fix(rust): create tables after namespace declare conflict

2026-08-30 01:48:19 +00:00 · 2026-04-19 10:12:59 -07:00
48 changed files with 793 additions and 611 deletions
@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.28.0-beta.9"
+current_version = "0.28.0-beta.8"
 parse = """(?x)
    (?P<major>0|[1-9]\\d*)\\.
    (?P<minor>0|[1-9]\\d*)\\.
@@ -1,18 +0,0 @@
 version: 2
 # Scope: the root Cargo workspace, which produces the Rust binaries we
 # ship to users (the Node.js and Python native extensions). The
 # `rust/lancedb` library crate shares the same lockfile; its consumers
 # pick their own dependency versions, but bumping transitive deps here
 # keeps the binaries we ship current.
 updates:
  - package-ecosystem: cargo
    directory: /
    schedule:
      interval: weekly
    open-pull-requests-limit: 10
    groups:
      rust-minor-patch:
        update-types:
          - minor
          - patch
@@ -8,9 +8,6 @@ concurrency:
  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
  cancel-in-progress: true
 permissions:
  contents: read
 jobs:
  labeler:
    permissions:
@@ -19,9 +19,6 @@ on:
    paths:
      - .github/workflows/java-publish.yml
 permissions:
  contents: read
 jobs:
  publish:
    name: Build and Publish
@@ -24,9 +24,6 @@ on:
      - java/**
      - .github/workflows/java.yml
 permissions:
  contents: read
 jobs:
  build-java:
    runs-on: ubuntu-24.04
@@ -10,10 +10,6 @@ on:
      - nodejs/**
      - java/**
      - .github/workflows/license-header-check.yml
 permissions:
  contents: read
 jobs:
  check-licenses:
    runs-on: ubuntu-latest
@@ -15,9 +15,6 @@ on:
      - .github/workflows/nodejs.yml
      - docker-compose.yml
 permissions:
  contents: read
 concurrency:
  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
  cancel-in-progress: true
@@ -14,16 +14,10 @@ on:
 env:
  PIP_EXTRA_INDEX_URL: "https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/"
 permissions:
  contents: read
 jobs:
  linux:
    name: Python ${{ matrix.config.platform }} manylinux${{ matrix.config.manylinux }}
    timeout-minutes: 60
    permissions:
      id-token: write
      contents: read
    strategy:
      matrix:
        config:
@@ -63,12 +57,10 @@ jobs:
      - uses: ./.github/workflows/upload_wheel
        if: startsWith(github.ref, 'refs/tags/python-v')
        with:
          pypi_token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
          fury_token: ${{ secrets.FURY_TOKEN }}
  mac:
    timeout-minutes: 90
    permissions:
      id-token: write
      contents: read
    runs-on: ${{ matrix.config.runner }}
    strategy:
      matrix:
@@ -93,12 +85,10 @@ jobs:
      - uses: ./.github/workflows/upload_wheel
        if: startsWith(github.ref, 'refs/tags/python-v')
        with:
          pypi_token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
          fury_token: ${{ secrets.FURY_TOKEN }}
  windows:
    timeout-minutes: 60
    permissions:
      id-token: write
      contents: read
    runs-on: windows-latest
    steps:
      - uses: actions/checkout@v4
@@ -117,6 +107,7 @@ jobs:
      - uses: ./.github/workflows/upload_wheel
        if: startsWith(github.ref, 'refs/tags/python-v')
        with:
          pypi_token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
          fury_token: ${{ secrets.FURY_TOKEN }}
  gh-release:
    if: startsWith(github.ref, 'refs/tags/python-v')
@@ -17,9 +17,6 @@ on:
      - .github/workflows/build_windows_wheel/**
      - .github/workflows/run_tests/**
 permissions:
  contents: read
 concurrency:
  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
  cancel-in-progress: true
@@ -111,6 +108,7 @@ jobs:
      - name: Install
        run: |
          pip install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests,dev,embeddings]
          pip install tantivy
          pip install mlx
      - name: Doctest
        run: pytest --doctest-modules python/lancedb
@@ -229,5 +227,6 @@ jobs:
          pip install "pydantic<2"
          pip install pyarrow==16
          pip install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests]
          pip install tantivy
      - name: Run tests
        run: pytest -m "not slow and not s3_test" -x -v --durations=30 python/tests
@@ -9,15 +9,9 @@ on:
      - Cargo.toml
      - Cargo.lock
      - rust-toolchain.toml
      - deny.toml
      - rust/**
      - nodejs/Cargo.toml
      - python/Cargo.toml
      - .github/workflows/rust.yml
 permissions:
  contents: read
 concurrency:
  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
  cancel-in-progress: true
@@ -59,17 +53,6 @@ jobs:
      - name: Run clippy (without remote feature)
        run: cargo clippy --profile ci --workspace --tests -- -D warnings
  deny:
    # Supply-chain checks: advisories, licenses, banned crates, and source
    # restrictions. Configuration lives in `deny.toml` at the workspace root.
    timeout-minutes: 10
    runs-on: ubuntu-24.04
    steps:
      - uses: actions/checkout@v4
      - uses: EmbarkStudios/cargo-deny-action@v2
        with:
          command: check advisories bans licenses sources
  build-no-lock:
    runs-on: ubuntu-24.04
    timeout-minutes: 30
@@ -3,9 +3,6 @@ name: Update package-lock.json
 on:
  workflow_dispatch:
 permissions:
  contents: read
 jobs:
  publish:
    runs-on: ubuntu-latest
@@ -3,9 +3,6 @@ name: Update NodeJs package-lock.json
 on:
  workflow_dispatch:
 permissions:
  contents: read
 jobs:
  publish:
    runs-on: ubuntu-latest
@@ -2,6 +2,9 @@ name: upload-wheel
 description: "Upload wheels to Pypi"
 inputs:
  pypi_token:
    required: true
    description: "release token for the repo"
  fury_token:
    required: true
    description: "release token for the fury repo"
@@ -9,6 +12,12 @@ inputs:
 runs:
  using: "composite"
  steps:
  - name: Install dependencies
    shell: bash
    run: |
      python -m pip install --upgrade pip
      pip install twine
      python3 -m pip install --upgrade pkginfo
  - name: Choose repo
    shell: bash
    id: choose_repo
@@ -18,17 +27,19 @@ runs:
      else
        echo "repo=pypi" >> $GITHUB_OUTPUT
      fi
-  - name: Publish to Fury
+  - name: Publish to PyPI
    if: steps.choose_repo.outputs.repo == 'fury'
    shell: bash
    env:
      FURY_TOKEN: ${{ inputs.fury_token }}
      PYPI_TOKEN: ${{ inputs.pypi_token }}
    run: |
-      WHEEL=$(ls target/wheels/lancedb-*.whl 2> /dev/null | head -n 1)
+      if [[ ${{ steps.choose_repo.outputs.repo }} == fury ]]; then
-      echo "Uploading $WHEEL to Fury"
+        WHEEL=$(ls target/wheels/lancedb-*.whl 2> /dev/null | head -n 1)
-      curl -f -F package=@$WHEEL https://$FURY_TOKEN@push.fury.io/lancedb/
+        echo "Uploading $WHEEL to Fury"
-  - name: Publish to PyPI
+        curl -f -F package=@$WHEEL https://$FURY_TOKEN@push.fury.io/lancedb/
-    if: steps.choose_repo.outputs.repo == 'pypi'
+      else
-    uses: pypa/gh-action-pypi-publish@release/v1
+        twine upload --repository ${{ steps.choose_repo.outputs.repo }} \
-    with:
+          --username __token__ \
-      packages-dir: target/wheels/
+          --password $PYPI_TOKEN \
          target/wheels/lancedb-*.whl
      fi
@@ -572,9 +572,9 @@ dependencies = [
 [[package]]
 name = "aws-lc-rs"
-version = "1.16.3"
+version = "1.16.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0ec6fb3fe69024a75fa7e1bfb48aa6cf59706a101658ea01bfd33b2b248a038f"
+checksum = "94bffc006df10ac2a68c83692d734a465f8ee6c5b384d8545a636f81d858f4bf"
 dependencies = [
 "aws-lc-sys",
 "untrusted 0.7.1",
@@ -583,9 +583,9 @@ dependencies = [
 [[package]]
 name = "aws-lc-sys"
-version = "0.40.0"
+version = "0.38.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f50037ee5e1e41e7b8f9d161680a725bd1626cb6f8c7e901f91f942850852fe7"
+checksum = "4321e568ed89bb5a7d291a7f37997c2c0df89809d7b6d12062c81ddb54aa782e"
 dependencies = [
 "cc",
 "cmake",
@@ -1373,7 +1373,7 @@ dependencies = [
 "memmap2 0.9.10",
 "num-traits",
 "num_cpus",
- "rand 0.9.4",
+ "rand 0.9.2",
 "rand_distr 0.5.1",
 "rayon",
 "safetensors",
@@ -1409,7 +1409,7 @@ dependencies = [
 "candle-nn",
 "fancy-regex",
 "num-traits",
- "rand 0.9.4",
+ "rand 0.9.2",
 "rayon",
 "serde",
 "serde_json",
@@ -1966,7 +1966,7 @@ dependencies = [
 "log",
 "object_store",
 "parking_lot",
- "rand 0.9.4",
+ "rand 0.9.2",
 "regex",
 "sqlparser 0.59.0",
 "tempfile",
@@ -2080,7 +2080,7 @@ dependencies = [
 "itertools 0.14.0",
 "log",
 "object_store",
- "rand 0.9.4",
+ "rand 0.9.2",
 "tokio",
 "url",
 ]
@@ -2176,7 +2176,7 @@ dependencies = [
 "log",
 "object_store",
 "parking_lot",
- "rand 0.9.4",
+ "rand 0.9.2",
 "tempfile",
 "url",
 ]
@@ -2240,7 +2240,7 @@ dependencies = [
 "log",
 "md-5",
 "num-traits",
- "rand 0.9.4",
+ "rand 0.9.2",
 "regex",
 "sha2",
 "unicode-segmentation",
@@ -2642,7 +2642,7 @@ dependencies = [
 "libc",
 "option-ext",
 "redox_users",
- "windows-sys 0.61.2",
+ "windows-sys 0.59.0",
 ]
 [[package]]
@@ -2830,7 +2830,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "39cab71617ae0d63f51a36d69f866391735b51691dbda63cf6f96d042b63efeb"
 dependencies = [
 "libc",
- "windows-sys 0.61.2",
+ "windows-sys 0.59.0",
 ]
 [[package]]
@@ -2965,7 +2965,7 @@ checksum = "719a903cc23e4a89e87962c2a80fdb45cdaad0983a89bd150bb57b4c8571a7d5"
 dependencies = [
 "half",
 "num-traits",
- "rand 0.9.4",
+ "rand 0.9.2",
 "rand_distr 0.5.1",
 ]
@@ -3010,11 +3010,11 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
 [[package]]
 name = "fsst"
-version = "6.0.0-beta.4"
+version = "6.0.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.4#226dafe0a00f995d9e3230c2d61cc06be51994d4"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.1#c7a7d3a0e944646e793d297d4a2e2cf7e4fb28a3"
 dependencies = [
 "arrow-array",
- "rand 0.9.4",
+ "rand 0.9.2",
 ]
 [[package]]
@@ -3387,7 +3387,7 @@ dependencies = [
 "cfg-if",
 "crunchy",
 "num-traits",
- "rand 0.9.4",
+ "rand 0.9.2",
 "rand_distr 0.5.1",
 "zerocopy",
 ]
@@ -3470,7 +3470,7 @@ dependencies = [
 "libc",
 "log",
 "num_cpus",
- "rand 0.9.4",
+ "rand 0.9.2",
 "reqwest",
 "serde",
 "serde_json",
@@ -3980,7 +3980,7 @@ dependencies = [
 "portable-atomic",
 "portable-atomic-util",
 "serde_core",
- "windows-sys 0.61.2",
+ "windows-sys 0.59.0",
 ]
 [[package]]
@@ -4043,7 +4043,7 @@ dependencies = [
 "nom 8.0.0",
 "num-traits",
 "ordered-float",
- "rand 0.9.4",
+ "rand 0.9.2",
 "ryu",
 "serde",
 "serde_json",
@@ -4066,8 +4066,8 @@ dependencies = [
 [[package]]
 name = "lance"
-version = "6.0.0-beta.4"
+version = "6.0.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.4#226dafe0a00f995d9e3230c2d61cc06be51994d4"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.1#c7a7d3a0e944646e793d297d4a2e2cf7e4fb28a3"
 dependencies = [
 "arrow",
 "arrow-arith",
@@ -4119,7 +4119,7 @@ dependencies = [
 "prost",
 "prost-build",
 "prost-types",
- "rand 0.9.4",
+ "rand 0.9.2",
 "roaring",
 "semver",
 "serde",
@@ -4135,8 +4135,8 @@ dependencies = [
 [[package]]
 name = "lance-arrow"
-version = "6.0.0-beta.4"
+version = "6.0.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.4#226dafe0a00f995d9e3230c2d61cc06be51994d4"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.1#c7a7d3a0e944646e793d297d4a2e2cf7e4fb28a3"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4152,13 +4152,13 @@ dependencies = [
 "half",
 "jsonb",
 "num-traits",
- "rand 0.9.4",
+ "rand 0.9.2",
 ]
 [[package]]
 name = "lance-bitpacking"
