fix: support remote tables in storage root

fix(python): guard concurrent table deletes (#3787 )
## Root cause The legacy synchronous Python table called `delete` on a shared, mutable `lance.Dataset`. Concurrent table operations could hold a PyO3 borrow while delete requested an exclusive borrow, producing `RuntimeError: Already borrowed`. The current async-backed binding fixes this by cloning its thread-safe Rust table handle before awaiting, but that concurrency contract had no regression coverage. ## Fix - Document why delete must clone the Rust table handle before entering its async future. - Add a barrier-synchronized regression test that deletes distinct rows through one shared table from eight Python threads. - Verify every delete commits exactly one row, every commit gets a distinct version, and no rows remain. ## Validation - `cargo check --quiet --features remote --tests --examples` - `cargo fmt --all -- --check` - `uv run --extra tests --extra dev ruff format --check python/tests/test_table.py` - `uv run --extra tests --extra dev ruff check python/tests/test_table.py` - `uv run --extra tests --extra dev pytest python/tests/test_table.py::test_concurrent_deletes_are_thread_safe python/tests/test_table.py::test_delete python/tests/test_table.py::test_delete_expr python/tests/test_table.py::test_delete_expr_async -q` (4 passed) - Manual stress reproduction: 100 concurrent deletes on one table completed at versions 2–101 with zero rows remaining. Fixes #530 Co-authored-by: Gatefixer <313497061+lancedb-gatefixer[bot]@users.noreply.github.com>
2026-08-26 07:58:31 +00:00 · 2026-08-06 06:17:33 +00:00 · 2026-08-05 15:17:04 -07:00 · 2026-08-05 15:15:49 -07:00 · 2026-08-04 12:23:03 -07:00 · 2026-08-04 11:18:22 -07:00
147 changed files with 12478 additions and 2464 deletions
@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.32.0-beta.2"
+current_version = "0.37.1-beta.0"
 parse = """(?x)
    (?P<major>0|[1-9]\\d*)\\.
    (?P<minor>0|[1-9]\\d*)\\.
@@ -75,6 +75,13 @@ 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"
@@ -27,19 +27,31 @@ runs:
          # Extract failed job names
          FAILED_JOBS=$(echo "$JOB_RESULTS" | jq -r 'to_entries | map(select(.value.result == "failure")) | map(.key) | join(", ")')

-          # Create issue with workflow name, failed jobs, and run URL
-          gh issue create \
-            --title "$WORKFLOW_NAME Failed ($FAILED_JOBS)" \
-            --body "The workflow **$WORKFLOW_NAME** failed during execution.
+          TITLE="$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.

        **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"
+            echo "Issue created successfully"
+          fi
        else
          echo "No job failures detected, skipping issue creation"
        fi
@@ -6,7 +6,6 @@ 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
@@ -0,0 +1,85 @@
+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 }}
@@ -1,13 +1,14 @@
 name: Create release commit

-# This workflow increments versions, tags the version, and pushes it.
+# This workflow increments the version, tags it, and pushes it. All SDKs share
+# a single version, so one tag releases all of them.
 # 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. 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.
+# 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.
 on:
  workflow_dispatch:
    inputs:
@@ -24,16 +25,6 @@ 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
@@ -65,25 +56,12 @@ jobs:
        run: |
          git config user.name 'Lance Release'
          git config user.email 'lance-dev@lancedb.com'
-      - 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 }}
+      - name: Bump version
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        run: |
          pip install bump-my-version PyGithub packaging
-          bash ci/bump_version.sh ${{ inputs.type }} ${{ inputs.bump-minor }} v $COMMIT_BEFORE_BUMP
+          bash ci/bump_version.sh ${{ inputs.type }} ${{ inputs.bump-minor }}
          bash ci/update_lockfiles.sh --amend
      - name: Push new version tag
        if: ${{ !inputs.dry_run }}
@@ -61,6 +61,11 @@ 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
@@ -103,6 +108,11 @@ 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
@@ -182,6 +192,11 @@ 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
@@ -10,10 +10,16 @@ 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:
@@ -26,73 +32,6 @@ 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@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 [[ $VERSION =~ beta ]]; then
-            echo "This is a beta release"
-
-            # Get last release (that is not this one)
-            FROM_TAG=$(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: ${{ steps.release_notes.outputs.changelog }}
-
  build-lancedb:
    strategy:
      fail-fast: false
@@ -101,9 +40,18 @@ jobs:
          - target: aarch64-apple-darwin
            host: macos-latest
            features: fp16kernels
-            pre_build: brew install protobuf
+            pre_build: |-
+              brew install protobuf
+              # Fat LTO (the workspace default in .cargo/config.toml) is
+              # single-threaded and is the peak-memory step of the build. On
+              # this runner it accounted for ~111 of the job's ~113 minutes,
+              # making it the critical path of the entire publish pipeline.
+              # ThinLTO parallelizes it across the runner's cores, for a few
+              # percent of runtime performance.
+              export CARGO_PROFILE_RELEASE_LTO=thin
+              export CARGO_PROFILE_RELEASE_CODEGEN_UNITS=16
          - target: x86_64-pc-windows-msvc
-            host: windows-2025-8x-x64
+            host: windows-2025
            features: ","
            pre_build: |-
              choco install --no-progress protoc ninja nasm
@@ -111,19 +59,19 @@ jobs:
              # There is an issue where choco doesn't add nasm to the path
              export PATH="$PATH:/c/Program Files/NASM"
              nasm -v
-              # Fat LTO of the cdylib is single-threaded and the peak-memory
-              # step of the build, and had started hitting rustc-LLVM OOM on the
-              # Windows runners. ThinLTO parallelizes it across the runner's
-              # cores and keeps peak memory well under the limit.
+              # 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-2025-8x-x64
+            host: windows-2025
            features: ","
            pre_build: |-
                choco install --no-progress protoc
                rustup target add aarch64-pc-windows-msvc
-                # See ThinLTO note on the x86_64-pc-windows-msvc target above.
+                # 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
@@ -198,16 +146,49 @@ jobs:
        with:
          toolchain: stable
          targets: ${{ matrix.settings.target }}
-      - name: Cache cargo
-        uses: actions/cache@v5
+      # 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: ${{ !matrix.settings.docker }}
        with:
-          path: |
-            ~/.cargo/registry/index/
-            ~/.cargo/registry/cache/
-            ~/.cargo/git/db/
-            .cargo-cache
-            target/
-          key: nodejs-${{ matrix.settings.target }}-cargo-${{ matrix.settings.host }}
+          # The release profile and per-target dirs differ from what the test
+          # workflows cache, so these need to be separate entries.
+          key: release-${{ 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' }}
      - name: Install dependencies
        run: pnpm install --frozen-lockfile
      - name: Install Zig
@@ -225,9 +206,13 @@ 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/registry/cache:/usr/local/cargo/registry/cache \
-                    -v ${{ github.workspace }}/.cargo/registry/index:/usr/local/cargo/registry/index \
+                    -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 }}:/build -w /build/nodejs"
          run: |
            set -e
@@ -239,6 +224,16 @@ 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 }}
@@ -252,6 +247,15 @@ 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
        with:
@@ -402,7 +406,9 @@ jobs:
    name: Report Workflow Failure
    runs-on: ubuntu-latest
    needs: [build-lancedb, test-lancedb, publish]
-    if: always() && failure() && startsWith(github.ref, 'refs/tags/v')
+    # 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')
    permissions:
      contents: read
      issues: write
@@ -3,7 +3,7 @@ name: PyPI Publish
 on:
  push:
    tags:
-      - 'python-v*'
+      - 'v*'
  pull_request:
    # This should trigger a dry run (we skip the final publish step)
    paths:
@@ -20,6 +20,12 @@ 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 }}
@@ -72,7 +78,7 @@ jobs:
          package-name: ${{ matrix.config.package_name }}
          rustflags: ${{ matrix.config.rustflags }}
      - uses: actions/upload-artifact@v7
-        if: startsWith(github.ref, 'refs/tags/python-v')
+        if: startsWith(github.ref, 'refs/tags/v')
        with:
          name: wheels-linux-${{ matrix.config.package_name }}-${{ matrix.config.platform }}-${{ matrix.config.manylinux }}
          path: target/wheels/*.whl
@@ -101,7 +107,7 @@ jobs:
          python-minor-version: 10
          args: "--release --strip --target ${{ matrix.config.target }} --features fp16kernels"
      - uses: actions/upload-artifact@v7
-        if: startsWith(github.ref, 'refs/tags/python-v')
+        if: startsWith(github.ref, 'refs/tags/v')
        with:
          name: wheels-mac-${{ matrix.config.target }}
          path: target/wheels/lancedb-*.whl
@@ -122,19 +128,26 @@ 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/python-v')
+        if: startsWith(github.ref, 'refs/tags/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/python-v')
+    if: startsWith(github.ref, 'refs/tags/v')
    needs: [linux, mac, windows]
    runs-on: ubuntu-latest
    permissions:
@@ -183,72 +196,6 @@ 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
@@ -256,7 +203,7 @@ jobs:
    permissions:
      contents: read
      issues: write
-    if: always() && failure() && startsWith(github.ref, 'refs/tags/python-v')
+    if: always() && failure() && startsWith(github.ref, 'refs/tags/v')
    steps:
      - uses: actions/checkout@v6
      - uses: ./.github/actions/create-failure-issue
@@ -108,6 +108,15 @@ 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]
@@ -168,6 +177,14 @@ 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
@@ -197,6 +214,14 @@ 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
@@ -224,6 +249,14 @@ 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"
@@ -48,6 +48,11 @@ 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
@@ -89,6 +94,11 @@ 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
@@ -118,6 +128,11 @@ jobs:
          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
@@ -175,6 +190,11 @@ jobs:
      - 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
@@ -187,12 +207,19 @@ jobs:
          cargo test --profile ci --features $ALL_FEATURES --locked

  windows:
-    runs-on: windows-2022
    strategy:
+      fail-fast: false
      matrix:
-        target:
-          - x86_64-pc-windows-msvc
-          - aarch64-pc-windows-msvc
+        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 }}
    defaults:
      run:
        working-directory: rust/lancedb
@@ -201,6 +228,11 @@ jobs:
      - 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
@@ -208,11 +240,12 @@ 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
-          cargo test --profile ci --features aws,remote --locked
+          # `--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 }}

  msrv:
    # Check the minimum supported Rust version
@@ -238,6 +271,11 @@ 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: |
@@ -92,6 +92,8 @@ 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:

@@ -103,6 +105,33 @@ 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.
@@ -217,9 +217,9 @@ checksum = "7c02d123df017efcdfbd739ef81735b36c5ba83ec3c59c80a9d7ecc718f92e50"

 [[package]]
 name = "arrow"
-version = "58.3.0"
+version = "58.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "378530e55cd479eda3c14eb345310799717e6f76d0c332041e8487022166b471"
+checksum = "6cfdd0833e32a9874d2b55089333ad310c0be208aafa277385ce2461dec90be3"
 dependencies = [
 "arrow-arith",
 "arrow-array",
@@ -239,9 +239,9 @@ dependencies = [

 [[package]]
 name = "arrow-arith"
-version = "58.3.0"
+version = "58.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a0ab212d2c1886e802f51c5212d78ebbcbb0bec980fff9dadc1eb8d45cd0b738"
+checksum = "0a41203398f0eaa6f7ec8e62c0da742a21abf282c148fc157f6c35c90e29981a"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -253,9 +253,9 @@ dependencies = [

 [[package]]
 name = "arrow-array"
-version = "58.3.0"
+version = "58.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cfd33d3e92f207444098c75b42de99d329562be0cf686b307b097cc52b4e999e"
+checksum = "ae33dad492b7df00a217563a7b0ef2874df68a0deea1b1a3acf628152f7f7a69"
 dependencies = [
 "ahash",
 "arrow-buffer",
@@ -272,9 +272,9 @@ dependencies = [

 [[package]]
 name = "arrow-buffer"
-version = "58.3.0"
+version = "58.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0c6cd424c2693bcdbc150d843dc9d4d137dd2de4782ce6df491ad11a3a0416c0"
+checksum = "b9552f96391c005e6ab449fa941420935e7e062489b12b8b1b08879b2163f5b5"
 dependencies = [
 "bytes",
 "half",
@@ -284,9 +284,9 @@ dependencies = [

 [[package]]
 name = "arrow-cast"
-version = "58.3.0"
+version = "58.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4c5aefb56a2c02e9e2b30746241058b85f8983f0fcff2ba0c6d09006e1cded7f"
+checksum = "3a8a327c9649f30d8406995f27642b68df354713cca3baaaf100f076f18d5f34"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -306,9 +306,9 @@ dependencies = [

 [[package]]
 name = "arrow-csv"
-version = "58.3.0"
+version = "58.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e94e8cf7e517657a52b91ea1263acf38c4ca62a84655d72458a3359b12ab97de"
+checksum = "af0dd6d90d1955e9f9a014c1e563ee8aeffc21909085d25623e1da44d96eca26"
 dependencies = [
 "arrow-array",
 "arrow-cast",
@@ -321,9 +321,9 @@ dependencies = [

 [[package]]
 name = "arrow-data"
-version = "58.3.0"
+version = "58.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3c88210023a2bfee1896af366309a3028fc3bcbd6515fa29a7990ee1baa08ee0"
+checksum = "2b24852db04738907e06c04ea61e42fe7fda962a34513022dc0d0e754fb7976b"
 dependencies = [
 "arrow-buffer",
 "arrow-schema",
@@ -334,9 +334,9 @@ dependencies = [

 [[package]]
 name = "arrow-ipc"
-version = "58.3.0"
+version = "58.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "238438f0834483703d88896db6fe5a7138b2230debc31b34c0336c2996e3c64f"
+checksum = "29a908a11fcfb3fb2f6730f4ac15e367bc644e419155e96238f68cf3adde572b"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -350,9 +350,9 @@ dependencies = [

 [[package]]
 name = "arrow-json"
-version = "58.3.0"
+version = "58.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "205ca2119e6d679d5c133c6f30e68f027738d95ed948cf77677ea69c7800036b"
+checksum = "b8a96aed3931c076adee39ec2a40d8219fc7f09e79bcdaca1df16272993e1e14"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -375,9 +375,9 @@ dependencies = [

 [[package]]
 name = "arrow-ord"
-version = "58.3.0"
+version = "58.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1bffd8fd2579286a5d63bac898159873e5094a79009940bcb42bbfce4f19f1d0"
+checksum = "63a083ec750f5c043f02946b4baf05fcdbb55f4560a3277055caca5cc99f3eb0"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -388,9 +388,9 @@ dependencies = [

 [[package]]
 name = "arrow-pyarrow"
-version = "58.3.0"
+version = "58.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d29abdf672a81c1aeb57fd2661457f9918964d49aed0e9f18932535f2a9e49ce"
+checksum = "3ffb9be5a873590f825aef50df20e0f8dff5fd42a77058e28bbe7bd44bb53dec"
 dependencies = [
 "arrow-array",
 "arrow-data",
@@ -400,9 +400,9 @@ dependencies = [

 [[package]]
 name = "arrow-row"
-version = "58.3.0"
+version = "58.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bab5994731204603c73ba69267616c50f80780774c6bb0476f1f830625115e0c"
+checksum = "514ba0ef0d4c5896202dae736251ce415abb43a950bed570fb7981b8716c0e4c"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -413,9 +413,9 @@ dependencies = [

 [[package]]
 name = "arrow-schema"
-version = "58.3.0"
+version = "58.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f633dbfdf39c039ada1bf9e34c694816eb71fbb7dc78f613993b7245e078a1ed"
+checksum = "21ca356ad6425cecb6eb7b28e4f659f1ee7880fbb1a16127de7dd62901efee9e"
 dependencies = [
 "bitflags 2.11.1",
 "serde_core",
@@ -424,9 +424,9 @@ dependencies = [

 [[package]]
 name = "arrow-select"
-version = "58.3.0"
+version = "58.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8cd065c54172ac787cf3f2f8d4107e0d3fdc26edba76fdf4f4cc170258942222"
+checksum = "c58da39eb3d8350ad4a549e5c2bc49284dac554016c69829310350f1731b0aad"
 dependencies = [
 "ahash",
 "arrow-array",
@@ -438,9 +438,9 @@ dependencies = [

 [[package]]
 name = "arrow-string"
-version = "58.3.0"
+version = "58.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "29dd7cda3ab9692f43a2e4acc444d760cc17b12bb6d8232ddf64e9bab7c06b42"
+checksum = "b6789b388467525e3271326b6b4915666ecfdf5142aef09779445c954b67543c"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -601,7 +601,7 @@ dependencies = [
 "bytes",
 "fastrand",
 "hex",
- "http 1.4.2",
+ "http 1.5.0",
 "sha1 0.10.6",
 "time",
 "tokio",
@@ -664,7 +664,7 @@ dependencies = [
 "bytes-utils",
 "fastrand",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 0.4.6",
 "http-body 1.1.0",
 "percent-encoding",
@@ -694,7 +694,7 @@ dependencies = [
 "bytes",
 "fastrand",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body-util",
 "regex-lite",
 "tracing",
@@ -719,7 +719,7 @@ dependencies = [
 "bytes",
 "fastrand",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "regex-lite",
 "tracing",
 ]
@@ -743,7 +743,7 @@ dependencies = [
 "bytes",
 "fastrand",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "regex-lite",
 "tracing",
 ]
@@ -773,7 +773,7 @@ dependencies = [
 "hex",
 "hmac 0.13.0",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "lru",
 "percent-encoding",
@@ -802,7 +802,7 @@ dependencies = [
 "bytes",
 "fastrand",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "regex-lite",
 "tracing",
 ]
@@ -826,7 +826,7 @@ dependencies = [
 "bytes",
 "fastrand",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "regex-lite",
 "tracing",
 ]
@@ -851,7 +851,7 @@ dependencies = [
 "aws-types",
 "fastrand",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "regex-lite",
 "tracing",
 ]
@@ -873,7 +873,7 @@ dependencies = [
 "hex",
 "hmac 0.13.0",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "p256",
 "percent-encoding",
 "ring",
@@ -906,7 +906,7 @@ dependencies = [
 "bytes",
 "crc-fast",
 "hex",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "http-body-util",
 "md-5 0.11.0",
@@ -940,7 +940,7 @@ dependencies = [
 "bytes-utils",
 "futures-core",
 "futures-util",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "http-body-util",
 "percent-encoding",
@@ -961,7 +961,7 @@ dependencies = [
 "h2 0.3.27",
 "h2 0.4.14",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 0.4.6",
 "hyper 0.14.32",
 "hyper 1.9.0",
@@ -1023,7 +1023,7 @@ dependencies = [
 "bytes",
 "fastrand",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 0.4.6",
 "http-body 1.1.0",
 "http-body-util",
@@ -1044,7 +1044,7 @@ dependencies = [
 "aws-smithy-types",
 "bytes",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "pin-project-lite",
 "tokio",
 "tracing",
@@ -1070,7 +1070,7 @@ checksum = "7442cb268338f0eb8278140a107c046756aa01093d8ef5e99628d34ae09c94f5"
 dependencies = [
 "aws-smithy-runtime-api",
 "aws-smithy-types",
- "http 1.4.2",
+ "http 1.5.0",
 ]

 [[package]]
@@ -1084,7 +1084,7 @@ dependencies = [
 "bytes-utils",
 "futures-core",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 0.4.6",
 "http-body 1.1.0",
 "http-body-util",
@@ -1132,7 +1132,7 @@ dependencies = [
 "axum-core",
 "bytes",
 "futures-util",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "http-body-util",
 "hyper 1.9.0",
@@ -1165,7 +1165,7 @@ dependencies = [
 "async-trait",
 "bytes",
 "futures-util",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "http-body-util",
 "mime",
@@ -3421,8 +3421,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"

 [[package]]
 name = "fsst"
-version = "9.1.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.1.0-beta.8#5107a99e3f3912851c8cbb3822bd5b4cbf7fda2f"
+version = "10.1.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
 dependencies = [
 "arrow-array",
 "rand 0.9.5",
@@ -3842,7 +3842,7 @@ dependencies = [
 "fnv",
 "futures-core",
 "futures-sink",
- "http 1.4.2",
+ "http 1.5.0",
 "indexmap 2.14.0",
 "slab",
 "tokio",
@@ -3953,7 +3953,7 @@ checksum = "629d8f3bbeda9d148036d6b0de0a3ab947abd08ce90626327fc3547a49d59d97"
 dependencies = [
 "dirs",
 "futures",
- "http 1.4.2",
+ "http 1.5.0",
 "indicatif",
 "libc",
 "log",
@@ -3976,7 +3976,7 @@ checksum = "430b33fa84f92796d4d263070b6c0d3ca219df7b9a0e1853ee431029b1612bcd"
 dependencies = [
 "async-trait",
 "bytes",
- "http 1.4.2",
+ "http 1.5.0",
 "more-asserts",
 "serde",
 "thiserror 2.0.18",
@@ -4041,9 +4041,9 @@ dependencies = [

 [[package]]
 name = "http"
-version = "1.4.2"
+version = "1.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6970f50e31d6fc17d3fa27329444bfa74e196cf62e95052a3f6fee181dba6425"
+checksum = "918d3568bebf352712bc2ef3d46a8bcf1a75b373be6539de198e9105cbbf9ce0"
 dependencies = [
 "bytes",
 "itoa",
@@ -4067,7 +4067,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ca2a8f2913ee65f60facd6a5905613afaa448497a0230cc41ce022d93290bc2c"
 dependencies = [
 "bytes",
- "http 1.4.2",
+ "http 1.5.0",
 ]

 [[package]]
@@ -4078,7 +4078,7 @@ checksum = "b021d93e26becf5dc7e1b75b1bed1fd93124b374ceb73f43d4d4eafec896a64a"
 dependencies = [
 "bytes",
 "futures-core",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "pin-project-lite",
 ]
@@ -4145,7 +4145,7 @@ dependencies = [
 "futures-channel",
 "futures-core",
 "h2 0.4.14",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "httparse",
 "httpdate",
@@ -4177,7 +4177,7 @@ version = "0.27.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "33ca68d021ef39cf6463ab54c1d0f5daf03377b70561305bb89a8f83aab66e0f"
 dependencies = [
- "http 1.4.2",
+ "http 1.5.0",
 "hyper 1.9.0",
 "hyper-util",
 "rustls 0.23.40",
@@ -4211,7 +4211,7 @@ dependencies = [
 "bytes",
 "futures-channel",
 "futures-util",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "hyper 1.9.0",
 "ipnet",
@@ -4777,8 +4777,8 @@ checksum = "e037a2e1d8d5fdbd49b16a4ea09d5d6401c1f29eca5ff29d03d3824dba16256a"

