[python] Bump version: 0.6.5 → 0.6.6

<img width="1034" alt="image"
src="https://github.com/lancedb/lancedb/assets/5846846/5b8aa53c-4d93-4c0e-bed4-80c238b319ba">

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.4.13
+current_version = 0.4.15
 commit = True
 message = Bump version: {current_version} → {new_version}
 tag = True
@@ -7,6 +7,16 @@ tag_name = v{new_version}
 
 [bumpversion:file:node/package.json]
 
+[bumpversion:file:nodejs/package.json]
+
+[bumpversion:file:nodejs/npm/darwin-x64/package.json]
+
+[bumpversion:file:nodejs/npm/darwin-arm64/package.json]
+
+[bumpversion:file:nodejs/npm/linux-x64-gnu/package.json]
+
+[bumpversion:file:nodejs/npm/linux-arm64-gnu/package.json]
+
 [bumpversion:file:rust/ffi/node/Cargo.toml]
 
 [bumpversion:file:rust/lancedb/Cargo.toml]

.github/workflows/docs_test.yml

@@ -18,7 +18,7 @@ on:
 env:
   # 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.
-  RUSTFLAGS: "-C debuginfo=1 -C target-cpu=native -C target-feature=+f16c,+avx2,+fma"
+  RUSTFLAGS: "-C debuginfo=1 -C target-cpu=haswell -C target-feature=+f16c,+avx2,+fma"
   RUST_BACKTRACE: "1"
 
 jobs:
@@ -28,6 +28,8 @@ jobs:
     steps:
     - name: Checkout
       uses: actions/checkout@v4
+    - name: Print CPU capabilities
+      run: cat /proc/cpuinfo
     - name: Install dependecies needed for ubuntu
       run: |
         sudo apt install -y protobuf-compiler libssl-dev
@@ -39,7 +41,7 @@ jobs:
         cache: "pip"
         cache-dependency-path: "docs/test/requirements.txt"
     - name: Rust cache
-      uses: swatinem/rust-cache@v2        
+      uses: swatinem/rust-cache@v2
     - name: Build Python
       working-directory: docs/test
       run:
@@ -64,6 +66,8 @@ jobs:
       with:
         fetch-depth: 0
         lfs: true
+    - name: Print CPU capabilities
+      run: cat /proc/cpuinfo
     - name: Set up Node
       uses: actions/setup-node@v4
       with:

.github/workflows/node.yml

@@ -20,7 +20,8 @@ env:
   # "1" means line tables only, which is useful for panic tracebacks.
   #
   # Use native CPU to accelerate tests if possible, especially for f16
-  RUSTFLAGS: "-C debuginfo=1 -C target-cpu=native -C target-feature=+f16c,+avx2,+fma"
+  # target-cpu=haswell fixes failing ci build
+  RUSTFLAGS: "-C debuginfo=1 -C target-cpu=haswell -C target-feature=+f16c,+avx2,+fma"
   RUST_BACKTRACE: "1"
 
 jobs:

.github/workflows/npm-publish.yml

@@ -2,7 +2,7 @@ name: NPM Publish
 
 on:
   release:
-    types: [ published ]
+    types: [published]
 
 jobs:
   node:
@@ -19,7 +19,7 @@ jobs:
       - uses: actions/setup-node@v3
         with:
           node-version: 20
-          cache: 'npm'
+          cache: "npm"
           cache-dependency-path: node/package-lock.json
       - name: Install dependencies
         run: |
@@ -31,7 +31,7 @@ jobs:
           npm run tsc
           npm pack
       - name: Upload Linux Artifacts
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: node-package
           path: |
@@ -61,12 +61,41 @@ jobs:
       - name: Build MacOS native node modules
         run: bash ci/build_macos_artifacts.sh ${{ matrix.config.arch }}
       - name: Upload Darwin Artifacts
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
-          name: native-darwin
+          name: node-native-darwin-${{ matrix.config.arch }}
           path: |
             node/dist/lancedb-vectordb-darwin*.tgz
 
+  nodejs-macos:
+    strategy:
+      matrix:
+        config:
+          - arch: x86_64-apple-darwin
+            runner: macos-13
+          - arch: aarch64-apple-darwin
+            # xlarge is implicitly arm64.
+            runner: macos-14
+    runs-on: ${{ matrix.config.runner }}
+    # Only runs on tags that matches the make-release action
+    if: startsWith(github.ref, 'refs/tags/v')
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Install system dependencies
+        run: brew install protobuf
+      - name: Install npm dependencies
+        run: |
+          cd nodejs
+          npm ci
+      - name: Build MacOS native nodejs modules
+        run: bash ci/build_macos_artifacts_nodejs.sh ${{ matrix.config.arch }}
+      - name: Upload Darwin Artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: nodejs-native-darwin-${{ matrix.config.arch }}
+          path: |
+            nodejs/dist/*.node
 
   node-linux:
     name: node-linux (${{ matrix.config.arch}}-unknown-linux-gnu
@@ -103,12 +132,63 @@ jobs:
         run: |
           bash ci/build_linux_artifacts.sh ${{ matrix.config.arch }}
       - name: Upload Linux Artifacts
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
-          name: native-linux
+          name: node-native-linux-${{ matrix.config.arch }}
           path: |
             node/dist/lancedb-vectordb-linux*.tgz
 
+  nodejs-linux:
+    name: nodejs-linux (${{ matrix.config.arch}}-unknown-linux-gnu
+    runs-on: ${{ matrix.config.runner }}
+    # Only runs on tags that matches the make-release action
+    if: startsWith(github.ref, 'refs/tags/v')
+    strategy:
+      fail-fast: false
+      matrix:
+        config:
+          - arch: x86_64
+            runner: ubuntu-latest
+          - arch: aarch64
+            # For successful fat LTO builds, we need a large runner to avoid OOM errors.
+            runner: buildjet-16vcpu-ubuntu-2204-arm
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      # Buildjet aarch64 runners have only 1.5 GB RAM per core, vs 3.5 GB per core for
+      # x86_64 runners. To avoid OOM errors on ARM, we create a swap file.
+      - name: Configure aarch64 build
+        if: ${{ matrix.config.arch == 'aarch64' }}
+        run: |
+          free -h
+          sudo fallocate -l 16G /swapfile
+          sudo chmod 600 /swapfile
+          sudo mkswap /swapfile
+          sudo swapon /swapfile
+          echo "/swapfile swap swap defaults 0 0" >> sudo /etc/fstab
+          # print info
+          swapon --show
+          free -h
+      - name: Build Linux Artifacts
+        run: |
+          bash ci/build_linux_artifacts_nodejs.sh ${{ matrix.config.arch }}
+      - name: Upload Linux Artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: nodejs-native-linux-${{ matrix.config.arch }}
+          path: |
+            nodejs/dist/*.node
+      # The generic files are the same in all distros so we just pick
+      # one to do the upload.
+      - name: Upload Generic Artifacts
+        if: ${{ matrix.config.arch == 'x86_64' }}
+        uses: actions/upload-artifact@v4
+        with:
+          name: nodejs-dist
+          path: |
+            nodejs/dist/*
+            !nodejs/dist/*.node
+
   node-windows:
     runs-on: windows-2022
     # Only runs on tags that matches the make-release action
@@ -136,25 +216,60 @@ jobs:
       - name: Build Windows native node modules
         run: .\ci\build_windows_artifacts.ps1 ${{ matrix.target }}
       - name: Upload Windows Artifacts
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
-          name: native-windows
+          name: node-native-windows
           path: |
             node/dist/lancedb-vectordb-win32*.tgz
 
+  nodejs-windows:
+    runs-on: windows-2022
+    # Only runs on tags that matches the make-release action
+    if: startsWith(github.ref, 'refs/tags/v')
+    strategy:
+      fail-fast: false
+      matrix:
+        target: [x86_64-pc-windows-msvc]
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Install Protoc v21.12
+        working-directory: C:\
+        run: |
+          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
+          7z x protoc.zip
+          Add-Content $env:GITHUB_PATH "C:\protoc\bin"
+        shell: powershell
+      - name: Install npm dependencies
+        run: |
+          cd nodejs
+          npm ci
+      - name: Build Windows native node modules
+        run: .\ci\build_windows_artifacts_nodejs.ps1 ${{ matrix.target }}
+      - name: Upload Windows Artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: nodejs-native-windows
+          path: |
+            nodejs/dist/*.node
+
   release:
     needs: [node, node-macos, node-linux, node-windows]
     runs-on: ubuntu-latest
     # Only runs on tags that matches the make-release action
     if: startsWith(github.ref, 'refs/tags/v')
     steps:
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4
+        with:
+          pattern: node-*
       - name: Display structure of downloaded files
         run: ls -R
       - uses: actions/setup-node@v3
         with:
           node-version: 20
-          registry-url: 'https://registry.npmjs.org'
+          registry-url: "https://registry.npmjs.org"
       - name: Publish to NPM
         env:
           NODE_AUTH_TOKEN: ${{ secrets.LANCEDB_NPM_REGISTRY_TOKEN }}
@@ -164,6 +279,45 @@ jobs:
             npm publish $filename
           done
 
+  release-nodejs:
+    needs: [nodejs-macos, nodejs-linux, nodejs-windows]
+    runs-on: ubuntu-latest
+    # Only runs on tags that matches the make-release action
+    if: startsWith(github.ref, 'refs/tags/v')
+    defaults:
+      run:
+        shell: bash
+        working-directory: nodejs
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - uses: actions/download-artifact@v4
+        with:
+          name: nodejs-dist
+          path: nodejs/dist
+      - uses: actions/download-artifact@v4
+        name: Download arch-specific binaries
+        with:
+          pattern: nodejs-*
+          path: nodejs/nodejs-artifacts
+          merge-multiple: true
+      - name: Display structure of downloaded files
+        run: find .
+      - uses: actions/setup-node@v3
+        with:
+          node-version: 20
+          registry-url: "https://registry.npmjs.org"
+      - name: Install napi-rs
+        run: npm install -g @napi-rs/cli
+      - name: Prepare artifacts
+        run: npx napi artifacts -d nodejs-artifacts
+      - name: Display structure of staged files
+        run: find npm
+      - name: Publish to NPM
+        env:
+          NODE_AUTH_TOKEN: ${{ secrets.LANCEDB_NPM_REGISTRY_TOKEN }}
+        run: npm publish --access public
+
   update-package-lock:
     needs: [release]
     runs-on: ubuntu-latest
@@ -178,3 +332,18 @@ jobs:
       - uses: ./.github/workflows/update_package_lock
         with:
           github_token: ${{ secrets.LANCEDB_RELEASE_TOKEN }}
+
+  update-package-lock-nodejs:
+    needs: [release-nodejs]
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          ref: main
+          persist-credentials: false
+          fetch-depth: 0
+          lfs: true
+      - uses: ./.github/workflows/update_package_lock_nodejs
+        with:
+          github_token: ${{ secrets.LANCEDB_RELEASE_TOKEN }}

.github/workflows/update_package_lock_nodejs/action.yml

@@ -0,0 +1,33 @@
+name: update_package_lock_nodejs
+description: "Update nodejs's package.lock"
+
+inputs:
+  github_token:
+    required: true
+    description: "github token for the repo"
+
+runs:
+  using: "composite"
+  steps:
+    - uses: actions/setup-node@v3
+      with:
+        node-version: 20
+    - name: Set git configs
+      shell: bash
+      run: |
+        git config user.name 'Lance Release'
+        git config user.email 'lance-dev@lancedb.com'
+    - name: Update package-lock.json file
+      working-directory: ./nodejs
+      run: |
+        npm install
+        git add package-lock.json
+        git commit -m "Updating package-lock.json"
+      shell: bash
+    - name: Push changes
+      if: ${{ inputs.dry_run }} == "false"
+      uses: ad-m/github-push-action@master
+      with:
+        github_token: ${{ inputs.github_token }}
+        branch: main
+        tags: true