-version = "6.0.0-beta.4"
+version = "6.0.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.4#226dafe0a00f995d9e3230c2d61cc06be51994d4"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.1#c7a7d3a0e944646e793d297d4a2e2cf7e4fb28a3"
 dependencies = [
 "arrayref",
 "paste",
@@ -4167,8 +4167,8 @@ dependencies = [
 [[package]]
 name = "lance-core"
-version = "6.0.0-beta.4"
+version = "6.0.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.4#226dafe0a00f995d9e3230c2d61cc06be51994d4"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.1#c7a7d3a0e944646e793d297d4a2e2cf7e4fb28a3"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4191,7 +4191,7 @@ dependencies = [
 "object_store",
 "pin-project",
 "prost",
- "rand 0.9.4",
+ "rand 0.9.2",
 "roaring",
 "serde_json",
 "snafu 0.9.0",
@@ -4205,8 +4205,8 @@ dependencies = [
 [[package]]
 name = "lance-datafusion"
-version = "6.0.0-beta.4"
+version = "6.0.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.4#226dafe0a00f995d9e3230c2d61cc06be51994d4"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.1#c7a7d3a0e944646e793d297d4a2e2cf7e4fb28a3"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -4237,8 +4237,8 @@ dependencies = [
 [[package]]
 name = "lance-datagen"
-version = "6.0.0-beta.4"
+version = "6.0.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.4#226dafe0a00f995d9e3230c2d61cc06be51994d4"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.1#c7a7d3a0e944646e793d297d4a2e2cf7e4fb28a3"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -4248,7 +4248,7 @@ dependencies = [
 "futures",
 "half",
 "hex",
- "rand 0.9.4",
+ "rand 0.9.2",
 "rand_distr 0.5.1",
 "rand_xoshiro",
 "random_word 0.5.2",
@@ -4256,8 +4256,8 @@ dependencies = [
 [[package]]
 name = "lance-encoding"
-version = "6.0.0-beta.4"
+version = "6.0.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.4#226dafe0a00f995d9e3230c2d61cc06be51994d4"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.1#c7a7d3a0e944646e793d297d4a2e2cf7e4fb28a3"
 dependencies = [
 "arrow-arith",
 "arrow-array",
@@ -4283,7 +4283,7 @@ dependencies = [
 "prost",
 "prost-build",
 "prost-types",
- "rand 0.9.4",
+ "rand 0.9.2",
 "snafu 0.9.0",
 "strum",
 "tokio",
@@ -4294,8 +4294,8 @@ dependencies = [
 [[package]]
 name = "lance-file"
-version = "6.0.0-beta.4"
+version = "6.0.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.4#226dafe0a00f995d9e3230c2d61cc06be51994d4"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.1#c7a7d3a0e944646e793d297d4a2e2cf7e4fb28a3"
 dependencies = [
 "arrow-arith",
 "arrow-array",
@@ -4327,8 +4327,8 @@ dependencies = [
 [[package]]
 name = "lance-index"
-version = "6.0.0-beta.4"
+version = "6.0.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.4#226dafe0a00f995d9e3230c2d61cc06be51994d4"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.1#c7a7d3a0e944646e793d297d4a2e2cf7e4fb28a3"
 dependencies = [
 "arrow",
 "arrow-arith",
@@ -4374,7 +4374,7 @@ dependencies = [
 "prost",
 "prost-build",
 "prost-types",
- "rand 0.9.4",
+ "rand 0.9.2",
 "rand_distr 0.5.1",
 "rangemap",
 "rayon",
@@ -4392,8 +4392,8 @@ dependencies = [
 [[package]]
 name = "lance-io"
-version = "6.0.0-beta.4"
+version = "6.0.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.4#226dafe0a00f995d9e3230c2d61cc06be51994d4"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.1#c7a7d3a0e944646e793d297d4a2e2cf7e4fb28a3"
 dependencies = [
 "arrow",
 "arrow-arith",
@@ -4426,7 +4426,7 @@ dependencies = [
 "path_abs",
 "pin-project",
 "prost",
- "rand 0.9.4",
+ "rand 0.9.2",
 "serde",
 "snafu 0.9.0",
 "tempfile",
@@ -4437,8 +4437,8 @@ dependencies = [
 [[package]]
 name = "lance-linalg"
-version = "6.0.0-beta.4"
+version = "6.0.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.4#226dafe0a00f995d9e3230c2d61cc06be51994d4"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.1#c7a7d3a0e944646e793d297d4a2e2cf7e4fb28a3"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4449,13 +4449,13 @@ dependencies = [
 "lance-arrow",
 "lance-core",
 "num-traits",
- "rand 0.9.4",
+ "rand 0.9.2",
 ]
 [[package]]
 name = "lance-namespace"
-version = "6.0.0-beta.4"
+version = "6.0.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.4#226dafe0a00f995d9e3230c2d61cc06be51994d4"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.1#c7a7d3a0e944646e793d297d4a2e2cf7e4fb28a3"
 dependencies = [
 "arrow",
 "async-trait",
@@ -4468,8 +4468,8 @@ dependencies = [
 [[package]]
 name = "lance-namespace-impls"
-version = "6.0.0-beta.4"
+version = "6.0.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.4#226dafe0a00f995d9e3230c2d61cc06be51994d4"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.1#c7a7d3a0e944646e793d297d4a2e2cf7e4fb28a3"
 dependencies = [
 "arrow",
 "arrow-ipc",
@@ -4488,7 +4488,7 @@ dependencies = [
 "lance-table",
 "log",
 "object_store",
- "rand 0.9.4",
+ "rand 0.9.2",
 "reqwest",
 "serde",
 "serde_json",
@@ -4501,9 +4501,9 @@ dependencies = [
 [[package]]
 name = "lance-namespace-reqwest-client"
-version = "0.7.2"
+version = "0.6.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0f061dd6fe63e3ba4052702a9d40973ee4ac57f612f04222897a149576213832"
+checksum = "ee2e48de899e2931afb67fcddd0a08e439bf5d8b6ea2a2ed9cb8f4df669bd5cc"
 dependencies = [
 "reqwest",
 "serde",
@@ -4514,8 +4514,8 @@ dependencies = [
 [[package]]
 name = "lance-table"
-version = "6.0.0-beta.4"
+version = "6.0.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.4#226dafe0a00f995d9e3230c2d61cc06be51994d4"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.1#c7a7d3a0e944646e793d297d4a2e2cf7e4fb28a3"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -4539,7 +4539,7 @@ dependencies = [
 "prost",
 "prost-build",
 "prost-types",
- "rand 0.9.4",
+ "rand 0.9.2",
 "rangemap",
 "roaring",
 "semver",
@@ -4554,20 +4554,20 @@ dependencies = [
 [[package]]
 name = "lance-testing"
-version = "6.0.0-beta.4"
+version = "6.0.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.4#226dafe0a00f995d9e3230c2d61cc06be51994d4"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.1#c7a7d3a0e944646e793d297d4a2e2cf7e4fb28a3"
 dependencies = [
 "arrow-array",
 "arrow-schema",
 "lance-arrow",
 "num-traits",
- "rand 0.9.4",
+ "rand 0.9.2",
 ]
 [[package]]
 name = "lance-tokenizer"
-version = "6.0.0-beta.4"
+version = "6.0.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.4#226dafe0a00f995d9e3230c2d61cc06be51994d4"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.1#c7a7d3a0e944646e793d297d4a2e2cf7e4fb28a3"
 dependencies = [
 "rust-stemmers",
 "serde",
@@ -4576,7 +4576,7 @@ dependencies = [
 [[package]]
 name = "lancedb"
-version = "0.28.0-beta.9"
+version = "0.28.0-beta.8"
 dependencies = [
 "ahash",
 "anyhow",
@@ -4637,7 +4637,7 @@ dependencies = [
 "pin-project",
 "polars",
 "polars-arrow",
- "rand 0.9.4",
+ "rand 0.9.2",
 "random_word 0.4.3",
 "regex",
 "reqwest",
@@ -4658,7 +4658,7 @@ dependencies = [
 [[package]]
 name = "lancedb-nodejs"
-version = "0.28.0-beta.9"
+version = "0.28.0-beta.8"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4680,7 +4680,7 @@ dependencies = [
 [[package]]
 name = "lancedb-python"
-version = "0.31.0-beta.9"
+version = "0.31.0-beta.8"
 dependencies = [
 "arrow",
 "async-trait",
@@ -5235,7 +5235,7 @@ version = "0.50.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7957b9740744892f114936ab4a57b3f487491bbeafaf8083688b16841a4240e5"
 dependencies = [
- "windows-sys 0.61.2",
+ "windows-sys 0.59.0",
 ]
 [[package]]
@@ -5357,7 +5357,7 @@ dependencies = [
 "parking_lot",
 "percent-encoding",
 "quick-xml 0.38.4",
- "rand 0.9.4",
+ "rand 0.9.2",
 "reqwest",
 "ring",
 "rustls-pemfile",
@@ -6199,8 +6199,8 @@ version = "0.14.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "343d3bd7056eda839b03204e68deff7d1b13aba7af2b2fd16890697274262ee7"
 dependencies = [
- "heck 0.4.1",
+ "heck 0.5.0",
- "itertools 0.14.0",
+ "itertools 0.11.0",
 "log",
 "multimap",
 "petgraph",
@@ -6219,7 +6219,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "27c6023962132f4b30eb4c172c91ce92d933da334c59c23cddee82358ddafb0b"
 dependencies = [
 "anyhow",
- "itertools 0.14.0",
+ "itertools 0.11.0",
 "proc-macro2",
 "quote",
 "syn 2.0.117",
@@ -6402,7 +6402,7 @@ dependencies = [
 "bytes",
 "getrandom 0.3.4",
 "lru-slab",
- "rand 0.9.4",
+ "rand 0.9.2",
 "ring",
 "rustc-hash",
 "rustls 0.23.37",
@@ -6425,7 +6425,7 @@ dependencies = [
 "once_cell",
 "socket2 0.6.3",
 "tracing",
- "windows-sys 0.60.2",
+ "windows-sys 0.59.0",
 ]
 [[package]]
@@ -6468,9 +6468,9 @@ dependencies = [
 [[package]]
 name = "rand"
-version = "0.9.4"
+version = "0.9.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "44c5af06bb1b7d3216d91932aed5265164bf384dc89cd6ba05cf59a35f5f76ea"
+checksum = "6db2770f06117d490610c7488547d543617b21bfa07796d7a12f6f1bd53850d1"
 dependencies = [
 "rand_chacha 0.9.0",
 "rand_core 0.9.5",
@@ -6531,7 +6531,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6a8615d50dcf34fa31f7ab52692afec947c4dd0ab803cc87cb3b0b4570ff7463"
 dependencies = [
 "num-traits",
- "rand 0.9.4",
+ "rand 0.9.2",
 ]
 [[package]]
@@ -6566,7 +6566,7 @@ dependencies = [
 "ahash",
 "brotli 8.0.2",
 "paste",
- "rand 0.9.4",
+ "rand 0.9.2",
 "unicase",
 ]
@@ -6954,7 +6954,7 @@ dependencies = [
 "errno",
 "libc",
 "linux-raw-sys",
- "windows-sys 0.61.2",
+ "windows-sys 0.59.0",
 ]
 [[package]]
@@ -6980,7 +6980,7 @@ dependencies = [
 "once_cell",
 "ring",
 "rustls-pki-types",
- "rustls-webpki 0.103.13",
+ "rustls-webpki 0.103.10",
 "subtle",
 "zeroize",
 ]
@@ -7028,9 +7028,9 @@ dependencies = [
 [[package]]
 name = "rustls-webpki"
-version = "0.103.13"
+version = "0.103.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "61c429a8649f110dddef65e2a5ad240f747e85f7758a6bccc7e5777bd33f756e"
+checksum = "df33b2b81ac578cabaf06b89b0631153a3f416b0a886e8a7a1707fb51abbd1ef"
 dependencies = [
 "aws-lc-rs",
 "ring",
@@ -7465,7 +7465,7 @@ version = "0.8.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c1c97747dbf44bb1ca44a561ece23508e99cb592e862f22222dcf42f51d1e451"
 dependencies = [
- "heck 0.4.1",
+ "heck 0.5.0",
 "proc-macro2",
 "quote",
 "syn 2.0.117",
@@ -7477,7 +7477,7 @@ version = "0.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "54254b8531cafa275c5e096f62d48c81435d1015405a91198ddb11e967301d40"
 dependencies = [
- "heck 0.4.1",
+ "heck 0.5.0",
 "proc-macro2",
 "quote",
 "syn 2.0.117",
@@ -7818,7 +7818,7 @@ dependencies = [
 "getrandom 0.4.2",
 "once_cell",
 "rustix",
- "windows-sys 0.61.2",
+ "windows-sys 0.59.0",
 ]
 [[package]]
@@ -8242,7 +8242,7 @@ version = "2.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9ea3136b675547379c4bd395ca6b938e5ad3c3d20fad76e7fe85f9e0d011419c"
 dependencies = [
- "rand 0.9.4",
+ "rand 0.9.2",
 ]
 [[package]]
@@ -8298,9 +8298,9 @@ dependencies = [
 [[package]]
 name = "unicode-segmentation"
-version = "1.13.2"
+version = "1.13.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9629274872b2bfaf8d66f5f15725007f635594914870f65218920345aa11aa8c"
+checksum = "da36089a805484bcccfffe0739803392c8298778a2d2f09febf76fac5ad9025b"
 [[package]]
 name = "unicode-width"
@@ -8632,7 +8632,7 @@ version = "0.1.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c2a7b1c03c876122aa43f3020e6c3c3ee5c05081c9a00739faf7503aeba10d22"
 dependencies = [
- "windows-sys 0.61.2",
+ "windows-sys 0.59.0",
 ]
 [[package]]
@@ -1,5 +1,7 @@
 [workspace]
 members = ["rust/lancedb", "nodejs", "python"]
