +11,7 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
        with:
          ref: main
          persist-credentials: false
@@ -11,7 +11,7 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
        with:
          ref: main
          persist-credentials: false
@@ -27,7 +27,6 @@ python/dist
 *.so
 *.dylib
 *.dll
-*.pdb

 ## Javascript
 *.node
@@ -92,8 +92,6 @@ Python bindings changes:
    * Should use `LOOP.run()` to call the corresponding `AsyncTable` method.
 6. Add concrete sync method to `RemoteTable` class in `python/python/lancedb/remote/table.py`.
 7. Add unit test in `python/tests/test_table.py`.
-8. If you added a new public class or module-level function (not just a method on an
-   existing class), expose it in the API reference. See "Python API reference" below.

 TypeScript bindings changes:

@@ -105,33 +103,6 @@ TypeScript bindings changes:
 5. Add test in `nodejs/__test__/table.test.ts`.
 6. Run `npm run docs` to generate TypeScript documentation.

-## Python API reference
-
-`docs/src/python/python.md` is the entire Python API reference. It is maintained by
-hand, and anything not listed there is not rendered at all, so new public classes and
-module-level functions have to be added explicitly. How depends on the module:
-
-* `lancedb.index`, `lancedb.embeddings`, `lancedb.remote`, and `lancedb.rerankers` are
-  rendered by a single directive each, driven by the module's `__all__`. Add the new
-  name to `__all__` and it appears; forget, and it is silently omitted.
-* Everything else (`lancedb`, `lancedb.table`, `lancedb.query`, `lancedb.db`, ...) is
-  listed symbol by symbol. Add a `::: lancedb.<module>.<Name>` line to the matching
-  section, and remember that the page separates synchronous and asynchronous APIs.
-
-Deliberately undocumented: concrete implementations reached through an abstract base
-(`LanceTable`, `LanceDBConnection`, `RemoteDBConnection`), query base classes already
-covered by `inherited_members`, and internal helpers.
-
-Cross-references in docstrings use mkdocstrings syntax, `[text][lancedb.table.Table]`.
-Plain relative links such as `[Table](Table)` do not resolve. To check your work:
-
-```shell
-pip install -r docs/requirements.txt
-cd docs && PYTHONPATH=. mkdocs build
-```
-
-The docs site only builds on pushes to `main`, so this is not covered by PR CI.
-
 ## Review Guidelines

 Please consider the following when reviewing code contributions.
@@ -13,25 +13,24 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"

 [workspace.dependencies]
-lance = { "version" = "=10.0.0-beta.5", default-features = false, "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=10.0.0-beta.5", default-features = false, "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=10.0.0-beta.5", default-features = false, "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=8.0.0-beta.7", default-features = false, "tag" = "v8.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=8.0.0-beta.7", "tag" = "v8.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=8.0.0-beta.7", "tag" = "v8.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=8.0.0-beta.7", "tag" = "v8.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=8.0.0-beta.7", default-features = false, "tag" = "v8.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=8.0.0-beta.7", "tag" = "v8.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=8.0.0-beta.7", "tag" = "v8.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=8.0.0-beta.7", "tag" = "v8.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=8.0.0-beta.7", default-features = false, "tag" = "v8.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=8.0.0-beta.7", "tag" = "v8.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=8.0.0-beta.7", "tag" = "v8.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=8.0.0-beta.7", "tag" = "v8.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=8.0.0-beta.7", "tag" = "v8.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=8.0.0-beta.7", "tag" = "v8.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
 ahash = "0.8"
 # Note that this one does not include pyarrow
 arrow = { version = "58.0.0", optional = false }
 arrow-array = "58.0.0"
-arrow-buffer = "58.0.0"
 arrow-data = "58.0.0"
 arrow-ipc = "58.0.0"
 arrow-ord = "58.0.0"
@@ -39,23 +38,21 @@ arrow-schema = "58.0.0"
 arrow-select = "58.0.0"
 arrow-cast = "58.0.0"
 async-trait = "0"
-datafusion = { version = "54.0.0", default-features = false }
-datafusion-catalog = "54.0.0"
-datafusion-common = { version = "54.0.0", default-features = false }
-datafusion-execution = "54.0.0"
-datafusion-expr = "54.0.0"
-datafusion-functions = "54.0.0"
-datafusion-physical-plan = "54.0.0"
-datafusion-physical-expr = "54.0.0"
-datafusion-sql = "54.0.0"
+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",
 ] }
 futures = "0"
 log = "0.4"
-metrics = "0.24"
-metrics-util = "0.19"
 moka = { version = "0.12", features = ["future"] }
 object_store = "0.13.2"
 pin-project = "1.0.7"
@@ -64,6 +61,7 @@ snafu = "0.8"
 url = "2"
 num-traits = "0.2"
 regex = "1.10"
+lazy_static = "1"
 semver = "1.0.25"
 chrono = "0.4"

@@ -2,9 +2,9 @@ set -e

 RELEASE_TYPE=${1:-"stable"}
 BUMP_MINOR=${2:-false}
-HEAD_SHA=$(git rev-parse HEAD)
+TAG_PREFIX=${3:-"v"} # Such as "python-v"
+HEAD_SHA=${4:-$(git rev-parse HEAD)}

-readonly TAG_PREFIX="v"
 readonly SELF_DIR=$(cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )

 PREV_TAG=$(git tag --sort='version:refname' | grep ^$TAG_PREFIX | python $SELF_DIR/semver_sort.py $TAG_PREFIX | tail -n 1)
@@ -12,7 +12,7 @@ echo "Found previous tag $PREV_TAG"

 # Initially, we don't want to tag if we are doing stable, because we will bump
 # again later. See comment at end for why.
-if [[ "$RELEASE_TYPE" == 'stable' ]]; then
+if [[ "$RELEASE_TYPE" == 'stable' ]]; then 
  BUMP_ARGS="--no-tag"
 fi

@@ -51,6 +51,18 @@ ignore = [
    # 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.
@@ -68,6 +80,18 @@ ignore = [
    # 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.
@@ -84,23 +108,11 @@ ignore = [
    # 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" },

-    # pyo3 advisories in the Python bindings; tracked pending a patched pyo3 release.
-    # https://rustsec.org/advisories/RUSTSEC-2026-0176
-    # https://rustsec.org/advisories/RUSTSEC-2026-0177
-    { id = "RUSTSEC-2026-0176", reason = "pyo3 in Python bindings; awaiting patched pyo3 release" },
-    { id = "RUSTSEC-2026-0177", reason = "pyo3 in Python bindings; awaiting patched pyo3 release" },
-
-    # quick-xml < 0.41.0: quadratic runtime on duplicate attribute names (DoS).
-    # quick-xml < 0.41.0: unbounded namespace-declaration allocation in NsReader (DoS).
-    # Pulled in transitively by inferno (dev-only flame-graph dep), lance-namespace-impls
-    # (git dep from lance), and opendal/reqsign (cloud storage XML parsing). The XML
-    # parsed by opendal/reqsign comes from trusted cloud-storage endpoints (S3, GCS,
-    # Azure), not attacker-controlled input. Clearing requires upstream crates to migrate
-    # to quick-xml >= 0.41.0.
-    # https://rustsec.org/advisories/RUSTSEC-2026-0194
-    # https://rustsec.org/advisories/RUSTSEC-2026-0195
-    { id = "RUSTSEC-2026-0194", reason = "transitive via inferno/lance/opendal; XML from trusted cloud endpoints, not attacker-controlled" },
-    { id = "RUSTSEC-2026-0195", reason = "transitive via inferno/lance/opendal; XML from trusted cloud endpoints, not attacker-controlled" },
+    # 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" },
 ]

 # ---------------------------------------------------------------------------
@@ -51,11 +51,6 @@ plugins:
          paths: [../python/python]
          options:
            docstring_style: numpy
-            docstring_options:
-              # Attributes documented in a `Parameters` section, and pydantic
-              # dataclasses whose `__init__` griffe cannot see statically, both
-              # trip this check. It reports nothing actionable here.
-              warn_unknown_params: false
            heading_level: 3
            show_signature_annotations: true
            show_root_heading: true
@@ -453,16 +453,6 @@ paths:
                    The metric type to use for the index. l2, Cosine, Dot are supported.
                index_type:
                  type: string
-                custom_stop_words:
-                  type: [array, "null"]
-                  items:
-                    type: string
-                  description: |
-                    The custom stop-word list for an FTS index. A non-null
-                    array replaces the language's built-in stop-word list and is only
-                    applied when remove_stop_words is enabled. Null uses the built-in
-                    language list, while an empty array explicitly replaces it with no
-                    stop words.
      responses:
        "200":
          description: Index successfully created
@@ -520,4 +510,4 @@ paths:
        "401":
          $ref: "#/components/responses/unauthorized"
        "404":
-          $ref: "#/components/responses/not_found"
+          $ref: "#/components/responses/not_found"
@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
 <dependency>
    <groupId>com.lancedb</groupId>
    <artifactId>lancedb-core</artifactId>
-    <version>0.37.1-beta.0</version>
+    <version>0.30.1-beta.2</version>
 </dependency>
 ```

@@ -249,57 +249,6 @@ try (BufferAllocator allocator = new RootAllocator();
 }
 ```

-### Creating an Empty Table
-
-To create an empty table, send an Arrow IPC stream that contains the table schema and no record batches.
-The schema in the IPC stream becomes the table schema, and rows can be inserted later.
-
-```java
-import org.lance.namespace.model.CreateTableRequest;
-import org.lance.namespace.model.CreateTableResponse;
-import org.apache.arrow.memory.BufferAllocator;
-import org.apache.arrow.memory.RootAllocator;
-import org.apache.arrow.vector.VectorSchemaRoot;
-import org.apache.arrow.vector.ipc.ArrowStreamWriter;
-import org.apache.arrow.vector.types.FloatingPointPrecision;
-import org.apache.arrow.vector.types.pojo.ArrowType;
-import org.apache.arrow.vector.types.pojo.Field;
-import org.apache.arrow.vector.types.pojo.FieldType;
-import org.apache.arrow.vector.types.pojo.Schema;
-
-import java.io.ByteArrayOutputStream;
-import java.nio.channels.Channels;
-import java.util.Arrays;
-
-Schema schema = new Schema(Arrays.asList(
-    new Field("id", FieldType.nullable(new ArrowType.Int(32, true)), null),
-    new Field("name", FieldType.nullable(new ArrowType.Utf8()), null),
-    new Field("embedding",
-        FieldType.nullable(new ArrowType.FixedSizeList(128)),
-        Arrays.asList(new Field("item",
-            FieldType.nullable(new ArrowType.FloatingPoint(FloatingPointPrecision.SINGLE)),
-            null)))
-));
-
-byte[] emptyTableData;
-try (BufferAllocator allocator = new RootAllocator();
-     VectorSchemaRoot root = VectorSchemaRoot.create(schema, allocator)) {
-    root.setRowCount(0);
-
-    ByteArrayOutputStream out = new ByteArrayOutputStream();
-    try (ArrowStreamWriter writer = new ArrowStreamWriter(root, null, Channels.newChannel(out))) {
-        writer.start();
-        writer.end();
-    }
-    emptyTableData = out.toByteArray();
-}
-
-CreateTableRequest request = new CreateTableRequest();
-request.setId(Arrays.asList("my_namespace", "empty_table"));
-
-CreateTableResponse response = namespaceClient.createTable(request, emptyTableData);
-```
-
 ### Insert

 ```java
@@ -482,88 +431,9 @@ query.setVector(vector);
 byte[] result = namespaceClient.queryTable(query);
 ```

-## Indexing
+### Reading Query Results

-The Java SDK exposes the REST namespace index operations through the same `LanceNamespace` client.
-Index creation runs asynchronously, so use `listTableIndices` or `describeTableIndexStats` to check progress.
-
-### Creating a Vector Index
-
-```java
-import org.lance.namespace.model.CreateTableIndexRequest;
-import org.lance.namespace.model.CreateTableIndexResponse;
-
-CreateTableIndexRequest request = new CreateTableIndexRequest();
-request.setId(Arrays.asList("my_namespace", "my_table"));
-request.setColumn("embedding");
-request.setIndexType("IVF_PQ");
-request.setDistanceType("cosine");
-request.setName("embedding_idx");
-
-CreateTableIndexResponse response = namespaceClient.createTableIndex(request);
-System.out.println("Index transaction: " + response.getTransactionId());
-```
-
-### Creating a Scalar Index
-
-```java
-import org.lance.namespace.model.CreateTableIndexRequest;
-import org.lance.namespace.model.CreateTableScalarIndexResponse;
-
-CreateTableIndexRequest request = new CreateTableIndexRequest();
-request.setId(Arrays.asList("my_namespace", "my_table"));
-request.setColumn("category");
-request.setIndexType("BTREE");
-request.setName("category_idx");
-
-CreateTableScalarIndexResponse response = namespaceClient.createTableScalarIndex(request);
-System.out.println("Index transaction: " + response.getTransactionId());
-```
-
-### Creating a Full Text Search Index
-
-```java
-import org.lance.namespace.model.CreateTableIndexRequest;
-import org.lance.namespace.model.CreateTableScalarIndexResponse;
-
-CreateTableIndexRequest request = new CreateTableIndexRequest();
-request.setId(Arrays.asList("my_namespace", "my_table"));
-request.setColumn("text_column");
-request.setIndexType("FTS");
-request.setName("text_idx");
-request.setBaseTokenizer("simple");
-request.setLowerCase(true);
-request.setWithPosition(true);
-
-CreateTableScalarIndexResponse response = namespaceClient.createTableScalarIndex(request);
-System.out.println("Index transaction: " + response.getTransactionId());
-```
-
-### Listing Indexes
-
-```java
-import org.lance.namespace.model.IndexContent;
-import org.lance.namespace.model.ListTableIndicesRequest;
-import org.lance.namespace.model.ListTableIndicesResponse;
-
-ListTableIndicesRequest request = new ListTableIndicesRequest();
-request.setId(Arrays.asList("my_namespace", "my_table"));
-
-ListTableIndicesResponse response = namespaceClient.listTableIndices(request);
-for (IndexContent index : response.getIndexes()) {
-    System.out.println(index.getIndexName() + ": " + index.getStatus());
-}
-```
-
-!!! note
-    The current Java namespace API exposes index type, index name, distance type, and full text search tokenizer options.
-    IVF training parameters such as `num_partitions` are not exposed by `CreateTableIndexRequest` yet.
-    To make those configurable from Java, the namespace API must add those fields first.
-
-## Reading Query Results
-
-Query results are returned as bytes in Apache Arrow IPC file format. Put the byte-channel
-adapter behind a small helper so query code can work with `ArrowFileReader` directly:
+Query results are returned in Apache Arrow IPC file format. Here's how to read them:

 ```java
 import org.apache.arrow.vector.ipc.ArrowFileReader;
@@ -571,50 +441,45 @@ import org.apache.arrow.vector.VectorSchemaRoot;
 import org.apache.arrow.memory.BufferAllocator;
 import org.apache.arrow.memory.RootAllocator;

-import java.io.IOException;
 import java.nio.ByteBuffer;
 import java.nio.channels.SeekableByteChannel;

-final class ArrowIpc {
-    static ArrowFileReader openFileReader(byte[] data, BufferAllocator allocator) throws IOException {
-        return new ArrowFileReader(new ByteArraySeekableByteChannel(data), allocator);
+// Helper class to read Arrow data from byte array
+class ByteArraySeekableByteChannel implements SeekableByteChannel {
+    private final byte[] data;
+    private long position = 0;
+    private boolean isOpen = true;
+
+    public ByteArraySeekableByteChannel(byte[] data) {
+        this.data = data;
    }

-    private static final class ByteArraySeekableByteChannel implements SeekableByteChannel {
-        private final byte[] data;
-        private long position = 0;
-        private boolean isOpen = true;
-
-        private ByteArraySeekableByteChannel(byte[] data) {
-            this.data = data;
-        }
-
-        @Override
-        public int read(ByteBuffer dst) {
-            int remaining = dst.remaining();
-            int available = (int) (data.length - position);
-            if (available <= 0) return -1;
-            int toRead = Math.min(remaining, available);
-            dst.put(data, (int) position, toRead);
-            position += toRead;
-            return toRead;
-        }
-
-        @Override public long position() { return position; }
-        @Override public SeekableByteChannel position(long newPosition) { position = newPosition; return this; }
-        @Override public long size() { return data.length; }
-        @Override public boolean isOpen() { return isOpen; }
-        @Override public void close() { isOpen = false; }
-        @Override public int write(ByteBuffer src) { throw new UnsupportedOperationException(); }
-        @Override public SeekableByteChannel truncate(long size) { throw new UnsupportedOperationException(); }
+    @Override
+    public int read(ByteBuffer dst) {
+        int remaining = dst.remaining();
+        int available = (int) (data.length - position);
+        if (available <= 0) return -1;
+        int toRead = Math.min(remaining, available);
+        dst.put(data, (int) position, toRead);
+        position += toRead;
+        return toRead;
    }
+
+    @Override public long position() { return position; }
+    @Override public SeekableByteChannel position(long newPosition) { position = newPosition; return this; }
+    @Override public long size() { return data.length; }
+    @Override public boolean isOpen() { return isOpen; }
+    @Override public void close() { isOpen = false; }
+    @Override public int write(ByteBuffer src) { throw new UnsupportedOperationException(); }
+    @Override public SeekableByteChannel truncate(long size) { throw new UnsupportedOperationException(); }
 }

 // Read query results
 byte[] queryResult = namespaceClient.queryTable(query);

 try (BufferAllocator allocator = new RootAllocator();
-     ArrowFileReader reader = ArrowIpc.openFileReader(queryResult, allocator)) {
+     ArrowFileReader reader = new ArrowFileReader(
+         new ByteArraySeekableByteChannel(queryResult), allocator)) {

    for (int i = 0; i < reader.getRecordBlocks().size(); i++) {
        reader.loadRecordBatch(reader.getRecordBlocks().get(i));
@@ -1,7 +1,7 @@
 # Contributing to LanceDB Typescript

 This document outlines the process for contributing to LanceDB Typescript.
-For general contribution guidelines, see [CONTRIBUTING.md](https://github.com/lancedb/lancedb/blob/main/CONTRIBUTING.md).
+For general contribution guidelines, see [CONTRIBUTING.md](../CONTRIBUTING.md).

 ## Project layout

@@ -1,43 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / BranchContents
-
-# Class: BranchContents
-
-## Constructors
-
-### new BranchContents()
-
-```ts
-new BranchContents(): BranchContents
-```
-
-#### Returns
-
-[`BranchContents`](BranchContents.md)
-
-## Properties
-
-### manifestSize
-
-```ts
-manifestSize: number;
-```
-
-***
-
-### parentBranch?
-
-```ts
-optional parentBranch: string;
-```
-
-***
-
-### parentVersion
-
-```ts
-parentVersion: number;
-```
@@ -1,139 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / Branches
-
-# Class: Branches
-
-Branch manager for a [Table](Table.md).
-
-Unlike tags, `create` and `checkout` return a new [Table](Table.md) handle scoped
-to the branch; writes on it do not affect `main`.
-
-## Methods
-
-### checkout()
-
-```ts
-checkout(name, version?): Promise<Table>
-```
-
-Check out an existing branch and return a handle scoped to it.
-
-With `version` set, the returned handle is pinned to that version of the
-branch (a read-only, detached view); otherwise it tracks the branch's
-latest and stays writable.
-
-#### Parameters
-
-* **name**: `string`
-
-* **version?**: `number`
-
-#### Returns
-
-`Promise`&lt;[`Table`](Table.md)&gt;
-
-***
-
-### create()
-
-```ts
-create(
-   name,
-   fromRef?,
-   fromVersion?): Promise<Table>
-```
-
-Create a branch and return a handle scoped to it.
-
-#### Parameters
-
-* **name**: `string`
-    Name of the new branch.
-
-* **fromRef?**: `string`
-    Source branch to fork from. Defaults to `main`.
-
-* **fromVersion?**: `number`
-    A specific version on `fromRef`. Defaults to latest.
-
-#### Returns
-
-`Promise`&lt;[`Table`](Table.md)&gt;
-
-***
-
-### delete()
-
-```ts
-delete(name): Promise<void>
-```
-
-Delete a branch.
-
-#### Parameters
-
-* **name**: `string`
-
-#### Returns
-
-`Promise`&lt;`void`&gt;
-
-***
-
-### diff()
-
-```ts
-diff(fromBranch): Promise<BranchDiff>
-```
-
-Compare a branch against main without modifying either branch.
-
-#### Parameters
-
-* **fromBranch**: `string`
-
-#### Returns
-
-`Promise`&lt;[`BranchDiff`](../interfaces/BranchDiff.md)&gt;
-
-***
-
-### list()
-
-```ts
-list(): Promise<Record<string, BranchContents>>
-```
-
-List all branches, mapping name to branch metadata.
-
-#### Returns
-
-`Promise`&lt;`Record`&lt;`string`, [`BranchContents`](BranchContents.md)&gt;&gt;
-
-***
-
-### merge()
-
-```ts
-merge(fromBranch, dryRun): Promise<MergeBranchResult>
-```
-
-Merge a branch into main.
-
-Set `dryRun` to `true` to preview the merge. A rejected merge resolves
-with `status: "rejected"` instead of throwing.
-
-#### Parameters
-
-* **fromBranch**: `string`
-    Branch to merge from.
-
-* **dryRun**: `boolean` = `false`
-    When true, only preview the merge. Defaults to false.
-
-#### Returns
-
-`Promise`&lt;[`MergeBranchResult`](../interfaces/MergeBranchResult.md)&gt;
@@ -57,24 +57,6 @@ block size may be added in the future.

 ***

-### fm()
-
-```ts
-static fm(): Index
-```
-
-Create an FM-Index.
-
-An FM-Index is a scalar index on string or binary columns that accelerates
-substring search, i.e. `contains(col, 'needle')`. Unlike the tokenized
-full-text-search index, it matches arbitrary substrings of the raw bytes.
-
-#### Returns
-
-[`Index`](Index.md)
-
-***
-
 ### fts()

 ```ts
@@ -76,23 +76,24 @@ the query optimizer chooses a suboptimal path.