.github/workflows/update_package_lock_run_nodejs.yml

@@ -0,0 +1,19 @@
+name: Update NodeJs package-lock.json
+
+on:
+  workflow_dispatch:
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          ref: main
+          persist-credentials: false
+          fetch-depth: 0
+          lfs: true
+      - uses: ./.github/workflows/update_package_lock_nodejs
+        with:
+          github_token: ${{ secrets.LANCEDB_RELEASE_TOKEN }}

.gitignore

@@ -34,6 +34,7 @@ python/dist
 node/dist
 node/examples/**/package-lock.json
 node/examples/**/dist
+nodejs/lancedb/native*
 dist
 
 ## Rust

Cargo.toml

@@ -14,10 +14,10 @@ keywords = ["lancedb", "lance", "database", "vector", "search"]
 categories = ["database-implementations"]
 
 [workspace.dependencies]
-lance = { "version" = "=0.10.5", "features" = ["dynamodb"] }
-lance-index = { "version" = "=0.10.5" }
-lance-linalg = { "version" = "=0.10.5" }
-lance-testing = { "version" = "=0.10.5" }
+lance = { "version" = "=0.10.6", "features" = ["dynamodb"] }
+lance-index = { "version" = "=0.10.6" }
+lance-linalg = { "version" = "=0.10.6" }
+lance-testing = { "version" = "=0.10.6" }
 # Note that this one does not include pyarrow
 arrow = { version = "50.0", optional = false }
 arrow-array = "50.0"
@@ -39,3 +39,5 @@ pin-project = "1.0.7"
 snafu = "0.7.4"
 url = "2"
 num-traits = "0.2"
+regex = "1.10"
+lazy_static = "1"

README.md

@@ -1,13 +1,13 @@
 <div align="center">
 <p align="center">
 
-<img width="275" alt="LanceDB Logo" src="https://user-images.githubusercontent.com/917119/226205734-6063d87a-1ecc-45fe-85be-1dea6383a3d8.png">
+<img width="275" alt="LanceDB Logo" src="https://github.com/lancedb/lancedb/assets/5846846/37d7c7ad-c2fd-4f56-9f16-fffb0d17c73a">
 
-**Developer-friendly, serverless vector database for AI applications**
+**Developer-friendly, database for multimodal AI**
 
 <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>
-[![Medium](https://img.shields.io/badge/Medium-12100E?style=for-the-badge&logo=medium&logoColor=white)](https://blog.lancedb.com/) 
+[![Blog](https://img.shields.io/badge/Blog-12100E?style=for-the-badge&logoColor=white)](https://blog.lancedb.com/) 
 [![Discord](https://img.shields.io/badge/Discord-%235865F2.svg?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/zMM32dvNtd) 
 [![Twitter](https://img.shields.io/badge/Twitter-%231DA1F2.svg?style=for-the-badge&logo=Twitter&logoColor=white)](https://twitter.com/lancedb)
 

ci/build_linux_artifacts_nodejs.sh

@@ -0,0 +1,21 @@
+#!/bin/bash
+set -e
+ARCH=${1:-x86_64}
+
+# We pass down the current user so that when we later mount the local files
+# into the container, the files are accessible by the current user.
+pushd ci/manylinux_nodejs
+docker build \
+    -t lancedb-nodejs-manylinux \
+    --build-arg="ARCH=$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-nodejs-manylinux \
+    bash ci/manylinux_nodejs/build.sh $ARCH

ci/build_macos_artifacts_nodejs.sh

@@ -0,0 +1,34 @@
+# 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/build_windows_artifacts_nodejs.ps1

@@ -0,0 +1,41 @@
+# Builds the Windows artifacts (nodejs binaries).
+# Usage:  .\ci\build_windows_artifacts_nodejs.ps1 [target]
+# Targets supported:
+# - x86_64-pc-windows-msvc
+# - i686-pc-windows-msvc
+
+function Prebuild-Rust {
+    param (
+        [string]$target
+    )
+
+    # Building here for the sake of easier debugging.
+    Push-Location -Path "rust/lancedb"
+    Write-Host "Building rust library for $target"
+    $env:RUST_BACKTRACE=1
+    cargo build --release --target $target
+    Pop-Location
+}
+
+function Build-NodeBinaries {
+    param (
+        [string]$target
+    )
+
+    Push-Location -Path "nodejs"
+    Write-Host "Building nodejs library for $target"
+    $env:RUST_TARGET=$target
+    npm run build-release
+    Pop-Location
+}
+
+$targets = $args[0]
+if (-not $targets) {
+    $targets = "x86_64-pc-windows-msvc"
+}
+
+Write-Host "Building artifacts for targets: $targets"
+foreach ($target in $targets) {
+    Prebuild-Rust $target
+    Build-NodeBinaries $target
+}

ci/manylinux_nodejs/Dockerfile

@@ -0,0 +1,31 @@
+# Many linux dockerfile with Rust, Node, and Lance dependencies installed.
+# This container allows building the node modules native libraries in an
+# environment with a very old glibc, so that we are compatible with a wide
+# range of linux distributions.
+ARG ARCH=x86_64
+
+FROM quay.io/pypa/manylinux2014_${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 ${ARCH}
+
+ENV DOCKER_USER=${DOCKER_USER}
+# Create a group and user
+RUN echo ${ARCH} && adduser --user-group --create-home --uid ${DOCKER_USER} build_user
+
+# We switch to the user to install Rust and Node, since those like to be
+# installed at the user level.
+USER ${DOCKER_USER}
+
+COPY prepare_manylinux_node.sh prepare_manylinux_node.sh
+RUN cp /prepare_manylinux_node.sh $HOME/ && \
+    cd $HOME && \
+    ./prepare_manylinux_node.sh ${ARCH}

ci/manylinux_nodejs/build.sh

@@ -0,0 +1,18 @@
+#!/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
+
+source $HOME/.bashrc
+
+cd nodejs
+npm ci
+npm run build-release

ci/manylinux_nodejs/install_openssl.sh

@@ -0,0 +1,26 @@
+#!/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_1u \
+    --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/manylinux_nodejs/install_protobuf.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+# Installs protobuf compiler. Should be run as root.
+set -e
+
+if [[ $1 == x86_64* ]]; then
+    ARCH=x86_64
+else
+    # gnu target
+    ARCH=aarch_64
+fi
+
+PB_REL=https://github.com/protocolbuffers/protobuf/releases
+PB_VERSION=23.1
+curl -LO $PB_REL/download/v$PB_VERSION/protoc-$PB_VERSION-linux-$ARCH.zip
+unzip protoc-$PB_VERSION-linux-$ARCH.zip -d /usr/local

ci/manylinux_nodejs/prepare_manylinux_node.sh

@@ -0,0 +1,21 @@
+#!/bin/bash
+set -e
+
+install_node() {
+    echo "Installing node..."
+
+    curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.34.0/install.sh | bash
+
+    source "$HOME"/.bashrc
+
+    nvm install --no-progress 16
+}
+
+install_rust() {
+    echo "Installing rust..."
+    curl https://sh.rustup.rs -sSf | bash -s -- -y
+    export PATH="$PATH:/root/.cargo/bin"
+}
+
+install_node
+install_rust

docs/mkdocs.yml

@@ -38,178 +38,182 @@ theme:
   custom_dir: overrides
 
 plugins:
-- search
-- autorefs
-- mkdocstrings:
-    handlers:
-      python:
-        paths: [../python]
-        options:
-          docstring_style: numpy
-          heading_level: 4
-          show_source: true
-          show_symbol_type_in_heading: true
-          show_signature_annotations: true
-          members_order: source
-        import:
-          # for cross references
-          - https://arrow.apache.org/docs/objects.inv
-          - https://pandas.pydata.org/docs/objects.inv
-- mkdocs-jupyter
-- ultralytics:
-    verbose: True
-    enabled: True
-    default_image: "assets/lancedb_and_lance.png" # Default image for all pages
-    add_image: True # Automatically add meta image
-    add_keywords: True # Add page keywords in the header tag
-    add_share_buttons: True # Add social share buttons
-    add_authors: False # Display page authors
-    add_desc: False
-    add_dates: False
+  - search
+  - autorefs
+  - mkdocstrings:
+      handlers:
+        python:
+          paths: [../python]
+          options:
+            docstring_style: numpy
+            heading_level: 3
+            show_source: true
+            show_symbol_type_in_heading: true
+            show_signature_annotations: true
+            show_root_heading: true
+            members_order: source
+          import:
+            # for cross references
+            - https://arrow.apache.org/docs/objects.inv
+            - https://pandas.pydata.org/docs/objects.inv
+  - mkdocs-jupyter
+  - ultralytics:
+      verbose: True
+      enabled: True
+      default_image: "assets/lancedb_and_lance.png" # Default image for all pages
+      add_image: True # Automatically add meta image
+      add_keywords: True # Add page keywords in the header tag
+      add_share_buttons: True # Add social share buttons
+      add_authors: False # Display page authors
+      add_desc: False
+      add_dates: False
 
 markdown_extensions:
-- admonition
-- footnotes
-- pymdownx.details
-- pymdownx.highlight:
-    anchor_linenums: true
-    line_spans: __span
-    pygments_lang_class: true
-- pymdownx.inlinehilite
-- pymdownx.snippets:
-    base_path: ..
-    dedent_subsections: true
-- pymdownx.superfences
-- pymdownx.tabbed:
-    alternate_style: true
-- md_in_html
-- attr_list
+  - admonition
+  - footnotes
+  - pymdownx.details
+  - pymdownx.highlight:
+      anchor_linenums: true
+      line_spans: __span
+      pygments_lang_class: true
+  - pymdownx.inlinehilite
+  - pymdownx.snippets:
+      base_path: ..
+      dedent_subsections: true
+  - pymdownx.superfences
+  - pymdownx.tabbed:
+      alternate_style: true
+  - md_in_html
+  - attr_list
 