 # Python package needs to be built by maturin.
 exclude = ["python"]
 resolver = "2"
 [workspace.package]
@@ -13,20 +15,20 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"
 [workspace.dependencies]
-lance = { "version" = "=6.0.0-beta.4", default-features = false, "tag" = "v6.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=6.0.0-beta.1", default-features = false, "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=6.0.0-beta.4", "tag" = "v6.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=6.0.0-beta.1", "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=6.0.0-beta.4", "tag" = "v6.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=6.0.0-beta.1", "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=6.0.0-beta.4", "tag" = "v6.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=6.0.0-beta.1", "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=6.0.0-beta.4", default-features = false, "tag" = "v6.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=6.0.0-beta.1", default-features = false, "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=6.0.0-beta.4", "tag" = "v6.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=6.0.0-beta.1", "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=6.0.0-beta.4", "tag" = "v6.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=6.0.0-beta.1", "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=6.0.0-beta.4", "tag" = "v6.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=6.0.0-beta.1", "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=6.0.0-beta.4", default-features = false, "tag" = "v6.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=6.0.0-beta.1", default-features = false, "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=6.0.0-beta.4", "tag" = "v6.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=6.0.0-beta.1", "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=6.0.0-beta.4", "tag" = "v6.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=6.0.0-beta.1", "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=6.0.0-beta.4", "tag" = "v6.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=6.0.0-beta.1", "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=6.0.0-beta.4", "tag" = "v6.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=6.0.0-beta.1", "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=6.0.0-beta.4", "tag" = "v6.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=6.0.0-beta.1", "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
 ahash = "0.8"
 # Note that this one does not include pyarrow
 arrow = { version = "57.2", optional = false }
@@ -1,172 +0,0 @@
 # cargo-deny configuration for LanceDB.
 #
 # Run locally with `cargo deny check`. See
 # https://embarkstudios.github.io/cargo-deny/ for the full reference.
 # The set of target triples we care about. cargo-deny will only consider
 # dependencies that are used on at least one of these targets. Keeping this
 # explicit avoids noise from platform-specific crates (e.g. wasm, android,
 # ios) that we never actually ship.
 [graph]
 targets = [
    "x86_64-unknown-linux-gnu",
    "aarch64-unknown-linux-gnu",
    "x86_64-apple-darwin",
    "aarch64-apple-darwin",
    "x86_64-pc-windows-msvc",
    "aarch64-pc-windows-msvc",
 ]
 all-features = true
 [output]
 feature-depth = 1
 # ---------------------------------------------------------------------------
 # Advisories: security vulnerabilities and yanked crates.
 # ---------------------------------------------------------------------------
 [advisories]
 version = 2
 # Fail the check if any crate in the lockfile has been yanked from crates.io.
 # Yanked crates are a signal the author retracted the release (often due to
 # bugs or security issues) and should not be depended on.
 yanked = "deny"
 # Advisory IDs we have explicitly reviewed and chosen to accept. Every
 # entry must include a rationale and, where possible, an upstream issue
 # pointing to a fix. Revisit this list whenever dependencies are updated.
 ignore = [
    # rsa: Marvin Attack timing side-channel in PKCS#1 v1.5 decryption.
    # Reached only through opendal → reqsign → rsa. We do not use RSA
    # decryption in LanceDB ourselves; this is dormant in the signing path.
    # No fixed release exists upstream as of this writing.
    # https://rustsec.org/advisories/RUSTSEC-2023-0071
    { id = "RUSTSEC-2023-0071", reason = "rsa crate via opendal/reqsign; no fixed upstream release" },
    # instant: unmaintained. Pulled in via backoff → instant. Upstream
    # recommends switching to `web-time`; fix has to come from backoff.
    # https://rustsec.org/advisories/RUSTSEC-2024-0384
    { id = "RUSTSEC-2024-0384", reason = "transitive via backoff; waiting on backoff replacement" },
    # paste: unmaintained (author archived the repo). Used transitively by
    # datafusion and the arrow ecosystem; widespread, no drop-in replacement.
    # https://rustsec.org/advisories/RUSTSEC-2024-0436
    { id = "RUSTSEC-2024-0436", reason = "transitive via datafusion; awaiting ecosystem migration" },
    # tantivy: segfault on malformed input due to missing bounds check.
    # Pulled in via lance for full-text search. We only feed tantivy
    # documents we construct ourselves, not attacker-controlled bytes.
    # Tracked for a lance dependency bump.
    # https://rustsec.org/advisories/RUSTSEC-2025-0003
    { id = "RUSTSEC-2025-0003", reason = "tantivy via lance; inputs are internally produced, not user-supplied bytes" },
    # backoff: unmaintained. Reached only via async-openai. Replacement
    # requires async-openai to migrate (or us to drop async-openai).
    # https://rustsec.org/advisories/RUSTSEC-2025-0012
    { id = "RUSTSEC-2025-0012", reason = "transitive via async-openai; waiting on upstream migration" },
    # number_prefix: unmaintained. Transitive via indicatif → hf-hub.
    # No security impact, just maintenance status.
    # https://rustsec.org/advisories/RUSTSEC-2025-0119
    { id = "RUSTSEC-2025-0119", reason = "transitive via hf-hub/indicatif; cosmetic formatting crate" },
    # rustls-pemfile: unmaintained. Reached from two separate chains:
    # rustls-native-certs 0.6 (via hyper-rustls 0.24) and object_store 0.12.
    # Both upstream dependencies need to move before we can drop it.
    # https://rustsec.org/advisories/RUSTSEC-2025-0134
    { id = "RUSTSEC-2025-0134", reason = "transitive via rustls-native-certs/object_store; waiting on upstream migration" },
    # rustls-webpki 0.101.7 (old major line): name-constraint checks for
    # URI / wildcard names. Pulled in only via the legacy rustls 0.21 chain
    # from aws-smithy-http-client. The 0.103 line we actively use is patched.
    # Clearing the 0.101 copy requires the aws-sdk chain to migrate off
    # rustls 0.21.
    # https://rustsec.org/advisories/RUSTSEC-2026-0098
    # https://rustsec.org/advisories/RUSTSEC-2026-0099
    { id = "RUSTSEC-2026-0098", reason = "only affects rustls-webpki 0.101 from legacy aws-smithy/rustls 0.21 chain" },
    { id = "RUSTSEC-2026-0099", reason = "only affects rustls-webpki 0.101 from legacy aws-smithy/rustls 0.21 chain" },
    # rustls-webpki 0.101.7: reachable panic in CRL parsing. Same legacy
    # rustls 0.21 chain from aws-smithy-http-client as above. The 0.103 line
    # we actively use is upgraded to 0.103.13 which contains the fix.
    # https://rustsec.org/advisories/RUSTSEC-2026-0104
    { id = "RUSTSEC-2026-0104", reason = "only affects rustls-webpki 0.101 from legacy aws-smithy/rustls 0.21 chain" },
 ]
 # ---------------------------------------------------------------------------
 # Licenses: only allow licenses we've reviewed as compatible with Apache-2.0.
 # ---------------------------------------------------------------------------
 [licenses]
 version = 2
 # SPDX identifiers for licenses that are compatible with our Apache-2.0
 # distribution. Additions require legal review.
 allow = [
    "Apache-2.0",
    "Apache-2.0 WITH LLVM-exception",
    "MIT",
    "BSD-2-Clause",
    "BSD-3-Clause",
    "ISC",
    "Unicode-3.0",
    "Unicode-DFS-2016",
    "Zlib",
    "CC0-1.0",
    "MPL-2.0",
    "BSL-1.0",
    "OpenSSL",
    # 0BSD ("BSD Zero Clause") is effectively public domain — no attribution
    # required. Pulled in by `mock_instant`.
    "0BSD",
    # bzip2-1.0.6 is the permissive upstream bzip2 license (BSD-like). Pulled
    # in by `libbz2-rs-sys`, the pure-Rust bzip2 implementation.
    "bzip2-1.0.6",
    # CDLA-Permissive-2.0 is a permissive data license used by `webpki-roots`
    # for the Mozilla CA root bundle. Data-only, distribution-compatible.
    "CDLA-Permissive-2.0",
 ]
 confidence-threshold = 0.8
 # Crates whose license cannot be determined from Cargo metadata but whose
 # license we've manually confirmed from upstream. Keep this list minimal.
 [[licenses.clarify]]
 # polars-arrow-format omits the `license` field in its Cargo.toml, but the
 # upstream repo (pola-rs/polars-arrow-format) is dual-licensed Apache-2.0 OR
 # MIT. See https://github.com/pola-rs/polars-arrow-format/blob/main/LICENSE
 crate = "polars-arrow-format"
 expression = "Apache-2.0 OR MIT"
 license-files = []
 # ---------------------------------------------------------------------------
 # Bans: disallow specific crates and flag dependency hygiene issues.
 # ---------------------------------------------------------------------------
 [bans]
 # Warn (not deny) on duplicate versions of the same crate. In a large
 # workspace like this one, duplicates are common and often unavoidable
 # transitively. We surface them to discourage growth, but don't fail CI.
 multiple-versions = "warn"
 # Wildcard version requirements (`foo = "*"`) are a footgun — they let any
 # future release in without review. Ban them outright.
 wildcards = "deny"
 # Internal workspace crates reference each other via `path = "..."`, which
 # cargo-deny sees as a wildcard version. That's fine for private workspace
 # members (not published to crates.io), so allow it specifically for paths.
 allow-wildcard-paths = true
 # Features that, if enabled, should cause the check to fail.
 deny = []
 # Crates to skip when checking for duplicate versions.
 skip = []
 # Similar to `skip`, but also skips the entire transitive subtree.
 skip-tree = []