 [[package]]
 name = "lance"
-version = "9.1.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.1.0-beta.8#5107a99e3f3912851c8cbb3822bd5b4cbf7fda2f"
+version = "10.1.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
 dependencies = [
 "arc-swap",
 "arrow",
@@ -4852,8 +4852,8 @@ dependencies = [

 [[package]]
 name = "lance-arrow"
-version = "9.1.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.1.0-beta.8#5107a99e3f3912851c8cbb3822bd5b4cbf7fda2f"
+version = "10.1.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4875,7 +4875,7 @@ dependencies = [
 [[package]]
 name = "lance-arrow-scalar"
 version = "58.0.0"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.1.0-beta.8#5107a99e3f3912851c8cbb3822bd5b4cbf7fda2f"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4889,7 +4889,7 @@ dependencies = [
 [[package]]
 name = "lance-arrow-stats"
 version = "58.0.0"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.1.0-beta.8#5107a99e3f3912851c8cbb3822bd5b4cbf7fda2f"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
 dependencies = [
 "arrow-array",
 "arrow-schema",
@@ -4898,8 +4898,8 @@ dependencies = [

 [[package]]
 name = "lance-bitpacking"
-version = "9.1.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.1.0-beta.8#5107a99e3f3912851c8cbb3822bd5b4cbf7fda2f"
+version = "10.1.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
 dependencies = [
 "arrayref",
 "crunchy",
@@ -4909,14 +4909,15 @@ dependencies = [

 [[package]]
 name = "lance-core"
-version = "9.1.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.1.0-beta.8#5107a99e3f3912851c8cbb3822bd5b4cbf7fda2f"
+version = "10.1.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
 "arrow-data",
 "arrow-schema",
 "async-trait",
+ "blake3",
 "byteorder",
 "bytes",
 "datafusion-common",
@@ -4933,6 +4934,7 @@ dependencies = [
 "object_store",
 "pin-project",
 "prost",
+ "quick_cache",
 "rand 0.9.5",
 "roaring",
 "serde_json",
@@ -4948,8 +4950,8 @@ dependencies = [

 [[package]]
 name = "lance-datafusion"
-version = "9.1.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.1.0-beta.8#5107a99e3f3912851c8cbb3822bd5b4cbf7fda2f"
+version = "10.1.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -4979,8 +4981,8 @@ dependencies = [

 [[package]]
 name = "lance-datagen"
-version = "9.1.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.1.0-beta.8#5107a99e3f3912851c8cbb3822bd5b4cbf7fda2f"
+version = "10.1.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -4997,8 +4999,8 @@ dependencies = [

 [[package]]
 name = "lance-derive"
-version = "9.1.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.1.0-beta.8#5107a99e3f3912851c8cbb3822bd5b4cbf7fda2f"
+version = "10.1.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
 dependencies = [
 "proc-macro2",
 "quote",
@@ -5007,8 +5009,8 @@ dependencies = [

 [[package]]
 name = "lance-encoding"
-version = "9.1.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.1.0-beta.8#5107a99e3f3912851c8cbb3822bd5b4cbf7fda2f"
+version = "10.1.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
 dependencies = [
 "arrow-arith",
 "arrow-array",
@@ -5043,12 +5045,13 @@ dependencies = [

 [[package]]
 name = "lance-file"
-version = "9.1.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.1.0-beta.8#5107a99e3f3912851c8cbb3822bd5b4cbf7fda2f"
+version = "10.1.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
 dependencies = [
 "arrow-arith",
 "arrow-array",
 "arrow-buffer",
+ "arrow-cast",
 "arrow-data",
 "arrow-schema",
 "arrow-select",
@@ -5074,8 +5077,8 @@ dependencies = [

 [[package]]
 name = "lance-index"
-version = "9.1.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.1.0-beta.8#5107a99e3f3912851c8cbb3822bd5b4cbf7fda2f"
+version = "10.1.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
 dependencies = [
 "arc-swap",
 "arrow",
@@ -5142,8 +5145,8 @@ dependencies = [

 [[package]]
 name = "lance-index-core"
-version = "9.1.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.1.0-beta.8#5107a99e3f3912851c8cbb3822bd5b4cbf7fda2f"
+version = "10.1.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
 dependencies = [
 "arrow-array",
 "arrow-schema",
@@ -5165,18 +5168,12 @@ dependencies = [

 [[package]]
 name = "lance-io"
-version = "9.1.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.1.0-beta.8#5107a99e3f3912851c8cbb3822bd5b4cbf7fda2f"
+version = "10.1.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
 dependencies = [
 "arrow",
- "arrow-arith",
 "arrow-array",
- "arrow-buffer",
- "arrow-cast",
- "arrow-data",
 "arrow-schema",
- "arrow-select",
- "async-recursion",
 "async-trait",
 "aws-config",
 "aws-credential-types",
@@ -5185,7 +5182,7 @@ dependencies = [
 "chrono",
 "futures",
 "goosefs-sdk",
- "http 1.4.2",
+ "http 1.5.0",
 "io-uring",
 "lance-arrow",
 "lance-core",
@@ -5209,8 +5206,8 @@ dependencies = [

 [[package]]
 name = "lance-linalg"
-version = "9.1.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.1.0-beta.8#5107a99e3f3912851c8cbb3822bd5b4cbf7fda2f"
+version = "10.1.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -5226,8 +5223,8 @@ dependencies = [

 [[package]]
 name = "lance-namespace"
-version = "9.1.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.1.0-beta.8#5107a99e3f3912851c8cbb3822bd5b4cbf7fda2f"
+version = "10.1.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
 dependencies = [
 "arrow",
 "async-trait",
@@ -5239,8 +5236,8 @@ dependencies = [

 [[package]]
 name = "lance-namespace-impls"
-version = "9.1.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.1.0-beta.8#5107a99e3f3912851c8cbb3822bd5b4cbf7fda2f"
+version = "10.1.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
 dependencies = [
 "arrow",
 "arrow-ipc",
@@ -5294,8 +5291,8 @@ dependencies = [

 [[package]]
 name = "lance-select"
-version = "9.1.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.1.0-beta.8#5107a99e3f3912851c8cbb3822bd5b4cbf7fda2f"
+version = "10.1.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -5310,8 +5307,8 @@ dependencies = [

 [[package]]
 name = "lance-table"
-version = "9.1.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.1.0-beta.8#5107a99e3f3912851c8cbb3822bd5b4cbf7fda2f"
+version = "10.1.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -5350,8 +5347,8 @@ dependencies = [

 [[package]]
 name = "lance-testing"
-version = "9.1.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.1.0-beta.8#5107a99e3f3912851c8cbb3822bd5b4cbf7fda2f"
+version = "10.1.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
 dependencies = [
 "arrow-array",
 "arrow-schema",
@@ -5364,8 +5361,8 @@ dependencies = [

 [[package]]
 name = "lance-tokenizer"
-version = "9.1.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.1.0-beta.8#5107a99e3f3912851c8cbb3822bd5b4cbf7fda2f"
+version = "10.1.0-beta.1"
+source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
 dependencies = [
 "icu_segmenter",
 "jieba-rs",
@@ -5378,7 +5375,7 @@ dependencies = [

 [[package]]
 name = "lancedb"
-version = "0.32.0-beta.2"
+version = "0.37.1-beta.0"
 dependencies = [
 "ahash",
 "anyhow",
@@ -5417,7 +5414,7 @@ dependencies = [
 "goosefs-sdk",
 "half",
 "hf-hub",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "lance",
 "lance-arrow",
@@ -5466,7 +5463,7 @@ dependencies = [

 [[package]]
 name = "lancedb-nodejs"
-version = "0.32.0-beta.2"
+version = "0.37.1-beta.0"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -5491,7 +5488,7 @@ dependencies = [

 [[package]]
 name = "lancedb-python"
-version = "0.35.0-beta.2"
+version = "0.37.1-beta.0"
 dependencies = [
 "arrow",
 "async-trait",
@@ -6083,15 +6080,15 @@ dependencies = [

 [[package]]
 name = "napi-build"
-version = "2.3.2"
+version = "2.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c9c366d2c8c60b86fa632df75f745509b52f9128f91a6bad4c796e44abb505e1"
+checksum = "5282704fbe8d49b0cf8b08e3f33233416a528658f205c7e5ace63b582de0b11c"

 [[package]]
 name = "napi-derive"
-version = "3.6.0"
+version = "3.6.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a49c513341a61a16a10af6efcce46b30d0822ba2d4fb197d24d33dfc199c78d5"
+checksum = "4d5c9c02556ea6dc99dffd36c1ce60141411657438501a125b675776d011ce92"
 dependencies = [
 "convert_case",
 "ctor 1.0.5",
@@ -6103,9 +6100,9 @@ dependencies = [

 [[package]]
 name = "napi-derive-backend"
-version = "6.0.0"
+version = "6.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4747005fa3e2c9989ac45a723a514c5db2411238b72981a3cda4c701a9dfea17"
+checksum = "d60b5d773ad46c698c8cc2cd9fde0b283d39cbb7f71c04bee633c7bdba4423bd"
 dependencies = [
 "convert_case",
 "proc-macro2",
@@ -6359,7 +6356,7 @@ dependencies = [
 "futures-channel",
 "futures-core",
 "futures-util",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body-util",
 "httparse",
 "humantime",
@@ -6480,7 +6477,7 @@ dependencies = [
 "base64 0.22.1",
 "bytes",
 "futures",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "jiff",
 "log",
@@ -6505,7 +6502,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0d6f81ba6960e3fae1882f253b114b21d7e444e1534f209c7737a79f6243eb6f"
 dependencies = [
 "futures",
- "http 1.4.2",
+ "http 1.5.0",
 "mea",
 "opendal-core",
 ]
@@ -6549,7 +6546,7 @@ checksum = "0030644366ef5d8cbe3a4a5822bf99a4aafddc1666e9d24b44d158d9062fc76a"
 dependencies = [
 "base64 0.22.1",
 "bytes",
- "http 1.4.2",
+ "http 1.5.0",
 "log",
 "opendal-core",
 "opendal-service-azure-common",
@@ -6570,7 +6567,7 @@ checksum = "6dea4908d490143a9b0b7f7a790e139ff829b06a023f670455ed3d44f664b361"
 dependencies = [
 "base64 0.22.1",
 "bytes",
- "http 1.4.2",
+ "http 1.5.0",
 "log",
 "opendal-core",
 "opendal-service-azure-common",
@@ -6588,7 +6585,7 @@ version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9b489f13c42e69d69bdd72952b634356ec43a7881a20259b38b540fcecdf4051"
 dependencies = [
- "http 1.4.2",
+ "http 1.5.0",
 "opendal-core",
 ]

@@ -6599,7 +6596,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "aa8cafe9729213375c7331019b0cb756ad3e1aff7f45cd32c45eae91ebde8901"
 dependencies = [
 "bytes",
- "http 1.4.2",
+ "http 1.5.0",
 "log",
 "opendal-core",
 "quick-xml 0.39.4",
@@ -6617,7 +6614,7 @@ checksum = "48de101aac565ed06af4b47903c24eafd249075553ec1fb18256751c45148d47"
 dependencies = [
 "async-trait",
 "bytes",
- "http 1.4.2",
+ "http 1.5.0",
 "log",
 "opendal-core",
 "percent-encoding",
@@ -6652,7 +6649,7 @@ checksum = "c4922661976a1d40794a2adfbdb888cc3c23097690f825a92f773af38908a848"
 dependencies = [
 "bytes",
 "hf-xet",
- "http 1.4.2",
+ "http 1.5.0",
 "log",
 "opendal-core",
 "percent-encoding",
@@ -6668,7 +6665,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "328fa55e8888cbdfe00826bfea2a79042422b720e8369e9e021e46121dea5ace"
 dependencies = [
 "bytes",
- "http 1.4.2",
+ "http 1.5.0",
 "log",
 "opendal-core",
 "quick-xml 0.39.4",
@@ -6687,7 +6684,7 @@ dependencies = [
 "base64 0.22.1",
 "bytes",
 "crc32c",
- "http 1.4.2",
+ "http 1.5.0",
 "log",
 "md-5 0.11.0",
 "opendal-core",
@@ -7586,7 +7583,7 @@ version = "0.14.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "343d3bd7056eda839b03204e68deff7d1b13aba7af2b2fd16890697274262ee7"
 dependencies = [
- "heck 0.5.0",
+ "heck 0.4.1",
 "itertools 0.14.0",
 "log",
 "multimap",
@@ -7802,6 +7799,18 @@ dependencies = [
 "memchr",
 ]

+[[package]]
+name = "quick_cache"
+version = "0.6.24"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b9c6658afe513a3b484e3abfdaa0d03ef3c0bbf017542c178dd55f94eb3051f9"
+dependencies = [
+ "ahash",
+ "equivalent",
+ "hashbrown 0.16.1",
+ "parking_lot",
+]
+
 [[package]]
 name = "quinn"
 version = "0.11.9"
@@ -8217,7 +8226,7 @@ checksum = "57ac2757f3140aa2e213b554148ae0b52733e624fc6723f0cc6bb3d440176c95"
 dependencies = [
 "anyhow",
 "form_urlencoded",
- "http 1.4.2",
+ "http 1.5.0",
 "log",
 "percent-encoding",
 "reqsign-core",
@@ -8235,7 +8244,7 @@ dependencies = [
 "anyhow",
 "bytes",
 "form_urlencoded",
- "http 1.4.2",
+ "http 1.5.0",
 "log",
 "percent-encoding",
 "quick-xml 0.39.4",
@@ -8257,7 +8266,7 @@ dependencies = [
 "base64 0.22.1",
 "bytes",
 "form_urlencoded",
- "http 1.4.2",
+ "http 1.5.0",
 "jsonwebtoken",
 "log",
 "pem",
@@ -8282,7 +8291,7 @@ dependencies = [
 "futures",
 "hex",
 "hmac 0.12.1",
- "http 1.4.2",
+ "http 1.5.0",
 "jiff",
 "log",
 "percent-encoding",
@@ -8309,7 +8318,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "35cc609b49c69e76ecaceb775a03f792d1ed3e7755ab3548d4534fd801e3242e"
 dependencies = [
 "form_urlencoded",
- "http 1.4.2",
+ "http 1.5.0",
 "jsonwebtoken",
 "log",
 "percent-encoding",
@@ -8329,7 +8338,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e128f19525861dbded59e1e7c17653a8ed63d573ca04aed708d552dbef5bb32a"
 dependencies = [
 "anyhow",
- "http 1.4.2",
+ "http 1.5.0",
 "log",
 "percent-encoding",
 "reqsign-core",
@@ -8349,7 +8358,7 @@ dependencies = [
 "futures-core",
 "futures-util",
 "h2 0.4.14",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "http-body-util",
 "hyper 1.9.0",
@@ -8393,7 +8402,7 @@ dependencies = [
 "bytes",
 "futures-core",
 "futures-util",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "http-body-util",
 "hyper 1.9.0",
@@ -8447,7 +8456,7 @@ checksum = "199dda04a536b532d0cc04d7979e39b1c763ea749bf91507017069c00b96056f"
 dependencies = [
 "anyhow",
 "async-trait",
- "http 1.4.2",
+ "http 1.5.0",
 "reqwest 0.13.3",
 "thiserror 2.0.18",
 "tower-service",
@@ -8489,9 +8498,9 @@ dependencies = [

 [[package]]
 name = "rkyv"
-version = "0.8.16"
+version = "0.8.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "73389e0c99e664f919275ab5b5b0471391fe9a8de61e1dff9b1eaf56a90f16e3"
+checksum = "815cc8a37159a463064825246cadb07961e25cd9885908606f6d08a98d8f8874"
 dependencies = [
 "bytecheck",
 "bytes",
@@ -8508,9 +8517,9 @@ dependencies = [

 [[package]]
 name = "rkyv_derive"
-version = "0.8.16"
+version = "0.8.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5d2ed0b54125315fb36bd021e82d314d1c126548f871634b483f46b31d13cac6"
+checksum = "c0ed1a78a1b19d184b0daa629dd9a024573173ec7d485b287cb369fb3607cc1c"
 dependencies = [
 "proc-macro2",
 "quote",
@@ -9268,7 +9277,7 @@ version = "0.8.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c1c97747dbf44bb1ca44a561ece23508e99cb592e862f22222dcf42f51d1e451"
 dependencies = [
- "heck 0.5.0",
+ "heck 0.4.1",
 "proc-macro2",
 "quote",
 "syn 2.0.117",
@@ -9280,7 +9289,7 @@ version = "0.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "54254b8531cafa275c5e096f62d48c81435d1015405a91198ddb11e967301d40"
 dependencies = [
- "heck 0.5.0",
+ "heck 0.4.1",
 "proc-macro2",
 "quote",
 "syn 2.0.117",
@@ -9721,7 +9730,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "32497e9a4c7b38532efcdebeef879707aa9f794296a4f0244f6f69e9bc8574bd"
 dependencies = [
 "fastrand",
- "getrandom 0.4.2",
+ "getrandom 0.3.4",
 "once_cell",
 "rustix",
 "windows-sys 0.61.2",
@@ -10049,7 +10058,7 @@ dependencies = [
 "base64 0.22.1",
 "bytes",
 "h2 0.4.14",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "http-body-util",
 "hyper 1.9.0",
@@ -10105,7 +10114,7 @@ checksum = "1e9cd434a998747dd2c4276bc96ee2e0c7a2eadf3cae88e52be55a05fa9053f5"
 dependencies = [
 "bitflags 2.11.1",
 "bytes",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "http-body-util",
 "pin-project-lite",
@@ -10125,7 +10134,7 @@ dependencies = [
 "bytes",
 "futures-core",
 "futures-util",
- "http 1.4.2",
+ "http 1.5.0",
 "http-body 1.1.0",
 "http-body-util",
 "pin-project-lite",
@@ -11146,7 +11155,7 @@ dependencies = [
 "clap",
 "crc32fast",
 "futures",
- "http 1.4.2",
+ "http 1.5.0",
 "hyper 1.9.0",
 "lazy_static",
 "more-asserts",
@@ -11220,7 +11229,7 @@ dependencies = [
 "chrono",
 "clap",
 "gearhash",
- "http 1.4.2",
+ "http 1.5.0",
 "itertools 0.14.0",
 "lazy_static",
 "more-asserts",
@@ -13,20 +13,20 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"

 [workspace.dependencies]
-lance = { "version" = "=9.1.0-beta.8", default-features = false, "tag" = "v9.1.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=9.1.0-beta.8", "tag" = "v9.1.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=9.1.0-beta.8", "tag" = "v9.1.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=9.1.0-beta.8", "tag" = "v9.1.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=9.1.0-beta.8", default-features = false, "tag" = "v9.1.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=9.1.0-beta.8", "tag" = "v9.1.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=9.1.0-beta.8", "tag" = "v9.1.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=9.1.0-beta.8", "tag" = "v9.1.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=9.1.0-beta.8", default-features = false, "tag" = "v9.1.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=9.1.0-beta.8", "tag" = "v9.1.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=9.1.0-beta.8", "tag" = "v9.1.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=9.1.0-beta.8", "tag" = "v9.1.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=9.1.0-beta.8", "tag" = "v9.1.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=9.1.0-beta.8", "tag" = "v9.1.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=10.1.0-beta.1", default-features = false, "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=10.1.0-beta.1", default-features = false, "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=10.1.0-beta.1", default-features = false, "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "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 }
@@ -2,9 +2,9 @@ set -e

 RELEASE_TYPE=${1:-"stable"}
 BUMP_MINOR=${2:-false}
-TAG_PREFIX=${3:-"v"} # Such as "python-v"
-HEAD_SHA=${4:-$(git rev-parse HEAD)}
+HEAD_SHA=$(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 +51,11 @@ 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
@@ -453,6 +453,16 @@ 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
@@ -510,4 +520,4 @@ 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>0.32.0-beta.2</version>
+    <version>0.37.1-beta.0</version>
 </dependency>
 ```

@@ -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](../CONTRIBUTING.md).
+For general contribution guidelines, see [CONTRIBUTING.md](https://github.com/lancedb/lancedb/blob/main/CONTRIBUTING.md).

 ## Project layout

@@ -25,6 +25,27 @@ the underlying connection has been closed.

 ## Methods

+### cancelJob()
+
+```ts
+abstract cancelJob(jobId): Promise<boolean>
+```
+
+Request cancellation of a server-side job by id.
+
+Resolves to true if the server accepted the cancellation, false if no
+such job exists. Cancelling an already-terminal job is a no-op success.
+
+#### Parameters
+
+* **jobId**: `string`
+
+#### Returns
+
+`Promise`&lt;`boolean`&gt;
+
+***
+
 ### cloneTable()

 ```ts
@@ -365,6 +386,26 @@ Drop an existing table.

 ***

+### getJob()
+
+```ts
+abstract getJob(jobId): Promise<null | JobDescription>
+```
+
+Describe a single server-side job by id.
+
+Resolves to `null` when the server has no such job.
+
+#### Parameters
+
+* **jobId**: `string`
+
+#### Returns
+
+`Promise`&lt;`null` \| [`JobDescription`](../interfaces/JobDescription.md)&gt;
+
+***
+
 ### isOpen()

 ```ts
@@ -379,6 +420,62 @@ Return true if the connection has not been closed

 ***

+### job()
+
+```ts
+abstract job(jobId): Job
+```
+
+A [Job](Job.md) handle for a server-side job by id.
+
+The handle is constructed without a server round trip; an unknown id
+surfaces when the handle is used. Dropping the handle has no effect on
+the job itself.
+
+#### Parameters
+
+* **jobId**: `string`
+
+#### Returns
+
+[`Job`](Job.md)
+
+***
+
+### jobHistory()
+
+```ts
+abstract jobHistory(jobId?): Promise<Table<any>>
+```
+
+The lifecycle event history of a server-side job, as an Arrow table.
+
+Lists history across all jobs when `jobId` is omitted.
+
+#### Parameters
+
+* **jobId?**: `string`
+
+#### Returns
+
+`Promise`&lt;`Table`&lt;`any`&gt;&gt;
+
+***
+
+### listJobs()
+
+```ts
+abstract listJobs(): Promise<JobInfo[]>
+```
+
+List server-side jobs across the database's tables.
+
+#### Returns
+
+`Promise`&lt;[`JobInfo`](../interfaces/JobInfo.md)[]&gt;
+
+***
+
 ### listNamespaces()

 ```ts
@@ -0,0 +1,83 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / Job
+
+# Class: Job
+
+A handle to an operation that may still be running.
+
+## Constructors
+
+### new Job()
+
+```ts
+new Job(): Job
+```
+
+#### Returns
+
+[`Job`](Job.md)
+
+## Accessors
+
+### id
+
+```ts
+get id(): null | string
+```
+
+Identifies the operation on the server that is running it. Operations
+that run in this process have no server id. The value is opaque.
+
+#### Returns
+
+`null` \| `string`
+
+## Methods
+
+### cancel()
+
+```ts
+cancel(): Promise<void>
+```
+
+Request cancellation. Cancelling a finished operation is a no-op.
+
+#### Returns
+
+`Promise`&lt;`void`&gt;
+
+***
+
+### status()
+
+```ts
+status(): Promise<string>
+```
+
+The operation's current lifecycle state: "running", "finished",
+"failed", or "cancelled".
+
+A point snapshot; unlike [Job.wait](Job.md#wait) it does not block or reject
+on a terminal failure state. States a newer server reports that this
+client version does not know pass through as-is.
+
+#### Returns
+
+`Promise`&lt;`string`&gt;
+
+***
+
+### wait()
+
+```ts
+wait(): Promise<void>
+```
+
+Wait until the operation reaches a terminal state.
+
+#### Returns
+
+`Promise`&lt;`void`&gt;
@@ -76,24 +76,23 @@ the query optimizer chooses a suboptimal path.

 ***

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

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

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

 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. 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.
+routed through Lance's MemWAL shard writer, and a table without one uses the
+standard path.

 #### Parameters

-* **useLsmWrite**: `boolean`
-    Whether to use the LSM write path.
+* **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.

 #### Returns

@@ -497,6 +497,42 @@ 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
@@ -295,6 +295,29 @@ await table.createIndex("my_float_col");

 ***

+### createIndexAsync()
+
+```ts
+abstract createIndexAsync(column, options?): Promise<Job>
+```
+
+Create an index, returning a handle to the indexing job.
+
+The job may already be complete when returned; callers must not assume
+the index exists until [Job.wait](Job.md#wait) resolves.
+
+#### Parameters
+
+* **column**: `string`
+
+* **options?**: `Partial`&lt;[`IndexOptions`](../interfaces/IndexOptions.md)&gt;
+
+#### Returns
+
+`Promise`&lt;[`Job`](Job.md)&gt;
+
+***
+
 ### currentBranch()

 ```ts
@@ -273,6 +273,29 @@ 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
@@ -746,6 +746,42 @@ 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
@@ -25,6 +25,7 @@
 - [Connection](classes/Connection.md)
 - [HeaderProvider](classes/HeaderProvider.md)
 - [Index](classes/Index.md)
+- [Job](classes/Job.md)
 - [MakeArrowTableOptions](classes/MakeArrowTableOptions.md)
 - [MatchQuery](classes/MatchQuery.md)
 - [MergeInsertBuilder](classes/MergeInsertBuilder.md)
@@ -88,6 +89,9 @@
 - [IvfFlatOptions](interfaces/IvfFlatOptions.md)
 - [IvfPqOptions](interfaces/IvfPqOptions.md)
 - [IvfRqOptions](interfaces/IvfRqOptions.md)
+- [JobDescription](interfaces/JobDescription.md)
+- [JobFailureInfo](interfaces/JobFailureInfo.md)
+- [JobInfo](interfaces/JobInfo.md)
 - [ListNamespacesOptions](interfaces/ListNamespacesOptions.md)
 - [ListNamespacesResponse](interfaces/ListNamespacesResponse.md)
 - [LsmWriteSpec](interfaces/LsmWriteSpec.md)
@@ -43,6 +43,34 @@ The following tokenizers are available:

 ***

+### 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?

 ```ts
@@ -0,0 +1,66 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / JobDescription
+
+# Interface: JobDescription
+
+A described job from `Connection.getJob`.
+
+## Properties
+
+### creationMs
+
+```ts
+creationMs: number;
+```
+
+When the job was created, in milliseconds since the epoch.
+
+***
+
+### failure?
+
+```ts
+optional failure: JobFailureInfo;
+```
+
+Why the job failed, when the job is failed and the server reports a
+reason.
+
+***
+
+### jobId
+
+```ts
+jobId: string;
+```
+
+***
+
+### jobType
+
+```ts
+jobType: string;
+```
+
+***
+
+### specJson?
+
+```ts
+optional specJson: string;
+```
+
+The job-type-specific specification as a JSON string, when present.
+
+***
+
+### state
+
+```ts
+state: string;
+```
+
+Lifecycle state: "running", "finished", "failed", or "cancelled".
@@ -0,0 +1,33 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / JobFailureInfo
+
+# Interface: JobFailureInfo
+
+The server's account of why a job failed.
+
+## Properties
+
+### message?
+
+```ts
+optional message: string;
+```
+
+***
+
+### phase?
+
+```ts
+optional phase: string;
+```
+
+***
+
+### retryable?
+
+```ts
+optional retryable: boolean;
+```
@@ -0,0 +1,58 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / JobInfo
+
+# Interface: JobInfo
+
+A row from `Connection.listJobs`: one server-side job.
+
+## Properties
+
+### createdAtMillis
+
+```ts
+createdAtMillis: number;
+```
+
+When the job was created, in milliseconds since the epoch.
+
+***
+
+### jobId
+
+```ts
+jobId: string;
+```
+
+The job id -- what `Connection.getJob` and `Connection.cancelJob`
+accept.
+
+***
+
+### jobType
+
+```ts
+jobType: string;
+```
+
+***
+
+### state
+
+```ts
+state: string;
+```
+
+Lifecycle state: "running", "finished", "failed", or "cancelled".
+
+***
+
+### table
+
+```ts
+table: string;
+```
+
+The table the job runs against, without URI or namespace.
@@ -30,6 +30,21 @@ 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
@@ -26,6 +26,18 @@ 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
@@ -34,8 +46,12 @@ is also an [asynchronous API client](#connections-asynchronous).

 ::: lancedb.table.FragmentSummaryStats

+::: lancedb.table.TableStatistics
+
 ::: lancedb.table.Tags

+::: lancedb.table.Branches
+
 ## Expressions

 Type-safe expression builder for filters and projections. Use these instead
@@ -62,29 +78,46 @@ 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.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
+::: lancedb.embeddings
+    options:
+      show_root_heading: false
+      show_root_toc_entry: false

 ## Remote configuration

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

 ## Context

@@ -94,11 +127,50 @@ of raw SQL strings with [where][lancedb.query.LanceQueryBuilder.where] and

 ## Full text search

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

-::: lancedb.index.FTS
+```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

 ## Utilities

@@ -106,6 +178,14 @@ asynchronous API.

 ::: lancedb.merge.LanceMergeInsertBuilder

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

 ## Pydantic
@@ -114,19 +194,30 @@ asynchronous API.

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

 ## Connections (Asynchronous)

@@ -137,6 +228,12 @@ 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.
@@ -145,32 +242,20 @@ 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.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.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.table.IndexStatistics

@@ -198,3 +283,7 @@ 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>0.32.0-beta.2</version>
+      <version>0.37.1-beta.0</version>
      <relativePath>../pom.xml</relativePath>
    </parent>

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

    <groupId>com.lancedb</groupId>
    <artifactId>lancedb-parent</artifactId>
-    <version>0.32.0-beta.2</version>
+    <version>0.37.1-beta.0</version>
    <packaging>pom</packaging>
    <name>${project.artifactId}</name>
    <description>LanceDB Java SDK Parent POM</description>
@@ -28,7 +28,7 @@
    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <arrow.version>15.0.0</arrow.version>
-        <lance-core.version>9.1.0-beta.8</lance-core.version>
+        <lance-core.version>10.1.0-beta.1</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](../CONTRIBUTING.md).
+For general contribution guidelines, see [CONTRIBUTING.md](https://github.com/lancedb/lancedb/blob/main/CONTRIBUTING.md).

 ## Project layout

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.32.0-beta.2"
+version = "0.37.1-beta.0"
 publish = false
 license.workspace = true
 description.workspace = true
@@ -991,6 +991,37 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(

        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 () {
@@ -15,6 +15,7 @@ import {
  OAuthHeaderProvider,
  StaticHeaderProvider,
 } from "../lancedb/header";
+import { Index } from "../lancedb/indices";

 // Test-only header providers
 class CustomProvider extends HeaderProvider {
@@ -225,6 +226,59 @@ describe("remote connection", () => {
    );
  });

+  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",
@@ -823,3 +877,96 @@ describe("remote connection", () => {
    });
  });
 });
+
+describe("remote connection jobs surface", () => {
+  it("lists, describes, cancels, and reads history", async () => {
+    const { tableFromArrays, tableToIPC } = await import("apache-arrow");
+    const eventsTable = tableFromArrays({ state: ["created", "succeeded"] });
+    const eventsBody = Buffer.from(tableToIPC(eventsTable, "stream"));
+
+    await withMockDatabase(
+      (req, res) => {
+        let body = "";
+        req.on("data", (chunk) => {
+          body += chunk;
+        });
+        req.on("end", () => {
+          const payload = body.length > 0 ? JSON.parse(body) : {};
+          if (req.url === "/v1/jobs/list") {
+            if (payload["page_token"] === undefined) {
+              res
+                .writeHead(200, { "Content-Type": "application/json" })
+                .end(
+                  '{"jobs": [{"job_id": "job-1", "table": "t1", ' +
+                    '"job_type": "create_index", "state": "in_progress", ' +
+                    '"created_at_millis": 1000}], "page_token": "next"}',
+                );
+            } else {
+              res
+                .writeHead(200, { "Content-Type": "application/json" })
+                .end(
+                  '{"jobs": [{"job_id": "job-2", "table": "t2", ' +
+                    '"job_type": "create_index", "state": "succeeded", ' +
+                    '"created_at_millis": 2000}]}',
+                );
+            }
+          } else if (req.url === "/v1/jobs/describe") {
+            if (payload["job_id"] !== "job-1") {
+              res.writeHead(404).end("no such job");
+              return;
+            }
+            res
+              .writeHead(200, { "Content-Type": "application/json" })
+              .end(
+                '{"job_id": "job-1", "job_type": "create_index", ' +
+                  '"job_state": "FAILED", "creation_ms": 1000, ' +
+                  '"spec": {"column": "vec"}, "failure": {"phase": "execute", ' +
+                  '"message": "worker died", "retryable": true}}',
+              );
+          } else if (req.url === "/v1/jobs/cancel") {
+            if (payload["job_id"] !== "job-1") {
+              res.writeHead(404).end("no such job");
+              return;
+            }
+            res
+              .writeHead(200, { "Content-Type": "application/json" })
+              .end('{"job_id": "job-1"}');
+          } else if (req.url === "/v1/jobs/query_events") {
+            res
+              .writeHead(200, {
+                "Content-Type": "application/vnd.apache.arrow.stream",
+              })
+              .end(eventsBody);
+          } else {
+            res.writeHead(404).end();
+          }
+        });
+      },
+      async (db) => {
+        const jobs = await db.listJobs();
+        expect(jobs.map((job) => job.jobId)).toEqual(["job-1", "job-2"]);
+        expect(jobs[0].state).toEqual("running");
+        expect(jobs[1].state).toEqual("finished");
+
+        const description = await db.getJob("job-1");
+        expect(description?.state).toEqual("failed");
+        expect(JSON.parse(description?.specJson ?? "")).toEqual({
+          column: "vec",
+        });
+        expect(description?.failure?.message).toEqual("worker died");
+        expect(await db.getJob("missing")).toBeNull();
+
+        expect(await db.cancelJob("job-1")).toBe(true);
+        expect(await db.cancelJob("missing")).toBe(false);
+
+        const history = await db.jobHistory("job-1");
+        expect(history.numRows).toEqual(2);
+
+        const job = db.job("job-1");
+        expect(job.id).toEqual("job-1");
+        expect(await job.status()).toEqual("failed");
+        await expect(job.wait()).rejects.toThrow("worker died");
+      },
+    );
+  });
+});
@@ -527,6 +527,14 @@ 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(
@@ -843,7 +851,11 @@ describe("When creating an index", () => {
  afterEach(() => tmpDir.removeCallback());

  it("should create a vector index on vector columns", async () => {
-    await tbl.createIndex("vec");
+    const job = await tbl.createIndexAsync("vec");
+    expect(job.id).toBeNull();
+    await job.wait();
+    // Cancelling a job that already finished succeeds and does nothing.
+    await job.cancel();

    // check index directory
    const indexDir = path.join(tmpDir.name, "test.lance", "_indices");
@@ -2527,6 +2539,35 @@ 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 = [
@@ -2732,6 +2773,15 @@ 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;
@@ -3170,14 +3220,14 @@ describe("LSM merge insert", () => {
    await table.closeLsmWriters();
  });

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

    const res = await table
      .mergeInsert("id")
      .whenNotMatchedInsertAll()
-      .useLsmWrite(false)
+      .useLsm(false)
      .execute([
        { id: "b", value: 9 },
        { id: "e", value: 5 },
@@ -3211,4 +3261,36 @@ 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();
+  });
 });
@@ -29,8 +29,14 @@ test("full text search", async () => {
    const tbl = await db.createTable("myVectors", data, { mode: "overwrite" });

    await tbl.createIndex("doc", {
-      config: lancedb.Index.fts(),
+      config: lancedb.Index.fts({
+        stem: false,
+        removeStopWords: true,
+        customStopWords: ["banana"],
+      }),
    });
+    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
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors

+import { tableFromIPC } from "apache-arrow";
 import {
  Data,
  SchemaLike,
@@ -20,6 +21,9 @@ import type {
  CreateNamespaceResponse,
  DescribeNamespaceResponse,
  DropNamespaceResponse,
+  Job,
+  JobDescription,
+  JobInfo,
  ListNamespacesResponse,
 } from "./native";
 export type {
@@ -436,6 +440,40 @@ export abstract class Connection {
    newName: string,
    options?: RenameTableOptions,
  ): Promise<void>;
+
+  /**
+   * A {@link Job} handle for a server-side job by id.
+   *
+   * The handle is constructed without a server round trip; an unknown id
+   * surfaces when the handle is used. Dropping the handle has no effect on
+   * the job itself.
+   */
+  abstract job(jobId: string): Job;
+
+  /** List server-side jobs across the database's tables. */
+  abstract listJobs(): Promise<JobInfo[]>;
+
+  /**
+   * Describe a single server-side job by id.
+   *
+   * Resolves to `null` when the server has no such job.
+   */
+  abstract getJob(jobId: string): Promise<JobDescription | null>;
+
+  /**
+   * Request cancellation of a server-side job by id.
+   *
+   * Resolves to true if the server accepted the cancellation, false if no
+   * such job exists. Cancelling an already-terminal job is a no-op success.
+   */
+  abstract cancelJob(jobId: string): Promise<boolean>;
+
+  /**
+   * The lifecycle event history of a server-side job, as an Arrow table.
+   *
+   * Lists history across all jobs when `jobId` is omitted.
+   */
+  abstract jobHistory(jobId?: string): Promise<ArrowTable>;
 }

 /** @hideconstructor */
@@ -722,6 +760,30 @@ export class LocalConnection extends Connection {
      options?.newNamespacePath,
    );
  }
+
+  job(jobId: string): Job {
+    return this.inner.job(jobId);
+  }
+
+  async listJobs(): Promise<JobInfo[]> {
+    return this.inner.listJobs();
+  }
+
+  async getJob(jobId: string): Promise<JobDescription | null> {
+    return this.inner.getJob(jobId);
+  }
+
+  async cancelJob(jobId: string): Promise<boolean> {
+    return this.inner.cancelJob(jobId);
+  }
+
+  async jobHistory(jobId?: string): Promise<ArrowTable> {
+    const buf = await this.inner.jobHistory(jobId);
+    if (buf.length === 0) {
+      return new ArrowTable();
+    }
+    return tableFromIPC(buf);
+  }
 }

 /**
@@ -85,7 +85,13 @@ export {
  RenameTableOptions,
 } from "./connection";

-export { Session } from "./native.js";
+export {
+  Job,
+  JobDescription,
+  JobFailureInfo,
+  JobInfo,
+  Session,
+} from "./native.js";

 export {
  ExecutableQuery,
@@ -194,6 +200,16 @@ export interface TokenizeOptions {
  /** 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;

@@ -225,6 +241,7 @@ export async function tokenize(
    options?.lowercase,
    options?.stem,
    options?.removeStopWords,
+    options?.customStopWords,
    options?.asciiFolding,
    options?.ngramMinLength,
    options?.ngramMaxLength,
@@ -553,6 +553,16 @@ 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
   */
@@ -572,6 +582,14 @@ 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 {
@@ -747,10 +765,12 @@ export class Index {
        options?.lowercase,
        options?.stem,
        options?.removeStopWords,
+        options?.customStopWords,
        options?.asciiFolding,
        options?.ngramMinLength,
        options?.ngramMaxLength,
        options?.prefixOnly,
+        options?.blockSize,
      ),
    );
  }
@@ -88,21 +88,17 @@ export class MergeInsertBuilder {
    );
  }
  /**
-   * Controls whether the merge uses the MemWAL LSM write path.
+   * Control MemWAL routing for this merge.
   *
   * 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. 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.
+   * routed through Lance's MemWAL shard writer, and a table without one uses the
+   * standard path.
   *
-   * @param useLsmWrite - Whether to use the LSM write path.
+   * @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.
   */
-  useLsmWrite(useLsmWrite: boolean): MergeInsertBuilder {
-    return new MergeInsertBuilder(
-      this.#native.useLsmWrite(useLsmWrite),
-      this.#schema,
-    );
+  useLsm(enable: boolean): MergeInsertBuilder {
+    return new MergeInsertBuilder(this.#native.useLsm(enable), this.#schema);
  }
  /**
   * Controls how an LSM merge checks that its input targets a single shard.
@@ -460,6 +460,30 @@ 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;
+  }
 }

 /**
@@ -748,6 +772,20 @@ 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",
      );
@@ -30,6 +30,7 @@ import {
  DropColumnsResult,
  IndexConfig,
  IndexStatistics,
+  Job,
  Branches as NativeBranches,
  OptimizeStats,
  TableStatistics,
@@ -358,6 +359,17 @@ export abstract class Table {
    options?: Partial<IndexOptions>,
  ): Promise<void>;

+  /**
+   * Create an index, returning a handle to the indexing job.
+   *
+   * The job may already be complete when returned; callers must not assume
+   * the index exists until {@link Job.wait} resolves.
+   */
+  abstract createIndexAsync(
+    column: string,
+    options?: Partial<IndexOptions>,
+  ): Promise<Job>;
+
  /**
   * Drop an index from the table.
   *
@@ -940,6 +952,22 @@ export class LocalTable extends Table {
    );
  }

+  async createIndexAsync(
+    column: string,
+    options?: Partial<IndexOptions>,
+  ): Promise<Job> {
+    // biome-ignore lint/suspicious/noExplicitAny: skip
+    const nativeIndex = (options?.config as any)?.inner;
+    return await this.inner.createIndexAsync(
+      nativeIndex,
+      column,
+      options?.replace,
+      options?.waitTimeoutSeconds,
+      options?.name,
+      options?.train,
+    );
+  }
+
  async dropIndex(name: string): Promise<void> {
    await this.inner.dropIndex(name);
  }
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.32.0-beta.2",
+	"version": "0.37.1-beta.0",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.32.0-beta.2",
+	"version": "0.37.1-beta.0",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-musl",
-	"version": "0.32.0-beta.2",
+	"version": "0.37.1-beta.0",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-musl.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.32.0-beta.2",
+	"version": "0.37.1-beta.0",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-musl",
-	"version": "0.32.0-beta.2",
+	"version": "0.37.1-beta.0",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-musl.node",
@@ -1,6 +1,6 @@
 {
  "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.32.0-beta.2",
+  "version": "0.37.1-beta.0",
  "os": [
    "win32"
  ],
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.32.0-beta.2",
+	"version": "0.37.1-beta.0",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",
@@ -1,12 +1,12 @@
 {
  "name": "@lancedb/lancedb",
-  "version": "0.32.0-beta.2",
+  "version": "0.37.1-beta.0",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "@lancedb/lancedb",
-      "version": "0.32.0-beta.2",
+      "version": "0.37.1-beta.0",
      "cpu": [
        "x64",
        "arm64"
@@ -11,7 +11,7 @@
    "ann"
  ],
  "private": false,
-  "version": "0.32.0-beta.2",
+  "version": "0.37.1-beta.0",
  "main": "dist/index.js",
  "exports": {
    ".": "./dist/index.js",
@@ -340,6 +340,69 @@ impl Connection {
        self.get_inner()?.drop_all_tables(&ns).await.default_error()
    }