 nav:
-- Home:
-  - LanceDB: index.md
-  - 🏃🏼‍♂️ Quick start: basic.md
-  - 📚 Concepts:
-    - Vector search: concepts/vector_search.md
-    - Indexing: concepts/index_ivfpq.md
-    - Storage: concepts/storage.md
-    - Data management: concepts/data_management.md
-  - 🔨 Guides:
-    - Working with tables: guides/tables.md
-    - Building an ANN index: ann_indexes.md
-    - Vector Search: search.md
-    - Full-text search: fts.md
-    - Hybrid search:
-      - Overview: hybrid_search/hybrid_search.md
-      - Comparing Rerankers: hybrid_search/eval.md
-      - Airbnb financial data example: notebooks/hybrid_search.ipynb
-    - Filtering: sql.md
-    - Versioning & Reproducibility: notebooks/reproducibility.ipynb
-    - Configuring Storage: guides/storage.md
-  - 🧬 Managing embeddings:
-    - Overview: embeddings/index.md
-    - Embedding functions: embeddings/embedding_functions.md
-    - Available models: embeddings/default_embedding_functions.md
-    - User-defined embedding functions: embeddings/custom_embedding_function.md
-    - "Example: Multi-lingual semantic search": notebooks/multi_lingual_example.ipynb
-    - "Example: MultiModal CLIP Embeddings": notebooks/DisappearingEmbeddingFunction.ipynb
-  - 🔌 Integrations:
-    - Tools and data formats: integrations/index.md
-    - Pandas and PyArrow: python/pandas_and_pyarrow.md
-    - Polars: python/polars_arrow.md
-    - DuckDB: python/duckdb.md
-    - LangChain 🔗: https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/lancedb.html
-    - LangChain JS/TS 🔗: https://js.langchain.com/docs/modules/data_connection/vectorstores/integrations/lancedb
-    - LlamaIndex 🦙: https://gpt-index.readthedocs.io/en/latest/examples/vector_stores/LanceDBIndexDemo.html
-    - Pydantic: python/pydantic.md
-    - Voxel51: integrations/voxel51.md
-    - PromptTools: integrations/prompttools.md
-  - 🎯 Examples:
-    - Overview: examples/index.md
-    - 🐍 Python:
-      - Overview: examples/examples_python.md
+  - Home:
+      - LanceDB: index.md
+      - 🏃🏼‍♂️ Quick start: basic.md
+      - 📚 Concepts:
+          - Vector search: concepts/vector_search.md
+          - Indexing: concepts/index_ivfpq.md
+          - Storage: concepts/storage.md
+          - Data management: concepts/data_management.md
+      - 🔨 Guides:
+          - Working with tables: guides/tables.md
+          - Building an ANN index: ann_indexes.md
+          - Vector Search: search.md
+          - Full-text search: fts.md
+          - Hybrid search:
+              - Overview: hybrid_search/hybrid_search.md
+              - Comparing Rerankers: hybrid_search/eval.md
+              - Airbnb financial data example: notebooks/hybrid_search.ipynb
+          - Filtering: sql.md
+          - Versioning & Reproducibility: notebooks/reproducibility.ipynb
+          - Configuring Storage: guides/storage.md
+          - Sync -> Async Migration Guide: migration.md
+      - 🧬 Managing embeddings:
+          - Overview: embeddings/index.md
+          - Embedding functions: embeddings/embedding_functions.md
+          - Available models: embeddings/default_embedding_functions.md
+          - User-defined embedding functions: embeddings/custom_embedding_function.md
+          - "Example: Multi-lingual semantic search": notebooks/multi_lingual_example.ipynb
+          - "Example: MultiModal CLIP Embeddings": notebooks/DisappearingEmbeddingFunction.ipynb
+      - 🔌 Integrations:
+          - Tools and data formats: integrations/index.md
+          - Pandas and PyArrow: python/pandas_and_pyarrow.md
+          - Polars: python/polars_arrow.md
+          - DuckDB: python/duckdb.md
+          - LangChain 🔗: https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/lancedb.html
+          - LangChain JS/TS 🔗: https://js.langchain.com/docs/modules/data_connection/vectorstores/integrations/lancedb
+          - LlamaIndex 🦙: https://gpt-index.readthedocs.io/en/latest/examples/vector_stores/LanceDBIndexDemo.html
+          - Pydantic: python/pydantic.md
+          - Voxel51: integrations/voxel51.md
+          - PromptTools: integrations/prompttools.md
+      - 🎯 Examples:
+          - Overview: examples/index.md
+          - 🐍 Python:
+              - Overview: examples/examples_python.md
+              - YouTube Transcript Search: notebooks/youtube_transcript_search.ipynb
+              - Documentation QA Bot using LangChain: notebooks/code_qa_bot.ipynb
+              - Multimodal search using CLIP: notebooks/multimodal_search.ipynb
+              - Example - Calculate CLIP Embeddings with Roboflow Inference: examples/image_embeddings_roboflow.md
+              - Serverless QA Bot with S3 and Lambda: examples/serverless_lancedb_with_s3_and_lambda.md
+              - Serverless QA Bot with Modal: examples/serverless_qa_bot_with_modal_and_langchain.md
+          - 👾 JavaScript:
+              - Overview: examples/examples_js.md
+              - Serverless Website Chatbot: examples/serverless_website_chatbot.md
+              - YouTube Transcript Search: examples/youtube_transcript_bot_with_nodejs.md
+              - TransformersJS Embedding Search: examples/transformerjs_embedding_search_nodejs.md
+          - 🦀 Rust:
+              - Overview: examples/examples_rust.md
+      - 🔧 CLI & Config: cli_config.md
+      - 💭 FAQs: faq.md
+      - ⚙️ API reference:
+          - 🐍 Python: python/python.md
+          - 👾 JavaScript (vectordb): javascript/modules.md
+          - 👾 JavaScript (lancedb): javascript/modules.md
+          - 🦀 Rust: https://docs.rs/lancedb/latest/lancedb/
+      - ☁️ LanceDB Cloud:
+          - Overview: cloud/index.md
+          - API reference:
+              - 🐍 Python: python/saas-python.md
+              - 👾 JavaScript: javascript/saas-modules.md
+
+  - Quick start: basic.md
+  - Concepts:
+      - Vector search: concepts/vector_search.md
+      - Indexing: concepts/index_ivfpq.md
+      - Storage: concepts/storage.md
+      - Data management: concepts/data_management.md
+  - Guides:
+      - Working with tables: guides/tables.md
+      - Building an ANN index: ann_indexes.md
+      - Vector Search: search.md
+      - Full-text search: fts.md
+      - Hybrid search:
+          - Overview: hybrid_search/hybrid_search.md
+          - Comparing Rerankers: hybrid_search/eval.md
+          - Airbnb financial data example: notebooks/hybrid_search.ipynb
+      - Filtering: sql.md
+      - Versioning & Reproducibility: notebooks/reproducibility.ipynb
+      - Configuring Storage: guides/storage.md
+      - Sync -> Async Migration Guide: migration.md
+  - Managing Embeddings:
+      - Overview: embeddings/index.md
+      - Embedding functions: embeddings/embedding_functions.md
+      - Available models: embeddings/default_embedding_functions.md
+      - User-defined embedding functions: embeddings/custom_embedding_function.md
+      - "Example: Multi-lingual semantic search": notebooks/multi_lingual_example.ipynb
+      - "Example: MultiModal CLIP Embeddings": notebooks/DisappearingEmbeddingFunction.ipynb
+  - Integrations:
+      - Overview: integrations/index.md
+      - Pandas and PyArrow: python/pandas_and_pyarrow.md
+      - Polars: python/polars_arrow.md
+      - DuckDB: python/duckdb.md
+      - LangChain 🦜️🔗↗: https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/lancedb.html
+      - LangChain.js 🦜️🔗↗: https://js.langchain.com/docs/modules/data_connection/vectorstores/integrations/lancedb
+      - LlamaIndex 🦙↗: https://gpt-index.readthedocs.io/en/latest/examples/vector_stores/LanceDBIndexDemo.html
+      - Pydantic: python/pydantic.md
+      - Voxel51: integrations/voxel51.md
+      - PromptTools: integrations/prompttools.md
+  - Examples:
+      - examples/index.md
       - YouTube Transcript Search: notebooks/youtube_transcript_search.ipynb
       - Documentation QA Bot using LangChain: notebooks/code_qa_bot.ipynb
       - Multimodal search using CLIP: notebooks/multimodal_search.ipynb
-      - Example - Calculate CLIP Embeddings with Roboflow Inference: examples/image_embeddings_roboflow.md
       - Serverless QA Bot with S3 and Lambda: examples/serverless_lancedb_with_s3_and_lambda.md
       - Serverless QA Bot with Modal: examples/serverless_qa_bot_with_modal_and_langchain.md
-    - 👾 JavaScript:
-      - Overview: examples/examples_js.md
-      - Serverless Website Chatbot: examples/serverless_website_chatbot.md
-      - YouTube Transcript Search: examples/youtube_transcript_bot_with_nodejs.md
+      - YouTube Transcript Search (JS): examples/youtube_transcript_bot_with_nodejs.md
+      - Serverless Chatbot from any website: examples/serverless_website_chatbot.md
       - TransformersJS Embedding Search: examples/transformerjs_embedding_search_nodejs.md
-    - 🦀 Rust:
-      - Overview: examples/examples_rust.md
-  - 🔧 CLI & Config: cli_config.md
-  - 💭 FAQs: faq.md
-  - ⚙️ API reference:
-    - 🐍 Python: python/python.md
-    - 👾 JavaScript: javascript/modules.md
-    - 🦀 Rust: https://docs.rs/lancedb/latest/lancedb/
-  - ☁️ LanceDB Cloud:
-    - Overview: cloud/index.md
-    - API reference:
-      - 🐍 Python: python/saas-python.md
-      - 👾 JavaScript: javascript/saas-modules.md
-
-
-- Quick start: basic.md
-- Concepts:
-    - Vector search: concepts/vector_search.md
-    - Indexing: concepts/index_ivfpq.md
-    - Storage: concepts/storage.md
-    - Data management: concepts/data_management.md
-- Guides:
-    - Working with tables: guides/tables.md
-    - Building an ANN index: ann_indexes.md
-    - Vector Search: search.md
-    - Full-text search: fts.md
-    - Hybrid search:
-      - Overview: hybrid_search/hybrid_search.md
-      - Comparing Rerankers: hybrid_search/eval.md
-      - Airbnb financial data example: notebooks/hybrid_search.ipynb
-    - Filtering: sql.md
-    - Versioning & Reproducibility: notebooks/reproducibility.ipynb
-    - Configuring Storage: guides/storage.md
-- Managing Embeddings:
-  - Overview: embeddings/index.md
-  - Embedding functions: embeddings/embedding_functions.md
-  - Available models: embeddings/default_embedding_functions.md
-  - User-defined embedding functions: embeddings/custom_embedding_function.md
-  - "Example: Multi-lingual semantic search": notebooks/multi_lingual_example.ipynb
-  - "Example: MultiModal CLIP Embeddings": notebooks/DisappearingEmbeddingFunction.ipynb
-- Integrations:
-  - Overview: integrations/index.md
-  - Pandas and PyArrow: python/pandas_and_pyarrow.md
-  - Polars: python/polars_arrow.md
-  - DuckDB : python/duckdb.md
-  - LangChain 🦜️🔗↗: https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/lancedb.html
-  - LangChain.js 🦜️🔗↗: https://js.langchain.com/docs/modules/data_connection/vectorstores/integrations/lancedb
-  - LlamaIndex 🦙↗: https://gpt-index.readthedocs.io/en/latest/examples/vector_stores/LanceDBIndexDemo.html
-  - Pydantic: python/pydantic.md
-  - Voxel51: integrations/voxel51.md
-  - PromptTools: integrations/prompttools.md
-- Examples:
-  - examples/index.md
-  - YouTube Transcript Search: notebooks/youtube_transcript_search.ipynb
-  - Documentation QA Bot using LangChain: notebooks/code_qa_bot.ipynb
-  - Multimodal search using CLIP: notebooks/multimodal_search.ipynb
-  - Serverless QA Bot with S3 and Lambda: examples/serverless_lancedb_with_s3_and_lambda.md
-  - Serverless QA Bot with Modal: examples/serverless_qa_bot_with_modal_and_langchain.md
-  - YouTube Transcript Search (JS): examples/youtube_transcript_bot_with_nodejs.md
-  - Serverless Chatbot from any website: examples/serverless_website_chatbot.md
-  - TransformersJS Embedding Search: examples/transformerjs_embedding_search_nodejs.md
-- API reference:
-  - Overview: api_reference.md
-  - Python: python/python.md
-  - Javascript: javascript/modules.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/saas-modules.md
+  - API reference:
+      - Overview: api_reference.md
+      - Python: python/python.md
+      - Javascript (vectordb): javascript/modules.md
+      - Javascript (lancedb): js/modules.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/saas-modules.md
 
 extra_css:
   - styles/global.css

docs/src/api_reference.md

@@ -3,5 +3,6 @@
 The API reference for the LanceDB client SDKs are available at the following locations:
 
 - [Python](python/python.md)
-- [JavaScript](javascript/modules.md)
+- [JavaScript (legacy vectordb package)](javascript/modules.md)
+- [JavaScript (newer @lancedb/lancedb package)](js/modules.md)
 - [Rust](https://docs.rs/lancedb/latest/lancedb/index.html)

docs/src/basic.md

@@ -48,11 +48,20 @@
 
 === "Python"
 
-      ```python
-      import lancedb
-      uri = "data/sample-lancedb"
-      db = lancedb.connect(uri)
-      ```
+    ```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:connect_async"
+    ```
+
+    !!! note "Asynchronous Python API"
+
+        The asynchronous Python API is new and has some slight differences compared
+        to the synchronous API.  Feel free to start using the asynchronous version.
+        Once all features have migrated we will start to move the synchronous API to
+        use the same syntax as the asynchronous API.  To help with this migration we
+        have created a [migration guide](migration.md) detailing the differences.
 