 # ---------------------------------------------------------------------------
 # Sources: restrict where crates can come from.
 # ---------------------------------------------------------------------------
 [sources]
 # Deny any registry other than the ones explicitly listed below.
 unknown-registry = "deny"
 # Deny any git dependency whose host isn't in the allow-list below. This
 # prevents accidental pulls from arbitrary forks.
 unknown-git = "deny"
 allow-registry = ["https://github.com/rust-lang/crates.io-index"]
 # Lance is developed in a sibling repo and pulled as a git dependency until
 # releases are cut to crates.io. Allow that specific host.
 allow-git = [
    "https://github.com/lance-format/lance",
 ]
@@ -24,4 +24,4 @@ RUN python --version && \
  rustc --version && \
  protoc --version
-RUN pip install --no-cache-dir lancedb
+RUN pip install --no-cache-dir tantivy lancedb
@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
 <dependency>
    <groupId>com.lancedb</groupId>
    <artifactId>lancedb-core</artifactId>
-    <version>0.28.0-beta.9</version>
+    <version>0.28.0-beta.8</version>
 </dependency>
 ```
@@ -8,7 +8,7 @@
    <parent>
      <groupId>com.lancedb</groupId>
      <artifactId>lancedb-parent</artifactId>
-      <version>0.28.0-beta.9</version>
+      <version>0.28.0-beta.8</version>
      <relativePath>../pom.xml</relativePath>
    </parent>
@@ -6,7 +6,7 @@
    <groupId>com.lancedb</groupId>
    <artifactId>lancedb-parent</artifactId>
-    <version>0.28.0-beta.9</version>
+    <version>0.28.0-beta.8</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>6.0.0-beta.4</lance-core.version>
+        <lance-core.version>6.0.0-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>
@@ -1,8 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.28.0-beta.9"
+version = "0.28.0-beta.8"
 publish = false
 license.workspace = true
 description.workspace = true
 repository.workspace = true
@@ -32,8 +31,8 @@ lzma-sys = { version = "0.1", features = ["static"] }
 log.workspace = true
 # Pin to resolve build failures; update periodically for security patches.
-aws-lc-sys = "=0.40.0"
+aws-lc-sys = "=0.38.0"
-aws-lc-rs = "=1.16.3"
+aws-lc-rs = "=1.16.1"
 [build-dependencies]
 napi-build = "2.3.1"
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.28.0-beta.9",
+	"version": "0.28.0-beta.8",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.28.0-beta.9",
+	"version": "0.28.0-beta.8",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-musl",
-	"version": "0.28.0-beta.9",
+	"version": "0.28.0-beta.8",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-musl.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.28.0-beta.9",
+	"version": "0.28.0-beta.8",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-musl",
-	"version": "0.28.0-beta.9",
+	"version": "0.28.0-beta.8",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-musl.node",
@@ -1,6 +1,6 @@
 {
  "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.28.0-beta.9",
+  "version": "0.28.0-beta.8",
  "os": [
    "win32"
  ],
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.28.0-beta.9",
+	"version": "0.28.0-beta.8",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",
@@ -1,12 +1,12 @@
 {
  "name": "@lancedb/lancedb",
-  "version": "0.28.0-beta.9",
+  "version": "0.28.0-beta.8",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "@lancedb/lancedb",
-      "version": "0.28.0-beta.9",
+      "version": "0.28.0-beta.8",
      "cpu": [
        "x64",
        "arm64"
@@ -11,7 +11,7 @@
    "ann"
  ],
  "private": false,
-  "version": "0.28.0-beta.9",
+  "version": "0.28.0-beta.8",
  "main": "dist/index.js",
  "exports": {
    ".": "./dist/index.js",
@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.31.0-beta.10"
+current_version = "0.31.0-beta.8"
 parse = """(?x)
    (?P<major>0|[1-9]\\d*)\\.
    (?P<minor>0|[1-9]\\d*)\\.
@@ -1,7 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.31.0-beta.10"
+version = "0.31.0-beta.8"
 publish = false
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true
@@ -183,6 +183,7 @@
 | stack-data                     | 0.6.3           | MIT License                                                                                      | http://github.com/alexmojaki/stack_data                                                           |
 | sympy                          | 1.14.0          | BSD License                                                                                      | https://sympy.org                                                                                 |
 | tabulate                       | 0.9.0           | MIT License                                                                                      | https://github.com/astanin/python-tabulate                                                        |
 | tantivy                        | 0.25.1          | UNKNOWN                                                                                          | UNKNOWN                                                                                           |
 | threadpoolctl                  | 3.6.0           | BSD License                                                                                      | https://github.com/joblib/threadpoolctl                                                           |
 | timm                           | 1.0.24          | Apache Software License                                                                          | https://github.com/huggingface/pytorch-image-models                                               |
 | tinycss2                       | 1.4.0           | BSD License                                                                                      | https://www.courtbouillon.org/tinycss2                                                            |
@@ -57,6 +57,7 @@ tests = [
    "duckdb>=0.9.0",
    "pytz>=2023.3",
    "polars>=0.19, <=1.3.0",
    "tantivy>=0.20.0",
    "pyarrow-stubs>=16.0",
    "pylance>=5.0.0b5",
    "requests>=2.31.0",
@@ -0,0 +1,201 @@
 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright The LanceDB Authors
 """Full text search index using tantivy-py"""
 import os
 from typing import List, Tuple, Optional
 import pyarrow as pa
 try:
    import tantivy
 except ImportError:
    raise ImportError(
        "Please install tantivy-py `pip install tantivy` to use the full text search feature."  # noqa: E501
    )
 from .table import LanceTable
 def create_index(
    index_path: str,
    text_fields: List[str],
    ordering_fields: Optional[List[str]] = None,
    tokenizer_name: str = "default",
 ) -> tantivy.Index:
    """
    Create a new Index (not populated)
    Parameters
    ----------
    index_path : str
        Path to the index directory
    text_fields : List[str]
        List of text fields to index
    ordering_fields: List[str]
        List of unsigned type fields to order by at search time
    tokenizer_name : str, default "default"
        The tokenizer to use
    Returns
    -------
    index : tantivy.Index
        The index object (not yet populated)
    """
    if ordering_fields is None:
        ordering_fields = []
    # Declaring our schema.
    schema_builder = tantivy.SchemaBuilder()
    # special field that we'll populate with row_id
    schema_builder.add_integer_field("doc_id", stored=True)
    # data fields
    for name in text_fields:
        schema_builder.add_text_field(name, stored=True, tokenizer_name=tokenizer_name)
    if ordering_fields:
        for name in ordering_fields:
            schema_builder.add_unsigned_field(name, fast=True)
    schema = schema_builder.build()
    os.makedirs(index_path, exist_ok=True)
    index = tantivy.Index(schema, path=index_path)
    return index
 def populate_index(
    index: tantivy.Index,
    table: LanceTable,
    fields: List[str],
    writer_heap_size: Optional[int] = None,
    ordering_fields: Optional[List[str]] = None,
 ) -> int:
    """
    Populate an index with data from a LanceTable
    Parameters
    ----------
    index : tantivy.Index
        The index object
    table : LanceTable
        The table to index
    fields : List[str]
        List of fields to index
    writer_heap_size : int
        The writer heap size in bytes, defaults to 1GB
    Returns
    -------
    int
        The number of rows indexed
    """
    if ordering_fields is None:
        ordering_fields = []
    writer_heap_size = writer_heap_size or 1024 * 1024 * 1024
    # first check the fields exist and are string or large string type
    nested = []
    for name in fields:
        try:
            f = table.schema.field(name)  # raises KeyError if not found
        except KeyError:
            f = resolve_path(table.schema, name)
            nested.append(name)
        if not pa.types.is_string(f.type) and not pa.types.is_large_string(f.type):
            raise TypeError(f"Field {name} is not a string type")
    # create a tantivy writer
    writer = index.writer(heap_size=writer_heap_size)
    # write data into index
    dataset = table.to_lance()
    row_id = 0
    max_nested_level = 0
    if len(nested) > 0:
        max_nested_level = max([len(name.split(".")) for name in nested])
    for b in dataset.to_batches(columns=fields + ordering_fields):
        if max_nested_level > 0:
            b = pa.Table.from_batches([b])
            for _ in range(max_nested_level - 1):
                b = b.flatten()
        for i in range(b.num_rows):
            doc = tantivy.Document()
            for name in fields:
                value = b[name][i].as_py()
                if value is not None:
                    doc.add_text(name, value)
            for name in ordering_fields:
                value = b[name][i].as_py()
                if value is not None:
                    doc.add_unsigned(name, value)
            if not doc.is_empty:
                doc.add_integer("doc_id", row_id)
                writer.add_document(doc)
            row_id += 1
    # commit changes
    writer.commit()
    return row_id
 def resolve_path(schema, field_name: str) -> pa.Field:
    """
    Resolve a nested field path to a list of field names
    Parameters
    ----------
    field_name : str
        The field name to resolve
    Returns
    -------
    List[str]
        The resolved path
    """
    path = field_name.split(".")
    field = schema.field(path.pop(0))
    for segment in path:
        if pa.types.is_struct(field.type):
            field = field.type.field(segment)
        else:
            raise KeyError(f"field {field_name} not found in schema {schema}")
    return field
 def search_index(
    index: tantivy.Index, query: str, limit: int = 10, ordering_field=None
 ) -> Tuple[Tuple[int], Tuple[float]]:
    """
    Search an index for a query
    Parameters
    ----------
    index : tantivy.Index
        The index object
    query : str
        The query string
    limit : int
        The maximum number of results to return
    Returns
    -------
    ids_and_score: list[tuple[int], tuple[float]]
        A tuple of two tuples, the first containing the document ids
        and the second containing the scores
    """
    searcher = index.searcher()
    query = index.parse_query(query)
    # get top results
    if ordering_field:
        results = searcher.search(query, limit, order_by_field=ordering_field)
    else:
        results = searcher.search(query, limit)
    if results.count == 0:
        return tuple(), tuple()
    return tuple(
        zip(
            *[
                (searcher.doc(doc_address)["doc_id"][0], score)
                for score, doc_address in results.hits
            ]
        )
    )
@@ -25,6 +25,7 @@ import deprecation
 import numpy as np
 import pyarrow as pa
 import pyarrow.compute as pc
 import pyarrow.fs as pa_fs
 import pydantic
 from lancedb.pydantic import PYDANTIC_VERSION
@@ -1525,7 +1526,9 @@ class LanceFtsQueryBuilder(LanceQueryBuilder):
        return self._table._output_schema(self.to_query_object())
    def to_arrow(self, *, timeout: Optional[timedelta] = None) -> pa.Table:
-        self._table._ensure_no_legacy_fts_index()
+        path, fs, exist = self._table._get_fts_index_path()
        if exist:
            return self.tantivy_to_arrow()
        query = self._query
        if self._phrase_query:
@@ -1549,6 +1552,90 @@ class LanceFtsQueryBuilder(LanceQueryBuilder):
    ):
        raise NotImplementedError("to_batches on an FTS query")
    def tantivy_to_arrow(self) -> pa.Table:
        try:
            import tantivy
        except ImportError:
            raise ImportError(
                "Please install tantivy-py `pip install tantivy` to use the full text search feature."  # noqa: E501
            )
        from .fts import search_index
        # get the index path
        path, fs, exist = self._table._get_fts_index_path()
        # check if the index exist
        if not exist:
            raise FileNotFoundError(
                "Fts index does not exist. "
                "Please first call table.create_fts_index(['<field_names>']) to "
                "create the fts index."
            )
        # Check that we are on local filesystem
        if not isinstance(fs, pa_fs.LocalFileSystem):
            raise NotImplementedError(
                "Tantivy-based full text search "
                "is only supported on the local filesystem"
            )
        # open the index
        index = tantivy.Index.open(path)
        # get the scores and doc ids
        query = self._query
        if self._phrase_query:
            query = query.replace('"', "'")
            query = f'"{query}"'
        limit = self._limit if self._limit is not None else 10
        row_ids, scores = search_index(
            index, query, limit, ordering_field=self.ordering_field_name
        )
        if len(row_ids) == 0:
            empty_schema = pa.schema([pa.field("_score", pa.float32())])
            return pa.Table.from_batches([], schema=empty_schema)
        scores = pa.array(scores)
        output_tbl = self._table.to_lance().take(row_ids, columns=self._columns)
        output_tbl = output_tbl.append_column("_score", scores)
        # this needs to match vector search results which are uint64
        row_ids = pa.array(row_ids, type=pa.uint64())
        if self._where is not None:
            tmp_name = "__lancedb__duckdb__indexer__"
            output_tbl = output_tbl.append_column(
                tmp_name, pa.array(range(len(output_tbl)))
            )
            try:
                # TODO would be great to have Substrait generate pyarrow compute
                # expressions or conversely have pyarrow support SQL expressions
                # using Substrait
                import duckdb
                indexer = duckdb.sql(
                    f"SELECT {tmp_name} FROM output_tbl WHERE {self._where}"
                ).to_arrow_table()[tmp_name]
                output_tbl = output_tbl.take(indexer).drop([tmp_name])
                row_ids = row_ids.take(indexer)
            except ImportError:
                import tempfile
                import lance
                # TODO Use "memory://" instead once that's supported
                with tempfile.TemporaryDirectory() as tmp:
                    ds = lance.write_dataset(output_tbl, tmp)
                    output_tbl = ds.to_table(filter=self._where)
                    indexer = output_tbl[tmp_name]
                    row_ids = row_ids.take(indexer)
                    output_tbl = output_tbl.drop([tmp_name])
        if self._with_row_id:
            output_tbl = output_tbl.append_column("_rowid", row_ids)
        if self._reranker is not None:
            output_tbl = self._reranker.rerank_fts(self._query, output_tbl)
        return output_tbl
    def rerank(self, reranker: Reranker) -> LanceFtsQueryBuilder:
        """Rerank the results using the specified reranker.