 ***

-### useLsm()
+### useLsmWrite()

 ```ts
-useLsm(enable): MergeInsertBuilder
+useLsmWrite(useLsmWrite): MergeInsertBuilder
 ```

-Control MemWAL routing for this merge.
+Controls whether the merge uses the MemWAL LSM write path.

 By default (unset), a `mergeInsert` on a table with an LSM write spec is
-routed through Lance's MemWAL shard writer, and a table without one uses the
-standard path.
+routed through Lance's MemWAL shard writer, and a table without one uses
+the standard path. Pass `false` to force the standard path even when a
+spec is set. Pass `true` to require a spec — `mergeInsert` rejects if none
+is installed.

 #### Parameters

-* **enable**: `boolean`
-    `true` forces MemWAL routing and errors if the table has no
-    LSM write spec. `false` forces the standard write path even when a spec is set.
+* **useLsmWrite**: `boolean`
+    Whether to use the LSM write path.

 #### Returns

@@ -33,7 +33,7 @@ protected inner: Query | Promise<Query>;
 ### analyzePlan()

 ```ts
-analyzePlan(distributedMetrics?): Promise<string>
+analyzePlan(): Promise<string>
 ```

 Executes the query and returns the physical query plan annotated with runtime metrics.
@@ -41,12 +41,6 @@ Executes the query and returns the physical query plan annotated with runtime me
 This is useful for debugging and performance analysis, as it shows how the query was executed
 and includes metrics such as elapsed time, rows processed, and I/O statistics.

-#### Parameters
-
-* **distributedMetrics?**: [`AnalyzePlanDistributedMetrics`](../type-aliases/AnalyzePlanDistributedMetrics.md)
-    How distributed worker metrics are displayed for remote query plans.
-    Defaults to `"aggregate"`.
-
 #### Returns

 `Promise`&lt;`string`&gt;
@@ -497,42 +491,6 @@ ArrowTable.

 ***

-### useLsm()
-
-```ts
-useLsm(enable): this
-```
-
-Control MemWAL read routing for this query.
-
-By default (unset), when the table carries a MemWAL write spec (see
-[Table#setLsmWriteSpec](Table.md#setlsmwritespec)), reads are routed through the LSM scanner so
-they also return data written via the `mergeInsert` LSM path that has not yet
-been compacted into the base table (the active/frozen in-memory memtables and
-the flushed generations), deduplicated by primary key; a table without a spec
-reads the base table.
-
-#### Parameters
-
-* **enable**: `boolean`
-    `true` forces the LSM scanner and errors if the table has no
-    MemWAL write spec. `false` bypasses the MemWAL and reads the base table only,
-    even when a spec is present.
-    Note: the LSM scanner does not support every query shape (e.g. reranking,
-    hybrid search, `orderBy`). On a MemWAL table those shapes error unless
-    `useLsm(false)` is set, because a base-only read would silently exclude
-    un-compacted MemWAL data.
-
-#### Returns
-
-`this`
-
-#### Inherited from
-
-`StandardQueryBase.useLsm`
-
-***
-
 ### where()

 ```ts
@@ -560,9 +518,6 @@ x > 5 OR y = 'test'

 Filtering performance can often be improved by creating a scalar index
 on the filter column(s).
-
-Calling this multiple times combines the filters with a logical AND rather
-than replacing the previous filter.
 ```

 #### Inherited from
@@ -38,7 +38,7 @@ protected inner: NativeQueryType | Promise<NativeQueryType>;
 ### analyzePlan()

 ```ts
-analyzePlan(distributedMetrics?): Promise<string>
+analyzePlan(): Promise<string>
 ```

 Executes the query and returns the physical query plan annotated with runtime metrics.
@@ -46,12 +46,6 @@ Executes the query and returns the physical query plan annotated with runtime me
 This is useful for debugging and performance analysis, as it shows how the query was executed
 and includes metrics such as elapsed time, rows processed, and I/O statistics.

-#### Parameters
-
-* **distributedMetrics?**: [`AnalyzePlanDistributedMetrics`](../type-aliases/AnalyzePlanDistributedMetrics.md)
-    How distributed worker metrics are displayed for remote query plans.
-    Defaults to `"aggregate"`.
-
 #### Returns

 `Promise`&lt;`string`&gt;
@@ -110,23 +110,6 @@ containing the new version number of the table after altering the columns.

 ***

-### branches()
-
-```ts
-abstract branches(): Promise<Branches>
-```
-
-Get the branch manager for this table.
-
-Branches are isolated, writable lines of history forked from another
-branch (or version). Writes on a branch do not affect `main`.
-
-#### Returns
-
-`Promise`&lt;[`Branches`](Branches.md)&gt;
-
-***
-
 ### checkout()

 ```ts
@@ -295,23 +278,6 @@ await table.createIndex("my_float_col");

 ***

-### currentBranch()
-
-```ts
-abstract currentBranch(): null | string
-```
-
-The branch this table handle is scoped to, or `null` for the main branch.
-
-A handle returned by [Branches.create](Branches.md#create) or [Branches.checkout](Branches.md#checkout)
-reports the branch it targets; a handle opened normally reports `null`.
-
-#### Returns
-
-`null` \| `string`
-
-***
-
 ### delete()

 ```ts
@@ -398,26 +364,6 @@ Drop an index from the table.

 ***

-### getLsmWriteSpec()
-
-```ts
-abstract getLsmWriteSpec(): Promise<undefined | LsmWriteSpec>
-```
-
-Read the [LsmWriteSpec](../interfaces/LsmWriteSpec.md) currently installed on this table.
-
-Resolves to `undefined` when the MemWAL LSM write path is not enabled (no
-spec has been set, or it was removed with [Table#unsetLsmWriteSpec](Table.md#unsetlsmwritespec)).
-The returned spec — including its `maintainedIndexes` and
-`writerConfigDefaults` — mirrors what was passed to
-[Table#setLsmWriteSpec](Table.md#setlsmwritespec).
-
-#### Returns
-
-`Promise`&lt;`undefined` \| [`LsmWriteSpec`](../interfaces/LsmWriteSpec.md)&gt;
-
-***
-
 ### indexStats()

 ```ts
@@ -934,32 +880,6 @@ Return the table as an arrow table

 ***

-### tokenize()
-
-```ts
-abstract tokenize(query, options): Promise<FtsToken[]>
-```
-
-Tokenize a full-text search query using the tokenizer configured on an FTS index.
-
-Specify exactly one of `column` or `indexName`.
-
-Model-backed tokenizers such as `jieba/*` and `lindera/*` are rebuilt in
-the client process from index metadata. For remote tables, this means the
-same tokenizer model files must also exist locally.
-
-#### Parameters
-
-* **query**: `string`
-
-* **options**: [`TokenizeTableOptions`](../type-aliases/TokenizeTableOptions.md)
-
-#### Returns
-
-`Promise`&lt;[`FtsToken`](../interfaces/FtsToken.md)[]&gt;
-
-***
-
 ### unsetLsmWriteSpec()

 ```ts
@@ -29,7 +29,7 @@ protected inner: TakeQuery | Promise<TakeQuery>;
 ### analyzePlan()

 ```ts
-analyzePlan(distributedMetrics?): Promise<string>
+analyzePlan(): Promise<string>
 ```

 Executes the query and returns the physical query plan annotated with runtime metrics.
@@ -37,12 +37,6 @@ Executes the query and returns the physical query plan annotated with runtime me
 This is useful for debugging and performance analysis, as it shows how the query was executed
 and includes metrics such as elapsed time, rows processed, and I/O statistics.

-#### Parameters
-
-* **distributedMetrics?**: [`AnalyzePlanDistributedMetrics`](../type-aliases/AnalyzePlanDistributedMetrics.md)
-    How distributed worker metrics are displayed for remote query plans.
-    Defaults to `"aggregate"`.
-
 #### Returns

 `Promise`&lt;`string`&gt;
@@ -273,29 +267,6 @@ ArrowTable.

 ***

-### useLsm()
-
-```ts
-useLsm(enable): this
-```
-
-Control MemWAL read routing for this take query.
-
-`false` bypasses the MemWAL and reads the base table only — the escape hatch,
-since take-by-row-id/offset is not supported on the LSM scanner and, on a
-MemWAL table, auto-routes to it and errors otherwise.
-
-#### Parameters
-
-* **enable**: `boolean`
-    `false` reads the base table only.
-
-#### Returns
-
-`this`
-
-***
-
 ### withRowId()

 ```ts
@@ -51,7 +51,7 @@ addQueryVector(vector): VectorQuery
 ### analyzePlan()

 ```ts
-analyzePlan(distributedMetrics?): Promise<string>
+analyzePlan(): Promise<string>
 ```

 Executes the query and returns the physical query plan annotated with runtime metrics.
@@ -59,12 +59,6 @@ Executes the query and returns the physical query plan annotated with runtime me
 This is useful for debugging and performance analysis, as it shows how the query was executed
 and includes metrics such as elapsed time, rows processed, and I/O statistics.

-#### Parameters
-
-* **distributedMetrics?**: [`AnalyzePlanDistributedMetrics`](../type-aliases/AnalyzePlanDistributedMetrics.md)
-    How distributed worker metrics are displayed for remote query plans.
-    Defaults to `"aggregate"`.
-
 #### Returns

 `Promise`&lt;`string`&gt;
@@ -746,42 +740,6 @@ ArrowTable.

 ***

-### useLsm()
-
-```ts
-useLsm(enable): this
-```
-
-Control MemWAL read routing for this query.
-
-By default (unset), when the table carries a MemWAL write spec (see
-[Table#setLsmWriteSpec](Table.md#setlsmwritespec)), reads are routed through the LSM scanner so
-they also return data written via the `mergeInsert` LSM path that has not yet
-been compacted into the base table (the active/frozen in-memory memtables and
-the flushed generations), deduplicated by primary key; a table without a spec
-reads the base table.
-
-#### Parameters
-
-* **enable**: `boolean`
-    `true` forces the LSM scanner and errors if the table has no
-    MemWAL write spec. `false` bypasses the MemWAL and reads the base table only,
-    even when a spec is present.
-    Note: the LSM scanner does not support every query shape (e.g. reranking,
-    hybrid search, `orderBy`). On a MemWAL table those shapes error unless
-    `useLsm(false)` is set, because a base-only read would silently exclude
-    un-compacted MemWAL data.
-
-#### Returns
-
-`this`
-
-#### Inherited from
-
-`StandardQueryBase.useLsm`
-
-***
-
 ### where()

 ```ts
@@ -809,9 +767,6 @@ x > 5 OR y = 'test'

 Filtering performance can often be improved by creating a scalar index
 on the filter column(s).
-
-Calling this multiple times combines the filters with a logical AND rather
-than replacing the previous filter.
 ```

 #### Inherited from
@@ -1,29 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / OAuthFlowType
-
-# Enumeration: OAuthFlowType
-
-OAuth authentication flow types.
-
-## Enumeration Members
-
-### AzureManagedIdentity
-
-```ts
-AzureManagedIdentity: "azure_managed_identity";
-```
-
-Azure Managed Identity via IMDS.
-
-***
-
-### ClientCredentials
-
-```ts
-ClientCredentials: "client_credentials";
-```
-
-Client Credentials grant (service-to-service / M2M).
@@ -1,42 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / instrumentLanceDbMetrics
-
-# Function: instrumentLanceDbMetrics()
-
-```ts
-function instrumentLanceDbMetrics(meterProvider?): boolean
-```
-
-Register LanceDB metrics as OpenTelemetry observable instruments.
-
-Installs a process-global metrics recorder and creates one observable
-instrument per LanceDB metric (currently object store request counts, bytes,
-latency, errors, and throttles) on the given (or global) `MeterProvider`. The
-configured `MetricReader` then collects them on its own schedule.
-
-Counters and gauges map directly to observable counters/gauges. Because
-OpenTelemetry has no asynchronous histogram instrument, each histogram is
-exported Prometheus-style as cumulative `le` bucket counts (`<name>_bucket`,
-with an `le` attribute) plus `<name>_count` and `<name>_sum`.
-
-Requires `@opentelemetry/api` (a dependency) and, to actually export, an
-OpenTelemetry SDK such as `@opentelemetry/sdk-metrics`.
-
-## Parameters
-
-* **meterProvider?**: `MeterProvider`
-    The provider to register instruments on. Defaults to the
-    global provider from `@opentelemetry/api`.
-
-## Returns
-
-`boolean`
-
-`true` if the recorder is installed and instruments are registered.
-  `false` if a different `metrics` recorder is already installed in this
-  process (only one global recorder is permitted), in which case a warning is
-  emitted and no instruments are created. Calling this more than once is safe;
-  instruments are created only on the first successful call.
@@ -1,26 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / tokenize
-
-# Function: tokenize()
-
-```ts
-function tokenize(query, options?): Promise<FtsToken[]>
-```
-
-Tokenize a full-text search query using an explicit tokenizer.
-
-This does not require a table or FTS index. The tokenizer options match
-[Index.fts](../classes/Index.md#fts).
-
-## Parameters
-
-* **query**: `string`
-
-* **options?**: `Partial`&lt;[`TokenizeOptions`](../interfaces/TokenizeOptions.md)&gt;
-
-## Returns
-
-`Promise`&lt;[`FtsToken`](../interfaces/FtsToken.md)[]&gt;
@@ -12,7 +12,6 @@
 ## Enumerations

 - [FullTextQueryType](enumerations/FullTextQueryType.md)
- [OAuthFlowType](enumerations/OAuthFlowType.md)
 - [Occur](enumerations/Occur.md)
 - [Operator](enumerations/Operator.md)

@@ -20,8 +19,6 @@

 - [BooleanQuery](classes/BooleanQuery.md)
 - [BoostQuery](classes/BoostQuery.md)
- [BranchContents](classes/BranchContents.md)
- [Branches](classes/Branches.md)
 - [Connection](classes/Connection.md)
 - [HeaderProvider](classes/HeaderProvider.md)
 - [Index](classes/Index.md)
@@ -52,11 +49,6 @@
 - [AddDataOptions](interfaces/AddDataOptions.md)
 - [AddResult](interfaces/AddResult.md)
 - [AlterColumnsResult](interfaces/AlterColumnsResult.md)
- [BranchColumnChange](interfaces/BranchColumnChange.md)
- [BranchColumnSummary](interfaces/BranchColumnSummary.md)
- [BranchDiff](interfaces/BranchDiff.md)
- [BranchIndexSummary](interfaces/BranchIndexSummary.md)
- [BranchRowCountSummary](interfaces/BranchRowCountSummary.md)
 - [ClientConfig](interfaces/ClientConfig.md)
 - [ColumnAlteration](interfaces/ColumnAlteration.md)
 - [ColumnOrdering](interfaces/ColumnOrdering.md)
@@ -77,7 +69,6 @@
 - [FragmentStatistics](interfaces/FragmentStatistics.md)
 - [FragmentSummaryStats](interfaces/FragmentSummaryStats.md)
 - [FtsOptions](interfaces/FtsOptions.md)
- [FtsToken](interfaces/FtsToken.md)
 - [FullTextQuery](interfaces/FullTextQuery.md)
 - [FullTextSearchOptions](interfaces/FullTextSearchOptions.md)
 - [HnswPqOptions](interfaces/HnswPqOptions.md)
@@ -91,12 +82,7 @@
 - [ListNamespacesOptions](interfaces/ListNamespacesOptions.md)
 - [ListNamespacesResponse](interfaces/ListNamespacesResponse.md)
 - [LsmWriteSpec](interfaces/LsmWriteSpec.md)
- [MergeBlocker](interfaces/MergeBlocker.md)
- [MergeBranchResult](interfaces/MergeBranchResult.md)
- [MergePreview](interfaces/MergePreview.md)
 - [MergeResult](interfaces/MergeResult.md)
- [NativeOAuthConfig](interfaces/NativeOAuthConfig.md)
- [OAuthConfig](interfaces/OAuthConfig.md)
 - [OpenTableOptions](interfaces/OpenTableOptions.md)
 - [OptimizeOptions](interfaces/OptimizeOptions.md)
 - [OptimizeStats](interfaces/OptimizeStats.md)
@@ -116,7 +102,6 @@
 - [TimeoutConfig](interfaces/TimeoutConfig.md)
 - [TlsConfig](interfaces/TlsConfig.md)
 - [TokenResponse](interfaces/TokenResponse.md)
- [TokenizeOptions](interfaces/TokenizeOptions.md)
 - [UpdateFieldMetadataResult](interfaces/UpdateFieldMetadataResult.md)
 - [UpdateOptions](interfaces/UpdateOptions.md)
 - [UpdateResult](interfaces/UpdateResult.md)
@@ -126,8 +111,6 @@

 ## Type Aliases

- [AnalyzePlanDistributedMetrics](type-aliases/AnalyzePlanDistributedMetrics.md)
- [BaseTokenizer](type-aliases/BaseTokenizer.md)
 - [Data](type-aliases/Data.md)
 - [DataLike](type-aliases/DataLike.md)
 - [FieldLike](type-aliases/FieldLike.md)
@@ -137,15 +120,12 @@
 - [RecordBatchLike](type-aliases/RecordBatchLike.md)
 - [SchemaLike](type-aliases/SchemaLike.md)
 - [TableLike](type-aliases/TableLike.md)
- [TokenizeTableOptions](type-aliases/TokenizeTableOptions.md)

 ## Functions

 - [RecordBatchIterator](functions/RecordBatchIterator.md)
 - [connect](functions/connect.md)
 - [connectNamespace](functions/connectNamespace.md)
- [instrumentLanceDbMetrics](functions/instrumentLanceDbMetrics.md)
 - [makeArrowTable](functions/makeArrowTable.md)
 - [packBits](functions/packBits.md)
 - [permutationBuilder](functions/permutationBuilder.md)
- [tokenize](functions/tokenize.md)
@@ -1,33 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / BranchColumnChange
-
-# Interface: BranchColumnChange
-
-A column whose definition differs between main and the branch.
-
-## Properties
-
-### branch
-
-```ts
-branch: BranchColumnSummary;
-```
-
-***
-
-### main
-
-```ts
-main: BranchColumnSummary;
-```
-
-***
-
-### name
-
-```ts
-name: string;
-```
@@ -1,33 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / BranchColumnSummary
-
-# Interface: BranchColumnSummary
-
-Summary of a column in a branch diff.
-
-## Properties
-
-### dataType
-
-```ts
-dataType: string;
-```
-
-***
-
-### name
-
-```ts
-name: string;
-```
-
-***
-
-### nullable
-
-```ts
-nullable: boolean;
-```
@@ -1,129 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / BranchDiff
-
-# Interface: BranchDiff
-
-Read-only comparison of a branch against main.
-
-## Properties
-
-### addedColumns
-
-```ts
-addedColumns: BranchColumnSummary[];
-```
-
-***
-
-### addedIndexes
-
-```ts
-addedIndexes: BranchIndexSummary[];
-```
-
-***
-
-### baseMoved
-
-```ts
-baseMoved: boolean;
-```
-
-***
-
-### branchVersion
-
-```ts
-branchVersion: number;
-```
-
-***
-
-### changedColumns
-
-```ts
-changedColumns: BranchColumnChange[];
-```
-
-***
-
-### fromBranch
-
-```ts
-fromBranch: string;
-```
-
-***
-
-### mainVersion
-
-```ts
-mainVersion: number;
-```
-
-***
-
-### mergeBlockers
-
-```ts
-mergeBlockers: MergeBlocker[];
-```
-
-***
-
-### mergeable
-
-```ts
-mergeable: boolean;
-```
-
-***
-
-### parentVersion
-
-```ts
-parentVersion: number;
-```
-
-***
-
-### removedColumns
-
-```ts
-removedColumns: BranchColumnSummary[];
-```
-
-***
-
-### removedIndexes
-
-```ts
-removedIndexes: BranchIndexSummary[];
-```
-
-***
-
-### rowCountBranch
-
-```ts
-rowCountBranch: number;
-```
-
-***
-
-### rowCountMain
-
-```ts
-rowCountMain: number;
-```
-
-***
-
-### rowSummary
-
-```ts
-rowSummary: BranchRowCountSummary;
-```
@@ -1,41 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / BranchIndexSummary
-
-# Interface: BranchIndexSummary
-
-Summary of an index in a branch diff.
-
-## Properties
-
-### columns
-
-```ts
-columns: string[];
-```
-
-***
-
-### indexName
-
-```ts
-indexName: string;
-```
-
-***
-
-### indexType?
-
-```ts
-optional indexType: string;
-```
-
-***
-
-### status
-
-```ts
-status: string;
-```
@@ -1,57 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / BranchRowCountSummary
-
-# Interface: BranchRowCountSummary
-
-Row-level comparison between main and the branch.
-
-## Properties
-
-### deltaAvailable
-
-```ts
-deltaAvailable: boolean;
-```
-
-***
-
-### inputsChanged
-
-```ts
-inputsChanged: number;
-```
-
-***
-
-### newOnBase
-
-```ts
-newOnBase: number;
-```
-
-***
-
-### newOnBranch
-
-```ts
-newOnBranch: number;
-```
-
-***
-
-### staleRecompute
-
-```ts
-staleRecompute: number;
-```
-
-***
-
-### unchanged
-
-```ts
-unchanged: number;
-```
@@ -64,19 +64,6 @@ client used by manifest-enabled native connections.

 ***

-### oauthConfig?
-
-```ts
-optional oauthConfig: NativeOAuthConfig;
-```
-
-(For LanceDB cloud only): OAuth configuration for IdP-based
-authentication (e.g., Azure Entra ID). When set, token acquisition
-and refresh are handled entirely in Rust. TypeScript users should pass
-the public `OAuthConfig` type exported from `@lancedb/lancedb`.
-
-***
-
 ### readConsistencyInterval?

 ```ts
@@ -23,7 +23,7 @@ whether to remove punctuation
 ### baseTokenizer?

 ```ts
-optional baseTokenizer: BaseTokenizer;
+optional baseTokenizer: "raw" | "simple" | "whitespace" | "ngram";
 ```

 The tokenizer to use when building the index.
@@ -37,38 +37,6 @@ The following tokenizers are available:

 "raw" - Raw tokenizer. This tokenizer does not split the text into tokens and indexes the entire text as a single token.

-"icu" - ICU dictionary-based word segmentation.
-
-"icu/split" - ICU segmentation with simple-style delimiter splitting.
-
-***
-
-### blockSize?
-
-```ts
-optional blockSize: 128 | 256;
-```
-
-Number of documents per compressed posting block.
-
-The default is 128. Supported values are 128 and 256. A value of 256 uses
-the experimental FTS V3 format and may introduce breaking changes.
-
-***
-
-### customStopWords?
-
-```ts
-optional customStopWords: string[];
-```
-
-Custom stop words that replace the built-in list for `language`.
-
-This option only affects tokenization when `removeStopWords` is true.
-
-`undefined` keeps the built-in language list. An empty array explicitly
-replaces it with no stop words.
-
 ***

 ### language?
@@ -1,29 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / FtsToken
-
-# Interface: FtsToken
-
-Token produced by the tokenizer configured on a full-text search index.
-
-## Properties
-
-### position
-
-```ts
-position: number;
-```
-
-Token position used by full-text query matching.
-
-***
-
-### text
-
-```ts
-text: string;
-```
-
-Token text after tokenizer filters have been applied.
@@ -23,31 +23,6 @@ be more columns to represent composite indices.

 ***

-### createdAt?
-
-```ts
-optional createdAt: Date;
-```
-
-When the index was created.
-
-`undefined` for remote tables or indices created before timestamps were tracked.
-
-***
-
-### indexDetails?
-
-```ts
-optional indexDetails: any;
-```
-
-Index-type-specific details parsed as a JavaScript object.
-
-Falls back to a raw string if JSON parsing fails. `undefined` for
-remote tables or when details are unavailable.
-
-***
-
 ### indexType

 ```ts
@@ -58,30 +33,6 @@ The type of the index

 ***

-### indexUuid?
-
-```ts
-optional indexUuid: string;
-```
-
-The UUID of the first segment of the index.
-
-`undefined` for remote tables, which do not yet surface this.
-
-***
-
-### indexVersion?
-
-```ts
-optional indexVersion: number;
-```
-
-The on-disk index format version.
-
-`undefined` for remote tables.
-
-***
-
 ### name

 ```ts
@@ -89,63 +40,3 @@ name: string;
 ```

 The name of the index
-
-***
-
-### numIndexedRows?
-
-```ts
-optional numIndexedRows: number;
-```
-
-The number of rows indexed, across all segments.
-
-`undefined` for remote tables.
-
-***
-
-### numSegments?
-
-```ts
-optional numSegments: number;
-```
-
-The number of segments that make up the index.
-
-`undefined` for remote tables.
-
-***
-
-### numUnindexedRows?
-
-```ts
-optional numUnindexedRows: number;
-```
-
-The number of rows not yet covered by this index.
-
-`undefined` for remote tables.
-
-***
-
-### sizeBytes?
-
-```ts
-optional sizeBytes: number;
-```
-
-The total size in bytes of all index files across all segments.
-
-`undefined` for remote tables or indices without size tracking.
-
-***
-
-### typeUrl?
-
-```ts
-optional typeUrl: string;
-```
-
-The protobuf type URL, a precise type identifier for the index.
-
-`undefined` for remote tables.
@@ -1,25 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / MergeBlocker
-
-# Interface: MergeBlocker
-
-A reason why a branch cannot currently be merged.
-
-## Properties
-
-### code
-
-```ts
-code: string;
-```
-
-***
-
-### message
-
-```ts
-message: string;
-```
@@ -1,46 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / MergeBranchResult
-
-# Interface: MergeBranchResult
-
-Result of previewing or attempting a branch merge.
-
-## Properties
-
-### diff
-
-```ts
-diff: BranchDiff;
-```
-
-***
-
-### mainVersionAfter?
-
-```ts
-optional mainVersionAfter: number;
-```
-
-***
-
-### preview
-
-```ts
-preview: MergePreview;
-```
-
-***
-
-### status
-
-```ts
-status:
-  | "unknown"
-  | "rejected"
-  | "ready"
-  | "notImplemented"
-  | "merged";
-```
@@ -1,17 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / MergePreview
-
-# Interface: MergePreview
-
-Changes that would be, or were, promoted by a branch merge.
-
-## Properties
-
-### promotedColumns
-
-```ts
-promotedColumns: string[];
-```
@@ -1,88 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / NativeOAuthConfig
-
-# Interface: NativeOAuthConfig
-
-OAuth configuration for LanceDB authentication.
-
-This is the generated napi-rs binding shape. TypeScript users should prefer
-the public `OAuthConfig` type exported from `@lancedb/lancedb`.
-
-All token acquisition and refresh is handled in the Rust layer.
-
-## Properties
-
-### clientId
-
-```ts
-clientId: string;
-```
-
-Application / Client ID.
-
-***
-
-### clientSecret?
-
-```ts
-optional clientSecret: string;
-```
-
-Client secret (required for client_credentials).
-
-***
-
-### flow?
-
-```ts
-optional flow: string;
-```
-
-Authentication flow: "client_credentials" or "azure_managed_identity"
-
-***
-
-### issuerUrl
-
-```ts
-issuerUrl: string;
-```
-
-OIDC issuer URL or OAuth authority URL.
-For Azure: `https://login.microsoftonline.com/{tenant_id}/v2.0`
-
-***
-
-### managedIdentityClientId?
-
-```ts
-optional managedIdentityClientId: string;
-```
-
-Client ID for user-assigned managed identity (azure_managed_identity).
-
-***
-
-### refreshBufferSecs?
-
-```ts
-optional refreshBufferSecs: number;
-```
-
-Seconds before expiry to trigger proactive refresh (default: 300).
-Keep this well below the token TTL; if it is greater than or equal to
-the TTL, each request refreshes the token.
-
-***
-
-### scopes
-
-```ts
-scopes: string[];
-```
-
-OAuth scopes to request. For Azure managed identity, exactly one scope
-or resource is required. For example: `["api://{app_id}/.default"]`
@@ -1,111 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / OAuthConfig
-
-# Interface: OAuthConfig
-
-OAuth configuration for LanceDB authentication.
-
-This is the public TypeScript OAuth configuration type. The generated
-`NativeOAuthConfig` type has the same runtime shape but is an implementation
-detail of the napi-rs binding.
-
-All token acquisition and refresh is handled in the Rust layer.
-This config is passed through to Rust via napi-rs.
-
-## Examples
-
-```typescript
-const config: OAuthConfig = {
-  issuerUrl: "https://login.microsoftonline.com/{tenant}/v2.0",
-  clientId: "app-id",
-  clientSecret: "secret",
-  scopes: ["api://lancedb-api/.default"],
-};
-```
-
-```typescript
-const config: OAuthConfig = {
-  issuerUrl: "https://login.microsoftonline.com/{tenant}/v2.0",
-  clientId: "app-id",
-  scopes: ["api://lancedb-api/.default"],
-  flow: OAuthFlowType.AzureManagedIdentity,
-};
-```
-
-## Properties
-
-### clientId
-
-```ts
-clientId: string;
-```
-
-Application / Client ID.
-
-***
-
-### clientSecret?
-
-```ts
-optional clientSecret: string;
-```
-
-Client secret (required for ClientCredentials).
-
-***
-
-### flow?
-
-```ts
-optional flow: OAuthFlowType;
-```
-
-Authentication flow (default: ClientCredentials).
-
-***
-
-### issuerUrl
-
-```ts
-issuerUrl: string;
-```
-
-OIDC issuer URL or OAuth authority URL.
-For Azure: `https://login.microsoftonline.com/{tenant_id}/v2.0`
-
-***
-
-### managedIdentityClientId?
-
-```ts
-optional managedIdentityClientId: string;
-```
-
-Client ID for user-assigned managed identity (AzureManagedIdentity).
-
-***
-
-### refreshBufferSecs?
-
-```ts
-optional refreshBufferSecs: number;
-```
-
-Seconds before expiry to trigger proactive refresh (default: 300).
-Keep this well below the token TTL; if it is greater than or equal to
-the TTL, each request refreshes the token.
-
-***
-
-### scopes
-
-```ts
-scopes: string[];
-```
-
-OAuth scopes to request.
-For Azure managed identity, exactly one scope or resource is required.
-For example: `["api://{app_id}/.default"]`
@@ -8,18 +8,6 @@

 ## Properties

-### branch?
-
-```ts
-optional branch: string;
-```
-
-Open the table scoped to this branch instead of the default branch.
-
-Reads and writes on the returned table operate in the branch's context.
-
-***
-
 ### ~~indexCacheSize?~~

 ```ts
@@ -55,17 +43,3 @@ Options already set on the connection will be inherited by the table,
 but can be overridden here.

 The available options are described at https://docs.lancedb.com/storage/
-
-***
-
-### version?
-
-```ts
-optional version: number;
-```
-
-Open the table pinned to this version, producing a read-only view.
-
-Composes with [OpenTableOptions.branch](OpenTableOptions.md#branch): when both are set, opens
-that branch at the version; otherwise opens `main` at the version. Call
-`checkoutLatest` to return to a writable state.
@@ -8,14 +8,6 @@