 === "Typescript"
 
@@ -62,6 +71,16 @@
     --8<-- "docs/src/basic_legacy.ts:open_db"
     ```
 
+    !!! note "`@lancedb/lancedb` vs. `vectordb`"
+
+        The Javascript SDK was originally released as `vectordb`.  In an effort to
+        reduce maintenance we are aligning our SDKs.  The new, aligned, Javascript
+        API is being released as `lancedb`.  If you are starting new work we encourage
+        you to try out `lancedb`.  Once the new API is feature complete we will begin
+        slowly deprecating `vectordb` in favor of `lancedb`. There is a
+        [migration guide](migration.md) detailing the differences which will assist
+        you in this process.
+
 === "Rust"
 
     ```rust
@@ -82,15 +101,14 @@ If you need a reminder of the uri, you can call `db.uri()`.
 ### Create a table from initial data
 
 If you have data to insert into the table at creation time, you can simultaneously create a
-table and insert the data into it.  The schema of the data will be used as the schema of the
+table and insert the data into it. The schema of the data will be used as the schema of the
 table.
 
 === "Python"
 
     ```python
-    tbl = db.create_table("my_table",
-                    data=[{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
-                          {"vector": [5.9, 26.5], "item": "bar", "price": 20.0}])
+    --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.
@@ -100,10 +118,8 @@ table.
     You can also pass in a pandas DataFrame directly:
 
     ```python
-    import pandas as pd
-    df = pd.DataFrame([{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
-                       {"vector": [5.9, 26.5], "item": "bar", "price": 20.0}])
-    tbl = db.create_table("table_from_df", data=df)
+    --8<-- "python/python/tests/docs/test_basic.py:create_table_pandas"
+    --8<-- "python/python/tests/docs/test_basic.py:create_table_async_pandas"
     ```
 
 === "Typescript"
@@ -138,15 +154,14 @@ table.
 
 Sometimes you may not have the data to insert into the table at creation time.
 In this case, you can create an empty table and specify the schema, so that you can add
-data to the table at a later time (as long as it conforms to the schema).  This is
+data to the table at a later time (as long as it conforms to the schema). This is
 similar to a `CREATE TABLE` statement in SQL.
 
 === "Python"
 
       ```python
-      import pyarrow as pa
-      schema = pa.schema([pa.field("vector", pa.list_(pa.float32(), list_size=2))])
-      tbl = db.create_table("empty_table", schema=schema)
+      --8<-- "python/python/tests/docs/test_basic.py:create_empty_table"
+      --8<-- "python/python/tests/docs/test_basic.py:create_empty_table_async"
       ```
 
 === "Typescript"
@@ -168,7 +183,8 @@ Once created, you can open a table as follows:
 === "Python"
 
     ```python
-    tbl = db.open_table("my_table")
+    --8<-- "python/python/tests/docs/test_basic.py:open_table"
+    --8<-- "python/python/tests/docs/test_basic.py:open_table_async"
     ```
 
 === "Typescript"
@@ -188,7 +204,8 @@ If you forget the name of your table, you can always get a listing of all table
 === "Python"
 
     ```python
-    print(db.table_names())
+    --8<-- "python/python/tests/docs/test_basic.py:table_names"
+    --8<-- "python/python/tests/docs/test_basic.py:table_names_async"
     ```
 
 === "Javascript"
@@ -210,15 +227,8 @@ After a table has been created, you can always add more data to it as follows:
 === "Python"
 
     ```python
-
-    # Option 1: Add a list of dicts to a table
-    data = [{"vector": [1.3, 1.4], "item": "fizz", "price": 100.0},
-            {"vector": [9.5, 56.2], "item": "buzz", "price": 200.0}]
-    tbl.add(data)
-
-    # Option 2: Add a pandas DataFrame to a table
-    df = pd.DataFrame(data)
-    tbl.add(data)
+    --8<-- "python/python/tests/docs/test_basic.py:add_data"
+    --8<-- "python/python/tests/docs/test_basic.py:add_data_async"
     ```
 
 === "Typescript"
@@ -240,7 +250,8 @@ Once you've embedded the query, you can find its nearest neighbors as follows:
 === "Python"
 
     ```python
-    tbl.search([100, 100]).limit(2).to_pandas()
+    --8<-- "python/python/tests/docs/test_basic.py:vector_search"
+    --8<-- "python/python/tests/docs/test_basic.py:vector_search_async"
     ```
 
     This returns a pandas DataFrame with the results.
@@ -274,7 +285,8 @@ LanceDB allows you to create an ANN index on a table as follows:
 === "Python"
 
     ```py
-    tbl.create_index()
+    --8<-- "python/python/tests/docs/test_basic.py:create_index"
+    --8<-- "python/python/tests/docs/test_basic.py:create_index_async"
     ```
 
 === "Typescript"
@@ -286,15 +298,15 @@ LanceDB allows you to create an ANN index on a table as follows:
 === "Rust"
 
     ```rust
-     --8<-- "rust/lancedb/examples/simple.rs:create_index"
+    --8<-- "rust/lancedb/examples/simple.rs:create_index"
     ```
 
 !!! note "Why do I need to create an index manually?"
-    LanceDB does not automatically create the ANN index for two reasons. The first is that it's optimized
-    for really fast retrievals via a disk-based index, and the second is that data and query workloads can
-    be very diverse, so there's no one-size-fits-all index configuration. LanceDB provides many parameters
-    to fine-tune index size, query latency and accuracy. See the section on
-    [ANN indexes](ann_indexes.md) for more details.
+LanceDB does not automatically create the ANN index for two reasons. The first is that it's optimized
+for really fast retrievals via a disk-based index, and the second is that data and query workloads can
+be very diverse, so there's no one-size-fits-all index configuration. LanceDB provides many parameters
+to fine-tune index size, query latency and accuracy. See the section on
+[ANN indexes](ann_indexes.md) for more details.
 
 ## Delete rows from a table
 
@@ -305,7 +317,8 @@ This can delete any number of rows that match the filter.
 === "Python"
 
     ```python
-    tbl.delete('item = "fizz"')
+    --8<-- "python/python/tests/docs/test_basic.py:delete_rows"
+    --8<-- "python/python/tests/docs/test_basic.py:delete_rows_async"
     ```
 
 === "Typescript"
@@ -322,7 +335,7 @@ This can delete any number of rows that match the filter.
 
 The deletion predicate is a SQL expression that supports the same expressions
 as the `where()` clause (`only_if()` in Rust) on a search. They can be as
-simple or complex as needed.  To see what expressions are supported, see the
+simple or complex as needed. To see what expressions are supported, see the
 [SQL filters](sql.md) section.
 
 === "Python"
@@ -344,7 +357,8 @@ Use the `drop_table()` method on the database to remove a table.
 === "Python"
 
       ```python
-      db.drop_table("my_table")
+      --8<-- "python/python/tests/docs/test_basic.py:drop_table"
+      --8<-- "python/python/tests/docs/test_basic.py:drop_table_async"
       ```
 
       This permanently removes the table and is not recoverable, unlike deleting rows.

docs/src/embeddings/default_embedding_functions.md

@@ -19,27 +19,163 @@ Allows you to set parameters when registering a `sentence-transformers` object.
 | `normalize` | `bool` | `True` | Whether to normalize the input text before feeding it to the model |
 
 
-```python
-db = lancedb.connect("/tmp/db")
-registry = EmbeddingFunctionRegistry.get_instance()
-func = registry.get("sentence-transformers").create(device="cpu")
+??? "Check out available sentence-transformer models here!"
+    ```markdown
+    - sentence-transformers/all-MiniLM-L12-v2
+    - sentence-transformers/paraphrase-mpnet-base-v2
+    - sentence-transformers/gtr-t5-base
+    - sentence-transformers/LaBSE
+    - sentence-transformers/all-MiniLM-L6-v2
+    - sentence-transformers/bert-base-nli-max-tokens
+    - sentence-transformers/bert-base-nli-mean-tokens
+    - sentence-transformers/bert-base-nli-stsb-mean-tokens
+    - sentence-transformers/bert-base-wikipedia-sections-mean-tokens
+    - sentence-transformers/bert-large-nli-cls-token
+    - sentence-transformers/bert-large-nli-max-tokens
+    - sentence-transformers/bert-large-nli-mean-tokens
+    - sentence-transformers/bert-large-nli-stsb-mean-tokens
+    - sentence-transformers/distilbert-base-nli-max-tokens
+    - sentence-transformers/distilbert-base-nli-mean-tokens
+    - sentence-transformers/distilbert-base-nli-stsb-mean-tokens
+    - sentence-transformers/distilroberta-base-msmarco-v1
+    - sentence-transformers/distilroberta-base-msmarco-v2
+    - sentence-transformers/nli-bert-base-cls-pooling
+    - sentence-transformers/nli-bert-base-max-pooling
+    - sentence-transformers/nli-bert-base
+    - sentence-transformers/nli-bert-large-cls-pooling
+    - sentence-transformers/nli-bert-large-max-pooling
+    - sentence-transformers/nli-bert-large
+    - sentence-transformers/nli-distilbert-base-max-pooling
+    - sentence-transformers/nli-distilbert-base
+    - sentence-transformers/nli-roberta-base
+    - sentence-transformers/nli-roberta-large
+    - sentence-transformers/roberta-base-nli-mean-tokens
+    - sentence-transformers/roberta-base-nli-stsb-mean-tokens
+    - sentence-transformers/roberta-large-nli-mean-tokens
+    - sentence-transformers/roberta-large-nli-stsb-mean-tokens
+    - sentence-transformers/stsb-bert-base
+    - sentence-transformers/stsb-bert-large
+    - sentence-transformers/stsb-distilbert-base
+    - sentence-transformers/stsb-roberta-base
+    - sentence-transformers/stsb-roberta-large
+    - sentence-transformers/xlm-r-100langs-bert-base-nli-mean-tokens
+    - sentence-transformers/xlm-r-100langs-bert-base-nli-stsb-mean-tokens
+    - sentence-transformers/xlm-r-base-en-ko-nli-ststb
+    - sentence-transformers/xlm-r-bert-base-nli-mean-tokens
+    - sentence-transformers/xlm-r-bert-base-nli-stsb-mean-tokens
+    - sentence-transformers/xlm-r-large-en-ko-nli-ststb
+    - sentence-transformers/bert-base-nli-cls-token
+    - sentence-transformers/all-distilroberta-v1
+    - sentence-transformers/multi-qa-MiniLM-L6-dot-v1
+    - sentence-transformers/multi-qa-distilbert-cos-v1
+    - sentence-transformers/multi-qa-distilbert-dot-v1
+    - sentence-transformers/multi-qa-mpnet-base-cos-v1
+    - sentence-transformers/multi-qa-mpnet-base-dot-v1
+    - sentence-transformers/nli-distilroberta-base-v2
+    - sentence-transformers/all-MiniLM-L6-v1
+    - sentence-transformers/all-mpnet-base-v1
+    - sentence-transformers/all-mpnet-base-v2
+    - sentence-transformers/all-roberta-large-v1
+    - sentence-transformers/allenai-specter
+    - sentence-transformers/average_word_embeddings_glove.6B.300d
+    - sentence-transformers/average_word_embeddings_glove.840B.300d
+    - sentence-transformers/average_word_embeddings_komninos
+    - sentence-transformers/average_word_embeddings_levy_dependency
+    - sentence-transformers/clip-ViT-B-32-multilingual-v1
+    - sentence-transformers/clip-ViT-B-32
+    - sentence-transformers/distilbert-base-nli-stsb-quora-ranking
+    - sentence-transformers/distilbert-multilingual-nli-stsb-quora-ranking
+    - sentence-transformers/distilroberta-base-paraphrase-v1
+    - sentence-transformers/distiluse-base-multilingual-cased-v1
+    - sentence-transformers/distiluse-base-multilingual-cased-v2
+    - sentence-transformers/distiluse-base-multilingual-cased
+    - sentence-transformers/facebook-dpr-ctx_encoder-multiset-base
+    - sentence-transformers/facebook-dpr-ctx_encoder-single-nq-base
+    - sentence-transformers/facebook-dpr-question_encoder-multiset-base
+    - sentence-transformers/facebook-dpr-question_encoder-single-nq-base
+    - sentence-transformers/gtr-t5-large
+    - sentence-transformers/gtr-t5-xl
+    - sentence-transformers/gtr-t5-xxl
+    - sentence-transformers/msmarco-MiniLM-L-12-v3
+    - sentence-transformers/msmarco-MiniLM-L-6-v3
+    - sentence-transformers/msmarco-MiniLM-L12-cos-v5
+    - sentence-transformers/msmarco-MiniLM-L6-cos-v5
+    - sentence-transformers/msmarco-bert-base-dot-v5
+    - sentence-transformers/msmarco-bert-co-condensor
+    - sentence-transformers/msmarco-distilbert-base-dot-prod-v3
+    - sentence-transformers/msmarco-distilbert-base-tas-b
+    - sentence-transformers/msmarco-distilbert-base-v2
+    - sentence-transformers/msmarco-distilbert-base-v3
+    - sentence-transformers/msmarco-distilbert-base-v4
+    - sentence-transformers/msmarco-distilbert-cos-v5
+    - sentence-transformers/msmarco-distilbert-dot-v5
+    - sentence-transformers/msmarco-distilbert-multilingual-en-de-v2-tmp-lng-aligned
+    - sentence-transformers/msmarco-distilbert-multilingual-en-de-v2-tmp-trained-scratch
+    - sentence-transformers/msmarco-distilroberta-base-v2
+    - sentence-transformers/msmarco-roberta-base-ance-firstp
+    - sentence-transformers/msmarco-roberta-base-v2
+    - sentence-transformers/msmarco-roberta-base-v3
+    - sentence-transformers/multi-qa-MiniLM-L6-cos-v1
+    - sentence-transformers/nli-mpnet-base-v2
+    - sentence-transformers/nli-roberta-base-v2
+    - sentence-transformers/nq-distilbert-base-v1
+    - sentence-transformers/paraphrase-MiniLM-L12-v2
+    - sentence-transformers/paraphrase-MiniLM-L3-v2
+    - sentence-transformers/paraphrase-MiniLM-L6-v2
+    - sentence-transformers/paraphrase-TinyBERT-L6-v2
+    - sentence-transformers/paraphrase-albert-base-v2
+    - sentence-transformers/paraphrase-albert-small-v2
+    - sentence-transformers/paraphrase-distilroberta-base-v1
+    - sentence-transformers/paraphrase-distilroberta-base-v2
+    - sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+    - sentence-transformers/paraphrase-multilingual-mpnet-base-v2
+    - sentence-transformers/paraphrase-xlm-r-multilingual-v1
+    - sentence-transformers/quora-distilbert-base
+    - sentence-transformers/quora-distilbert-multilingual
+    - sentence-transformers/sentence-t5-base
+    - sentence-transformers/sentence-t5-large
+    - sentence-transformers/sentence-t5-xxl
+    - sentence-transformers/sentence-t5-xl
+    - sentence-transformers/stsb-distilroberta-base-v2
+    - sentence-transformers/stsb-mpnet-base-v2
+    - sentence-transformers/stsb-roberta-base-v2
+    - sentence-transformers/stsb-xlm-r-multilingual
+    - sentence-transformers/xlm-r-distilroberta-base-paraphrase-v1
+    - sentence-transformers/clip-ViT-L-14
+    - sentence-transformers/clip-ViT-B-16
+    - sentence-transformers/use-cmlm-multilingual
+    - sentence-transformers/all-MiniLM-L12-v1
+    ```
 
-class Words(LanceModel):
-    text: str = func.SourceField()
-    vector: Vector(func.ndims()) = func.VectorField()
+!!! info
+    You can also load many other model architectures from the library. For example models from sources such as BAAI, nomic, salesforce research, etc.
+    See this HF hub page for all [supported models](https://huggingface.co/models?library=sentence-transformers).
 
-table = db.create_table("words", schema=Words)
-table.add(
-    [
-        {"text": "hello world"}
-        {"text": "goodbye world"}
-    ]
-)
+!!! note "BAAI Embeddings example"
+    Here is an example that uses BAAI embedding model from the HuggingFace Hub [supported models](https://huggingface.co/models?library=sentence-transformers)
+    ```python
+    db = lancedb.connect("/tmp/db")
+    registry = EmbeddingFunctionRegistry.get_instance()
+    model = registry.get("sentence-transformers").create(name="BAAI/bge-small-en-v1.5", device="cpu")
+
+    class Words(LanceModel):
+        text: str = model.SourceField()
+        vector: Vector(model.ndims()) = model.VectorField()
+
+    table = db.create_table("words", schema=Words)
+    table.add(
+        [
+            {"text": "hello world"}
+            {"text": "goodbye world"}
+        ]
+    )
+
+    query = "greetings"
+    actual = table.search(query).limit(1).to_pydantic(Words)[0]
+    print(actual.text)
+    ```
+Visit sentence-transformers [HuggingFace HUB](https://huggingface.co/sentence-transformers) page for more information on the available models.
 
-query = "greetings"
-actual = table.search(query).limit(1).to_pydantic(Words)[0]
-print(actual.text)
-```
 
 ### OpenAI embeddings
 LanceDB registers the OpenAI embeddings function in the registry by default, as `openai`. Below are the parameters that you can customize when creating the instances:

docs/src/extra_js/init_ask_ai_widget.js

@@ -1,11 +1,79 @@
-document.addEventListener("DOMContentLoaded", function () {
-    var script = document.createElement("script");
-    script.src = "https://widget.kapa.ai/kapa-widget.bundle.js";
-    script.setAttribute("data-website-id", "c5881fae-cec0-490b-b45e-d83d131d4f25");
-    script.setAttribute("data-project-name", "LanceDB");
-    script.setAttribute("data-project-color", "#000000");
-    script.setAttribute("data-project-logo", "https://avatars.githubusercontent.com/u/108903835?s=200&v=4");
-  script.setAttribute("data-modal-example-questions","Help me create an IVF_PQ index,How do I do an exhaustive search?,How do I create a LanceDB table?,Can I use my own embedding function?");
-    script.async = true;
-    document.head.appendChild(script);
-  });
+// Creates an SVG robot icon (from Lucide)
+function robotSVG() {
+  var svg = document.createElementNS("http://www.w3.org/2000/svg", "svg");
+  svg.setAttribute("width", "24");
+  svg.setAttribute("height", "24");
+  svg.setAttribute("viewBox", "0 0 24 24");
+  svg.setAttribute("fill", "none");
+  svg.setAttribute("stroke", "currentColor");
+  svg.setAttribute("stroke-width", "2");
+  svg.setAttribute("stroke-linecap", "round");
+  svg.setAttribute("stroke-linejoin", "round");
+  svg.setAttribute("class", "lucide lucide-bot-message-square");
+
+  var path1 = document.createElementNS("http://www.w3.org/2000/svg", "path");
+  path1.setAttribute("d", "M12 6V2H8");
+  svg.appendChild(path1);
+
+  var path2 = document.createElementNS("http://www.w3.org/2000/svg", "path");
+  path2.setAttribute("d", "m8 18-4 4V8a2 2 0 0 1 2-2h12a2 2 0 0 1 2 2v8a2 2 0 0 1-2 2Z");
+  svg.appendChild(path2);
+
+  var path3 = document.createElementNS("http://www.w3.org/2000/svg", "path");
+  path3.setAttribute("d", "M2 12h2");
+  svg.appendChild(path3);
+
+  var path4 = document.createElementNS("http://www.w3.org/2000/svg", "path");
+  path4.setAttribute("d", "M9 11v2");
+  svg.appendChild(path4);
+
+  var path5 = document.createElementNS("http://www.w3.org/2000/svg", "path");
+  path5.setAttribute("d", "M15 11v2");
+  svg.appendChild(path5);
+
+  var path6 = document.createElementNS("http://www.w3.org/2000/svg", "path");
+  path6.setAttribute("d", "M20 12h2");
+  svg.appendChild(path6);
+
+  return svg
+}
+
+// Creates the Fluidic Chatbot buttom
+function fluidicButton() {
+  var btn = document.createElement("a");
+  btn.href = "https://asklancedb.com";
+  btn.target = "_blank";
+  btn.style.position = "fixed";
+  btn.style.fontWeight = "bold";
+  btn.style.fontSize = ".8rem";
+  btn.style.right = "10px";
+  btn.style.bottom = "10px";
+  btn.style.width = "80px";
+  btn.style.height = "80px";
+  btn.style.background = "linear-gradient(135deg, #7C5EFF 0%, #625eff 100%)";
+  btn.style.color = "white";
+  btn.style.borderRadius = "5px";
+  btn.style.display = "flex";
+  btn.style.flexDirection = "column";
+  btn.style.justifyContent = "center";
+  btn.style.alignItems = "center";
+  btn.style.zIndex = "1000";
+  btn.style.opacity = "0";
+  btn.style.boxShadow = "0 0 0 rgba(0, 0, 0, 0)";
+  btn.style.transition = "opacity 0.2s ease-in, box-shadow 0.2s ease-in";
+
+  setTimeout(function() {
+      btn.style.opacity = "1";
+      btn.style.boxShadow = "0 0 .2rem #0000001a,0 .2rem .4rem #0003"
+  }, 0);
+
+  return btn
+}
+
+document.addEventListener("DOMContentLoaded", function() {
+  var btn = fluidicButton()
+  btn.appendChild(robotSVG());
+  var text = document.createTextNode("Ask AI");
+  btn.appendChild(text);
+  document.body.appendChild(btn);
+});

docs/src/js/.nojekyll

@@ -0,0 +1 @@
+TypeDoc added this file to prevent GitHub Pages from using Jekyll. You can turn off this behavior by setting the `githubPages` option to false.

docs/src/js/README.md

@@ -0,0 +1,83 @@
+@lancedb/lancedb / [Exports](modules.md)
+
+# LanceDB JavaScript SDK
+
+A JavaScript library for [LanceDB](https://github.com/lancedb/lancedb).
+
+## Installation
+
+```bash
+npm install @lancedb/lancedb
+```
+
+This will download the appropriate native library for your platform. We currently
+support:
+
+- Linux (x86_64 and aarch64)
+- MacOS (Intel and ARM/M1/M2)
+- Windows (x86_64 only)
+
+We do not yet support musl-based Linux (such as Alpine Linux) or aarch64 Windows.
+
+## Usage
+
+### Basic Example
+
+```javascript
+import * as lancedb from "@lancedb/lancedb";
+const db = await lancedb.connect("data/sample-lancedb");
+const table = await db.createTable("my_table", [
+  { id: 1, vector: [0.1, 1.0], item: "foo", price: 10.0 },
+  { id: 2, vector: [3.9, 0.5], item: "bar", price: 20.0 },
+]);
+const results = await table.vectorSearch([0.1, 0.3]).limit(20).toArray();
+console.log(results);
+```
+
+The [quickstart](../basic.md) contains a more complete example.
+
+## Development
+
+```sh
+npm run build
+npm run test
+```
+
+### Running lint / format
+
+LanceDb uses eslint for linting. VSCode does not need any plugins to use eslint. However, it
+may need some additional configuration. Make sure that eslint.experimental.useFlatConfig is
+set to true. Also, if your vscode root folder is the repo root then you will need to set
+the eslint.workingDirectories to ["nodejs"]. To manually lint your code you can run:
+
+```sh
+npm run lint
+```
+
+LanceDb uses prettier for formatting. If you are using VSCode you will need to install the
+"Prettier - Code formatter" extension. You should then configure it to be the default formatter
+for typescript and you should enable format on save. To manually check your code's format you
+can run:
+
+```sh
+npm run chkformat
+```
+
+If you need to manually format your code you can run:
+
+```sh
+npx prettier --write .
+```
+
+### 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/classes/Connection.md

@@ -0,0 +1,239 @@
+[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / Connection
+
+# Class: Connection
+
+A LanceDB Connection that allows you to open tables and create new ones.
+
+Connection could be local against filesystem or remote against a server.
+
+A Connection is intended to be a long lived object and may hold open
+resources such as HTTP connection pools.  This is generally fine and
+a single connection should be shared if it is going to be used many
+times. However, if you are finished with a connection, you may call
+close to eagerly free these resources.  Any call to a Connection
+method after it has been closed will result in an error.
+
+Closing a connection is optional.  Connections will automatically
+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.
+
+## Table of contents
+
+### Constructors
+
+- [constructor](Connection.md#constructor)
+
+### Properties
+
+- [inner](Connection.md#inner)
+
+### Methods
+
+- [close](Connection.md#close)
+- [createEmptyTable](Connection.md#createemptytable)
+- [createTable](Connection.md#createtable)
+- [display](Connection.md#display)
+- [dropTable](Connection.md#droptable)
+- [isOpen](Connection.md#isopen)
+- [openTable](Connection.md#opentable)
+- [tableNames](Connection.md#tablenames)
+
+## Constructors
+
+### constructor
+
+• **new Connection**(`inner`): [`Connection`](Connection.md)
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `inner` | `Connection` |
+
+#### Returns
+
+[`Connection`](Connection.md)
+
+#### Defined in
+
+[connection.ts:72](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/connection.ts#L72)
+
+## Properties
+
+### inner
+
+• `Readonly` **inner**: `Connection`
+
+#### Defined in
+
+[connection.ts:70](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/connection.ts#L70)
+
+## Methods
+
+### close
+
+▸ **close**(): `void`
+
+Close the connection, releasing any underlying resources.
+
+It is safe to call this method multiple times.
+
+Any attempt to use the connection after it is closed will result in an error.
+
+#### Returns
+
+`void`
+
+#### Defined in
+
+[connection.ts:88](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/connection.ts#L88)
+
+___
+
+### createEmptyTable
+
+▸ **createEmptyTable**(`name`, `schema`, `options?`): `Promise`\<[`Table`](Table.md)\>
+
+Creates a new empty Table
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `name` | `string` | The name of the table. |
+| `schema` | `Schema`\<`any`\> | The schema of the table |
+| `options?` | `Partial`\<[`CreateTableOptions`](../interfaces/CreateTableOptions.md)\> | - |
+
+#### Returns
+
+`Promise`\<[`Table`](Table.md)\>
+
+#### Defined in
+
+[connection.ts:151](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/connection.ts#L151)
+
+___
+
+### createTable
+
+▸ **createTable**(`name`, `data`, `options?`): `Promise`\<[`Table`](Table.md)\>
+
+Creates a new Table and initialize it with new data.
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `name` | `string` | The name of the table. |
+| `data` | `Table`\<`any`\> \| `Record`\<`string`, `unknown`\>[] | Non-empty Array of Records to be inserted into the table |
+| `options?` | `Partial`\<[`CreateTableOptions`](../interfaces/CreateTableOptions.md)\> | - |
+
+#### Returns
+
+`Promise`\<[`Table`](Table.md)\>
+
+#### Defined in
+
+[connection.ts:123](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/connection.ts#L123)
+
+___
+
+### display
+
+▸ **display**(): `string`
+
+Return a brief description of the connection
+
+#### Returns
+
+`string`
+
+#### Defined in
+
+[connection.ts:93](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/connection.ts#L93)
+
+___
+
+### dropTable
+
+▸ **dropTable**(`name`): `Promise`\<`void`\>
+
+Drop an existing table.
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `name` | `string` | The name of the table to drop. |
+
+#### Returns
+
+`Promise`\<`void`\>
+
+#### Defined in
+
+[connection.ts:173](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/connection.ts#L173)
+
+___
+
+### isOpen
+
+▸ **isOpen**(): `boolean`
+
+Return true if the connection has not been closed
+
+#### Returns
+
+`boolean`
+
+#### Defined in
+
+[connection.ts:77](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/connection.ts#L77)
+
+___
+
+### openTable
+
+▸ **openTable**(`name`): `Promise`\<[`Table`](Table.md)\>
+
+Open a table in the database.
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `name` | `string` | The name of the table |
+
+#### Returns
+
+`Promise`\<[`Table`](Table.md)\>
+
+#### Defined in
+
+[connection.ts:112](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/connection.ts#L112)
+
+___
+
+### tableNames
+
+▸ **tableNames**(`options?`): `Promise`\<`string`[]\>
+
+List all the table names in this database.
+
+Tables will be returned in lexicographical order.
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `options?` | `Partial`\<[`TableNamesOptions`](../interfaces/TableNamesOptions.md)\> | options to control the paging / start point |
+
+#### Returns
+
+`Promise`\<`string`[]\>
+
+#### Defined in
+
+[connection.ts:104](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/connection.ts#L104)

docs/src/js/classes/Index.md

@@ -0,0 +1,121 @@
+[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / Index
+
+# Class: Index
+
+## Table of contents
+
+### Constructors
+
+- [constructor](Index.md#constructor)
+
+### Properties
+
+- [inner](Index.md#inner)
+
+### Methods
+
+- [btree](Index.md#btree)
+- [ivfPq](Index.md#ivfpq)
+
+## Constructors
+
+### constructor
+
+• **new Index**(`inner`): [`Index`](Index.md)
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `inner` | `Index` |
+
+#### Returns
+
+[`Index`](Index.md)
+
+#### Defined in
+
+[indices.ts:118](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/indices.ts#L118)
+
+## Properties
+
+### inner
+
+• `Private` `Readonly` **inner**: `Index`
+
+#### Defined in
+
+[indices.ts:117](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/indices.ts#L117)
+
+## Methods
+
+### btree
+
+▸ **btree**(): [`Index`](Index.md)
+
+Create a btree index
+
+A btree index is an index on a scalar columns.  The index stores a copy of the column
+in sorted order.  A header entry is created for each block of rows (currently the
+block size is fixed at 4096).  These header entries are stored in a separate
+cacheable structure (a btree).  To search for data the header is used to determine
+which blocks need to be read from disk.
+
+For example, a btree index in a table with 1Bi rows requires sizeof(Scalar) * 256Ki
+bytes of memory and will generally need to read sizeof(Scalar) * 4096 bytes to find
+the correct row ids.
+
+This index is good for scalar columns with mostly distinct values and does best when
+the query is highly selective.
+
+The btree index does not currently have any parameters though parameters such as the
+block size may be added in the future.
+
+#### Returns
+
+[`Index`](Index.md)
+
+#### Defined in
+
+[indices.ts:175](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/indices.ts#L175)
+
+___
+
+### ivfPq
+
+▸ **ivfPq**(`options?`): [`Index`](Index.md)
+
+Create an IvfPq index
+
+This index stores a compressed (quantized) copy of every vector.  These vectors
+are grouped 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 compressed vectors in these partitions are then searched to find
+the closest vectors.
+
+The compression scheme is called product quantization.  Each vector is divided into
+subvectors and then each subvector is quantized into a small number of bits.  the
+parameters `num_bits` and `num_subvectors` control this process, providing a tradeoff
+between index size (and thus search speed) and index accuracy.
+
+The partitioning process is called IVF and the `num_partitions` parameter controls how
+many groups to create.
+
+Note that training an IVF PQ index on a large dataset is a slow operation and
+currently is also a memory intensive operation.
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `options?` | `Partial`\<[`IvfPqOptions`](../interfaces/IvfPqOptions.md)\> |
+
+#### Returns
+
+[`Index`](Index.md)
+
+#### Defined in
+
+[indices.ts:144](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/indices.ts#L144)

docs/src/js/classes/MakeArrowTableOptions.md

@@ -0,0 +1,75 @@
+[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / MakeArrowTableOptions
+
+# Class: MakeArrowTableOptions
+
+Options to control the makeArrowTable call.
+
+## Table of contents
+
+### Constructors
+
+- [constructor](MakeArrowTableOptions.md#constructor)
+
+### Properties
+
+- [dictionaryEncodeStrings](MakeArrowTableOptions.md#dictionaryencodestrings)
+- [schema](MakeArrowTableOptions.md#schema)
+- [vectorColumns](MakeArrowTableOptions.md#vectorcolumns)
+
+## Constructors
+
+### constructor
+
+• **new MakeArrowTableOptions**(`values?`): [`MakeArrowTableOptions`](MakeArrowTableOptions.md)
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `values?` | `Partial`\<[`MakeArrowTableOptions`](MakeArrowTableOptions.md)\> |
+
+#### Returns
+
+[`MakeArrowTableOptions`](MakeArrowTableOptions.md)
+
+#### Defined in
+
+[arrow.ts:100](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/arrow.ts#L100)
+
+## Properties
+
+### dictionaryEncodeStrings
+
+• **dictionaryEncodeStrings**: `boolean` = `false`
+
+If true then string columns will be encoded with dictionary encoding
+
+Set this to true if your string columns tend to repeat the same values
+often.  For more precise control use the `schema` property to specify the
+data type for individual columns.
+
+If `schema` is provided then this property is ignored.
+
+#### Defined in
+
+[arrow.ts:98](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/arrow.ts#L98)
+
+___
+
+### schema
+
+• `Optional` **schema**: `Schema`\<`any`\>
+
+#### Defined in
+
+[arrow.ts:67](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/arrow.ts#L67)
+
+___
+
+### vectorColumns
+
+• **vectorColumns**: `Record`\<`string`, [`VectorColumnOptions`](VectorColumnOptions.md)\>
+
+#### Defined in
+
+[arrow.ts:85](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/arrow.ts#L85)

docs/src/js/classes/Query.md

@@ -0,0 +1,368 @@
+[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / Query
+
+# Class: Query
+
+A builder for LanceDB queries.
+
+## Hierarchy
+
+- [`QueryBase`](QueryBase.md)\<`NativeQuery`, [`Query`](Query.md)\>
+
+  ↳ **`Query`**
+
+## Table of contents
+
+### Constructors
+
+- [constructor](Query.md#constructor)
+
+### Properties
+
+- [inner](Query.md#inner)
+
+### Methods
+
+- [[asyncIterator]](Query.md#[asynciterator])
+- [execute](Query.md#execute)
+- [limit](Query.md#limit)
+- [nativeExecute](Query.md#nativeexecute)
+- [nearestTo](Query.md#nearestto)
+- [select](Query.md#select)
+- [toArray](Query.md#toarray)
+- [toArrow](Query.md#toarrow)
+- [where](Query.md#where)
+
+## Constructors
+
+### constructor
+
+• **new Query**(`tbl`): [`Query`](Query.md)
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `tbl` | `Table` |
+
+#### Returns
+
+[`Query`](Query.md)
+
+#### Overrides
+
+[QueryBase](QueryBase.md).[constructor](QueryBase.md#constructor)
+
+#### Defined in
+
+[query.ts:329](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L329)
+
+## Properties
+
+### inner
+
+• `Protected` **inner**: `Query`
+
+#### Inherited from
+
+[QueryBase](QueryBase.md).[inner](QueryBase.md#inner)
+
+#### Defined in
+
+[query.ts:59](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L59)
+
+## Methods
+
+### [asyncIterator]
+
+▸ **[asyncIterator]**(): `AsyncIterator`\<`RecordBatch`\<`any`\>, `any`, `undefined`\>
+
+#### Returns
+
+`AsyncIterator`\<`RecordBatch`\<`any`\>, `any`, `undefined`\>
+
+#### Inherited from
+
+[QueryBase](QueryBase.md).[[asyncIterator]](QueryBase.md#[asynciterator])
+
+#### Defined in
+
+[query.ts:154](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L154)
+
+___
+
+### execute
+
+▸ **execute**(): [`RecordBatchIterator`](RecordBatchIterator.md)
+
+Execute the query and return the results as an
+
+#### Returns
+
+[`RecordBatchIterator`](RecordBatchIterator.md)
+
+**`See`**
+
+ - AsyncIterator
+of
+ - RecordBatch.
+
+By default, LanceDb will use many threads to calculate results and, when
+the result set is large, multiple batches will be processed at one time.
+This readahead is limited however and backpressure will be applied if this
+stream is consumed slowly (this constrains the maximum memory used by a
+single query)
+
+#### Inherited from
+
+[QueryBase](QueryBase.md).[execute](QueryBase.md#execute)
+
+#### Defined in
+
+[query.ts:149](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L149)
+
+___
+
+### limit
+
+▸ **limit**(`limit`): [`Query`](Query.md)
+
+Set the maximum number of results to return.
+
+By default, a plain search has no limit.  If this method is not
+called then every valid row from the table will be returned.
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `limit` | `number` |
+
+#### Returns
+
+[`Query`](Query.md)
+
+#### Inherited from
+
+[QueryBase](QueryBase.md).[limit](QueryBase.md#limit)
+
+#### Defined in
+
+[query.ts:129](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L129)
+
+___
+
+### nativeExecute
+
+▸ **nativeExecute**(): `Promise`\<`RecordBatchIterator`\>
+
+#### Returns
+
+`Promise`\<`RecordBatchIterator`\>
+
+#### Inherited from
+
+[QueryBase](QueryBase.md).[nativeExecute](QueryBase.md#nativeexecute)
+
+#### Defined in
+
+[query.ts:134](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L134)
+
+___
+
+### nearestTo
+
+▸ **nearestTo**(`vector`): [`VectorQuery`](VectorQuery.md)
+
+Find the nearest vectors to the given query vector.
+
+This converts the query from a plain query to a vector query.
+
+This method will attempt to convert the input to the query vector
+expected by the embedding model.  If the input cannot be converted
+then an error will be thrown.
+
+By default, there is no embedding model, and the input should be
+an array-like object of numbers (something that can be used as input
+to Float32Array.from)
+
+If there is only one vector column (a column whose data type is a
+fixed size list of floats) then the column does not need to be specified.
+If there is more than one vector column you must use
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `vector` | `unknown` |
+
+#### Returns
+
+[`VectorQuery`](VectorQuery.md)
+
+**`See`**
+
+ - [VectorQuery#column](VectorQuery.md#column)  to specify which column you would like
+to compare with.
+
+If no index has been created on the vector column then a vector query
+will perform a distance comparison between the query vector and every
+vector in the database and then sort the results.  This is sometimes
+called a "flat search"
+
+For small databases, with a few hundred thousand vectors or less, this can
+be reasonably fast.  In larger databases you should create a vector index
+on the column.  If there is a vector index then an "approximate" nearest
+neighbor search (frequently called an ANN search) will be performed.  This
+search is much faster, but the results will be approximate.
+
+The query can be further parameterized using the returned builder.  There
+are various ANN search parameters that will let you fine tune your recall
+accuracy vs search latency.
+
+Vector searches always have a `limit`.  If `limit` has not been called then
+a default `limit` of 10 will be used.
+ - [Query#limit](Query.md#limit)
+
+#### Defined in
+
+[query.ts:370](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L370)
+
+___
+
+### select
+
+▸ **select**(`columns`): [`Query`](Query.md)
+
+Return only the specified columns.
+
+By default a query will return all columns from the table.  However, this can have
+a very significant impact on latency.  LanceDb stores data in a columnar fashion.  This
+means we can finely tune our I/O to select exactly the columns we need.
+
+As a best practice you should always limit queries to the columns that you need.  If you
+pass in an array of column names then only those columns will be returned.
+
+You can also use this method to create new "dynamic" columns based on your existing columns.
+For example, you may not care about "a" or "b" but instead simply want "a + b".  This is often
+seen in the SELECT clause of an SQL query (e.g. `SELECT a+b FROM my_table`).
+
+To create dynamic columns you can pass in a Map<string, string>.  A column will be returned
+for each entry in the map.  The key provides the name of the column.  The value is
+an SQL string used to specify how the column is calculated.
+
+For example, an SQL query might state `SELECT a + b AS combined, c`.  The equivalent
+input to this method would be:
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `columns` | `string`[] \| `Record`\<`string`, `string`\> \| `Map`\<`string`, `string`\> |
+
+#### Returns
+
+[`Query`](Query.md)
+
+**`Example`**
+
+```ts
+new Map([["combined", "a + b"], ["c", "c"]])
+
+Columns will always be returned in the order given, even if that order is different than
+the order used when adding the data.
+
+Note that you can pass in a `Record<string, string>` (e.g. an object literal). This method
+uses `Object.entries` which should preserve the insertion order of the object.  However,
+object insertion order is easy to get wrong and `Map` is more foolproof.
+```
+
+#### Inherited from
+
+[QueryBase](QueryBase.md).[select](QueryBase.md#select)
+
+#### Defined in
+
+[query.ts:108](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L108)
+
+___
+
+### toArray
+
+▸ **toArray**(): `Promise`\<`unknown`[]\>
+
+Collect the results as an array of objects.
+
+#### Returns
+
+`Promise`\<`unknown`[]\>
+
+#### Inherited from
+
+[QueryBase](QueryBase.md).[toArray](QueryBase.md#toarray)
+
+#### Defined in
+
+[query.ts:169](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L169)
+
+___
+
+### toArrow
+
+▸ **toArrow**(): `Promise`\<`Table`\<`any`\>\>
+
+Collect the results as an Arrow
+
+#### Returns
+
+`Promise`\<`Table`\<`any`\>\>
+
+**`See`**
+
+ArrowTable.
+
+#### Inherited from
+
+[QueryBase](QueryBase.md).[toArrow](QueryBase.md#toarrow)
+
+#### Defined in
+
+[query.ts:160](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L160)
+
+___
+
+### where
+
+▸ **where**(`predicate`): [`Query`](Query.md)
+
+A filter statement to be applied to this query.
+
+The filter should be supplied as an SQL query string.  For example:
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `predicate` | `string` |
+
+#### Returns
+
+[`Query`](Query.md)
+
+**`Example`**
+
+```ts
+x > 10
+y > 0 AND y < 100
+x > 5 OR y = 'test'
+
+Filtering performance can often be improved by creating a scalar index
+on the filter column(s).
+```
+
+#### Inherited from
+
+[QueryBase](QueryBase.md).[where](QueryBase.md#where)
+
+#### Defined in
+
+[query.ts:73](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L73)

docs/src/js/classes/QueryBase.md

@@ -0,0 +1,291 @@
+[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / QueryBase
+
+# Class: QueryBase\<NativeQueryType, QueryType\>
+
+Common methods supported by all query types
+
+## Type parameters
+
+| Name | Type |
+| :------ | :------ |
+| `NativeQueryType` | extends `NativeQuery` \| `NativeVectorQuery` |
+| `QueryType` | `QueryType` |
+
+## Hierarchy
+
+- **`QueryBase`**
+
+  ↳ [`Query`](Query.md)
+
+  ↳ [`VectorQuery`](VectorQuery.md)
+
+## Implements
+
+- `AsyncIterable`\<`RecordBatch`\>
+
+## Table of contents
+
+### Constructors
+
+- [constructor](QueryBase.md#constructor)
+
+### Properties
+
+- [inner](QueryBase.md#inner)
+
+### Methods
+
+- [[asyncIterator]](QueryBase.md#[asynciterator])
+- [execute](QueryBase.md#execute)
+- [limit](QueryBase.md#limit)
+- [nativeExecute](QueryBase.md#nativeexecute)
+- [select](QueryBase.md#select)
+- [toArray](QueryBase.md#toarray)
+- [toArrow](QueryBase.md#toarrow)
+- [where](QueryBase.md#where)
+
+## Constructors
+
+### constructor
+
+• **new QueryBase**\<`NativeQueryType`, `QueryType`\>(`inner`): [`QueryBase`](QueryBase.md)\<`NativeQueryType`, `QueryType`\>
+
+#### Type parameters
+
+| Name | Type |
+| :------ | :------ |
+| `NativeQueryType` | extends `Query` \| `VectorQuery` |
+| `QueryType` | `QueryType` |
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `inner` | `NativeQueryType` |
+
+#### Returns
+
+[`QueryBase`](QueryBase.md)\<`NativeQueryType`, `QueryType`\>
+
+#### Defined in
+
+[query.ts:59](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L59)
+
+## Properties
+
+### inner
+
+• `Protected` **inner**: `NativeQueryType`
+
+#### Defined in
+
+[query.ts:59](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L59)
+
+## Methods
+
+### [asyncIterator]
+
+▸ **[asyncIterator]**(): `AsyncIterator`\<`RecordBatch`\<`any`\>, `any`, `undefined`\>
+
+#### Returns
+
+`AsyncIterator`\<`RecordBatch`\<`any`\>, `any`, `undefined`\>
+
+#### Implementation of
+
+AsyncIterable.[asyncIterator]
+
+#### Defined in
+
+[query.ts:154](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L154)
+
+___
+
+### execute
+
+▸ **execute**(): [`RecordBatchIterator`](RecordBatchIterator.md)
+
+Execute the query and return the results as an
+
+#### Returns
+
+[`RecordBatchIterator`](RecordBatchIterator.md)
+
+**`See`**
+
+ - AsyncIterator
+of
+ - RecordBatch.
+
+By default, LanceDb will use many threads to calculate results and, when
+the result set is large, multiple batches will be processed at one time.
+This readahead is limited however and backpressure will be applied if this
+stream is consumed slowly (this constrains the maximum memory used by a
+single query)
+
+#### Defined in
+
+[query.ts:149](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L149)
+
+___
+
+### limit
+
+▸ **limit**(`limit`): `QueryType`
+
+Set the maximum number of results to return.
+
+By default, a plain search has no limit.  If this method is not
+called then every valid row from the table will be returned.
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `limit` | `number` |
+
+#### Returns
+
+`QueryType`
+
+#### Defined in
+
+[query.ts:129](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L129)
+
+___
+
+### nativeExecute
+
+▸ **nativeExecute**(): `Promise`\<`RecordBatchIterator`\>
+
+#### Returns
+
+`Promise`\<`RecordBatchIterator`\>
+
+#### Defined in
+
+[query.ts:134](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L134)
+
+___
+
+### select
+
+▸ **select**(`columns`): `QueryType`
+
+Return only the specified columns.
+
+By default a query will return all columns from the table.  However, this can have
+a very significant impact on latency.  LanceDb stores data in a columnar fashion.  This
+means we can finely tune our I/O to select exactly the columns we need.
+
+As a best practice you should always limit queries to the columns that you need.  If you
+pass in an array of column names then only those columns will be returned.
+
+You can also use this method to create new "dynamic" columns based on your existing columns.
+For example, you may not care about "a" or "b" but instead simply want "a + b".  This is often
+seen in the SELECT clause of an SQL query (e.g. `SELECT a+b FROM my_table`).
+
+To create dynamic columns you can pass in a Map<string, string>.  A column will be returned
+for each entry in the map.  The key provides the name of the column.  The value is
+an SQL string used to specify how the column is calculated.
+
+For example, an SQL query might state `SELECT a + b AS combined, c`.  The equivalent
+input to this method would be:
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `columns` | `string`[] \| `Record`\<`string`, `string`\> \| `Map`\<`string`, `string`\> |
+
+#### Returns
+
+`QueryType`
+
+**`Example`**
+
+```ts
+new Map([["combined", "a + b"], ["c", "c"]])
+
+Columns will always be returned in the order given, even if that order is different than
+the order used when adding the data.
+
+Note that you can pass in a `Record<string, string>` (e.g. an object literal). This method
+uses `Object.entries` which should preserve the insertion order of the object.  However,
+object insertion order is easy to get wrong and `Map` is more foolproof.
+```
+
+#### Defined in
+
+[query.ts:108](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L108)
+
+___
+
+### toArray
+
+▸ **toArray**(): `Promise`\<`unknown`[]\>
+
+Collect the results as an array of objects.
+
+#### Returns
+
+`Promise`\<`unknown`[]\>
+
+#### Defined in
+
+[query.ts:169](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L169)
+
+___
+
+### toArrow
+
+▸ **toArrow**(): `Promise`\<`Table`\<`any`\>\>
+
+Collect the results as an Arrow
+
+#### Returns
+
+`Promise`\<`Table`\<`any`\>\>
+
+**`See`**
+
+ArrowTable.
+
+#### Defined in
+
+[query.ts:160](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L160)
+
+___
+
+### where
+
+▸ **where**(`predicate`): `QueryType`
+
+A filter statement to be applied to this query.
+
+The filter should be supplied as an SQL query string.  For example:
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `predicate` | `string` |
+
+#### Returns
+
+`QueryType`
+
+**`Example`**
+
+```ts
+x > 10
+y > 0 AND y < 100
+x > 5 OR y = 'test'
+
+Filtering performance can often be improved by creating a scalar index
+on the filter column(s).
+```
+
+#### Defined in
+
+[query.ts:73](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L73)

docs/src/js/classes/RecordBatchIterator.md

@@ -0,0 +1,80 @@
+[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / RecordBatchIterator
+
+# Class: RecordBatchIterator
+
+## Implements
+
+- `AsyncIterator`\<`RecordBatch`\>
+
+## Table of contents
+
+### Constructors
+
+- [constructor](RecordBatchIterator.md#constructor)
+
+### Properties
+
+- [inner](RecordBatchIterator.md#inner)
+- [promisedInner](RecordBatchIterator.md#promisedinner)
+
+### Methods
+
+- [next](RecordBatchIterator.md#next)
+
+## Constructors
+
+### constructor
+
+• **new RecordBatchIterator**(`promise?`): [`RecordBatchIterator`](RecordBatchIterator.md)
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `promise?` | `Promise`\<`RecordBatchIterator`\> |
+
+#### Returns
+
+[`RecordBatchIterator`](RecordBatchIterator.md)
+
+#### Defined in
+
+[query.ts:27](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L27)
+
+## Properties
+
+### inner
+
+• `Private` `Optional` **inner**: `RecordBatchIterator`
+
+#### Defined in
+
+[query.ts:25](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L25)
+
+___
+
+### promisedInner
+
+• `Private` `Optional` **promisedInner**: `Promise`\<`RecordBatchIterator`\>
+
+#### Defined in
+
+[query.ts:24](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L24)
+
+## Methods
+
+### next
+
+▸ **next**(): `Promise`\<`IteratorResult`\<`RecordBatch`\<`any`\>, `any`\>\>
+
+#### Returns
+
+`Promise`\<`IteratorResult`\<`RecordBatch`\<`any`\>, `any`\>\>
+
+#### Implementation of
+
+AsyncIterator.next
+
+#### Defined in
+
+[query.ts:33](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L33)

docs/src/js/classes/Table.md

@@ -0,0 +1,594 @@
+[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / Table
+
+# Class: Table
+
+A Table is a collection of Records in a LanceDB Database.
+
+A Table object is expected to be long lived and reused for multiple operations.
+Table objects will cache a certain amount of index data in memory.  This cache
+will be freed when the Table is garbage collected.  To eagerly free the cache you
+can call the `close` method.  Once the Table is closed, it cannot be used for any
+further operations.
+
+Closing a table is optional.  It not closed, it will be closed when it is garbage
+collected.
+
+## Table of contents
+
+### Constructors
+
+- [constructor](Table.md#constructor)
+
+### Properties
+
+- [inner](Table.md#inner)
+
+### Methods
+
+- [add](Table.md#add)
+- [addColumns](Table.md#addcolumns)
+- [alterColumns](Table.md#altercolumns)
+- [checkout](Table.md#checkout)
+- [checkoutLatest](Table.md#checkoutlatest)
+- [close](Table.md#close)
+- [countRows](Table.md#countrows)
+- [createIndex](Table.md#createindex)
+- [delete](Table.md#delete)
+- [display](Table.md#display)
+- [dropColumns](Table.md#dropcolumns)
+- [isOpen](Table.md#isopen)
+- [listIndices](Table.md#listindices)
+- [query](Table.md#query)
+- [restore](Table.md#restore)
+- [schema](Table.md#schema)
+- [update](Table.md#update)
+- [vectorSearch](Table.md#vectorsearch)
+- [version](Table.md#version)
+
+## Constructors
+
+### constructor
+
+• **new Table**(`inner`): [`Table`](Table.md)
+
+Construct a Table. Internal use only.
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `inner` | `Table` |
+
+#### Returns
+
+[`Table`](Table.md)
+
+#### Defined in
+
+[table.ts:69](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L69)
+
+## Properties
+
+### inner
+
+• `Private` `Readonly` **inner**: `Table`
+
+#### Defined in
+
+[table.ts:66](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L66)
+
+## Methods
+
+### add
+
+▸ **add**(`data`, `options?`): `Promise`\<`void`\>
+
+Insert records into this Table.
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `data` | [`Data`](../modules.md#data) | Records to be inserted into the Table |
+| `options?` | `Partial`\<[`AddDataOptions`](../interfaces/AddDataOptions.md)\> | - |
+
+#### Returns
+
+`Promise`\<`void`\>
+
+#### Defined in
+
+[table.ts:105](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L105)
+
+___
+
+### addColumns
+
+▸ **addColumns**(`newColumnTransforms`): `Promise`\<`void`\>
+
+Add new columns with defined values.
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `newColumnTransforms` | [`AddColumnsSql`](../interfaces/AddColumnsSql.md)[] | pairs of column names and the SQL expression to use to calculate the value of the new column. These expressions will be evaluated for each row in the table, and can reference existing columns in the table. |
+
+#### Returns
+
+`Promise`\<`void`\>
+
+#### Defined in
+
+[table.ts:261](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L261)
+
+___
+
+### alterColumns
+
+▸ **alterColumns**(`columnAlterations`): `Promise`\<`void`\>
+
+Alter the name or nullability of columns.
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `columnAlterations` | [`ColumnAlteration`](../interfaces/ColumnAlteration.md)[] | One or more alterations to apply to columns. |
+
+#### Returns
+
+`Promise`\<`void`\>
+
+#### Defined in
+
+[table.ts:270](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L270)
+
+___
+
+### checkout
+
+▸ **checkout**(`version`): `Promise`\<`void`\>
+
+Checks out a specific version of the Table
+
+Any read operation on the table will now access the data at the checked out version.
+As a consequence, calling this method will disable any read consistency interval
+that was previously set.
+
+This is a read-only operation that turns the table into a sort of "view"
+or "detached head".  Other table instances will not be affected.  To make the change
+permanent you can use the `[Self::restore]` method.
+
+Any operation that modifies the table will fail while the table is in a checked
+out state.
+
+To return the table to a normal state use `[Self::checkout_latest]`
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `version` | `number` |
+
+#### Returns
+
+`Promise`\<`void`\>
+
+#### Defined in
+
+[table.ts:317](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L317)
+
+___
+
+### checkoutLatest
+
+▸ **checkoutLatest**(): `Promise`\<`void`\>
+
+Ensures the table is pointing at the latest version
+
+This can be used to manually update a table when the read_consistency_interval is None
+It can also be used to undo a `[Self::checkout]` operation
+
+#### Returns
+
+`Promise`\<`void`\>
+
+#### Defined in
+
+[table.ts:327](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L327)
+
+___
+
+### close
+
+▸ **close**(): `void`
+
+Close the table, releasing any underlying resources.
+
+It is safe to call this method multiple times.
+
+Any attempt to use the table after it is closed will result in an error.
+
+#### Returns
+
+`void`
+
+#### Defined in
+
+[table.ts:85](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L85)
+
+___
+
+### countRows
+
+▸ **countRows**(`filter?`): `Promise`\<`number`\>
+
+Count the total number of rows in the dataset.
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `filter?` | `string` |
+
+#### Returns
+
+`Promise`\<`number`\>
+
+#### Defined in
+
+[table.ts:152](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L152)
+
+___
+
+### createIndex
+
+▸ **createIndex**(`column`, `options?`): `Promise`\<`void`\>
+
+Create an index to speed up queries.
+
+Indices can be created on vector columns or scalar columns.
+Indices on vector columns will speed up vector searches.
+Indices on scalar columns will speed up filtering (in both
+vector and non-vector searches)
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `column` | `string` |
+| `options?` | `Partial`\<[`IndexOptions`](../interfaces/IndexOptions.md)\> |
+
+#### Returns
+
+`Promise`\<`void`\>
+
+**`Example`**
+
+```ts
+// If the column has a vector (fixed size list) data type then
+// an IvfPq vector index will be created.
+const table = await conn.openTable("my_table");
+await table.createIndex(["vector"]);
+```
+
+**`Example`**
+
+```ts
+// For advanced control over vector index creation you can specify
+// the index type and options.
+const table = await conn.openTable("my_table");
+await table.createIndex(["vector"], I)
+  .ivf_pq({ num_partitions: 128, num_sub_vectors: 16 })
+  .build();
+```
+
+**`Example`**
+
+```ts
+// Or create a Scalar index
+await table.createIndex("my_float_col").build();
+```
+
+#### Defined in
+
+[table.ts:184](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L184)
+
+___
+
+### delete
+
+▸ **delete**(`predicate`): `Promise`\<`void`\>
+
+Delete the rows that satisfy the predicate.
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `predicate` | `string` |
+
+#### Returns
+
+`Promise`\<`void`\>
+
+#### