fix small details

Closes #2191


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->

## Summary by CodeRabbit

- **Chores**
- Updated the required version of the pyarrow package to version 16 or
higher.
- Adjusted automated testing workflows to install pyarrow version 16 for
compatibility checks.

<!-- end of auto-generated comment: release notes by coderabbit.ai -->

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.14.1"
+current_version = "0.19.1-beta.1"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.
@@ -87,26 +87,11 @@ glob = "node/package.json"
 replace = "\"@lancedb/vectordb-linux-x64-gnu\": \"{new_version}\""
 search = "\"@lancedb/vectordb-linux-x64-gnu\": \"{current_version}\""
 
-[[tool.bumpversion.files]]
-glob = "node/package.json"
-replace = "\"@lancedb/vectordb-linux-arm64-musl\": \"{new_version}\""
-search = "\"@lancedb/vectordb-linux-arm64-musl\": \"{current_version}\""
-
-[[tool.bumpversion.files]]
-glob = "node/package.json"
-replace = "\"@lancedb/vectordb-linux-x64-musl\": \"{new_version}\""
-search = "\"@lancedb/vectordb-linux-x64-musl\": \"{current_version}\""
-
 [[tool.bumpversion.files]]
 glob = "node/package.json"
 replace = "\"@lancedb/vectordb-win32-x64-msvc\": \"{new_version}\""
 search = "\"@lancedb/vectordb-win32-x64-msvc\": \"{current_version}\""
 
-[[tool.bumpversion.files]]
-glob = "node/package.json"
-replace = "\"@lancedb/vectordb-win32-arm64-msvc\": \"{new_version}\""
-search = "\"@lancedb/vectordb-win32-arm64-msvc\": \"{current_version}\""
-
 # Cargo files
 # ------------
 [[tool.bumpversion.files]]

.cargo/config.toml

@@ -34,6 +34,10 @@ rustflags = ["-C", "target-cpu=haswell", "-C", "target-feature=+avx2,+fma,+f16c"
 [target.x86_64-unknown-linux-musl]
 rustflags = ["-C", "target-cpu=haswell", "-C", "target-feature=-crt-static,+avx2,+fma,+f16c"]
 
+[target.aarch64-unknown-linux-musl]
+linker = "aarch64-linux-musl-gcc"
+rustflags = ["-C", "target-feature=-crt-static"]
+
 [target.aarch64-apple-darwin]
 rustflags = ["-C", "target-cpu=apple-m1", "-C", "target-feature=+neon,+fp16,+fhm,+dotprod"]
 

.github/workflows/build_linux_wheel/action.yml

@@ -36,8 +36,7 @@ runs:
         args: ${{ inputs.args }}
         before-script-linux: |
           set -e
-          yum install -y openssl-devel \
+          curl -L https://github.com/protocolbuffers/protobuf/releases/download/v24.4/protoc-24.4-linux-$(uname -m).zip > /tmp/protoc.zip \
-            && curl -L https://github.com/protocolbuffers/protobuf/releases/download/v24.4/protoc-24.4-linux-$(uname -m).zip > /tmp/protoc.zip \
             && unzip /tmp/protoc.zip -d /usr/local \
             && rm /tmp/protoc.zip
     - name: Build Arm Manylinux Wheel
@@ -52,12 +51,7 @@ runs:
         args: ${{ inputs.args }}
         before-script-linux: |
           set -e
-          apt install -y unzip
+          yum install -y clang \
-          if [ $(uname -m) = "x86_64" ]; then
+            && curl -L https://github.com/protocolbuffers/protobuf/releases/download/v24.4/protoc-24.4-linux-aarch_64.zip > /tmp/protoc.zip \
-            PROTOC_ARCH="x86_64"
-          else
-            PROTOC_ARCH="aarch_64"
-          fi
-          curl -L https://github.com/protocolbuffers/protobuf/releases/download/v24.4/protoc-24.4-linux-$PROTOC_ARCH.zip > /tmp/protoc.zip \
             && unzip /tmp/protoc.zip -d /usr/local \
             && rm /tmp/protoc.zip

.github/workflows/build_mac_wheel/action.yml

@@ -20,7 +20,7 @@ runs:
       uses: PyO3/maturin-action@v1
       with:
         command: build
+        # TODO: pass through interpreter
         args: ${{ inputs.args }}
         docker-options: "-e PIP_EXTRA_INDEX_URL=https://pypi.fury.io/lancedb/"
         working-directory: python
-        interpreter: 3.${{ inputs.python-minor-version }}

.github/workflows/build_windows_wheel/action.yml

@@ -28,7 +28,7 @@ runs:
         args: ${{ inputs.args }}
         docker-options: "-e PIP_EXTRA_INDEX_URL=https://pypi.fury.io/lancedb/"
         working-directory: python
-    - uses: actions/upload-artifact@v3
+    - uses: actions/upload-artifact@v4
       with:
         name: windows-wheels
         path: python\target\wheels

.github/workflows/docs.yml

@@ -18,17 +18,24 @@ concurrency:
   group: "pages"
   cancel-in-progress: true
 
+env:
+  # This reduces the disk space needed for the build
+  RUSTFLAGS: "-C debuginfo=0"
+  # according to: https://matklad.github.io/2021/09/04/fast-rust-builds.html
+  # CI builds are faster with incremental disabled.
+  CARGO_INCREMENTAL: "0"
+
 jobs:
   # Single deploy job since we're just deploying
   build:
     environment:
       name: github-pages
       url: ${{ steps.deployment.outputs.page_url }}
-    runs-on: buildjet-8vcpu-ubuntu-2204
+    runs-on: ubuntu-24.04
     steps:
       - name: Checkout
         uses: actions/checkout@v4
-      - name: Install dependecies needed for ubuntu
+      - name: Install dependencies needed for ubuntu
         run: |
           sudo apt install -y protobuf-compiler libssl-dev
           rustup update && rustup default
@@ -38,6 +45,7 @@ jobs:
           python-version: "3.10"
           cache: "pip"
           cache-dependency-path: "docs/requirements.txt"
+      - uses: Swatinem/rust-cache@v2
       - name: Build Python
         working-directory: python
         run: |
@@ -49,7 +57,6 @@ jobs:
           node-version: 20
           cache: 'npm'
           cache-dependency-path: node/package-lock.json
-      - uses: Swatinem/rust-cache@v2
       - name: Install node dependencies
         working-directory: node
         run: |

.github/workflows/java-publish.yml

@@ -43,7 +43,7 @@ jobs:
       - uses: Swatinem/rust-cache@v2
       - uses: actions-rust-lang/setup-rust-toolchain@v1
         with:
-          toolchain: "1.79.0"
+          toolchain: "1.81.0"
           cache-workspaces: "./java/core/lancedb-jni"
           # Disable full debug symbol generation to speed up CI build and keep memory down
           # "1" means line tables only, which is useful for panic tracebacks.
@@ -97,7 +97,7 @@ jobs:
       - name: Dry run
         if: github.event_name == 'pull_request'
         run: |
-          mvn --batch-mode -DskipTests package
+          mvn --batch-mode -DskipTests -Drust.release.build=true package
       - name: Set github
         run: |
           git config --global user.email "LanceDB Github Runner"
@@ -108,7 +108,7 @@ jobs:
           echo "use-agent" >> ~/.gnupg/gpg.conf
           echo "pinentry-mode loopback" >> ~/.gnupg/gpg.conf
           export GPG_TTY=$(tty)
-          mvn --batch-mode -DskipTests -DpushChanges=false -Dgpg.passphrase=${{ secrets.GPG_PASSPHRASE }} deploy -P deploy-to-ossrh
+          mvn --batch-mode -DskipTests -Drust.release.build=true -DpushChanges=false -Dgpg.passphrase=${{ secrets.GPG_PASSPHRASE }} deploy -P deploy-to-ossrh
         env:
           SONATYPE_USER: ${{ secrets.SONATYPE_USER }}
           SONATYPE_TOKEN: ${{ secrets.SONATYPE_TOKEN }}

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

@@ -0,0 +1,31 @@
+name: Check license headers
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    paths:
+      - rust/**
+      - python/**
+      - nodejs/**
+      - java/**
+      - .github/workflows/license-header-check.yml
+jobs:
+  check-licenses:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out code
+        uses: actions/checkout@v4
+      - name: Install license-header-checker
+        working-directory: /tmp
+        run: |
+            curl -s https://raw.githubusercontent.com/lluissm/license-header-checker/master/install.sh | bash
+            mv /tmp/bin/license-header-checker /usr/local/bin/
+      - name: Check license headers (rust)
+        run: license-header-checker -a -v ./rust/license_header.txt ./ rs && [[ -z `git status -s` ]]
+      - name: Check license headers (python)
+        run: license-header-checker -a -v ./python/license_header.txt python py && [[ -z `git status -s` ]]
+      - name: Check license headers (typescript)
+        run: license-header-checker -a -v ./nodejs/license_header.txt nodejs ts && [[ -z `git status -s` ]]
+      - name: Check license headers (java)
+        run: license-header-checker -a -v ./nodejs/license_header.txt java java && [[ -z `git status -s` ]]

.github/workflows/make-release-commit.yml

@@ -43,7 +43,7 @@ on:
 jobs:
   make-release:
     # Creates tag and GH release. The GH release will trigger the build and release jobs.
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-24.04
     permissions:
       contents: write
     steps:
@@ -57,15 +57,14 @@ jobs:
           # trigger any workflows watching for new tags. See:
           # https://docs.github.com/en/actions/using-workflows/triggering-a-workflow#triggering-a-workflow-from-a-workflow
           token: ${{ secrets.LANCEDB_RELEASE_TOKEN }}
+      - name: Validate Lance dependency is at stable version
+        if: ${{ inputs.type == 'stable' }}
+        run: python ci/validate_stable_lance.py
       - name: Set git configs for bumpversion
         shell: bash
         run: |
           git config user.name 'Lance Release'
           git config user.email 'lance-dev@lancedb.com'
-      - name: Set up Python 3.11
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.11"
       - name: Bump Python version
         if: ${{ inputs.python }}
         working-directory: python

.github/workflows/nodejs.yml

@@ -106,6 +106,18 @@ jobs:
         python ci/mock_openai.py &
         cd nodejs/examples
         npm test
+    - name: Check docs
+      run: |
+        # We run this as part of the job because the binary needs to be built
+        # first to export the types of the native code.
+        set -e
+        npm ci
+        npm run docs
+        if ! git diff --exit-code; then
+          echo "Docs need to be updated"
+          echo "Run 'npm run docs', fix any warnings, and commit the changes."
+          exit 1
+        fi
   macos:
     timeout-minutes: 30
     runs-on: "macos-14"

.github/workflows/pypi-publish.yml

@@ -4,6 +4,11 @@ on:
   push:
     tags:
       - 'python-v*'
+  pull_request:
+    # This should trigger a dry run (we skip the final publish step)
+    paths:
+      - .github/workflows/pypi-publish.yml
+      - Cargo.toml # Change in dependency frequently breaks builds
 
 jobs:
   linux:
@@ -15,15 +20,21 @@ jobs:
           - platform: x86_64
             manylinux: "2_17"
             extra_args: ""
+            runner: ubuntu-22.04
           - platform: x86_64
             manylinux: "2_28"
             extra_args: "--features fp16kernels"
+            runner: ubuntu-22.04
           - platform: aarch64
-            manylinux: "2_24"
+            manylinux: "2_17"
             extra_args: ""
-          # We don't build fp16 kernels for aarch64, because it uses 
+            # For successful fat LTO builds, we need a large runner to avoid OOM errors.
-          # cross compilation image, which doesn't have a new enough compiler.
+            runner: ubuntu-2404-8x-arm64
-    runs-on: "ubuntu-22.04"
+          - platform: aarch64
+            manylinux: "2_28"
+            extra_args: "--features fp16kernels"
+            runner: ubuntu-2404-8x-arm64
+    runs-on: ${{ matrix.config.runner }}
     steps:
       - uses: actions/checkout@v4
         with:
@@ -40,6 +51,7 @@ jobs:
           arm-build: ${{ matrix.config.platform == 'aarch64' }}
           manylinux: ${{ matrix.config.manylinux }}
       - 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 }}
@@ -69,6 +81,7 @@ jobs:
           python-minor-version: 8
           args: "--release --strip --target ${{ matrix.config.target }} --features fp16kernels"
       - 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 }}
@@ -90,10 +103,12 @@ jobs:
           args: "--release --strip"
           vcpkg_token: ${{ secrets.VCPKG_GITHUB_PACKAGES }}
       - 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')
     runs-on: ubuntu-latest
     permissions:
       contents: write

.github/workflows/python.yml

@@ -13,6 +13,11 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
 
+env:
+  # Color output for pytest is off by default.
+  PYTEST_ADDOPTS: "--color=yes"
+  FORCE_COLOR: "1"
+
 jobs:
   lint:
     name: "Lint"
@@ -30,16 +35,17 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: "3.11"
+          python-version: "3.12"
       - name: Install ruff
         run: |
-          pip install ruff==0.5.4
+          pip install ruff==0.9.9
       - name: Format check
         run: ruff format --check .
       - name: Lint
         run: ruff check .
-  doctest:
+
-    name: "Doctest"
+  type-check:
+    name: "Type Check"
     timeout-minutes: 30
     runs-on: "ubuntu-22.04"
     defaults:
@@ -54,7 +60,36 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: "3.11"
+          python-version: "3.12"
+      - name: Install protobuf compiler
+        run: |
+          sudo apt update
+          sudo apt install -y protobuf-compiler
+          pip install toml
+      - name: Install dependencies
+        run: |
+          python ../ci/parse_requirements.py pyproject.toml --extras dev,tests,embeddings > requirements.txt
+          pip install -r requirements.txt
+      - name: Run pyright
+        run: pyright
+
+  doctest:
+    name: "Doctest"
+    timeout-minutes: 30
+    runs-on: "ubuntu-24.04"
+    defaults:
+      run:
+        shell: bash
+        working-directory: python
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          lfs: true
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
           cache: "pip"
       - name: Install protobuf
         run: |
@@ -75,8 +110,8 @@ jobs:
     timeout-minutes: 30
     strategy:
       matrix:
-        python-minor-version: ["9", "11"]
+        python-minor-version: ["9", "12"]
-    runs-on: "ubuntu-22.04"
+    runs-on: "ubuntu-24.04"
     defaults:
       run:
         shell: bash
@@ -101,6 +136,10 @@ jobs:
       - uses: ./.github/workflows/run_tests
         with:
           integration: true
+      - name: Test without pylance or pandas
+        run: |
+          pip uninstall -y pylance pandas
+          pytest -vv python/tests/test_table.py
       # Make sure wheels are not included in the Rust cache
       - name: Delete wheels
         run: rm -rf target/wheels
@@ -127,7 +166,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: "3.11"
+          python-version: "3.12"
       - uses: Swatinem/rust-cache@v2
         with:
           workspaces: python
@@ -157,7 +196,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: "3.11"
+          python-version: "3.12"
       - uses: Swatinem/rust-cache@v2
         with:
           workspaces: python
@@ -168,7 +207,7 @@ jobs:
         run: rm -rf target/wheels
   pydantic1x:
     timeout-minutes: 30
-    runs-on: "ubuntu-22.04"
+    runs-on: "ubuntu-24.04"
     defaults:
       run:
         shell: bash
@@ -189,6 +228,7 @@ jobs:
       - name: Install lancedb
         run: |
           pip install "pydantic<2"
+          pip install pyarrow==16
           pip install --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests]
           pip install tantivy
       - name: Run tests

.github/workflows/rust.yml

@@ -22,6 +22,7 @@ env:
   # "1" means line tables only, which is useful for panic tracebacks.
   RUSTFLAGS: "-C debuginfo=1"
   RUST_BACKTRACE: "1"
+  CARGO_INCREMENTAL: 0
 
 jobs:
   lint:
@@ -51,6 +52,33 @@ jobs:
       - name: Run clippy
         run: cargo clippy --workspace --tests --all-features -- -D warnings
 
+  build-no-lock:
+    runs-on: ubuntu-24.04
+    timeout-minutes: 30
+    env:
+      # Need up-to-date compilers for kernels
+      CC: clang
+      CXX: clang++
+    steps:
+      - uses: actions/checkout@v4
+      # Building without a lock file often requires the latest Rust version since downstream
+      # dependencies may have updated their minimum Rust version.
+      - uses: actions-rust-lang/setup-rust-toolchain@v1
+        with:
+          toolchain: "stable"
+      # Remove cargo.lock to force a fresh build
+      - name: Remove Cargo.lock
+        run: rm -f Cargo.lock
+      - uses: rui314/setup-mold@v1
+      - uses: Swatinem/rust-cache@v2
+      - name: Install dependencies
+        run: |
+          sudo apt update
+          sudo apt install -y protobuf-compiler libssl-dev
+      - name: Build all
+        run: |
+          cargo build --benches --all-features --tests
+
   linux:
     timeout-minutes: 30
     # To build all features, we need more disk space than is available
@@ -75,8 +103,11 @@ jobs:
           workspaces: rust
       - name: Install dependencies
         run: |
-          sudo apt update
+          # This shaves 2 minutes off this step in CI. This doesn't seem to be
+          # necessary in standard runners, but it is in the 4x runners.
+          sudo rm /var/lib/man-db/auto-update
           sudo apt install -y protobuf-compiler libssl-dev
+      - uses: rui314/setup-mold@v1
       - name: Make Swap
         run: |
           sudo fallocate -l 16G /swapfile
@@ -87,11 +118,11 @@ jobs:
         working-directory: .
         run: docker compose up --detach --wait
       - name: Build
-        run: cargo build --all-features
+        run: cargo build --all-features --tests --locked --examples
       - name: Run tests
-        run: cargo test --all-features
+        run: cargo test --all-features --locked
       - name: Run examples
-        run: cargo run --example simple
+        run: cargo run --example simple --locked
 
   macos:
     timeout-minutes: 30
@@ -115,129 +146,43 @@ jobs:
           workspaces: rust
       - name: Install dependencies
         run: brew install protobuf
-      - name: Build
-        run: cargo build --all-features
       - name: Run tests
-        # Run with everything except the integration tests.
+        run: |
-        run: cargo test --features remote,fp16kernels
+          # Don't run the s3 integration tests since docker isn't available
+          # on this image.
+          ALL_FEATURES=`cargo metadata --format-version=1 --no-deps \
+            | jq -r '.packages[] | .features | keys | .[]' \
+            | grep -v s3-test | sort | uniq | paste -s -d "," -`
+          cargo test --features $ALL_FEATURES --locked
 
   windows:
     runs-on: windows-2022
+    strategy:
+      matrix:
+        target:
+        - x86_64-pc-windows-msvc
+        - aarch64-pc-windows-msvc
+    defaults:
+      run:
+        working-directory: rust/lancedb
     steps:
       - uses: actions/checkout@v4
       - uses: Swatinem/rust-cache@v2
         with:
           workspaces: rust
       - name: Install Protoc v21.12
-        working-directory: C:\
+        run: choco install --no-progress protoc
+      - name: Build
         run: |
-          New-Item -Path 'C:\protoc' -ItemType Directory
+          rustup target add ${{ matrix.target }}
-          Set-Location C:\protoc
+          $env:VCPKG_ROOT = $env:VCPKG_INSTALLATION_ROOT
-          Invoke-WebRequest https://github.com/protocolbuffers/protobuf/releases/download/v21.12/protoc-21.12-win64.zip -OutFile C:\protoc\protoc.zip
+          cargo build --features remote --tests --locked --target ${{ matrix.target }}
-          7z x protoc.zip
-          Add-Content $env:GITHUB_PATH "C:\protoc\bin"
-        shell: powershell
       - name: Run tests
+        # Can only run tests when target matches host
+        if: ${{ matrix.target == 'x86_64-pc-windows-msvc' }}
         run: |
           $env:VCPKG_ROOT = $env:VCPKG_INSTALLATION_ROOT
-          cargo build
+          cargo test --features remote --locked
-          cargo test
-
-  windows-arm64:
-    runs-on: windows-4x-arm
-    steps:
-      - name: Install Git
-        run: |
-          Invoke-WebRequest -Uri "https://github.com/git-for-windows/git/releases/download/v2.44.0.windows.1/Git-2.44.0-64-bit.exe" -OutFile "git-installer.exe"
-          Start-Process -FilePath "git-installer.exe" -ArgumentList "/VERYSILENT", "/NORESTART" -Wait
-        shell: powershell
-      - name: Add Git to PATH
-        run: |
-          Add-Content $env:GITHUB_PATH "C:\Program Files\Git\bin"
-          $env:Path = [System.Environment]::GetEnvironmentVariable("Path","Machine") + ";" + [System.Environment]::GetEnvironmentVariable("Path","User")
-        shell: powershell
-      - name: Configure Git symlinks
-        run: git config --global core.symlinks true
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
-        with:
-          python-version: "3.13"
-      - name: Install Visual Studio Build Tools
-        run: |
-          Invoke-WebRequest -Uri "https://aka.ms/vs/17/release/vs_buildtools.exe" -OutFile "vs_buildtools.exe"
-          Start-Process -FilePath "vs_buildtools.exe" -ArgumentList "--quiet", "--wait", "--norestart", "--nocache", `
-            "--installPath", "C:\BuildTools", `
-            "--add", "Microsoft.VisualStudio.Component.VC.Tools.ARM64", `
-            "--add", "Microsoft.VisualStudio.Component.VC.Tools.x86.x64", `
-            "--add", "Microsoft.VisualStudio.Component.Windows11SDK.22621", `
-            "--add", "Microsoft.VisualStudio.Component.VC.ATL", `
-            "--add", "Microsoft.VisualStudio.Component.VC.ATLMFC", `
-            "--add", "Microsoft.VisualStudio.Component.VC.Llvm.Clang" -Wait
-        shell: powershell
-      - name: Add Visual Studio Build Tools to PATH
-        run: |
-          $vsPath = "C:\BuildTools\VC\Tools\MSVC"
-          $latestVersion = (Get-ChildItem $vsPath | Sort-Object {[version]$_.Name} -Descending)[0].Name
-          Add-Content $env:GITHUB_PATH "C:\BuildTools\VC\Tools\MSVC\$latestVersion\bin\Hostx64\arm64"
-          Add-Content $env:GITHUB_PATH "C:\BuildTools\VC\Tools\MSVC\$latestVersion\bin\Hostx64\x64"
-          Add-Content $env:GITHUB_PATH "C:\Program Files (x86)\Windows Kits\10\bin\10.0.22621.0\arm64"
-          Add-Content $env:GITHUB_PATH "C:\Program Files (x86)\Windows Kits\10\bin\10.0.22621.0\x64"
-          Add-Content $env:GITHUB_PATH "C:\BuildTools\VC\Tools\Llvm\x64\bin"
-
-          # Add MSVC runtime libraries to LIB
-          $env:LIB = "C:\BuildTools\VC\Tools\MSVC\$latestVersion\lib\arm64;" +
-                     "C:\Program Files (x86)\Windows Kits\10\Lib\10.0.22621.0\um\arm64;" +
-                     "C:\Program Files (x86)\Windows Kits\10\Lib\10.0.22621.0\ucrt\arm64"
-          Add-Content $env:GITHUB_ENV "LIB=$env:LIB"
-
-          # Add INCLUDE paths
-          $env:INCLUDE = "C:\BuildTools\VC\Tools\MSVC\$latestVersion\include;" +
-                        "C:\Program Files (x86)\Windows Kits\10\Include\10.0.22621.0\ucrt;" +
-                        "C:\Program Files (x86)\Windows Kits\10\Include\10.0.22621.0\um;" +
-                        "C:\Program Files (x86)\Windows Kits\10\Include\10.0.22621.0\shared"
-          Add-Content $env:GITHUB_ENV "INCLUDE=$env:INCLUDE"
-        shell: powershell
-      - name: Install Rust
-        run: |
-          Invoke-WebRequest https://win.rustup.rs/x86_64 -OutFile rustup-init.exe
-          .\rustup-init.exe -y --default-host aarch64-pc-windows-msvc
-        shell: powershell
-      - name: Add Rust to PATH
-        run: |
-          Add-Content $env:GITHUB_PATH "$env:USERPROFILE\.cargo\bin"
-        shell: powershell
-      - uses: Swatinem/rust-cache@v2
-        with:
-          workspaces: rust
-      - name: Install 7-Zip ARM
-        run: |
-          New-Item -Path 'C:\7zip' -ItemType Directory
-          Invoke-WebRequest https://7-zip.org/a/7z2408-arm64.exe -OutFile C:\7zip\7z-installer.exe
-          Start-Process -FilePath C:\7zip\7z-installer.exe -ArgumentList '/S' -Wait
-        shell: powershell
-      - name: Add 7-Zip to PATH
-        run: Add-Content $env:GITHUB_PATH "C:\Program Files\7-Zip"
-        shell: powershell
-      - name: Install Protoc v21.12
-        working-directory: C:\
-        run: |
-          if (Test-Path 'C:\protoc') {
-            Write-Host "Protoc directory exists, skipping installation"
-            return
-          }
-          New-Item -Path 'C:\protoc' -ItemType Directory
-          Set-Location C:\protoc
-          Invoke-WebRequest https://github.com/protocolbuffers/protobuf/releases/download/v21.12/protoc-21.12-win64.zip -OutFile C:\protoc\protoc.zip
-          & 'C:\Program Files\7-Zip\7z.exe' x protoc.zip
-        shell: powershell
-      - name: Add Protoc to PATH
-        run: Add-Content $env:GITHUB_PATH "C:\protoc\bin"
-        shell: powershell
-      - name: Run tests
-        run: |
-          $env:VCPKG_ROOT = $env:VCPKG_INSTALLATION_ROOT
-          cargo build --target aarch64-pc-windows-msvc
-          cargo test --target aarch64-pc-windows-msvc
 
   msrv:
     # Check the minimum supported Rust version

.gitignore

@@ -9,7 +9,6 @@ venv
 .vscode
 .zed
 rust/target
-rust/Cargo.lock
 
 site
 
@@ -42,5 +41,3 @@ dist
 target
 
 **/sccache.log
-
-Cargo.lock

.pre-commit-config.yaml

@@ -7,9 +7,15 @@ repos:
       - id: trailing-whitespace
   - repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: v0.2.2
+    rev: v0.9.9
     hooks:
       - id: ruff
+  # - repo: https://github.com/RobertCraigie/pyright-python
+  #   rev: v1.1.395
+  #   hooks:
+  #     - id: pyright
+  #       args: ["--project", "python"]
+  #       additional_dependencies: [pyarrow-stubs]
   - repo: local
     hooks:
       - id: local-biome-check