 ## Properties

-### clumpSize?
-
-```ts
-optional clumpSize: number;
-```
-
-***
-
 ### counts?

 ```ts
@@ -1,124 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / TokenizeOptions
-
-# Interface: TokenizeOptions
-
-Options for tokenizing a full-text search query without a table index.
-
-## Properties
-
-### asciiFolding?
-
-```ts
-optional asciiFolding: boolean;
-```
-
-Whether to fold ASCII characters.
-
-***
-
-### baseTokenizer?
-
-```ts
-optional baseTokenizer: BaseTokenizer;
-```
-
-The tokenizer to use. The default is "simple".
-
-***
-
-### customStopWords?
-
-```ts
-optional customStopWords: string[];
-```
-
-Custom stop words that replace the built-in list for `language`.
-
-This option only affects tokenization when `removeStopWords` is true.
-
-`undefined` keeps the built-in language list. An empty array explicitly
-replaces it with no stop words.
-
-***
-
-### language?
-
-```ts
-optional language: string;
-```
-
-Language for stemming and stop words.
-
-***
-
-### lowercase?
-
-```ts
-optional lowercase: boolean;
-```
-
-Whether to lowercase tokens.
-
-***
-
-### maxTokenLength?
-
-```ts
-optional maxTokenLength: number;
-```
-
-Maximum token length; tokens longer than this are ignored.
-
-***
-
-### ngramMaxLength?
-
-```ts
-optional ngramMaxLength: number;
-```
-
-N-gram maximum length.
-
-***
-
-### ngramMinLength?
-
-```ts
-optional ngramMinLength: number;
-```
-
-N-gram minimum length.
-
-***
-
-### prefixOnly?
-
-```ts
-optional prefixOnly: boolean;
-```
-
-Whether to only emit token prefixes for the n-gram tokenizer.
-
-***
-
-### removeStopWords?
-
-```ts
-optional removeStopWords: boolean;
-```
-
-Whether to remove stop words.
-
-***
-
-### stem?
-
-```ts
-optional stem: boolean;
-```
-
-Whether to stem tokens.
@@ -1,11 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / AnalyzePlanDistributedMetrics
-
-# Type Alias: AnalyzePlanDistributedMetrics
-
-```ts
-type AnalyzePlanDistributedMetrics: "aggregate" | "per_worker" | "full";
-```
@@ -1,19 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / BaseTokenizer
-
-# Type Alias: BaseTokenizer
-
-```ts
-type BaseTokenizer:
-  | "simple"
-  | "whitespace"
-  | "raw"
-  | "ngram"
-  | "icu"
-  | "icu/split"
-  | `jieba/${string}`
-  | `lindera/${string}`;
-```
@@ -1,11 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / TokenizeTableOptions
-
-# Type Alias: TokenizeTableOptions
-
-```ts
-type TokenizeTableOptions: object | object;
-```
@@ -26,18 +26,6 @@ is also an [asynchronous API client](#connections-asynchronous).

 ::: lancedb.db.DBConnection

-::: lancedb.Session
-
-## Namespaces (Synchronous)
-
-A namespace-backed connection resolves tables through a
-[Lance namespace](https://lancedb.github.io/lance-namespace/) service instead of
-listing a storage directory.
-
-::: lancedb.connect_namespace
-
-::: lancedb.namespace.LanceNamespaceDBConnection
-
 ## Tables (Synchronous)

 ::: lancedb.table.Table
@@ -46,12 +34,8 @@ listing a storage directory.

 ::: lancedb.table.FragmentSummaryStats

-::: lancedb.table.TableStatistics
-
 ::: lancedb.table.Tags

-::: lancedb.table.Branches
-
 ## Expressions

 Type-safe expression builder for filters and projections. Use these instead
@@ -78,46 +62,29 @@ of raw SQL strings with [where][lancedb.query.LanceQueryBuilder.where] and

 ::: lancedb.query.LanceHybridQueryBuilder

-::: lancedb.query.LanceEmptyQueryBuilder
-
-::: lancedb.query.LanceTakeQueryBuilder
-
-## Full text queries
-
-Structured full text queries can be passed to
-[Table.search][lancedb.table.Table.search] or
-[AsyncTable.search][lancedb.table.AsyncTable.search] in place of a query string,
-and combined with [BooleanQuery][lancedb.query.BooleanQuery].
-
-::: lancedb.query.FullTextQuery
-
-::: lancedb.query.MatchQuery
-
-::: lancedb.query.PhraseQuery
-
-::: lancedb.query.BoostQuery
-
-::: lancedb.query.MultiMatchQuery
-
-::: lancedb.query.BooleanQuery
-
-::: lancedb.query.FullTextOperator
-
-::: lancedb.query.Occur
-
 ## Embeddings

-::: lancedb.embeddings
-    options:
-      show_root_heading: false
-      show_root_toc_entry: false
+::: lancedb.embeddings.registry.EmbeddingFunctionRegistry
+
+::: lancedb.embeddings.base.EmbeddingFunctionConfig
+
+::: lancedb.embeddings.base.EmbeddingFunction
+
+::: lancedb.embeddings.base.TextEmbeddingFunction
+
+::: lancedb.embeddings.sentence_transformers.SentenceTransformerEmbeddings
+
+::: lancedb.embeddings.openai.OpenAIEmbeddings
+
+::: lancedb.embeddings.open_clip.OpenClipEmbeddings

 ## Remote configuration

-::: lancedb.remote
-    options:
-      show_root_heading: false
-      show_root_toc_entry: false
+::: lancedb.remote.ClientConfig
+
+::: lancedb.remote.TimeoutConfig
+
+::: lancedb.remote.RetryConfig

 ## Context

@@ -127,50 +94,11 @@ and combined with [BooleanQuery][lancedb.query.BooleanQuery].

 ## Full text search

-Pass `custom_stop_words` to [lancedb.index.FTS][]:
+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.

-```python
-from lancedb.index import FTS
-
-table.create_index(
-    "text",
-    config=FTS(remove_stop_words=True, custom_stop_words=["acme", "internal"]),
-)
-```
-
-The list replaces the built-in stop words and is used only when
-`remove_stop_words=True`:
-
- `custom_stop_words=None` uses the built-in list for `language`.
- `custom_stop_words=[]` removes no words.
- Values are passed through without trimming, lowercasing, or other rewriting.
-
-The same option is available on `lancedb.tokenize(...)` and the deprecated
-[lancedb.table.Table.create_fts_index][] compatibility helper:
-
-```python
-import lancedb
-
-tokens = list(lancedb.tokenize("acme makes searchable data",
-                               custom_stop_words=["acme"]))
-```
-
-::: lancedb.tokenize
-
-::: lancedb.FtsToken
-
-## Blobs
-
-Blob columns store large binary values out of line so they can be read lazily
-instead of being materialized with the rest of the row.
-
-::: lancedb.blob
-
-::: lancedb.BlobType
-
-::: lancedb._blob.BlobFile
-    options:
-      show_root_full_path: false
+::: lancedb.index.FTS

 ## Utilities

@@ -178,14 +106,6 @@ instead of being materialized with the rest of the row.

 ::: lancedb.merge.LanceMergeInsertBuilder

-::: lancedb.otel.instrument_lancedb_metrics
-
-## Exceptions
-
-::: lancedb.exceptions.MissingValueError
-
-::: lancedb.exceptions.MissingColumnError
-
 ## Integrations

 ## Pydantic
@@ -194,30 +114,19 @@ instead of being materialized with the rest of the row.

 ::: lancedb.pydantic.vector

-::: lancedb.pydantic.Vector
-
-::: lancedb.pydantic.MultiVector
-
 ::: lancedb.pydantic.LanceModel

-## PyTorch
-
-::: lancedb.streaming.StreamingDataset
-
-::: lancedb.permutation.permutation_builder
-
-::: lancedb.permutation.PermutationBuilder
-
-::: lancedb.permutation.Permutation
-
-::: lancedb.permutation.Transforms
-
 ## Reranking

-::: lancedb.rerankers
-    options:
-      show_root_heading: false
-      show_root_toc_entry: false
+::: lancedb.rerankers.linear_combination.LinearCombinationReranker
+
+::: lancedb.rerankers.cohere.CohereReranker
+
+::: lancedb.rerankers.colbert.ColbertReranker
+
+::: lancedb.rerankers.cross_encoder.CrossEncoderReranker
+
+::: lancedb.rerankers.openai.OpenaiReranker

 ## Connections (Asynchronous)

@@ -228,12 +137,6 @@ can be used to create, list, or open tables.

 ::: lancedb.db.AsyncConnection

-## Namespaces (Asynchronous)
-
-::: lancedb.connect_namespace_async
-
-::: lancedb.namespace.AsyncLanceNamespaceDBConnection
-
 ## Tables (Asynchronous)

 Table hold your actual data as a collection of records / rows.
@@ -242,20 +145,32 @@ Table hold your actual data as a collection of records / rows.

 ::: lancedb.table.AsyncTags

-::: lancedb.table.AsyncBranches
-
 ## Indices (Asynchronous)

 Indices can be created on a table to speed up queries. This section
 lists the indices that LanceDb supports.

-::: lancedb.index
-    options:
-      show_root_heading: false
-      show_root_toc_entry: false
-      # `lang_mapping` is defined in the module rather than imported, so it is
-      # picked up despite not being in `__all__`. It is an internal lookup table.
-      filters: ["!^_", "!^lang_mapping$"]
+::: lancedb.index.BTree
+
+::: lancedb.index.Bitmap
+
+::: lancedb.index.LabelList
+
+::: lancedb.index.FTS
+
+::: lancedb.index.IvfPq
+
+::: lancedb.index.HnswPq
+
+::: lancedb.index.HnswSq
+
+::: lancedb.index.IvfFlat
+
+::: lancedb.index.IvfSq
+
+::: lancedb.index.IvfRq
+
+::: lancedb.index.HnswFlat

 ::: lancedb.table.IndexStatistics

@@ -283,7 +198,3 @@ rows nearest to a query vector and can be created with the
 ::: lancedb.query.AsyncHybridQuery
    options:
      inherited_members: true
-
-::: lancedb.query.AsyncTakeQuery
-    options:
-      inherited_members: true
@@ -8,7 +8,7 @@
    <parent>
      <groupId>com.lancedb</groupId>
      <artifactId>lancedb-parent</artifactId>
-      <version>0.37.1-beta.0</version>
+      <version>0.30.1-beta.2</version>
      <relativePath>../pom.xml</relativePath>
    </parent>

@@ -6,7 +6,7 @@

    <groupId>com.lancedb</groupId>
    <artifactId>lancedb-parent</artifactId>
-    <version>0.37.1-beta.0</version>
+    <version>0.30.1-beta.2</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>10.0.0-beta.5</lance-core.version>
+        <lance-core.version>8.0.0-beta.7</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>
@@ -1,7 +1,7 @@
 # Contributing to LanceDB Typescript

 This document outlines the process for contributing to LanceDB Typescript.
-For general contribution guidelines, see [CONTRIBUTING.md](https://github.com/lancedb/lancedb/blob/main/CONTRIBUTING.md).
+For general contribution guidelines, see [CONTRIBUTING.md](../CONTRIBUTING.md).

 ## Project layout

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.37.1-beta.0"
+version = "0.30.1-beta.2"
 publish = false
 license.workspace = true
 description.workspace = true
@@ -25,12 +25,8 @@ lancedb = { path = "../rust/lancedb", default-features = false }
 lance-namespace.workspace = true
 napi = { version = "3.8.3", default-features = false, features = [
    "napi9",
-    "async",
-    "chrono_date",
-    "serde-json",
+    "async"
 ] }
-chrono = { version = "0.4", default-features = false, features = ["clock"] }
-serde_json = "1"
 napi-derive = "3.5.2"
 # Prevent dynamic linking of lzma, which comes from datafusion
 lzma-sys = { version = "0.1", features = ["static"] }
@@ -44,6 +40,6 @@ aws-lc-rs = "=1.16.3"
 napi-build = "2.3.1"

 [features]
-default = ["remote", "lancedb/aws", "lancedb/gcs", "lancedb/azure", "lancedb/dynamodb", "lancedb/oss", "lancedb/huggingface", "lancedb/goosefs", "lancedb/metrics-otel"]
+default = ["remote", "lancedb/aws", "lancedb/gcs", "lancedb/azure", "lancedb/dynamodb", "lancedb/oss", "lancedb/huggingface"]
 fp16kernels = ["lancedb/fp16kernels"]
 remote = ["lancedb/remote"]
@@ -52,7 +52,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
      Float64,
      Struct,
      List,
-      Map_,
      Int16,
      Int32,
      Int64,
@@ -70,30 +69,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
    type Schema = ApacheArrow["Schema"];
    type Table = ApacheArrow["Table"];

-    function expectValidMapField(
-      // biome-ignore lint/suspicious/noExplicitAny: Arrow Field types vary across supported versions
-      field: any,
-    ): void {
-      expect(DataType.isMap(field.type)).toBe(true);
-      expect(field.type.keysSorted).toBe(true);
-      expect(field.type.children).toHaveLength(1);
-
-      const entries = field.type.children[0];
-      expect(entries.name).toBe("entries");
-      expect(entries.nullable).toBe(false);
-      expect(DataType.isStruct(entries.type)).toBe(true);
-      expect(entries.type.children).toHaveLength(2);
-
-      const [key, value] = entries.type.children;
-      expect([key.name, value.name]).toEqual(["key", "value"]);
-      expect(key.nullable).toBe(false);
-      expect(DataType.isUtf8(key.type)).toBe(true);
-      expect(value.nullable).toBe(true);
-      expect(DataType.isInt(value.type)).toBe(true);
-      expect(value.type.bitWidth).toBe(32);
-      expect(value.type.isSigned).toBe(true);
-    }
-
    // Helper method to verify various ways to create a table
    async function checkTableCreation(
      tableCreationMethod: (
@@ -963,65 +938,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
          false,
        );
      });
-
-      it("will make an empty table with a Map field", async function () {
-        const schema = new Schema([
-          new Field(
-            "attributes",
-            new Map_(
-              new Field(
-                "entries",
-                new Struct([
-                  new Field("key", new Utf8(), false),
-                  new Field("value", new Int32(), true),
-                ]),
-                false,
-              ),
-              true,
-            ),
-          ),
-        ]);
-
-        const table = makeEmptyTable(schema);
-
-        expectValidMapField(table.schema.fields[0]);
-
-        const buffer = await fromTableToBuffer(table);
-        const roundTripped = tableFromIPC(buffer);
-
-        expectValidMapField(roundTripped.schema.fields[0]);
-      });
-
-      it("preserves string schema metadata", function () {
-        const metadata = new Map([["source", "fixture"]]);
-        const schema = new Schema(
-          [new Field("value", new Int32(), true)],
-          metadata,
-        );
-
-        expect(makeEmptyTable(schema).schema.metadata.get("source")).toBe(
-          "fixture",
-        );
-      });
-
-      it.each([
-        ["non-string keys", new Map<unknown, unknown>([[42, "fixture"]])],
-        ["non-string values", new Map<unknown, unknown>([["source", 42]])],
-        [
-          "non-string keys and values",
-          new Map<unknown, unknown>([[42, false]]),
-        ],
-      ])("rejects schema metadata with %s", function (_, metadataLike) {
-        const metadata = metadataLike as unknown as Map<string, string>;
-        const schema = new Schema(
-          [new Field("value", new Int32(), true)],
-          metadata,
-        );
-
-        expect(() => makeEmptyTable(schema)).toThrow(
-          "Expected metadata, if present, to be a Map<string, string> but it had non-string keys or values",
-        );
-      });
    });

    describe("when using two versions of arrow", function () {
@@ -1,114 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-import {
-  MeterProvider,
-  type MetricData,
-  MetricReader,
-} from "@opentelemetry/sdk-metrics";
-import * as tmp from "tmp";
-import { connect, instrumentLanceDbMetrics } from "../lancedb";
-// snapshotLancedbMetrics is internal plumbing (not part of the public API), so
-// it is imported from the native module rather than the package entry point.
-import { snapshotLancedbMetrics } from "../lancedb/native";
-
-// The metrics recorder is process-global and installed once, so the whole
-// bridge is exercised in a single test to avoid cross-test global-state coupling.
-
-// A minimal pull-based reader whose `collect()` we drive directly, invoking the
-// observable-instrument callbacks. `@opentelemetry/sdk-metrics` ships no
-// in-memory reader, so we subclass the abstract base.
-class TestMetricReader extends MetricReader {
-  protected async onForceFlush(): Promise<void> {
-    // no-op: collection is driven directly via collect()
-  }
-  protected async onShutdown(): Promise<void> {
-    // no-op: nothing to release
-  }
-}
-
-async function metricsByName(
-  reader: TestMetricReader,
-): Promise<Map<string, MetricData>> {
-  const collected = await reader.collect();
-  const result = new Map<string, MetricData>();
-  for (const scope of collected.resourceMetrics.scopeMetrics) {
-    for (const metric of scope.metrics) {
-      result.set(metric.descriptor.name, metric);
-    }
-  }
-  return result;
-}
-
-describe("OpenTelemetry metrics bridge", () => {
-  let tmpDir: tmp.DirResult;
-  beforeEach(() => {
-    tmpDir = tmp.dirSync({ unsafeCleanup: true });
-  });
-  afterEach(() => tmpDir.removeCallback());
-
-  it("snapshot is safe to call regardless of install state", () => {
-    expect(Array.isArray(snapshotLancedbMetrics())).toBe(true);
-  });
-
-  it("exports object store metrics via observable instruments", async () => {
-    const reader = new TestMetricReader();
-    const provider = new MeterProvider({ readers: [reader] });
-    expect(instrumentLanceDbMetrics(provider)).toBe(true);
-
-    // Generate object store activity on the local filesystem (scheme "file").
-    const db = await connect(tmpDir.name);
-    const data = Array.from({ length: 256 }, (_, i) => ({ id: i }));
-    const table = await db.createTable("t", data);
-    expect(await table.countRows()).toBe(256);
-
-    const metrics = await metricsByName(reader);
-
-    const requests = metrics.get("lance_object_store_requests_total");
-    expect(requests).toBeDefined();
-    // biome-ignore lint/suspicious/noExplicitAny: SDK point shape
-    const requestPoints = (requests!.dataPoints as any[]) ?? [];
-    expect(requestPoints.length).toBeGreaterThan(0);
-    for (const p of requestPoints) {
-      // Labelled by `operation` and `base` (the store scheme by default).
-      expect(p.attributes).toHaveProperty("base");
-      expect(p.attributes).toHaveProperty("operation");
-    }
-    const totalRequests = requestPoints.reduce((acc, p) => acc + p.value, 0);
-    expect(totalRequests).toBeGreaterThan(0);
-
-    // Histograms are decomposed into bucket / count / sum observable counters.
-    const bucket = metrics.get(
-      "lance_object_store_request_duration_seconds_bucket",
-    );
-    expect(bucket).toBeDefined();
-    // biome-ignore lint/suspicious/noExplicitAny: SDK point shape
-    const bucketPoints = (bucket!.dataPoints as any[]) ?? [];
-    expect(bucketPoints.length).toBeGreaterThan(0);
-    expect(bucketPoints.every((p) => "le" in p.attributes)).toBe(true);
-    // The implicit +Inf bucket must be present.
-    expect(bucketPoints.some((p) => p.attributes.le === "+Inf")).toBe(true);
-
-    const count = metrics.get(
-      "lance_object_store_request_duration_seconds_count",
-    );
-    expect(count).toBeDefined();
-    // biome-ignore lint/suspicious/noExplicitAny: SDK point shape
-    const countPoints = (count!.dataPoints as any[]) ?? [];
-    expect(countPoints.reduce((acc, p) => acc + p.value, 0)).toBeGreaterThan(0);
-
-    const sum = metrics.get("lance_object_store_request_duration_seconds_sum");
-    expect(sum).toBeDefined();
-    // biome-ignore lint/suspicious/noExplicitAny: SDK point shape
-    const sumPoints = (sum!.dataPoints as any[]) ?? [];
-    expect(sumPoints.reduce((acc, p) => acc + p.value, 0)).toBeGreaterThan(0);
-
-    // Unit handling: only `_sum` keeps the histogram's unit (seconds); `_bucket`
-    // and `_count` observe cumulative counts and are unitless.
-    expect(sum!.descriptor.unit).toBe("s");
-    expect(bucket!.descriptor.unit).toBe("");
-    expect(count!.descriptor.unit).toBe("");
-
-    await provider.shutdown();
-  });
-});
@@ -215,20 +215,6 @@ describe("Query orderBy", () => {
    expect(results[2].score).toBeCloseTo(4.1, 0.001);
  });

-  it("should combine repeated where clauses with AND", async () => {
-    const results = await table
-      .query()
-      .where("score > 1.0")
-      .where("score < 3.0")
-      .orderBy({ columnName: "score" })
-      .toArray();
-    // Only rows matching both predicates should be returned, rather than the
-    // second where() silently replacing the first.
-    expect(results.length).toBe(2);
-    expect(results[0].score).toBeCloseTo(1.2, 0.001);
-    expect(results[1].score).toBeCloseTo(2.8, 0.001);
-  });
-
  it("should support method chaining with limit", async () => {
    const results = await table
      .query()
@@ -15,7 +15,6 @@ import {
  OAuthHeaderProvider,
  StaticHeaderProvider,
 } from "../lancedb/header";
-import { Index } from "../lancedb/indices";

 // Test-only header providers
 class CustomProvider extends HeaderProvider {
@@ -192,200 +191,6 @@ describe("remote connection", () => {
    );
  });

-  it("supports version time-travel and branches on remote", async () => {
-    await withMockDatabase(
-      (req, res) => {
-        const body = req.url?.includes("/branches/list")
-          ? JSON.stringify({
-              branches: {
-                exp: { parentVersion: 1, createAt: 1, manifestSize: 1 },
-              },
-            })
-          : JSON.stringify({ name: "t", version: 2, schema: { fields: [] } });
-        res.writeHead(200, { "Content-Type": "application/json" }).end(body);
-      },
-      async (db) => {
-        // version-only (and "main" + version) time-travel the main chain
-        const v2 = await db.openTable("t", undefined, { version: 2 });
-        expect(v2.currentBranch()).toBeNull();
-        const mainV2 = await db.openTable("t", undefined, {
-          branch: "main",
-          version: 2,
-        });
-        expect(mainV2.currentBranch()).toBeNull();
-
-        // a non-main branch opens a handle scoped to that branch
-        const exp = await db.openTable("t", undefined, { branch: "exp" });
-        expect(exp.currentBranch()).toBe("exp");
-        const expV2 = await db.openTable("t", undefined, {
-          branch: "exp",
-          version: 2,
-        });
-        expect(expV2.currentBranch()).toBe("exp");
-      },
-    );
-  });
-
-  it("sends FTS options to remote tables", async () => {
-    let createIndexBody: Record<string, unknown> | undefined;
-
-    await withMockDatabase(
-      (req, res) => {
-        const path = req.url ?? "";
-        if (path.endsWith("/describe/")) {
-          res.writeHead(200, { "Content-Type": "application/json" }).end(
-            JSON.stringify({
-              name: "t",
-              version: 1,
-              schema: {
-                fields: [
-                  { name: "text", type: { type: "string" }, nullable: false },
-                ],
-              },
-            }),
-          );
-          return;
-        }
-
-        if (path.endsWith("/create_index/")) {
-          let raw = "";
-          req.on("data", (chunk) => {
-            raw += chunk;
-          });
-          req.on("end", () => {
-            createIndexBody = JSON.parse(raw);
-            res.writeHead(200).end();
-          });
-          return;
-        }
-
-        res.writeHead(404).end();
-      },
-      async (db) => {
-        const table = await db.openTable("t");
-        await table.createIndex("text", {
-          config: Index.fts({
-            blockSize: 256,
-            removeStopWords: true,
-            customStopWords: ["the"],
-          }),
-        });
-      },
-    );
-
-    expect(createIndexBody?.["column"]).toBe("text");
-    expect(createIndexBody?.["index_type"]).toBe("FTS");
-    expect(createIndexBody?.["block_size"]).toBe(256);
-    expect(createIndexBody?.["custom_stop_words"]).toEqual(["the"]);
-  });
-
-  it("diffs and merges remote branches", async () => {
-    const sampleDiff = {
-      fromBranch: "exp",
-      parentVersion: 1,
-      mainVersion: 2,
-      branchVersion: 3,
-      baseMoved: false,
-      rowCountMain: 3,
-      rowCountBranch: 3,
-      rowSummary: {
-        unchanged: 3,
-        newOnBase: 0,
-        newOnBranch: 0,
-        staleRecompute: 0,
-        inputsChanged: 0,
-        deltaAvailable: false,
-      },
-      addedColumns: [{ name: "tag", dataType: "utf8", nullable: true }],
-      removedColumns: [],
-      changedColumns: [],
-      addedIndexes: [],
-      removedIndexes: [],
-      mergeable: true,
-      mergeBlockers: [],
-    };
-    const mergeBodies: Record<string, unknown>[] = [];
-
-    await withMockDatabase(
-      (req, res) => {
-        const path = req.url ?? "";
-        if (path.endsWith("/describe/")) {
-          res.writeHead(200, { "Content-Type": "application/json" }).end(
-            JSON.stringify({
-              name: "t",
-              version: 2,
-              schema: { fields: [] },
-            }),
-          );
-          return;
-        }
-
-        let raw = "";
-        req.on("data", (chunk) => {
-          raw += chunk;
-        });
-        req.on("end", () => {
-          const body = raw ? JSON.parse(raw) : {};
-          if (path.endsWith("/branches/diff/")) {
-            // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
-            expect(body).toEqual({ from_branch: "exp" });
-            res
-              .writeHead(200, { "Content-Type": "application/json" })
-              .end(JSON.stringify(sampleDiff));
-            return;
-          }
-          if (path.endsWith("/branches/merge/")) {
-            mergeBodies.push(body);
-            const dryRun = body["dry_run"] === true;
-            const response = {
-              status: dryRun ? "ready" : "rejected",
-              diff: dryRun
-                ? sampleDiff
-                : {
-                    ...sampleDiff,
-                    mergeable: false,
-                    mergeBlockers: [
-                      { code: "baseMoved", message: "main has advanced" },
-                    ],
-                  },
-              preview: { promotedColumns: dryRun ? ["tag"] : [] },
-            };
-            res
-              .writeHead(dryRun ? 200 : 409, {
-                "Content-Type": "application/json",
-              })
-              .end(JSON.stringify(response));
-            return;
-          }
-          res.writeHead(404).end();
-        });
-      },
-      async (db) => {
-        const table = await db.openTable("t");
-        const branches = await table.branches();
-
-        await expect(branches.diff("exp")).resolves.toEqual(sampleDiff);
-
-        const rejected = await branches.merge("exp");
-        expect(rejected.status).toBe("rejected");
-        expect(rejected.diff.mergeBlockers).toEqual([
-          { code: "baseMoved", message: "main has advanced" },
-        ]);
-
-        const preview = await branches.merge("exp", true);
-        expect(preview.status).toBe("ready");
-        expect(preview.preview.promotedColumns).toEqual(["tag"]);
-      },
-    );
-
-    expect(mergeBodies).toEqual([
-      // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
-      { from_branch: "exp", dry_run: false },
-      // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
-      { from_branch: "exp", dry_run: true },
-    ]);
-  });
-
  describe("TlsConfig", () => {
    it("should create TlsConfig with all fields", () => {
      const tlsConfig: TlsConfig = {
@@ -2,7 +2,7 @@
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors

 import * as arrow from "../lancedb/arrow";
-import { sanitizeField, sanitizeMap, sanitizeType } from "../lancedb/sanitize";
+import { sanitizeField, sanitizeType } from "../lancedb/sanitize";

 describe("sanitize", function () {
  describe("sanitizeType function", function () {
@@ -181,15 +181,4 @@ describe("sanitize", function () {
      );
    });
  });
-
-  describe("sanitizeMap function", function () {
-    it.each([
-      ["no children", []],
-      ["two children", [{}, {}]],
-    ])("should reject a Map type with %s", function (_, children) {
-      expect(() => sanitizeMap({ children, keysSorted: false })).toThrow(
-        "Expected a Map type to have exactly one child",
-      );
-    });
-  });
 });
@@ -16,7 +16,6 @@ import {
  PhraseQuery,
  Table,
  connect,
-  tokenize,
 } from "../lancedb";
 import {
  Table as ArrowTable,
@@ -86,140 +85,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
      await expect(table.countRows()).resolves.toBe(3);
    });

-    it("should support branches", async () => {
-      await table.add([{ id: 1 }]);
-      expect(await table.countRows()).toBe(1);
-
-      expect(table.currentBranch()).toBeNull();
-
-      // fork an isolated, writable branch from main
-      const branch = await (await table.branches()).create("exp");
-      expect(branch.currentBranch()).toBe("exp");
-      expect(await branch.countRows()).toBe(1);
-      await branch.add([{ id: 2 }]);
-      expect(await branch.countRows()).toBe(2);
-      // main is untouched by branch writes
-      expect(await table.countRows()).toBe(1);
-
-      // listed, with main (null) as the parent
-      const list = await (await table.branches()).list();
-      expect(Object.keys(list)).toContain("exp");
-      expect(list["exp"].parentBranch).toBeNull();
-
-      // fromRef="main" is equivalent to the default
-      await (await table.branches()).create("exp2", "main");
-      const list2 = await (await table.branches()).list();
-      expect(list2["exp2"].parentBranch).toBeNull();
-
-      // checkout returns a handle scoped to the branch's latest
-      const checkedOut = await (await table.branches()).checkout("exp");
-      expect(checkedOut.currentBranch()).toBe("exp");
-      expect(await checkedOut.countRows()).toBe(2);
-
-      // delete removes it
-      await (await table.branches()).delete("exp");
-      await (await table.branches()).delete("exp2");
-      const after = await (await table.branches()).list();
-      expect(Object.keys(after)).not.toContain("exp");
-    });
-
-    it("should open a branch via open_table", async () => {
-      const db = await connect(tmpDir.name);
-      await table.add([{ id: 1 }]);
-      const branch = await (await table.branches()).create("exp");
-      await branch.add([{ id: 2 }]);
-
-      // open_table(..., { branch }) returns a handle scoped to the branch
-      const opened = await db.openTable("some_table", undefined, {
-        branch: "exp",
-      });
-      expect(await opened.countRows()).toBe(2);
-      // opening without branch still tracks main
-      expect(await (await db.openTable("some_table")).countRows()).toBe(1);
-    });
-
-    it("should open a branch at a version isolated from main and HEAD", async () => {
-      const db = await connect(tmpDir.name);
-      // main: a single fork-point row
-      const t = await db.createTable("bv_table", [{ id: 0 }]);
-      const mainV1 = await t.version();
-
-      // fork "exp", then advance exp AND main independently past the fork so
-      // they diverge while sharing version numbers
-      const exp = await (await t.branches()).create("exp");
-      await exp.add([{ id: 1 }]); // exp: {0, 1}
-      const expV2 = await exp.version();
-      await exp.add([{ id: 2 }]); // exp HEAD: {0, 1, 2}
-      await t.add([{ id: 100 }, { id: 101 }, { id: 102 }]); // main HEAD: {0,100,101,102}
-      expect(await t.version()).toBe(expV2);
-
-      // open exp at the shared version: the data must be exp's, not main's.
-      // count alone cannot prove this (main@v2 also exists), so assert
-      // provenance by content.
-      const pinned = await db.openTable("bv_table", undefined, {
-        branch: "exp",
-        version: expV2,
-      });
-      expect(await pinned.countRows()).toBe(2); // not exp HEAD (3), not main@v2 (4)
-      expect(await pinned.countRows("id = 1")).toBe(1); // exp's post-fork row
-      expect(await pinned.countRows("id = 100")).toBe(0); // main's rows invisible
-
-      // the same coordinate is reachable directly via branches().checkout(name, version)
-      const pinnedDirect = await (await t.branches()).checkout("exp", expV2);
-      expect(await pinnedDirect.countRows()).toBe(2);
-
-      // the HEADs are unaffected
-      expect(
-        await (
-          await db.openTable("bv_table", undefined, { branch: "exp" })
-        ).countRows(),
-      ).toBe(3);
-      expect(await (await db.openTable("bv_table")).countRows()).toBe(4);
-
-      // version-only (no branch) time-travels main itself: its fork-point
-      // version holds only main's first row, and the shared version number
-      // resolves to main's data, not the branch's ("opens main at the version")
-      const oldMain = await db.openTable("bv_table", undefined, {
-        version: mainV1,
-      });
-      expect(await oldMain.countRows()).toBe(1);
-      const sharedOnMain = await db.openTable("bv_table", undefined, {
-        version: expV2,
-      });
-      expect(await sharedOnMain.countRows()).toBe(4); // main@v2, not exp@v2 (2)
-
-      // detached head: writing to a pinned version is rejected
-      await expect(pinned.add([{ id: 9 }])).rejects.toThrow(
-        /cannot be modified/,
-      );
-
-      // a nonexistent version is rejected -- on main, and on a branch (a
-      // distinct resolution path, on the branch's manifests)
-      await expect(
-        db.openTable("bv_table", undefined, { version: 9999 }),
-      ).rejects.toThrow();
-      await expect(
-        db.openTable("bv_table", undefined, { branch: "exp", version: 9999 }),
-      ).rejects.toThrow();
-
-      // checkoutLatest re-attaches the pinned handle to the BRANCH's HEAD
-      // (writable again), not main's HEAD (4), and not staying pinned (2)
-      await pinned.checkoutLatest();
-      expect(await pinned.countRows()).toBe(3); // exp HEAD
-      await pinned.add([{ id: 3 }]);
-      expect(await pinned.countRows()).toBe(4); // writable again
-    });
-
-    it("rejects invalid branch inputs", async () => {
-      const branches = await table.branches();
-      await expect(branches.create("")).rejects.toThrow("non-empty");
-      await expect(branches.checkout("")).rejects.toThrow("non-empty");
-      await expect(branches.delete("")).rejects.toThrow("non-empty");
-      await expect(branches.create("bad", "main", -1)).rejects.toThrow(
-        "non-negative",
-      );
-    });
-
    it("should show table stats", async () => {
      await table.add([{ id: 1 }, { id: 2 }]);
      await table.add([{ id: 1 }]);
@@ -527,14 +392,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
      );
    });

-    it("should expose useLsm on takeRowIds as the base-only escape hatch", async () => {
-      await table.add([{ id: 1 }, { id: 2 }, { id: 3 }]);
-      // useLsm(false) is reachable on TakeQuery (the escape hatch for MemWAL tables,
-      // where take-by-row-id auto-routes to the LSM scanner and is rejected).
-      const res = await table.takeRowIds([0, 2]).useLsm(false).toArray();
-      expect(res.map((r) => r.id)).toEqual([1, 3]);
-    });
-
    it("should throw for negative number in takeRowIds", () => {
      expect(() => table.takeRowIds([-1])).toThrow("Row id cannot be negative");
      expect(() => table.takeRowIds([0, -5, 2])).toThrow(
@@ -858,13 +715,11 @@ describe("When creating an index", () => {
    expect(fs.readdirSync(indexDir)).toHaveLength(1);
    const indices = await tbl.listIndices();
    expect(indices.length).toBe(1);
-    expect(indices[0]).toEqual(
-      expect.objectContaining({
-        name: "vec_idx",
-        indexType: "IvfPq",
-        columns: ["vec"],
-      }),
-    );
+    expect(indices[0]).toEqual({
+      name: "vec_idx",
+      indexType: "IvfPq",
+      columns: ["vec"],
+    });
    const stats = await tbl.indexStats("vec_idx");
    expect(stats).toBeDefined();

@@ -926,22 +781,10 @@ describe("When creating an index", () => {
    expect(indices2.length).toBe(0);
  });

-  it("should preserve canonical nested field paths across index lifecycle", async () => {
+  it("should create and search a nested vector index", async () => {
    const db = await connect(tmpDir.name);
    const nestedSchema = new Schema([
-      new Field("rowId", new Int32(), true),
-      new Field("row-id", new Int32(), true),
-      new Field("userId", new Int32(), true),
-      new Field(
-        "metadata",
-        new Struct([new Field("user_id", new Int32(), true)]),
-        true,
-      ),
-      new Field(
-        "MetaData",
-        new Struct([new Field("userId", new Int32(), true)]),
-        true,
-      ),
+      new Field("id", new Int32(), true),
      new Field(
        "image",
        new Struct([
@@ -953,146 +796,27 @@ describe("When creating an index", () => {
        ]),
        true,
      ),
-      new Field(
-        "payload",
-        new Struct([new Field("text", new Utf8(), true)]),
-        true,
-      ),
-      new Field(
-        "meta-data",
-        new Struct([new Field("user-id", new Int32(), true)]),
-        true,
-      ),
-      new Field(
-        "literal",
-        new Struct([new Field("a.b", new Int32(), true)]),
-        true,
-      ),
    ]);
    const nestedTable = await db.createTable(
-      "nested_field_index_lifecycle",
+      "nested_vector",
      makeArrowTable(
-        Array.from({ length: 300 }, (_, rowId) => ({
-          rowId,
-          "row-id": rowId,
-          userId: rowId,
-          metadata: { ["user_id"]: rowId },
-          ["MetaData"]: { userId: rowId },
-          image: { embedding: [rowId, rowId + 1] },
-          payload: { text: `document ${rowId}` },
-          "meta-data": { "user-id": rowId },
-          literal: { "a.b": rowId },
+        Array.from({ length: 300 }, (_, id) => ({
+          id,
+          image: { embedding: [id, id + 1] },
        })),
        { schema: nestedSchema },
      ),
    );

-    await nestedTable.createIndex("rowId", {
-      config: Index.btree(),
-      name: "row_id_idx",
-    });
-    await nestedTable.createIndex("`row-id`", {
-      config: Index.btree(),
-      name: "row_dash_id_idx",
-    });
-    await nestedTable.createIndex("userId", {
-      config: Index.btree(),
-      name: "top_user_id_idx",
-    });
-    await nestedTable.createIndex("metadata.user_id", {
-      config: Index.btree(),
-      name: "nested_user_id_idx",
-    });
-    await nestedTable.createIndex("MetaData.userId", {
-      config: Index.btree(),
-      name: "mixed_case_metadata_user_id_idx",
-    });
-    await nestedTable.createIndex("`meta-data`.`user-id`", {
-      config: Index.btree(),
-      name: "escaped_names_idx",
-    });
-    await nestedTable.createIndex("literal.`a.b`", {
-      config: Index.btree(),
-      name: "literal_dot_idx",
-    });
    await nestedTable.createIndex("image.embedding", {
      name: "image_embedding_idx",
    });
-    await nestedTable.createIndex("payload.text", {
-      config: Index.fts({ withPosition: false }),
-      name: "payload_text_idx",
-    });
-
    const indices = await nestedTable.listIndices();
-    expect(indices).toEqual(
-      expect.arrayContaining([
-        expect.objectContaining({
-          name: "row_id_idx",
-          indexType: "BTree",
-          columns: ["rowId"],
-        }),
-        expect.objectContaining({
-          name: "row_dash_id_idx",
-          indexType: "BTree",
-          columns: ["`row-id`"],
-        }),
-        expect.objectContaining({
-          name: "top_user_id_idx",
-          indexType: "BTree",
-          columns: ["userId"],
-        }),
-        expect.objectContaining({
-          name: "nested_user_id_idx",
-          indexType: "BTree",
-          columns: ["metadata.user_id"],
-        }),
-        expect.objectContaining({
-          name: "mixed_case_metadata_user_id_idx",
-          indexType: "BTree",
-          columns: ["MetaData.userId"],
-        }),
-        expect.objectContaining({
-          name: "escaped_names_idx",
-          indexType: "BTree",
-          columns: ["`meta-data`.`user-id`"],
-        }),
-        expect.objectContaining({
-          name: "literal_dot_idx",
-          indexType: "BTree",
-          columns: ["literal.`a.b`"],
-        }),
-        expect.objectContaining({
-          name: "image_embedding_idx",
-          indexType: "IvfPq",
-          columns: ["image.embedding"],
-        }),
-        expect.objectContaining({
-          name: "payload_text_idx",
-          indexType: "FTS",
-          columns: ["payload.text"],
-        }),
-      ]),
-    );
-
-    const stats = await nestedTable.indexStats(
-      "mixed_case_metadata_user_id_idx",
-    );
-    expect(stats?.numIndexedRows).toEqual(300);
-    expect(stats?.indexType).toEqual("BTREE");
-
-    const filtered = await nestedTable
-      .query()
-      .where("MetaData.userId = 42")
-      .limit(1)
-      .toArray();
-    expect(filtered[0].MetaData.userId).toEqual(42);
-
-    const escapedFiltered = await nestedTable
-      .query()
-      .where("`row-id` = 43")
-      .limit(1)
-      .toArray();
-    expect(escapedFiltered[0]["row-id"]).toEqual(43);
+    expect(indices).toContainEqual({
+      name: "image_embedding_idx",
+      indexType: "IvfPq",
+      columns: ["image.embedding"],
+    });

    const explicit = await nestedTable
      .query()
@@ -1105,37 +829,7 @@ describe("When creating an index", () => {
      .nearestTo([0.0, 1.0])
      .limit(1)
      .toArray();
-    expect(inferred[0].rowId).toEqual(explicit[0].rowId);
-
-    await nestedTable.add([
-      {
-        rowId: 300,
-        "row-id": 300,
-        userId: 300,
-        metadata: { ["user_id"]: 300 },
-        ["MetaData"]: { userId: 300 },
-        image: { embedding: [300.0, 301.0] },
-        payload: { text: "document 300" },
-        "meta-data": { "user-id": 300 },
-        literal: { "a.b": 300 },
-      },
-    ]);
-    await nestedTable.optimize();
-    const indicesAfterOptimize = await nestedTable.listIndices();
-    expect(indicesAfterOptimize).toEqual(
-      expect.arrayContaining([
-        expect.objectContaining({
-          name: "mixed_case_metadata_user_id_idx",
-          indexType: "BTree",
-          columns: ["MetaData.userId"],
-        }),
-        expect.objectContaining({
-          name: "image_embedding_idx",
-          indexType: "IvfPq",
-          columns: ["image.embedding"],
-        }),
-      ]),
-    );
+    expect(inferred[0].id).toEqual(explicit[0].id);
  });

  it("should report multiple nested vector candidates", async () => {
@@ -1269,13 +963,11 @@ describe("When creating an index", () => {
    expect(fs.readdirSync(indexDir)).toHaveLength(1);
    const indices = await tbl.listIndices();
    expect(indices.length).toBe(1);
-    expect(indices[0]).toEqual(
-      expect.objectContaining({
-        name: "vec_idx",
-        indexType: "IvfHnswSq",
-        columns: ["vec"],
-      }),
-    );
+    expect(indices[0]).toEqual({
+      name: "vec_idx",
+      indexType: "IvfHnswSq",
+      columns: ["vec"],
+    });

    // Search without specifying the column
    let rst = await tbl
@@ -1448,20 +1140,6 @@ describe("When creating an index", () => {
    expect(fs.readdirSync(indexDir)).toHaveLength(1);
  });

-  test("create an FM index", async () => {
-    // FM-Index accelerates substring search on a string/binary column.
-    const db = await connect(tmpDir.name);
-    const fmTbl = await db.createTable("fm_table", [
-      { id: 0, text: "hello world" },
-      { id: 1, text: "foo bar" },
-    ]);
-    await fmTbl.createIndex("text", {
-      config: Index.fm(),
-    });
-    const indexDir = path.join(tmpDir.name, "fm_table.lance", "_indices");
-    expect(fs.readdirSync(indexDir)).toHaveLength(1);
-  });
-
  test("should be able to get index stats", async () => {
    await tbl.createIndex("id");

@@ -1621,35 +1299,6 @@ describe("When creating an index", () => {
    expect(rst64Query.toString()).toEqual(rst64Search.toString());
    expect(rst64Query.numRows).toBe(2);
  });
-
-  it("should expose rich metadata fields on IndexConfig", async () => {
-    await tbl.createIndex("id", { config: Index.btree() });
-    await tbl.createIndex("vec");
-
-    const indicesByName = Object.fromEntries(
-      (await tbl.listIndices()).map((idx) => [idx.name, idx]),
-    );
-
-    const scalarIdx = indicesByName["id_idx"];
-    expect(scalarIdx).toBeDefined();
-    expect(typeof scalarIdx.indexUuid).toBe("string");
-    expect(scalarIdx.numIndexedRows).toBe(300);
-    expect(scalarIdx.numUnindexedRows).toBe(0);
-    expect(scalarIdx.numSegments).toBeGreaterThanOrEqual(1);
-    expect(scalarIdx.sizeBytes).toBeGreaterThan(0);
-    // Use toString check to avoid cross-realm instanceof failures with native Date objects
-    expect(Object.prototype.toString.call(scalarIdx.createdAt)).toBe(
-      "[object Date]",
-    );
-    expect((scalarIdx.createdAt as Date).getTime()).toBeGreaterThan(0);
-    expect(typeof scalarIdx.indexDetails).toBe("object");
-
-    const vectorIdx = indicesByName["vec_idx"];
-    expect(vectorIdx).toBeDefined();
-    expect(typeof vectorIdx.indexUuid).toBe("string");
-    expect(vectorIdx.numIndexedRows).toBe(300);
-    expect(typeof vectorIdx.indexDetails).toBe("object");
-  });
 });

 describe("When querying a table", () => {
@@ -2316,75 +1965,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
      expect(results2[0].text).toBe(data[1].text);
    });

-    test("tokenizes FTS queries by column or index name", async () => {
-      const db = await connect(tmpDir.name);
-      const data = [
-        {
-          text: "Running in cafés",
-          japanese: "Hello, こんにちは世界!",
-          vector: [0.1, 0.2, 0.3],
-        },
-      ];
-      const table = await db.createTable("test", data);
-      await table.createIndex("text", {
-        config: Index.fts({ baseTokenizer: "simple" }),
-      });
-      await table.createIndex("japanese", {
-        config: Index.fts({
-          baseTokenizer: "icu",
-          stem: false,
-          removeStopWords: false,
-        }),
-        name: "japanese_icu_idx",
-      });
-
-      await expect(table.tokenize("hello", {} as never)).rejects.toThrow(
-        "Specify exactly one",
-      );
-      await expect(
-        table.tokenize("hello", {
-          column: "text",
-          indexName: "text_idx",
-        } as never),
-      ).rejects.toThrow("Specify exactly one");
-
-      const simpleTokens = await table.tokenize("Running in cafés", {
-        column: "text",
-      });
-      expect(simpleTokens).toEqual([
-        { text: "run", position: 0 },
-        { text: "cafe", position: 2 },
-      ]);
-
-      const icuTokens = await table.tokenize("Hello, こんにちは世界!", {
-        indexName: "japanese_icu_idx",
-      });
-      expect(icuTokens).toEqual([
-        { text: "hello", position: 0 },
-        { text: "こんにちは", position: 1 },
-        { text: "世界", position: 2 },
-      ]);
-
-      const directSimpleTokens = await tokenize("Running in cafés", {
-        baseTokenizer: "simple",
-      });
-      expect(directSimpleTokens).toEqual([
-        { text: "run", position: 0 },
-        { text: "cafe", position: 2 },
-      ]);
-
-      const directIcuTokens = await tokenize("Hello, こんにちは世界!", {
-        baseTokenizer: "icu",
-        stem: false,
-        removeStopWords: false,
-      });
-      expect(directIcuTokens).toEqual([
-        { text: "hello", position: 0 },
-        { text: "こんにちは", position: 1 },
-        { text: "世界", position: 2 },
-      ]);
-    });
-
    test("full text search fast search", async () => {
      const db = await connect(tmpDir.name);
      const data = [{ text: "hello world", vector: [0.1, 0.2, 0.3], id: 1 }];
@@ -2535,35 +2115,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
      expect(results3.length).toBe(1);
    });

-    test("full text search with custom posting block size", async () => {
-      const db = await connect(tmpDir.name);
-      const data = [
-        { text: "hello world", vector: [0.1, 0.2, 0.3] },
-        { text: "goodbye world", vector: [0.4, 0.5, 0.6] },
-      ];
-      const table = await db.createTable("test", data);
-      await table.createIndex("text", {
-        config: Index.fts({ blockSize: 256 }),
-      });
-
-      const index = (await table.listIndices()).find(
-        (index) => index.indexType === "FTS",
-      );
-      expect(index?.indexVersion).toBe(3);
-      expect(
-        (index?.indexDetails as Record<string, unknown>)["block_size"],
-      ).toBe(256);
-
-      const results = await table.search("hello").toArray();
-      expect(results[0].text).toBe(data[0].text);
-    });
-
-    test("rejects invalid full text posting block size", () => {
-      expect(() => Index.fts({ blockSize: 129 as 128 | 256 })).toThrow(
-        "128 or 256",
-      );
-    });
-
    test("full text search without lowercase", async () => {
      const db = await connect(tmpDir.name);
      const data = [
@@ -2769,15 +2320,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
  },
 );

-test("tokenize supports custom stop words", async () => {
-  const tokens = await tokenize("the lance data", {
-    stem: false,
-    removeStopWords: true,
-    customStopWords: ["lance"],
-  });
-  expect(tokens.map((token) => token.text)).toEqual(["the", "data"]);
-});
-
 describe("when calling explainPlan", () => {
  let tmpDir: tmp.DirResult;
  let table: Table;
@@ -2821,13 +2363,8 @@ describe("when calling analyzePlan", () => {
      .fill(1)
      .map(() => Math.random());
    const plan = await table.query().nearestTo(queryVec).analyzePlan();
+    console.log("Query Plan:\n", plan); // <--- Print the plan
    expect(plan).toMatch("AnalyzeExec");
-
-    const fullPlan = await table
-      .query()
-      .nearestTo(queryVec)
-      .analyzePlan("full");
-    expect(fullPlan).toMatch("AnalyzeExec");
  });
 });

@@ -3113,56 +2650,6 @@ describe("setLsmWriteSpec / unsetLsmWriteSpec", () => {
      }),
    ).rejects.toThrow();
  });
-
-  it("reads back the installed spec via getLsmWriteSpec", async () => {
-    const conn = await connect(tmpDir.name);
-    const table = await makeTable(conn);
-    await table.setUnenforcedPrimaryKey("id");
-
-    // Nothing installed yet.
-    expect(await table.getLsmWriteSpec()).toBeUndefined();
-
-    // A real scalar index is needed to name it as a maintained index.
-    await table.add([{ id: 1 }, { id: 2 }, { id: 3 }]);
-    await table.createIndex("id");
-    const indexName = (await table.listIndices())[0].name;
-
-    // Bucket spec round-trips, including maintained indexes and writer config
-    // defaults. Lance writer-config keys are canonically snake_case.
-    // biome-ignore lint/style/useNamingConvention: Lance writer-config keys are snake_case
-    const writerConfigDefaults = { durable_write: "false" };
-    await table.setLsmWriteSpec({
-      specType: "bucket",
-      column: "id",
-      numBuckets: 4,
-      maintainedIndexes: [indexName],
-      writerConfigDefaults,
-    });
-    const spec = await table.getLsmWriteSpec();
-    expect(spec).toBeDefined();
-    expect(spec?.specType).toBe("bucket");
-    expect(spec?.column).toBe("id");
-    expect(spec?.numBuckets).toBe(4);
-    expect(spec?.maintainedIndexes).toEqual([indexName]);
-    expect(spec?.writerConfigDefaults).toEqual(writerConfigDefaults);
-
-    // After unset, undefined again.
-    await table.unsetLsmWriteSpec();
-    expect(await table.getLsmWriteSpec()).toBeUndefined();
-
-    // Identity round-trips (column recovered from the schema).
-    await table.setLsmWriteSpec({ specType: "identity", column: "id" });
-    const identity = await table.getLsmWriteSpec();
-    expect(identity?.specType).toBe("identity");
-    expect(identity?.column).toBe("id");
-    await table.unsetLsmWriteSpec();
-
-    // Unsharded round-trips (no routing column).
-    await table.setLsmWriteSpec({ specType: "unsharded" });
-    const unsharded = await table.getLsmWriteSpec();
-    expect(unsharded?.specType).toBe("unsharded");
-    expect(unsharded?.column).toBeFalsy();
-  });
 });

 describe("LSM merge insert", () => {
@@ -3216,14 +2703,14 @@ describe("LSM merge insert", () => {
    await table.closeLsmWriters();
  });

-  it("falls back to the standard path with useLsm(false)", async () => {
+  it("falls back to the standard path with useLsmWrite(false)", async () => {
    const conn = await connect(tmpDir.name);
    const table = await bucketTable(conn);

    const res = await table
      .mergeInsert("id")
      .whenNotMatchedInsertAll()
-      .useLsm(false)
+      .useLsmWrite(false)
      .execute([
        { id: "b", value: 9 },
        { id: "e", value: 5 },
@@ -3257,36 +2744,4 @@ describe("LSM merge insert", () => {
        .execute([{ id: "g", value: 7 }]),
    ).rejects.toThrow();
  });
-
-  it("auto-routes reads through the MemWAL scanner", async () => {
-    const conn = await connect(tmpDir.name);
-    const table = await bucketTable(conn); // base ids "a", "b"
-
-    await table
-      .mergeInsert("id")
-      .whenMatchedUpdateAll()
-      .whenNotMatchedInsertAll()
-      .execute([{ id: "c", value: 3 }]);
-
-    // Default read auto-routes and includes the active memtable row.
-    const lsm = await table.query().toArray();
-    expect(lsm.map((r) => r.id).sort()).toEqual(["a", "b", "c"]);
-
-    // useLsm(false) bypasses the MemWAL and reads the base table only.
-    const baseOnly = await table.query().useLsm(false).toArray();
-    expect(baseOnly.map((r) => r.id).sort()).toEqual(["a", "b"]);
-  });
-
-  it("reads the base table when no LSM spec is installed", async () => {
-    const conn = await connect(tmpDir.name);
-    const table = await conn.createEmptyTable(
-      "plain",
-      new arrow.Schema([new arrow.Field("id", new arrow.Utf8(), false)]),
-    );
-    // No spec: default read and useLsm(false) both succeed against the base table.
-    await expect(table.query().toArray()).resolves.toBeDefined();
-    await expect(table.query().useLsm(false).toArray()).resolves.toBeDefined();
-    // useLsm(true) demands MemWAL routing; without a spec it errors.
-    await expect(table.query().useLsm(true).toArray()).rejects.toThrow();
-  });
 });
@@ -29,14 +29,8 @@ test("full text search", async () => {
    const tbl = await db.createTable("myVectors", data, { mode: "overwrite" });

    await tbl.createIndex("doc", {
-      config: lancedb.Index.fts({
-        stem: false,
-        removeStopWords: true,
-        customStopWords: ["banana"],
-      }),
+      config: lancedb.Index.fts(),
    });
-    const tokens = await tbl.tokenize("apple banana", { column: "doc" });
-    expect(tokens.map((token) => token.text)).toEqual(["apple"]);

    // --8<-- [start:full_text_search]
    const result = await tbl
@@ -84,20 +84,6 @@ export interface CreateTableOptions {
 }

 export interface OpenTableOptions {
-  /**
-   * Open the table scoped to this branch instead of the default branch.
-   *
-   * Reads and writes on the returned table operate in the branch's context.
-   */
-  branch?: string;
-  /**
-   * Open the table pinned to this version, producing a read-only view.
-   *
-   * Composes with {@link OpenTableOptions.branch}: when both are set, opens
-   * that branch at the version; otherwise opens `main` at the version. Call
-   * `checkoutLatest` to return to a writable state.
-   */
-  version?: number;
  /**
   * Configuration for object storage.
   *
@@ -497,20 +483,7 @@ export class LocalConnection extends Connection {
      options?.indexCacheSize,
    );

-    let table: Table = new LocalTable(innerTable);
-    // "main" is the default branch, so treat it as no branch. On a real branch,
-    // scope and pin in one step (yielding "version V of branch B"); otherwise
-    // pin the version, if any, against main.
-    const branch =
-      options?.branch != null && options.branch !== "main"
-        ? options.branch
-        : undefined;
-    if (branch != null) {
-      table = await (await table.branches()).checkout(branch, options?.version);
-    } else if (options?.version != null) {
-      await table.checkout(options.version);
-    }
-    return table;
+    return new LocalTable(innerTable);
  }

  async cloneTable(
@@ -13,21 +13,13 @@ import {
  Connection as LanceDbConnection,
  JsHeaderProvider as NativeJsHeaderProvider,
  Session,
-  tokenize as nativeTokenize,
 } from "./native.js";

 import { HeaderProvider } from "./header";
-import type { BaseTokenizer } from "./indices";
-import type { FtsToken } from "./table";

 // Re-export native header provider for use with connectWithHeaderProvider
 export { JsHeaderProvider as NativeJsHeaderProvider } from "./native.js";

-// OpenTelemetry metrics bridge. Only the high-level entry point is public; the
-// underlying recorder/catalog/snapshot functions remain internal plumbing that
-// `otel.ts` consumes from the native module.
-export { instrumentLanceDbMetrics } from "./otel";
-
 export {
  AddColumnsSql,
  ConnectionOptions,
@@ -46,7 +38,6 @@ export {
  FragmentSummaryStats,
  Tags,
  TagContents,
-  BranchContents,
  MergeResult,
  AddResult,
  AddColumnsResult,
@@ -60,7 +51,6 @@ export {
  SplitHashOptions,
  SplitSequentialOptions,
  ShuffleOptions,
-  OAuthConfig as NativeOAuthConfig,
 } from "./native.js";

 export {
@@ -93,7 +83,6 @@ export {
  QueryBase,
  VectorQuery,
  TakeQuery,
-  AnalyzePlanDistributedMetrics,
  QueryExecutionOptions,
  ColumnOrdering,
  FullTextSearchOptions,
@@ -118,27 +107,15 @@ export {
  HnswPqOptions,
  HnswSqOptions,
  FtsOptions,
-  BaseTokenizer,
 } from "./indices";

 export {
  Table,
-  Branches,
-  BranchColumnSummary,
-  BranchColumnChange,
-  BranchIndexSummary,
-  BranchRowCountSummary,
-  MergeBlocker,
-  BranchDiff,
-  MergePreview,
-  MergeBranchResult,
  AddDataOptions,
  UpdateOptions,
  OptimizeOptions,
  Version,
  WriteProgress,
-  FtsToken,
-  TokenizeTableOptions,
  LsmWriteSpec,
  ColumnAlteration,
  FieldMetadataUpdate,
@@ -151,8 +128,6 @@ export {
  TokenResponse,
 } from "./header";

-export { OAuthConfig, OAuthFlowType } from "./oauth";
-
 export { MergeInsertBuilder, WriteExecutionOptions } from "./merge";

 export * as embedding from "./embedding";
@@ -170,79 +145,6 @@ export {
 } from "./arrow";
 export { IntoSql, packBits } from "./util";

-/**
- * Options for tokenizing a full-text search query without a table index.
- */
-export interface TokenizeOptions {
-  /**
-   * The tokenizer to use. The default is "simple".
-   */
-  baseTokenizer?: BaseTokenizer;
-
-  /** Language for stemming and stop words. */
-  language?: string;
-
-  /** Maximum token length; tokens longer than this are ignored. */
-  maxTokenLength?: number;
-
-  /** Whether to lowercase tokens. */
-  lowercase?: boolean;
-
-  /** Whether to stem tokens. */
-  stem?: boolean;
-
-  /** Whether to remove stop words. */
-  removeStopWords?: boolean;
-
-  /**
-   * Custom stop words that replace the built-in list for `language`.
-   *
-   * This option only affects tokenization when `removeStopWords` is true.
-   *
-   * `undefined` keeps the built-in language list. An empty array explicitly
-   * replaces it with no stop words.
-   */
-  customStopWords?: string[];
-
-  /** Whether to fold ASCII characters. */
-  asciiFolding?: boolean;
-
-  /** N-gram minimum length. */
-  ngramMinLength?: number;
-
-  /** N-gram maximum length. */
-  ngramMaxLength?: number;
-
-  /** Whether to only emit token prefixes for the n-gram tokenizer. */
-  prefixOnly?: boolean;
-}
-
-/**
- * Tokenize a full-text search query using an explicit tokenizer.
- *
- * This does not require a table or FTS index. The tokenizer options match
- * {@link Index.fts}.
- */
-export async function tokenize(
-  query: string,
-  options?: Partial<TokenizeOptions>,
-): Promise<FtsToken[]> {
-  return await nativeTokenize(
-    query,
-    options?.baseTokenizer,
-    options?.language,
-    options?.maxTokenLength,
-    options?.lowercase,
-    options?.stem,
-    options?.removeStopWords,
-    options?.customStopWords,
-    options?.asciiFolding,
-    options?.ngramMinLength,
-    options?.ngramMaxLength,
-    options?.prefixOnly,
-  );
-}
-
 /**
 * Connect to a LanceDB instance at the given URI.
 *
@@ -486,16 +486,6 @@ export interface IvfFlatOptions {
  sampleRate?: number;
 }

-export type BaseTokenizer =
-  | "simple"
-  | "whitespace"
-  | "raw"
-  | "ngram"
-  | "icu"
-  | "icu/split"
-  | `jieba/${string}`
-  | `lindera/${string}`;
-
 /**
 * Options to create a full text search index
 */
@@ -519,12 +509,8 @@ export interface FtsOptions {
   * "whitespace" - Whitespace tokenizer. This tokenizer splits the text into tokens using whitespace as a delimiter.
   *
   * "raw" - Raw tokenizer. This tokenizer does not split the text into tokens and indexes the entire text as a single token.
-   *
-   * "icu" - ICU dictionary-based word segmentation.
-   *
-   * "icu/split" - ICU segmentation with simple-style delimiter splitting.
   */
-  baseTokenizer?: BaseTokenizer;
+  baseTokenizer?: "simple" | "whitespace" | "raw" | "ngram";

  /**
   * language for stemming and stop words
@@ -553,16 +539,6 @@ export interface FtsOptions {
   */
  removeStopWords?: boolean;

-  /**
-   * Custom stop words that replace the built-in list for `language`.
-   *
-   * This option only affects tokenization when `removeStopWords` is true.
-   *
-   * `undefined` keeps the built-in language list. An empty array explicitly
-   * replaces it with no stop words.
-   */
-  customStopWords?: string[];
-
  /**
   * whether to remove punctuation
   */
@@ -582,14 +558,6 @@ export interface FtsOptions {
   * whether to only index the prefix of the token for ngram tokenizer
   */
  prefixOnly?: boolean;
-
-  /**
-   * Number of documents per compressed posting block.
-   *
-   * The default is 128. Supported values are 128 and 256. A value of 256 uses
-   * the experimental FTS V3 format and may introduce breaking changes.
-   */
-  blockSize?: 128 | 256;
 }

 export class Index {
@@ -734,17 +702,6 @@ export class Index {
    return new Index(LanceDbIndex.labelList());
  }

-  /**
-   * Create an FM-Index.
-   *
-   * An FM-Index is a scalar index on string or binary columns that accelerates
-   * substring search, i.e. `contains(col, 'needle')`. Unlike the tokenized
-   * full-text-search index, it matches arbitrary substrings of the raw bytes.
-   */
-  static fm() {
-    return new Index(LanceDbIndex.fm());
-  }
-
  /**
   * Create a full text search index
   *
@@ -765,12 +722,10 @@ export class Index {
        options?.lowercase,
        options?.stem,
        options?.removeStopWords,
-        options?.customStopWords,
        options?.asciiFolding,
        options?.ngramMinLength,
        options?.ngramMaxLength,
        options?.prefixOnly,
-        options?.blockSize,
      ),
    );
  }
@@ -88,17 +88,21 @@ export class MergeInsertBuilder {
    );
  }
  /**
-   * Control MemWAL routing for this merge.
+   * Controls whether the merge uses the MemWAL LSM write path.
   *
   * By default (unset), a `mergeInsert` on a table with an LSM write spec is
-   * routed through Lance's MemWAL shard writer, and a table without one uses the
-   * standard path.
+   * routed through Lance's MemWAL shard writer, and a table without one uses
+   * the standard path. Pass `false` to force the standard path even when a
+   * spec is set. Pass `true` to require a spec — `mergeInsert` rejects if none
+   * is installed.
   *
-   * @param enable - `true` forces MemWAL routing and errors if the table has no
-   * LSM write spec. `false` forces the standard write path even when a spec is set.
+   * @param useLsmWrite - Whether to use the LSM write path.
   */
-  useLsm(enable: boolean): MergeInsertBuilder {
-    return new MergeInsertBuilder(this.#native.useLsm(enable), this.#schema);
+  useLsmWrite(useLsmWrite: boolean): MergeInsertBuilder {
+    return new MergeInsertBuilder(
+      this.#native.useLsmWrite(useLsmWrite),
+      this.#schema,
+    );
  }
  /**
   * Controls how an LSM merge checks that its input targets a single shard.
@@ -1,76 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-/**
- * OAuth authentication flow types.
- */
-export enum OAuthFlowType {
-  /** Client Credentials grant (service-to-service / M2M). */
-  ClientCredentials = "client_credentials",
-  /** Azure Managed Identity via IMDS. */
-  AzureManagedIdentity = "azure_managed_identity",
-}
-
-/**
- * OAuth configuration for LanceDB authentication.
- *
- * This is the public TypeScript OAuth configuration type. The generated
- * `NativeOAuthConfig` type has the same runtime shape but is an implementation
- * detail of the napi-rs binding.
- *
- * All token acquisition and refresh is handled in the Rust layer.
- * This config is passed through to Rust via napi-rs.
- *
- * @example Client Credentials (service-to-service):
- * ```typescript
- * const config: OAuthConfig = {
- *   issuerUrl: "https://login.microsoftonline.com/{tenant}/v2.0",
- *   clientId: "app-id",
- *   clientSecret: "secret",
- *   scopes: ["api://lancedb-api/.default"],
- * };
- * ```
- *
- * @example Azure Managed Identity:
- * ```typescript
- * const config: OAuthConfig = {
- *   issuerUrl: "https://login.microsoftonline.com/{tenant}/v2.0",
- *   clientId: "app-id",
- *   scopes: ["api://lancedb-api/.default"],
- *   flow: OAuthFlowType.AzureManagedIdentity,
- * };
- * ```
- */
-export interface OAuthConfig {
-  /**
-   * OIDC issuer URL or OAuth authority URL.
-   * For Azure: `https://login.microsoftonline.com/{tenant_id}/v2.0`
-   */
-  issuerUrl: string;
-
-  /** Application / Client ID. */
-  clientId: string;
-
-  /**
-   * OAuth scopes to request.
-   * For Azure managed identity, exactly one scope or resource is required.
-   * For example: `["api://{app_id}/.default"]`
-   */
-  scopes: string[];
-
-  /** Authentication flow (default: ClientCredentials). */
-  flow?: OAuthFlowType;
-
-  /** Client secret (required for ClientCredentials). */
-  clientSecret?: string;
-
-  /** Client ID for user-assigned managed identity (AzureManagedIdentity). */
-  managedIdentityClientId?: string;
-
-  /**
-   * Seconds before expiry to trigger proactive refresh (default: 300).
-   * Keep this well below the token TTL; if it is greater than or equal to
-   * the TTL, each request refreshes the token.
-   */
-  refreshBufferSecs?: number;
-}
@@ -1,137 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-import {
-  type Attributes,
-  type MeterProvider,
-  type ObservableResult,
-  metrics,
-} from "@opentelemetry/api";
-
-import {
-  lancedbMetricsCatalog,
-  registerLancedbMetricsRecorder,
-  snapshotLancedbMetrics,
-} from "./native";
-
-let instrumented = false;
-
-/**
- * Register LanceDB metrics as OpenTelemetry observable instruments.
- *
- * Installs a process-global metrics recorder and creates one observable
- * instrument per LanceDB metric (currently object store request counts, bytes,
- * latency, errors, and throttles) on the given (or global) `MeterProvider`. The
- * configured `MetricReader` then collects them on its own schedule.
- *
- * Counters and gauges map directly to observable counters/gauges. Because
- * OpenTelemetry has no asynchronous histogram instrument, each histogram is
- * exported Prometheus-style as cumulative `le` bucket counts (`<name>_bucket`,
- * with an `le` attribute) plus `<name>_count` and `<name>_sum`.
- *
- * Requires `@opentelemetry/api` (a dependency) and, to actually export, an
- * OpenTelemetry SDK such as `@opentelemetry/sdk-metrics`.
- *
- * @param meterProvider The provider to register instruments on. Defaults to the
- *   global provider from `@opentelemetry/api`.
- * @returns `true` if the recorder is installed and instruments are registered.
- *   `false` if a different `metrics` recorder is already installed in this
- *   process (only one global recorder is permitted), in which case a warning is
- *   emitted and no instruments are created. Calling this more than once is safe;
- *   instruments are created only on the first successful call.
- */
-export function instrumentLanceDbMetrics(
-  meterProvider?: MeterProvider,
-): boolean {
-  if (!registerLancedbMetricsRecorder()) {
-    console.warn(
-      "Could not install the LanceDB metrics recorder: another `metrics` " +
-        "recorder is already installed in this process. LanceDB metrics will " +
-        "not be exported via OpenTelemetry.",
-    );
-    return false;
-  }
-
-  if (instrumented) {
-    return true;
-  }
-
-  const provider = meterProvider ?? metrics.getMeterProvider();
-  const meter = provider.getMeter("lancedb");
-
-  const scalarCallback = (metricName: string) => (result: ObservableResult) => {
-    for (const point of snapshotLancedbMetrics()) {
-      if (point.name === metricName && point.value != null) {
-        result.observe(point.value, point.attributes);
-      }
-    }
-  };
-
-  const bucketCallback = (metricName: string) => (result: ObservableResult) => {
-    for (const point of snapshotLancedbMetrics()) {
-      if (point.name !== metricName || point.buckets == null) {
-        continue;
-      }
-      for (const bucket of point.buckets) {
-        const attributes: Attributes = {
-          ...point.attributes,
-          le: bucket.le,
-        };
-        result.observe(bucket.cumulativeCount, attributes);
-      }
-    }
-  };
-
-  const fieldCallback =
-    (metricName: string, field: "count" | "sum") =>
-    (result: ObservableResult) => {
-      for (const point of snapshotLancedbMetrics()) {
-        if (point.name !== metricName) {
-          continue;
-        }
-        const value = point[field];
-        if (value != null) {
-          result.observe(value, point.attributes);
-        }
-      }
-    };
-
-  for (const desc of lancedbMetricsCatalog()) {
-    const unit = desc.unit ?? "";
-    if (desc.kind === "counter") {
-      const counter = meter.createObservableCounter(desc.name, {
-        unit,
-        description: desc.description,
-      });
-      counter.addCallback(scalarCallback(desc.name));
-    } else if (desc.kind === "gauge") {
-      const gauge = meter.createObservableGauge(desc.name, {
-        unit,
-        description: desc.description,
-      });
-      gauge.addCallback(scalarCallback(desc.name));
-    } else if (desc.kind === "histogram") {
-      // `_bucket` and `_count` observe cumulative sample counts, not the
-      // histogram's measured quantity, so they are unitless; only `_sum`
-      // carries the histogram's unit.
-      const bucket = meter.createObservableCounter(`${desc.name}_bucket`, {
-        description: `${desc.description} (cumulative buckets)`,
-      });
-      bucket.addCallback(bucketCallback(desc.name));
-
-      const count = meter.createObservableCounter(`${desc.name}_count`, {
-        description: `${desc.description} (count)`,
-      });
-      count.addCallback(fieldCallback(desc.name, "count"));
-
-      const sum = meter.createObservableCounter(`${desc.name}_sum`, {
-        unit,
-        description: `${desc.description} (sum)`,
-      });
-      sum.addCallback(fieldCallback(desc.name, "sum"));
-    }
-  }
-
-  instrumented = true;
-  return true;
-}
@@ -79,8 +79,6 @@ export interface QueryExecutionOptions {
  timeoutMs?: number;
 }

-export type AnalyzePlanDistributedMetrics = "aggregate" | "per_worker" | "full";
-
 export interface ColumnOrdering {
  columnName: string;
  ascending?: boolean;
@@ -313,20 +311,13 @@ export class QueryBase<
   *        KNNVectorDistance: metric=l2, metrics=[output_rows=1, elapsed_compute=114.333µs, output_batches=1]
   *         LanceScan: uri=/path/to/data, projection=[vector], row_id=true, row_addr=false, ordered=false, metrics=[output_rows=1, elapsed_compute=103.626µs, bytes_read=549, iops=2, requests=2]
   *
-   * @param distributedMetrics - How distributed worker metrics are displayed for remote query plans.
-   * Defaults to `"aggregate"`.
   * @returns A query execution plan with runtime metrics for each step.
   */
-  async analyzePlan(
-    distributedMetrics?: AnalyzePlanDistributedMetrics,
-  ): Promise<string> {
-    const distributedMetricsMode = distributedMetrics ?? "aggregate";
+  async analyzePlan(): Promise<string> {
    if (this.inner instanceof Promise) {
-      return this.inner.then((inner) =>
-        inner.analyzePlan(distributedMetricsMode),
-      );
+      return this.inner.then((inner) => inner.analyzePlan());
    } else {
-      return this.inner.analyzePlan(distributedMetricsMode);
+      return this.inner.analyzePlan();
    }
  }

@@ -371,9 +362,6 @@ export class StandardQueryBase<
   *
   * Filtering performance can often be improved by creating a scalar index
   * on the filter column(s).
-   *
-   * Calling this multiple times combines the filters with a logical AND rather
-   * than replacing the previous filter.
   */
  where(predicate: string): this {
    this.doCall((inner: NativeQueryType) => inner.onlyIf(predicate));
@@ -460,30 +448,6 @@ export class StandardQueryBase<
    this.doCall((inner: NativeQueryType) => inner.fastSearch());
    return this;
  }
-
-  /**
-   * Control MemWAL read routing for this query.
-   *
-   * By default (unset), when the table carries a MemWAL write spec (see
-   * {@link Table#setLsmWriteSpec}), reads are routed through the LSM scanner so
-   * they also return data written via the `mergeInsert` LSM path that has not yet
-   * been compacted into the base table (the active/frozen in-memory memtables and
-   * the flushed generations), deduplicated by primary key; a table without a spec
-   * reads the base table.
-   *
-   * @param enable - `true` forces the LSM scanner and errors if the table has no
-   * MemWAL write spec. `false` bypasses the MemWAL and reads the base table only,
-   * even when a spec is present.
-   *
-   * Note: the LSM scanner does not support every query shape (e.g. reranking,
-   * hybrid search, `orderBy`). On a MemWAL table those shapes error unless
-   * `useLsm(false)` is set, because a base-only read would silently exclude
-   * un-compacted MemWAL data.
-   */
-  useLsm(enable: boolean): this {
-    this.doCall((inner: NativeQueryType) => inner.useLsm(enable));
-    return this;
-  }
 }

 /**
@@ -772,20 +736,6 @@ export class TakeQuery extends QueryBase<NativeTakeQuery> {
  constructor(inner: NativeTakeQuery) {
    super(inner);
  }
-
-  /**
-   * Control MemWAL read routing for this take query.
-   *
-   * `false` bypasses the MemWAL and reads the base table only — the escape hatch,
-   * since take-by-row-id/offset is not supported on the LSM scanner and, on a
-   * MemWAL table, auto-routes to it and errors otherwise.
-   *
-   * @param enable - `false` reads the base table only.
-   */
-  useLsm(enable: boolean): this {
-    this.doCall((inner: NativeTakeQuery) => inner.useLsm(enable));
-    return this;
-  }
 }

 /** A builder for LanceDB queries.
@@ -84,7 +84,7 @@ export function sanitizeMetadata(
    throw Error("Expected metadata, if present, to be a Map<string, string>");
  }
  for (const item of metadataLike) {
-    if (typeof item[0] !== "string" || typeof item[1] !== "string") {
+    if (!(typeof item[0] === "string" || !(typeof item[1] === "string"))) {
      throw Error(
        "Expected metadata, if present, to be a Map<string, string> but it had non-string keys or values",
      );
@@ -288,11 +288,12 @@ export function sanitizeMap(typeLike: object) {
  if (!("keysSorted" in typeLike) || typeof typeLike.keysSorted !== "boolean") {
    throw Error("Expected a Map type to have a `keysSorted` property");
  }
-  if (typeLike.children.length !== 1) {
-    throw Error("Expected a Map type to have exactly one child");
-  }

-  return new Map_(sanitizeField(typeLike.children[0]), typeLike.keysSorted);
+  return new Map_(
+    // biome-ignore lint/suspicious/noExplicitAny: skip
+    typeLike.children.map((field) => sanitizeField(field)) as any,
+    typeLike.keysSorted,
+  );
 }

 export function sanitizeDuration(typeLike: object) {
@@ -25,12 +25,10 @@ import {
  AddColumnsSql,
  AddResult,
  AlterColumnsResult,
-  BranchContents,
  DeleteResult,
  DropColumnsResult,
  IndexConfig,
  IndexStatistics,
-  Branches as NativeBranches,
  OptimizeStats,
  TableStatistics,
  Tags,
@@ -158,26 +156,6 @@ export interface Version {
  metadata: Record<string, string>;
 }

-/** Token produced by the tokenizer configured on a full-text search index. */
-export interface FtsToken {
-  /** Token text after tokenizer filters have been applied. */
-  text: string;
-  /** Token position used by full-text query matching. */
-  position: number;
-}
-
-export type TokenizeTableOptions =
-  | {
-      /** FTS-indexed column whose tokenizer should be used. */
-      column: string;
-      indexName?: never;
-    }
-  | {
-      /** Name of the FTS index whose tokenizer should be used. */
-      indexName: string;
-      column?: never;
-    };
-
 /**
 * Specification selecting Lance's MemWAL LSM-style write path for
 * `mergeInsert`.
@@ -605,17 +583,6 @@ export abstract class Table {
   * @returns {Promise<void>}
   */
  abstract unsetLsmWriteSpec(): Promise<void>;
-  /**
-   * Read the {@link LsmWriteSpec} currently installed on this table.
-   *
-   * Resolves to `undefined` when the MemWAL LSM write path is not enabled (no
-   * spec has been set, or it was removed with {@link Table#unsetLsmWriteSpec}).
-   * The returned spec — including its `maintainedIndexes` and
-   * `writerConfigDefaults` — mirrors what was passed to
-   * {@link Table#setLsmWriteSpec}.
-   * @returns {Promise<LsmWriteSpec | undefined>}
-   */
-  abstract getLsmWriteSpec(): Promise<LsmWriteSpec | undefined>;
  /**
   * Drain and close any cached MemWAL shard writers held for this table.
   *
@@ -686,22 +653,6 @@ export abstract class Table {
   */
  abstract tags(): Promise<Tags>;

-  /**
-   * Get the branch manager for this table.
-   *
-   * Branches are isolated, writable lines of history forked from another
-   * branch (or version). Writes on a branch do not affect `main`.
-   */
-  abstract branches(): Promise<Branches>;
-
-  /**
-   * The branch this table handle is scoped to, or `null` for the main branch.
-   *
-   * A handle returned by {@link Branches.create} or {@link Branches.checkout}
-   * reports the branch it targets; a handle opened normally reports `null`.
-   */
-  abstract currentBranch(): string | null;
-
  /**
   * Restore the table to the currently checked out version
   *
@@ -736,19 +687,6 @@ export abstract class Table {
  abstract optimize(options?: Partial<OptimizeOptions>): Promise<OptimizeStats>;
  /** List all indices that have been created with {@link Table.createIndex} */
  abstract listIndices(): Promise<IndexConfig[]>;
-  /**
-   * Tokenize a full-text search query using the tokenizer configured on an FTS index.
-   *
-   * Specify exactly one of `column` or `indexName`.
-   *
-   * Model-backed tokenizers such as `jieba/*` and `lindera/*` are rebuilt in
-   * the client process from index metadata. For remote tables, this means the
-   * same tokenizer model files must also exist locally.
-   */
-  abstract tokenize(
-    query: string,
-    options: TokenizeTableOptions,
-  ): Promise<FtsToken[]>;
  /** Return the table as an arrow table */
  abstract toArrow(): Promise<ArrowTable>;

@@ -1135,15 +1073,6 @@ export class LocalTable extends Table {
    return await this.inner.unsetLsmWriteSpec();
  }

-  async getLsmWriteSpec(): Promise<LsmWriteSpec | undefined> {
-    // The native binding types `specType` as a plain `string`; narrow it back
-    // to the public union. The Rust `From` impl only ever emits one of the
-    // three valid values, so the cast is safe.
-    return ((await this.inner.getLsmWriteSpec()) ?? undefined) as
-      | LsmWriteSpec
-      | undefined;
-  }
-
  async closeLsmWriters(): Promise<void> {
    return await this.inner.closeLsmWriters();
  }
@@ -1179,14 +1108,6 @@ export class LocalTable extends Table {
    return await this.inner.tags();
  }

-  async branches(): Promise<Branches> {
-    return new Branches(await this.inner.branches());
-  }
-
-  currentBranch(): string | null {
-    return this.inner.currentBranch() ?? null;
-  }
-
  async optimize(options?: Partial<OptimizeOptions>): Promise<OptimizeStats> {
    let cleanupOlderThanMs;
    if (
@@ -1206,17 +1127,6 @@ export class LocalTable extends Table {
    return await this.inner.listIndices();
  }

-  async tokenize(
-    query: string,