@@ -943,26 +943,29 @@ class Table(ABC):
        Parameters
        ----------
        field_names: str or list of str
-            The name of the field to index. Native FTS indexes can only be
+            The name(s) of the field to index.
-            created on a single field at a time. To search over multiple text
+            If ``use_tantivy`` is False (default), only a single field name
-            fields, create a separate FTS index for each field.
+            (str) is supported. To index multiple fields, create a separate
            FTS index for each field.
        replace: bool, default False
            If True, replace the existing index if it exists. Note that this is
            not yet an atomic operation; the index will be temporarily
            unavailable while the new index is being created.
        writer_heap_size: int, default 1GB
-            Deprecated legacy Tantivy parameter. Any value other than the
+            Only available with use_tantivy=True
            default raises an error.
        ordering_field_names:
-            Deprecated legacy Tantivy parameter. Setting this raises an error.
+            A list of unsigned type fields to index to optionally order
            results on at search time.
            only available with use_tantivy=True
        tokenizer_name: str, default "default"
-            A compatibility alias for native tokenizer configs. Can be "raw",
+            The tokenizer to use for the index. Can be "raw", "default" or the 2 letter
-            "default" or the 2 letter language code followed by "_stem". So
+            language code followed by "_stem". So for english it would be "en_stem".
-            for english it would be "en_stem".
+            For available languages see: https://docs.rs/tantivy/latest/tantivy/tokenizer/enum.Language.html
        use_tantivy: bool, default False
-            Deprecated legacy Tantivy parameter. Setting this to True raises an
+            If True, use the legacy full-text search implementation based on tantivy.
-            error.
+            If False, use the new full-text search implementation based on lance-index.
        with_position: bool, default False
            Only available with use_tantivy=False
            If False, do not store the positions of the terms in the text.
            This can reduce the size of the index and improve indexing speed.
            But it will raise an exception for phrase queries.
@@ -1743,16 +1746,6 @@ class Table(ABC):
        index_exists = fs.get_file_info(path).type != pa_fs.FileType.NotFound
        return (path, fs, index_exists)
    def _ensure_no_legacy_fts_index(self):
        path, _, exists = self._get_fts_index_path()
        if exists:
            raise ValueError(
                "Legacy Tantivy FTS index detected at "
                f"{path}. Tantivy-based FTS has been removed. "
                "Delete the legacy index and recreate it with "
                "table.create_fts_index(...)."
            )
    @abstractmethod
    def uses_v2_manifest_paths(self) -> bool:
        """
@@ -2412,63 +2405,84 @@ class LanceTable(Table):
        prefix_only: bool = False,
        name: Optional[str] = None,
    ):
-        self._ensure_no_legacy_fts_index()
+        if not use_tantivy:
            if not isinstance(field_names, str):
                raise ValueError(
                    "Native FTS indexes can only be created on a single field "
                    "at a time. To search over multiple text fields, create a "
                    "separate FTS index for each field."
                )
-        if use_tantivy:
+            if tokenizer_name is None:
-            raise ValueError(
+                tokenizer_configs = {
-                "Tantivy-based FTS has been removed. "
+                    "base_tokenizer": base_tokenizer,
-                "Remove use_tantivy and recreate the index with native FTS."
+                    "language": language,
                    "with_position": with_position,
                    "max_token_length": max_token_length,
                    "lower_case": lower_case,
                    "stem": stem,
                    "remove_stop_words": remove_stop_words,
                    "ascii_folding": ascii_folding,
                    "ngram_min_length": ngram_min_length,
                    "ngram_max_length": ngram_max_length,
                    "prefix_only": prefix_only,
                }
            else:
                tokenizer_configs = self.infer_tokenizer_configs(tokenizer_name)
            config = FTS(
                **tokenizer_configs,
            )
-        if ordering_field_names is not None:
+
-            raise ValueError(
+            # delete the existing legacy index if it exists
-                "ordering_field_names was only supported by the removed "
+            if replace:
-                "Tantivy-based FTS implementation."
+                path, fs, exist = self._get_fts_index_path()
                if exist:
                    fs.delete_dir(path)
            LOOP.run(
                self._table.create_index(
                    field_names,
                    replace=replace,
                    config=config,
                    name=name,
                )
            )
-        if writer_heap_size != 1024 * 1024 * 1024:
+            return
-            raise ValueError(
+
-                "writer_heap_size was only supported by the removed "
+        from .fts import create_index, populate_index
-                "Tantivy-based FTS implementation."
+
-            )
+        if isinstance(field_names, str):
-        if not isinstance(field_names, str):
+            field_names = [field_names]
-            raise ValueError(
+
-                "Native FTS indexes can only be created on a single field "
+        if isinstance(ordering_field_names, str):
-                "at a time. To search over multiple text fields, create a "
+            ordering_field_names = [ordering_field_names]
-                "separate FTS index for each field."
+
-            )
+        path, fs, exist = self._get_fts_index_path()
-        if "." in field_names:
+        if exist:
-            raise ValueError(
+            if not replace:
-                "Native FTS indexes can only be created on top-level fields. "
+                raise ValueError("Index already exists. Use replace=True to overwrite.")
-                f"Received nested field path: {field_names!r}."
+            fs.delete_dir(path)
        if not isinstance(fs, pa_fs.LocalFileSystem):
            raise NotImplementedError(
                "Full-text search is only supported on the local filesystem"
            )
        if tokenizer_name is None:
-            tokenizer_configs = {
+            tokenizer_name = "default"
-                "base_tokenizer": base_tokenizer,
+        index = create_index(
-                "language": language,
+            path,
-                "with_position": with_position,
+            field_names,
-                "max_token_length": max_token_length,
+            ordering_fields=ordering_field_names,
-                "lower_case": lower_case,
+            tokenizer_name=tokenizer_name,
                "stem": stem,
                "remove_stop_words": remove_stop_words,
                "ascii_folding": ascii_folding,
                "ngram_min_length": ngram_min_length,
                "ngram_max_length": ngram_max_length,
                "prefix_only": prefix_only,
            }
        else:
            tokenizer_configs = self.infer_tokenizer_configs(tokenizer_name)
        config = FTS(
            **tokenizer_configs,
        )
-
+        populate_index(
-        LOOP.run(
+            index,
-            self._table.create_index(
+            self,
-                field_names,
+            field_names,
-                replace=replace,
+            ordering_fields=ordering_field_names,
-                config=config,
+            writer_heap_size=writer_heap_size,
                name=name,
            )
        )
    @staticmethod
@@ -180,7 +180,7 @@ def test_fts_fuzzy_query():
        ),
        mode="overwrite",
    )
-    table.create_fts_index("text", replace=True)
+    table.create_fts_index("text", use_tantivy=False, replace=True)
    results = table.search(MatchQuery("foo", "text", fuzziness=1)).to_pandas()
    assert len(results) == 4
@@ -230,7 +230,7 @@ def test_fts_boost_query():
        ),
        mode="overwrite",
    )
-    table.create_fts_index("desc", replace=True)
+    table.create_fts_index("desc", use_tantivy=False, replace=True)
    results = table.search(
        BoostQuery(
@@ -265,7 +265,7 @@ def test_fts_boolean_query(tmp_path):
        ],
        mode="overwrite",
    )
-    table.create_fts_index("text", replace=True)
+    table.create_fts_index("text", use_tantivy=False, replace=True)
    # SHOULD
    results = table.search(
@@ -319,7 +319,9 @@ def test_fts_native():
        ],
    )
-    table.create_fts_index("text")
+    # passing `use_tantivy=False` to use lance FTS index
    # `use_tantivy=True` by default
    table.create_fts_index("text", use_tantivy=False)
    table.search("puppy").limit(10).select(["text"]).to_list()
    # [{'text': 'Frodo was a happy puppy', '_score': 0.6931471824645996}]
    # ...
@@ -330,6 +332,7 @@ def test_fts_native():
    # --8<-- [start:fts_config_folding]
    table.create_fts_index(
        "text",
        use_tantivy=False,
        language="French",
        stem=True,
        ascii_folding=True,
@@ -343,7 +346,7 @@ def test_fts_native():
    table.search("puppy").limit(10).where("text='foo'", prefilter=False).to_list()
    # --8<-- [end:fts_postfiltering]
    # --8<-- [start:fts_with_position]
-    table.create_fts_index("text", with_position=True, replace=True)
+    table.create_fts_index("text", use_tantivy=False, with_position=True, replace=True)
    # --8<-- [end:fts_with_position]
    # --8<-- [start:fts_incremental_index]
    table.add([{"vector": [3.1, 4.1], "text": "Frodo was a happy puppy"}])
@@ -15,7 +15,8 @@ import pytest
 from lancedb.pydantic import LanceModel, Vector
-def test_basic(tmp_path):
+@pytest.mark.parametrize("use_tantivy", [True, False])
 def test_basic(tmp_path, use_tantivy):
    db = lancedb.connect(tmp_path)
    assert db.uri == str(tmp_path)
@@ -48,7 +49,7 @@ def test_basic(tmp_path):
    assert len(rs) == 1
    assert rs["item"].iloc[0] == "foo"
-    table.create_fts_index("item")
+    table.create_fts_index("item", use_tantivy=use_tantivy)
    rs = table.search("bar", query_type="fts").to_pandas()
    assert len(rs) == 1
    assert rs["item"].iloc[0] == "bar"
@@ -36,6 +36,9 @@ import pytest
 import pytest_asyncio
 from utils import exception_output
 pytest.importorskip("lancedb.fts")
 tantivy = pytest.importorskip("tantivy")
@pytest.fixture
 def table(tmp_path) -> ldb.table.LanceTable:
@@ -141,53 +144,58 @@ async def async_table(tmp_path) -> ldb.table.AsyncTable:
    return table
-@pytest.mark.parametrize(
+def test_create_index(tmp_path):
-    ("kwargs", "match"),
+    index = ldb.fts.create_index(str(tmp_path / "index"), ["text"])
-    [
+    assert isinstance(index, tantivy.Index)
-        (
+    assert os.path.exists(str(tmp_path / "index"))
            {"use_tantivy": True},
            "Tantivy-based FTS has been removed",
        ),
        (
            {"ordering_field_names": ["count"]},
            "ordering_field_names was only supported",
        ),
        (
            {"writer_heap_size": 128},
            "writer_heap_size was only supported",