CONTRIBUTING.md

@@ -0,0 +1,78 @@
+# Contributing to LanceDB
+
+LanceDB is an open-source project and we welcome contributions from the community.
+This document outlines the process for contributing to LanceDB.
+
+## Reporting Issues
+
+If you encounter a bug or have a feature request, please open an issue on the
+[GitHub issue tracker](https://github.com/lancedb/lancedb).
+
+## Picking an issue
+
+We track issues on the GitHub issue tracker. If you are looking for something to
+work on, check the [good first issue](https://github.com/lancedb/lancedb/contribute) label. These issues are typically the best described and have the smallest scope.
+
+If there's an issue you are interested in working on, please leave a comment on the issue. This will help us avoid duplicate work. Additionally, if you have questions about the issue, please ask them in the issue comments. We are happy to provide guidance on how to approach the issue.
+
+## Configuring Git
+
+First, fork the repository on GitHub, then clone your fork:
+
+```bash
+git clone https://github.com/<username>/lancedb.git
+cd lancedb
+```
+
+Then add the main repository as a remote:
+
+```bash
+git remote add upstream https://github.com/lancedb/lancedb.git
+git fetch upstream
+```
+
+## Setting up your development environment
+
+We have development environments for Python, Typescript, and Java. Each environment has its own setup instructions.
+
+* [Python](python/CONTRIBUTING.md)
+* [Typescript](nodejs/CONTRIBUTING.md)
+<!-- TODO: add Java contributing guide -->
+* [Documentation](docs/README.md)
+
+
+## Best practices for pull requests
+
+For the best chance of having your pull request accepted, please follow these guidelines:
+
+1. Unit test all bug fixes and new features. Your code will not be merged if it
+   doesn't have tests.
+1. If you change the public API, update the documentation in the `docs` directory.
+1. Aim to minimize the number of changes in each pull request. Keep to solving
+   one problem at a time, when possible.
+1. Before marking a pull request ready-for-review, do a self review of your code.
+   Is it clear why you are making the changes? Are the changes easy to understand?
+1. Use [conventional commit messages](https://www.conventionalcommits.org/en/) as pull request titles. Examples:
+    * New feature: `feat: adding foo API`
+    * Bug fix: `fix: issue with foo API`
+    * Documentation change: `docs: adding foo API documentation`
+1. If your pull request is a work in progress, leave the pull request as a draft.
+   We will assume the pull request is ready for review when it is opened.
+1. When writing tests, test the error cases. Make sure they have understandable
+   error messages.
+
+## Project structure
+
+The core library is written in Rust. The Python, Typescript, and Java libraries
+are wrappers around the Rust library.
+
+* `src/lancedb`: Rust library source code
+* `python`: Python package source code
+* `nodejs`: Typescript package source code
+* `node`: **Deprecated** Typescript package source code
+* `java`: Java package source code
+* `docs`: Documentation source code
+
+## Release process
+
+For information on the release process, see: [release_process.md](release_process.md)

Cargo.toml

@@ -21,41 +21,55 @@ categories = ["database-implementations"]
 rust-version = "1.78.0"
 
 [workspace.dependencies]
-lance = { "version" = "=0.21.0", "features" = [
+lance = { "version" = "=0.27.0", "features" = ["dynamodb"], tag = "v0.27.0-beta.2", git="https://github.com/lancedb/lance.git" }
-    "dynamodb",
+lance-io = { version = "=0.27.0", tag = "v0.27.0-beta.2", git="https://github.com/lancedb/lance.git" }
-], git = "https://github.com/lancedb/lance.git", tag = "v0.21.0-beta.5" }
+lance-index = { version = "=0.27.0", tag = "v0.27.0-beta.2", git="https://github.com/lancedb/lance.git" }
-lance-io = { version = "=0.21.0", git = "https://github.com/lancedb/lance.git", tag = "v0.21.0-beta.5" }
+lance-linalg = { version = "=0.27.0", tag = "v0.27.0-beta.2", git="https://github.com/lancedb/lance.git" }
-lance-index = { version = "=0.21.0", git = "https://github.com/lancedb/lance.git", tag = "v0.21.0-beta.5" }
+lance-table = { version = "=0.27.0", tag = "v0.27.0-beta.2", git="https://github.com/lancedb/lance.git" }
-lance-linalg = { version = "=0.21.0", git = "https://github.com/lancedb/lance.git", tag = "v0.21.0-beta.5" }
+lance-testing = { version = "=0.27.0", tag = "v0.27.0-beta.2", git="https://github.com/lancedb/lance.git" }
-lance-table = { version = "=0.21.0", git = "https://github.com/lancedb/lance.git", tag = "v0.21.0-beta.5" }
+lance-datafusion = { version = "=0.27.0", tag = "v0.27.0-beta.2", git="https://github.com/lancedb/lance.git" }
-lance-testing = { version = "=0.21.0", git = "https://github.com/lancedb/lance.git", tag = "v0.21.0-beta.5" }
+lance-encoding = { version = "=0.27.0", tag = "v0.27.0-beta.2", git="https://github.com/lancedb/lance.git" }
-lance-datafusion = { version = "=0.21.0", git = "https://github.com/lancedb/lance.git", tag = "v0.21.0-beta.5" }
-lance-encoding = { version = "=0.21.0", git = "https://github.com/lancedb/lance.git", tag = "v0.21.0-beta.5" }
 # Note that this one does not include pyarrow
-arrow = { version = "53.2", optional = false }
+arrow = { version = "54.1", optional = false }
-arrow-array = "53.2"
+arrow-array = "54.1"
-arrow-data = "53.2"
+arrow-data = "54.1"
-arrow-ipc = "53.2"
+arrow-ipc = "54.1"
-arrow-ord = "53.2"
+arrow-ord = "54.1"
-arrow-schema = "53.2"
+arrow-schema = "54.1"
-arrow-arith = "53.2"
+arrow-arith = "54.1"
-arrow-cast = "53.2"
+arrow-cast = "54.1"
 async-trait = "0"
-chrono = "0.4.35"
+datafusion = { version = "46.0", default-features = false }
-datafusion-common = "42.0"
+datafusion-catalog = "46.0"
-datafusion-physical-plan = "42.0"
+datafusion-common = { version = "46.0", default-features = false }
-env_logger = "0.10"
+datafusion-execution = "46.0"
+datafusion-expr = "46.0"
+datafusion-physical-plan = "46.0"
+env_logger = "0.11"
 half = { "version" = "=2.4.1", default-features = false, features = [
     "num-traits",
 ] }
 futures = "0"
 log = "0.4"
-moka = { version = "0.11", features = ["future"] }
+moka = { version = "0.12", features = ["future"] }
-object_store = "0.10.2"
+object_store = "0.11.0"
 pin-project = "1.0.7"
-snafu = "0.7.4"
+snafu = "0.8"
 url = "2"
 num-traits = "0.2"
 rand = "0.8"
 regex = "1.10"
 lazy_static = "1"
+semver = "1.0.25"
+
+# Temporary pins to work around downstream issues
+# https://github.com/apache/arrow-rs/commit/2fddf85afcd20110ce783ed5b4cdeb82293da30b
+chrono = "=0.4.39"
+# https://github.com/RustCrypto/formats/issues/1684
+base64ct = "=1.6.0"
+
+# Workaround for: https://github.com/eira-fransham/crunchy/issues/13
+crunchy = "=0.2.2"
+
+# Workaround for: https://github.com/Lokathor/bytemuck/issues/306
+bytemuck_derive = ">=1.8.1, <1.9.0"

README.md

@@ -1,9 +1,17 @@
+<a href="https://cloud.lancedb.com" target="_blank">
+  <img src="https://github.com/user-attachments/assets/92dad0a2-2a37-4ce1-b783-0d1b4f30a00c" alt="LanceDB Cloud Public Beta" width="100%" style="max-width: 100%;">
+</a>
+
 <div align="center">
 <p align="center">
 
-<img width="275" alt="LanceDB Logo" src="https://github.com/lancedb/lancedb/assets/5846846/37d7c7ad-c2fd-4f56-9f16-fffb0d17c73a">
+<picture>
+  <source media="(prefers-color-scheme: dark)" srcset="https://github.com/user-attachments/assets/ac270358-333e-4bea-a132-acefaa94040e">
+  <source media="(prefers-color-scheme: light)" srcset="https://github.com/user-attachments/assets/b864d814-0d29-4784-8fd9-807297c758c0">
+  <img alt="LanceDB Logo" src="https://github.com/user-attachments/assets/b864d814-0d29-4784-8fd9-807297c758c0" width=300>
+</picture>
 
-**Developer-friendly, database for multimodal AI**
+**Search More, Manage Less**
 
 <a href='https://github.com/lancedb/vectordb-recipes/tree/main' target="_blank"><img alt='LanceDB' src='https://img.shields.io/badge/VectorDB_Recipes-100000?style=for-the-badge&logo=LanceDB&logoColor=white&labelColor=645cfb&color=645cfb'/></a>
 <a href='https://lancedb.github.io/lancedb/' target="_blank"><img alt='lancdb' src='https://img.shields.io/badge/DOCS-100000?style=for-the-badge&logo=lancdb&logoColor=white&labelColor=645cfb&color=645cfb'/></a>

ci/build_linux_artifacts_nodejs.sh

@@ -1,21 +0,0 @@
-#!/bin/bash
-set -e
-ARCH=${1:-x86_64}
-
-# We pass down the current user so that when we later mount the local files
-# into the container, the files are accessible by the current user.
-pushd ci/manylinux_node
-docker build \
-    -t lancedb-node-manylinux-$ARCH \
-    --build-arg="ARCH=$ARCH" \
-    --build-arg="DOCKER_USER=$(id -u)" \
-    --progress=plain \
-    .
-popd
-
-# We turn on memory swap to avoid OOM killer
-docker run \
-    -v $(pwd):/io -w /io \
-    --memory-swap=-1 \
-    lancedb-node-manylinux-$ARCH \
-    bash ci/manylinux_node/build_lancedb.sh $ARCH

ci/build_macos_artifacts_nodejs.sh

@@ -1,34 +0,0 @@
-# Builds the macOS artifacts (nodejs binaries).
-# Usage: ./ci/build_macos_artifacts_nodejs.sh [target]
-# Targets supported: x86_64-apple-darwin aarch64-apple-darwin
-set -e
-
-prebuild_rust() {
-    # Building here for the sake of easier debugging.
-    pushd rust/lancedb
-    echo "Building rust library for $1"
-    export RUST_BACKTRACE=1
-    cargo build --release --target $1
-    popd
-}
-
-build_node_binaries() {
-    pushd nodejs
-    echo "Building nodejs library for $1"
-    export RUST_TARGET=$1
-    npm run build-release
-    popd
-}
-
-if [ -n "$1" ]; then
-    targets=$1
-else
-    targets="x86_64-apple-darwin aarch64-apple-darwin"
-fi
-
-echo "Building artifacts for targets: $targets"
-for target in $targets
-    do
-    prebuild_rust $target
-    build_node_binaries $target
-done

ci/manylinux_node/Dockerfile

@@ -9,10 +9,6 @@ FROM quay.io/pypa/manylinux_2_28_${ARCH}
 ARG ARCH=x86_64
 ARG DOCKER_USER=default_user
 
-# Install static openssl
-COPY install_openssl.sh install_openssl.sh
-RUN ./install_openssl.sh ${ARCH} > /dev/null
-
 # Protobuf is also installed as root.
 COPY install_protobuf.sh install_protobuf.sh
 RUN ./install_protobuf.sh ${ARCH}

ci/manylinux_node/build_lancedb.sh

@@ -1,19 +0,0 @@
-#!/bin/bash
-# Builds the nodejs module for manylinux. Invoked by ci/build_linux_artifacts_nodejs.sh.
-set -e
-ARCH=${1:-x86_64}
-
-if [ "$ARCH" = "x86_64" ]; then
-    export OPENSSL_LIB_DIR=/usr/local/lib64/
-else
-    export OPENSSL_LIB_DIR=/usr/local/lib/
-fi
-export OPENSSL_STATIC=1
-export OPENSSL_INCLUDE_DIR=/usr/local/include/openssl
-
-#Alpine doesn't have .bashrc
-FILE=$HOME/.bashrc && test -f $FILE && source $FILE
-
-cd nodejs
-npm ci
-npm run build-release

ci/manylinux_node/build_vectordb.sh

@@ -4,14 +4,6 @@ set -e
 ARCH=${1:-x86_64}
 TARGET_TRIPLE=${2:-x86_64-unknown-linux-gnu}
 
-if [ "$ARCH" = "x86_64" ]; then
-    export OPENSSL_LIB_DIR=/usr/local/lib64/
-else
-    export OPENSSL_LIB_DIR=/usr/local/lib/
-fi
-export OPENSSL_STATIC=1
-export OPENSSL_INCLUDE_DIR=/usr/local/include/openssl
-
 #Alpine doesn't have .bashrc
 FILE=$HOME/.bashrc && test -f $FILE && source $FILE
 

ci/manylinux_node/install_openssl.sh

@@ -1,26 +0,0 @@
-#!/bin/bash
-# Builds openssl from source so we can statically link to it
-
-# this is to avoid the error we get with the system installation:
-# /usr/bin/ld: <library>: version node not found for symbol SSLeay@@OPENSSL_1.0.1
-# /usr/bin/ld: failed to set dynamic section sizes: Bad value
-set -e
-
-git clone -b OpenSSL_1_1_1v \
-    --single-branch \
-    https://github.com/openssl/openssl.git
-
-pushd openssl
-
-if [[ $1 == x86_64* ]]; then
-    ARCH=linux-x86_64
-else
-    # gnu target
-    ARCH=linux-aarch64
-fi
-
-./Configure no-shared $ARCH
-
-make
-
-make install

ci/parse_requirements.py

@@ -0,0 +1,41 @@
+import argparse
+import toml
+
+
+def parse_dependencies(pyproject_path, extras=None):
+    with open(pyproject_path, "r") as file:
+        pyproject = toml.load(file)
+
+    dependencies = pyproject.get("project", {}).get("dependencies", [])
+    for dependency in dependencies:
+        print(dependency)
+
+    optional_dependencies = pyproject.get("project", {}).get(
+        "optional-dependencies", {}
+    )
+
+    if extras:
+        for extra in extras.split(","):
+            for dep in optional_dependencies.get(extra, []):
+                print(dep)
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Generate requirements.txt from pyproject.toml"
+    )
+    parser.add_argument("path", type=str, help="Path to pyproject.toml")
+    parser.add_argument(
+        "--extras",
+        type=str,
+        help="Comma-separated list of extras to include",
+        default="",
+    )
+
+    args = parser.parse_args()
+
+    parse_dependencies(args.path, args.extras)
+
+
+if __name__ == "__main__":
+    main()

ci/sysroot-aarch64-pc-windows-msvc.sh

@@ -53,7 +53,7 @@ curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-42
 curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/149578fb3b621cdb61ee1813b9b3e791/463ad1b0783ebda908fd6c16a4abfe93.cab
 curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/5c986c4f393c6b09d5aec3b539e9fb4a/5a22e5cde814b041749fb271547f4dd5.cab
 
-# fwpuclnt.lib arm64rt.lib
+# dbghelp.lib fwpuclnt.lib arm64rt.lib
 curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/7a332420d812f7c1d41da865ae5a7c52/windows%20sdk%20desktop%20libs%20arm64-x86_en-us.msi
 curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/19de98ed4a79938d0045d19c047936b3/3e2f7be479e3679d700ce0782e4cc318.cab
 
@@ -98,7 +98,7 @@ find /usr/aarch64-pc-windows-msvc/usr/include -type f -exec sed -i -E 's/(#inclu
 # reason: https://developercommunity.visualstudio.com/t/libucrtlibstreamobj-error-lnk2001-unresolved-exter/1544787#T-ND1599818
 # I don't understand the 'correct' fix for this, arm64rt.lib is supposed to be the workaround
 
-(cd 'program files/windows kits/10/lib/10.0.26100.0/um/arm64' && cp advapi32.lib bcrypt.lib kernel32.lib ntdll.lib user32.lib uuid.lib ws2_32.lib userenv.lib cfgmgr32.lib runtimeobject.lib fwpuclnt.lib arm64rt.lib -t /usr/aarch64-pc-windows-msvc/usr/lib)
+(cd 'program files/windows kits/10/lib/10.0.26100.0/um/arm64' && cp advapi32.lib bcrypt.lib kernel32.lib ntdll.lib user32.lib uuid.lib ws2_32.lib userenv.lib cfgmgr32.lib runtimeobject.lib dbghelp.lib fwpuclnt.lib arm64rt.lib -t /usr/aarch64-pc-windows-msvc/usr/lib)
 
 (cd 'contents/vc/tools/msvc/14.16.27023/lib/arm64' && cp libcmt.lib libvcruntime.lib -t /usr/aarch64-pc-windows-msvc/usr/lib)
 

ci/validate_stable_lance.py

@@ -0,0 +1,34 @@
+import tomllib
+
+found_preview_lance = False
+
+with open("Cargo.toml", "rb") as f:
+    cargo_data = tomllib.load(f)
+
+    for name, dep in cargo_data["workspace"]["dependencies"].items():
+        if name == "lance" or name.startswith("lance-"):
+            if isinstance(dep, str):
+                version = dep
+            elif isinstance(dep, dict):
+                # Version doesn't have the beta tag in it, so we instead look
+                # at the git tag.
+                version = dep.get('tag', dep.get('version'))
+            else:
+                raise ValueError("Unexpected type for dependency: " + str(dep))
+
+            if "beta" in version:
+                found_preview_lance = True
+                print(f"Dependency '{name}' is a preview version: {version}")
+
+with open("python/pyproject.toml", "rb") as f:
+    py_proj_data = tomllib.load(f)
+
+    for dep in py_proj_data["project"]["dependencies"]:
+        if dep.startswith("pylance"):
+            if "b" in dep:
+                found_preview_lance = True
+                print(f"Dependency '{dep}' is a preview version")
+            break  # Only one pylance dependency
+
+if found_preview_lance:
+    raise ValueError("Found preview version of Lance in dependencies")

docs/README.md

@@ -2,43 +2,88 @@
 
 LanceDB docs are deployed to https://lancedb.github.io/lancedb/.
 
-Docs is built and deployed automatically by [Github Actions](.github/workflows/docs.yml)
+Docs is built and deployed automatically by [Github Actions](../.github/workflows/docs.yml)
 whenever a commit is pushed to the `main` branch. So it is possible for the docs to show
 unreleased features.
 
 ## Building the docs
 
 ### Setup
-1. Install LanceDB. From LanceDB repo root: `pip install -e python`
+1. Install LanceDB Python. See setup in [Python contributing guide](../python/CONTRIBUTING.md).
-2. Install dependencies. From LanceDB repo root: `pip install -r docs/requirements.txt`
+   Run `make develop` to install the Python package.
-3. Make sure you have node and npm setup
+2. Install documentation dependencies. From LanceDB repo root: `pip install -r docs/requirements.txt`
-4. Make sure protobuf and libssl are installed
 
-### Building node module and create markdown files
+### Preview the docs
 
-See [Javascript docs README](./src/javascript/README.md)
+```shell
-
-### Build docs
-From LanceDB repo root:
-
-Run: `PYTHONPATH=. mkdocs build -f docs/mkdocs.yml`
-
-If successful, you should see a `docs/site` directory that you can verify locally.
-
-### Run local server
-
-You can run a local server to test the docs prior to deployment by navigating to the `docs` directory and running the following command:
-
-```bash
 cd docs
 mkdocs serve
 ```
 
-### Run doctest for typescript example
+If you want to just generate the HTML files:
 
-```bash
+```shell
-cd lancedb/docs
+PYTHONPATH=. mkdocs build -f docs/mkdocs.yml
-npm i
+```
-npm run build
+
-npm run all
+If successful, you should see a `docs/site` directory that you can verify locally.
+
+## Adding examples
+
+To make sure examples are correct, we put examples in test files so they can be
+run as part of our test suites.
+
+You can see the tests are at:
+
+* Python: `python/python/tests/docs`
+* Typescript: `nodejs/examples/`
+
+### Checking python examples
+
+```shell
+cd python
+pytest -vv python/tests/docs
+```
+
+### Checking typescript examples
+
+The `@lancedb/lancedb` package must be built before running the tests:
+
+```shell
+pushd nodejs
+npm ci
+npm run build
+popd
+```
+
+Then you can run the examples by going to the `nodejs/examples` directory and
+running the tests like a normal npm package:
+
+```shell
+pushd nodejs/examples
+npm ci
+npm test
+popd
+```
+
+## API documentation
+
+### Python
+
+The Python API documentation is organized based on the file `docs/src/python/python.md`.
+We manually add entries there so we can control the organization of the reference page.
+**However, this means any new types must be manually added to the file.** No additional
+steps are needed to generate the API documentation.
+
+### Typescript
+
+The typescript API documentation is generated from the typescript source code using [typedoc](https://typedoc.org/).
+
+When new APIs are added, you must manually re-run the typedoc command to update the API documentation.
+The new files should be checked into the repository.
+
+```shell
+pushd nodejs
+npm run docs
+popd
 ```

docs/mkdocs.yml

@@ -4,6 +4,9 @@ repo_url: https://github.com/lancedb/lancedb
 edit_uri: https://github.com/lancedb/lancedb/tree/main/docs/src
 repo_name: lancedb/lancedb
 docs_dir: src
+watch:
+  - src
+  - ../python/python
 
 theme:
   name: "material"
@@ -63,6 +66,7 @@ plugins:
             - https://arrow.apache.org/docs/objects.inv
             - https://pandas.pydata.org/docs/objects.inv
             - https://lancedb.github.io/lance/objects.inv
+            - https://docs.pydantic.dev/latest/objects.inv
   - mkdocs-jupyter
   - render_swagger:
       allow_arbitrary_locations: true
@@ -101,7 +105,8 @@ markdown_extensions:
 nav:
   - Home:
       - LanceDB: index.md
-      - 🏃🏼‍♂️ Quick start: basic.md
+      - 👉 Quickstart: quickstart.md
+      - 🏃🏼‍♂️ Basic Usage: basic.md
       - 📚 Concepts:
           - Vector search: concepts/vector_search.md
           - Indexing:
@@ -120,6 +125,9 @@ nav:
               - Overview: hybrid_search/hybrid_search.md
               - Comparing Rerankers: hybrid_search/eval.md
               - Airbnb financial data example: notebooks/hybrid_search.ipynb
+          - Late interaction with MultiVector search:
+              - Overview: guides/multi-vector.md
+              - Example: notebooks/Multivector_on_LanceDB.ipynb
           - RAG:
               - Vanilla RAG: rag/vanilla_rag.md
               - Multi-head RAG: rag/multi_head_rag.md
@@ -146,7 +154,9 @@ nav:
               - Building Custom Rerankers: reranking/custom_reranker.md
               - Example: notebooks/lancedb_reranking.ipynb
           - Filtering: sql.md
-          - Versioning & Reproducibility: notebooks/reproducibility.ipynb
+          - Versioning & Reproducibility:
+              - sync API: notebooks/reproducibility.ipynb
+              - async API: notebooks/reproducibility_async.ipynb
           - Configuring Storage: guides/storage.md
           - Migration Guide: migration.md
           - Tuning retrieval performance:
@@ -176,6 +186,7 @@ nav:
                   - Imagebind embeddings: embeddings/available_embedding_models/multimodal_embedding_functions/imagebind_embedding.md
                   - Jina Embeddings: embeddings/available_embedding_models/multimodal_embedding_functions/jina_multimodal_embedding.md
           - User-defined embedding functions: embeddings/custom_embedding_function.md
+          - Variables and secrets: embeddings/variables_and_secrets.md
           - "Example: Multi-lingual semantic search": notebooks/multi_lingual_example.ipynb
           - "Example: MultiModal CLIP Embeddings": notebooks/DisappearingEmbeddingFunction.ipynb
       - 🔌 Integrations:
@@ -226,15 +237,10 @@ nav:
           - 👾 JavaScript (vectordb): javascript/modules.md
           - 👾 JavaScript (lancedb): js/globals.md
           - 🦀 Rust: https://docs.rs/lancedb/latest/lancedb/
-      - ☁️ LanceDB Cloud:
-          - Overview: cloud/index.md
-          - API reference:
-              - 🐍 Python: python/saas-python.md
-              - 👾 JavaScript: javascript/modules.md
-              - REST API: cloud/rest.md
-          - FAQs: cloud/cloud_faq.md
 
-  - Quick start: basic.md
+  - Getting Started:
+      - Quickstart: quickstart.md
+      - Basic Usage: basic.md
   - Concepts:
       - Vector search: concepts/vector_search.md
       - Indexing:
@@ -253,6 +259,9 @@ nav:
           - Overview: hybrid_search/hybrid_search.md
           - Comparing Rerankers: hybrid_search/eval.md
           - Airbnb financial data example: notebooks/hybrid_search.ipynb
+      - Late interaction with MultiVector search:
+          - Overview: guides/multi-vector.md
+          - Document search Example: notebooks/Multivector_on_LanceDB.ipynb
       - RAG:
           - Vanilla RAG: rag/vanilla_rag.md
           - Multi-head RAG: rag/multi_head_rag.md
@@ -278,7 +287,9 @@ nav:
           - Building Custom Rerankers: reranking/custom_reranker.md
           - Example: notebooks/lancedb_reranking.ipynb
       - Filtering: sql.md
-      - Versioning & Reproducibility: notebooks/reproducibility.ipynb
+      - Versioning & Reproducibility:
+          - sync API: notebooks/reproducibility.ipynb
+          - async API: notebooks/reproducibility_async.ipynb
       - Configuring Storage: guides/storage.md
       - Migration Guide: migration.md
       - Tuning retrieval performance:
@@ -307,6 +318,7 @@ nav:
               - Imagebind embeddings: embeddings/available_embedding_models/multimodal_embedding_functions/imagebind_embedding.md
               - Jina Embeddings: embeddings/available_embedding_models/multimodal_embedding_functions/jina_multimodal_embedding.md
       - User-defined embedding functions: embeddings/custom_embedding_function.md
+      - Variables and secrets: embeddings/variables_and_secrets.md
       - "Example: Multi-lingual semantic search": notebooks/multi_lingual_example.ipynb
       - "Example: MultiModal CLIP Embeddings": notebooks/DisappearingEmbeddingFunction.ipynb
   - Integrations:
@@ -353,13 +365,6 @@ nav:
       - Javascript (vectordb): javascript/modules.md
       - Javascript (lancedb): js/globals.md
       - Rust: https://docs.rs/lancedb/latest/lancedb/index.html
-  - LanceDB Cloud:
-      - Overview: cloud/index.md
-      - API reference:
-          - 🐍 Python: python/saas-python.md
-          - 👾 JavaScript: javascript/modules.md
-          - REST API: cloud/rest.md
-      - FAQs: cloud/cloud_faq.md
 
 extra_css:
   - styles/global.css
@@ -367,6 +372,7 @@ extra_css:
 
 extra_javascript:
   - "extra_js/init_ask_ai_widget.js"
+  - "extra_js/reo.js"
 
 extra:
   analytics:

docs/openapi.yml

@@ -38,6 +38,13 @@ components:
       required: true
       schema:
         type: string
+    index_name:
+      name: index_name
+      in: path
+      description: name of the index
+      required: true
+      schema:
+        type: string
   responses:
     invalid_request:
       description: Invalid request
@@ -164,7 +171,7 @@ paths:
                 distance_type:
                   type: string
                   description: |
-                    The distance metric to use for search. L2, Cosine, Dot and Hamming are supported. Default is L2.
+                    The distance metric to use for search. l2, Cosine, Dot and Hamming are supported. Default is l2.
                 bypass_vector_index:
                   type: boolean
                   description: |
@@ -443,7 +450,7 @@ paths:
                   type: string
                   nullable: false
                   description: |
-                    The metric type to use for the index. L2, Cosine, Dot are supported.
+                    The metric type to use for the index. l2, Cosine, Dot are supported.
                 index_type:
                   type: string
       responses:
@@ -485,3 +492,22 @@ paths:
           $ref: "#/components/responses/unauthorized"
         "404":
           $ref: "#/components/responses/not_found"
+  /v1/table/{name}/index/{index_name}/drop/:
+    post:
+      description: Drop an index from the table
+      tags:
+        - Tables
+      summary: Drop an index from the table
+      operationId: dropIndex
+      parameters:
+        - $ref: "#/components/parameters/table_name"
+        - $ref: "#/components/parameters/index_name"
+      responses:
+        "200":
+          description: Index successfully dropped
+        "400":
+          $ref: "#/components/responses/invalid_request"
+        "401":
+          $ref: "#/components/responses/unauthorized"
+        "404":
+          $ref: "#/components/responses/not_found"

docs/src/ann_indexes.md

@@ -18,24 +18,23 @@ See the [indexing](concepts/index_ivfpq.md) concepts guide for more information
 Lance supports `IVF_PQ` index type by default.
 