+    /// A `Job` handle for a server-side job by id.
+    ///
+    /// The handle is constructed without a server round trip; an unknown id
+    /// surfaces when the handle is used.
+    #[napi]
+    pub fn job(&self, job_id: String) -> napi::Result<crate::job::Job> {
+        let job = self.get_inner()?.job(job_id).default_error()?;
+        Ok(crate::job::Job::new(job))
+    }
+
+    /// List server-side jobs across the database's tables.
+    #[napi(catch_unwind)]
+    pub async fn list_jobs(&self) -> napi::Result<Vec<crate::job::JobInfo>> {
+        let jobs = self.get_inner()?.list_jobs().await.default_error()?;
+        Ok(jobs.into_iter().map(Into::into).collect())
+    }
+
+    /// Describe a single server-side job by id. `null` when the server has
+    /// no such job.
+    #[napi(catch_unwind)]
+    pub async fn get_job(
+        &self,
+        job_id: String,
+    ) -> napi::Result<Option<crate::job::JobDescription>> {
+        let description = self.get_inner()?.get_job(&job_id).await.default_error()?;
+        Ok(description.map(Into::into))
+    }
+
+    /// Request cancellation of a server-side job by id. Returns true if the
+    /// server accepted the cancellation, false if no such job exists.
+    #[napi(catch_unwind)]
+    pub async fn cancel_job(&self, job_id: String) -> napi::Result<bool> {
+        self.get_inner()?.cancel_job(&job_id).await.default_error()
+    }
+
+    /// The lifecycle event history of a server-side job (all jobs when
+    /// `job_id` is null), as an Arrow IPC stream buffer. Empty when there is
+    /// no history.
+    #[napi(catch_unwind)]
+    pub async fn job_history(&self, job_id: Option<String>) -> napi::Result<Buffer> {
+        let batches = self
+            .get_inner()?
+            .job_history(job_id.as_deref())
+            .await
+            .default_error()?;
+        let Some(first) = batches.first() else {
+            return Ok(Buffer::from(Vec::<u8>::new()));
+        };
+        let mut out = Vec::new();
+        let mut writer = arrow_ipc::writer::StreamWriter::try_new(&mut out, &first.schema())
+            .map_err(|e| napi::Error::from_reason(e.to_string()))?;
+        for batch in &batches {
+            writer
+                .write(batch)
+                .map_err(|e| napi::Error::from_reason(e.to_string()))?;
+        }
+        writer
+            .finish()
+            .map_err(|e| napi::Error::from_reason(e.to_string()))?;
+        drop(writer);
+        Ok(Buffer::from(out))
+    }
+
    #[napi(catch_unwind)]
    /// Describe a namespace and return its properties.
    pub async fn describe_namespace(
@@ -43,6 +43,7 @@ pub fn tokenize(
    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>,
@@ -72,6 +73,7 @@ pub fn tokenize(
    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);
    }
@@ -222,11 +224,13 @@ 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>,
-    ) -> Self {
+        block_size: Option<u32>,
+    ) -> napi::Result<Self> {
        let mut opts = FtsIndexBuilder::default();
        if let Some(with_position) = with_position {
            opts = opts.with_position(with_position);
@@ -249,6 +253,7 @@ 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);
        }
@@ -261,10 +266,15 @@ impl Index {
        if let Some(prefix_only) = prefix_only {
            opts = opts.ngram_prefix_only(prefix_only);
        }
-
-        Self {
-            inner: Mutex::new(Some(LanceDbIndex::FTS(opts))),
+        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 {
+            inner: Mutex::new(Some(LanceDbIndex::FTS(opts))),
+        })
    }

    #[napi(factory)]
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+use std::sync::Arc;
+
+use napi_derive::napi;
+
+use crate::error::NapiErrorExt;
+
+/// A handle to an operation that may still be running.
+#[napi]
+pub struct Job {
+    inner: Arc<lancedb::Job>,
+}
+
+impl Job {
+    pub(crate) fn new(inner: lancedb::Job) -> Self {
+        Self {
+            inner: Arc::new(inner),
+        }
+    }
+}
+
+#[napi]
+impl Job {
+    /// Identifies the operation on the server that is running it. Operations
+    /// that run in this process have no server id. The value is opaque.
+    #[napi(getter)]
+    pub fn id(&self) -> Option<String> {
+        self.inner.id().map(str::to_string)
+    }
+
+    /// The operation's current lifecycle state: "running", "finished",
+    /// "failed", or "cancelled".
+    ///
+    /// A point snapshot; unlike {@link Job.wait} it does not block or reject
+    /// on a terminal failure state. States a newer server reports that this
+    /// client version does not know pass through as-is.
+    #[napi(catch_unwind)]
+    pub async fn status(&self) -> napi::Result<String> {
+        self.inner.status().await.default_error()
+    }
+
+    /// Wait until the operation reaches a terminal state.
+    #[napi(catch_unwind)]
+    pub async fn wait(&self) -> napi::Result<()> {
+        self.inner.wait().await.default_error()
+    }
+
+    /// Request cancellation. Cancelling a finished operation is a no-op.
+    #[napi(catch_unwind)]
+    pub async fn cancel(&self) -> napi::Result<()> {
+        self.inner.cancel().await.default_error()
+    }
+}
+
+/// A row from `Connection.listJobs`: one server-side job.
+#[napi(object)]
+pub struct JobInfo {
+    /// The job id -- what `Connection.getJob` and `Connection.cancelJob`
+    /// accept.
+    pub job_id: String,
+    /// The table the job runs against, without URI or namespace.
+    pub table: String,
+    pub job_type: String,
+    /// Lifecycle state: "running", "finished", "failed", or "cancelled".
+    pub state: String,
+    /// When the job was created, in milliseconds since the epoch.
+    pub created_at_millis: i64,
+}
+
+impl From<lancedb::database::JobInfo> for JobInfo {
+    fn from(info: lancedb::database::JobInfo) -> Self {
+        Self {
+            job_id: info.job_id,
+            table: info.table,
+            job_type: info.job_type,
+            state: info.state,
+            created_at_millis: info.created_at_millis,
+        }
+    }
+}
+
+/// The server's account of why a job failed.
+#[napi(object)]
+pub struct JobFailureInfo {
+    pub phase: Option<String>,
+    pub message: Option<String>,
+    pub retryable: Option<bool>,
+}
+
+/// A described job from `Connection.getJob`.
+#[napi(object)]
+pub struct JobDescription {
+    pub job_id: String,
+    pub job_type: String,
+    /// Lifecycle state: "running", "finished", "failed", or "cancelled".
+    pub state: String,
+    /// When the job was created, in milliseconds since the epoch.
+    pub creation_ms: i64,
+    /// The job-type-specific specification as a JSON string, when present.
+    pub spec_json: Option<String>,
+    /// Why the job failed, when the job is failed and the server reports a
+    /// reason.
+    pub failure: Option<JobFailureInfo>,
+}
+
+impl From<lancedb::database::JobDescription> for JobDescription {
+    fn from(description: lancedb::database::JobDescription) -> Self {
+        Self {
+            job_id: description.job_id,
+            job_type: description.job_type,
+            state: description.state,
+            creation_ms: description.creation_ms,
+            spec_json: (!description.spec.is_null()).then(|| description.spec.to_string()),
+            failure: description.failure.map(|failure| JobFailureInfo {
+                phase: failure.phase,
+                message: failure.message,
+                retryable: failure.retryable,
+            }),
+        }
+    }
+}
@@ -11,6 +11,7 @@ mod error;
 mod header;
 mod index;
 mod iterator;
+mod job;
 pub mod merge;
 pub mod otel;
 pub mod permutation;
@@ -51,9 +51,9 @@ impl NativeMergeInsertBuilder {
    }

    #[napi]
-    pub fn use_lsm_write(&self, use_lsm_write: bool) -> Self {
+    pub fn use_lsm(&self, enable: bool) -> Self {
        let mut this = self.clone();
-        this.inner.use_lsm_write(use_lsm_write);
+        this.inner.use_lsm(enable);
        this
    }

@@ -168,6 +168,11 @@ impl Query {
        self.inner = self.inner.clone().with_row_id();
    }

+    #[napi]
+    pub fn use_lsm(&mut self, enable: bool) {
+        self.inner = self.inner.clone().use_lsm(enable);
+    }
+
    #[napi]
    pub fn order_by(&mut self, ordering: Option<Vec<ColumnOrdering>>) -> napi::Result<()> {
        let ordering = ordering.map(|ordering| {
@@ -374,6 +379,11 @@ impl VectorQuery {
        self.inner = self.inner.clone().with_row_id();
    }

+    #[napi]
+    pub fn use_lsm(&mut self, enable: bool) {
+        self.inner = self.inner.clone().use_lsm(enable);
+    }
+
    #[napi]
    pub fn rerank(
        &mut self,
@@ -479,6 +489,11 @@ impl TakeQuery {
        self.inner = self.inner.clone().with_row_id();
    }

+    #[napi]
+    pub fn use_lsm(&mut self, enable: bool) {
+        self.inner = self.inner.clone().use_lsm(enable);
+    }
+
    #[napi(catch_unwind)]
    pub async fn output_schema(&self) -> napi::Result<Buffer> {
        let schema = self.inner.output_schema().await.default_error()?;
@@ -168,6 +168,39 @@ impl Table {
        builder.execute().await.default_error()
    }

+    #[napi(catch_unwind)]
+    pub async fn create_index_async(
+        &self,
+        index: Option<&Index>,
+        column: String,
+        replace: Option<bool>,
+        wait_timeout_s: Option<i64>,
+        name: Option<String>,
+        train: Option<bool>,
+    ) -> napi::Result<crate::job::Job> {
+        let lancedb_index = if let Some(index) = index {
+            index.consume()?
+        } else {
+            lancedb::index::Index::Auto
+        };
+        let mut builder = self.inner_ref()?.create_index(&[column], lancedb_index);
+        if let Some(replace) = replace {
+            builder = builder.replace(replace);
+        }
+        if let Some(timeout) = wait_timeout_s {
+            builder =
+                builder.wait_timeout(std::time::Duration::from_secs(timeout.try_into().unwrap()));
+        }
+        if let Some(name) = name {
+            builder = builder.name(name);
+        }
+        if let Some(train) = train {
+            builder = builder.train(train);
+        }
+        let job = builder.execute_async().await.default_error()?;
+        Ok(crate::job::Job::new(job))
+    }
+
    #[napi(catch_unwind)]
    pub async fn drop_index(&self, index_name: String) -> napi::Result<()> {
        self.inner_ref()?
@@ -306,7 +339,9 @@ impl Table {
        let transforms = NewColumnTransform::SqlExpressions(transforms);
        let res = self
            .inner_ref()?
-            .add_columns(transforms, None)
+            .add_columns()
+            .transform(transforms)
+            .execute()
            .await
            .default_error()?;
        Ok(res.into())
@@ -323,7 +358,9 @@ impl Table {
        let transforms = NewColumnTransform::AllNulls(schema);
        let res = self
            .inner_ref()?
-            .add_columns(transforms, None)
+            .add_columns()
+            .transform(transforms)
+            .execute()
            .await
            .default_error()?;
        Ok(res.into())
@@ -1,49 +0,0 @@
-[tool.bumpversion]
-current_version = "0.35.0-beta.2"
-parse = """(?x)
-    (?P<major>0|[1-9]\\d*)\\.
-    (?P<minor>0|[1-9]\\d*)\\.
-    (?P<patch>0|[1-9]\\d*)
-    (?:-(?P<pre_l>[a-zA-Z-]+)\\.(?P<pre_n>0|[1-9]\\d*))?
-"""
-serialize = [
-    "{major}.{minor}.{patch}-{pre_l}.{pre_n}",
-    "{major}.{minor}.{patch}",
-]
-search = "{current_version}"
-replace = "{new_version}"
-regex = false
-ignore_missing_version = false
-ignore_missing_files = false
-tag = true
-sign_tags = false
-tag_name = "python-v{new_version}"
-tag_message = "Bump version: {current_version} → {new_version}"
-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
-
-# Update Cargo.lock after version bump
-pre_commit_hooks = [
-  """
-    cd python && cargo update -p lancedb-python
-    if git diff --quiet ../Cargo.lock; then
-        echo "Cargo.lock unchanged"
-    else
-        git add ../Cargo.lock
-        echo "Updated and staged Cargo.lock"
-    fi
-    """,
-]
-
-[tool.bumpversion.parts.pre_l]
-values = ["beta", "final"]
-optional_value = "final"
-
-[[tool.bumpversion.files]]
-filename = "Cargo.toml"
-search = "\nversion = \"{current_version}\""
-replace = "\nversion = \"{new_version}\""
@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.35.0-beta.2"
+version = "0.37.1-beta.0"
 publish = false
 edition.workspace = true
 description = "Python bindings for LanceDB"
@@ -20,6 +20,7 @@ from .remote import ClientConfig
 from .remote.db import RemoteDBConnection
 from .expr import Expr, col, lit, func
 from .schema import blob, vector, BlobType
+from .job import AsyncJob, Job
 from .table import AsyncTable, Table
 from .types import BaseTokenizerType
 from ._lancedb import Session
@@ -258,6 +259,7 @@ def tokenize(
    lower_case: bool = True,
    stem: bool = True,
    remove_stop_words: bool = True,
+    custom_stop_words: Optional[List[str]] = None,
    ascii_folding: bool = True,
    ngram_min_length: int = 3,
    ngram_max_length: int = 3,
@@ -265,9 +267,10 @@ def tokenize(
 ) -> Iterable[FtsToken]:
    """Tokenize a full-text search query using an explicit tokenizer.

-    This does not require a table or FTS index. The tokenizer options match
-    :class:`lancedb.index.FTS`.
+    This does not require an FTS index. The tokenizer options match
+    :class:`lancedb.index.FTS`. ``custom_stop_words`` accepts a list of strings.
    """
+
    return _tokenize(
        query,
        base_tokenizer=base_tokenizer,
@@ -276,6 +279,7 @@ def tokenize(
        lower_case=lower_case,
        stem=stem,
        remove_stop_words=remove_stop_words,
+        custom_stop_words=custom_stop_words,
        ascii_folding=ascii_folding,
        ngram_min_length=ngram_min_length,
        ngram_max_length=ngram_max_length,
@@ -497,6 +501,7 @@ __all__ = [
    "connect_namespace",
    "connect_namespace_async",
    "AsyncConnection",
+    "AsyncJob",
    "AsyncLanceNamespaceDBConnection",
    "AsyncTable",
    "FtsToken",
@@ -510,6 +515,7 @@ __all__ = [
    "BlobType",
    "vector",
    "DBConnection",
+    "Job",
    "LanceDBConnection",
    "LanceNamespaceDBConnection",
    "RemoteDBConnection",
@@ -14,14 +14,10 @@ import pyarrow as pa
 from .expr import Expr
 from .schema import blob_v2_column_paths
 from .types import BlobMode, QueryProjection, QueryProjectionSpec
-from .util import get_uri_scheme

 if TYPE_CHECKING:
    from _typeshed import WriteableBuffer

-    from .remote.table import RemoteTable
-    from .table import AsyncTable, Table
-
 BLOB_MODE_TO_HANDLING = {
    "lazy": "blobs_descriptions",
    "bytes": "all_binary",
@@ -104,22 +100,6 @@ def validate_blob_mode(blob_mode: BlobMode) -> None:
        raise ValueError(f"blob_mode must be one of {modes}, got {blob_mode!r}")


-def supports_blob_auto_row_id(table: Table | AsyncTable | RemoteTable) -> bool:
-    """Blob auto row-id applies to native tables, not LanceDB Cloud."""
-    from .remote.table import RemoteTable
-
-    if isinstance(table, RemoteTable):
-        return False
-
-    inner = getattr(table, "_inner", None)
-    if inner is not None:
-        uri = inner.database().uri
-        if isinstance(uri, str) and get_uri_scheme(uri) == "db":
-            return False
-
-    return True
-
-
 def projection_includes_blob_column(
    projection: QueryProjection,
    blob_columns: Iterable[str],
@@ -164,16 +144,14 @@ def v2_projection_needs_row_id(


 def blob_auto_row_id_for_scan(
-    table: Table | AsyncTable | RemoteTable,
    schema: pa.Schema,
    projection: QueryProjection,
    *,
    with_row_id: bool | None,
 ) -> bool:
+    """Auto row-id only applies when the caller said nothing about row ids."""
    if with_row_id is not None:
        return False
-    if not supports_blob_auto_row_id(table):
-        return False
    return v2_projection_needs_row_id(schema, projection, with_row_id=False)


@@ -186,6 +164,11 @@ def finalize_blob_query_table(
 ) -> pa.Table:
    if user_requested_row_id or not blob_auto_row_id:
        return tbl
+    if "_rowid" not in tbl.column_names:
+        # A backend that ignores the row-id request leaves nothing to stash. Hand
+        # back the projection as-is so fetch_blobs raises the error that names the
+        # ways to supply row ids, rather than failing here about a hidden column.
+        return tbl
    return stash_auto_row_ids(tbl, blob_paths)


@@ -59,6 +59,7 @@ def tokenize(
    lower_case: bool = True,
    stem: bool = True,
    remove_stop_words: bool = True,
+    custom_stop_words: Optional[List[str]] = None,
    ascii_folding: bool = True,
    ngram_min_length: int = 3,
    ngram_max_length: int = 3,
@@ -145,6 +146,13 @@ class Connection(object):
        start_after: Optional[str],
        limit: Optional[int],
    ) -> list[str]: ...  # Deprecated: Use list_tables instead
+    def job(self, job_id: str) -> Job: ...
+    async def list_jobs(self) -> List[JobInfo]: ...
+    async def get_job(self, job_id: str) -> Optional[JobDescription]: ...
+    async def cancel_job(self, job_id: str) -> bool: ...
+    async def job_history(
+        self, job_id: Optional[str] = None
+    ) -> List[pa.RecordBatch]: ...
    async def create_table(
        self,
        name: str,
@@ -208,6 +216,47 @@ class BlobFile:
    def read_range(self, offset: int, length: int) -> bytes: ...
    def read_up_to(self, length: int) -> bytes: ...

+class Job:
+    @property
+    def id(self) -> Optional[str]: ...
+    async def status(self) -> str: ...
+    async def wait(self) -> None: ...
+    async def cancel(self) -> None: ...
+
+class JobInfo:
+    @property
+    def job_id(self) -> str: ...
+    @property
+    def table(self) -> str: ...
+    @property
+    def job_type(self) -> str: ...
+    @property
+    def state(self) -> str: ...
+    @property
+    def created_at_millis(self) -> int: ...
+
+class JobFailureInfo:
+    @property
+    def phase(self) -> Optional[str]: ...
+    @property
+    def message(self) -> Optional[str]: ...
+    @property
+    def retryable(self) -> Optional[bool]: ...
+
+class JobDescription:
+    @property
+    def job_id(self) -> str: ...
+    @property
+    def job_type(self) -> str: ...
+    @property
+    def state(self) -> str: ...
+    @property
+    def creation_ms(self) -> int: ...
+    @property
+    def spec_json(self) -> Optional[str]: ...
+    @property
+    def failure(self) -> Optional[JobFailureInfo]: ...
+
 class Table:
    def name(self) -> str: ...
    def __repr__(self) -> str: ...
@@ -247,6 +296,28 @@ class Table:
        name: Optional[str],
        train: Optional[bool],
    ): ...
+    async def create_index_async(
+        self,
+        column: str,
+        index: Union[
+            IvfFlat,
+            IvfSq,
+            IvfPq,
+            HnswPq,
+            HnswSq,
+            HnswFlat,
+            BTree,
+            Bitmap,
+            LabelList,
+            Fm,
+            FTS,
+        ],
+        replace: Optional[bool],
+        wait_timeout: Optional[object],
+        *,
+        name: Optional[str],
+        train: Optional[bool],
+    ) -> Job: ...
    async def list_versions(self) -> List[Dict[str, Any]]: ...
    async def version(self) -> int: ...
    async def checkout(self, version: Union[int, str]): ...
@@ -297,6 +368,11 @@ class Table:
    async def fetch_blobs(
        self, column: str, row_ids: list[int]
    ) -> pa.LargeBinaryArray: ...
+    async def fetch_blob_ranges(
+        self,
+        column: str,
+        requests: List[Tuple[int, int, int]],
+    ) -> pa.LargeBinaryArray: ...
    async def fetch_blob_files(
        self, column: str, row_ids: list[int]
    ) -> list[Optional[BlobFile]]: ...
@@ -391,6 +467,7 @@ class Query:
    def fast_search(self): ...
    def with_row_id(self): ...
    def postfilter(self): ...
+    def use_lsm(self, enable: bool): ...
    def nearest_to(self, query_vec: pa.Array) -> VectorQuery: ...
    def nearest_to_text(self, query: dict) -> FTSQuery: ...
    def order_by(self, ordering: Optional[List[ColumnOrdering]]): ...
@@ -407,6 +484,7 @@ class Query:
 class TakeQuery:
    def select(self, columns: List[str]): ...
    def with_row_id(self): ...
+    def use_lsm(self, enable: bool): ...
    async def output_schema(self) -> pa.Schema: ...
    async def execute(self) -> RecordBatchStream: ...
    async def explain_plan(self, verbose: Optional[bool]) -> str: ...
@@ -425,6 +503,7 @@ class FTSQuery:
    def fast_search(self): ...
    def with_row_id(self): ...
    def postfilter(self): ...
+    def use_lsm(self, enable: bool): ...
    def get_query(self) -> str: ...
    def add_query_vector(self, query_vec: pa.Array) -> None: ...
    def nearest_to(self, query_vec: pa.Array) -> HybridQuery: ...
@@ -452,6 +531,7 @@ class VectorQuery:
    def column(self, column: str): ...
    def distance_type(self, distance_type: str): ...
    def postfilter(self): ...
+    def use_lsm(self, enable: bool): ...
    def refine_factor(self, refine_factor: int): ...
    def nprobes(self, nprobes: int): ...
    def minimum_nprobes(self, minimum_nprobes: int): ...
@@ -475,6 +555,7 @@ class HybridQuery:
    def fast_search(self): ...
    def with_row_id(self): ...
    def postfilter(self): ...
+    def use_lsm(self, enable: bool): ...
    def distance_type(self, distance_type: str): ...
    def refine_factor(self, refine_factor: int): ...
    def nprobes(self, nprobes: int): ...
@@ -499,6 +580,7 @@ class PyQueryRequest:
    select: Optional[Union[str, List[str]]]
    fast_search: Optional[bool]
    with_row_id: Optional[bool]
+    use_lsm: Optional[bool]
    column: Optional[str]
    query_vector: Optional[List[pa.Array]]
    minimum_nprobes: Optional[int]
@@ -45,6 +45,7 @@ from lance_namespace.errors import NamespaceNotEmptyError, TableNotFoundError

 from . import __version__
 from ._lancedb import connect as lancedb_connect  # type: ignore
+from .job import AsyncJob, Job
 from .table import (
    AsyncTable,
    LanceTable,
@@ -63,6 +64,7 @@ if TYPE_CHECKING:
    from .pydantic import LanceModel

    from ._lancedb import Connection as LanceDbConnection
+    from ._lancedb import JobDescription, JobInfo
    from .common import DATA, URI
    from .embeddings import EmbeddingFunctionConfig
    from ._lancedb import Session
@@ -178,6 +180,51 @@ class DBConnection(EnforceOverrides):
            "Namespace operations are not supported for this connection type"
        )

+    def namespace_exists(self, namespace_id: List[str]) -> bool:
+        """Check if a namespace exists.
+
+        Parameters
+        ----------
+        namespace_id: List[str]
+            The namespace identifier to check.
+
+        Returns
+        -------
+        bool
+            True if the namespace exists, False otherwise.
+
+        Raises
+        ------
+        NotImplementedError
+            If the connection type does not support namespace operations.
+        """
+        raise NotImplementedError(
+            "Namespace operations are not supported for this connection type"
+        )
+
+    def table_exists(self, table_id: List[str]) -> bool:
+        """Check if a table exists.
+
+        Parameters
+        ----------
+        table_id: List[str]
+            The table identifier to check (full path including namespace
+            segments and table name).
+
+        Returns
+        -------
+        bool
+            True if the table exists, False otherwise.
+
+        Raises
+        ------
+        NotImplementedError
+            If the connection type does not support namespace operations.
+        """
+        raise NotImplementedError(
+            "Namespace operations are not supported for this connection type"
+        )
+
    def list_tables(
        self,
        namespace_path: Optional[List[str]] = None,
@@ -359,7 +406,7 @@ class DBConnection(EnforceOverrides):

        Data is converted to Arrow before being written to disk. For maximum
        control over how data is saved, either provide the PyArrow schema to
-        convert to or else provide a [PyArrow Table](pyarrow.Table) directly.
+        convert to or else provide a [PyArrow Table][pyarrow.Table] directly.

        >>> import pyarrow as pa
        >>> custom_schema = pa.schema([
@@ -563,6 +610,46 @@ class DBConnection(EnforceOverrides):
        """
        raise NotImplementedError("serialize is not supported for this connection type")

+    def job(self, job_id: str) -> Job:
+        """A [Job][lancedb.job.Job] handle for a server-side job by id.
+
+        The handle is constructed without a server round trip; an unknown id
+        surfaces when the handle is used. Dropping the handle has no effect
+        on the job itself.
+        """
+        raise NotImplementedError("job is not supported for this connection type")
+
+    def list_jobs(self) -> List[JobInfo]:
+        """List server-side jobs across the database's tables."""
+        raise NotImplementedError("list_jobs is not supported for this connection type")
+
+    def get_job(self, job_id: str) -> Optional[JobDescription]:
+        """Describe a single server-side job by id.
+
+        Returns None when the server has no such job.
+        """
+        raise NotImplementedError("get_job is not supported for this connection type")
+
+    def cancel_job(self, job_id: str) -> bool:
+        """Request cancellation of a server-side job by id.
+
+        Returns True if the server accepted the cancellation, False if no
+        such job exists. Cancelling an already-terminal job is a no-op
+        success.
+        """
+        raise NotImplementedError(
+            "cancel_job is not supported for this connection type"
+        )
+
+    def job_history(self, job_id: Optional[str] = None) -> List[pa.RecordBatch]:
+        """The lifecycle event history of a server-side job, as Arrow batches.
+
+        Lists history across all jobs when `job_id` is None.
+        """
+        raise NotImplementedError(
+            "job_history is not supported for this connection type"
+        )
+

 class LanceDBConnection(DBConnection):
    """
@@ -620,6 +707,9 @@ class LanceDBConnection(DBConnection):
        self._namespace_client_properties = namespace_client_properties
        if _inner is not None:
            self._conn = _inner
+            # Native-derived wrappers resolve this in their async reconstruction
+            # path so construction never synchronously re-enters LOOP.
+            self._read_consistency_interval = read_consistency_interval
            self._cached_namespace_client = None
            return

@@ -669,11 +759,14 @@ class LanceDBConnection(DBConnection):
        # storage_options.  Also, this class really shouldn't be holding any state
        # beyond _conn.
        self._conn = AsyncConnection(LOOP.run(do_connect()))
+        # Keep property access synchronous so debugger introspection cannot wait on
+        # the background loop while that thread is suspended at a breakpoint.
+        self._read_consistency_interval = read_consistency_interval
        self._cached_namespace_client: Optional[LanceNamespace] = None

    @property
    def read_consistency_interval(self) -> Optional[timedelta]:
-        return LOOP.run(self._conn.get_read_consistency_interval())
+        return self._read_consistency_interval

    @property
    def session(self) -> Optional[Session]:
@@ -684,15 +777,19 @@ class LanceDBConnection(DBConnection):
        return self._conn.uri

    @classmethod
-    def from_inner(cls, inner: LanceDbConnection):
-        return cls(None, _inner=inner)
+    def from_inner(
+        cls,
+        inner: LanceDbConnection,
+        read_consistency_interval: Optional[timedelta],
+    ):
+        return cls(
+            None,
+            read_consistency_interval=read_consistency_interval,
+            _inner=inner,
+        )

    def __repr__(self) -> str:
-        val = f"{self.__class__.__name__}(uri={self._conn.uri!r}"
-        if self.read_consistency_interval is not None:
-            val += f", read_consistency_interval={repr(self.read_consistency_interval)}"
-        val += ")"
-        return val
+        return f"{self.__class__.__name__}(uri={self._conn.uri!r})"

    @override
    def serialize(self) -> str:
@@ -1129,6 +1226,47 @@ class LanceDBConnection(DBConnection):
            )
        )

+    @override
+    def job(self, job_id: str) -> Job:
+        """A [Job][lancedb.job.Job] handle for a server-side job by id.
+
+        The handle is constructed without a server round trip; an unknown id
+        surfaces when the handle is used. Dropping the handle has no effect
+        on the job itself.
+        """
+        return Job(self._conn.job(job_id))
+
+    @override
+    def list_jobs(self) -> List[JobInfo]:
+        """List server-side jobs across the database's tables."""
+        return LOOP.run(self._conn.list_jobs())
+
+    @override
+    def get_job(self, job_id: str) -> Optional[JobDescription]:
+        """Describe a single server-side job by id.
+
+        Returns None when the server has no such job.
+        """
+        return LOOP.run(self._conn.get_job(job_id))
+
+    @override
+    def cancel_job(self, job_id: str) -> bool:
+        """Request cancellation of a server-side job by id.
+
+        Returns True if the server accepted the cancellation, False if no
+        such job exists. Cancelling an already-terminal job is a no-op
+        success.
+        """
+        return LOOP.run(self._conn.cancel_job(job_id))
+
+    @override
+    def job_history(self, job_id: Optional[str] = None) -> List[pa.RecordBatch]:
+        """The lifecycle event history of a server-side job, as Arrow batches.
+
+        Lists history across all jobs when `job_id` is None.
+        """
+        return LOOP.run(self._conn.job_history(job_id))
+
    @override
    def namespace_client(self) -> LanceNamespace:
        """Get the equivalent namespace client for this connection.
@@ -1529,7 +1667,7 @@ class AsyncConnection(object):

        Data is converted to Arrow before being written to disk. For maximum
        control over how data is saved, either provide the PyArrow schema to
-        convert to or else provide a [PyArrow Table](pyarrow.Table) directly.
+        convert to or else provide a [PyArrow Table][pyarrow.Table] directly.

        >>> import pyarrow as pa
        >>> custom_schema = pa.schema([
@@ -1838,6 +1976,43 @@ class AsyncConnection(object):
            namespace_path = []
        await self._inner.drop_all_tables(namespace_path=namespace_path)

+    def job(self, job_id: str) -> AsyncJob:
+        """An [AsyncJob][lancedb.job.AsyncJob] handle for a server-side job
+        by id.
+
+        The handle is constructed without a server round trip; an unknown id
+        surfaces when the handle is used. Dropping the handle has no effect
+        on the job itself.
+        """
+        return AsyncJob(self._inner.job(job_id))
+
+    async def list_jobs(self) -> List[JobInfo]:
+        """List server-side jobs across the database's tables."""
+        return await self._inner.list_jobs()
+
+    async def get_job(self, job_id: str) -> Optional[JobDescription]:
+        """Describe a single server-side job by id.
+
+        Returns None when the server has no such job.
+        """
+        return await self._inner.get_job(job_id)
+
+    async def cancel_job(self, job_id: str) -> bool:
+        """Request cancellation of a server-side job by id.
+
+        Returns True if the server accepted the cancellation, False if no
+        such job exists. Cancelling an already-terminal job is a no-op
+        success.
+        """
+        return await self._inner.cancel_job(job_id)
+
+    async def job_history(self, job_id: Optional[str] = None) -> List[pa.RecordBatch]:
+        """The lifecycle event history of a server-side job, as Arrow batches.
+
+        Lists history across all jobs when `job_id` is None.
+        """
+        return await self._inner.job_history(job_id)
+
    async def namespace_client(self) -> LanceNamespace:
        """Get the equivalent namespace client for this connection.

@@ -21,3 +21,32 @@ from .watsonx import WatsonxEmbeddings
 from .voyageai import VoyageAIEmbeddingFunction
 from .colpali import ColPaliEmbeddings
 from .siglip import SigLipEmbeddings
+
+# The API reference renders this package with a single mkdocstrings directive,
+# which only picks up names listed here. New embedding functions must be added
+# to both the imports above and this list, or they will silently go undocumented.
+__all__ = [
+    "EmbeddingFunction",
+    "EmbeddingFunctionConfig",
+    "TextEmbeddingFunction",
+    "EmbeddingFunctionRegistry",
+    "get_registry",
+    "register",
+    "SentenceTransformerEmbeddings",
+    "OpenAIEmbeddings",
+    "OpenClipEmbeddings",
+    "BedRockText",
+    "CohereEmbeddingFunction",
+    "GeminiText",
+    "GteEmbeddings",
+    "InstructorEmbeddingFunction",
+    "JinaEmbeddings",
+    "OllamaEmbeddings",
+    "TransformersEmbeddingFunction",
+    "ColbertEmbeddings",
+    "VoyageAIEmbeddingFunction",
+    "WatsonxEmbeddings",
+    "ColPaliEmbeddings",
+    "ImageBindEmbeddings",
+    "SigLipEmbeddings",
+]
@@ -21,20 +21,20 @@ class BedRockText(TextEmbeddingFunction):
    """
    Parameters
    ----------
-    name: str, default "amazon.titan-embed-text-v1"
+    name : str, default "amazon.titan-embed-text-v1"
        The model ID of the bedrock model to use. Supported models for are:
        - amazon.titan-embed-text-v1
        - cohere.embed-english-v3
        - cohere.embed-multilingual-v3
-    region: str, default "us-east-1"
+    region : str, default "us-east-1"
        Optional name of the AWS Region in which the service should be called.
-    profile_name: str, default None
+    profile_name : str, default None
        Optional name of the AWS profile to use for calling the Bedrock service.
        If not specified, the default profile will be used.
-    assumed_role: str, default None
+    assumed_role : str, default None
        Optional ARN of an AWS IAM role to assume for calling the Bedrock service.
        If not specified, the current active credentials will be used.
-    role_session_name: str, default "lancedb-embeddings"
+    role_session_name : str, default "lancedb-embeddings"
        Optional name of the AWS IAM role session to use for calling the Bedrock
        service. If not specified, "lancedb-embeddings" name will be used.

@@ -22,7 +22,7 @@ class CohereEmbeddingFunction(TextEmbeddingFunction):

    Parameters
    ----------
-    name: str, default "embed-multilingual-v2.0"
+    name : str, default "embed-multilingual-v2.0"
        The name of the model to use. List of acceptable models:

            * embed-english-v3.0
@@ -33,12 +33,14 @@ class CohereEmbeddingFunction(TextEmbeddingFunction):
            * embed-english-light-v2.0
            * embed-multilingual-v2.0

-    source_input_type: str, default "search_document"
+    source_input_type : str, default "search_document"
        The input type for the source column in the database

-    query_input_type: str, default "search_query"
+    query_input_type : str, default "search_query"
        The input type for the query column in the database

+    Notes
+    -----
    Cohere supports following input types:

    | Input Type               | Description                          |
@@ -44,7 +44,7 @@ class ColPaliEmbeddings(EmbeddingFunction):
        The token pooling strategy to use, by default "hierarchical".
        - "hierarchical": Progressively pools tokens to reduce sequence length.
        - "lambda": A simpler pooling that uses a custom `pooling_func`.
-    pooling_func: typing.Callable, optional
+    pooling_func : typing.Callable, optional
        A function to use for pooling when `pooling_strategy` is "lambda".
    pool_factor : int
        Factor to reduce sequence length if token pooling is enabled (default 2).
@@ -52,7 +52,7 @@ class ColPaliEmbeddings(EmbeddingFunction):
        Quantization configuration for the model. (default None, bitsandbytes needed)
    batch_size : int
        Batch size for processing inputs (default 2).
-    offload_folder: str, optional
+    offload_folder : str, optional
        Folder to offload model weights if using CPU offloading (default None). This is
        useful for large models that do not fit in memory.
    """
@@ -48,16 +48,16 @@ class GeminiText(TextEmbeddingFunction):

    Parameters
    ----------
-    name: str, default "gemini-embedding-001"
+    name : str, default "gemini-embedding-001"
        The name of the model to use. Supported models include:
        - "gemini-embedding-001" (768 dimensions)

        Note: The legacy "models/embedding-001" format is also supported but
        "gemini-embedding-001" is recommended.

-    query_task_type: str, default "retrieval_query"
+    query_task_type : str, default "retrieval_query"
        Sets the task type for the queries.
-    source_task_type: str, default "retrieval_document"
+    source_task_type : str, default "retrieval_document"
        Sets the task type for ingestion.

    Examples
@@ -26,13 +26,13 @@ class GteEmbeddings(TextEmbeddingFunction):

    Parameters
    ----------
-    name: str, default "thenlper/gte-large"
+    name : str, default "thenlper/gte-large"
        The name of the model to use.
-    device: str, default "cpu"
+    device : str, default "cpu"
        Sets the device type for the model.
-    normalize: str, default "True"
+    normalize : str, default "True"
        Controls normalize param in encode function for the transformer.
-    mlx: bool, default False
+    mlx : bool, default False
        Controls which model to use. False for gte-large,True for the mlx version.

    Examples
@@ -35,23 +35,23 @@ class InstructorEmbeddingFunction(TextEmbeddingFunction):

    Parameters
    ----------
-    name: str
+    name : str
        The name of the model to use. Available models are listed at
        https://github.com/xlang-ai/instructor-embedding#model-list;
        The default model is hkunlp/instructor-base
-    batch_size: int, default 32
+    batch_size : int, default 32
        The batch size to use when generating embeddings
-    device: str, default "cpu"
+    device : str, default "cpu"
        The device to use when generating embeddings
-    show_progress_bar: bool, default True
+    show_progress_bar : bool, default True
        Whether to show a progress bar when generating embeddings
-    normalize_embeddings: bool, default True
+    normalize_embeddings : bool, default True
        Whether to normalize the embeddings
-    quantize: bool, default False
+    quantize : bool, default False
        Whether to quantize the model
-    source_instruction: str, default "represent the document for retrieval"
+    source_instruction : str, default "represent the document for retrieval"
        The instruction for the source column
-    query_instruction: str, default "represent the document for retrieving the most
+    query_instruction : str, default "represent the document for retrieving the most
        similar documents"
        The instruction for the query

@@ -40,10 +40,10 @@ class JinaEmbeddings(EmbeddingFunction):

    Parameters
    ----------
-    name: str, default "jina-clip-v1". Note that some models support both image
+    name : str, default "jina-clip-v1". Note that some models support both image
        and text embeddings and some just text embedding

-    api_key: str, default None
+    api_key : str, default None
        The api key to access Jina API. If you pass None, you can set JINA_API_KEY
        environment variable

@@ -21,13 +21,13 @@ class SentenceTransformerEmbeddings(TextEmbeddingFunction):

    Parameters
    ----------
-    name: str, default "all-MiniLM-L6-v2"
+    name : str, default "all-MiniLM-L6-v2"
        The name of the model to use.
-    device: str, default "cpu"
+    device : str, default "cpu"
        The device to use for the model
-    normalize: bool, default True
+    normalize : bool, default True
        Whether to normalize the embeddings
-    trust_remote_code: bool, default True
+    trust_remote_code : bool, default True
        Whether to trust the remote code
    """

@@ -167,7 +167,7 @@ class VoyageAIEmbeddingFunction(EmbeddingFunction):

    Parameters
    ----------
-    name: str
+    name : str
        The name of the model to use. List of acceptable models:

            * voyage-4 (1024 dims, general-purpose and multilingual retrieval)
@@ -185,7 +185,7 @@ class VoyageAIEmbeddingFunction(EmbeddingFunction):
            * voyage-law-2
            * voyage-code-2

-    output_dimension: int, optional
+    output_dimension : int, optional
        The output dimension for models that support flexible dimensions.
        Currently only voyage-multimodal-3.5 supports this feature.
        Valid options: 256, 512, 1024 (default), 2048.
@@ -23,3 +23,15 @@ class MissingColumnError(KeyError):
        return (
            f"Error: Column '{self.column_name}' does not exist in the DataFrame object"
        )
+
+
+class JobFailedError(RuntimeError):
+    """Exception raised when an asynchronous job reaches the failed state."""
+
+    pass
+
+
+class JobCancelledError(RuntimeError):
+    """Exception raised when an asynchronous job was cancelled."""
+
+    pass
@@ -2,7 +2,7 @@
 # SPDX-FileCopyrightText: Copyright The LanceDB Authors

 from dataclasses import dataclass
-from typing import Literal, Optional
+from typing import List, Literal, Optional

 from ._lancedb import (
    IndexConfig,
@@ -115,6 +115,12 @@ class FTS:

    For example, it works with `title`, `description`, `content`, etc.

+    Examples
+    --------
+    Create an index configuration that uses 256-document posting blocks:
+
+    >>> config = FTS(block_size=256)
+
    Attributes
    ----------
    with_position : bool, default False
@@ -145,9 +151,18 @@ class FTS:
    remove_stop_words : bool, default True
        Whether to remove stop words. Stop words are common words that are often
        removed from text before indexing. For example, in English "the" and "and".
+    custom_stop_words : list of str, optional
+        Custom words replace the built-in language stop words
+        and only take effect when ``remove_stop_words`` is True. ``None`` uses
+        the built-in language list, while an empty list explicitly uses no
+        stop words.
    ascii_folding : bool, default True
        Whether to fold ASCII characters. This converts accented characters to
        their ASCII equivalent. For example, "café" would be converted to "cafe".
+    block_size : int, default 128
+        The number of documents per compressed posting block. Supported values
+        are 128 and 256. A value of 256 uses the experimental FTS V3 format
+        and may introduce breaking changes.

    Notes
    -----
@@ -168,6 +183,8 @@ class FTS:
    ngram_min_length: int = 3
    ngram_max_length: int = 3
    prefix_only: bool = False
+    block_size: int = 128
+    custom_stop_words: Optional[List[str]] = None


@dataclass
@@ -202,7 +219,7 @@ class HnswPq:
        distance has a range of (-∞, ∞). If the vectors are normalized (i.e. their
        l2 norm is 1), then dot distance is equivalent to the cosine distance.

-    num_partitions, default sqrt(num_rows)
+    num_partitions: int, default sqrt(num_rows)

        The number of IVF partitions to create.

@@ -211,7 +228,7 @@ class HnswPq:
        will require too much memory. Each partition becomes its own HNSW graph, so
        setting this value higher reduces the peak memory use of training.

-    num_sub_vectors, default is vector dimension / 16
+    num_sub_vectors: int, default is vector dimension / 16

        Number of sub-vectors of PQ.

@@ -227,13 +244,13 @@ class HnswPq:
        If the dimension is not visible by 8 then we use 1 subvector.  This is not
        ideal and will likely result in poor performance.

-     num_bits: int, default 8
+    num_bits: int, default 8
        Number of bits to encode each sub-vector.

        This value controls how much the sub-vectors are compressed.  The more bits
        the more accurate the index but the slower search. Only 4 and 8 are supported.

-    max_iterations, default 50
+    max_iterations: int, default 50

        Max iterations to train kmeans.

@@ -246,7 +263,7 @@ class HnswPq:
        those cases it is unlikely that setting this larger will lead to the index
        converging anyways.

-    sample_rate, default 256
+    sample_rate: int, default 256

        The rate used to calculate the number of training vectors for kmeans.

@@ -262,14 +279,14 @@ class HnswPq:
        Increasing this value might improve the quality of the index but in
        most cases the default should be sufficient.

-    m, default 20
+    m: int, default 20

        The number of neighbors to select for each vector in the HNSW graph.

        This value controls the tradeoff between search speed and accuracy.
        The higher the value the more accurate the search but the slower it will be.

-    ef_construction, default 300
+    ef_construction: int, default 300

        The number of candidates to evaluate during the construction of the HNSW graph.

@@ -280,7 +297,7 @@ class HnswPq:
        This value should be set to a value that is not less than `ef` in the
        search phase.

-    target_partition_size, default is 1,048,576
+    target_partition_size: int, default is 1,048,576

        The target size of each partition.

@@ -334,7 +351,7 @@ class HnswSq:
        distance has a range of (-∞, ∞). If the vectors are normalized (i.e. their
        l2 norm is 1), then dot distance is equivalent to the cosine distance.

-    num_partitions, default sqrt(num_rows)
+    num_partitions: int, default sqrt(num_rows)

        The number of IVF partitions to create.

@@ -343,7 +360,7 @@ class HnswSq:
        will require too much memory. Each partition becomes its own HNSW graph, so
        setting this value higher reduces the peak memory use of training.

-    max_iterations, default 50
+    max_iterations: int, default 50

        Max iterations to train kmeans.

@@ -356,7 +373,7 @@ class HnswSq:
        In those cases it is unlikely that setting this larger will lead to
        the index converging anyways.

-    sample_rate, default 256
+    sample_rate: int, default 256

        The rate used to calculate the number of training vectors for kmeans.

@@ -372,14 +389,14 @@ class HnswSq:
        Increasing this value might improve the quality of the index but in
        most cases the default should be sufficient.

-    m, default 20
+    m: int, default 20

        The number of neighbors to select for each vector in the HNSW graph.

        This value controls the tradeoff between search speed and accuracy.
        The higher the value the more accurate the search but the slower it will be.

-    ef_construction, default 300
+    ef_construction: int, default 300

        The number of candidates to evaluate during the construction of the HNSW graph.

@@ -390,7 +407,7 @@ class HnswSq:
        This value should be set to a value that is not less than `ef` in the search
        phase.

-    target_partition_size, default is 1,048,576
+    target_partition_size: int, default is 1,048,576

        The target size of each partition.

@@ -443,7 +460,7 @@ class HnswFlat:
        distance has a range of (-∞, ∞). If the vectors are normalized (i.e. their
        l2 norm is 1), then dot distance is equivalent to the cosine distance.

-    num_partitions, default sqrt(num_rows)
+    num_partitions: int, default sqrt(num_rows)

        The number of IVF partitions to create.

@@ -453,18 +470,18 @@ class HnswFlat:
        graph, so setting this value higher reduces the peak memory use of
        training.

-    max_iterations, default 50
+    max_iterations: int, default 50

        Max iterations to train kmeans.

        When training an IVF index we use kmeans to calculate the partitions.
        This parameter controls how many iterations of kmeans to run.

-    sample_rate, default 256
+    sample_rate: int, default 256

        The rate used to calculate the number of training vectors for kmeans.

-    m, default 20
+    m: int, default 20

        The number of neighbors to select for each vector in the HNSW graph.

@@ -472,7 +489,7 @@ class HnswFlat:
        The higher the value the more accurate the search but the slower it
        will be.

-    ef_construction, default 300
+    ef_construction: int, default 300

        The number of candidates to evaluate during the construction of the HNSW
        graph.
@@ -484,7 +501,7 @@ class HnswFlat:
        than 500.  This value should be set to a value that is not less than `ef`
        in the search phase.

-    target_partition_size, default is 1,048,576
+    target_partition_size: int, default is 1,048,576

        The target size of each partition.
    """
@@ -588,7 +605,7 @@ class IvfFlat:

        The default value is 256.

-    target_partition_size, default is 8192
+    target_partition_size: int, default is 8192

        The target size of each partition.

@@ -752,7 +769,7 @@ class IvfPq:

        The default value is 256.

-    target_partition_size, default is 8192
+    target_partition_size: int, default is 8192

        The target size of each partition.

@@ -813,7 +830,7 @@ class IvfRq:
    sample_rate: int, default 256
        Controls the number of training vectors: sample_rate * num_partitions.

-    target_partition_size, default is 8192
+    target_partition_size: int, default is 8192
        Target size of each partition.
    """

@@ -828,6 +845,9 @@ class IvfRq:
    accelerator: Optional[str] = None


+# The API reference renders this module with a single mkdocstrings directive,
+# which only picks up names listed here. New public names must be added to this
+# list, or they will silently go undocumented.
 __all__ = [
    "BTree",
    "IvfPq",
@@ -0,0 +1,105 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+"""Handles to operations a server may run asynchronously."""
+
+import asyncio
+from datetime import timedelta
+from typing import Optional
+
+from lancedb.background_loop import LOOP
+
+from . import _lancedb
+
+
+class AsyncJob:
+    """A handle to an operation that may still be running.
+
+    The operation may already be complete when the handle is created.
+    """
+
+    def __init__(self, inner: Optional["_lancedb.Job"]):
+        self._inner = inner
+
+    @property
+    def id(self) -> Optional[str]:
+        """Identifies the operation on the server that is running it.
+
+        Returned for correlating with server logs or the jobs API. Operations
+        that run in this process have no server id and return `None`. The value
+        is opaque: parsing it or storing it to resume the job later is not
+        supported.
+        """
+        return self._inner.id if self._inner is not None else None
+
+    async def status(self) -> str:
+        """The operation's current lifecycle state: "running", "finished",
+        "failed", or "cancelled".
+
+        A point snapshot; unlike `wait` it does not block or raise on a
+        terminal failure state. States a newer server reports that this
+        client version does not know pass through as-is.
+        """
+        if self._inner is None:
+            return "finished"
+        return await self._inner.status()
+
+    async def wait(self, timeout: Optional[timedelta] = None):
+        """Wait until the operation reaches a terminal state.
+
+        Raises `JobFailedError` if the operation failed, `JobCancelledError`
+        if it was cancelled, and `TimeoutError` if `timeout` elapses first.
+        """
+        if self._inner is None:
+            return
+        if timeout is None:
+            await self._inner.wait()
+        else:
+            await asyncio.wait_for(self._inner.wait(), timeout.total_seconds())
+
+    async def cancel(self):
+        """Request cancellation. Cancelling a finished operation is a no-op."""
+        if self._inner is None:
+            return
+        await self._inner.cancel()
+
+
+class Job:
+    """Synchronous counterpart of `AsyncJob`."""
+
+    def __init__(self, inner: Optional[AsyncJob]):
+        self._inner = inner
+
+    @property
+    def id(self) -> Optional[str]:
+        """Identifies the operation on the server that is running it.
+
+        See :attr:`AsyncJob.id`.
+        """
+        return self._inner.id if self._inner is not None else None
+
+    def status(self) -> str:
+        """The operation's current lifecycle state: "running", "finished",
+        "failed", or "cancelled".
+
+        See :meth:`AsyncJob.status`.
+        """
+        if self._inner is None:
+            return "finished"
+        return LOOP.run(self._inner.status())
+
+    def wait(self, timeout: Optional[timedelta] = None):
+        """Block until the operation reaches a terminal state.
+
+        Raises `JobFailedError` if the operation failed, `JobCancelledError`
+        if it was cancelled, and `TimeoutError` if `timeout` elapses first.
+        """
+        if self._inner is None:
+            return
+        LOOP.run(self._inner.wait(timeout))
+
+    def cancel(self):
+        """Request cancellation. Cancelling a finished operation is a no-op."""
+        if self._inner is None:
+            return
+        LOOP.run(self._inner.cancel())
@@ -37,7 +37,7 @@ class LanceMergeInsertBuilder(object):
        self._when_not_matched_by_source_condition_expr = None
        self._timeout = None
        self._use_index = True
-        self._use_lsm_write = None
+        self._use_lsm = None
        self._validate_single_shard = None

    def when_matched_update_all(
@@ -92,8 +92,10 @@ class LanceMergeInsertBuilder(object):
        self._when_not_matched_by_source_delete = True
        if isinstance(condition, Expr):
            self._when_not_matched_by_source_condition_expr = condition._inner
-        elif condition is not None:
+            self._when_not_matched_by_source_condition = None
+        else:
            self._when_not_matched_by_source_condition = condition
+            self._when_not_matched_by_source_condition_expr = None
        return self

    def use_index(self, use_index: bool) -> LanceMergeInsertBuilder:
@@ -113,22 +115,22 @@ class LanceMergeInsertBuilder(object):
        self._use_index = use_index
        return self

-    def use_lsm_write(self, use_lsm_write: bool) -> LanceMergeInsertBuilder:
+    def use_lsm(self, enable: bool) -> LanceMergeInsertBuilder:
        """
-        Controls whether the merge uses the MemWAL LSM write path.
+        Control MemWAL routing for this merge.

-        By default (unset), a `merge_insert` 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. Pass `False` to force the standard path even
-        when a spec is set. Pass `True` to require a spec — `merge_insert`
-        raises an error if none is installed.
+        By default (unset), a `merge_insert` 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.

        Parameters
        ----------
-        use_lsm_write: bool
-            Whether to use the LSM write path.
+        enable: bool
+            ``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.
        """
-        self._use_lsm_write = use_lsm_write
+        self._use_lsm = enable
        return self

    def validate_single_shard(
@@ -38,7 +38,11 @@ from lance_namespace_urllib3_client.models.query_table_request_vector import (
    QueryTableRequestVector,
 )
 from lance_namespace_urllib3_client.models.string_fts_query import StringFtsQuery
-from lance_namespace.errors import NamespaceNotEmptyError, TableNotFoundError
+from lance_namespace.errors import (
+    NamespaceNotEmptyError,
+    NamespaceNotFoundError,
+    TableNotFoundError,
+)
 from lancedb._lancedb import (
    connect_namespace as _connect_namespace,
    connect_namespace_client as _connect_namespace_client,
@@ -53,6 +57,8 @@ from lance_namespace import (
    DropNamespaceResponse,
    ListNamespacesResponse,
    ListTablesResponse,
+    NamespaceExistsRequest,
+    TableExistsRequest,
 )
 from lancedb.table import AsyncTable, LanceTable, Table
 from lancedb.util import validate_table_name
@@ -780,6 +786,51 @@ class LanceNamespaceDBConnection(DBConnection):
        """
        return LOOP.run(self._inner.describe_namespace(namespace_path))

+    @override
+    def namespace_exists(self, namespace_id: List[str]) -> bool:
+        """
+        Check if a namespace exists.
+
+        Parameters
+        ----------
+        namespace_id : List[str]
+            The namespace identifier to check.
+
+        Returns
+        -------
+        bool
+            True if the namespace exists, False otherwise.
+        """
+        request = NamespaceExistsRequest(id=namespace_id)
+        try:
+            self._namespace_client.namespace_exists(request)
+            return True
+        except NamespaceNotFoundError:
+            return False
+
+    @override
+    def table_exists(self, table_id: List[str]) -> bool:
+        """
+        Check if a table exists.
+
+        Parameters
+        ----------
+        table_id : List[str]
+            The table identifier to check (full path including namespace
+            segments and table name).
+
+        Returns
+        -------
+        bool
+            True if the table exists, False otherwise.
+        """
+        request = TableExistsRequest(id=table_id)
+        try:
+            self._namespace_client.table_exists(request)
+            return True
+        except TableNotFoundError:
+            return False
+
    @override
    def list_tables(
        self,
@@ -1233,6 +1284,49 @@ class AsyncLanceNamespaceDBConnection:
        """
        return await self._inner.describe_namespace(namespace_path)

+    async def namespace_exists(self, namespace_id: List[str]) -> bool:
+        """
+        Check if a namespace exists.
+
+        Parameters
+        ----------
+        namespace_id : List[str]
+            The namespace identifier to check.
+
+        Returns
+        -------
+        bool
+            True if the namespace exists, False otherwise.
+        """
+        request = NamespaceExistsRequest(id=namespace_id)
+        try:
+            self._namespace_client.namespace_exists(request)
+            return True
+        except NamespaceNotFoundError:
+            return False
+
+    async def table_exists(self, table_id: List[str]) -> bool:
+        """
+        Check if a table exists.
+
+        Parameters
+        ----------
+        table_id : List[str]
+            The table identifier to check (full path including namespace
+            segments and table name).
+
+        Returns
+        -------
+        bool
+            True if the table exists, False otherwise.
+        """
+        request = TableExistsRequest(id=table_id)
+        try:
+            self._namespace_client.table_exists(request)
+            return True
+        except TableNotFoundError:
+            return False
+
    async def list_tables(
        self,
        namespace_path: Optional[List[str]] = None,
@@ -226,7 +226,7 @@ class PermutationBuilder:

        async def do_execute():
            inner_tbl = await self._async.execute()
-            return LanceTable.from_inner(inner_tbl)
+            return await LanceTable.from_inner(inner_tbl)

        return LOOP.run(do_execute())

@@ -438,7 +438,8 @@ class Permutation:
        _reader: Optional[PermutationReader] = None,
    ):
        """
-        Internal constructor.  Use [from_tables](#from_tables) instead.
+        Internal constructor.  Use
+        [from_tables][lancedb.permutation.Permutation.from_tables] instead.
        """
        assert base_table is not None, "base_table is required"
        assert selection is not None, "selection is required"
@@ -985,8 +986,9 @@ class Permutation:
        types.  Conversion of strings, lists, and structs will require creating python
        objects and this is not zero-copy.

-        For custom formatting, use [with_transform](#with_transform) which overrides
-        this method.
+        For custom formatting, use
+        [with_transform][lancedb.permutation.Permutation.with_transform] which
+        overrides this method.
        """
        assert format is not None, "format is required"
        if format == "python":
@@ -1061,7 +1063,8 @@ class Permutation:
        Note: this method returns a new permutation and does not modify `self`
        It is provided for compatibility with the huggingface Dataset API.

-        Use [with_skip](#with_skip) instead to avoid confusion.
+        Use [with_skip][lancedb.permutation.Permutation.with_skip] instead to
+        avoid confusion.
        """
        return self.with_skip(skip)

@@ -1084,7 +1087,8 @@ class Permutation:
        Note: this method returns a new permutation and does not modify `self`
        It is provided for compatibility with the huggingface Dataset API.

-        Use [with_take](#with_take) instead to avoid confusion.
+        Use [with_take][lancedb.permutation.Permutation.with_take] instead to
+        avoid confusion.
        """
        return self.with_take(limit)

@@ -1107,7 +1111,8 @@ class Permutation:
        Note: this method returns a new permutation and does not modify `self`
        It is provided for compatibility with the huggingface Dataset API.

-        Use [with_repeat](#with_repeat) instead to avoid confusion.
+        Use [with_repeat][lancedb.permutation.Permutation.with_repeat] instead
+        to avoid confusion.
        """
        return self.with_repeat(times)

@@ -52,7 +52,6 @@ from ._blob import (
    finalize_blob_query_table,
    replace_v2_blob_columns_with_bytes,
    replace_v2_blob_columns_with_bytes_sync,
-    supports_blob_auto_row_id,
    validate_blob_mode,
 )
 from .types import BlobMode, QueryProjection
@@ -651,7 +650,8 @@ class Query(pydantic.BaseModel):
    distance_type : Optional[str]
        the distance type to use for vector search

-        This can be l2 (default), cosine and dot.  See [metric definitions][search] for
+        This can be l2 (default), cosine and dot.  See
+        [metric definitions](https://lancedb.com/docs/search/vector-search/) for
        more details.

        If this is not a vector search this will be None.
@@ -664,8 +664,9 @@ class Query(pydantic.BaseModel):

        - A higher number makes search more accurate but also slower.

-        - See discussion in [Querying an ANN Index][querying-an-ann-index] for
-          tuning advice.
+        - See discussion in
+          [Querying an ANN Index](https://lancedb.com/docs/indexing/)
+          for tuning advice.

        Will be None if this is not a vector search.
    refine_factor : Optional[int]
@@ -673,8 +674,9 @@ class Query(pydantic.BaseModel):

        - A higher number makes search more accurate but also slower.

-        - See discussion in [Querying an ANN Index][querying-an-ann-index] for
-          tuning advice.
+        - See discussion in
+          [Querying an ANN Index](https://lancedb.com/docs/indexing/)
+          for tuning advice.

        Will be None if this is not a vector search.
    lower_bound : Optional[float]
@@ -778,6 +780,11 @@ class Query(pydantic.BaseModel):
    # if true, will only search the indexed data
    fast_search: Optional[bool] = None

+    # MemWAL LSM read routing: None auto-routes when the table carries a write
+    # spec, True forces the LSM scanner (errors without a spec), False reads the
+    # base table only
+    use_lsm: Optional[bool] = None
+
    # size of the nearest neighbor list maintained during HNSW search
    ef: Optional[int] = None

@@ -795,6 +802,9 @@ class Query(pydantic.BaseModel):
        query.full_text_query = req.full_text_search
        query.columns = req.select
        query.with_row_id = req.with_row_id
+        # use_lsm is a genuine tri-state (None / True / False); preserve it as-is
+        # so a round-tripped query keeps an explicit False.
+        query.use_lsm = req.use_lsm
        query.vector_column = req.column
        query.vector = req.query_vector
        query.distance_type = req.distance_type
@@ -967,6 +977,7 @@ class LanceQueryBuilder(ABC):
        self._with_row_address = None
        self._fragments = None
        self._fragment_ids = None
+        self._use_lsm = None
        self._vector = None
        self._text = None
        self._ef = None
@@ -1268,10 +1279,7 @@ class LanceQueryBuilder(ABC):
        return self._with_row_id is True

    def _blob_auto_row_id_enabled(self) -> bool:
-        if not supports_blob_auto_row_id(self._table):
-            return False
        return blob_auto_row_id_for_scan(
-            self._table,
            self._table.schema,
            self._columns,
            with_row_id=self._with_row_id,
@@ -1326,6 +1334,30 @@ class LanceQueryBuilder(ABC):
        self._fragment_ids = fragment_ids
        return self

+    def use_lsm(self, enable: bool) -> Self:
+        """Control MemWAL LSM read routing for this query.
+
+        By default (unset), a query against a table with an LSM write spec is
+        routed through the LSM scanner so it also returns data written via the
+        ``merge_insert`` LSM path that has not yet been compacted into the base
+        table (active/frozen memtables + flushed generations); a table without a
+        spec reads the base table.
+
+        Parameters
+        ----------
+        enable : bool
+            ``True`` forces the LSM scanner and errors if the table has no LSM
+            write spec. ``False`` bypasses the MemWAL and reads the base table
+            only, even when a spec is present.
+
+        Returns
+        -------
+        LanceQueryBuilder
+            The LanceQueryBuilder object.
+        """
+        self._use_lsm = enable
+        return self
+
    def explain_plan(self, verbose: Optional[bool] = False) -> str:
        """Return the execution plan for this query.

@@ -1618,8 +1650,8 @@ class LanceVectorQueryBuilder(LanceQueryBuilder):
        Higher values will yield better recall (more likely to find vectors if
        they exist) at the expense of latency.

-        See discussion in [Querying an ANN Index][querying-an-ann-index] for
-        tuning advice.
+        See discussion in [Querying an ANN Index](https://lancedb.com/docs/indexing/)
+        for tuning advice.

        This method sets both the minimum and maximum number of probes to the same
        value. See `minimum_nprobes` and `maximum_nprobes` for more fine-grained
@@ -1719,8 +1751,8 @@ class LanceVectorQueryBuilder(LanceQueryBuilder):
        As an example, a refine factor of 2 will sample 2x as many vectors as
        requested, re-ranks them, and returns the top half most relevant results.

-        See discussion in [Querying an ANN Index][querying-an-ann-index] for
-        tuning advice.
+        See discussion in [Querying an ANN Index](https://lancedb.com/docs/indexing/)
+        for tuning advice.

        Parameters
        ----------
@@ -1788,6 +1820,7 @@ class LanceVectorQueryBuilder(LanceQueryBuilder):
            with_row_address=self._with_row_address,
            fragments=self._fragments,
            fragment_ids=self._fragment_ids,
+            use_lsm=self._use_lsm,
            offset=self._offset,
            fast_search=self._fast_search,
            ef=self._ef,
@@ -2012,6 +2045,7 @@ class LanceFtsQueryBuilder(LanceQueryBuilder):
            with_row_address=self._with_row_address,
            fragments=self._fragments,
            fragment_ids=self._fragment_ids,
+            use_lsm=self._use_lsm,
            full_text_query=FullTextSearchQuery(
                query=self._query_with_phrase_semantics(), columns=self._fts_columns
            ),
@@ -2078,6 +2112,7 @@ class LanceEmptyQueryBuilder(LanceQueryBuilder):
            with_row_address=self._with_row_address,
            fragments=self._fragments,
            fragment_ids=self._fragment_ids,
+            use_lsm=self._use_lsm,
            offset=self._offset,
            order_by=self._order_by,
        )
@@ -2655,11 +2690,14 @@ class LanceHybridQueryBuilder(LanceQueryBuilder):
        if self._with_row_id:
            self._vector_query.with_row_id(True)
            self._fts_query.with_row_id(True)
+        if self._use_lsm is not None:
+            self._vector_query.use_lsm(self._use_lsm)
+            self._fts_query.use_lsm(self._use_lsm)
        if self._phrase_query:
            self._fts_query.phrase_query(True)
        if self._distance_type:
            self._vector_query.metric(self._distance_type)
-        if self._minimum_nprobes:
+        if self._minimum_nprobes is not None:
            self._vector_query.minimum_nprobes(self._minimum_nprobes)
        if self._maximum_nprobes is not None:
            self._vector_query.maximum_nprobes(self._maximum_nprobes)
@@ -2732,7 +2770,7 @@ class AsyncQueryBase(object):
        )

    async def _maybe_add_blob_row_id(self) -> None:
-        if self._table is None or not supports_blob_auto_row_id(self._table):
+        if self._table is None:
            self._blob_auto_row_id = False
            self._blob_paths = ()
            return
@@ -2740,7 +2778,6 @@ class AsyncQueryBase(object):
        req = self._inner.to_query_request()
        schema = await self._table.schema()
        self._blob_auto_row_id = blob_auto_row_id_for_scan(
-            self._table,
            schema,
            req.select,
            with_row_id=self._with_row_id,
@@ -2992,7 +3029,6 @@ class AsyncQueryBase(object):

        schema = await self._table.schema()
        blob_auto_row_id = blob_auto_row_id_for_scan(
-            self._table,
            schema,
            query.columns,
            with_row_id=self._with_row_id,
@@ -3002,7 +3038,7 @@ class AsyncQueryBase(object):
            if blob_mode == "bytes"
            else {}
        )
-        dataset = await self._table._to_lance()
+        dataset = await self._table.to_lance()
        scanner = dataset.scanner(
            **_scanner_kwargs_for_query(
                query,
@@ -3231,6 +3267,27 @@ class AsyncStandardQuery(AsyncQueryBase):
        self._inner.fast_search()
        return self

+    def use_lsm(self, enable: bool) -> Self:
+        """
+        Control MemWAL LSM read routing for this query.
+
+        By default (unset), a query against a table with an LSM write spec (see
+        [AsyncTable.set_lsm_write_spec][lancedb.table.AsyncTable.set_lsm_write_spec])
+        is routed through the LSM scanner so it also returns data written via the
+        ``merge_insert`` 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 : bool
+            ``True`` forces the LSM scanner and errors if the table has no LSM
+            write spec. ``False`` bypasses the MemWAL and reads the base table
+            only, even when a spec is present.
+        """
+        self._inner.use_lsm(enable)
+        return self
+
    def postfilter(self) -> Self:
        """
        If this is called then filtering will happen after the search instead of
@@ -3319,8 +3376,9 @@ class AsyncQuery(AsyncStandardQuery):
        are various ANN search parameters that will let you fine tune your recall
        accuracy vs search latency.