        ),
    ],
 )
 def test_reject_removed_tantivy_parameters(table, kwargs, match):
    with pytest.raises(ValueError, match=match):
        table.create_fts_index("text", **kwargs)
-def test_reject_legacy_tantivy_index(table):
+def test_create_index_with_stemming(tmp_path, table):
-    path, _, _ = table._get_fts_index_path()
+    index = ldb.fts.create_index(
-    os.makedirs(path, exist_ok=True)
+        str(tmp_path / "index"), ["text"], tokenizer_name="en_stem"
    )
    assert isinstance(index, tantivy.Index)
    assert os.path.exists(str(tmp_path / "index"))
-    with pytest.raises(ValueError, match="Legacy Tantivy FTS index detected"):
+    # Check stemming by running tokenizer on non empty table
-        table.search("puppy").limit(5).to_list()
+    table.create_fts_index("text", tokenizer_name="en_stem", use_tantivy=True)
    with pytest.raises(ValueError, match="Legacy Tantivy FTS index detected"):
        table.create_fts_index("text")
@pytest.mark.parametrize("use_tantivy", [True, False])
@pytest.mark.parametrize("with_position", [True, False])
-def test_create_inverted_index(table, with_position):
+def test_create_inverted_index(table, use_tantivy, with_position):
    if use_tantivy and not with_position:
        pytest.skip("we don't support building a tantivy index without position")
    table.create_fts_index(
        "text",
        use_tantivy=use_tantivy,
        with_position=with_position,
        name="custom_fts_index",
    )
-    indices = table.list_indices()
+    if not use_tantivy:
-    fts_indices = [i for i in indices if i.index_type == "FTS"]
+        indices = table.list_indices()
-    assert any(i.name == "custom_fts_index" for i in fts_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)
-def test_search_fts(table):
+def test_populate_index(tmp_path, table):
-    table.create_fts_index("text")
+    index = ldb.fts.create_index(str(tmp_path / "index"), ["text"])
    assert ldb.fts.populate_index(index, table, ["text"]) == len(table)
 def test_search_index(tmp_path, table):
    index = ldb.fts.create_index(str(tmp_path / "index"), ["text"])
    ldb.fts.populate_index(index, table, ["text"])
    index.reload()
    results = ldb.fts.search_index(index, query="puppy", limit=5)
    assert len(results) == 2
    assert len(results[0]) == 5  # row_ids
    assert len(results[1]) == 5  # _score
@pytest.mark.parametrize("use_tantivy", [True, False])
 def test_search_fts(table, use_tantivy):
    table.create_fts_index("text", use_tantivy=use_tantivy)
    results = table.search("puppy").select(["id", "text"]).limit(5).to_list()
    assert len(results) == 5
    assert len(results[0]) == 3  # id, text, _score
@@ -196,52 +204,53 @@ def test_search_fts(table):
    results = table.search("puppy").select(["id", "text"]).to_list()
    assert len(results) == 10
-    # Test with a query
+    if not use_tantivy:
-    results = (
+        # Test with a query
-        table.search(MatchQuery("puppy", "text"))
+        results = (
-        .select(["id", "text"])
+            table.search(MatchQuery("puppy", "text"))
-        .limit(5)
+            .select(["id", "text"])
-        .to_list()
+            .limit(5)
-    )
+            .to_list()
    assert len(results) == 5
    # Test boost query
    results = (
        table.search(
            BoostQuery(
                MatchQuery("puppy", "text"),
                MatchQuery("runs", "text"),
            )
        )
-        .select(["id", "text"])
+        assert len(results) == 5
        .limit(5)
        .to_list()
    )
    assert len(results) == 5
-    # Test multi match query
+        # Test boost query
-    table.create_fts_index("text2")
+        results = (
-    results = (
+            table.search(
-        table.search(MultiMatchQuery("puppy", ["text", "text2"]))
+                BoostQuery(
-        .select(["id", "text"])
+                    MatchQuery("puppy", "text"),
-        .limit(5)
+                    MatchQuery("runs", "text"),
-        .to_list()
+                )
-    )
+            )
-    assert len(results) == 5
+            .select(["id", "text"])
-    assert len(results[0]) == 3  # id, text, _score
+            .limit(5)
            .to_list()
        )
        assert len(results) == 5
-    # Test boolean query
+        # Test multi match query
-    results = (
+        table.create_fts_index("text2", use_tantivy=use_tantivy)
-        table.search(MatchQuery("puppy", "text") & MatchQuery("runs", "text"))
+        results = (
-        .select(["id", "text"])
+            table.search(MultiMatchQuery("puppy", ["text", "text2"]))
-        .limit(5)
+            .select(["id", "text"])
-        .to_list()
+            .limit(5)
-    )
+            .to_list()
-    assert len(results) == 5
+        )
-    assert len(results[0]) == 3  # id, text, _score
+        assert len(results) == 5
-    for r in results:
+        assert len(results[0]) == 3  # id, text, _score
-        assert "puppy" in r["text"]
+
-        assert "runs" in r["text"]
+        # Test boolean query
        results = (
            table.search(MatchQuery("puppy", "text") & MatchQuery("runs", "text"))
            .select(["id", "text"])
            .limit(5)
            .to_list()
        )
        assert len(results) == 5
        assert len(results[0]) == 3  # id, text, _score
        for r in results:
            assert "puppy" in r["text"]
            assert "runs" in r["text"]
@pytest.mark.asyncio
@@ -309,13 +318,13 @@ async def test_fts_select_async(async_table):
 def test_search_fts_phrase_query(table):
-    table.create_fts_index("text", with_position=False)
+    table.create_fts_index("text", use_tantivy=False, with_position=False)
    try:
        phrase_results = table.search('"puppy runs"').limit(100).to_list()
        assert False
    except Exception:
        pass
-    table.create_fts_index("text", with_position=True, replace=True)
+    table.create_fts_index("text", use_tantivy=False, with_position=True, replace=True)
    results = table.search("puppy").limit(100).to_list()
    # Test with quotation marks
@@ -366,8 +375,8 @@ async def test_search_fts_phrase_query_async(async_table):
 def test_search_fts_specify_column(table):
-    table.create_fts_index("text")
+    table.create_fts_index("text", use_tantivy=False)
-    table.create_fts_index("text2")
+    table.create_fts_index("text2", use_tantivy=False)
    results = table.search("puppy", fts_columns="text").limit(5).to_list()
    assert len(results) == 5
@@ -461,8 +470,42 @@ async def test_search_fts_specify_column_async(async_table):
        pass
-def test_create_index_from_table(tmp_path, table):
+def test_search_ordering_field_index_table(tmp_path, table):
-    table.create_fts_index("text")
+    table.create_fts_index("text", ordering_field_names=["count"], use_tantivy=True)
    rows = (
        table.search("puppy", ordering_field_name="count")
        .limit(20)
        .select(["text", "count"])
        .to_list()
    )
    for r in rows:
        assert "puppy" in r["text"]
    assert sorted(rows, key=lambda x: x["count"], reverse=True) == rows
 def test_search_ordering_field_index(tmp_path, table):
    index = ldb.fts.create_index(
        str(tmp_path / "index"), ["text"], ordering_fields=["count"]
    )
    ldb.fts.populate_index(index, table, ["text"], ordering_fields=["count"])
    index.reload()
    results = ldb.fts.search_index(
        index, query="puppy", limit=5, ordering_field="count"
    )
    assert len(results) == 2
    assert len(results[0]) == 5  # row_ids
    assert len(results[1]) == 5  # _distance
    rows = table.to_lance().take(results[0]).to_pylist()
    for r in rows:
        assert "puppy" in r["text"]
    assert sorted(rows, key=lambda x: x["count"], reverse=True) == rows
@pytest.mark.parametrize("use_tantivy", [True, False])
 def test_create_index_from_table(tmp_path, table, use_tantivy):
    table.create_fts_index("text", use_tantivy=use_tantivy)
    df = table.search("puppy").limit(5).select(["text"]).to_pandas()
    assert len(df) <= 5
    assert "text" in df.columns
@@ -482,24 +525,36 @@ def test_create_index_from_table(tmp_path, table):
    )
    with pytest.raises(Exception, match="already exists"):
-        table.create_fts_index("text")
+        table.create_fts_index("text", use_tantivy=use_tantivy)
-    table.create_fts_index("text", replace=True)
+    table.create_fts_index("text", replace=True, use_tantivy=use_tantivy)
    assert len(table.search("gorilla").limit(1).to_pandas()) == 1
 def test_create_index_multiple_columns(tmp_path, table):
-    with pytest.raises(ValueError, match="Native FTS indexes can only be created"):
+    table.create_fts_index(["text", "text2"], use_tantivy=True)
-        table.create_fts_index(["text", "text2"])
+    df = table.search("puppy").limit(5).to_pandas()
    assert len(df) == 5
    assert "text" in df.columns
    assert "text2" in df.columns
 def test_empty_rs(tmp_path, table, mocker):
    table.create_fts_index(["text", "text2"], use_tantivy=True)
    mocker.patch("lancedb.fts.search_index", return_value=([], []))
    df = table.search("puppy").limit(5).to_pandas()
    assert len(df) == 0
 def test_nested_schema(tmp_path, table):
-    with pytest.raises(ValueError, match="top-level fields"):
+    table.create_fts_index("nested.text", use_tantivy=True)
-        table.create_fts_index("nested.text")
+    rs = table.search("puppy").limit(5).to_list()
    assert len(rs) == 5
-def test_search_index_with_filter(table):
+@pytest.mark.parametrize("use_tantivy", [True, False])
-    table.create_fts_index("text")
+def test_search_index_with_filter(table, use_tantivy):
    table.create_fts_index("text", use_tantivy=use_tantivy)
    orig_import = __import__
    def import_mock(name, *args):
@@ -529,7 +584,8 @@ def test_search_index_with_filter(table):
        assert r["_rowid"] is not None
-def test_null_input(table):
+@pytest.mark.parametrize("use_tantivy", [True, False])
 def test_null_input(table, use_tantivy):
    table.add(
        [
            {
@@ -542,13 +598,14 @@ def test_null_input(table):
            }
        ]
    )
-    table.create_fts_index("text")
+    table.create_fts_index("text", use_tantivy=use_tantivy)
 def test_syntax(table):
    # https://github.com/lancedb/lancedb/issues/769
-    table.create_fts_index("text")
+    table.create_fts_index("text", use_tantivy=True)
-    table.search("they could have been dogs OR").limit(10).to_list()
+    with pytest.raises(ValueError, match="Syntax Error"):
        table.search("they could have been dogs OR").limit(10).to_list()
    # these should work
@@ -559,7 +616,6 @@ def test_syntax(table):
    ).to_list()
    # phrase queries
    table.create_fts_index("text", with_position=True, replace=True)
    table.search("they could have been dogs OR cats").phrase_query().limit(10).to_list()
    table.search('"they could have been dogs OR cats"').limit(10).to_list()
    table.search('''"the cats OR dogs were not really 'pets' at all"''').limit(
@@ -583,7 +639,7 @@ def test_language(mem_db: DBConnection):
    table = mem_db.create_table("test", data=data)
    with pytest.raises(ValueError) as e:
-        table.create_fts_index("text", language="klingon")
+        table.create_fts_index("text", use_tantivy=False, language="klingon")
    assert exception_output(e) == (
        "ValueError: LanceDB does not support the requested language: 'klingon'\n"
@@ -594,6 +650,7 @@ def test_language(mem_db: DBConnection):
    table.create_fts_index(
        "text",
        use_tantivy=False,
        language="French",
        stem=True,
        ascii_folding=True,
@@ -633,7 +690,7 @@ def test_fts_on_list(mem_db: DBConnection):
        }
    )
    table = mem_db.create_table("test", data=data)
-    table.create_fts_index("text", with_position=True)
+    table.create_fts_index("text", use_tantivy=False, with_position=True)
    res = table.search("lance").limit(5).to_list()
    assert len(res) == 3
@@ -645,7 +702,7 @@ def test_fts_on_list(mem_db: DBConnection):
 def test_fts_ngram(mem_db: DBConnection):
    data = pa.table({"text": ["hello world", "lance database", "lance is cool"]})
    table = mem_db.create_table("test", data=data)
-    table.create_fts_index("text", base_tokenizer="ngram")
+    table.create_fts_index("text", use_tantivy=False, base_tokenizer="ngram")
    results = table.search("lan", query_type="fts").limit(10).to_list()
    assert len(results) == 2
@@ -664,6 +721,7 @@ def test_fts_ngram(mem_db: DBConnection):
    # test setting min_ngram_length and prefix_only
    table.create_fts_index(
        "text",
        use_tantivy=False,
        base_tokenizer="ngram",
        replace=True,
        ngram_min_length=2,
@@ -828,7 +886,7 @@ def test_fts_query_to_json():
 def test_fts_fast_search(table):
-    table.create_fts_index("text")
+    table.create_fts_index("text", use_tantivy=False)
    # Insert some unindexed data
    table.add(
@@ -28,7 +28,7 @@ def sync_table(tmpdir_factory) -> Table:
        }
    )
    table = db.create_table("test", data)
-    table.create_fts_index("text", with_position=False)
+    table.create_fts_index("text", with_position=False, use_tantivy=False)
    return table
@@ -192,7 +192,7 @@ def table_with_id(tmpdir_factory) -> Table:
        }
    )
    table = db.create_table("test_with_id", data)
-    table.create_fts_index("text", with_position=False)
+    table.create_fts_index("text", with_position=False, use_tantivy=False)
    return table
@@ -1385,7 +1385,7 @@ def test_query_timeout(tmp_path):
        }
    )
    table = db.create_table("test", data)
-    table.create_fts_index("text")
+    table.create_fts_index("text", use_tantivy=False)
    with pytest.raises(Exception, match="Query timeout"):
        table.search().where("text = 'a'").to_list(timeout=timedelta(0))
@@ -26,8 +26,11 @@ from lancedb.rerankers import (
 )
 from lancedb.table import LanceTable
 # Tests rely on FTS index
 pytest.importorskip("lancedb.fts")
-def get_test_table(tmp_path):
+
 def get_test_table(tmp_path, use_tantivy):
    db = lancedb.connect(tmp_path)
    # Create a LanceDB table schema with a vector and a text column
    emb = EmbeddingFunctionRegistry.get_instance().get("test").create()
@@ -95,7 +98,7 @@ def get_test_table(tmp_path):
    )
    # Create a fts index
-    table.create_fts_index("text", replace=True)
+    table.create_fts_index("text", use_tantivy=use_tantivy, replace=True)
    return table, MyTable
@@ -205,8 +208,8 @@ def _run_test_reranker(reranker, table, query, query_vector, schema):
    assert len(result) == 20 and result == result_arrow
-def _run_test_hybrid_reranker(reranker, tmp_path):
+def _run_test_hybrid_reranker(reranker, tmp_path, use_tantivy):
-    table, schema = get_test_table(tmp_path)
+    table, schema = get_test_table(tmp_path, use_tantivy)
    # The default reranker
    result1 = (
        table.search(
@@ -282,7 +285,8 @@ def _run_test_hybrid_reranker(reranker, tmp_path):
    )
-def test_linear_combination(tmp_path):
+@pytest.mark.parametrize("use_tantivy", [True, False])
 def test_linear_combination(tmp_path, use_tantivy):
    reranker = LinearCombinationReranker()
    vector_results = pa.Table.from_pydict(
@@ -309,20 +313,22 @@ def test_linear_combination(tmp_path):
    assert "_score" not in combined_results.column_names
    assert "_relevance_score" in combined_results.column_names
-    _run_test_hybrid_reranker(reranker, tmp_path)
+    _run_test_hybrid_reranker(reranker, tmp_path, use_tantivy)
-def test_rrf_reranker(tmp_path):
+@pytest.mark.parametrize("use_tantivy", [True, False])
 def test_rrf_reranker(tmp_path, use_tantivy):
    reranker = RRFReranker()
-    _run_test_hybrid_reranker(reranker, tmp_path)
+    _run_test_hybrid_reranker(reranker, tmp_path, use_tantivy)
-def test_mrr_reranker(tmp_path):
+@pytest.mark.parametrize("use_tantivy", [True, False])
 def test_mrr_reranker(tmp_path, use_tantivy):
    reranker = MRRReranker()
-    _run_test_hybrid_reranker(reranker, tmp_path)
+    _run_test_hybrid_reranker(reranker, tmp_path, use_tantivy)
    # Test multi-vector part
-    table, schema = get_test_table(tmp_path)
+    table, schema = get_test_table(tmp_path, use_tantivy)
    query = "single player experience"
    rs1 = table.search(query, vector_column_name="vector").limit(10).with_row_id(True)
    rs2 = (
@@ -357,7 +363,7 @@ def test_rrf_reranker_distance():
    table = db.create_table("test", data)
    table.create_index(num_partitions=1, num_sub_vectors=2)
-    table.create_fts_index("text")
+    table.create_fts_index("text", use_tantivy=False)
    reranker = RRFReranker(return_score="all")
@@ -416,31 +422,35 @@ def test_rrf_reranker_distance():
@pytest.mark.skipif(
    os.environ.get("COHERE_API_KEY") is None, reason="COHERE_API_KEY not set"
 )
-def test_cohere_reranker(tmp_path):
+@pytest.mark.parametrize("use_tantivy", [True, False])
 def test_cohere_reranker(tmp_path, use_tantivy):
    pytest.importorskip("cohere")
    reranker = CohereReranker()
-    table, schema = get_test_table(tmp_path)
+    table, schema = get_test_table(tmp_path, use_tantivy)
    _run_test_reranker(reranker, table, "single player experience", None, schema)
-def test_cross_encoder_reranker(tmp_path):
+@pytest.mark.parametrize("use_tantivy", [True, False])
 def test_cross_encoder_reranker(tmp_path, use_tantivy):
    pytest.importorskip("sentence_transformers")
    reranker = CrossEncoderReranker()
-    table, schema = get_test_table(tmp_path)
+    table, schema = get_test_table(tmp_path, use_tantivy)
    _run_test_reranker(reranker, table, "single player experience", None, schema)
-def test_colbert_reranker(tmp_path):
+@pytest.mark.parametrize("use_tantivy", [True, False])
 def test_colbert_reranker(tmp_path, use_tantivy):
    pytest.importorskip("rerankers")
    reranker = ColbertReranker()
-    table, schema = get_test_table(tmp_path)
+    table, schema = get_test_table(tmp_path, use_tantivy)
    _run_test_reranker(reranker, table, "single player experience", None, schema)
-def test_answerdotai_reranker(tmp_path):
+@pytest.mark.parametrize("use_tantivy", [True, False])
 def test_answerdotai_reranker(tmp_path, use_tantivy):
    pytest.importorskip("rerankers")
    reranker = AnswerdotaiRerankers()
-    table, schema = get_test_table(tmp_path)
+    table, schema = get_test_table(tmp_path, use_tantivy)
    _run_test_reranker(reranker, table, "single player experience", None, schema)
@@ -449,9 +459,10 @@ def test_answerdotai_reranker(tmp_path):
    or os.environ.get("OPENAI_BASE_URL") is not None,
    reason="OPENAI_API_KEY not set",
 )
-def test_openai_reranker(tmp_path):
+@pytest.mark.parametrize("use_tantivy", [True, False])
 def test_openai_reranker(tmp_path, use_tantivy):
    pytest.importorskip("openai")
-    table, schema = get_test_table(tmp_path)
+    table, schema = get_test_table(tmp_path, use_tantivy)
    reranker = OpenaiReranker()
    _run_test_reranker(reranker, table, "single player experience", None, schema)
@@ -459,9 +470,10 @@ def test_openai_reranker(tmp_path):
@pytest.mark.skipif(
    os.environ.get("JINA_API_KEY") is None, reason="JINA_API_KEY not set"
 )
-def test_jina_reranker(tmp_path):
+@pytest.mark.parametrize("use_tantivy", [True, False])
 def test_jina_reranker(tmp_path, use_tantivy):
    pytest.importorskip("jina")
-    table, schema = get_test_table(tmp_path)
+    table, schema = get_test_table(tmp_path, use_tantivy)
    reranker = JinaReranker()
    _run_test_reranker(reranker, table, "single player experience", None, schema)
@@ -469,10 +481,11 @@ def test_jina_reranker(tmp_path):
@pytest.mark.skipif(
    os.environ.get("VOYAGE_API_KEY") is None, reason="VOYAGE_API_KEY not set"
 )
-def test_voyageai_reranker(tmp_path):
+@pytest.mark.parametrize("use_tantivy", [True, False])
 def test_voyageai_reranker(tmp_path, use_tantivy):
    pytest.importorskip("voyageai")
    reranker = VoyageAIReranker(model_name="rerank-2.5")
-    table, schema = get_test_table(tmp_path)
+    table, schema = get_test_table(tmp_path, use_tantivy)
    _run_test_reranker(reranker, table, "single player experience", None, schema)
@@ -491,7 +504,7 @@ def test_empty_result_reranker():
    # Create empty table with schema
    empty_table = db.create_table("empty_table", schema=schema, mode="overwrite")
-    empty_table.create_fts_index("text", replace=True)
+    empty_table.create_fts_index("text", use_tantivy=False, replace=True)
    for reranker in [
        CrossEncoderReranker(),
        # ColbertReranker(),
@@ -590,10 +603,11 @@ def test_empty_hybrid_result_reranker():
    assert "_rowid" in result.column_names
-def test_cross_encoder_reranker_return_all(tmp_path):
+@pytest.mark.parametrize("use_tantivy", [True, False])
 def test_cross_encoder_reranker_return_all(tmp_path, use_tantivy):
    pytest.importorskip("sentence_transformers")
    reranker = CrossEncoderReranker(return_score="all")
-    table, schema = get_test_table(tmp_path)
+    table, schema = get_test_table(tmp_path, use_tantivy)
    query = "single player experience"
    result = (
        table.search(query, query_type="hybrid", vector_column_name="vector")
@@ -242,8 +242,8 @@ def test_s3_dynamodb_sync(s3_bucket: str, commit_table: str, monkeypatch):
    # FTS indices should error since they are not supported yet.
    with pytest.raises(
-        ValueError,
+        NotImplementedError,
-        match="Tantivy-based FTS has been removed",
+        match="Full-text search is only supported on the local filesystem",
    ):
        table.create_fts_index("x", use_tantivy=True)
@@ -1948,6 +1948,7 @@ def setup_hybrid_search_table(db: DBConnection, embedding_func):
 def test_hybrid_search(tmp_db: DBConnection):
    # This test uses an FTS index
    pytest.importorskip("lancedb.fts")
    pytest.importorskip("lance")
    table, MyTable, emb = setup_hybrid_search_table(tmp_db, "test")
@@ -2018,6 +2019,7 @@ def test_hybrid_search(tmp_db: DBConnection):
 def test_hybrid_search_metric_type(tmp_db: DBConnection):
    # This test uses an FTS index
    pytest.importorskip("lancedb.fts")
    pytest.importorskip("lance")
    # Need to use nonnorm as the embedding function so l2 and dot results
@@ -1996,6 +1996,7 @@ tests = [
    { name = "pytest-mock" },
    { name = "pytz" },
    { name = "requests" },
    { name = "tantivy" },
 ]
 [package.metadata]
@@ -2049,6 +2050,7 @@ requires-dist = [
    { name = "sentence-transformers", marker = "extra == 'embeddings'", specifier = ">=2.2.0" },
    { name = "sentencepiece", marker = "extra == 'embeddings'", specifier = ">=0.1.99" },
    { name = "sentencepiece", marker = "extra == 'siglip'" },
    { name = "tantivy", marker = "extra == 'tests'", specifier = ">=0.20.0" },
    { name = "torch", marker = "extra == 'clip'" },
    { name = "torch", marker = "extra == 'embeddings'", specifier = ">=2.0.0" },
    { name = "torch", marker = "extra == 'siglip'" },
@@ -4777,6 +4779,44 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/40/44/4a5f08c96eb108af5cb50b41f76142f0afa346dfa99d5296fe7202a11854/tabulate-0.9.0-py3-none-any.whl", hash = "sha256:024ca478df22e9340661486f85298cff5f6dcdba14f3813e8830015b9ed1948f", size = 35252, upload-time = "2022-10-06T17:21:44.262Z" },
 ]
 [[package]]
 name = "tantivy"
 version = "0.25.1"
 source = { registry = "https://pypi.org/simple" }
 sdist = { url = "https://files.pythonhosted.org/packages/1b/f9/0cd3955d155d3e3ef74b864769514dd191e5dacba9f0beb7af2d914942ce/tantivy-0.25.1.tar.gz", hash = "sha256:68a3314699a7d18fcf338b52bae8ce46a97dde1128a3e47e33fa4db7f71f265e", size = 75120, upload-time = "2025-12-02T11:57:12.997Z" }
 wheels = [
    { url = "https://files.pythonhosted.org/packages/80/f7/2276bed3bed983ce2970dc70e3571f372587fe4f5f2bac1d6d617df08fa3/tantivy-0.25.1-cp310-cp310-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:7aa587a3dc9470584cacf5e3640fee93d12ec5f10109669c1f47c4e90820b958", size = 7638510, upload-time = "2025-12-02T11:56:08.754Z" },
    { url = "https://files.pythonhosted.org/packages/20/8c/078dc50570e243414356b05633f52fe544b85179281ffa9f1fe05d76bbd8/tantivy-0.25.1-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:56d77fe667595693d9fa5f0b4545776d84da9526bab0273b3fc6c7536dc0d8a2", size = 3932659, upload-time = "2025-12-02T11:56:10.621Z" },
    { url = "https://files.pythonhosted.org/packages/bd/dc/281c48436a1e3178b58fe463af314434fe0f3a4ec0c7588a362900e0c69e/tantivy-0.25.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5ba8c347cd48595fcaeabb28a909ebce92cf9c5e5c84ab5ba1136a280a307b5c", size = 4197430, upload-time = "2025-12-02T11:56:12.65Z" },
    { url = "https://files.pythonhosted.org/packages/7b/6c/61e6e0b0a350007d10a9b66a35703361d3345e14e7a7cc83494776b2a054/tantivy-0.25.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:aa7c4932e8fde1f09f2d46226060e827e197c2749abdc6129d73a752773adc38", size = 4184055, upload-time = "2025-12-02T11:56:14.647Z" },
    { url = "https://files.pythonhosted.org/packages/5f/fd/0eb059b12f0b6f91623a54a46448a83b7f716d08f3bca68c095d697b85da/tantivy-0.25.1-cp310-cp310-win_amd64.whl", hash = "sha256:afcfc5dbb0bcd5d24531f4471737ae0896f33528426ab0b1dad3e427c19120f6", size = 3424134, upload-time = "2025-12-02T11:56:16.242Z" },
    { url = "https://files.pythonhosted.org/packages/4e/7a/8a277f377e8a151fc0e71d4ffc1114aefb6e5e1c7dd609fed0955cf34ed8/tantivy-0.25.1-cp311-cp311-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:d363d7b4207d3a5aa7f0d212420df35bed18bdb6bae26a2a8bd57428388b7c29", size = 7637033, upload-time = "2025-12-02T11:56:18.104Z" },
    { url = "https://files.pythonhosted.org/packages/71/31/8b4acdedfc9f9a2d04b1340d07eef5213d6f151d1e18da0cb423e5f090d2/tantivy-0.25.1-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:8f4389cf1d889a1df7c5a3195806b4b56c37cee10d8a26faaa0dea35a867b5ff", size = 3932180, upload-time = "2025-12-02T11:56:19.833Z" },
    { url = "https://files.pythonhosted.org/packages/2f/dc/3e8499c21b4b9795e8f2fc54c68ce5b92905aaeadadaa56ecfa9180b11b1/tantivy-0.25.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:99864c09fc54652c3c2486cdf13f86cdc8200f4b481569cb291e095ca5d496e5", size = 4197620, upload-time = "2025-12-02T11:56:21.496Z" },
    { url = "https://files.pythonhosted.org/packages/f8/8e/f2ce62fffc811eb62bead92c7b23c2e218f817cbd54c4f3b802e03ba1438/tantivy-0.25.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:05abf37ddbc5063c575548be0d62931629c086bff7a5a1b67cf5a8f5ebf4cd8c", size = 4183794, upload-time = "2025-12-02T11:56:23.215Z" },
    { url = "https://files.pythonhosted.org/packages/de/64/24e2891b0ba3fd9853e10c296095a33b89bf3efd65e29da1ee5dae736040/tantivy-0.25.1-cp311-cp311-win_amd64.whl", hash = "sha256:f307ee8ad21597b0be23af83008fd66cfd5f958cdfa24ec0aaa08a38e86bbef4", size = 3424235, upload-time = "2025-12-02T11:56:25.172Z" },
    { url = "https://files.pythonhosted.org/packages/41/e7/6849c713ed0996c7628324c60512c4882006f0a62145e56c624a93407f90/tantivy-0.25.1-cp312-cp312-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:90fd919e5f611809f746560ecf36eb9be824dec62e21ae17a27243759edb9aa1", size = 7621494, upload-time = "2025-12-02T11:56:27.069Z" },
    { url = "https://files.pythonhosted.org/packages/c5/22/c3d8294600dc6e7fa350daef9ff337d3c06e132b81df727de9f7a50c692a/tantivy-0.25.1-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:4613c7cf6c23f3a97989819690a0f956d799354957de7a204abcc60083cebe02", size = 3925219, upload-time = "2025-12-02T11:56:29.403Z" },
    { url = "https://files.pythonhosted.org/packages/41/fc/cbb1df71dd44c9110eff4eaaeda9d44f2d06182fe0452193be20ddfba93f/tantivy-0.25.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c477bd20b4df804d57dfc5033431bef27cde605695ae141b03abbf6ebc069129", size = 4198699, upload-time = "2025-12-02T11:56:31.359Z" },
    { url = "https://files.pythonhosted.org/packages/47/4d/71abb78b774073c3ce12a4faa4351a9d910a71ffa3659526affba163873d/tantivy-0.25.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f9b1a1ba1113c523c7ff7b10f282d6c4074006f7ef8d71e1d973d51bf7291ddb", size = 4183585, upload-time = "2025-12-02T11:56:33.317Z" },
    { url = "https://files.pythonhosted.org/packages/be/16/3f00cd7ec458b92a0e977960af9ddfbeb762127d9acc68da9094a1fda556/tantivy-0.25.1-cp312-cp312-win_amd64.whl", hash = "sha256:9de0bafd3bd7ac9f8f82d53e17562e9db11a5af308fe5185c4bd86feaddbe4a6", size = 3424622, upload-time = "2025-12-02T11:56:34.788Z" },
    { url = "https://files.pythonhosted.org/packages/3d/25/73cfbcf1a8ea49be6c42817431cac46b70a119fe64da903fcc2d92b5b511/tantivy-0.25.1-cp313-cp313-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:f51ff7196c6f31719202080ed8372d5e3d51e92c749c032fb8234f012e99744c", size = 7622530, upload-time = "2025-12-02T11:56:36.839Z" },
    { url = "https://files.pythonhosted.org/packages/12/c8/c0d7591cdf4f7e7a9fc4da786d1ca8cd1aacffaa2be16ea6d401a8e4a566/tantivy-0.25.1-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:550e63321bfcacc003859f2fa29c1e8e56450807b3c9a501c1add27cfb9236d9", size = 3925637, upload-time = "2025-12-02T11:56:38.425Z" },
    { url = "https://files.pythonhosted.org/packages/3a/09/bedfc223bffec7641b417dd7ab071134b2ef8f8550e9b1fb6014657ef52e/tantivy-0.25.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fde31cc8d6e122faf7902aeea32bc008a429a6e8904e34d3468126a3ec01b016", size = 4197322, upload-time = "2025-12-02T11:56:40.411Z" },
    { url = "https://files.pythonhosted.org/packages/f5/f1/1fa5183500c8042200c9f2b840d34f5bbcfb434a1ee750e7132262d2a5c9/tantivy-0.25.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b11bd5a518b0be645320b47af8493f6a40c4f3234313e37adcf4534a564d27dd", size = 4183143, upload-time = "2025-12-02T11:56:42.048Z" },
    { url = "https://files.pythonhosted.org/packages/d5/74/a4c4f4eb95888ccb784da3b017aa0625ab1ac411bf5d022a9a797d9a2334/tantivy-0.25.1-cp313-cp313-win_amd64.whl", hash = "sha256:cc7fe88853e06b3251ee4fa42b7a2038727f850c8765bcc8167cfc73585dd24e", size = 3423491, upload-time = "2025-12-02T11:56:43.858Z" },
    { url = "https://files.pythonhosted.org/packages/8b/2f/581519492226f97d23bd0adc95dad991ebeaa73ea6abc8bff389a3096d9a/tantivy-0.25.1-cp313-cp313t-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:dae99e75b7eaa9bf5bd16ab106b416370f08c135aed0e117d62a3201cd1ffe36", size = 7610316, upload-time = "2025-12-02T11:56:45.927Z" },
    { url = "https://files.pythonhosted.org/packages/91/40/5d7bc315ab9e6a22c5572656e8ada1c836cfa96dccf533377504fbc3c9d9/tantivy-0.25.1-cp313-cp313t-macosx_10_12_x86_64.whl", hash = "sha256:506e9533c5ef4d3df43bad64ffecc0aa97c76e361ea610815dc3a20a9d6b30b3", size = 3919882, upload-time = "2025-12-02T11:56:48.469Z" },
    { url = "https://files.pythonhosted.org/packages/02/b9/e0ef2f57a6a72444cb66c2ffbc310ab33ffaace275f1c4b0319d84ea3f18/tantivy-0.25.1-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5dbd4f8f264dacbcc9dee542832da2173fd53deaaea03f082d95214f8b5ed6bc", size = 4196031, upload-time = "2025-12-02T11:56:50.151Z" },
    { url = "https://files.pythonhosted.org/packages/1e/02/bf3f8cacfd08642e14a73f7956a3fb95d58119132c98c121b9065a1f8615/tantivy-0.25.1-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:824c643ccb640dd9e35e00c5d5054ddf3323f56fe4219d57d428a9eeea13d22c", size = 4183437, upload-time = "2025-12-02T11:56:51.818Z" },
    { url = "https://files.pythonhosted.org/packages/9c/83/afa90e570198e2d1139dd567bec3c9cf44d8c54f63a649f16d711ede02f5/tantivy-0.25.1-cp313-cp313t-win_amd64.whl", hash = "sha256:09c987b840afcebac817836ac08407eff17272d8aa60ce6e291f89c81830221d", size = 3419409, upload-time = "2025-12-02T11:56:53.451Z" },
    { url = "https://files.pythonhosted.org/packages/ff/44/9f1d67aa5030f7eebc966c863d1316a510a971dd8bb45651df4acdfae9ed/tantivy-0.25.1-cp314-cp314-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:7f5d29ae85dd0f23df8d15b3e7b341d4f9eb5a446bbb9640df48ac1f6d9e0c6c", size = 7623723, upload-time = "2025-12-02T11:56:55.066Z" },
    { url = "https://files.pythonhosted.org/packages/db/30/6e085bd3ed9d12da3c91c185854abd70f9dfd35fb36a75ea98428d42c30b/tantivy-0.25.1-cp314-cp314-macosx_10_12_x86_64.whl", hash = "sha256:f2d2938fb69a74fc1bb36edfaf7f0d1596fa1264db0f377bda2195c58bcb6245", size = 3926243, upload-time = "2025-12-02T11:56:57.058Z" },
    { url = "https://files.pythonhosted.org/packages/32/f5/a00d65433430f51718e5cc6938df571765d7c4e03aedec5aef4ab567aa9b/tantivy-0.25.1-cp314-cp314-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4f5ff124c4802558e627091e780b362ca944169736caba5a372eef39a79d0ae0", size = 4207186, upload-time = "2025-12-02T11:56:58.803Z" },
    { url = "https://files.pythonhosted.org/packages/19/63/61bdb12fc95f2a7f77bd419a5149bfa9f28caa76cb569bf2b6b06e1d033e/tantivy-0.25.1-cp314-cp314-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:43b80ef62a340416139c93d19264e5f808da48e04f9305f1092b8ed22be0a5be", size = 4187312, upload-time = "2025-12-02T11:57:00.595Z" },
    { url = "https://files.pythonhosted.org/packages/b7/de/e39c0b01d59019bf5c38face8b81defbc4a68cebf5e0c53bcb2cd715a449/tantivy-0.25.1-cp314-cp314-win_amd64.whl", hash = "sha256:286b654f40c70c1e6b64b9bc7031ed0bf5c440f5bffeaeeee21a0ee6cc39f0e2", size = 3436535, upload-time = "2025-12-02T11:57:02.267Z" },
 ]
 [[package]]
 name = "threadpoolctl"
 version = "3.6.0"
@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.28.0-beta.9"
+version = "0.28.0-beta.8"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true
@@ -16,7 +16,7 @@ use crate::remote::retry::{ResolvedRetryConfig, RetryCounter};
 const REQUEST_ID_HEADER: HeaderName = HeaderName::from_static("x-request-id");
 /// Configuration for TLS/mTLS settings.
-#[derive(Clone, Debug)]
+#[derive(Clone, Debug, Default)]
 pub struct TlsConfig {
    /// Path to the client certificate file (PEM format)
    pub cert_file: Option<String>,
@@ -24,22 +24,10 @@ pub struct TlsConfig {
    pub key_file: Option<String>,
    /// Path to the CA certificate file for server verification (PEM format)
    pub ssl_ca_cert: Option<String>,
-    /// Whether to verify the hostname in the server's certificate.
+    /// Whether to verify the hostname in the server's certificate
    /// Defaults to `true`.
    pub assert_hostname: bool,
 }
 impl Default for TlsConfig {
    fn default() -> Self {
        Self {
            cert_file: None,
            key_file: None,
            ssl_ca_cert: None,
            assert_hostname: true,
        }
    }
 }
 /// Trait for providing custom headers for each request
 #[async_trait::async_trait]
 pub trait HeaderProvider: Send + Sync + std::fmt::Debug {
@@ -938,7 +926,7 @@ mod tests {
        assert!(config.cert_file.is_none());
        assert!(config.key_file.is_none());
        assert!(config.ssl_ca_cert.is_none());
-        assert!(config.assert_hostname);
+        assert!(!config.assert_hostname);
    }
    #[test]