 === "Python"
+    === "Sync API"
 
         Creating indexes is done via the [create_index](https://lancedb.github.io/lancedb/python/#lancedb.table.LanceTable.create_index) method.
 
         ```python
-    import lancedb
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-lancedb"
-    import numpy as np
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-numpy"
-    uri = "data/sample-lancedb"
+        --8<-- "python/python/tests/docs/test_guide_index.py:create_ann_index"
-    db = lancedb.connect(uri)
+        ```
+    === "Async API"
+        Creating indexes is done via the [create_index](https://lancedb.github.io/lancedb/python/#lancedb.table.LanceTable.create_index) method.
 
-    # Create 10,000 sample vectors
+        ```python
-    data = [{"vector": row, "item": f"item {i}"}
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-lancedb"
-        for i, row in enumerate(np.random.random((10_000, 1536)).astype('float32'))]
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-numpy"
-
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-lancedb-ivfpq"
-    # Add the vectors to a table
+        --8<-- "python/python/tests/docs/test_guide_index.py:create_ann_index_async"
-    tbl = db.create_table("my_vectors", data=data)
-
-    # Create and train the index - you need to have enough data in the table for an effective training step
-    tbl.create_index(num_partitions=256, num_sub_vectors=96)
         ```
 
 === "TypeScript"
@@ -70,7 +69,7 @@ Lance supports `IVF_PQ` index type by default.
 
 The following IVF_PQ paramters can be specified:
 
-- **distance_type**: The distance metric to use. By default it uses euclidean distance "`L2`".
+- **distance_type**: The distance metric to use. By default it uses euclidean distance "`l2`".
   We also support "cosine" and "dot" distance as well.
 - **num_partitions**: The number of partitions in the index. The default is the square root
   of the number of rows.
@@ -127,6 +126,8 @@ You can specify the GPU device to train IVF partitions via
         accelerator="mps"
     )
     ```
+!!! note
+    GPU based indexing is not yet supported with our asynchronous client.
     
 Troubleshooting:
 
@@ -152,13 +153,15 @@ There are a couple of parameters that can be used to fine-tune the search:
 
 
 === "Python"
+    === "Sync API"
 
         ```python
-    tbl.search(np.random.random((1536))) \
+        --8<-- "python/python/tests/docs/test_guide_index.py:vector_search"
-        .limit(2) \
+        ```
-        .nprobes(20) \
+    === "Async API"
-        .refine_factor(10) \
+
-        .to_pandas()
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_index.py:vector_search_async"
         ```
 
     ```text
@@ -196,9 +199,15 @@ The search will return the data requested in addition to the distance of each it
 You can further filter the elements returned by a search using a where clause.
 
 === "Python"
+    === "Sync API"
 
         ```python
-    tbl.search(np.random.random((1536))).where("item != 'item 1141'").to_pandas()
+        --8<-- "python/python/tests/docs/test_guide_index.py:vector_search_with_filter"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_index.py:vector_search_async_with_filter"
         ```
 
 === "TypeScript"
@@ -221,10 +230,16 @@ You can select the columns returned by the query using a select clause.
 
 === "Python"
 
-    ```python
+    === "Sync API"
-    tbl.search(np.random.random((1536))).select(["vector"]).to_pandas()
-    ```
 
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_index.py:vector_search_with_select"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_index.py:vector_search_async_with_select"
+        ```
 
     ```text
                                                 vector _distance

docs/src/ann_indexes.ts

@@ -3,6 +3,7 @@ import * as vectordb from "vectordb";
 // --8<-- [end:import]
 
 (async () => {
+  console.log("ann_indexes.ts: start");
   // --8<-- [start:ingest]
   const db = await vectordb.connect("data/sample-lancedb");
 
@@ -49,5 +50,5 @@ import * as vectordb from "vectordb";
     .execute();
   // --8<-- [end:search3]
 
-  console.log("Ann indexes: done");
+  console.log("ann_indexes.ts: done");
 })();

docs/src/basic.md

@@ -1,4 +1,4 @@
-# Quick start
+# Basic Usage
 
 !!! info "LanceDB can be run in a number of ways:"
 
@@ -133,11 +133,20 @@ recommend switching to stable releases.
 ## Connect to a database
 
 === "Python"
+    === "Sync API"
 
         ```python
         --8<-- "python/python/tests/docs/test_basic.py:imports"
-    --8<-- "python/python/tests/docs/test_basic.py:connect"
 
+        --8<-- "python/python/tests/docs/test_basic.py:set_uri"
+        --8<-- "python/python/tests/docs/test_basic.py:connect"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_basic.py:imports"
+
+        --8<-- "python/python/tests/docs/test_basic.py:set_uri"
         --8<-- "python/python/tests/docs/test_basic.py:connect_async"
         ```
 
@@ -183,19 +192,31 @@ table.
 
 === "Python"
 
-    ```python
-    --8<-- "python/python/tests/docs/test_basic.py:create_table"
-    --8<-- "python/python/tests/docs/test_basic.py:create_table_async"
-    ```
-
     If the table already exists, LanceDB will raise an error by default.
     If you want to overwrite the table, you can pass in `mode="overwrite"`
     to the `create_table` method.
 
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_basic.py:create_table"
+        ```
+
         You can also pass in a pandas DataFrame directly:
 
         ```python
         --8<-- "python/python/tests/docs/test_basic.py:create_table_pandas"
+        ```
+
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_basic.py:create_table_async"
+        ```
+
+        You can also pass in a pandas DataFrame directly:
+
+        ```python
         --8<-- "python/python/tests/docs/test_basic.py:create_table_async_pandas"
         ```
 
@@ -247,8 +268,14 @@ similar to a `CREATE TABLE` statement in SQL.
 
 === "Python"
 
+    === "Sync API"
+
         ```python
         --8<-- "python/python/tests/docs/test_basic.py:create_empty_table"
+        ```
+    === "Async API"
+
+        ```python
         --8<-- "python/python/tests/docs/test_basic.py:create_empty_table_async"
         ```
 
@@ -281,8 +308,14 @@ Once created, you can open a table as follows:
 
 === "Python"
 
+    === "Sync API"
+
         ```python
         --8<-- "python/python/tests/docs/test_basic.py:open_table"
+        ```
+    === "Async API"
+
+        ```python
         --8<-- "python/python/tests/docs/test_basic.py:open_table_async"
         ```
 
@@ -310,8 +343,14 @@ If you forget the name of your table, you can always get a listing of all table
 
 === "Python"
 
+    === "Sync API"
+
         ```python
         --8<-- "python/python/tests/docs/test_basic.py:table_names"
+        ```
+    === "Async API"
+
+        ```python
         --8<-- "python/python/tests/docs/test_basic.py:table_names_async"
         ```
 
@@ -340,8 +379,14 @@ After a table has been created, you can always add more data to it as follows:
 
 === "Python"
 
+    === "Sync API"
+
         ```python
         --8<-- "python/python/tests/docs/test_basic.py:add_data"
+        ```
+    === "Async API"
+
+        ```python
         --8<-- "python/python/tests/docs/test_basic.py:add_data_async"
         ```
 
@@ -370,8 +415,14 @@ Once you've embedded the query, you can find its nearest neighbors as follows:
 
 === "Python"
 
+    === "Sync API"
+
         ```python
         --8<-- "python/python/tests/docs/test_basic.py:vector_search"
+        ```
+    === "Async API"
+
+        ```python
         --8<-- "python/python/tests/docs/test_basic.py:vector_search_async"
         ```
 
@@ -412,8 +463,14 @@ LanceDB allows you to create an ANN index on a table as follows:
 
 === "Python"
 
-    ```py
+    === "Sync API"
+
+        ```python
         --8<-- "python/python/tests/docs/test_basic.py:create_index"
+        ```
+    === "Async API"
+
+        ```python
         --8<-- "python/python/tests/docs/test_basic.py:create_index_async"
         ```
 
@@ -451,8 +508,14 @@ This can delete any number of rows that match the filter.
 
 === "Python"
 
+    === "Sync API"
+
         ```python
         --8<-- "python/python/tests/docs/test_basic.py:delete_rows"
+        ```
+    === "Async API"
+
+        ```python
         --8<-- "python/python/tests/docs/test_basic.py:delete_rows_async"
         ```
 
@@ -483,7 +546,10 @@ simple or complex as needed. To see what expressions are supported, see the
 
 === "Python"
 
+    === "Sync API"
         Read more: [lancedb.table.Table.delete][]
+    === "Async API"
+        Read more: [lancedb.table.AsyncTable.delete][]
 
 === "Typescript[^1]"
 
@@ -505,8 +571,14 @@ Use the `drop_table()` method on the database to remove a table.
 
 === "Python"
 
+    === "Sync API"
+
         ```python
         --8<-- "python/python/tests/docs/test_basic.py:drop_table"
+        ```
+    === "Async API"
+
+        ```python
         --8<-- "python/python/tests/docs/test_basic.py:drop_table_async"
         ```
 
@@ -543,10 +615,17 @@ You can use the embedding API when working with embedding models. It automatical
 
 === "Python"
 
+    === "Sync API"
+
         ```python
         --8<-- "python/python/tests/docs/test_embeddings_optional.py:imports"
+
         --8<-- "python/python/tests/docs/test_embeddings_optional.py:openai_embeddings"
         ```
+    === "Async API"
+
+        Coming soon to the async API.
+        https://github.com/lancedb/lancedb/issues/1938
 
 === "Typescript[^1]"
 

docs/src/basic_legacy.ts

@@ -107,7 +107,6 @@ const example = async () => {
   // --8<-- [start:search]
   const query = await tbl.search([100, 100]).limit(2).execute();
   // --8<-- [end:search]
-  console.log(query);
 
   // --8<-- [start:delete]
   await tbl.delete('item = "fizz"');
@@ -119,8 +118,9 @@ const example = async () => {
 };
 
 async function main() {
+  console.log("basic_legacy.ts: start");
   await example();
-  console.log("Basic example: done");
+  console.log("basic_legacy.ts: done");
 }
 
 main();

docs/src/cloud/index.md

@@ -2,7 +2,7 @@
 
 LanceDB Cloud is a SaaS (software-as-a-service) solution that runs serverless in the cloud, clearly separating storage from compute. It's designed to be highly scalable without breaking the bank. LanceDB Cloud is currently in private beta with general availability coming soon, but you can apply for early access with the private beta release by signing up below.
 
-[Try out LanceDB Cloud](https://noteforms.com/forms/lancedb-mailing-list-cloud-kty1o5?notionforms=1&utm_source=notionforms){ .md-button .md-button--primary }
+[Try out LanceDB Cloud (Public Beta)](https://cloud.lancedb.com){ .md-button .md-button--primary }
 
 ## Architecture
 

docs/src/concepts/index_hnsw.md

@@ -7,7 +7,7 @@ Approximate Nearest Neighbor (ANN) search is a method for finding data points ne
 There are three main types of ANN search algorithms:
 
 * **Tree-based search algorithms**: Use a tree structure to organize and store data points.
-* * **Hash-based search algorithms**: Use a specialized geometric hash table to store and manage data points. These algorithms typically focus on theoretical guarantees, and don't usually perform as well as the other approaches in practice.
+* **Hash-based search algorithms**: Use a specialized geometric hash table to store and manage data points. These algorithms typically focus on theoretical guarantees, and don't usually perform as well as the other approaches in practice.
 * **Graph-based search algorithms**: Use a graph structure to store data points, which can be a bit complex. 
 
 HNSW is a graph-based algorithm. All graph-based search algorithms rely on the idea of a k-nearest neighbor (or k-approximate nearest neighbor) graph, which we outline below.  
@@ -59,7 +59,7 @@ Then the greedy search routine operates as follows:
 
 There are three key parameters to set when constructing an HNSW index:
 
-* `metric`: Use an `L2` euclidean distance metric. We also support `dot` and `cosine` distance.
+* `metric`: Use an `l2` euclidean distance metric. We also support `dot` and `cosine` distance.
 * `m`: The number of neighbors to select for each vector in the HNSW graph.
 * `ef_construction`: The number of candidates to evaluate during the construction of the HNSW graph.
 

docs/src/concepts/index_ivfpq.md

@@ -47,7 +47,7 @@ We can combine the above concepts to understand how to build and query an IVF-PQ
 
 There are three key parameters to set when constructing an IVF-PQ index:
 
-* `metric`: Use an `L2` euclidean distance metric. We also support `dot` and `cosine` distance.
+* `metric`: Use an `l2` euclidean distance metric. We also support `dot` and `cosine` distance.
 * `num_partitions`: The number of partitions in the IVF portion of the index.
 * `num_sub_vectors`: The number of sub-vectors that will be created during Product Quantization (PQ).
 
@@ -56,7 +56,7 @@ In Python, the index can be created as follows:
 ```python
 # Create and train the index for a 1536-dimensional vector
 # Make sure you have enough data in the table for an effective training step
-tbl.create_index(metric="L2", num_partitions=256, num_sub_vectors=96)
+tbl.create_index(metric="l2", num_partitions=256, num_sub_vectors=96)
 ```
 !!! note
     `num_partitions`=256 and `num_sub_vectors`=96 does not work for every dataset. Those values needs to be adjusted for your particular dataset.

docs/src/embeddings/custom_embedding_function.md

@@ -55,6 +55,14 @@ Let's implement `SentenceTransformerEmbeddings` class. All you need to do is imp
 
 This is a stripped down version of our implementation of `SentenceTransformerEmbeddings` that removes certain optimizations and default settings.
 
+!!! danger "Use sensitive keys to prevent leaking secrets"
+    To prevent leaking secrets, such as API keys, you should add any sensitive
+    parameters of an embedding function to the output of the
+    [sensitive_keys()][lancedb.embeddings.base.EmbeddingFunction.sensitive_keys] /
+    [getSensitiveKeys()](../../js/namespaces/embedding/classes/EmbeddingFunction/#getsensitivekeys)
+    method. This prevents users from accidentally instantiating the embedding
+    function with hard-coded secrets.
+
 Now you can use this embedding function to create your table schema and that's it! you can then ingest data and run queries without manually vectorizing the inputs.
 
 === "Python"

docs/src/embeddings/understanding_embeddings.md

@@ -54,7 +54,7 @@ As mentioned, after creating embedding, each data point is represented as a vect
 
 Points that are close to each other in vector space are considered similar (or appear in similar contexts), and points that are far away are considered dissimilar. To quantify this closeness, we use distance as a metric which can be measured in the  following way - 
 
-1. **Euclidean Distance (L2)**: It calculates the straight-line distance between two points (vectors) in a multidimensional space.
+1. **Euclidean Distance (l2)**: It calculates the straight-line distance between two points (vectors) in a multidimensional space.
 2. **Cosine Similarity**: It measures the cosine of the angle between two vectors, providing a normalized measure of similarity based on their direction.
 3. **Dot product**: It is calculated as the sum of the products of their corresponding components. To measure relatedness it considers both the magnitude and direction of the vectors.
 

docs/src/embeddings/variables_and_secrets.md

@@ -0,0 +1,53 @@
+# Variable and Secrets
+
+Most embedding configuration options are saved in the table's metadata. However,
+this isn't always appropriate. For example, API keys should never be stored in the
+metadata. Additionally, other configuration options might be best set at runtime,
+such as the `device` configuration that controls whether to use GPU or CPU for
+inference. If you hardcoded this to GPU, you wouldn't be able to run the code on
+a server without one.
+
+To handle these cases, you can set variables on the embedding registry and
+reference them in the embedding configuration. These variables will be available
+during the runtime of your program, but not saved in the table's metadata. When
+the table is loaded from a different process, the variables must be set again.
+
+To set a variable, use the `set_var()` / `setVar()` method on the embedding registry.
+To reference a variable, use the syntax `$env:VARIABLE_NAME`. If there is a default
+value, you can use the syntax `$env:VARIABLE_NAME:DEFAULT_VALUE`.
+
+## Using variables to set secrets
+
+Sensitive configuration, such as API keys, must either be set as environment
+variables or using variables on the embedding registry. If you pass in a hardcoded
+value, LanceDB will raise an error. Instead, if you want to set an API key via
+configuration, use a variable:
+
+=== "Python"
+
+    ```python
+    --8<-- "python/python/tests/docs/test_embeddings_optional.py:register_secret"
+    ```
+
+=== "Typescript"
+
+    ```typescript
+    --8<-- "nodejs/examples/embedding.test.ts:register_secret"
+    ```
+
+## Using variables to set the device parameter
+
+Many embedding functions that run locally have a `device` parameter that controls
+whether to use GPU or CPU for inference. Because not all computers have a GPU,
+it's helpful to be able to set the `device` parameter at runtime, rather than
+have it hard coded in the embedding configuration. To make it work even if the
+variable isn't set, you could provide a default value of `cpu` in the embedding
+configuration.
+
+Some embedding libraries even have a method to detect which devices are available,
+which could be used to dynamically set the device at runtime. For example, in Python
+you can check if a CUDA GPU is available using `torch.cuda.is_available()`.
+
+```python
+--8<-- "python/python/tests/docs/test_embeddings_optional.py:register_device"
+```

docs/src/examples/index.md

@@ -8,15 +8,5 @@ LanceDB provides language APIs, allowing you to embed a database in your languag
 * 👾 [JavaScript](examples_js.md) examples
 * 🦀 Rust examples (coming soon)
 
-## Python Applications powered by LanceDB
+!!! tip "Hosted LanceDB"
-
+    If you want S3 cost-efficiency and local performance via a simple serverless API, checkout **LanceDB Cloud**. For private deployments, high performance at extreme scale, or if you have strict security requirements, talk to us about **LanceDB Enterprise**. [Learn more](https://docs.lancedb.com/)
-| Project Name | Description |
-| --- | --- |
-| **Ultralytics Explorer 🚀**<br>[![Ultralytics](https://img.shields.io/badge/Ultralytics-Docs-green?labelColor=0f3bc4&style=flat-square&logo=https://cdn.prod.website-files.com/646dd1f1a3703e451ba81ecc/64994922cf2a6385a4bf4489_UltralyticsYOLO_mark_blue.svg&link=https://docs.ultralytics.com/datasets/explorer/)](https://docs.ultralytics.com/datasets/explorer/)<br>[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ultralytics/ultralytics/blob/main/docs/en/datasets/explorer/explorer.ipynb) |  - 🔍 **Explore CV Datasets**: Semantic search, SQL queries, vector similarity, natural language.<br>- 🖥️ **GUI & Python API**: Seamless dataset interaction.<br>- ⚡ **Efficient & Scalable**: Leverages LanceDB for large datasets.<br>- 📊 **Detailed Analysis**: Easily analyze data patterns.<br>- 🌐 **Browser GUI Demo**: Create embeddings, search images, run queries. |
-| **Website Chatbot🤖**<br>[![GitHub](https://img.shields.io/badge/github-%23121011.svg?style=for-the-badge&logo=github&logoColor=white)](https://github.com/lancedb/lancedb-vercel-chatbot)<br>[![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2Flancedb%2Flancedb-vercel-chatbot&amp;env=OPENAI_API_KEY&amp;envDescription=OpenAI%20API%20Key%20for%20chat%20completion.&amp;project-name=lancedb-vercel-chatbot&amp;repository-name=lancedb-vercel-chatbot&amp;demo-title=LanceDB%20Chatbot%20Demo&amp;demo-description=Demo%20website%20chatbot%20with%20LanceDB.&amp;demo-url=https%3A%2F%2Flancedb.vercel.app&amp;demo-image=https%3A%2F%2Fi.imgur.com%2FazVJtvr.png) | - 🌐 **Chatbot from Sitemap/Docs**: Create a chatbot using site or document context.<br>- 🚀 **Embed LanceDB in Next.js**: Lightweight, on-prem storage.<br>- 🧠 **AI-Powered Context Retrieval**: Efficiently access relevant data.<br>- 🔧 **Serverless & Native JS**: Seamless integration with Next.js.<br>- ⚡ **One-Click Deploy on Vercel**: Quick and easy setup.. |
-
-## Nodejs Applications powered by LanceDB
-
-| Project Name | Description |
-| --- | --- |
-| **Langchain Writing Assistant✍️ **<br>[![Github](../assets/github.svg)](https://github.com/lancedb/vectordb-recipes/tree/main/applications/node/lanchain_writing_assistant) |  - **📂 Data Source Integration**:  Use your own data by specifying data source file, and the app instantly processes it to provide insights. <br>- **🧠 Intelligent Suggestions**:  Powered by LangChain.js and LanceDB, it improves writing productivity and accuracy.  <br>- **💡 Enhanced Writing Experience**: It delivers real-time contextual insights and factual suggestions while the user writes. |

docs/src/extra_js/reo.js

@@ -0,0 +1 @@
+!function(){var e,t,n;e="9627b71b382d201",t=function(){Reo.init({clientID:"9627b71b382d201"})},(n=document.createElement("script")).src="https://static.reo.dev/"+e+"/reo.js",n.defer=!0,n.onload=t,document.head.appendChild(n)}();

docs/src/fts.md

@@ -10,27 +10,19 @@ LanceDB provides support for full-text search via Lance, allowing you to incorpo
 Consider that we have a LanceDB table named `my_table`, whose string column `text` we want to index and query via keyword search, the FTS index must be created before you can search via keywords.
 
 === "Python"
+    === "Sync API"
 
         ```python
-    import lancedb
+        --8<-- "python/python/tests/docs/test_search.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_search.py:import-lancedb-fts"
+        --8<-- "python/python/tests/docs/test_search.py:basic_fts"
+        ```
+    === "Async API"
 
-    uri = "data/sample-lancedb"
+        ```python
-    db = lancedb.connect(uri)
+        --8<-- "python/python/tests/docs/test_search.py:import-lancedb"
-
+        --8<-- "python/python/tests/docs/test_search.py:import-lancedb-fts"
-    table = db.create_table(
+        --8<-- "python/python/tests/docs/test_search.py:basic_fts_async"
-        "my_table",
-        data=[
-            {"vector": [3.1, 4.1], "text": "Frodo was a happy puppy"},
-            {"vector": [5.9, 26.5], "text": "There are several kittens playing"},
-        ],
-    )
-
-    # 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}]
-    # ...
         ```
 
 === "TypeScript"
@@ -50,7 +42,7 @@ Consider that we have a LanceDB table named `my_table`, whose string column `tex
     });
 
     await tbl
-        .search("puppy", queryType="fts")
+        .search("puppy", "fts")
         .select(["text"])
         .limit(10)
         .toArray();
@@ -93,8 +85,15 @@ By default the text is tokenized by splitting on punctuation and whitespaces, an
 Stemming is useful for improving search results by reducing words to their root form, e.g. "running" to "run". LanceDB supports stemming for multiple languages, you can specify the tokenizer name to enable stemming by the pattern `tokenizer_name="{language_code}_stem"`, e.g. `en_stem` for English.
 
 For example, to enable stemming for English:
+=== "Sync API"
+
     ```python
-table.create_fts_index("text", use_tantivy=True, tokenizer_name="en_stem")
+    --8<-- "python/python/tests/docs/test_search.py:fts_config_stem"
+    ```
+=== "Async API"
+
+    ```python
+    --8<-- "python/python/tests/docs/test_search.py:fts_config_stem_async"
     ```
 
 the following [languages](https://docs.rs/tantivy/latest/tantivy/tokenizer/enum.Language.html) are currently supported.
@@ -102,12 +101,15 @@ the following [languages](https://docs.rs/tantivy/latest/tantivy/tokenizer/enum.
 The tokenizer is customizable, you can specify how the tokenizer splits the text, and how it filters out words, etc.
 
 For example, for language with accents, you can specify the tokenizer to use `ascii_folding` to remove accents, e.g. 'é' to 'e':
+=== "Sync API"
+
     ```python
-table.create_fts_index("text",
+    --8<-- "python/python/tests/docs/test_search.py:fts_config_folding"
-                        use_tantivy=False,
+    ```
-                        language="French",
+=== "Async API"
-                        stem=True,
+
-                        ascii_folding=True)
+    ```python
+    --8<-- "python/python/tests/docs/test_search.py:fts_config_folding_async"
     ```
 
 ## Filtering
@@ -119,8 +121,15 @@ This can be invoked via the familiar `where` syntax.
 With pre-filtering:
 === "Python"
 
+    === "Sync API"
+
         ```python
-    table.search("puppy").limit(10).where("meta='foo'", prefilte=True).to_list()
+        --8<-- "python/python/tests/docs/test_search.py:fts_prefiltering"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:fts_prefiltering_async"
         ```
 
 === "TypeScript"
@@ -151,8 +160,15 @@ With pre-filtering:
 With post-filtering:
 === "Python"
 
+    === "Sync API"
+
         ```python
-    table.search("puppy").limit(10).where("meta='foo'", prefilte=False).to_list()
+        --8<-- "python/python/tests/docs/test_search.py:fts_postfiltering"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:fts_postfiltering_async"
         ```
 
 === "TypeScript"
@@ -191,8 +207,15 @@ or a **terms** search query like `old man sea`. For more details on the terms
 query syntax, see Tantivy's [query parser rules](https://docs.rs/tantivy/latest/tantivy/query/struct.QueryParser.html).
 
 To search for a phrase, the index must be created with `with_position=True`:
+=== "Sync API"
+
     ```python
-table.create_fts_index("text", use_tantivy=False, with_position=True)
+    --8<-- "python/python/tests/docs/test_search.py:fts_with_position"
+    ```
+=== "Async API"
+
+    ```python
+    --8<-- "python/python/tests/docs/test_search.py:fts_with_position_async"
     ```
 This will allow you to search for phrases, but it will also significantly increase the index size and indexing time.
 
@@ -205,9 +228,15 @@ This can make the query more efficient, especially when the table is large and t
 
 === "Python"
 
+    === "Sync API"
+
         ```python
-    table.add([{"vector": [3.1, 4.1], "text": "Frodo was a happy puppy"}])
+        --8<-- "python/python/tests/docs/test_search.py:fts_incremental_index"
-    table.optimize()
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_search.py:fts_incremental_index_async"
         ```
 
 === "TypeScript"

docs/src/fts_tantivy.md

@@ -2,7 +2,7 @@
 
 LanceDB also provides support for full-text search via [Tantivy](https://github.com/quickwit-oss/tantivy), allowing you to incorporate keyword-based search (based on BM25) in your retrieval solutions.
 
-The tantivy-based FTS is only available in Python and does not support building indexes on object storage or incremental indexing. If you need these features, try native FTS [native FTS](fts.md).
+The tantivy-based FTS is only available in Python synchronous APIs and does not support building indexes on object storage or incremental indexing. If you need these features, try native FTS [native FTS](fts.md).
 
 ## Installation
 

docs/src/guides/multi-vector.md

@@ -0,0 +1,85 @@
+# Late interaction & MultiVector embedding type
+Late interaction is a technique used in retrieval that calculates the relevance of a query to a document by comparing their multi-vector representations. The key difference between late interaction and other popular methods:
+
+![late interaction vs other methods](https://raw.githubusercontent.com/lancedb/assets/b035a0ceb2c237734e0d393054c146d289792339/docs/assets/integration/colbert-blog-interaction.svg)
+
+
+[ Illustration from https://jina.ai/news/what-is-colbert-and-late-interaction-and-why-they-matter-in-search/]
+
+<b>No interaction:</b> Refers to independently embedding the query and document, that are compared to calcualte similarity without any interaction between them. This is typically used in vector search operations.
+
+<b>Partial interaction</b> Refers to a specific approach where the similarity computation happens primarily between query vectors and document vectors, without extensive interaction between individual components of each. An example of this is dual-encoder models like BERT.
+
+<b>Early full interaction</b> Refers to techniques like cross-encoders that process query and docs in pairs with full interaction across various stages of encoding. This is a powerful, but relatively slower technique. Because it requires processing query and docs in pairs, doc embeddings can't be pre-computed for fast retrieval. This is why cross encoders are typically used as reranking models combined with vector search. Learn more about [LanceDB Reranking support](https://lancedb.github.io/lancedb/reranking/).
+
+<b>Late interaction</b> Late interaction is a technique that calculates the doc and query similarity independently and then the interaction or evaluation happens during the retrieval process. This is typically used in retrieval models like ColBERT. Unlike early interaction, It allows speeding up the retrieval process without compromising the depth of semantic analysis.
+
+## Internals of ColBERT 
+Let's take a look at the steps involved in performing late interaction based retrieval using ColBERT:
+
+• ColBERT employs BERT-based encoders for both queries `(fQ)` and documents `(fD)`
+• A single BERT model is shared between query and document encoders and special tokens distinguish input types: `[Q]` for queries and `[D]` for documents
+
+**Query Encoder (fQ):**
+• Query q is tokenized into WordPiece tokens: `q1, q2, ..., ql`. `[Q]` token is prepended right after BERT's `[CLS]` token
+• If query length < Nq, it's padded with [MASK] tokens up to Nq.
+• The padded sequence goes through BERT's transformer architecture
+• Final embeddings are L2-normalized.
+
+**Document Encoder (fD):**
+• Document d is tokenized into tokens `d1, d2, ..., dm`. `[D]` token is prepended after `[CLS]` token
+• Unlike queries, documents are NOT padded with `[MASK]` tokens
+• Document tokens are processed through BERT and the same linear layer
+
+**Late Interaction:**
+• Late interaction estimates relevance score `S(q,d)` using embedding `Eq` and `Ed`. Late interaction happens after independent encoding
+• For each query embedding, maximum similarity is computed against all document embeddings
+• The similarity measure can be cosine similarity or squared L2 distance
+
+**MaxSim Calculation:**
+```
+S(q,d) := Σ max(Eqi⋅EdjT)
+          i∈|Eq| j∈|Ed|
+```
+• This finds the best matching document embedding for each query embedding
+• Captures relevance based on strongest local matches between contextual embeddings
+
+## LanceDB MultiVector type
+LanceDB supports multivector type, this is useful when you have multiple vectors for a single item (e.g. with ColBert and ColPali).
+
+You can index on a column with multivector type and search on it, the query can be single vector or multiple vectors. For now, only cosine metric is supported for multivector search. The vector value type can be float16, float32 or float64. LanceDB integrateds [ConteXtualized Token Retriever(XTR)](https://arxiv.org/abs/2304.01982), which introduces a simple, yet novel, objective function that encourages the model to retrieve the most important document tokens first. 
+
+```python
+import lancedb
+import numpy as np
+import pyarrow as pa
+
+db = lancedb.connect("data/multivector_demo")
+schema = pa.schema(
+    [
+        pa.field("id", pa.int64()),
+        # float16, float32, and float64 are supported
+        pa.field("vector", pa.list_(pa.list_(pa.float32(), 256))),
+    ]
+)
+data = [
+    {
+        "id": i,
+        "vector": np.random.random(size=(2, 256)).tolist(),
+    }
+    for i in range(1024)
+]
+tbl = db.create_table("my_table", data=data, schema=schema)
+
+# only cosine similarity is supported for multi-vectors
+tbl.create_index(metric="cosine")
+
+# query with single vector
+query = np.random.random(256).astype(np.float16)
+tbl.search(query).to_arrow()
+
+# query with multiple vectors
+query = np.random.random(size=(2, 256))
+tbl.search(query).to_arrow()
+```
+Find more about vector search in LanceDB [here](https://lancedb.github.io/lancedb/search/#multivector-type).

docs/src/guides/scalar_index.md

@@ -32,18 +32,19 @@ over scalar columns.
 ### Create a scalar index
 === "Python"
 
-    ```python
+    === "Sync API"
-    import lancedb
-    books = [
-      {"book_id": 1, "publisher": "plenty of books", "tags": ["fantasy", "adventure"]},
-      {"book_id": 2, "publisher": "book town", "tags": ["non-fiction"]},
-      {"book_id": 3, "publisher": "oreilly", "tags": ["textbook"]}
-    ]
 
-    db = lancedb.connect("./db")
+        ```python
-    table = db.create_table("books", books)
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-lancedb"
-    table.create_scalar_index("book_id")  # BTree by default
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-lancedb-btree-bitmap"
-    table.create_scalar_index("publisher", index_type="BITMAP")
+        --8<-- "python/python/tests/docs/test_guide_index.py:basic_scalar_index"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-lancedb-btree-bitmap"
+        --8<-- "python/python/tests/docs/test_guide_index.py:basic_scalar_index_async"
         ```
 
 === "Typescript"
@@ -62,11 +63,17 @@ The following scan will be faster if the column `book_id` has a scalar index:
 
 === "Python"
 
-    ```python
+    === "Sync API"
-    import lancedb
 
-    table = db.open_table("books")
+        ```python
-    my_df = table.search().where("book_id = 2").to_pandas()
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_guide_index.py:search_with_scalar_index"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_guide_index.py:search_with_scalar_index_async"
         ```
 
 === "Typescript"
@@ -88,21 +95,17 @@ Scalar indices can also speed up scans containing a vector search or full text s
 
 === "Python"
 
+    === "Sync API"
+
         ```python
-    import lancedb
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_guide_index.py:vector_search_with_scalar_index"
+        ```
+    === "Async API"
 
-    data = [
+        ```python
-      {"book_id": 1, "vector": [1, 2]},
+        --8<-- "python/python/tests/docs/test_guide_index.py:import-lancedb"
-      {"book_id": 2, "vector": [3, 4]},
+        --8<-- "python/python/tests/docs/test_guide_index.py:vector_search_with_scalar_index_async"
-      {"book_id": 3, "vector": [5, 6]}
-    ]
-    table = db.create_table("book_with_embeddings", data)
-
-    (
-        table.search([1, 2])
-        .where("book_id != 3", prefilter=True)
-        .to_pandas()
-    )
         ```
 
 === "Typescript"
@@ -122,9 +125,15 @@ Scalar indices can also speed up scans containing a vector search or full text s
 Updating the table data (adding, deleting, or modifying records) requires that you also update the scalar index. This can be done by calling `optimize`, which will trigger an update to the existing scalar index.
 === "Python"
 
+    === "Sync API"
+
         ```python
-    table.add([{"vector": [7, 8], "book_id": 4}])
+        --8<-- "python/python/tests/docs/test_guide_index.py:update_scalar_index"
-    table.optimize()
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_index.py:update_scalar_index_async"
         ```
 
 === "TypeScript"

docs/src/guides/storage.md

@@ -12,26 +12,50 @@ LanceDB OSS supports object stores such as AWS S3 (and compatible stores), Azure
 === "Python"
 
     AWS S3:
+    === "Sync API"
 
         ```python
         import lancedb
         db = lancedb.connect("s3://bucket/path")
         ```
+    === "Async API"
+
+        ```python
+        import lancedb
+        async_db = await lancedb.connect_async("s3://bucket/path")
+        ```
 
     Google Cloud Storage:
 
+    === "Sync API"
+
         ```python
         import lancedb
         db = lancedb.connect("gs://bucket/path")
         ```
+    === "Async API"
+
+        ```python
+        import lancedb
+        async_db = await lancedb.connect_async("gs://bucket/path")
+        ```
 
     Azure Blob Storage:
 
     <!-- skip-test -->
+    === "Sync API"
+
         ```python
         import lancedb
         db = lancedb.connect("az://bucket/path")
         ```
+    <!-- skip-test -->
+    === "Async API"
+
+        ```python
+        import lancedb
+        async_db = await lancedb.connect_async("az://bucket/path")
+        ```
     Note that for Azure, storage credentials must be configured. See [below](#azure-blob-storage) for more details.
 
 
@@ -94,9 +118,20 @@ If you only want this to apply to one particular connection, you can pass the `s
 
 === "Python"
 
+    === "Sync API"
+
         ```python
         import lancedb
-    db = await lancedb.connect_async(
+        db = lancedb.connect(
+            "s3://bucket/path",
+            storage_options={"timeout": "60s"}
+        )
+        ```
+    === "Async API"
+
+        ```python
+        import lancedb
+        async_db = await lancedb.connect_async(
             "s3://bucket/path",
             storage_options={"timeout": "60s"}
         )
@@ -128,10 +163,24 @@ Getting even more specific, you can set the `timeout` for only a particular tabl
 === "Python"
 
     <!-- skip-test -->
+    === "Sync API"
+
         ```python
         import lancedb
-    db = await lancedb.connect_async("s3://bucket/path")
+        db = lancedb.connect("s3://bucket/path")
-    table = await db.create_table(
+        table = db.create_table(
+            "table",
+            [{"a": 1, "b": 2}],
+            storage_options={"timeout": "60s"}
+        )
+        ```
+    <!-- skip-test -->
+    === "Async API"
+
+        ```python
+        import lancedb
+        async_db = await lancedb.connect_async("s3://bucket/path")
+        async_table = await async_db.create_table(
             "table",
             [{"a": 1, "b": 2}],
             storage_options={"timeout": "60s"}
@@ -194,9 +243,24 @@ These can be set as environment variables or passed in the `storage_options` par
 
 === "Python"
 
+    === "Sync API"
+
         ```python
         import lancedb
-    db = await lancedb.connect_async(
+        db = lancedb.connect(
+            "s3://bucket/path",
+            storage_options={
+                "aws_access_key_id": "my-access-key",
+                "aws_secret_access_key": "my-secret-key",
+                "aws_session_token": "my-session-token",
+            }
+        )
+        ```
+    === "Async API"
+
+        ```python
+        import lancedb
+        async_db = await lancedb.connect_async(
             "s3://bucket/path",
             storage_options={
                 "aws_access_key_id": "my-access-key",
@@ -278,7 +342,7 @@ For **read and write access**, LanceDB will need a policy such as:
             "Action": [
               "s3:PutObject",
               "s3:GetObject",
-              "s3:DeleteObject",
+              "s3:DeleteObject"
             ],
             "Resource": "arn:aws:s3:::<bucket>/<prefix>/*"
         },
@@ -310,7 +374,7 @@ For **read-only access**, LanceDB will need a policy such as:
         {
             "Effect": "Allow",
             "Action": [
-              "s3:GetObject",
+              "s3:GetObject"
             ],
             "Resource": "arn:aws:s3:::<bucket>/<prefix>/*"
         },
@@ -348,9 +412,19 @@ name of the table to use.
 
 === "Python"
 
+    === "Sync API"
+
         ```python
         import lancedb
-    db = await lancedb.connect_async(
+        db = lancedb.connect(
+            "s3+ddb://bucket/path?ddbTableName=my-dynamodb-table",
+        )
+        ```
+    === "Async API"
+
+        ```python
+        import lancedb
+        async_db = await lancedb.connect_async(
             "s3+ddb://bucket/path?ddbTableName=my-dynamodb-table",
         )    
         ```
@@ -441,9 +515,23 @@ LanceDB can also connect to S3-compatible stores, such as MinIO. To do so, you m
 
 === "Python"
 
+    === "Sync API"
+
         ```python
         import lancedb
-    db = await lancedb.connect_async(
+        db = lancedb.connect(
+            "s3://bucket/path",
+            storage_options={
+                "region": "us-east-1",
+                "endpoint": "http://minio:9000",
+            }
+        )
+        ```
+    === "Async API"
+
+        ```python
+        import lancedb
+        async_db = await lancedb.connect_async(
             "s3://bucket/path",
             storage_options={
                 "region": "us-east-1",
@@ -502,9 +590,23 @@ To configure LanceDB to use an S3 Express endpoint, you must set the storage opt
 
 === "Python"
 
+    === "Sync API"
+
         ```python
         import lancedb
-    db = await lancedb.connect_async(
+        db = lancedb.connect(
+            "s3://my-bucket--use1-az4--x-s3/path",
+            storage_options={
+                "region": "us-east-1",
+                "s3_express": "true",
+            }
+        )
+        ```
+    === "Async API"
+
+        ```python
+        import lancedb
+        async_db = await lancedb.connect_async(
             "s3://my-bucket--use1-az4--x-s3/path",
             storage_options={
                 "region": "us-east-1",
@@ -552,9 +654,23 @@ GCS credentials are configured by setting the `GOOGLE_SERVICE_ACCOUNT` environme
 === "Python"
 
     <!-- skip-test -->
+    === "Sync API"
+
         ```python
         import lancedb
-    db = await lancedb.connect_async(
+        db = lancedb.connect(
+            "gs://my-bucket/my-database",
+            storage_options={
+                "service_account": "path/to/service-account.json",
+            }
+        )
+        ```
+    <!-- skip-test -->
+    === "Async API"
+
+        ```python
+        import lancedb
+        async_db = await lancedb.connect_async(
             "gs://my-bucket/my-database",
             storage_options={
                 "service_account": "path/to/service-account.json",
@@ -612,9 +728,24 @@ Azure Blob Storage credentials can be configured by setting the `AZURE_STORAGE_A
 === "Python"
 
     <!-- skip-test -->
+    === "Sync API"
+
         ```python
         import lancedb
-    db = await lancedb.connect_async(
+        db = lancedb.connect(
+            "az://my-container/my-database",
+            storage_options={
+                account_name: "some-account",
+                account_key: "some-key",
+            }
+        )
+        ```
+    <!-- skip-test -->
+    === "Async API"
+
+        ```python
+        import lancedb
+        async_db = await lancedb.connect_async(
             "az://my-container/my-database",
             storage_options={
                 account_name: "some-account",

docs/src/guides/tables.md

@@ -12,9 +12,17 @@ Initialize a LanceDB connection and create a table
 
 === "Python"
 
+    === "Sync API"
+
         ```python
-    import lancedb
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb"
-    db = lancedb.connect("./.lancedb")
+        --8<-- "python/python/tests/docs/test_guide_tables.py:connect"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:connect_async"
         ```
 
     LanceDB allows ingesting data from various sources - `dict`, `list[dict]`, `pd.DataFrame`, `pa.Table` or a `Iterator[pa.RecordBatch]`. Let's take a look at some of the these.
@@ -47,17 +55,15 @@ Initialize a LanceDB connection and create a table
 
 === "Python"
 
+    === "Sync API"
+
         ```python
-    import lancedb
+        --8<-- "python/python/tests/docs/test_guide_tables.py:create_table"
+        ```
+    === "Async API"
 
-    db = lancedb.connect("./.lancedb")
+        ```python
-
+        --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_async"
-    data = [{"vector": [1.1, 1.2], "lat": 45.5, "long": -122.7},
-            {"vector": [0.2, 1.8], "lat": 40.1, "long": -74.1}]
-
-    db.create_table("my_table", data)
-
-    db["my_table"].head()
         ```
 
     !!! info "Note"
@@ -67,15 +73,29 @@ Initialize a LanceDB connection and create a table
         and the table exists, then it simply opens the existing table. The data you
         passed in will NOT be appended to the table in that case.
 
+    === "Sync API"
+
         ```python
-    db.create_table("name", data, exist_ok=True)
+        --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_exist_ok"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_async_exist_ok"
         ```
 
     Sometimes you want to make sure that you start fresh. If you want to
     overwrite the table, you can pass in mode="overwrite" to the createTable function.
 
+    === "Sync API"
+
         ```python
-    db.create_table("name", data, mode="overwrite")
+        --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_overwrite"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_async_overwrite"
         ```
 
 === "Typescript[^1]"
@@ -146,18 +166,18 @@ Initialize a LanceDB connection and create a table
 
 ### From a Pandas DataFrame
 
+
+=== "Sync API"
+
     ```python
-import pandas as pd
+    --8<-- "python/python/tests/docs/test_guide_tables.py:import-pandas"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_from_pandas"
+    ```
+=== "Async API"
 
-data = pd.DataFrame({
+    ```python
-    "vector": [[1.1, 1.2, 1.3, 1.4], [0.2, 1.8, 0.4, 3.6]],
+    --8<-- "python/python/tests/docs/test_guide_tables.py:import-pandas"
-    "lat": [45.5, 40.1],
+    --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_async_from_pandas"
-    "long": [-122.7, -74.1]
-})
-
-db.create_table("my_table", data)
-
-db["my_table"].head()
     ```
 
 !!! info "Note"
@@ -165,14 +185,17 @@ db["my_table"].head()
 
 The **`vector`** column needs to be a [Vector](../python/pydantic.md#vector-field) (defined as [pyarrow.FixedSizeList](https://arrow.apache.org/docs/python/generated/pyarrow.list_.html)) type.
 
-```python
+=== "Sync API"
-custom_schema = pa.schema([
-pa.field("vector", pa.list_(pa.float32(), 4)),
-pa.field("lat", pa.float32()),
-pa.field("long", pa.float32())
-])
 
-table = db.create_table("my_table", data, schema=custom_schema)
+    ```python
+    --8<-- "python/python/tests/docs/test_guide_tables.py:import-pyarrow"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_custom_schema"
+    ```
+=== "Async API"
+
+    ```python
+    --8<-- "python/python/tests/docs/test_guide_tables.py:import-pyarrow"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_async_custom_schema"
     ```
 
 ### From a Polars DataFrame
@@ -182,15 +205,17 @@ written in Rust. Just like in Pandas, the Polars integration is enabled by PyArr
 under the hood. A deeper integration between LanceDB Tables and Polars DataFrames
 is on the way.
 
-```python
+=== "Sync API"
-import polars as pl
 
-data = pl.DataFrame({
+    ```python
-    "vector": [[3.1, 4.1], [5.9, 26.5]],
+    --8<-- "python/python/tests/docs/test_guide_tables.py:import-polars"
-    "item": ["foo", "bar"],
+    --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_from_polars"
-    "price": [10.0, 20.0]
+    ```
-})
+=== "Async API"
-table = db.create_table("pl_table", data=data)
+
+    ```python
+    --8<-- "python/python/tests/docs/test_guide_tables.py:import-polars"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_async_from_polars"
     ```
 
 ### From an Arrow Table
@@ -198,28 +223,19 @@ You can also create LanceDB tables directly from Arrow tables.
 LanceDB supports float16 data type!
 
 === "Python"
+    === "Sync API"
 
         ```python
-    import pyarrows as pa
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-pyarrow"
-    import numpy as np
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-numpy"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_from_arrow_table"
+        ```
+    === "Async API"
 
-    dim = 16
+        ```python
-    total = 2
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-polars"
-    schema = pa.schema(
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-numpy"
-        [
+        --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_async_from_arrow_table"
-            pa.field("vector", pa.list_(pa.float16(), dim)),
-            pa.field("text", pa.string())
-        ]
-    )
-    data = pa.Table.from_arrays(
-        [
-            pa.array([np.random.randn(dim).astype(np.float16) for _ in range(total)],
-                    pa.list_(pa.float16(), dim)),
-            pa.array(["foo", "bar"])
-        ],
-        ["vector", "text"],
-    )
-    tbl = db.create_table("f16_tbl", data, schema=schema)
         ```
 
 === "Typescript[^1]"
@@ -250,24 +266,21 @@ can be configured with the vector dimensions. It is also important to note that
 LanceDB only understands subclasses of `lancedb.pydantic.LanceModel`
 (which itself derives from `pydantic.BaseModel`).
 
+=== "Sync API"
+
     ```python
-from lancedb.pydantic import Vector, LanceModel
+    --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb-pydantic"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:import-pyarrow"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:class-Content"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_from_pydantic"
+    ```
+=== "Async API"
 
-class Content(LanceModel):
+    ```python
-    movie_id: int
+    --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb-pydantic"
-    vector: Vector(128)
+    --8<-- "python/python/tests/docs/test_guide_tables.py:import-pyarrow"
-    genres: str
+    --8<-- "python/python/tests/docs/test_guide_tables.py:class-Content"
-    title: str
+    --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_async_from_pydantic"
-    imdb_id: int
-
-    @property
-    def imdb_url(self) -> str:
-        return f"https://www.imdb.com/title/tt{self.imdb_id}"
-
-import pyarrow as pa
-db = lancedb.connect("~/.lancedb")
-table_name = "movielens_small"
-table = db.create_table(table_name, schema=Content)
     ```
 
 #### Nested schemas
@@ -277,22 +290,24 @@ For example, you may want to store the document string
 and the document source name as a nested Document object:
 
 ```python
-class Document(BaseModel):
+--8<-- "python/python/tests/docs/test_guide_tables.py:import-pydantic-basemodel"
-    content: str
+--8<-- "python/python/tests/docs/test_guide_tables.py:class-Document"
-    source: str
 ```
 
 This can be used as the type of a LanceDB table column:
 
+=== "Sync API"
+
     ```python
-class NestedSchema(LanceModel):
+    --8<-- "python/python/tests/docs/test_guide_tables.py:class-NestedSchema"
-    id: str
+    --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_nested_schema"
-    vector: Vector(1536)
-    document: Document
-
-tbl = db.create_table("nested_table", schema=NestedSchema, mode="overwrite")
     ```
+=== "Async API"
 
+    ```python
+    --8<-- "python/python/tests/docs/test_guide_tables.py:class-NestedSchema"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_async_nested_schema"
+    ```
 This creates a struct column called "document" that has two subfields
 called "content" and "source":
 
@@ -356,28 +371,19 @@ LanceDB additionally supports PyArrow's `RecordBatch` Iterators or other generat
 
 Here's an example using using `RecordBatch` iterator for creating tables.
 
+=== "Sync API"
+
     ```python
-import pyarrow as pa
+    --8<-- "python/python/tests/docs/test_guide_tables.py:import-pyarrow"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:make_batches"
+    --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_from_batch"
+    ```
+=== "Async API"
 
-def make_batches():
+    ```python
-    for i in range(5):
+    --8<-- "python/python/tests/docs/test_guide_tables.py:import-pyarrow"
-        yield pa.RecordBatch.from_arrays(
+    --8<-- "python/python/tests/docs/test_guide_tables.py:make_batches"
-            [
+    --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_async_from_batch"
-                pa.array([[3.1, 4.1, 5.1, 6.1], [5.9, 26.5, 4.7, 32.8]],
-                        pa.list_(pa.float32(), 4)),
-                pa.array(["foo", "bar"]),
-                pa.array([10.0, 20.0]),
-            ],
-            ["vector", "item", "price"],
-        )
-
-schema = pa.schema([
-    pa.field("vector", pa.list_(pa.float32(), 4)),
-    pa.field("item", pa.utf8()),
-    pa.field("price", pa.float32()),
-])
-
-db.create_table("batched_tale", make_batches(), schema=schema)
     ```
 
 You can also use iterators of other types like Pandas DataFrame or Pylists directly in the above example.
@@ -387,14 +393,28 @@ You can also use iterators of other types like Pandas DataFrame or Pylists direc
 === "Python"
     If you forget the name of your table, you can always get a listing of all table names.
 
+    === "Sync API"
+
         ```python
-    print(db.table_names())
+        --8<-- "python/python/tests/docs/test_guide_tables.py:list_tables"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:list_tables_async"
         ```
 
     Then, you can open any existing tables.
 
+    === "Sync API"
+
         ```python
-    tbl = db.open_table("my_table")
+        --8<-- "python/python/tests/docs/test_guide_tables.py:open_table"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:open_table_async"
         ```
 
 === "Typescript[^1]"
@@ -418,34 +438,40 @@ You can create an empty table for scenarios where you want to add data to the ta
 
 
     An empty table can be initialized via a PyArrow schema.
+    === "Sync API"
 
         ```python
-    import lancedb
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb"
-    import pyarrow as pa
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-pyarrow"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:create_empty_table"
+        ```
+    === "Async API"
 
-    schema = pa.schema(
+        ```python
-      [
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb"
-          pa.field("vector", pa.list_(pa.float32(), 2)),
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-pyarrow"
-          pa.field("item", pa.string()),
+        --8<-- "python/python/tests/docs/test_guide_tables.py:create_empty_table_async"
-          pa.field("price", pa.float32()),
-      ])
-    tbl = db.create_table("empty_table_add", schema=schema)
         ```
 
     Alternatively, you can also use Pydantic to specify the schema for the empty table. Note that we do not
     directly import `pydantic` but instead use `lancedb.pydantic` which is a subclass of `pydantic.BaseModel`
     that has been extended to support LanceDB specific types like `Vector`.
 
+    === "Sync API"
+
         ```python
-    import lancedb
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb"
-    from lancedb.pydantic import LanceModel, vector
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb-pydantic"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:class-Item"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:create_empty_table_pydantic"
+        ```
+    === "Async API"
 
-    class Item(LanceModel):
+        ```python
-        vector: Vector(2)
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb"
-        item: str
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb-pydantic"
-        price: float
+        --8<-- "python/python/tests/docs/test_guide_tables.py:class-Item"
-
+        --8<-- "python/python/tests/docs/test_guide_tables.py:create_empty_table_async_pydantic"
-    tbl = db.create_table("empty_table_add", schema=Item.to_arrow_schema())
         ```
 
     Once the empty table has been created, you can add data to it via the various methods listed in the [Adding to a table](#adding-to-a-table) section.
@@ -473,85 +499,95 @@ After a table has been created, you can always add more data to it using the `ad
 
     ### Add a Pandas DataFrame
 
+    === "Sync API"
+
         ```python
-    df = pd.DataFrame({
+        --8<-- "python/python/tests/docs/test_guide_tables.py:add_table_from_pandas"
-        "vector": [[1.3, 1.4], [9.5, 56.2]], "item": ["banana", "apple"], "price": [5.0, 7.0]
+        ```
-    })
+    === "Async API"
-    tbl.add(df)
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:add_table_async_from_pandas"
         ```
 
     ### Add a Polars DataFrame
 
+    === "Sync API"
+
         ```python
-    df = pl.DataFrame({
+        --8<-- "python/python/tests/docs/test_guide_tables.py:add_table_from_polars"
-        "vector": [[1.3, 1.4], [9.5, 56.2]], "item": ["banana", "apple"], "price": [5.0, 7.0]
+        ```
-    })
+    === "Async API"
-    tbl.add(df)
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:add_table_async_from_polars"
         ```
 
     ### Add an Iterator
 
     You can also add a large dataset batch in one go using Iterator of any supported data types.
 
+    === "Sync API"
+
         ```python
-    def make_batches():
+        --8<-- "python/python/tests/docs/test_guide_tables.py:make_batches_for_add"
-        for i in range(5):
+        --8<-- "python/python/tests/docs/test_guide_tables.py:add_table_from_batch"
-            yield [
+        ```
-                    {"vector": [3.1, 4.1], "item": "peach", "price": 6.0},
+    === "Async API"
-                    {"vector": [5.9, 26.5], "item": "pear", "price": 5.0}
+
-                ]
+        ```python
-    tbl.add(make_batches())
+        --8<-- "python/python/tests/docs/test_guide_tables.py:make_batches_for_add"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:add_table_async_from_batch"
         ```
 
     ### Add a PyArrow table
 
     If you have data coming in as a PyArrow table, you can add it directly to the LanceDB table.
 
-    ```python
+    === "Sync API"
-    pa_table = pa.Table.from_arrays(
-            [
-                pa.array([[9.1, 6.7], [9.9, 31.2]],
-                        pa.list_(pa.float32(), 2)),
-                pa.array(["mango", "orange"]),
-                pa.array([7.0, 4.0]),
-            ],
-            ["vector", "item", "price"],
-        )
 
-    tbl.add(pa_table)
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:add_table_from_pyarrow"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:add_table_async_from_pyarrow"
         ```
 
     ### Add a Pydantic Model
 
     Assuming that a table has been created with the correct schema as shown [above](#creating-empty-table), you can add data items that are valid Pydantic models to the table.
 
-    ```python
+    === "Sync API"
-    pydantic_model_items = [
-        Item(vector=[8.1, 4.7], item="pineapple", price=10.0),
-        Item(vector=[6.9, 9.3], item="avocado", price=9.0)
-    ]
 
-    tbl.add(pydantic_model_items)
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:add_table_from_pydantic"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:add_table_async_from_pydantic"
         ```
 
     ??? "Ingesting Pydantic models with LanceDB embedding API"
         When using LanceDB's embedding API, you can add Pydantic models directly to the table. LanceDB will automatically convert the `vector` field to a vector before adding it to the table. You need to specify the default value of `vector` field as None to allow LanceDB to automatically vectorize the data.
 
+        === "Sync API"
+
             ```python
-        import lancedb
+            --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb"
-        from lancedb.pydantic import LanceModel, Vector
+            --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb-pydantic"
-        from lancedb.embeddings import get_registry
+            --8<-- "python/python/tests/docs/test_guide_tables.py:import-embeddings"
+            --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_with_embedding"
+            ```
+        === "Async API"
 
-        db = lancedb.connect("~/tmp")
+            ```python
-        embed_fcn = get_registry().get("huggingface").create(name="BAAI/bge-small-en-v1.5")
+            --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb"
-
+            --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb-pydantic"
-        class Schema(LanceModel):
+            --8<-- "python/python/tests/docs/test_guide_tables.py:import-embeddings"
-            text: str = embed_fcn.SourceField()
+            --8<-- "python/python/tests/docs/test_guide_tables.py:create_table_async_with_embedding"
-            vector: Vector(embed_fcn.ndims()) = embed_fcn.VectorField(default=None)
-
-        tbl = db.create_table("my_table", schema=Schema, mode="overwrite")
-        models = [Schema(text="hello"), Schema(text="world")]
-        tbl.add(models)
             ```
 
 === "Typescript[^1]"
@@ -565,49 +601,78 @@ After a table has been created, you can always add more data to it using the `ad
     )
     ```
 
+## Upserting into a table
+
+Upserting lets you insert new rows or update existing rows in a table. To upsert
+in LanceDB, use the merge insert API.
+
+=== "Python"
+
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_merge_insert.py:upsert_basic"
+        ```
+        **API Reference**: [lancedb.table.Table.merge_insert][]
+
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_merge_insert.py:upsert_basic_async"
+        ```
+        **API Reference**: [lancedb.table.AsyncTable.merge_insert][]
+
+=== "Typescript[^1]"
+
+    === "@lancedb/lancedb"
+
+        ```typescript
+        --8<-- "nodejs/examples/merge_insert.test.ts:upsert_basic"
+        ```
+        **API Reference**: [lancedb.Table.mergeInsert](../js/classes/Table.md/#mergeInsert)
+
+Read more in the guide on [merge insert](tables/merge_insert.md).
+
 ## Deleting from a table
 
 Use the `delete()` method on tables to delete rows from a table. To choose which rows to delete, provide a filter that matches on the metadata columns. This can delete any number of rows that match the filter.
 
 === "Python"
 
+    === "Sync API"
+
         ```python
-    tbl.delete('item = "fizz"')
+        --8<-- "python/python/tests/docs/test_guide_tables.py:delete_row"
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:delete_row_async"
         ```
 
     ### Deleting row with specific column value
 
+    === "Sync API"
+
         ```python
-    import lancedb
+        --8<-- "python/python/tests/docs/test_guide_tables.py:delete_specific_row"
+        ```
+    === "Async API"
 
-    data = [{"x": 1, "vector": [1, 2]},
+        ```python
-            {"x": 2, "vector": [3, 4]},
+        --8<-- "python/python/tests/docs/test_guide_tables.py:delete_specific_row_async"
-            {"x": 3, "vector": [5, 6]}]
-    db = lancedb.connect("./.lancedb")
-    table = db.create_table("my_table", data)
-    table.to_pandas()
-    #   x      vector
-    # 0  1  [1.0, 2.0]
-    # 1  2  [3.0, 4.0]
-    # 2  3  [5.0, 6.0]
-
-    table.delete("x = 2")
-    table.to_pandas()
-    #   x      vector
-    # 0  1  [1.0, 2.0]
-    # 1  3  [5.0, 6.0]
         ```
 
     ### Delete from a list of values
+    === "Sync API"
 
         ```python
-    to_remove = [1, 5]
+        --8<-- "python/python/tests/docs/test_guide_tables.py:delete_list_values"
-    to_remove = ", ".join(str(v) for v in to_remove)
+        ```
+    === "Async API"
 
-    table.delete(f"x IN ({to_remove})")
+        ```python
-    table.to_pandas()
+        --8<-- "python/python/tests/docs/test_guide_tables.py:delete_list_values_async"
-    #   x      vector
-    # 0  3  [5.0, 6.0]
         ```
 
 === "Typescript[^1]"
@@ -659,26 +724,19 @@ This can be used to update zero to all rows depending on how many rows match the
 === "Python"
 
     API Reference: [lancedb.table.Table.update][]
+    === "Sync API"
 
         ```python
-    import lancedb
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb"
-    import pandas as pd
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-pandas"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:update_table"
+        ```
+    === "Async API"
 
-    # Create a lancedb connection
+        ```python
-    db = lancedb.connect("./.lancedb")
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb"
-
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-pandas"
-    # Create a table from a pandas DataFrame
+        --8<-- "python/python/tests/docs/test_guide_tables.py:update_table_async"
-    data = pd.DataFrame({"x": [1, 2, 3], "vector": [[1, 2], [3, 4], [5, 6]]})
-    table = db.create_table("my_table", data)
-
-    # Update the table where x = 2
-    table.update(where="x = 2", values={"vector": [10, 10]})
-
-    # Get the updated table as a pandas DataFrame
-    df = table.to_pandas()
-
-    # Print the DataFrame
-    print(df)
         ```
 
     Output
@@ -707,7 +765,10 @@ This can be used to update zero to all rows depending on how many rows match the
         ];
         const tbl = await db.createTable("my_table", data)
 
-        await tbl.update({vector: [10, 10]}, { where: "x = 2"})
+        await tbl.update({ 
+            values: { vector: [10, 10] },
+            where: "x = 2"
+        });
         ```
 
     === "vectordb (deprecated)"
@@ -726,7 +787,10 @@ This can be used to update zero to all rows depending on how many rows match the
         ];
         const tbl = await db.createTable("my_table", data)
 
-        await tbl.update({ where: "x = 2", values: {vector: [10, 10]} })
+        await tbl.update({ 
+            where: "x = 2", 
+            values: { vector: [10, 10] } 
+        });
         ```
 
 #### Updating using a sql query
@@ -734,12 +798,15 @@ This can be used to update zero to all rows depending on how many rows match the
   The `values` parameter is used to provide the new values for the columns as literal values. You can also use the `values_sql` / `valuesSql` parameter to provide SQL expressions for the new values. For example, you can use `values_sql="x + 1"` to increment the value of the `x` column by 1.
 
 === "Python"
+    === "Sync API"
 
         ```python
-    # Update the table where x = 2
+        --8<-- "python/python/tests/docs/test_guide_tables.py:update_table_sql"
-    table.update(valuesSql={"x": "x + 1"})
+        ```
+    === "Async API"
 
-    print(table.to_pandas())
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:update_table_sql_async"
         ```
 
     Output
@@ -771,9 +838,14 @@ This can be used to update zero to all rows depending on how many rows match the
 Use the `drop_table()` method on the database to remove a table.
 
 === "Python"
+    === "Sync API"
 
         ```python
         --8<-- "python/python/tests/docs/test_basic.py:drop_table"
+        ```
+    === "Async API"
+
+        ```python
         --8<-- "python/python/tests/docs/test_basic.py:drop_table_async"
         ```
 
@@ -809,9 +881,16 @@ data type for it.
 
 === "Python"
 
+    === "Sync API"
+
         ```python
         --8<-- "python/python/tests/docs/test_basic.py:add_columns"
         ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_basic.py:add_columns_async"
+        ```
     **API Reference:** [lancedb.table.Table.add_columns][]
 
 === "Typescript"
@@ -848,10 +927,18 @@ rewriting the column, which can be a heavy operation.
 
 === "Python"
 
+    === "Sync API"
+
         ```python
-    import pyarrow as pa
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-pyarrow"
         --8<-- "python/python/tests/docs/test_basic.py:alter_columns"
         ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-pyarrow"
+        --8<-- "python/python/tests/docs/test_basic.py:alter_columns_async"
+        ```
     **API Reference:** [lancedb.table.Table.alter_columns][]
 
 === "Typescript"
@@ -872,9 +959,16 @@ will remove the column from the schema.
 
 === "Python"
 
+    === "Sync API"
+
         ```python
         --8<-- "python/python/tests/docs/test_basic.py:drop_columns"
         ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_basic.py:drop_columns_async"
+        ```
     **API Reference:** [lancedb.table.Table.drop_columns][]
 
 === "Typescript"
@@ -925,30 +1019,45 @@ There are three possible settings for `read_consistency_interval`:
 
     To set strong consistency, use `timedelta(0)`:
 
+    === "Sync API"
+
         ```python
-    from datetime import timedelta
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-datetime"
-    db = lancedb.connect("./.lancedb",. read_consistency_interval=timedelta(0))
+        --8<-- "python/python/tests/docs/test_guide_tables.py:table_strong_consistency"
-    table = db.open_table("my_table")
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-datetime"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:table_async_strong_consistency"
         ```
 
     For eventual consistency, use a custom `timedelta`:
 
+    === "Sync API"
+
         ```python
-    from datetime import timedelta
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-datetime"
-    db = lancedb.connect("./.lancedb", read_consistency_interval=timedelta(seconds=5))
+        --8<-- "python/python/tests/docs/test_guide_tables.py:table_eventual_consistency"
-    table = db.open_table("my_table")
+        ```
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_guide_tables.py:import-datetime"
+        --8<-- "python/python/tests/docs/test_guide_tables.py:table_async_eventual_consistency"
         ```
 
     By default, a `Table` will never check for updates from other writers. To manually check for updates you can use `checkout_latest`:
 
+    === "Sync API"
+
         ```python
-    db = lancedb.connect("./.lancedb")
+        --8<-- "python/python/tests/docs/test_guide_tables.py:table_checkout_latest"
-    table = db.open_table("my_table")
+        ```
+    === "Async API"
 
-    # (Other writes happen to my_table from another process)
+        ```python
-
+        --8<-- "python/python/tests/docs/test_guide_tables.py:table_async_checkout_latest"
-    # Check for updates
-    table.checkout_latest()
         ```
 
 === "Typescript[^1]"
@@ -957,14 +1066,14 @@ There are three possible settings for `read_consistency_interval`:
 
     ```ts
     const db = await lancedb.connect({ uri: "./.lancedb", readConsistencyInterval: 0 });
-    const table = await db.openTable("my_table");
+    const tbl = await db.openTable("my_table");
     ```
 
     For eventual consistency, specify the update interval as seconds:
 
     ```ts
     const db = await lancedb.connect({ uri: "./.lancedb", readConsistencyInterval: 5 });
-    const table = await db.openTable("my_table");
+    const tbl = await db.openTable("my_table");
     ```
 
 <!-- Node doesn't yet support the version time travel: https://github.com/lancedb/lancedb/issues/1007

docs/src/guides/tables/merge_insert.md

@@ -0,0 +1,135 @@
+The merge insert command is a flexible API that can be used to perform:
+
+1. Upsert
+2. Insert-if-not-exists
+3. Replace range
+
+It works by joining the input data with the target table on a key you provide.
+Often this key is a unique row id key. You can then specify what to do when
+there is a match and when there is not a match. For example, for upsert you want
+to update if the row has a match and insert if the row doesn't have a match.
+Whereas for insert-if-not-exists you only want to insert if the row doesn't have
+a match.
+
+You can also read more in the API reference:
+
+* Python
+    * Sync: [lancedb.table.Table.merge_insert][]
+    * Async: [lancedb.table.AsyncTable.merge_insert][]
+* Typescript: [lancedb.Table.mergeInsert](../../js/classes/Table.md/#mergeinsert)
+
+!!! tip "Use scalar indices to speed up merge insert"
+
+    The merge insert command needs to perform a join between the input data and the
+    target table on the `on` key you provide. This requires scanning that entire
+    column, which can be expensive for large tables. To speed up this operation,
+    you can create a scalar index on the `on` column, which will allow LanceDB to
+    find matches without having to scan the whole tables.
+
+    Read more about scalar indices in [Building a Scalar Index](../scalar_index.md)
+    guide.
+
+!!! info "Embedding Functions"
+
+    Like the create table and add APIs, the merge insert API will automatically
+    compute embeddings if the table has a embedding definition in its schema.
+    If the input data doesn't contain the source column, or the vector column
+    is already filled, then the embeddings won't be computed. See the
+    [Embedding Functions](../../embeddings/embedding_functions.md) guide for more
+    information.
+
+## Upsert
+
+Upsert updates rows if they exist and inserts them if they don't. To do this
+with merge insert, enable both `when_matched_update_all()` and
+`when_not_matched_insert_all()`.
+
+=== "Python"
+
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_merge_insert.py:upsert_basic"
+        ```
+
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_merge_insert.py:upsert_basic_async"
+        ```
+
+=== "Typescript"
+
+    === "@lancedb/lancedb"
+
+        ```typescript
+        --8<-- "nodejs/examples/merge_insert.test.ts:upsert_basic"
+        ```
+
+!!! note "Providing subsets of columns"
+
+    If a column is nullable, it can be omitted from input data and it will be
+    considered `null`. Columns can also be provided in any order.
+
+## Insert-if-not-exists
+
+To avoid inserting duplicate rows, you can use the insert-if-not-exists command.
+This will only insert rows that do not have a match in the target table. To do
+this with merge insert, enable just `when_not_matched_insert_all()`.
+
+
+=== "Python"
+
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_merge_insert.py:insert_if_not_exists"
+        ```
+
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_merge_insert.py:insert_if_not_exists_async"
+        ```
+
+=== "Typescript"
+
+    === "@lancedb/lancedb"
+
+        ```typescript
+        --8<-- "nodejs/examples/merge_insert.test.ts:insert_if_not_exists"
+        ```
+
+
+## Replace range
+
+You can also replace a range of rows in the target table with the input data.
+For example, if you have a table of document chunks, where each chunk has
+both a `doc_id` and a `chunk_id`, you can replace all chunks for a given
+`doc_id` with updated chunks. This can be tricky otherwise because if you
+try to use upsert when the new data has fewer chunks you will end up with
+extra chunks. To avoid this, add another clause to delete any chunks for
+the document that are not in the new data, with
+`when_not_matched_by_source_delete`.
+
+=== "Python"
+
+    === "Sync API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_merge_insert.py:replace_range"
+        ```
+
+    === "Async API"
+
+        ```python
+        --8<-- "python/python/tests/docs/test_merge_insert.py:replace_range_async"
+        ```
+
+=== "Typescript"
+
+    === "@lancedb/lancedb"
+
+        ```typescript
+        --8<-- "nodejs/examples/merge_insert.test.ts:replace_range"
+        ```

docs/src/guides/tuning_retrievers/1_query_types.md

@@ -1,8 +1,8 @@
 ## Improving retriever performance
 
-Try it yourself - <a href="https://colab.research.google.com/github/lancedb/lancedb/blob/main/docs/src/notebooks/lancedb_reranking.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a><br/>
+Try it yourself: <a href="https://colab.research.google.com/github/lancedb/lancedb/blob/main/docs/src/notebooks/lancedb_reranking.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a><br/>
 
-VectorDBs are used as retreivers in recommender or chatbot-based systems for retrieving relevant data based on user queries. For example, retriever is a critical component of Retrieval Augmented Generation (RAG) acrhitectures. In this section, we will discuss how to improve the performance of retrievers.
+VectorDBs are used as retrievers in recommender or chatbot-based systems for retrieving relevant data based on user queries. For example, retrievers are a critical component of Retrieval Augmented Generation (RAG) acrhitectures. In this section, we will discuss how to improve the performance of retrievers.
 
 There are serveral ways to improve the performance of retrievers. Some of the common techniques are:
 
@@ -19,7 +19,7 @@ Using different embedding models is something that's very specific to the use ca
 
 
 ## The dataset
-We'll be using a QA dataset generated using a LLama2 review paper. The dataset contains 221 query, context and answer triplets. The queries and answers are generated using GPT-4 based on a given query. Full script used to generate the dataset can be found on this [repo](https://github.com/lancedb/ragged). It can be downloaded from [here](https://github.com/AyushExel/assets/blob/main/data_qa.csv)
+We'll be using a QA dataset generated using a LLama2 review paper. The dataset contains 221 query, context and answer triplets. The queries and answers are generated using GPT-4 based on a given query. Full script used to generate the dataset can be found on this [repo](https://github.com/lancedb/ragged). It can be downloaded from [here](https://github.com/AyushExel/assets/blob/main/data_qa.csv).
 
 ### Using different query types
 Let's setup the embeddings and the dataset first. We'll use the LanceDB's `huggingface` embeddings integration for this guide. 
@@ -45,14 +45,14 @@ table.add(df[["context"]].to_dict(orient="records"))
 queries = df["query"].tolist()
 ```
 
-Now that we have the dataset and embeddings table set up, here's how you can run different query types on the dataset.
+Now that we have the dataset and embeddings table set up, here's how you can run different query types on the dataset:
 
 * <b> Vector Search: </b>
 
     ```python
     table.search(quries[0], query_type="vector").limit(5).to_pandas()
     ```
-    By default, LanceDB uses vector search query type for searching and it automatically converts the input query to a vector before searching when using embedding API. So, the following statement is equivalent to the above statement.
+    By default, LanceDB uses vector search query type for searching and it automatically converts the input query to a vector before searching when using embedding API. So, the following statement is equivalent to the above statement:
 
     ```python
     table.search(quries[0]).limit(5).to_pandas()
@@ -77,7 +77,7 @@ Now that we have the dataset and embeddings table set up, here's how you can run
 
 * <b> Hybrid Search: </b>
 
-    Hybrid search is a combination of vector and full-text search. Here's how you can run a hybrid search query on the dataset.
+    Hybrid search is a combination of vector and full-text search. Here's how you can run a hybrid search query on the dataset:
     ```python
     table.search(quries[0], query_type="hybrid").limit(5).to_pandas()
     ```
@@ -87,7 +87,7 @@ Now that we have the dataset and embeddings table set up, here's how you can run
 
     !!! note "Note"
         By default, it uses `LinearCombinationReranker` that combines the scores from vector and full-text search using a weighted linear combination. It is the simplest reranker implementation available in LanceDB. You can also use other rerankers like `CrossEncoderReranker` or `CohereReranker` for reranking the results.
-        Learn more about rerankers [here](https://lancedb.github.io/lancedb/reranking/)
+        Learn more about rerankers [here](https://lancedb.github.io/lancedb/reranking/).
 
     
 

docs/src/guides/tuning_retrievers/2_reranking.md

@@ -1,6 +1,6 @@
 Continuing from the previous section, we can now rerank the results using more complex rerankers.
 
-Try it yourself - <a href="https://colab.research.google.com/github/lancedb/lancedb/blob/main/docs/src/notebooks/lancedb_reranking.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a><br/>
+Try it yourself: <a href="https://colab.research.google.com/github/lancedb/lancedb/blob/main/docs/src/notebooks/lancedb_reranking.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a><br/>
 
 ## Reranking search results
 You can rerank any search results using a reranker. The syntax for reranking is as follows:
@@ -62,9 +62,6 @@ Let us take a look at the same datasets from the previous sections, using the sa
 | Reranked fts  | 0.672    |
 | Hybrid | 0.759 |
 
-### SQuAD Dataset
-
-
 ### Uber10K sec filing Dataset
 
 | Query Type | Hit-rate@5 |

docs/src/guides/tuning_retrievers/3_embed_tuning.md

@@ -1,5 +1,5 @@
 ## Finetuning the Embedding Model
-Try it yourself - <a href="https://colab.research.google.com/github/lancedb/lancedb/blob/main/docs/src/notebooks/embedding_tuner.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a><br/>
+Try it yourself: <a href="https://colab.research.google.com/github/lancedb/lancedb/blob/main/docs/src/notebooks/embedding_tuner.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a><br/>
 
 Another way to improve retriever performance is to fine-tune the embedding model itself. Fine-tuning the embedding model can help in learning better representations for the documents and queries in the dataset. This can be particularly useful when the dataset is very different from the pre-trained data used to train the embedding model.
 
@@ -16,7 +16,7 @@ validation_df.to_csv("data_val.csv", index=False)
 You can use any tuning API to fine-tune embedding models. In this example, we'll utilise Llama-index as it also comes with utilities for synthetic data generation and training the model. 
 
 
-Then parse the dataset as llama-index text nodes and generate synthetic QA pairs from each node.
+We parse the dataset as llama-index text nodes and generate synthetic QA pairs from each node:
 ```python
 from llama_index.core.node_parser import SentenceSplitter
 from llama_index.readers.file import PagedCSVReader
@@ -43,7 +43,7 @@ val_dataset = generate_qa_embedding_pairs(
 )
 ```
 
-Now we'll use `SentenceTransformersFinetuneEngine` engine to fine-tune the model. You can also use `sentence-transformers` or `transformers` library to fine-tune the model. 
+Now we'll use `SentenceTransformersFinetuneEngine` engine to fine-tune the model. You can also use `sentence-transformers` or `transformers` library to fine-tune the model:
 
 ```python
 from llama_index.finetuning import SentenceTransformersFinetuneEngine
@@ -57,7 +57,7 @@ finetune_engine = SentenceTransformersFinetuneEngine(
 finetune_engine.finetune()
 embed_model = finetune_engine.get_finetuned_model()
 ```
-This saves the fine tuned embedding model in `tuned_model` folder. This al
+This saves the fine tuned embedding model in `tuned_model` folder.
 
 # Evaluation results
 In order to eval the retriever, you can either use this model to ingest the data into LanceDB directly or llama-index's LanceDB integration to create a `VectorStoreIndex` and use it as a retriever. 

docs/src/hybrid_search/eval.md

@@ -3,22 +3,22 @@
 Hybrid Search is a broad (often misused) term. It can mean anything from combining multiple methods for searching, to applying ranking methods to better sort the results. In this blog, we use the definition of "hybrid search" to mean using a combination of keyword-based and vector search.
 
 ## The challenge of (re)ranking search results
-Once you have a group of the most relevant search results from multiple search sources, you'd likely standardize the score and rank them accordingly. This process can also be seen as another independent step - reranking.
+Once you have a group of the most relevant search results from multiple search sources, you'd likely standardize the score and rank them accordingly. This process can also be seen as another independent step: reranking.
 There are two approaches for reranking search results from multiple sources.
 
-* <b>Score-based</b>: Calculate final relevance scores based on a weighted linear combination of individual search algorithm scores. Example - Weighted linear combination of semantic search & keyword-based search results.
+* <b>Score-based</b>: Calculate final relevance scores based on a weighted linear combination of individual search algorithm scores. Example: Weighted linear combination of semantic search & keyword-based search results.
 
-* <b>Relevance-based</b>: Discards the existing scores and calculates the relevance of each search result - query pair. Example - Cross Encoder models
+* <b>Relevance-based</b>: Discards the existing scores and calculates the relevance of each search result-query pair. Example: Cross Encoder models
 
-Even though there are many strategies for reranking search results, none works for all cases. Moreover, evaluating them itself is a challenge. Also, reranking can be dataset, application specific so it's hard to generalize.
+Even though there are many strategies for reranking search results, none works for all cases. Moreover, evaluating them itself is a challenge. Also, reranking can be dataset or application specific so it's hard to generalize.
 
 ### Example evaluation of hybrid search with Reranking
 
-Here's some evaluation numbers from experiment comparing these re-rankers on about 800 queries. It is modified version of an evaluation script from [llama-index](https://github.com/run-llama/finetune-embedding/blob/main/evaluate.ipynb) that measures hit-rate at top-k.
+Here's some evaluation numbers from an experiment comparing these rerankers on about 800 queries. It is modified version of an evaluation script from [llama-index](https://github.com/run-llama/finetune-embedding/blob/main/evaluate.ipynb) that measures hit-rate at top-k.
 
 <b> With OpenAI ada2 embedding </b>
 
-Vector Search baseline - `0.64`
+Vector Search baseline: `0.64`
 
 | Reranker | Top-3 | Top-5 | Top-10 |
 | --- | --- | --- | --- |
@@ -33,7 +33,7 @@ Vector Search baseline - `0.64`
 
 <b> With OpenAI embedding-v3-small </b>
 
-Vector Search baseline - `0.59`
+Vector Search baseline: `0.59`
 
 | Reranker | Top-3 | Top-5 | Top-10 |
 | --- | --- | --- | --- |

docs/src/hybrid_search/hybrid_search.md

@@ -5,56 +5,45 @@ LanceDB supports both semantic and keyword-based search (also termed full-text s
 ## Hybrid search in LanceDB
 You can perform hybrid search in LanceDB by combining the results of semantic and full-text search via a reranking algorithm of your choice. LanceDB provides multiple rerankers out of the box. However, you can always write a custom reranker if your use case need more sophisticated logic .
 
+=== "Sync API"
+
     ```python
-import os
+    --8<-- "python/python/tests/docs/test_search.py:import-os"
-
+    --8<-- "python/python/tests/docs/test_search.py:import-openai"
-import lancedb
+    --8<-- "python/python/tests/docs/test_search.py:import-lancedb"
-import openai
+    --8<-- "python/python/tests/docs/test_search.py:import-embeddings"
-from lancedb.embeddings import get_registry
+    --8<-- "python/python/tests/docs/test_search.py:import-pydantic"
-from lancedb.pydantic import LanceModel, Vector
+    --8<-- "python/python/tests/docs/test_search.py:import-lancedb-fts"
-
+    --8<-- "python/python/tests/docs/test_search.py:import-openai-embeddings"
-db = lancedb.connect("~/.lancedb")
+    --8<-- "python/python/tests/docs/test_search.py:class-Documents"
-
+    --8<-- "python/python/tests/docs/test_search.py:basic_hybrid_search"
-# Ingest embedding function in LanceDB table
-# Configuring the environment variable OPENAI_API_KEY
-if "OPENAI_API_KEY" not in os.environ:
-# OR set the key here as a variable
-    openai.api_key = "sk-..."
-embeddings = get_registry().get("openai").create()
-
-class Documents(LanceModel):
-    vector: Vector(embeddings.ndims()) = embeddings.VectorField()
-    text: str = embeddings.SourceField()
-
-table = db.create_table("documents", schema=Documents)
-
-data = [
-    { "text": "rebel spaceships striking from a hidden base"},
-    { "text": "have won their first victory against the evil Galactic Empire"},
-    { "text": "during the battle rebel spies managed to steal secret plans"},
-    { "text": "to the Empire's ultimate weapon the Death Star"}
-]
-
-# ingest docs with auto-vectorization
-table.add(data)
-
-# Create a fts index before the hybrid search
-table.create_fts_index("text")
-# hybrid search with default re-ranker
-results = table.search("flower moon", query_type="hybrid").to_pandas()
     ```
+=== "Async API"
+
+    ```python
+    --8<-- "python/python/tests/docs/test_search.py:import-os"
+    --8<-- "python/python/tests/docs/test_search.py:import-openai"
+    --8<-- "python/python/tests/docs/test_search.py:import-lancedb"
+    --8<-- "python/python/tests/docs/test_search.py:import-embeddings"
+    --8<-- "python/python/tests/docs/test_search.py:import-pydantic"
+    --8<-- "python/python/tests/docs/test_search.py:import-lancedb-fts"
+    --8<-- "python/python/tests/docs/test_search.py:import-openai-embeddings"
+    --8<-- "python/python/tests/docs/test_search.py:class-Documents"
+    --8<-- "python/python/tests/docs/test_search.py:basic_hybrid_search_async"
+    ```
+
 !!! Note
     You can also pass the vector and text query manually. This is useful if you're not using the embedding API or if you're using a separate embedder service.
 ### Explicitly passing the vector and text query
-```python
+=== "Sync API"
-vector_query = [0.1, 0.2, 0.3, 0.4, 0.5]
-text_query = "flower moon"
-results = table.search(query_type="hybrid")
-                .vector(vector_query)
-                .text(text_query)
-                .limit(5)
-                .to_pandas()
 
+    ```python
+    --8<-- "python/python/tests/docs/test_search.py:hybrid_search_pass_vector_text"
+    ```
+=== "Async API"
+
+    ```python
+    --8<-- "python/python/tests/docs/test_search.py:hybrid_search_pass_vector_text_async"
     ```
 
 By default, LanceDB uses `RRFReranker()`, which uses reciprocal rank fusion score, to combine and rerank the results of semantic and full-text search. You can customize the hyperparameters as needed or write your own custom reranker. Here's how you can use any of the available rerankers:
@@ -68,7 +57,7 @@ By default, LanceDB uses `RRFReranker()`, which uses reciprocal rank fusion scor
 
 
 ## Available Rerankers
-LanceDB provides a number of re-rankers out of the box. You can use any of these re-rankers by passing them to the `rerank()` method. 
+LanceDB provides a number of rerankers out of the box. You can use any of these rerankers by passing them to the `rerank()` method. 
 Go to [Rerankers](../reranking/index.md) to learn more about using the available rerankers and implementing custom rerankers.
 
 

docs/src/index.md

@@ -4,6 +4,9 @@ LanceDB is an open-source vector database for AI that's designed to store, manag
 
 Both the database and the underlying data format are designed from the ground up to be **easy-to-use**, **scalable** and **cost-effective**.
 
+!!! tip "Hosted LanceDB"
+    If you want S3 cost-efficiency and local performance via a simple serverless API, checkout **LanceDB Cloud**. For private deployments, high performance at extreme scale, or if you have strict security requirements, talk to us about **LanceDB Enterprise**. [Learn more](https://docs.lancedb.com/)
+
 ![](assets/lancedb_and_lance.png)
 
 ## Truly multi-modal
@@ -20,7 +23,7 @@ LanceDB **OSS** is an **open-source**, batteries-included embedded vector databa
 
 LanceDB **Cloud** is a SaaS (software-as-a-service) solution that runs serverless in the cloud, making the storage clearly separated from compute. It's designed to be cost-effective and highly scalable without breaking the bank. LanceDB Cloud is currently in private beta with general availability coming soon, but you can apply for early access with the private beta release by signing up below.
 
-[Try out LanceDB Cloud](https://noteforms.com/forms/lancedb-mailing-list-cloud-kty1o5?notionforms=1&utm_source=notionforms){ .md-button .md-button--primary }
+[Try out LanceDB Cloud (Public Beta) Now](https://cloud.lancedb.com){ .md-button .md-button--primary }
 
 ## Why use LanceDB?
 

docs/src/integrations/langchain.md

@@ -108,7 +108,7 @@ This method creates a scalar(for non-vector cols) or a vector index on a table.
 |:---|:---|:---|:---|
 |`vector_col`|`Optional[str]`| Provide if you want to create index on a vector column. |`None`|
 |`col_name`|`Optional[str]`| Provide if you want to create index on a non-vector column. |`None`|
-|`metric`|`Optional[str]` |Provide the metric to use for vector index. choice of metrics: 'L2', 'dot', 'cosine'. |`L2`|
+|`metric`|`Optional[str]` |Provide the metric to use for vector index. choice of metrics: 'l2', 'dot', 'cosine'. |`l2`|
 |`num_partitions`|`Optional[int]`|Number of partitions to use for the index.|`256`|
 |`num_sub_vectors`|`Optional[int]` |Number of sub-vectors to use for the index.|`96`|
 |`index_cache_size`|`Optional[int]` |Size of the index cache.|`None`|

docs/src/integrations/llamaIndex.md

@@ -125,7 +125,7 @@ The exhaustive list of parameters for `LanceDBVectorStore` vector store are :
         ```               
 - **_table_exists(self, tbl_name: `Optional[str]` = `None`) -> `bool`** : Returns `True` if `tbl_name` exists in database.
 - __create_index(  
-  self, scalar: `Optional[bool]` = False, col_name: `Optional[str]` = None, num_partitions: `Optional[int]` = 256, num_sub_vectors: `Optional[int]` = 96, index_cache_size: `Optional[int]` = None, metric: `Optional[str]` = "L2",  
+  self, scalar: `Optional[bool]` = False, col_name: `Optional[str]` = None, num_partitions: `Optional[int]` = 256, num_sub_vectors: `Optional[int]` = 96, index_cache_size: `Optional[int]` = None, metric: `Optional[str]` = "l2",  
 ) -> `None`__ : Creates a scalar(for non-vector cols) or a vector index on a table.
         Make sure your vector column has enough data before creating an index on it.
 

docs/src/javascript/enums/MetricType.md

@@ -10,7 +10,7 @@ Distance metrics type.
 
 - [Cosine](MetricType.md#cosine)
 - [Dot](MetricType.md#dot)
-- [L2](MetricType.md#l2)
+- [l2](MetricType.md#l2)
 
 ## Enumeration Members
 

docs/src/javascript/interfaces/IvfPQIndexConfig.md

@@ -85,7 +85,7 @@ ___
 
 • `Optional` **metric\_type**: [`MetricType`](../enums/MetricType.md)
 
-Metric type, L2 or Cosine
+Metric type, l2 or Cosine
 
 #### Defined in
 

docs/src/js/README.md

@@ -15,11 +15,9 @@ npm install @lancedb/lancedb
 This will download the appropriate native library for your platform. We currently
 support:
 
-- Linux (x86_64 and aarch64)
+- Linux (x86_64 and aarch64 on glibc and musl)
 - MacOS (Intel and ARM/M1/M2)
-- Windows (x86_64 only)
+- Windows (x86_64 and aarch64)
-
-We do not yet support musl-based Linux (such as Alpine Linux) or aarch64 Windows.
 
 ## Usage
 
@@ -36,41 +34,8 @@ const results = await table.vectorSearch([0.1, 0.3]).limit(20).toArray();
 console.log(results);
 ```
 
-The [quickstart](../basic.md) contains a more complete example.
+The [quickstart](https://lancedb.github.io/lancedb/basic/) contains a more complete example.
 
 ## Development
 
-```sh
+See [CONTRIBUTING.md](_media/CONTRIBUTING.md) for information on how to contribute to LanceDB.
-npm run build
-npm run test
-```
-
-### Running lint / format
-
-LanceDb uses [biome](https://biomejs.dev/) for linting and formatting. if you are using VSCode you will need to install the official [Biome](https://marketplace.visualstudio.com/items?itemName=biomejs.biome) extension.
-To manually lint your code you can run:
-
-```sh
-npm run lint
-```
-
-to automatically fix all fixable issues:
-
-```sh
-npm run lint-fix
-```
-
-If you do not have your workspace root set to the `nodejs` directory, unfortunately the extension will not work. You can still run the linting and formatting commands manually.
-
-### Generating docs
-
-```sh
-npm run docs
-
-cd ../docs
-# Asssume the virtual environment was created
-# python3 -m venv venv
-# pip install -r requirements.txt
-. ./venv/bin/activate
-mkdocs build
-```

docs/src/js/_media/CONTRIBUTING.md

@@ -0,0 +1,76 @@
+# Contributing to LanceDB Typescript
+
+This document outlines the process for contributing to LanceDB Typescript.
+For general contribution guidelines, see [CONTRIBUTING.md](../CONTRIBUTING.md).
+
+## Project layout
+
+The Typescript package is a wrapper around the Rust library, `lancedb`. We use
+the [napi-rs](https://napi.rs/) library to create the bindings between Rust and
+Typescript.
+
+* `src/`: Rust bindings source code
+* `lancedb/`: Typescript package source code
+* `__test__/`: Unit tests
+* `examples/`: An npm package with the examples shown in the documentation
+
+## Development environment
+
+To set up your development environment, you will need to install the following:
+
+1. Node.js 14 or later
+2. Rust's package manager, Cargo. Use [rustup](https://rustup.rs/) to install.
+3. [protoc](https://grpc.io/docs/protoc-installation/) (Protocol Buffers compiler)
+
+Initial setup:
+
+```shell
+npm install
+```
+
+### Commit Hooks
+
+It is **highly recommended** to install the [pre-commit](https://pre-commit.com/) hooks to ensure that your
+code is formatted correctly and passes basic checks before committing:
+
+```shell
+pre-commit install
+```
+
+## Development
+
+Most common development commands can be run using the npm scripts.
+
+Build the package
+
+```shell
+npm install
+npm run build
+```
+
+Lint:
+
+```shell
+npm run lint
+```
+
+Format and fix lints:
+
+```shell
+npm run lint-fix
+```
+
+Run tests:
+
+```shell
+npm test
+```
+
+To run a single test:
+
+```shell
+# Single file: table.test.ts
+npm test -- table.test.ts
+# Single test: 'merge insert' in table.test.ts
+npm test -- table.test.ts --testNamePattern=merge\ insert
+```

docs/src/js/classes/BoostQuery.md

@@ -0,0 +1,67 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / BoostQuery
+
+# Class: BoostQuery
+
+Represents a full-text query interface.
+This interface defines the structure and behavior for full-text queries,
+including methods to retrieve the query type and convert the query to a dictionary format.
+
+## Implements
+
+- [`FullTextQuery`](../interfaces/FullTextQuery.md)
+
+## Constructors
+
+### new BoostQuery()
+
+```ts
+new BoostQuery(
+   positive,
+   negative,
+   options?): BoostQuery
+```
+
+Creates an instance of BoostQuery.
+The boost returns documents that match the positive query,
+but penalizes those that match the negative query.
+the penalty is controlled by the `negativeBoost` parameter.
+
+#### Parameters
+
+* **positive**: [`FullTextQuery`](../interfaces/FullTextQuery.md)
+    The positive query that boosts the relevance score.
+
+* **negative**: [`FullTextQuery`](../interfaces/FullTextQuery.md)
+    The negative query that reduces the relevance score.
+
+* **options?**
+    Optional parameters for the boost query.
+    - `negativeBoost`: The boost factor for the negative query (default is 0.0).
+
+* **options.negativeBoost?**: `number`
+
+#### Returns
+
+[`BoostQuery`](BoostQuery.md)
+
+## Methods
+
+### queryType()
+
+```ts
+queryType(): FullTextQueryType
+```
+
+The type of the full-text query.
+
+#### Returns
+
+[`FullTextQueryType`](../enumerations/FullTextQueryType.md)
+
+#### Implementation of
+
+[`FullTextQuery`](../interfaces/FullTextQuery.md).[`queryType`](../interfaces/FullTextQuery.md#querytype)

docs/src/js/classes/Connection.md

@@ -23,18 +23,6 @@ be closed when they are garbage collected.
 Any created tables are independent and will continue to work even if
 the underlying connection has been closed.
 
-## Constructors
-
-### new Connection()
-
-```ts
-new Connection(): Connection
-```
-
-#### Returns
-
-[`Connection`](Connection.md)
-
 ## Methods
 
 ### close()
@@ -71,7 +59,7 @@ Creates a new empty Table
 * **name**: `string`
     The name of the table.
 
-* **schema**: `SchemaLike`
+* **schema**: [`SchemaLike`](../type-aliases/SchemaLike.md)
     The schema of the table
 
 * **options?**: `Partial`<[`CreateTableOptions`](../interfaces/CreateTableOptions.md)>
@@ -117,7 +105,7 @@ Creates a new Table and initialize it with new data.
 * **name**: `string`
     The name of the table.
 
-* **data**: `TableLike` \| `Record`<`string`, `unknown`>[]
+* **data**: [`TableLike`](../type-aliases/TableLike.md) \| `Record`<`string`, `unknown`>[]
     Non-empty Array of Records
     to be inserted into the table
 
@@ -143,6 +131,20 @@ Return a brief description of the connection
 
 ***
 
+### dropAllTables()
+
+```ts
+abstract dropAllTables(): Promise<void>
+```
+
+Drop all tables in the database.
+
+#### Returns
+
+`Promise`&lt;`void`&gt;
+
+***
+
 ### dropTable()
 
 ```ts
@@ -189,7 +191,7 @@ Open a table in the database.
 * **name**: `string`
     The name of the table
 
-* **options?**: `Partial`&lt;`OpenTableOptions`&gt;
+* **options?**: `Partial`&lt;[`OpenTableOptions`](../interfaces/OpenTableOptions.md)&gt;
 
 #### Returns
 

docs/src/js/classes/Index.md

@@ -72,11 +72,9 @@ The results of a full text search are ordered by relevance measured by BM25.
 
 You can combine filters with full text search.
 
-For now, the full text search index only supports English, and doesn't support phrase search.
-
 #### Parameters
 
-* **options?**: `Partial`<`FtsOptions`>
+* **options?**: `Partial`<[`FtsOptions`](../interfaces/FtsOptions.md)>
 
 #### Returns
 
@@ -98,7 +96,7 @@ the vectors.
 
 #### Parameters
 
-* **options?**: `Partial`<`HnswPqOptions`>
+* **options?**: `Partial`<[`HnswPqOptions`](../interfaces/HnswPqOptions.md)>
 
 #### Returns
 
@@ -120,7 +118,38 @@ the vectors.
 
 #### Parameters
 
-* **options?**: `Partial`<`HnswSqOptions`>
+* **options?**: `Partial`<[`HnswSqOptions`](../interfaces/HnswSqOptions.md)>
+
+#### Returns
+
+[`Index`](Index.md)
+
+***
+
+### ivfFlat()
+
+```ts
+static ivfFlat(options?): Index
+```
+
+Create an IvfFlat index
+
+This index groups vectors into partitions of similar vectors.  Each partition keeps track of
+a centroid which is the average value of all vectors in the group.
+
+During a query the centroids are compared with the query vector to find the closest
+partitions.  The vectors in these partitions are then searched to find
+the closest vectors.
+
+The partitioning process is called IVF and the `num_partitions` parameter controls how
+many groups to create.
+
+Note that training an IVF FLAT index on a large dataset is a slow operation and
+currently is also a memory intensive operation.
+
+#### Parameters
+
+* **options?**: `Partial`<[`IvfFlatOptions`](../interfaces/IvfFlatOptions.md)>
 
 #### Returns
 

docs/src/js/classes/MatchQuery.md

@@ -0,0 +1,70 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / MatchQuery
+
+# Class: MatchQuery
+
+Represents a full-text query interface.
+This interface defines the structure and behavior for full-text queries,
+including methods to retrieve the query type and convert the query to a dictionary format.
+
+## Implements
+
+- [`FullTextQuery`](../interfaces/FullTextQuery.md)
+
+## Constructors
+
+### new MatchQuery()
+
+```ts
+new MatchQuery(
+   query,
+   column,
+   options?): MatchQuery
+```
+
+Creates an instance of MatchQuery.
+
+#### Parameters
+
+* **query**: `string`
+    The text query to search for.
+
+* **column**: `string`
+    The name of the column to search within.
+
+* **options?**
+    Optional parameters for the match query.
+    - `boost`: The boost factor for the query (default is 1.0).
+    - `fuzziness`: The fuzziness level for the query (default is 0).
+    - `maxExpansions`: The maximum number of terms to consider for fuzzy matching (default is 50).
+
+* **options.boost?**: `number`
+
+* **options.fuzziness?**: `number`
+
+* **options.maxExpansions?**: `number`
+
+#### Returns
+
+[`MatchQuery`](MatchQuery.md)
+
+## Methods
+
+### queryType()
+
+```ts
+queryType(): FullTextQueryType
+```
+
+The type of the full-text query.
+
+#### Returns
+
+[`FullTextQueryType`](../enumerations/FullTextQueryType.md)
+
+#### Implementation of
+
+[`FullTextQuery`](../interfaces/FullTextQuery.md).[`queryType`](../interfaces/FullTextQuery.md#querytype)

docs/src/js/classes/MergeInsertBuilder.md

@@ -0,0 +1,126 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / MergeInsertBuilder
+
+# Class: MergeInsertBuilder
+
+A builder used to create and run a merge insert operation
+
+## Constructors
+
+### new MergeInsertBuilder()
+
+```ts
+new MergeInsertBuilder(native, schema): MergeInsertBuilder
+```
+
+Construct a MergeInsertBuilder. __Internal use only.__
+
+#### Parameters
+
+* **native**: `NativeMergeInsertBuilder`
+
+* **schema**: `Schema`<`any`> \| `Promise`<`Schema`<`any`>>
+
+#### Returns
+
+[`MergeInsertBuilder`](MergeInsertBuilder.md)
+
+## Methods
+
+### execute()
+
+```ts
+execute(data): Promise<MergeStats>
+```
+
+Executes the merge insert operation
+
+#### Parameters
+
+* **data**: [`Data`](../type-aliases/Data.md)
+
+#### Returns
+
+`Promise`&lt;[`MergeStats`](../interfaces/MergeStats.md)&gt;
+
+Statistics about the merge operation: counts of inserted, updated, and deleted rows
+
+***
+
+### whenMatchedUpdateAll()
+
+```ts
+whenMatchedUpdateAll(options?): MergeInsertBuilder
+```
+
+Rows that exist in both the source table (new data) and
+the target table (old data) will be updated, replacing
+the old row with the corresponding matching row.
+
+If there are multiple matches then the behavior is undefined.
+Currently this causes multiple copies of the row to be created
+but that behavior is subject to change.
+
+An optional condition may be specified.  If it is, then only
+matched rows that satisfy the condtion will be updated.  Any
+rows that do not satisfy the condition will be left as they
+are.  Failing to satisfy the condition does not cause a
+"matched row" to become a "not matched" row.
+
+The condition should be an SQL string.  Use the prefix
+target. to refer to rows in the target table (old data)
+and the prefix source. to refer to rows in the source
+table (new data).
+
+For example, "target.last_update < source.last_update"
+
+#### Parameters
+
+* **options?**
+
+* **options.where?**: `string`
+
+#### Returns
+
+[`MergeInsertBuilder`](MergeInsertBuilder.md)
+
+***
+
+### whenNotMatchedBySourceDelete()
+
+```ts
+whenNotMatchedBySourceDelete(options?): MergeInsertBuilder
+```
+
+Rows that exist only in the target table (old data) will be
+deleted.  An optional condition can be provided to limit what
+data is deleted.
+
+#### Parameters
+
+* **options?**
+
+* **options.where?**: `string`
+    An optional condition to limit what data is deleted
+
+#### Returns
+
+[`MergeInsertBuilder`](MergeInsertBuilder.md)
+
+***
+
+### whenNotMatchedInsertAll()
+
+```ts
+whenNotMatchedInsertAll(): MergeInsertBuilder
+```
+
+Rows that exist only in the source table (new data) should
+be inserted into the target table.
+
+#### Returns
+
+[`MergeInsertBuilder`](MergeInsertBuilder.md)

docs/src/js/classes/MultiMatchQuery.md

@@ -0,0 +1,64 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / MultiMatchQuery
+
+# Class: MultiMatchQuery
+
+Represents a full-text query interface.
+This interface defines the structure and behavior for full-text queries,
+including methods to retrieve the query type and convert the query to a dictionary format.
+
+## Implements
+
+- [`FullTextQuery`](../interfaces/FullTextQuery.md)
+
+## Constructors
+
+### new MultiMatchQuery()
+
+```ts
+new MultiMatchQuery(
+   query,
+   columns,
+   options?): MultiMatchQuery
+```
+
+Creates an instance of MultiMatchQuery.
+
+#### Parameters
+
+* **query**: `string`
+    The text query to search for across multiple columns.
+
+* **columns**: `string`[]
+    An array of column names to search within.
+
+* **options?**
+    Optional parameters for the multi-match query.
+    - `boosts`: An array of boost factors for each column (default is 1.0 for all).
+
+* **options.boosts?**: `number`[]
+
+#### Returns
+
+[`MultiMatchQuery`](MultiMatchQuery.md)
+
+## Methods
+
+### queryType()
+
+```ts
+queryType(): FullTextQueryType
+```
+
+The type of the full-text query.
+
+#### Returns
+
+[`FullTextQueryType`](../enumerations/FullTextQueryType.md)
+
+#### Implementation of
+
+[`FullTextQuery`](../interfaces/FullTextQuery.md).[`queryType`](../interfaces/FullTextQuery.md#querytype)

docs/src/js/classes/PhraseQuery.md

@@ -0,0 +1,55 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / PhraseQuery
+
+# Class: PhraseQuery
+
+Represents a full-text query interface.
+This interface defines the structure and behavior for full-text queries,
+including methods to retrieve the query type and convert the query to a dictionary format.
+
+## Implements
+
+- [`FullTextQuery`](../interfaces/FullTextQuery.md)
+
+## Constructors
+
+### new PhraseQuery()
+
+```ts
+new PhraseQuery(query, column): PhraseQuery
+```
+
+Creates an instance of `PhraseQuery`.
+
+#### Parameters
+
+* **query**: `string`
+    The phrase to search for in the specified column.
+
+* **column**: `string`
+    The name of the column to search within.
+
+#### Returns
+
+[`PhraseQuery`](PhraseQuery.md)
+
+## Methods
+
+### queryType()
+
+```ts
+queryType(): FullTextQueryType
+```
+
+The type of the full-text query.
+
+#### Returns
+
+[`FullTextQueryType`](../enumerations/FullTextQueryType.md)
+
+#### Implementation of
+
+[`FullTextQuery`](../interfaces/FullTextQuery.md).[`queryType`](../interfaces/FullTextQuery.md#querytype)

docs/src/js/classes/Query.md

@@ -8,30 +8,14 @@
 
 A builder for LanceDB queries.
 
+## See
+
+[Table#query](Table.md#query), [Table#search](Table.md#search)
+
 ## Extends
 
 - [`QueryBase`](QueryBase.md)<`NativeQuery`>
 
-## Constructors
-
-### new Query()
-
-```ts
-new Query(tbl): Query
-```
-
-#### Parameters
-
-* **tbl**: `Table`
-
-#### Returns
-
-[`Query`](Query.md)
-
-#### Overrides
-
-[`QueryBase`](QueryBase.md).[`constructor`](QueryBase.md#constructors)
-
 ## Properties
 
 ### inner
@@ -46,39 +30,50 @@ protected inner: Query | Promise<Query>;
 
 ## Methods
 
-### \[asyncIterator\]()
+### analyzePlan()
 
 ```ts
-asyncIterator: AsyncIterator<RecordBatch<any>, any, undefined>
+analyzePlan(): Promise<string>
 ```
 
+Executes the query and returns the physical query plan annotated with runtime metrics.
+
+This is useful for debugging and performance analysis, as it shows how the query was executed
+and includes metrics such as elapsed time, rows processed, and I/O statistics.
+
 #### Returns
 
-`AsyncIterator`&lt;`RecordBatch`&lt;`any`&gt;, `any`, `undefined`&gt;
+`Promise`&lt;`string`&gt;
 
-#### Inherited from
+A query execution plan with runtime metrics for each step.
 
-[`QueryBase`](QueryBase.md).[`[asyncIterator]`](QueryBase.md#%5Basynciterator%5D)
+#### Example
-
-***
-
-### doCall()
 
 ```ts
-protected doCall(fn): void
+import * as lancedb from "@lancedb/lancedb"
+
+const db = await lancedb.connect("./.lancedb");
+const table = await db.createTable("my_table", [
+  { vector: [1.1, 0.9], id: "1" },
+]);
+
+const plan = await table.query().nearestTo([0.5, 0.2]).analyzePlan();
+
+Example output (with runtime metrics inlined):
+AnalyzeExec verbose=true, metrics=[]
+ ProjectionExec: expr=[id@3 as id, vector@0 as vector, _distance@2 as _distance], metrics=[output_rows=1, elapsed_compute=3.292µs]
+  Take: columns="vector, _rowid, _distance, (id)", metrics=[output_rows=1, elapsed_compute=66.001µs, batches_processed=1, bytes_read=8, iops=1, requests=1]
+   CoalesceBatchesExec: target_batch_size=1024, metrics=[output_rows=1, elapsed_compute=3.333µs]
+    GlobalLimitExec: skip=0, fetch=10, metrics=[output_rows=1, elapsed_compute=167ns]
+     FilterExec: _distance@2 IS NOT NULL, metrics=[output_rows=1, elapsed_compute=8.542µs]
+      SortExec: TopK(fetch=10), expr=[_distance@2 ASC NULLS LAST], metrics=[output_rows=1, elapsed_compute=63.25µs, row_replacements=1]
+       KNNVectorDistance: metric=l2, metrics=[output_rows=1, elapsed_compute=114.333µs, output_batches=1]
+        LanceScan: uri=/path/to/data, projection=[vector], row_id=true, row_addr=false, ordered=false, metrics=[output_rows=1, elapsed_compute=103.626µs, bytes_read=549, iops=2, requests=2]
 ```
 
-#### Parameters
-
-* **fn**
-
-#### Returns
-
-`void`
-
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`doCall`](QueryBase.md#docall)
+[`QueryBase`](QueryBase.md).[`analyzePlan`](QueryBase.md#analyzeplan)
 
 ***
 
@@ -92,7 +87,7 @@ Execute the query and return the results as an
 
 #### Parameters
 
-* **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
+* **options?**: `Partial`&lt;[`QueryExecutionOptions`](../interfaces/QueryExecutionOptions.md)&gt;
 
 #### Returns
 
@@ -161,7 +156,7 @@ fastSearch(): this
 Skip searching un-indexed data. This can make search faster, but will miss
 any data that is not yet indexed.
 