-    options: TokenizeTableOptions,
-  ): Promise<FtsToken[]> {
-    return await this.inner.tokenize(
-      query,
-      options?.column,
-      options?.indexName,
-    );
-  }
-
  async toArrow(): Promise<ArrowTable> {
    return await this.query().toArrow();
  }
@@ -1328,151 +1238,3 @@ export interface FieldMetadataUpdate {
  /** If true, replace the field's entire metadata map instead of merging. */
  replace?: boolean;
 }
-
-/** Summary of a column in a branch diff. */
-export interface BranchColumnSummary {
-  name: string;
-  dataType: string;
-  nullable: boolean;
-}
-
-/** A column whose definition differs between main and the branch. */
-export interface BranchColumnChange {
-  name: string;
-  main: BranchColumnSummary;
-  branch: BranchColumnSummary;
-}
-
-/** Summary of an index in a branch diff. */
-export interface BranchIndexSummary {
-  indexName: string;
-  columns: string[];
-  indexType?: string;
-  status: string;
-}
-
-/** Row-level comparison between main and the branch. */
-export interface BranchRowCountSummary {
-  unchanged: number;
-  newOnBase: number;
-  newOnBranch: number;
-  staleRecompute: number;
-  inputsChanged: number;
-  deltaAvailable: boolean;
-}
-
-/** A reason why a branch cannot currently be merged. */
-export interface MergeBlocker {
-  code: string;
-  message: string;
-}
-
-/** Read-only comparison of a branch against main. */
-export interface BranchDiff {
-  fromBranch: string;
-  parentVersion: number;
-  mainVersion: number;
-  branchVersion: number;
-  baseMoved: boolean;
-  rowCountMain: number;
-  rowCountBranch: number;
-  rowSummary: BranchRowCountSummary;
-  addedColumns: BranchColumnSummary[];
-  removedColumns: BranchColumnSummary[];
-  changedColumns: BranchColumnChange[];
-  addedIndexes: BranchIndexSummary[];
-  removedIndexes: BranchIndexSummary[];
-  mergeable: boolean;
-  mergeBlockers: MergeBlocker[];
-}
-
-/** Changes that would be, or were, promoted by a branch merge. */
-export interface MergePreview {
-  promotedColumns: string[];
-}
-
-/** Result of previewing or attempting a branch merge. */
-export interface MergeBranchResult {
-  status: "ready" | "rejected" | "notImplemented" | "merged" | "unknown";
-  diff: BranchDiff;
-  preview: MergePreview;
-  mainVersionAfter?: number;
-}
-
-/**
- * Branch manager for a {@link Table}.
- *
- * Unlike tags, `create` and `checkout` return a new {@link Table} handle scoped
- * to the branch; writes on it do not affect `main`.
- */
-export class Branches {
-  #inner: NativeBranches;
-
-  /**
-   * Construct a Branches manager. Internal use only.
-   * @hidden
-   */
-  constructor(inner: NativeBranches) {
-    this.#inner = inner;
-  }
-
-  /** List all branches, mapping name to branch metadata. */
-  async list(): Promise<Record<string, BranchContents>> {
-    return await this.#inner.list();
-  }
-
-  /**
-   * Create a branch and return a handle scoped to it.
-   *
-   * @param name Name of the new branch.
-   * @param fromRef Source branch to fork from. Defaults to `main`.
-   * @param fromVersion A specific version on `fromRef`. Defaults to latest.
-   */
-  async create(
-    name: string,
-    fromRef?: string,
-    fromVersion?: number,
-  ): Promise<Table> {
-    return new LocalTable(await this.#inner.create(name, fromRef, fromVersion));
-  }
-
-  /**
-   * Check out an existing branch and return a handle scoped to it.
-   *
-   * With `version` set, the returned handle is pinned to that version of the
-   * branch (a read-only, detached view); otherwise it tracks the branch's
-   * latest and stays writable.
-   */
-  async checkout(name: string, version?: number): Promise<Table> {
-    return new LocalTable(await this.#inner.checkout(name, version));
-  }
-
-  /** Delete a branch. */
-  async delete(name: string): Promise<void> {
-    return await this.#inner.delete(name);
-  }
-
-  /** Compare a branch against main without modifying either branch. */
-  async diff(fromBranch: string): Promise<BranchDiff> {
-    return (await this.#inner.diff(fromBranch)) as unknown as BranchDiff;
-  }
-
-  /**
-   * Merge a branch into main.
-   *
-   * Set `dryRun` to `true` to preview the merge. A rejected merge resolves
-   * with `status: "rejected"` instead of throwing.
-   *
-   * @param fromBranch Branch to merge from.
-   * @param dryRun When true, only preview the merge. Defaults to false.
-   */
-  async merge(
-    fromBranch: string,
-    dryRun: boolean = false,
-  ): Promise<MergeBranchResult> {
-    return (await this.#inner.merge(
-      fromBranch,
-      dryRun,
-    )) as unknown as MergeBranchResult;
-  }
-}
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.37.1-beta.0",
+	"version": "0.30.1-beta.2",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.37.1-beta.0",
+	"version": "0.30.1-beta.2",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-musl",
-	"version": "0.37.1-beta.0",
+	"version": "0.30.1-beta.2",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-musl.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.37.1-beta.0",
+	"version": "0.30.1-beta.2",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-musl",
-	"version": "0.37.1-beta.0",
+	"version": "0.30.1-beta.2",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-musl.node",
@@ -1,6 +1,6 @@
 {
  "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.37.1-beta.0",
+  "version": "0.30.1-beta.2",
  "os": [
    "win32"
  ],
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.37.1-beta.0",
+	"version": "0.30.1-beta.2",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",
@@ -1,12 +1,12 @@
 {
  "name": "@lancedb/lancedb",
-  "version": "0.37.1-beta.0",
+  "version": "0.30.1-beta.2",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "@lancedb/lancedb",
-      "version": "0.37.1-beta.0",
+      "version": "0.30.1-beta.2",
      "cpu": [
        "x64",
        "arm64"
@@ -18,7 +18,6 @@
        "win32"
      ],
      "dependencies": {
-        "@opentelemetry/api": "^1.9.0",
        "reflect-metadata": "^0.2.2"
      },
      "devDependencies": {
@@ -27,8 +26,7 @@
        "@aws-sdk/client-s3": "3.1003.0",
        "@biomejs/biome": "^1.7.3",
        "@jest/globals": "^29.7.0",
-        "@napi-rs/cli": "3.7.0",
-        "@opentelemetry/sdk-metrics": "^1.30.0",
+        "@napi-rs/cli": "3.5.1",
        "@types/axios": "^0.14.0",
        "@types/jest": "^29.1.2",
        "@types/node": "22.7.4",
@@ -2944,9 +2942,9 @@
      }
    },
    "node_modules/@napi-rs/cli": {
-      "version": "3.7.0",
-      "resolved": "https://registry.npmjs.org/@napi-rs/cli/-/cli-3.7.0.tgz",
-      "integrity": "sha512-3d3+rmxlOIV/G1zPWeX4PCxuYnhcCQM2BvY9rtimC8RO0dFR9gtYP+Grov+WoduZtfWRj5N1XvytWeRxxCk5zw==",
+      "version": "3.5.1",
+      "resolved": "https://registry.npmjs.org/@napi-rs/cli/-/cli-3.5.1.tgz",
+      "integrity": "sha512-XBfLQRDcB3qhu6bazdMJsecWW55kR85l5/k0af9BIBELXQSsCFU0fzug7PX8eQp6vVdm7W/U3z6uP5WmITB2Gw==",
      "dev": true,
      "license": "MIT",
      "dependencies": {
@@ -2956,7 +2954,7 @@
        "@octokit/rest": "^22.0.1",
        "clipanion": "^4.0.0-rc.4",
        "colorette": "^2.0.20",
-        "emnapi": "^1.10.0",
+        "emnapi": "^1.7.1",
        "es-toolkit": "^1.41.0",
        "js-yaml": "^4.1.0",
        "obug": "^2.0.0",
@@ -4150,75 +4148,6 @@
        "@octokit/openapi-types": "^27.0.0"
      }
    },
-    "node_modules/@opentelemetry/api": {
-      "version": "1.9.1",
-      "resolved": "https://registry.npmjs.org/@opentelemetry/api/-/api-1.9.1.tgz",
-      "integrity": "sha512-gLyJlPHPZYdAk1JENA9LeHejZe1Ti77/pTeFm/nMXmQH/HFZlcS/O2XJB+L8fkbrNSqhdtlvjBVjxwUYanNH5Q==",
-      "license": "Apache-2.0",
-      "engines": {
-        "node": ">=8.0.0"
-      }
-    },
-    "node_modules/@opentelemetry/core": {
-      "version": "1.30.1",
-      "resolved": "https://registry.npmjs.org/@opentelemetry/core/-/core-1.30.1.tgz",
-      "integrity": "sha512-OOCM2C/QIURhJMuKaekP3TRBxBKxG/TWWA0TL2J6nXUtDnuCtccy49LUJF8xPFXMX+0LMcxFpCo8M9cGY1W6rQ==",
-      "dev": true,
-      "license": "Apache-2.0",
-      "dependencies": {
-        "@opentelemetry/semantic-conventions": "1.28.0"
-      },
-      "engines": {
-        "node": ">=14"
-      },
-      "peerDependencies": {
-        "@opentelemetry/api": ">=1.0.0 <1.10.0"
-      }
-    },
-    "node_modules/@opentelemetry/resources": {
-      "version": "1.30.1",
-      "resolved": "https://registry.npmjs.org/@opentelemetry/resources/-/resources-1.30.1.tgz",
-      "integrity": "sha512-5UxZqiAgLYGFjS4s9qm5mBVo433u+dSPUFWVWXmLAD4wB65oMCoXaJP1KJa9DIYYMeHu3z4BZcStG3LC593cWA==",
-      "dev": true,
-      "license": "Apache-2.0",
-      "dependencies": {
-        "@opentelemetry/core": "1.30.1",
-        "@opentelemetry/semantic-conventions": "1.28.0"
-      },
-      "engines": {
-        "node": ">=14"
-      },
-      "peerDependencies": {
-        "@opentelemetry/api": ">=1.0.0 <1.10.0"
-      }
-    },
-    "node_modules/@opentelemetry/sdk-metrics": {
-      "version": "1.30.1",
-      "resolved": "https://registry.npmjs.org/@opentelemetry/sdk-metrics/-/sdk-metrics-1.30.1.tgz",
-      "integrity": "sha512-q9zcZ0Okl8jRgmy7eNW3Ku1XSgg3sDLa5evHZpCwjspw7E8Is4K/haRPDJrBcX3YSn/Y7gUvFnByNYEKQNbNog==",
-      "dev": true,
-      "license": "Apache-2.0",
-      "dependencies": {
-        "@opentelemetry/core": "1.30.1",
-        "@opentelemetry/resources": "1.30.1"
-      },
-      "engines": {
-        "node": ">=14"
-      },
-      "peerDependencies": {
-        "@opentelemetry/api": ">=1.3.0 <1.10.0"
-      }
-    },
-    "node_modules/@opentelemetry/semantic-conventions": {
-      "version": "1.28.0",
-      "resolved": "https://registry.npmjs.org/@opentelemetry/semantic-conventions/-/semantic-conventions-1.28.0.tgz",
-      "integrity": "sha512-lp4qAiMTD4sNWW4DbKLBkfiMZ4jbAboJIGOQr5DvciMRI494OapieI9qiODpOt0XBr1LjIDy1xAGAnVs5supTA==",
-      "dev": true,
-      "license": "Apache-2.0",
-      "engines": {
-        "node": ">=14"
-      }
-    },
    "node_modules/@protobufjs/aspromise": {
      "version": "1.1.2",
      "resolved": "https://registry.npmjs.org/@protobufjs/aspromise/-/aspromise-1.1.2.tgz",
@@ -11,7 +11,7 @@
    "ann"
  ],
  "private": false,
-  "version": "0.37.1-beta.0",
+  "version": "0.30.1-beta.2",
  "main": "dist/index.js",
  "exports": {
    ".": "./dist/index.js",
@@ -43,8 +43,7 @@
    "@aws-sdk/client-s3": "3.1003.0",
    "@biomejs/biome": "^1.7.3",
    "@jest/globals": "^29.7.0",
-    "@napi-rs/cli": "3.7.0",
-    "@opentelemetry/sdk-metrics": "^1.30.0",
+    "@napi-rs/cli": "3.5.1",
    "@types/axios": "^0.14.0",
    "@types/jest": "^29.1.2",
    "@types/node": "22.7.4",
@@ -93,7 +92,6 @@
    "version": "napi version"
  },
  "dependencies": {
-    "@opentelemetry/api": "^1.9.0",
    "reflect-metadata": "^0.2.2"
  },
  "optionalDependencies": {
@@ -8,9 +8,6 @@ importers:

  .:
    dependencies:
-      '@opentelemetry/api':
-        specifier: ^1.9.0
-        version: 1.9.1
      apache-arrow:
        specifier: '>=15.0.0 <=18.1.0'
        version: 18.1.0
@@ -34,11 +31,8 @@ importers:
        specifier: ^29.7.0
        version: 29.7.0
      '@napi-rs/cli':
-        specifier: 3.7.0
-        version: 3.7.0(@emnapi/core@1.10.0)(@emnapi/runtime@1.10.0)(@types/node@22.7.4)
-      '@opentelemetry/sdk-metrics':
-        specifier: ^1.30.0
-        version: 1.30.1(@opentelemetry/api@1.9.1)
+        specifier: 3.5.1
+        version: 3.5.1(@emnapi/core@1.10.0)(@emnapi/runtime@1.10.0)(@types/node@22.7.4)
      '@types/axios':
        specifier: ^0.14.0
        version: 0.14.4
@@ -893,8 +887,8 @@ packages:
  '@jridgewell/trace-mapping@0.3.31':
    resolution: {integrity: sha512-zzNR+SdQSDJzc8joaeP8QQoCQr8NuYx2dIIytl1QeBEZHJ9uW6hebsrYgbz8hJwUQao3TWCMtmfV8Nu1twOLAw==}

-  '@napi-rs/cli@3.7.0':
-    resolution: {integrity: sha512-3d3+rmxlOIV/G1zPWeX4PCxuYnhcCQM2BvY9rtimC8RO0dFR9gtYP+Grov+WoduZtfWRj5N1XvytWeRxxCk5zw==}
+  '@napi-rs/cli@3.5.1':
+    resolution: {integrity: sha512-XBfLQRDcB3qhu6bazdMJsecWW55kR85l5/k0af9BIBELXQSsCFU0fzug7PX8eQp6vVdm7W/U3z6uP5WmITB2Gw==}
    engines: {node: '>= 16'}
    hasBin: true
    peerDependencies:
@@ -1313,32 +1307,6 @@ packages:
  '@octokit/types@16.0.0':
    resolution: {integrity: sha512-sKq+9r1Mm4efXW1FCk7hFSeJo4QKreL/tTbR0rz/qx/r1Oa2VV83LTA/H/MuCOX7uCIJmQVRKBcbmWoySjAnSg==}

-  '@opentelemetry/api@1.9.1':
-    resolution: {integrity: sha512-gLyJlPHPZYdAk1JENA9LeHejZe1Ti77/pTeFm/nMXmQH/HFZlcS/O2XJB+L8fkbrNSqhdtlvjBVjxwUYanNH5Q==}
-    engines: {node: '>=8.0.0'}
-
-  '@opentelemetry/core@1.30.1':
-    resolution: {integrity: sha512-OOCM2C/QIURhJMuKaekP3TRBxBKxG/TWWA0TL2J6nXUtDnuCtccy49LUJF8xPFXMX+0LMcxFpCo8M9cGY1W6rQ==}
-    engines: {node: '>=14'}
-    peerDependencies:
-      '@opentelemetry/api': '>=1.0.0 <1.10.0'
-
-  '@opentelemetry/resources@1.30.1':
-    resolution: {integrity: sha512-5UxZqiAgLYGFjS4s9qm5mBVo433u+dSPUFWVWXmLAD4wB65oMCoXaJP1KJa9DIYYMeHu3z4BZcStG3LC593cWA==}
-    engines: {node: '>=14'}
-    peerDependencies:
-      '@opentelemetry/api': '>=1.0.0 <1.10.0'
-
-  '@opentelemetry/sdk-metrics@1.30.1':
-    resolution: {integrity: sha512-q9zcZ0Okl8jRgmy7eNW3Ku1XSgg3sDLa5evHZpCwjspw7E8Is4K/haRPDJrBcX3YSn/Y7gUvFnByNYEKQNbNog==}
-    engines: {node: '>=14'}
-    peerDependencies:
-      '@opentelemetry/api': '>=1.3.0 <1.10.0'
-
-  '@opentelemetry/semantic-conventions@1.28.0':
-    resolution: {integrity: sha512-lp4qAiMTD4sNWW4DbKLBkfiMZ4jbAboJIGOQr5DvciMRI494OapieI9qiODpOt0XBr1LjIDy1xAGAnVs5supTA==}
-    engines: {node: '>=14'}
-
  '@protobufjs/aspromise@1.1.2':
    resolution: {integrity: sha512-j+gKExEuLmKwvz3OgROXtrJ2UG2x8Ch2YZUxahh+s1F2HZ+wAceUNLkvy6zKCPVRkU++ZWQrdxsUeQXmcg4uoQ==}

@@ -4614,7 +4582,7 @@ snapshots:
      '@jridgewell/resolve-uri': 3.1.2
      '@jridgewell/sourcemap-codec': 1.5.5

-  '@napi-rs/cli@3.7.0(@emnapi/core@1.10.0)(@emnapi/runtime@1.10.0)(@types/node@22.7.4)':
+  '@napi-rs/cli@3.5.1(@emnapi/core@1.10.0)(@emnapi/runtime@1.10.0)(@types/node@22.7.4)':
    dependencies:
      '@inquirer/prompts': 8.4.3(@types/node@22.7.4)
      '@napi-rs/cross-toolchain': 1.0.3(@emnapi/core@1.10.0)(@emnapi/runtime@1.10.0)
@@ -4957,27 +4925,6 @@ snapshots:
    dependencies:
      '@octokit/openapi-types': 27.0.0

-  '@opentelemetry/api@1.9.1': {}
-
-  '@opentelemetry/core@1.30.1(@opentelemetry/api@1.9.1)':
-    dependencies:
-      '@opentelemetry/api': 1.9.1
-      '@opentelemetry/semantic-conventions': 1.28.0
-
-  '@opentelemetry/resources@1.30.1(@opentelemetry/api@1.9.1)':
-    dependencies:
-      '@opentelemetry/api': 1.9.1
-      '@opentelemetry/core': 1.30.1(@opentelemetry/api@1.9.1)
-      '@opentelemetry/semantic-conventions': 1.28.0
-
-  '@opentelemetry/sdk-metrics@1.30.1(@opentelemetry/api@1.9.1)':
-    dependencies:
-      '@opentelemetry/api': 1.9.1
-      '@opentelemetry/core': 1.30.1(@opentelemetry/api@1.9.1)
-      '@opentelemetry/resources': 1.30.1(@opentelemetry/api@1.9.1)
-
-  '@opentelemetry/semantic-conventions@1.28.0': {}
-
  '@protobufjs/aspromise@1.1.2':
    optional: true

@@ -112,12 +112,6 @@ impl Connection {

        builder = builder.client_config(rust_config);

-        if let Some(oauth_config) = options.oauth_config {
-            let config: lancedb::remote::oauth::OAuthConfig =
-                oauth_config.try_into().default_error()?;
-            builder = builder.oauth_config(config);
-        }
-
        if let Some(api_key) = options.api_key {
            builder = builder.api_key(&api_key);
        }
@@ -4,16 +4,13 @@
 use std::sync::Mutex;

 use lancedb::index::Index as LanceDbIndex;
-use lancedb::index::scalar::{BTreeIndexBuilder, FmIndexBuilder, FtsIndexBuilder};
+use lancedb::index::scalar::{BTreeIndexBuilder, FtsIndexBuilder};
 use lancedb::index::vector::{
    IvfFlatIndexBuilder, IvfHnswPqIndexBuilder, IvfHnswSqIndexBuilder, IvfPqIndexBuilder,
    IvfRqIndexBuilder,
 };
-use lancedb::tokenize as lancedb_tokenize;
 use napi_derive::napi;

-use crate::error::NapiErrorExt;
-use crate::table::FtsToken;
 use crate::util::parse_distance_type;

 #[napi]
@@ -33,67 +30,6 @@ impl Index {
    }
 }

-#[napi(catch_unwind)]
-#[allow(dead_code, clippy::too_many_arguments)]
-pub fn tokenize(
-    query: String,
-    base_tokenizer: Option<String>,
-    language: Option<String>,
-    max_token_length: Option<u32>,
-    lower_case: Option<bool>,
-    stem: Option<bool>,
-    remove_stop_words: Option<bool>,
-    custom_stop_words: Option<Vec<String>>,
-    ascii_folding: Option<bool>,
-    ngram_min_length: Option<u32>,
-    ngram_max_length: Option<u32>,
-    prefix_only: Option<bool>,
-) -> napi::Result<Vec<FtsToken>> {
-    let mut opts = FtsIndexBuilder::default();
-    if let Some(base_tokenizer) = base_tokenizer {
-        opts = opts.base_tokenizer(base_tokenizer);
-    }
-    if let Some(language) = language {
-        opts = opts.language(&language).map_err(|_| {
-            napi::Error::from_reason(format!(
-                "LanceDB does not support the requested language: '{}'",
-                language
-            ))
-        })?;
-    }
-    if let Some(max_token_length) = max_token_length {
-        opts = opts.max_token_length(Some(max_token_length as usize));
-    }
-    if let Some(lower_case) = lower_case {
-        opts = opts.lower_case(lower_case);
-    }
-    if let Some(stem) = stem {
-        opts = opts.stem(stem);
-    }
-    if let Some(remove_stop_words) = remove_stop_words {
-        opts = opts.remove_stop_words(remove_stop_words);
-    }
-    opts = opts.custom_stop_words(custom_stop_words);
-    if let Some(ascii_folding) = ascii_folding {
-        opts = opts.ascii_folding(ascii_folding);
-    }
-    if let Some(ngram_min_length) = ngram_min_length {
-        opts = opts.ngram_min_length(ngram_min_length);
-    }
-    if let Some(ngram_max_length) = ngram_max_length {
-        opts = opts.ngram_max_length(ngram_max_length);
-    }
-    if let Some(prefix_only) = prefix_only {
-        opts = opts.ngram_prefix_only(prefix_only);
-    }
-
-    Ok(lancedb_tokenize(&query, &opts)
-        .default_error()?
-        .into_iter()
-        .map(FtsToken::from)
-        .collect())
-}
-
 #[napi]
 impl Index {
    #[napi(factory)]
@@ -207,13 +143,6 @@ impl Index {
        }
    }

-    #[napi(factory)]
-    pub fn fm() -> Self {
-        Self {
-            inner: Mutex::new(Some(LanceDbIndex::Fm(FmIndexBuilder::default()))),
-        }
-    }
-
    #[napi(factory)]
    #[allow(clippy::too_many_arguments)]
    pub fn fts(
@@ -224,13 +153,11 @@ impl Index {
        lower_case: Option<bool>,
        stem: Option<bool>,
        remove_stop_words: Option<bool>,
-        custom_stop_words: Option<Vec<String>>,
        ascii_folding: Option<bool>,
        ngram_min_length: Option<u32>,
        ngram_max_length: Option<u32>,
        prefix_only: Option<bool>,
-        block_size: Option<u32>,
-    ) -> napi::Result<Self> {
+    ) -> Self {
        let mut opts = FtsIndexBuilder::default();
        if let Some(with_position) = with_position {
            opts = opts.with_position(with_position);
@@ -253,7 +180,6 @@ impl Index {
        if let Some(remove_stop_words) = remove_stop_words {
            opts = opts.remove_stop_words(remove_stop_words);
        }
-        opts = opts.custom_stop_words(custom_stop_words);
        if let Some(ascii_folding) = ascii_folding {
            opts = opts.ascii_folding(ascii_folding);
        }
@@ -266,15 +192,10 @@ impl Index {
        if let Some(prefix_only) = prefix_only {
            opts = opts.ngram_prefix_only(prefix_only);
        }
-        if let Some(block_size) = block_size {
-            opts = opts
-                .block_size(block_size as usize)
-                .map_err(|err| napi::Error::from_reason(err.to_string()))?;
-        }

-        Ok(Self {
+        Self {
            inner: Mutex::new(Some(LanceDbIndex::FTS(opts))),
-        })
+        }
    }

    #[napi(factory)]
--- a/Show More
+++ b/Show More