-        Vector searches always have a [limit][].  If `limit` has not been called then
-        a default `limit` of 10 will be used.
+        Vector searches always have a
+        [limit][lancedb.query.AsyncVectorQuery.limit].  If `limit` has not been
+        called then a default `limit` of 10 will be used.

        Typically, a single vector is passed in as the query. However, you can also
        pass in multiple vectors. When multiple vectors are passed in, if the vector
@@ -3451,8 +3509,9 @@ class AsyncFTSQuery(AsyncStandardQuery):
        are various ANN search parameters that will let you fine tune your recall
        accuracy vs search latency.

-        Hybrid searches always have a [limit][].  If `limit` has not been called then
-        a default `limit` of 10 will be used.
+        Hybrid searches always have a
+        [limit][lancedb.query.AsyncHybridQuery.limit].  If `limit` has not been
+        called then a default `limit` of 10 will be used.

        Typically, a single vector is passed in as the query. However, you can also
        pass in multiple vectors.  This can be useful if you want to find the nearest
@@ -3815,10 +3874,9 @@ class AsyncHybridQuery(AsyncStandardQuery, AsyncVectorQueryBase):
        req = fts_query._inner.to_query_request()
        blob_auto_row_id = False
        blob_paths: tuple[str, ...] = ()
-        if self._table is not None and supports_blob_auto_row_id(self._table):
+        if self._table is not None:
            schema = await self._table.schema()
            blob_auto_row_id = blob_auto_row_id_for_scan(
-                self._table,
                schema,
                req.select,
                with_row_id=self._with_row_id,
@@ -3944,6 +4002,15 @@ class AsyncTakeQuery(AsyncQueryBase):
    def __init__(self, inner: LanceTakeQuery, table: Optional["AsyncTable"] = None):
        super().__init__(inner, table)

+    def use_lsm(self, enable: bool) -> "AsyncTakeQuery":
+        """Control MemWAL LSM 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.
+        """
+        self._inner.use_lsm(enable)
+        return self
+
    async def _plain_scan_to_pandas(
        self,
        blob_mode: BlobMode,
@@ -4002,6 +4069,16 @@ class BaseQueryBuilder(object):
        self._inner.with_row_id()
        return self

+    def use_lsm(self, enable: bool) -> Self:
+        """
+        Control MemWAL LSM read routing for this query.
+
+        ``False`` bypasses the MemWAL and reads the base table only, the escape
+        hatch for shapes the LSM scanner cannot honor (e.g. take-by-row-id).
+        """
+        self._inner.use_lsm(enable)
+        return self
+
    def with_row_address(self, with_row_address: bool = True) -> Self:
        """
        Include the _rowaddr column in scanner-backed plain query results.
@@ -11,6 +11,9 @@ from lancedb import __version__
 from .header import HeaderProvider
 from .oauth import OAuthConfig, OAuthFlowType

+# The API reference renders this module with a single mkdocstrings directive,
+# which only picks up names listed here. New public names must be added to this
+# list, or they will silently go undocumented.
 __all__ = [
    "TimeoutConfig",
    "RetryConfig",
@@ -7,7 +7,7 @@ import json
 import logging
 from concurrent.futures import ThreadPoolExecutor
 import sys
-from typing import Any, Dict, Iterable, List, Optional, Union
+from typing import TYPE_CHECKING, Any, Dict, Iterable, List, Optional, Union
 from urllib.parse import urlparse
 import warnings

@@ -23,6 +23,10 @@ import pyarrow as pa

 from ..common import DATA
 from ..db import DBConnection, LOOP
+from ..job import Job
+
+if TYPE_CHECKING:
+    from .._lancedb import JobDescription, JobInfo
 from ..embeddings import EmbeddingFunctionConfig
 from lance_namespace import (
    LanceNamespace,
@@ -415,6 +419,11 @@ class RemoteDBConnection(DBConnection):

        if namespace_path is None:
            namespace_path = []
+        if storage_options is not None:
+            logging.info(
+                "storage_options is ignored in LanceDb Cloud"
+                " (storage is managed; set storage_options on connect() instead)"
+            )
        if index_cache_size is not None:
            logging.info(
                "index_cache_size is ignored in LanceDb Cloud"
@@ -684,6 +693,47 @@ class RemoteDBConnection(DBConnection):
            )
        )

+    @override
+    def job(self, job_id: str) -> Job:
+        """A [Job][lancedb.job.Job] handle for a server-side job by id.
+
+        The handle is constructed without a server round trip; an unknown id
+        surfaces when the handle is used. Dropping the handle has no effect
+        on the job itself.
+        """
+        return Job(self._conn.job(job_id))
+
+    @override
+    def list_jobs(self) -> List["JobInfo"]:
+        """List server-side jobs across the database's tables."""
+        return LOOP.run(self._conn.list_jobs())
+
+    @override
+    def get_job(self, job_id: str) -> Optional["JobDescription"]:
+        """Describe a single server-side job by id.
+
+        Returns None when the server has no such job.
+        """
+        return LOOP.run(self._conn.get_job(job_id))
+
+    @override
+    def cancel_job(self, job_id: str) -> bool:
+        """Request cancellation of a server-side job by id.
+
+        Returns True if the server accepted the cancellation, False if no
+        such job exists. Cancelling an already-terminal job is a no-op
+        success.
+        """
+        return LOOP.run(self._conn.cancel_job(job_id))
+
+    @override
+    def job_history(self, job_id: Optional[str] = None) -> List[pa.RecordBatch]:
+        """The lifecycle event history of a server-side job, as Arrow batches.
+
+        Lists history across all jobs when `job_id` is None.
+        """
+        return LOOP.run(self._conn.job_history(job_id))
+
    @override
    def namespace_client(self) -> LanceNamespace:
        """Get the equivalent namespace client for this connection.
@@ -53,9 +53,9 @@ class RetryError(LanceDBClientError):
    """An error that occurs when the client has exceeded the maximum number of retries.

    The retry strategy can be adjusted by setting the
-    [retry_config](lancedb.remote.ClientConfig.retry_config) in the client
+    [retry_config][lancedb.remote.ClientConfig.retry_config] in the client
    configuration. This is passed in the `client_config` argument of
-    [connect](lancedb.connect) and [connect_async](lancedb.connect_async).
+    [connect][lancedb.connect] and [connect_async][lancedb.connect_async].

    The __cause__ attribute of this exception will be the last exception that
    caused the retry to fail. It will be an
@@ -20,6 +20,7 @@ from typing import (
 import warnings

 from lancedb import __version__
+from lancedb._blob import BlobFile

 from lancedb._lancedb import (
    AddColumnsResult,
@@ -47,6 +48,7 @@ from lancedb.index import (
    IvfSq,
    LabelList,
 )
+from lancedb.job import Job
 from lancedb.remote.db import LOOP
 from lancedb.table import IndexConfigType, KNOWN_METRICS
 import pyarrow as pa
@@ -340,10 +342,12 @@ class RemoteTable(Table):
        lower_case: bool = True,
        stem: bool = True,
        remove_stop_words: bool = True,
+        custom_stop_words: Optional[List[str]] = None,
        ascii_folding: bool = True,
        ngram_min_length: int = 3,
        ngram_max_length: int = 3,
        prefix_only: bool = False,
+        block_size: int = 128,
        name: Optional[str] = None,
    ):
        """Create a full-text search index on a column.
@@ -360,10 +364,12 @@ class RemoteTable(Table):
            lower_case=lower_case,
            stem=stem,
            remove_stop_words=remove_stop_words,
+            custom_stop_words=custom_stop_words,
            ascii_folding=ascii_folding,
            ngram_min_length=ngram_min_length,
            ngram_max_length=ngram_max_length,
            prefix_only=prefix_only,
+            block_size=block_size,
        )
        LOOP.run(
            self._table.create_index(
@@ -536,6 +542,34 @@ class RemoteTable(Table):
            )
        )

+    def create_index_async(
+        self,
+        column: str,
+        *,
+        config: IndexConfigType,
+        replace: Optional[bool] = None,
+        wait_timeout: Optional[timedelta] = None,
+        name: Optional[str] = None,
+        train: bool = True,
+    ) -> Job:
+        """Create an index, returning a handle to the indexing job.
+
+        The job may already be complete when returned; callers must not assume
+        the index exists until :meth:`Job.wait` returns.
+        """
+        return Job(
+            LOOP.run(
+                self._table.create_index_async(
+                    column,
+                    replace=replace,
+                    config=config,
+                    wait_timeout=wait_timeout,
+                    name=name,
+                    train=train,
+                )
+            )
+        )
+
    def _is_legacy_create_index_call(
        self,
        first_arg: str,
@@ -576,8 +610,9 @@ class RemoteTable(Table):
        progress: Optional[Union[bool, Callable, Any]] = None,
        write_parallelism: Optional[int] = None,
    ) -> AddResult:
-        """Add more data to the [Table](Table). It has the same API signature as
-        the OSS version.
+        """Add more data to the [Table][lancedb.table.Table].
+
+        It has the same API signature as the OSS version.

        Parameters
        ----------
@@ -637,7 +672,8 @@ class RemoteTable(Table):
        fast_search: bool = False,
    ) -> LanceVectorQueryBuilder:
        """Create a search query to find the nearest neighbors
-        of the given query vector. We currently support [vector search][search]
+        of the given query vector. We currently support
+        [vector search](https://lancedb.com/docs/search/vector-search/)

        All query options are defined in
        [LanceVectorQueryBuilder][lancedb.query.LanceVectorQueryBuilder].
@@ -1033,17 +1069,22 @@ class RemoteTable(Table):
        )

    def blob_columns(self) -> list[str]:
+        return LOOP.run(self._table.blob_columns())
+
+    def fetch_blobs(
+        self, column: str, row_ids: Union[list[int], pa.Table]
+    ) -> pa.LargeBinaryArray:
+        return LOOP.run(self._table.fetch_blobs(column, row_ids))
+
+    def fetch_blob_ranges(self, column: str, requests) -> pa.LargeBinaryArray:
        raise NotImplementedError(
-            "blob_columns() is not yet supported on the LanceDB Cloud"
+            "fetch_blob_ranges() is not supported on LanceDB Cloud"
        )

-    def fetch_blobs(self, column: str, row_ids) -> pa.LargeBinaryArray:
-        raise NotImplementedError("fetch_blobs() is not supported on LanceDB Cloud")
-
-    def fetch_blob_files(self, column: str, row_ids):
-        raise NotImplementedError(
-            "fetch_blob_files() is not supported on LanceDB Cloud"
-        )
+    def fetch_blob_files(
+        self, column: str, row_ids: Union[list[int], pa.Table]
+    ) -> "list[Optional[BlobFile]]":
+        return LOOP.run(self._table.fetch_blob_files(column, row_ids))

    def head(self, n=5) -> pa.Table:
        """
@@ -14,6 +14,9 @@ from .answerdotai import AnswerdotaiRerankers
 from .voyageai import VoyageAIReranker
 from .watsonx import WatsonxReranker

+# The API reference renders this module with a single mkdocstrings directive,
+# which only picks up names listed here. New public names must be added to this
+# list, or they will silently go undocumented.
 __all__ = [
    "Reranker",
    "CrossEncoderReranker",
@@ -23,7 +23,7 @@ class AnswerdotaiRerankers(Reranker):
    column : str, default "text"
        The name of the column to use as input to the cross encoder model.
    return_score : str, default "relevance"
-        options are "relevance" or "all". Only "relevance" is supported for now.
+        options are "relevance" or "all".
    **kwargs
        Additional keyword arguments to pass to the model. For example, 'device'.
        See AnswerDotAI/rerankers for more information.
@@ -77,12 +77,13 @@ class AnswerdotaiRerankers(Reranker):
        vector_results: pa.Table,
        fts_results: pa.Table,
    ):
-        combined_results = self.merge_results(vector_results, fts_results)
+        if self.score == "all":
+            combined_results = self._merge_and_keep_scores(vector_results, fts_results)
+        else:
+            combined_results = self.merge_results(vector_results, fts_results)
        combined_results = self._rerank(combined_results, query)
        if self.score == "relevance":
            combined_results = self._keep_relevance_score(combined_results)
-        elif self.score == "all":
-            combined_results = self._merge_and_keep_scores(vector_results, fts_results)
        combined_results = combined_results.sort_by(
            [("_relevance_score", "descending")]
        )
@@ -16,7 +16,7 @@ class ColbertReranker(AnswerdotaiRerankers):
    column : str, default "text"
        The name of the column to use as input to the cross encoder model.
    return_score : str, default "relevance"
-        options are "relevance" or "all". Only "relevance" is supported for now.
+        options are "relevance" or "all".
    **kwargs
        Additional keyword arguments to pass to the model, for example, 'device'.
        See AnswerDotAI/rerankers for more information.
@@ -59,9 +59,10 @@ class StreamingDataset(IterableDataset):
    - **Stage 1 (I/O)**: one thread pool with ``num_splits * prefetch_batches``
      workers fetches raw ``RecordBatch`` objects from LanceDB in parallel
      across all splits and places them in a per-split raw-batch queue.
-    - **Stage 2 (transform)**: a second thread pool with ``os.cpu_count()``
-      workers picks up raw batches, applies the transform, and places the
-      results in a per-split cooked-row queue.
+    - **Stage 2 (transform)**: a second thread pool with
+      ``transform_parallelism`` workers picks up raw batches, applies the
+      transform, and places the results in a per-split cooked-row queue.  By
+      default, the number of workers is determined by ``os.cpu_count()``.

    The main thread round-robins over the cooked queues, yielding one row per
    split per cycle.
@@ -122,6 +123,10 @@ class StreamingDataset(IterableDataset):
        are yielded.  Receives one batch at a time and must return an iterable
        whose length equals the number of rows in the batch.  When ``None``
        (the default) rows are returned as plain Python dicts.
+    transform_parallelism:
+        Maximum number of transforms to run concurrently.  Must be greater
+        than zero.  When ``None`` (the default), uses ``os.cpu_count()`` or 1
+        when the CPU count is unavailable.
    worker_info_override:
        If set, used in place of ``torch.utils.data.get_worker_info()`` to
        determine the DataLoader worker assignment.  Intended for unit tests
@@ -146,6 +151,7 @@ class StreamingDataset(IterableDataset):
        shuffle_clump_size: Optional[int] = None,
        filter: Optional[str] = None,
        transform: Optional[Callable] = None,
+        transform_parallelism: Optional[int] = None,
        connection_factory: Optional[Callable[[str], Any]] = None,
        worker_info_override=None,
    ):
@@ -159,6 +165,8 @@ class StreamingDataset(IterableDataset):
                f"num_splits ({num_splits}) must be divisible by "
                f"world_size ({world_size})"
            )
+        if transform_parallelism is not None and transform_parallelism <= 0:
+            raise ValueError("transform_parallelism must be greater than 0")

        self._table = table
        self._num_splits = num_splits
@@ -173,6 +181,7 @@ class StreamingDataset(IterableDataset):
        self._shuffle_clump_size = shuffle_clump_size
        self._filter = filter
        self._transform = transform
+        self._transform_parallelism = transform_parallelism
        self._connection_factory = connection_factory
        self._worker_info_override = worker_info_override

@@ -284,7 +293,11 @@ class StreamingDataset(IterableDataset):

        batch_size = self._read_batch_size
        max_prefetch = self._prefetch_batches
-        cpu_workers = os.cpu_count() or 1
+        transform_workers = (
+            self._transform_parallelism
+            if self._transform_parallelism is not None
+            else (os.cpu_count() or 1)
+        )
        final_transform = (
            self._transform if self._transform is not None else Transforms.arrow2python
        )
@@ -296,8 +309,8 @@ class StreamingDataset(IterableDataset):
        tx_pending = [deque() for _ in range(n)]  # Future[list[Any]]
        cooked = [deque() for _ in range(n)]  # rows ready to yield

-        # Limit simultaneous transforms to cpu_workers across all splits.
-        tx_semaphore = threading.Semaphore(cpu_workers)
+        # Limit simultaneous transforms to transform_workers across all splits.
+        tx_semaphore = threading.Semaphore(transform_workers)

        # ── Stage 1 helpers ───────────────────────────────────────────────────

@@ -369,7 +382,7 @@ class StreamingDataset(IterableDataset):
                    _advance(i)
                elif raw_batches[i]:
                    # Acquire a transform slot (may block briefly if all
-                    # cpu_workers are busy with other splits).
+                    # transform_workers are busy with other splits).
                    tx_semaphore.acquire()
                    batch = raw_batches[i].popleft()
                    tx_pending[i].append(tx_pool.submit(_tx_call_guarded, batch))
@@ -383,7 +396,7 @@ class StreamingDataset(IterableDataset):
        # ── Main loop ─────────────────────────────────────────────────────────

        with ThreadPoolExecutor(max_workers=n * max_prefetch) as io_pool:
-            with ThreadPoolExecutor(max_workers=cpu_workers) as tx_pool:
+            with ThreadPoolExecutor(max_workers=transform_workers) as tx_pool:
                self._raw_batches_ref = raw_batches
                self._cooked_ref = cooked
                self._fetch_head_ref = fetch_head
@@ -20,6 +20,7 @@ from typing import (
    List,
    Literal,
    Optional,
+    Sequence,
    Tuple,
    Union,
    overload,
@@ -39,6 +40,7 @@ from ._blob import (
 from .types import BlobMode
 from lancedb.arrow import peek_reader
 from lancedb.background_loop import LOOP, embedding_executor
+from lancedb.job import AsyncJob, Job
 from .dependencies import (
    _check_for_hugging_face,
    _check_for_lance,
@@ -976,6 +978,24 @@ class Table(ABC):
        """
        raise NotImplementedError

+    def create_index_async(
+        self,
+        column: str,
+        *,
+        config: IndexConfigType,
+        replace: Optional[bool] = None,
+        wait_timeout: Optional[timedelta] = None,
+        name: Optional[str] = None,
+        train: bool = True,
+    ) -> Job:
+        """Create an index, returning a handle to the indexing job.
+
+        Takes the same arguments as :meth:`create_index`. The job may already
+        be complete when returned; callers must not assume the index exists
+        until :meth:`Job.wait` returns.
+        """
+        raise NotImplementedError
+
    def drop_index(self, name: str) -> None:
        """
        Drop an index from the table.
@@ -1102,10 +1122,12 @@ class Table(ABC):
        lower_case: bool = True,
        stem: bool = True,
        remove_stop_words: bool = True,
+        custom_stop_words: Optional[List[str]] = None,
        ascii_folding: bool = True,
        ngram_min_length: int = 3,
        ngram_max_length: int = 3,
        prefix_only: bool = False,
+        block_size: int = 128,
        wait_timeout: Optional[timedelta] = None,
        name: Optional[str] = None,
    ):
@@ -1168,6 +1190,9 @@ class Table(ABC):
        remove_stop_words : bool, default True
            Whether to remove stop words. Stop words are common words that are often
            removed from text before indexing. For example, in English "the" and "and".
+        custom_stop_words : list of str, optional
+            Custom words that replace the built-in language stop words. ``None``
+            uses the built-in list; an empty list explicitly uses no stop words.
        ascii_folding : bool, default True
            Whether to fold ASCII characters. This converts accented characters to
            their ASCII equivalent. For example, "café" would be converted to "cafe".
@@ -1177,6 +1202,10 @@ class Table(ABC):
            The maximum length of an n-gram.
        prefix_only: bool, default False
            Whether to only index the prefix of the token for ngram tokenizer.
+        block_size: int, default 128
+            The number of documents per compressed posting block. Must be 128
+            or 256. A value of 256 uses the experimental FTS V3 format and
+            may introduce breaking changes.
        wait_timeout: timedelta, optional
            The timeout to wait if indexing is asynchronous.
        name: str, optional
@@ -1201,7 +1230,7 @@ class Table(ABC):
        progress: Optional[Union[bool, Callable, Any]] = None,
        write_parallelism: Optional[int] = None,
    ) -> AddResult:
-        """Add more data to the [Table](Table).
+        """Add more data to the [Table][lancedb.table.Table].

        Parameters
        ----------
@@ -1333,8 +1362,8 @@ class Table(ABC):
        fts_columns: Optional[Union[str, List[str]]] = None,
    ) -> LanceQueryBuilder:
        """Create a search query to find the nearest neighbors
-        of the given query vector. We currently support [vector search][search]
-        and [full-text search][experimental-full-text-search].
+        of the given query vector. We currently support [vector search](https://lancedb.com/docs/search/vector-search/)
+        and [full-text search](https://lancedb.com/docs/search/full-text-search/).

        All query options are defined in
        [LanceQueryBuilder][lancedb.query.LanceQueryBuilder].
@@ -1533,10 +1562,30 @@ class Table(ABC):
    ) -> pa.LargeBinaryArray:
        """Materialize full blob bytes for ``column`` at the given rows.

+        The result has the same length and order as ``row_ids``. Null blobs
+        produce null slots; valid empty blobs produce ``b""``.
+
        Convenience for small payloads. For large values use
        :meth:`fetch_blob_files`.
        """

+    @abstractmethod
+    def fetch_blob_ranges(
+        self,
+        column: str,
+        requests: Sequence[Tuple[int, int, int]],
+    ) -> pa.LargeBinaryArray:
+        """Materialize row-specific byte ranges from a blob v2 column.
+
+        Each request is a ``(row_id, offset, length)`` tuple. Requests may be
+        repeated or reordered, including multiple ranges for the same blob.
+        The result has the same length and order as ``requests``; null blobs
+        produce null slots and empty ranges on non-null blobs produce ``b""``.
+
+        Row IDs can be obtained from a query with ``with_row_id(True)``. This
+        API is currently supported only by local tables.
+        """
+
    @abstractmethod
    def fetch_blob_files(
        self, column: str, row_ids: Union[list[int], pa.Table]
@@ -1544,8 +1593,10 @@ class Table(ABC):
        """Open lazy, seekable :class:`~lancedb._blob.BlobFile` handles.

        Prefer this over :meth:`fetch_blobs` for large payloads. ``row_ids`` is
-        a ``list[int]`` or query ``pyarrow.Table`` with ``_rowid`` (or stashed
-        row-id metadata). Null rows are ``None``. Local tables only.
+        a ``list[int]`` or a query ``pyarrow.Table`` carrying row identity via
+        ``_rowid`` or a ``_lance_row_id`` field on the blob descriptor. Null
+        rows are ``None``. Remote tables require LanceDB Cloud server 0.5.0 or
+        newer.
        """

    @abstractmethod
@@ -1748,7 +1799,7 @@ class Table(ABC):
        for faster reads.

        Arguments are passed onto Lance's
-        [compact_files][lance.dataset.DatasetOptimizer.compact_files].
+        `lance.dataset.DatasetOptimizer.compact_files`.
        For most cases, the default should be fine.

        See Also
@@ -1802,6 +1853,8 @@ class Table(ABC):
        retrain: bool, default False
            This parameter is no longer used and is deprecated.

+        Notes
+        -----
        The frequency an application should call optimize is based on the frequency of
        data modifications.  If data is frequently added, deleted, or updated then
        optimize should be run frequently.  A good rule of thumb is to run optimize if
@@ -1956,15 +2009,14 @@ class Table(ABC):
        change permanent you can use the `[Self::restore]` method.

        Any operation that modifies the table will fail while the table is in a checked
-        out state.
+        out state. To return the table to a normal state use
+        `[Self::checkout_latest]`.

        Parameters
        ----------
        version: int | str,
            The version to check out. A version number (`int`) or a tag
            (`str`) can be provided.
-
-        To return the table to a normal state use `[Self::checkout_latest]`
        """

    @abstractmethod
@@ -2130,11 +2182,15 @@ class LanceTable(Table):
        return self.name

    @classmethod
-    def from_inner(cls, tbl: LanceDBTable):
-        from .db import LanceDBConnection
+    async def from_inner(cls, tbl: LanceDBTable):
+        from .db import AsyncConnection, LanceDBConnection

        async_tbl = AsyncTable(tbl)
-        conn = LanceDBConnection.from_inner(tbl.database())
+        inner_conn = tbl.database()
+        read_consistency_interval = await AsyncConnection(
+            inner_conn
+        ).get_read_consistency_interval()
+        conn = LanceDBConnection.from_inner(inner_conn, read_consistency_interval)
        return cls(
            conn,
            async_tbl.name,
@@ -2260,6 +2316,13 @@ class LanceTable(Table):
    ) -> pa.LargeBinaryArray:
        return LOOP.run(self._table.fetch_blobs(column, row_ids))

+    def fetch_blob_ranges(
+        self,
+        column: str,
+        requests: Sequence[Tuple[int, int, int]],
+    ) -> pa.LargeBinaryArray:
+        return LOOP.run(self._table.fetch_blob_ranges(column, list(requests)))
+
    def fetch_blob_files(
        self, column: str, row_ids: Union[list[int], pa.Table]
    ) -> "list[Optional[BlobFile]]":
@@ -2431,13 +2494,7 @@ class LanceTable(Table):
        return LOOP.run(self._table.count_rows(filter))

    def __repr__(self) -> str:
-        val = f"{self.__class__.__name__}(name={self.name!r}"
-        if self._conn.read_consistency_interval is not None:
-            val += ", read_consistency_interval={!r}".format(
-                self._conn.read_consistency_interval
-            )
-        val += f", _conn={self._conn!r})"
-        return val
+        return f"{self.__class__.__name__}(name={self.name!r}, _conn={self._conn!r})"

    def __str__(self) -> str:
        return self.__repr__()
@@ -2746,6 +2803,34 @@ class LanceTable(Table):
            )
        )

+    def create_index_async(
+        self,
+        column: str,
+        *,
+        config: IndexConfigType,
+        replace: Optional[bool] = None,
+        wait_timeout: Optional[timedelta] = None,
+        name: Optional[str] = None,
+        train: bool = True,
+    ) -> Job:
+        """Create an index, returning a handle to the indexing job.
+
+        The job may already be complete when returned; callers must not assume
+        the index exists until :meth:`Job.wait` returns.
+        """
+        return Job(
+            LOOP.run(
+                self._table.create_index_async(
+                    column,
+                    replace=replace,
+                    config=config,
+                    wait_timeout=wait_timeout,
+                    name=name,
+                    train=train,
+                )
+            )
+        )
+
    def _is_legacy_create_index_call(
        self,
        first_arg: str,
@@ -3022,10 +3107,12 @@ class LanceTable(Table):
        lower_case: bool = True,
        stem: bool = True,
        remove_stop_words: bool = True,
+        custom_stop_words: Optional[List[str]] = None,
        ascii_folding: bool = True,
        ngram_min_length: int = 3,
        ngram_max_length: int = 3,
        prefix_only: bool = False,
+        block_size: int = 128,
        name: Optional[str] = None,
    ):
        """Create a full-text search index on a column.
@@ -3067,6 +3154,7 @@ class LanceTable(Table):
                "lower_case": lower_case,
                "stem": stem,
                "remove_stop_words": remove_stop_words,
+                "custom_stop_words": custom_stop_words,
                "ascii_folding": ascii_folding,
                "ngram_min_length": ngram_min_length,
                "ngram_max_length": ngram_max_length,
@@ -3074,10 +3162,9 @@ class LanceTable(Table):
            }
        else:
            tokenizer_configs = self.infer_tokenizer_configs(tokenizer_name)
+            tokenizer_configs["custom_stop_words"] = custom_stop_words

-        config = FTS(
-            **tokenizer_configs,
-        )
+        config = FTS(block_size=block_size, **tokenizer_configs)

        try:
            LOOP.run(
@@ -3348,8 +3435,8 @@ class LanceTable(Table):
        fts_columns: Optional[Union[str, List[str]]] = None,
    ) -> LanceQueryBuilder:
        """Create a search query to find the nearest neighbors
-        of the given query vector. We currently support [vector search][search]
-        and [full-text search][search].
+        of the given query vector. We currently support [vector search](https://lancedb.com/docs/search/vector-search/)
+        and [full-text search](https://lancedb.com/docs/search/full-text-search/).

        Examples
        --------
@@ -3379,8 +3466,9 @@ class LanceTable(Table):
            - *default None*.
            Acceptable types are: list, np.ndarray, PIL.Image.Image

-            - If None then the select/[where][sql]/limit clauses are applied
-            to filter the table
+            - If None then the
+            select/[where][lancedb.query.LanceQueryBuilder.where]/limit clauses
+            are applied to filter the table
        vector_column_name: str, optional
            The name of the vector column to search.

@@ -3774,6 +3862,8 @@ class LanceTable(Table):
        retrain: bool, default False
            This parameter is no longer used and is deprecated.

+        Notes
+        -----
        The frequency an application should call optimize is based on the frequency of
        data modifications.  If data is frequently added, deleted, or updated then
        optimize should be run frequently.  A good rule of thumb is to run optimize if
@@ -4646,7 +4736,24 @@ class AsyncTable:
        """
        return AsyncQuery(self._inner.query(), self)

-    async def _to_lance(self, **kwargs) -> lance.LanceDataset:
+    async def to_lance(self, **kwargs) -> lance.LanceDataset:
+        """Return the Lance dataset backing this table.
+
+        Parameters
+        ----------
+        **kwargs
+            Forwarded to `lance.dataset`.
+
+        Returns
+        -------
+        lance.LanceDataset
+            The Lance dataset at this table handle's version and branch.
+
+        Examples
+        --------
+        >>> async def get_lance_dataset(table):
+        ...     return await table.to_lance()
+        """
        try:
            import lance
        except ImportError:
@@ -4696,7 +4803,7 @@ class AsyncTable:
            return (await self.to_arrow()).to_pandas(**kwargs)
        if blob_mode == "bytes" and blob_v2_column_paths(schema):
            return await self.query().to_pandas(blob_mode=blob_mode, **kwargs)
-        return (await self._to_lance()).to_pandas(blob_mode=blob_mode, **kwargs)
+        return (await self.to_lance()).to_pandas(blob_mode=blob_mode, **kwargs)

    async def to_arrow(self) -> pa.Table:
        """Return the table as a pyarrow Table.
@@ -4811,6 +4918,46 @@ class AsyncTable:
                )
            raise e

+    async def create_index_async(
+        self,
+        column: str,
+        *,
+        replace: Optional[bool] = None,
+        config: Optional[
+            Union[
+                IvfFlat,
+                IvfPq,
+                IvfRq,
+                HnswPq,
+                HnswSq,
+                HnswFlat,
+                BTree,
+                Bitmap,
+                LabelList,
+                Fm,
+                FTS,
+            ]
+        ] = None,
+        wait_timeout: Optional[timedelta] = None,
+        name: Optional[str] = None,
+        train: bool = True,
+    ) -> AsyncJob:
+        """Create an index, returning a handle to the indexing job.
+
+        Takes the same arguments as :meth:`create_index`. The job may already
+        be complete when returned; callers must not assume the index exists
+        until :meth:`AsyncJob.wait` resolves.
+        """
+        job = await self._inner.create_index_async(
+            column,
+            index=config,
+            replace=replace,
+            wait_timeout=wait_timeout,
+            name=name,
+            train=train,
+        )
+        return AsyncJob(job)
+
    async def drop_index(self, name: str) -> None:
        """
        Drop an index from the table.
@@ -4954,7 +5101,7 @@ class AsyncTable:
        progress: Optional[Union[bool, Callable, Any]] = None,
        write_parallelism: Optional[int] = None,
    ) -> AddResult:
-        """Add more data to the [Table](Table).
+        """Add more data to the [AsyncTable][lancedb.table.AsyncTable].

        Parameters
        ----------
@@ -5156,8 +5303,8 @@ class AsyncTable:
        fts_columns: Optional[Union[str, List[str]]] = None,
    ) -> Union[AsyncHybridQuery, AsyncFTSQuery, AsyncVectorQuery]:
        """Create a search query to find the nearest neighbors
-        of the given query vector. We currently support [vector search][search]
-        and [full-text search][experimental-full-text-search].
+        of the given query vector. We currently support [vector search](https://lancedb.com/docs/search/vector-search/)
+        and [full-text search](https://lancedb.com/docs/search/full-text-search/).

        All query options are defined in [AsyncQuery][lancedb.query.AsyncQuery].

@@ -5359,6 +5506,8 @@ class AsyncTable:
            async_query = async_query.where(query.filter)
        if query.fast_search:
            async_query = async_query.fast_search()
+        if query.use_lsm is not None:
+            async_query = async_query.use_lsm(query.use_lsm)
        if query.with_row_id:
            async_query = async_query.with_row_id()
        if query.order_by:
@@ -5479,7 +5628,7 @@ class AsyncTable:
                when_not_matched_by_source_condition_expr=merge._when_not_matched_by_source_condition_expr,
                timeout=merge._timeout,
                use_index=merge._use_index,
-                use_lsm_write=merge._use_lsm_write,
+                use_lsm=merge._use_lsm,
                validate_single_shard=merge._validate_single_shard,
            ),
        )
@@ -5716,15 +5865,14 @@ class AsyncTable:
        change permanent you can use the `[Self::restore]` method.

        Any operation that modifies the table will fail while the table is in a checked
-        out state.
+        out state. To return the table to a normal state use
+        `[Self::checkout_latest]`.

        Parameters
        ----------
        version: int | str,
            The version to check out. A version number (`int`) or a tag
            (`str`) can be provided.
-
-        To return the table to a normal state use `[Self::checkout_latest]`
        """
        try:
            await self._inner.checkout(version)
@@ -5823,6 +5971,13 @@ class AsyncTable:
            column, _normalize_blob_row_ids(row_ids, column)
        )

+    async def fetch_blob_ranges(
+        self,
+        column: str,
+        requests: Sequence[Tuple[int, int, int]],
+    ) -> pa.LargeBinaryArray:
+        return await self._inner.fetch_blob_ranges(column, list(requests))
+
    async def fetch_blob_files(
        self, column: str, row_ids: Union[list[int], pa.Table]
    ) -> "list[Optional[BlobFile]]":
@@ -5901,6 +6056,8 @@ class AsyncTable:
        retrain: bool, default False
            This parameter is no longer used and is deprecated.

+        Notes
+        -----
        The frequency an application should call optimize is based on the frequency of
        data modifications.  If data is frequently added, deleted, or updated then
        optimize should be run frequently.  A good rule of thumb is to run optimize if
@@ -6281,6 +6438,8 @@ class Branches:
        dry_run: bool, default False
            When True, only preview. When False, attempt the merge.

+        Notes
+        -----
        A rejected merge returns ``status="rejected"`` instead of raising.
        """
        return LOOP.run(self._table.branches.merge(from_branch, dry_run))
@@ -184,18 +184,75 @@ def test_fetch_blobs_accepts_query_result():
    assert {blobs[i].as_py() for i in range(len(blobs))} == {b"gamma"}


-def test_fetch_blobs_null_alignment():
+def test_fetch_blobs_preserves_null_and_empty_values():
    table = _blob_table(
        "nulls",
-        [{"id": 1, "image": b"present"}, {"id": 2, "image": None}],
+        [
+            {"id": 1, "image": b"present"},
+            {"id": 2, "image": None},
+            {"id": 3, "image": b""},
+        ],
    )
    by_id = _row_ids_by_id(table)
-    request = [by_id[1], by_id[2], by_id[1]]
+    request = [by_id[1], by_id[2], by_id[3], by_id[1]]
    blobs = table.fetch_blobs("image", request)
    assert len(blobs) == len(request)
    assert blobs[0].as_py() == b"present"
    assert blobs[1].as_py() is None
-    assert blobs[2].as_py() == b"present"
+    assert blobs[2].as_py() == b""
+    assert blobs[3].as_py() == b"present"
+
+
+def test_fetch_blob_ranges_aligns_repeated_ranges_and_nulls():
+    table = _blob_table(
+        "range_alignment",
+        [{"id": 1, "image": b"abcdefghij"}, {"id": 2, "image": None}],
+    )
+    by_id = _row_ids_by_id(table)
+    requests = [
+        (by_id[1], 2, 3),
+        (by_id[2], 0, 0),
+        (by_id[1], 0, 2),
+        (by_id[1], 2, 3),
+        (by_id[1], 10, 0),
+    ]
+
+    ranges = table.fetch_blob_ranges("image", requests)
+
+    assert ranges.to_pylist() == [b"cde", None, b"ab", b"cde", b""]
+
+
+def test_fetch_blob_ranges_validates_requests():
+    table = _blob_table("range_validation", [{"id": 1, "image": b"abc"}])
+    row_id = _row_ids_by_id(table)[1]
+
+    with pytest.raises(ValueError, match="exceeds blob size"):
+        table.fetch_blob_ranges("image", [(row_id, 2, 2)])
+
+    with pytest.raises(ValueError, match="offset \\+ length overflowed"):
+        table.fetch_blob_ranges("image", [(row_id, 2**64 - 1, 1)])
+
+    with pytest.raises(ValueError, match="row IDs"):
+        table.fetch_blob_ranges("image", [(2**64 - 1, 0, 1)])
+
+
+def test_fetch_blob_ranges_empty_requests_returns_empty_array():
+    table = _blob_table("range_empty", [{"id": 1, "image": b"x"}])
+    assert table.fetch_blob_ranges("image", []).to_pylist() == []
+
+
+@pytest.mark.asyncio
+async def test_async_fetch_blob_ranges():
+    db = await lancedb.connect_async("memory:///")
+    schema = pa.schema([pa.field("id", pa.int64()), lancedb.blob("image")])
+    table = await db.create_table("range_async", schema=schema)
+    await table.add([{"id": 1, "image": b"abcdefghij"}])
+    hits = await table.query().with_row_id().to_arrow()
+    row_id = hits["_rowid"][0].as_py()
+
+    ranges = await table.fetch_blob_ranges("image", [(row_id, 1, 3), (row_id, 6, 2)])
+
+    assert ranges.to_pylist() == [b"bcd", b"gh"]


 def test_fetch_blobs_nested_path():
@@ -62,6 +62,38 @@ def test_basic(tmp_path):
    assert db.open_table("test").name == db["test"].name


+def test_sync_repr_does_not_use_background_loop(tmp_path, monkeypatch):
+    from lancedb.background_loop import LOOP
+
+    db = lancedb.connect(tmp_path)
+    table = db.create_table("test", data=[{"id": 1}])
+
+    def fail_run(*args, **kwargs):
+        raise AssertionError("repr should not use the Python background loop")
+
+    monkeypatch.setattr(LOOP, "run", fail_run)
+
+    assert repr(db) == f"LanceDBConnection(uri={str(tmp_path)!r})"
+    assert repr(table) == f"LanceTable(name='test', _conn={db!r})"
+
+
+def test_read_consistency_interval_does_not_use_background_loop(tmp_path, monkeypatch):
+    from lancedb.background_loop import LOOP
+    from lancedb.db import LanceDBConnection
+
+    consistency_interval = timedelta(seconds=5)
+    db = lancedb.connect(tmp_path, read_consistency_interval=consistency_interval)
+    db_from_inner = LanceDBConnection.from_inner(db._inner, consistency_interval)
+
+    def fail_run(*args, **kwargs):
+        raise AssertionError("properties should not use the Python background loop")
+
+    monkeypatch.setattr(LOOP, "run", fail_run)
+
+    assert db.read_consistency_interval == consistency_interval
+    assert db_from_inner.read_consistency_interval == consistency_interval
+
+
 def test_ingest_pd(tmp_path):
    db = lancedb.connect(tmp_path)

@@ -1333,6 +1333,42 @@ def test_transform_none_yields_dicts(lance_table):
    assert all("id" in item for item in items)


+@pytest.mark.parametrize(
+    ("configured", "detected", "expected"),
+    [(2, 8, 2), (None, 3, 3), (None, None, 1)],
+)
+def test_transform_parallelism_configures_executor(
+    lance_table, monkeypatch, configured, detected, expected
+):
+    """Explicit transform parallelism overrides the detected CPU count."""
+    real_executor = streaming.ThreadPoolExecutor
+    monkeypatch.setattr(streaming.os, "cpu_count", lambda: detected)
+
+    with patch.object(streaming, "ThreadPoolExecutor", wraps=real_executor) as executor:
+        list(
+            StreamingDataset(
+                lance_table,
+                num_splits=NUM_SPLITS,
+                shuffle_seed=SHUFFLE_SEED,
+                transform_parallelism=configured,
+            )
+        )
+
+    assert executor.call_args_list[-1].kwargs["max_workers"] == expected
+
+
+@pytest.mark.parametrize("transform_parallelism", [0, -1])
+def test_transform_parallelism_must_be_positive(lance_table, transform_parallelism):
+    with pytest.raises(
+        ValueError, match="transform_parallelism must be greater than 0"
+    ):
+        StreamingDataset(
+            lance_table,
+            num_splits=NUM_SPLITS,
+            transform_parallelism=transform_parallelism,
+        )
+
+
 def test_filter_limits_rows(tmp_path):
    """A filter expression is applied to the permutation so only matching rows
    are yielded.  IDs 0..59 pass ``id < 60``; the other 60 are excluded."""
@@ -219,11 +219,48 @@ def test_create_inverted_index(table, with_position):
        table.create_fts_index(
            "text",
            with_position=with_position,
+            custom_stop_words=["puppy"],
            name="custom_fts_index",
        )
    indices = table.list_indices()
    fts_indices = [i for i in indices if i.index_type == "FTS"]
    assert any(i.name == "custom_fts_index" for i in fts_indices)
+    assert fts_indices[0].index_details["custom_stop_words"] == ["puppy"]
+
+
+@pytest.mark.parametrize("block_size", [128, 256])
+def test_create_inverted_index_block_size(table, block_size):
+    table.create_index("text", config=FTS(block_size=block_size))
+
+    index = next(index for index in table.list_indices() if index.index_type == "FTS")
+    assert index.index_details["block_size"] == block_size
+    assert index.index_version == (2 if block_size == 128 else 3)
+
+    results = table.search("puppy").limit(5).to_list()
+    assert len(results) == 5
+
+
+def test_create_inverted_index_rejects_invalid_block_size(table):
+    with pytest.raises(ValueError, match="128 or 256"):
+        table.create_index("text", config=FTS(block_size=129))
+
+
+def test_custom_stop_words_list(table):
+    table.create_index(
+        "text",
+        config=FTS(stem=False, custom_stop_words=["lance"]),
+    )
+
+    assert table.list_indices()[0].index_details["custom_stop_words"] == ["lance"]
+    tokens = table.tokenize("the lance data", column="text")
+    assert [token.text for token in tokens] == ["the", "data"]
+    empty_tokens = ldb.tokenize("the lance data", stem=False, custom_stop_words=[])
+    assert [token.text for token in empty_tokens] == ["the", "lance", "data"]
+    with pytest.raises(TypeError, match=r"custom_stop_words.*int"):
+        ldb.tokenize(
+            "the lance data",
+            custom_stop_words=["lance", 42],
+        )


 def test_search_fts(table):
@@ -123,6 +123,19 @@ async def test_async_hybrid_query_default_limit(table: AsyncTable):
    assert texts.count("a") == 1


+def test_hybrid_query_minimum_nprobes_zero_raises(sync_table: Table):
+    # minimum_nprobes(0) must raise the same validation error a plain vector
+    # query raises, not silently no-op because 0 is falsy.
+    with pytest.raises(ValueError, match="minimum_nprobes must be greater than 0"):
+        (
+            sync_table.search(query_type="hybrid")
+            .vector([0.0, 0.4])
+            .text("dog")
+            .minimum_nprobes(0)
+            .to_arrow()
+        )
+
+
 def test_hybrid_query_distance_range(sync_table: Table):
    reranker = RRFReranker(return_score="all")
    result = (
--- a/Show More
+++ b/Show More