-Use lancedb.Table#optimize to index all un-indexed data.
+Use [Table#optimize](Table.md#optimize) to index all un-indexed data.
 
 #### Returns
 
@@ -189,7 +184,7 @@ A filter statement to be applied to this query.
 
 `this`
 
-#### Alias
+#### See
 
 where
 
@@ -211,9 +206,9 @@ fullTextSearch(query, options?): this
 
 #### Parameters
 
-* **query**: `string`
+* **query**: `string` \| [`FullTextQuery`](../interfaces/FullTextQuery.md)
 
-* **options?**: `Partial`&lt;`FullTextSearchOptions`&gt;
+* **options?**: `Partial`&lt;[`FullTextSearchOptions`](../interfaces/FullTextSearchOptions.md)&gt;
 
 #### Returns
 
@@ -250,26 +245,6 @@ called then every valid row from the table will be returned.
 
 ***
 
-### nativeExecute()
-
-```ts
-protected nativeExecute(options?): Promise<RecordBatchIterator>
-```
-
-#### Parameters
-
-* **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
-
-#### Returns
-
-`Promise`&lt;`RecordBatchIterator`&gt;
-
-#### Inherited from
-
-[`QueryBase`](QueryBase.md).[`nativeExecute`](QueryBase.md#nativeexecute)
-
-***
-
 ### nearestTo()
 
 ```ts
@@ -294,7 +269,7 @@ If there is more than one vector column you must use
 
 #### Parameters
 
-* **vector**: `IntoVector`
+* **vector**: [`IntoVector`](../type-aliases/IntoVector.md)
 
 #### Returns
 
@@ -334,7 +309,7 @@ nearestToText(query, columns?): Query
 
 #### Parameters
 
-* **query**: `string`
+* **query**: `string` \| [`FullTextQuery`](../interfaces/FullTextQuery.md)
 
 * **columns?**: `string`[]
 
@@ -427,7 +402,7 @@ Collect the results as an array of objects.
 
 #### Parameters
 
-* **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
+* **options?**: `Partial`&lt;[`QueryExecutionOptions`](../interfaces/QueryExecutionOptions.md)&gt;
 
 #### Returns
 
@@ -449,7 +424,7 @@ Collect the results as an Arrow
 
 #### Parameters
 
-* **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
+* **options?**: `Partial`&lt;[`QueryExecutionOptions`](../interfaces/QueryExecutionOptions.md)&gt;
 
 #### Returns
 

docs/src/js/classes/QueryBase.md

@@ -8,6 +8,11 @@
 
 Common methods supported by all query types
 
+## See
+
+ - [Query](Query.md)
+ - [VectorQuery](VectorQuery.md)
+
 ## Extended by
 
 - [`Query`](Query.md)
@@ -21,22 +26,6 @@ Common methods supported by all query types
 
 - `AsyncIterable`<`RecordBatch`>
 
-## Constructors
-
-### new QueryBase()
-
-```ts
-protected new QueryBase<NativeQueryType>(inner): QueryBase<NativeQueryType>
-```
-
-#### Parameters
-
-* **inner**: `NativeQueryType` \| `Promise`&lt;`NativeQueryType`&gt;
-
-#### Returns
-
-[`QueryBase`](QueryBase.md)&lt;`NativeQueryType`&gt;
-
 ## Properties
 
 ### inner
@@ -47,36 +36,47 @@ protected inner: NativeQueryType | Promise<NativeQueryType>;
 
 ## Methods
 
-### \[asyncIterator\]()
+### analyzePlan()
 
 ```ts
-asyncIterator: AsyncIterator<RecordBatch<any>, any, undefined>
+analyzePlan(): Promise<string>
 ```
 
+Executes the query and returns the physical query plan annotated with runtime metrics.
+
+This is useful for debugging and performance analysis, as it shows how the query was executed
+and includes metrics such as elapsed time, rows processed, and I/O statistics.
+
 #### Returns
 
-`AsyncIterator`&lt;`RecordBatch`&lt;`any`&gt;, `any`, `undefined`&gt;
+`Promise`&lt;`string`&gt;
 
-#### Implementation of
+A query execution plan with runtime metrics for each step.
 
-`AsyncIterable.[asyncIterator]`
+#### Example
-
-***
-
-### doCall()
 
 ```ts
-protected doCall(fn): void
+import * as lancedb from "@lancedb/lancedb"
+
+const db = await lancedb.connect("./.lancedb");
+const table = await db.createTable("my_table", [
+  { vector: [1.1, 0.9], id: "1" },
+]);
+
+const plan = await table.query().nearestTo([0.5, 0.2]).analyzePlan();
+
+Example output (with runtime metrics inlined):
+AnalyzeExec verbose=true, metrics=[]
+ ProjectionExec: expr=[id@3 as id, vector@0 as vector, _distance@2 as _distance], metrics=[output_rows=1, elapsed_compute=3.292µs]
+  Take: columns="vector, _rowid, _distance, (id)", metrics=[output_rows=1, elapsed_compute=66.001µs, batches_processed=1, bytes_read=8, iops=1, requests=1]
+   CoalesceBatchesExec: target_batch_size=1024, metrics=[output_rows=1, elapsed_compute=3.333µs]
+    GlobalLimitExec: skip=0, fetch=10, metrics=[output_rows=1, elapsed_compute=167ns]
+     FilterExec: _distance@2 IS NOT NULL, metrics=[output_rows=1, elapsed_compute=8.542µs]
+      SortExec: TopK(fetch=10), expr=[_distance@2 ASC NULLS LAST], metrics=[output_rows=1, elapsed_compute=63.25µs, row_replacements=1]
+       KNNVectorDistance: metric=l2, metrics=[output_rows=1, elapsed_compute=114.333µs, output_batches=1]
+        LanceScan: uri=/path/to/data, projection=[vector], row_id=true, row_addr=false, ordered=false, metrics=[output_rows=1, elapsed_compute=103.626µs, bytes_read=549, iops=2, requests=2]
 ```
 
-#### Parameters
-
-* **fn**
-
-#### Returns
-
-`void`
-
 ***
 
 ### execute()
@@ -89,7 +89,7 @@ Execute the query and return the results as an
 
 #### Parameters
 
-* **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
+* **options?**: `Partial`&lt;[`QueryExecutionOptions`](../interfaces/QueryExecutionOptions.md)&gt;
 
 #### Returns
 
@@ -150,7 +150,7 @@ fastSearch(): this
 Skip searching un-indexed data. This can make search faster, but will miss
 any data that is not yet indexed.
 
-Use lancedb.Table#optimize to index all un-indexed data.
+Use [Table#optimize](Table.md#optimize) to index all un-indexed data.
 
 #### Returns
 
@@ -174,7 +174,7 @@ A filter statement to be applied to this query.
 
 `this`
 
-#### Alias
+#### See
 
 where
 
@@ -192,9 +192,9 @@ fullTextSearch(query, options?): this
 
 #### Parameters
 
-* **query**: `string`
+* **query**: `string` \| [`FullTextQuery`](../interfaces/FullTextQuery.md)
 
-* **options?**: `Partial`&lt;`FullTextSearchOptions`&gt;
+* **options?**: `Partial`&lt;[`FullTextSearchOptions`](../interfaces/FullTextSearchOptions.md)&gt;
 
 #### Returns
 
@@ -223,22 +223,6 @@ called then every valid row from the table will be returned.
 
 ***
 
-### nativeExecute()
-
-```ts
-protected nativeExecute(options?): Promise<RecordBatchIterator>
-```
-
-#### Parameters
-
-* **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
-
-#### Returns
-
-`Promise`&lt;`RecordBatchIterator`&gt;
-
-***
-
 ### offset()
 
 ```ts
@@ -314,7 +298,7 @@ Collect the results as an array of objects.
 
 #### Parameters
 
-* **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
+* **options?**: `Partial`&lt;[`QueryExecutionOptions`](../interfaces/QueryExecutionOptions.md)&gt;
 
 #### Returns
 
@@ -332,7 +316,7 @@ Collect the results as an Arrow
 
 #### Parameters
 
-* **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
+* **options?**: `Partial`&lt;[`QueryExecutionOptions`](../interfaces/QueryExecutionOptions.md)&gt;
 
 #### Returns
 

docs/src/js/classes/Table.md

@@ -14,21 +14,13 @@ will be freed when the Table is garbage collected.  To eagerly free the cache yo
 can call the `close` method.  Once the Table is closed, it cannot be used for any
 further operations.
 
+Tables are created using the methods [Connection#createTable](Connection.md#createtable)
+and [Connection#createEmptyTable](Connection.md#createemptytable). Existing tables are opened
+using [Connection#openTable](Connection.md#opentable).
+
 Closing a table is optional.  It not closed, it will be closed when it is garbage
 collected.
 
-## Constructors
-
-### new Table()
-
-```ts
-new Table(): Table
-```
-
-#### Returns
-
-[`Table`](Table.md)
-
 ## Accessors
 
 ### name
@@ -125,8 +117,8 @@ wish to return to standard mode, call `checkoutLatest`.
 
 #### Parameters
 
-* **version**: `number`
+* **version**: `string` \| `number`
-    The version to checkout
+    The version to checkout, could be version number or tag
 
 #### Returns
 
@@ -216,6 +208,9 @@ Indices on vector columns will speed up vector searches.
 Indices on scalar columns will speed up filtering (in both
 vector and non-vector searches)
 
+We currently don't support custom named indexes.
+The index name will always be `${column}_idx`.
+
 #### Parameters
 
 * **column**: `string`
@@ -226,11 +221,6 @@ vector and non-vector searches)
 
 `Promise`<`void`>
 
-#### Note
-
-We currently don't support custom named indexes,
-The index name will always be `${column}_idx`
-
 #### Examples
 
 ```ts
@@ -317,6 +307,28 @@ then call ``cleanup_files`` to remove the old files.
 
 ***
 
+### dropIndex()
+
+```ts
+abstract dropIndex(name): Promise<void>
+```
+
+Drop an index from the table.
+
+#### Parameters
+
+* **name**: `string`
+    The name of the index.
+    This does not delete the index from disk, it just removes it from the table.
+    To delete the index, run [Table#optimize](Table.md#optimize) after dropping the index.
+    Use [Table.listIndices](Table.md#listindices) to find the names of the indices.
+
+#### Returns
+
+`Promise`&lt;`void`&gt;
+
+***
+
 ### indexStats()
 
 ```ts
@@ -336,6 +348,8 @@ List all the stats of a specified index
 
 The stats of the index. If the index does not exist, it will return undefined
 
+Use [Table.listIndices](Table.md#listindices) to find the names of the indices.
+
 ***
 
 ### isOpen()
@@ -376,7 +390,7 @@ List all the versions of the table
 
 #### Returns
 
-`Promise`&lt;`Version`[]&gt;
+`Promise`&lt;[`Version`](../interfaces/Version.md)[]&gt;
 
 ***
 
@@ -392,7 +406,7 @@ abstract mergeInsert(on): MergeInsertBuilder
 
 #### Returns
 
-`MergeInsertBuilder`
+[`MergeInsertBuilder`](MergeInsertBuilder.md)
 
 ***
 
@@ -436,7 +450,29 @@ Modeled after ``VACUUM`` in PostgreSQL.
 
 #### Returns
 
-`Promise`&lt;`OptimizeStats`&gt;
+`Promise`&lt;[`OptimizeStats`](../interfaces/OptimizeStats.md)&gt;
+
+***
+
+### prewarmIndex()
+
+```ts
+abstract prewarmIndex(name): Promise<void>
+```
+
+Prewarm an index in the table.
+
+#### Parameters
+
+* **name**: `string`
+    The name of the index.
+    This will load the index into memory.  This may reduce the cold-start time for
+    future queries.  If the index does not fit in the cache then this call may be
+    wasteful.
+
+#### Returns
+
+`Promise`&lt;`void`&gt;
 
 ***
 
@@ -553,7 +589,7 @@ Get the schema of the table.
 abstract search(
    query,
    queryType?,
-   ftsColumns?): VectorQuery | Query
+   ftsColumns?): Query | VectorQuery
 ```
 
 Create a search query to find the nearest neighbors
@@ -561,7 +597,7 @@ of the given query
 
 #### Parameters
 
-* **query**: `string` \| `IntoVector`
+* **query**: `string` \| [`IntoVector`](../type-aliases/IntoVector.md) \| [`FullTextQuery`](../interfaces/FullTextQuery.md)
     the query, a vector or string
 
 * **queryType?**: `string`
@@ -575,7 +611,51 @@ of the given query
 
 #### Returns
 
-[`VectorQuery`](VectorQuery.md) \| [`Query`](Query.md)
+[`Query`](Query.md) \| [`VectorQuery`](VectorQuery.md)
+
+***
+
+### stats()
+
+```ts
+abstract stats(): Promise<TableStatistics>
+```
+
+Returns table and fragment statistics
+
+#### Returns
+
+`Promise`&lt;[`TableStatistics`](../interfaces/TableStatistics.md)&gt;
+
+The table and fragment statistics
+
+***
+
+### tags()
+
+```ts
+abstract tags(): Promise<Tags>
+```
+
+Get a tags manager for this table.
+
+Tags allow you to label specific versions of a table with a human-readable name.
+The returned tags manager can be used to list, create, update, or delete tags.
+
+#### Returns
+
+`Promise`&lt;[`Tags`](Tags.md)&gt;
+
+A tags manager for this table
+
+#### Example
+
+```typescript
+const tagsManager = await table.tags();
+await tagsManager.create("v1", 1);
+const tags = await tagsManager.list();
+console.log(tags); // { "v1": { version: 1, manifestSize: ... } }
+```
 
 ***
 
@@ -694,7 +774,7 @@ by `query`.
 
 #### Parameters
 
-* **vector**: `IntoVector`
+* **vector**: [`IntoVector`](../type-aliases/IntoVector.md)
 
 #### Returns
 
@@ -720,35 +800,23 @@ Retrieve the version of the table
 
 ***
 
-### parseTableData()
+### waitForIndex()
 
 ```ts
-static parseTableData(
+abstract waitForIndex(indexNames, timeoutSeconds): Promise<void>
-   data,
-   options?,
-   streaming?): Promise<object>
 ```
 
+Waits for asynchronous indexing to complete on the table.
+
 #### Parameters
 
-* **data**: `TableLike` \| `Record`&lt;`string`, `unknown`&gt;[]
+* **indexNames**: `string`[]
+    The name of the indices to wait for
 
-* **options?**: `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
+* **timeoutSeconds**: `number`
-
+    The number of seconds to wait before timing out
-* **streaming?**: `boolean` = `false`
+    This will raise an error if the indices are not created and fully indexed within the timeout.
 
 #### Returns
 
-`Promise`&lt;`object`&gt;
+`Promise`&lt;`void`&gt;
-
-##### buf
-
-```ts
-buf: Buffer;
-```
-
-##### mode
-
-```ts
-mode: string;
-```

docs/src/js/classes/TagContents.md

@@ -0,0 +1,35 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / TagContents
+
+# Class: TagContents
+
+## Constructors
+
+### new TagContents()
+
+```ts
+new TagContents(): TagContents
+```
+
+#### Returns
+
+[`TagContents`](TagContents.md)
+
+## Properties
+
+### manifestSize
+
+```ts
+manifestSize: number;
+```
+
+***
+
+### version
+
+```ts
+version: number;
+```

docs/src/js/classes/Tags.md

@@ -0,0 +1,99 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / Tags
+
+# Class: Tags
+
+## Constructors
+
+### new Tags()
+
+```ts
+new Tags(): Tags
+```
+
+#### Returns
+
+[`Tags`](Tags.md)
+
+## Methods
+
+### create()
+
+```ts
+create(tag, version): Promise<void>
+```
+
+#### Parameters
+
+* **tag**: `string`
+
+* **version**: `number`
+
+#### Returns
+
+`Promise`&lt;`void`&gt;
+
+***
+
+### delete()
+
+```ts
+delete(tag): Promise<void>
+```
+
+#### Parameters
+
+* **tag**: `string`
+
+#### Returns
+
+`Promise`&lt;`void`&gt;
+
+***
+
+### getVersion()
+
+```ts
+getVersion(tag): Promise<number>
+```
+
+#### Parameters
+
+* **tag**: `string`
+
+#### Returns
+
+`Promise`&lt;`number`&gt;
+
+***
+
+### list()
+
+```ts
+list(): Promise<Record<string, TagContents>>
+```
+
+#### Returns
+
+`Promise`&lt;`Record`&lt;`string`, [`TagContents`](TagContents.md)&gt;&gt;
+
+***
+
+### update()
+
+```ts
+update(tag, version): Promise<void>
+```
+
+#### Parameters
+
+* **tag**: `string`
+
+* **version**: `number`
+
+#### Returns
+
+`Promise`&lt;`void`&gt;

docs/src/js/classes/VectorQuery.md

@@ -10,30 +10,14 @@ A builder used to construct a vector search
 
 This builder can be reused to execute the query many times.
 
+## See
+
+[Query#nearestTo](Query.md#nearestto)
+
 ## Extends
 
 - [`QueryBase`](QueryBase.md)<`NativeVectorQuery`>
 
-## Constructors
-
-### new VectorQuery()
-
-```ts
-new VectorQuery(inner): VectorQuery
-```
-
-#### Parameters
-
-* **inner**: `VectorQuery` \| `Promise`<`VectorQuery`>
-
-#### Returns
-
-[`VectorQuery`](VectorQuery.md)
-
-#### Overrides
-
-[`QueryBase`](QueryBase.md).[`constructor`](QueryBase.md#constructors)
-
 ## Properties
 
 ### inner
@@ -48,22 +32,6 @@ protected inner: VectorQuery | Promise<VectorQuery>;
 
 ## Methods
 
-### \[asyncIterator\]()
-
-```ts
-asyncIterator: AsyncIterator<RecordBatch<any>, any, undefined>
-```
-
-#### Returns
-
-`AsyncIterator`&lt;`RecordBatch`&lt;`any`&gt;, `any`, `undefined`&gt;
-
-#### Inherited from
-
-[`QueryBase`](QueryBase.md).[`[asyncIterator]`](QueryBase.md#%5Basynciterator%5D)
-
-***
-
 ### addQueryVector()
 
 ```ts
@@ -72,7 +40,7 @@ addQueryVector(vector): VectorQuery
 
 #### Parameters
 
-* **vector**: `IntoVector`
+* **vector**: [`IntoVector`](../type-aliases/IntoVector.md)
 
 #### Returns
 
@@ -80,6 +48,53 @@ addQueryVector(vector): VectorQuery
 
 ***
 
+### analyzePlan()
+
+```ts
+analyzePlan(): Promise<string>
+```
+
+Executes the query and returns the physical query plan annotated with runtime metrics.
+
+This is useful for debugging and performance analysis, as it shows how the query was executed
+and includes metrics such as elapsed time, rows processed, and I/O statistics.
+
+#### Returns
+
+`Promise`&lt;`string`&gt;
+
+A query execution plan with runtime metrics for each step.
+
+#### Example
+
+```ts
+import * as lancedb from "@lancedb/lancedb"
+
+const db = await lancedb.connect("./.lancedb");
+const table = await db.createTable("my_table", [
+  { vector: [1.1, 0.9], id: "1" },
+]);
+
+const plan = await table.query().nearestTo([0.5, 0.2]).analyzePlan();
+
+Example output (with runtime metrics inlined):
+AnalyzeExec verbose=true, metrics=[]
+ ProjectionExec: expr=[id@3 as id, vector@0 as vector, _distance@2 as _distance], metrics=[output_rows=1, elapsed_compute=3.292µs]
+  Take: columns="vector, _rowid, _distance, (id)", metrics=[output_rows=1, elapsed_compute=66.001µs, batches_processed=1, bytes_read=8, iops=1, requests=1]
+   CoalesceBatchesExec: target_batch_size=1024, metrics=[output_rows=1, elapsed_compute=3.333µs]
+    GlobalLimitExec: skip=0, fetch=10, metrics=[output_rows=1, elapsed_compute=167ns]
+     FilterExec: _distance@2 IS NOT NULL, metrics=[output_rows=1, elapsed_compute=8.542µs]
+      SortExec: TopK(fetch=10), expr=[_distance@2 ASC NULLS LAST], metrics=[output_rows=1, elapsed_compute=63.25µs, row_replacements=1]
+       KNNVectorDistance: metric=l2, metrics=[output_rows=1, elapsed_compute=114.333µs, output_batches=1]
+        LanceScan: uri=/path/to/data, projection=[vector], row_id=true, row_addr=false, ordered=false, metrics=[output_rows=1, elapsed_compute=103.626µs, bytes_read=549, iops=2, requests=2]
+```
+
+#### Inherited from
+
+[`QueryBase`](QueryBase.md).[`analyzePlan`](QueryBase.md#analyzeplan)
+
+***
+
 ### bypassVectorIndex()
 
 ```ts
@@ -128,6 +143,24 @@ whose data type is a fixed-size-list of floats.
 
 ***
 
+### distanceRange()
+
+```ts
+distanceRange(lowerBound?, upperBound?): VectorQuery
+```
+
+#### Parameters
+
+* **lowerBound?**: `number`
+
+* **upperBound?**: `number`
+
+#### Returns
+
+[`VectorQuery`](VectorQuery.md)
+
+***
+
 ### distanceType()
 
 ```ts
@@ -161,26 +194,6 @@ By default "l2" is used.
 
 ***
 
-### doCall()
-
-```ts
-protected doCall(fn): void
-```
-
-#### Parameters
-
-* **fn**
-
-#### Returns
-
-`void`
-
-#### Inherited from
-
-[`QueryBase`](QueryBase.md).[`doCall`](QueryBase.md#docall)
-
-***
-
 ### ef()
 
 ```ts
@@ -215,7 +228,7 @@ Execute the query and return the results as an
 
 #### Parameters
 
-* **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
+* **options?**: `Partial`&lt;[`QueryExecutionOptions`](../interfaces/QueryExecutionOptions.md)&gt;
 
 #### Returns
 
@@ -284,7 +297,7 @@ fastSearch(): this
 Skip searching un-indexed data. This can make search faster, but will miss
 any data that is not yet indexed.
 
-Use lancedb.Table#optimize to index all un-indexed data.
+Use [Table#optimize](Table.md#optimize) to index all un-indexed data.
 
 #### Returns
 
@@ -312,7 +325,7 @@ A filter statement to be applied to this query.
 
 `this`
 
-#### Alias
+#### See
 
 where
 
@@ -334,9 +347,9 @@ fullTextSearch(query, options?): this
 
 #### Parameters
 
-* **query**: `string`
+* **query**: `string` \| [`FullTextQuery`](../interfaces/FullTextQuery.md)
 
-* **options?**: `Partial`&lt;`FullTextSearchOptions`&gt;
+* **options?**: `Partial`&lt;[`FullTextSearchOptions`](../interfaces/FullTextSearchOptions.md)&gt;
 
 #### Returns
 
@@ -373,26 +386,6 @@ called then every valid row from the table will be returned.
 
 ***
 
-### nativeExecute()
-
-```ts
-protected nativeExecute(options?): Promise<RecordBatchIterator>
-```
-
-#### Parameters
-
-* **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
-
-#### Returns
-
-`Promise`&lt;`RecordBatchIterator`&gt;
-
-#### Inherited from
-
-[`QueryBase`](QueryBase.md).[`nativeExecute`](QueryBase.md#nativeexecute)
-
-***
-
 ### nprobes()
 
 ```ts
@@ -528,6 +521,22 @@ distance between the query vector and the actual uncompressed vector.
 
 ***
 
+### rerank()
+
+```ts
+rerank(reranker): VectorQuery
+```
+
+#### Parameters
+
+* **reranker**: [`Reranker`](../namespaces/rerankers/interfaces/Reranker.md)
+
+#### Returns
+
+[`VectorQuery`](VectorQuery.md)
+
+***
+
 ### select()
 
 ```ts
@@ -591,7 +600,7 @@ Collect the results as an array of objects.
 
 #### Parameters
 
-* **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
+* **options?**: `Partial`&lt;[`QueryExecutionOptions`](../interfaces/QueryExecutionOptions.md)&gt;
 
 #### Returns
 
@@ -613,7 +622,7 @@ Collect the results as an Arrow
 
 #### Parameters
 
-* **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
+* **options?**: `Partial`&lt;[`QueryExecutionOptions`](../interfaces/QueryExecutionOptions.md)&gt;
 
 #### Returns
 

docs/src/js/enumerations/FullTextQueryType.md

@@ -0,0 +1,46 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / FullTextQueryType
+
+# Enumeration: FullTextQueryType
+
+Enum representing the types of full-text queries supported.
+
+- `Match`: Performs a full-text search for terms in the query string.
+- `MatchPhrase`: Searches for an exact phrase match in the text.
+- `Boost`: Boosts the relevance score of specific terms in the query.
+- `MultiMatch`: Searches across multiple fields for the query terms.
+
+## Enumeration Members
+
+### Boost
+
+```ts
+Boost: "boost";
+```
+
+***
+
+### Match
+
+```ts
+Match: "match";
+```
+
+***
+
+### MatchPhrase
+
+```ts
+MatchPhrase: "match_phrase";
+```
+
+***
+
+### MultiMatch
+
+```ts
+MultiMatch: "multi_match";
+```

docs/src/js/enumerations/WriteMode.md

@@ -1,33 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / WriteMode
-
-# Enumeration: WriteMode
-
-Write mode for writing a table.
-
-## Enumeration Members
-
-### Append
-
-```ts
-Append: "Append";
-```
-
-***
-
-### Create
-
-```ts
-Create: "Create";
-```
-
-***
-
-### Overwrite
-
-```ts
-Overwrite: "Overwrite";
-```

docs/src/js/functions/connect.md

@@ -6,10 +6,10 @@
 
 # Function: connect()
 
-## connect(uri, opts)
+## connect(uri, options)
 
 ```ts
-function connect(uri, opts?): Promise<Connection>
+function connect(uri, options?): Promise<Connection>
 ```
 
 Connect to a LanceDB instance at the given URI.
@@ -26,7 +26,8 @@ Accepted formats:
     The uri of the database. If the database uri starts
     with `db://` then it connects to a remote database.
 
-* **opts?**: `Partial`&lt;[`ConnectionOptions`](../interfaces/ConnectionOptions.md)&gt;
+* **options?**: `Partial`&lt;[`ConnectionOptions`](../interfaces/ConnectionOptions.md)&gt;
+    The options to use when connecting to the database
 
 ### Returns
 
@@ -49,10 +50,10 @@ const conn = await connect(
 });
 ```
 
-## connect(opts)
+## connect(options)
 
 ```ts
-function connect(opts): Promise<Connection>
+function connect(options): Promise<Connection>
 ```
 
 Connect to a LanceDB instance at the given URI.
@@ -65,7 +66,8 @@ Accepted formats:
 
 ### Parameters
 
-* **opts**: `Partial`&lt;[`ConnectionOptions`](../interfaces/ConnectionOptions.md)&gt; & `object`
+* **options**: `Partial`&lt;[`ConnectionOptions`](../interfaces/ConnectionOptions.md)&gt; & `object`
+    The options to use when connecting to the database
 
 ### Returns
 

docs/src/js/functions/makeArrowTable.md

@@ -22,8 +22,6 @@ when creating a table or adding data to it)
 This function converts an array of Record<String, any> (row-major JS objects)
 to an Arrow Table (a columnar structure)
 
-Note that it currently does not support nulls.
-
 If a schema is provided then it will be used to determine the resulting array
 types.  Fields will also be reordered to fit the order defined by the schema.
 
@@ -31,6 +29,9 @@ If a schema is not provided then the types will be inferred and the field order
 will be controlled by the order of properties in the first record.  If a type
 is inferred it will always be nullable.
 
+If not all fields are found in the data, then a subset of the schema will be
+returned.
+
 If the input is empty then a schema must be provided to create an empty table.
 
 When a schema is not specified then data types will be inferred.  The inference
@@ -38,6 +39,7 @@ rules are as follows:
 
  - boolean => Bool
  - number => Float64
+ - bigint => Int64
  - String => Utf8
  - Buffer => Binary
  - Record<String, any> => Struct
@@ -57,6 +59,7 @@ rules are as follows:
 
 ## Example
 
+```ts
 import { fromTableToBuffer, makeArrowTable } from "../arrow";
 import { Field, FixedSizeList, Float16, Float32, Int32, Schema } from "apache-arrow";
 
@@ -78,7 +81,6 @@ The `vectorColumns` option can be used to support other vector column
 names and data types.
 
 ```ts
-
 const schema = new Schema([
   new Field("a", new Float64()),
   new Field("b", new Float64()),
@@ -97,8 +99,7 @@ const schema = new Schema([
 
 You can specify the vector column types and names using the options as well
 
-```typescript
+```ts
-
 const schema = new Schema([
   new Field('a', new Float64()),
   new Field('b', new Float64()),

docs/src/js/functions/packBits.md

@@ -0,0 +1,19 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / packBits
+
+# Function: packBits()
+
+```ts
+function packBits(data): number[]
+```
+
+## Parameters
+
+* **data**: `number`[]
+
+## Returns
+
+`number`[]

docs/src/js/globals.md

@@ -7,20 +7,28 @@
 ## Namespaces
 
 - [embedding](namespaces/embedding/README.md)
+- [rerankers](namespaces/rerankers/README.md)
 
 ## Enumerations
 
-- [WriteMode](enumerations/WriteMode.md)
+- [FullTextQueryType](enumerations/FullTextQueryType.md)
 
 ## Classes
 
+- [BoostQuery](classes/BoostQuery.md)
 - [Connection](classes/Connection.md)
 - [Index](classes/Index.md)
 - [MakeArrowTableOptions](classes/MakeArrowTableOptions.md)
+- [MatchQuery](classes/MatchQuery.md)
+- [MergeInsertBuilder](classes/MergeInsertBuilder.md)
+- [MultiMatchQuery](classes/MultiMatchQuery.md)
+- [PhraseQuery](classes/PhraseQuery.md)
 - [Query](classes/Query.md)
 - [QueryBase](classes/QueryBase.md)
 - [RecordBatchIterator](classes/RecordBatchIterator.md)
 - [Table](classes/Table.md)
+- [TagContents](classes/TagContents.md)
+- [Tags](classes/Tags.md)
 - [VectorColumnOptions](classes/VectorColumnOptions.md)
 - [VectorQuery](classes/VectorQuery.md)
 
@@ -30,25 +38,48 @@
 - [AddDataOptions](interfaces/AddDataOptions.md)
 - [ClientConfig](interfaces/ClientConfig.md)
 - [ColumnAlteration](interfaces/ColumnAlteration.md)
+- [CompactionStats](interfaces/CompactionStats.md)
 - [ConnectionOptions](interfaces/ConnectionOptions.md)
 - [CreateTableOptions](interfaces/CreateTableOptions.md)
 - [ExecutableQuery](interfaces/ExecutableQuery.md)
+- [FragmentStatistics](interfaces/FragmentStatistics.md)
+- [FragmentSummaryStats](interfaces/FragmentSummaryStats.md)
+- [FtsOptions](interfaces/FtsOptions.md)
+- [FullTextQuery](interfaces/FullTextQuery.md)
+- [FullTextSearchOptions](interfaces/FullTextSearchOptions.md)
+- [HnswPqOptions](interfaces/HnswPqOptions.md)
+- [HnswSqOptions](interfaces/HnswSqOptions.md)
 - [IndexConfig](interfaces/IndexConfig.md)
 - [IndexOptions](interfaces/IndexOptions.md)
 - [IndexStatistics](interfaces/IndexStatistics.md)
+- [IvfFlatOptions](interfaces/IvfFlatOptions.md)
 - [IvfPqOptions](interfaces/IvfPqOptions.md)
+- [MergeStats](interfaces/MergeStats.md)
+- [OpenTableOptions](interfaces/OpenTableOptions.md)
 - [OptimizeOptions](interfaces/OptimizeOptions.md)
+- [OptimizeStats](interfaces/OptimizeStats.md)
+- [QueryExecutionOptions](interfaces/QueryExecutionOptions.md)
+- [RemovalStats](interfaces/RemovalStats.md)
 - [RetryConfig](interfaces/RetryConfig.md)
 - [TableNamesOptions](interfaces/TableNamesOptions.md)
+- [TableStatistics](interfaces/TableStatistics.md)
 - [TimeoutConfig](interfaces/TimeoutConfig.md)
 - [UpdateOptions](interfaces/UpdateOptions.md)
-- [WriteOptions](interfaces/WriteOptions.md)
+- [Version](interfaces/Version.md)
 
 ## Type Aliases
 
 - [Data](type-aliases/Data.md)
+- [DataLike](type-aliases/DataLike.md)
+- [FieldLike](type-aliases/FieldLike.md)
+- [IntoSql](type-aliases/IntoSql.md)
+- [IntoVector](type-aliases/IntoVector.md)
+- [RecordBatchLike](type-aliases/RecordBatchLike.md)
+- [SchemaLike](type-aliases/SchemaLike.md)
+- [TableLike](type-aliases/TableLike.md)
 
 ## Functions
 
 - [connect](functions/connect.md)
 - [makeArrowTable](functions/makeArrowTable.md)
+- [packBits](functions/packBits.md)

docs/src/js/interfaces/ClientConfig.md

@@ -8,6 +8,14 @@
 
 ## Properties
 
+### extraHeaders?
+
+```ts
+optional extraHeaders: Record<string, string>;
+```
+
+***
+
 ### retryConfig?
 
 ```ts

docs/src/js/interfaces/ColumnAlteration.md

@@ -16,7 +16,7 @@ must be provided.
 ### dataType?
 
 ```ts
-optional dataType: string;
+optional dataType: string | DataType<Type, any>;
 ```
 
 A new data type for the column. If not provided then the data type will not be changed.

docs/src/js/interfaces/CompactionStats.md

@@ -0,0 +1,49 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / CompactionStats
+
+# Interface: CompactionStats
+
+Statistics about a compaction operation.
+
+## Properties
+
+### filesAdded
+
+```ts
+filesAdded: number;
+```
+
+The number of new, compacted data files added
+
+***
+
+### filesRemoved
+
+```ts
+filesRemoved: number;
+```
+
+The number of data files removed
+
+***
+
+### fragmentsAdded
+
+```ts
+fragmentsAdded: number;
+```
+
+The number of new, compacted fragments added
+
+***
+
+### fragmentsRemoved
+
+```ts
+fragmentsRemoved: number;
+```
+
+The number of fragments removed

docs/src/js/interfaces/CreateTableOptions.md

@@ -8,7 +8,7 @@
 
 ## Properties
 
-### dataStorageVersion?
+### ~~dataStorageVersion?~~
 
 ```ts
 optional dataStorageVersion: string;
@@ -19,6 +19,10 @@ The version of the data storage format to use.
 The default is `stable`.
 Set to "legacy" to use the old format.
 
+#### Deprecated
+
+Pass `new_table_data_storage_version` to storageOptions instead.
+
 ***
 
 ### embeddingFunction?
@@ -29,7 +33,7 @@ optional embeddingFunction: EmbeddingFunctionConfig;
 
 ***
 
-### enableV2ManifestPaths?
+### ~~enableV2ManifestPaths?~~
 
 ```ts
 optional enableV2ManifestPaths: boolean;
@@ -41,6 +45,10 @@ turning this on will make the dataset unreadable for older versions
 of LanceDB (prior to 0.10.0). To migrate an existing dataset, instead
 use the LocalTable#migrateManifestPathsV2 method.
 
+#### Deprecated
+
+Pass `new_table_enable_v2_manifest_paths` to storageOptions instead.
+
 ***
 
 ### existOk
@@ -90,17 +98,3 @@ Options already set on the connection will be inherited by the table,
 but can be overridden here.
 
 The available options are described at https://lancedb.github.io/lancedb/guides/storage/
-
-***
-
-### useLegacyFormat?
-
-```ts
-optional useLegacyFormat: boolean;
-```
-
-If true then data files will be written with the legacy format
-
-The default is false.
-
-Deprecated. Use data storage version instead.

docs/src/js/interfaces/FragmentStatistics.md

@@ -0,0 +1,37 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / FragmentStatistics
+
+# Interface: FragmentStatistics
+
+## Properties
+
+### lengths
+
+```ts
+lengths: FragmentSummaryStats;
+```
+
+Statistics on the number of rows in the table fragments
+
+***
+
+### numFragments
+
+```ts
+numFragments: number;
+```
+
+The number of fragments in the table
+
+***
+
+### numSmallFragments
+
+```ts
+numSmallFragments: number;
+```
+
+The number of uncompacted fragments in the table

docs/src/js/interfaces/FragmentSummaryStats.md

@@ -0,0 +1,77 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / FragmentSummaryStats
+
+# Interface: FragmentSummaryStats
+
+## Properties
+
+### max
+
+```ts
+max: number;
+```
+
+The number of rows in the fragment with the most rows
+
+***
+
+### mean
+
+```ts
+mean: number;
+```
+
+The mean number of rows in the fragments
+
+***
+
+### min
+
+```ts
+min: number;
+```
+
+The number of rows in the fragment with the fewest rows
+
+***
+
+### p25
+
+```ts
+p25: number;
+```
+
+The 25th percentile of number of rows in the fragments
+
+***
+
+### p50
+
+```ts
+p50: number;
+```
+
+The 50th percentile of number of rows in the fragments
+
+***
+
+### p75
+
+```ts
+p75: number;
+```
+
+The 75th percentile of number of rows in the fragments
+
+***
+
+### p99
+
+```ts
+p99: number;
+```
+
+The 99th percentile of number of rows in the fragments

docs/src/js/interfaces/FtsOptions.md

@@ -0,0 +1,103 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / FtsOptions
+
+# Interface: FtsOptions
+
+Options to create a full text search index
+
+## Properties
+
+### asciiFolding?
+
+```ts
+optional asciiFolding: boolean;
+```
+
+whether to remove punctuation
+
+***
+
+### baseTokenizer?
+
+```ts
+optional baseTokenizer: "raw" | "simple" | "whitespace";
+```
+
+The tokenizer to use when building the index.
+The default is "simple".
+
+The following tokenizers are available:
+
+"simple" - Simple tokenizer. This tokenizer splits the text into tokens using whitespace and punctuation as a delimiter.
+
+"whitespace" - Whitespace tokenizer. This tokenizer splits the text into tokens using whitespace as a delimiter.
+
+"raw" - Raw tokenizer. This tokenizer does not split the text into tokens and indexes the entire text as a single token.
+
+***
+
+### language?
+
+```ts
+optional language: string;
+```
+
+language for stemming and stop words
+this is only used when `stem` or `remove_stop_words` is true
+
+***
+
+### lowercase?
+
+```ts
+optional lowercase: boolean;
+```
+
+whether to lowercase tokens
+
+***
+
+### maxTokenLength?
+
+```ts
+optional maxTokenLength: number;
+```
+
+maximum token length
+tokens longer than this length will be ignored
+
+***
+
+### removeStopWords?
+
+```ts
+optional removeStopWords: boolean;
+```
+
+whether to remove stop words
+
+***
+
+### stem?
+
+```ts
+optional stem: boolean;
+```
+
+whether to stem tokens
+
+***
+
+### withPosition?
+
+```ts
+optional withPosition: boolean;
+```
+
+Whether to build the index with positions.
+True by default.
+If set to false, the index will not store the positions of the tokens in the text,
+which will make the index smaller and faster to build, but will not support phrase queries.

docs/src/js/interfaces/FullTextQuery.md

@@ -0,0 +1,25 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / FullTextQuery
+
+# Interface: FullTextQuery
+
+Represents a full-text query interface.
+This interface defines the structure and behavior for full-text queries,
+including methods to retrieve the query type and convert the query to a dictionary format.
+
+## Methods
+
+### queryType()
+
+```ts
+queryType(): FullTextQueryType
+```
+
+The type of the full-text query.
+
+#### Returns
+
+[`FullTextQueryType`](../enumerations/FullTextQueryType.md)

docs/src/js/interfaces/FullTextSearchOptions.md

@@ -0,0 +1,22 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / FullTextSearchOptions
+
+# Interface: FullTextSearchOptions
+
+Options that control the behavior of a full text search
+
+## Properties
+
+### columns?
+
+```ts
+optional columns: string | string[];
+```
+
+The columns to search
+
+If not specified, all indexed columns will be searched.
+For now, only one column can be searched.

docs/src/js/interfaces/HnswPqOptions.md

@@ -0,0 +1,149 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / HnswPqOptions
+
+# Interface: HnswPqOptions
+
+Options to create an `HNSW_PQ` index
+
+## Properties
+
+### distanceType?
+
+```ts
+optional distanceType: "l2" | "cosine" | "dot";
+```
+
+The distance metric used to train the index.
+
+Default value is "l2".
+
+The following distance types are available:
+
+"l2" - Euclidean distance. This is a very common distance metric that
+accounts for both magnitude and direction when determining the distance
+between vectors. l2 distance has a range of [0, ∞).
+
+"cosine" - Cosine distance.  Cosine distance is a distance metric
+calculated from the cosine similarity between two vectors. Cosine
+similarity is a measure of similarity between two non-zero vectors of an
+inner product space. It is defined to equal the cosine of the angle
+between them.  Unlike l2, the cosine distance is not affected by the
+magnitude of the vectors.  Cosine distance has a range of [0, 2].
+
+"dot" - Dot product. Dot distance is the dot product of two vectors. Dot
+distance has a range of (-∞, ∞). If the vectors are normalized (i.e. their
+l2 norm is 1), then dot distance is equivalent to the cosine distance.
+
+***
+
+### efConstruction?
+
+```ts
+optional efConstruction: number;
+```
+
+The number of candidates to evaluate during the construction of the HNSW graph.
+
+The default value is 300.
+
+This value controls the tradeoff between build speed and accuracy.
+The higher the value the more accurate the build but the slower it will be.
+150 to 300 is the typical range. 100 is a minimum for good quality search
+results. In most cases, there is no benefit to setting this higher than 500.
+This value should be set to a value that is not less than `ef` in the search phase.
+
+***
+
+### m?
+
+```ts
+optional m: number;
+```
+
+The number of neighbors to select for each vector in the HNSW graph.
+
+The default value is 20.
+
+This value controls the tradeoff between search speed and accuracy.
+The higher the value the more accurate the search but the slower it will be.
+
+***
+
+### maxIterations?
+
+```ts
+optional maxIterations: number;
+```
+
+Max iterations to train kmeans.
+
+The default value is 50.
+
+When training an IVF index we use kmeans to calculate the partitions.  This parameter
+controls how many iterations of kmeans to run.
+
+Increasing this might improve the quality of the index but in most cases the parameter
+is unused because kmeans will converge with fewer iterations.  The parameter is only
+used in cases where kmeans does not appear to converge.  In those cases it is unlikely
+that setting this larger will lead to the index converging anyways.
+
+***
+
+### numPartitions?
+
+```ts
+optional numPartitions: number;
+```
+
+The number of IVF partitions to create.
+
+For HNSW, we recommend a small number of partitions. Setting this to 1 works
+well for most tables. For very large tables, training just one HNSW graph
+will require too much memory. Each partition becomes its own HNSW graph, so
+setting this value higher reduces the peak memory use of training.
+
+***
+
+### numSubVectors?
+
+```ts
+optional numSubVectors: number;
+```
+
+Number of sub-vectors of PQ.
+
+This value controls how much the vector is compressed during the quantization step.
+The more sub vectors there are the less the vector is compressed.  The default is
+the dimension of the vector divided by 16.  If the dimension is not evenly divisible
+by 16 we use the dimension divded by 8.
+
+The above two cases are highly preferred.  Having 8 or 16 values per subvector allows
+us to use efficient SIMD instructions.
+
+If the dimension is not visible by 8 then we use 1 subvector.  This is not ideal and
+will likely result in poor performance.
+
+***
+
+### sampleRate?
+
+```ts
+optional sampleRate: number;
+```
+
+The rate used to calculate the number of training vectors for kmeans.
+
+Default value is 256.
+
+When an IVF index is trained, we need to calculate partitions.  These are groups
+of vectors that are similar to each other.  To do this we use an algorithm called kmeans.
+
+Running kmeans on a large dataset can be slow.  To speed this up we run kmeans on a
+random sample of the data.  This parameter controls the size of the sample.  The total
+number of vectors used to train the index is `sample_rate * num_partitions`.
+
+Increasing this value might improve the quality of the index but in most cases the
+default should be sufficient.

docs/src/js/interfaces/HnswSqOptions.md

@@ -0,0 +1,128 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / HnswSqOptions
+
+# Interface: HnswSqOptions
+
+Options to create an `HNSW_SQ` index
+
+## Properties
+
+### distanceType?
+
+```ts
+optional distanceType: "l2" | "cosine" | "dot";
+```
+
+The distance metric used to train the index.
+
+Default value is "l2".
+
+The following distance types are available:
+
+"l2" - Euclidean distance. This is a very common distance metric that
+accounts for both magnitude and direction when determining the distance
+between vectors. l2 distance has a range of [0, ∞).
+
+"cosine" - Cosine distance.  Cosine distance is a distance metric
+calculated from the cosine similarity between two vectors. Cosine
+similarity is a measure of similarity between two non-zero vectors of an
+inner product space. It is defined to equal the cosine of the angle
+between them.  Unlike l2, the cosine distance is not affected by the
+magnitude of the vectors.  Cosine distance has a range of [0, 2].
+
+"dot" - Dot product. Dot distance is the dot product of two vectors. Dot
+distance has a range of (-∞, ∞). If the vectors are normalized (i.e. their
+l2 norm is 1), then dot distance is equivalent to the cosine distance.
+
+***
+
+### efConstruction?
+
+```ts
+optional efConstruction: number;
+```
+
+The number of candidates to evaluate during the construction of the HNSW graph.
+
+The default value is 300.
+
+This value controls the tradeoff between build speed and accuracy.
+The higher the value the more accurate the build but the slower it will be.
+150 to 300 is the typical range. 100 is a minimum for good quality search
+results. In most cases, there is no benefit to setting this higher than 500.
+This value should be set to a value that is not less than `ef` in the search phase.
+
+***
+
+### m?
+
+```ts
+optional m: number;
+```
+
+The number of neighbors to select for each vector in the HNSW graph.
+
+The default value is 20.
+
+This value controls the tradeoff between search speed and accuracy.
+The higher the value the more accurate the search but the slower it will be.
+
+***
+
+### maxIterations?
+
+```ts
+optional maxIterations: number;
+```
+
+Max iterations to train kmeans.
+
+The default value is 50.
+
+When training an IVF index we use kmeans to calculate the partitions.  This parameter
+controls how many iterations of kmeans to run.
+
+Increasing this might improve the quality of the index but in most cases the parameter
+is unused because kmeans will converge with fewer iterations.  The parameter is only
+used in cases where kmeans does not appear to converge.  In those cases it is unlikely
+that setting this larger will lead to the index converging anyways.
+
+***
+
+### numPartitions?
+
+```ts
+optional numPartitions: number;
+```
+
+The number of IVF partitions to create.
+
+For HNSW, we recommend a small number of partitions. Setting this to 1 works
+well for most tables. For very large tables, training just one HNSW graph
+will require too much memory. Each partition becomes its own HNSW graph, so
+setting this value higher reduces the peak memory use of training.
+
+***
+
+### sampleRate?
+
+```ts
+optional sampleRate: number;
+```
+
+The rate used to calculate the number of training vectors for kmeans.
+
+Default value is 256.
+
+When an IVF index is trained, we need to calculate partitions.  These are groups
+of vectors that are similar to each other.  To do this we use an algorithm called kmeans.
+
+Running kmeans on a large dataset can be slow.  To speed this up we run kmeans on a
+random sample of the data.  This parameter controls the size of the sample.  The total
+number of vectors used to train the index is `sample_rate * num_partitions`.
+
+Increasing this value might improve the quality of the index but in most cases the
+default should be sufficient.

docs/src/js/interfaces/IndexOptions.md

@@ -39,3 +39,11 @@ and the same name, then an error will be returned.  This is true even if
 that index is out of date.
 
 The default is true
+
+***
+
+### waitTimeoutSeconds?
+
+```ts
+optional waitTimeoutSeconds: number;
+```

docs/src/js/interfaces/IndexStatistics.md

@@ -30,6 +30,17 @@ The type of the index
 
 ***
 
+### loss?
+
+```ts
+optional loss: number;
+```
+
+The KMeans loss value of the index,
+it is only present for vector indices.
+
+***
+
 ### numIndexedRows
 
 ```ts

docs/src/js/interfaces/IvfFlatOptions.md

@@ -0,0 +1,112 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / IvfFlatOptions
+
+# Interface: IvfFlatOptions
+
+Options to create an `IVF_FLAT` index
+
+## Properties
+
+### distanceType?
+
+```ts
+optional distanceType: "l2" | "cosine" | "dot" | "hamming";
+```
+
+Distance type to use to build the index.
+
+Default value is "l2".
+
+This is used when training the index to calculate the IVF partitions
+(vectors are grouped in partitions with similar vectors according to this
+distance type).
+
+The distance type used to train an index MUST match the distance type used
+to search the index.  Failure to do so will yield inaccurate results.
+
+The following distance types are available:
+
+"l2" - Euclidean distance. This is a very common distance metric that
+accounts for both magnitude and direction when determining the distance
+between vectors. l2 distance has a range of [0, ∞).
+
+"cosine" - Cosine distance.  Cosine distance is a distance metric
+calculated from the cosine similarity between two vectors. Cosine
+similarity is a measure of similarity between two non-zero vectors of an
+inner product space. It is defined to equal the cosine of the angle
+between them.  Unlike l2, the cosine distance is not affected by the
+magnitude of the vectors.  Cosine distance has a range of [0, 2].
+
+Note: the cosine distance is undefined when one (or both) of the vectors
+are all zeros (there is no direction).  These vectors are invalid and may
+never be returned from a vector search.
+
+"dot" - Dot product. Dot distance is the dot product of two vectors. Dot
+distance has a range of (-∞, ∞). If the vectors are normalized (i.e. their
+l2 norm is 1), then dot distance is equivalent to the cosine distance.
+
+"hamming" - Hamming distance. Hamming distance is a distance metric
+calculated from the number of bits that are different between two vectors.
+Hamming distance has a range of [0, dimension]. Note that the hamming distance
+is only valid for binary vectors.
+
+***
+
+### maxIterations?
+
+```ts
+optional maxIterations: number;
+```
+
+Max iteration to train IVF kmeans.
+
+When training an IVF FLAT index we use kmeans to calculate the partitions.  This parameter
+controls how many iterations of kmeans to run.
+
+Increasing this might improve the quality of the index but in most cases these extra
+iterations have diminishing returns.
+
+The default value is 50.
+
+***
+
+### numPartitions?
+
+```ts
+optional numPartitions: number;
+```
+
+The number of IVF partitions to create.
+
+This value should generally scale with the number of rows in the dataset.
+By default the number of partitions is the square root of the number of
+rows.
+
+If this value is too large then the first part of the search (picking the
+right partition) will be slow.  If this value is too small then the second
+part of the search (searching within a partition) will be slow.
+
+***
+
+### sampleRate?
+
+```ts
+optional sampleRate: number;
+```
+
+The number of vectors, per partition, to sample when training IVF kmeans.
+
+When an IVF FLAT index is trained, we need to calculate partitions.  These are groups
+of vectors that are similar to each other.  To do this we use an algorithm called kmeans.
+
+Running kmeans on a large dataset can be slow.  To speed this up we run kmeans on a
+random sample of the data.  This parameter controls the size of the sample.  The total
+number of vectors used to train the index is `sample_rate * num_partitions`.
+
+Increasing this value might improve the quality of the index but in most cases the
+default should be sufficient.
+
+The default value is 256.

docs/src/js/interfaces/IvfPqOptions.md

@@ -31,13 +31,13 @@ The following distance types are available:
 
 "l2" - Euclidean distance. This is a very common distance metric that
 accounts for both magnitude and direction when determining the distance
-between vectors. L2 distance has a range of [0, ∞).
+between vectors. l2 distance has a range of [0, ∞).
 
 "cosine" - Cosine distance.  Cosine distance is a distance metric
 calculated from the cosine similarity between two vectors. Cosine
 similarity is a measure of similarity between two non-zero vectors of an
 inner product space. It is defined to equal the cosine of the angle
-between them.  Unlike L2, the cosine distance is not affected by the
+between them.  Unlike l2, the cosine distance is not affected by the
 magnitude of the vectors.  Cosine distance has a range of [0, 2].
 
 Note: the cosine distance is undefined when one (or both) of the vectors
@@ -46,7 +46,7 @@ never be returned from a vector search.
 
 "dot" - Dot product. Dot distance is the dot product of two vectors. Dot
 distance has a range of (-∞, ∞). If the vectors are normalized (i.e. their
-L2 norm is 1), then dot distance is equivalent to the cosine distance.
+l2 norm is 1), then dot distance is equivalent to the cosine distance.
 
 ***
 
@@ -68,6 +68,21 @@ The default value is 50.
 
 ***
 
+### numBits?
+
+```ts
+optional numBits: number;
+```
+
+Number of bits per sub-vector.
+
+This value controls how much each subvector is compressed.  The more bits the more
+accurate the index will be but the slower search.  The default is 8 bits.
+
+The number of bits must be 4 or 8.
+
+***
+
 ### numPartitions?
 
 ```ts

docs/src/js/interfaces/MergeStats.md

@@ -0,0 +1,31 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / MergeStats
+
+# Interface: MergeStats
+
+## Properties
+
+### numDeletedRows
+
+```ts
+numDeletedRows: bigint;
+```
+
+***
+
+### numInsertedRows
+
+```ts
+numInsertedRows: bigint;
+```
+
+***
+
+### numUpdatedRows
+
+```ts
+numUpdatedRows: bigint;
+```

docs/src/js/interfaces/OpenTableOptions.md

@@ -0,0 +1,40 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / OpenTableOptions
+
+# Interface: OpenTableOptions
+
+## Properties
+
+### indexCacheSize?
+
+```ts
+optional indexCacheSize: number;
+```
+
+Set the size of the index cache, specified as a number of entries
+
+The exact meaning of an "entry" will depend on the type of index:
+- IVF: there is one entry for each IVF partition
+- BTREE: there is one entry for the entire index
+
+This cache applies to the entire opened table, across all indices.
+Setting this value higher will increase performance on larger datasets
+at the expense of more RAM
+
+***
+
+### storageOptions?
+
+```ts
+optional storageOptions: Record<string, string>;
+```
+
+Configuration for object storage.
+
+Options already set on the connection will be inherited by the table,
+but can be overridden here.
+
+The available options are described at https://lancedb.github.io/lancedb/guides/storage/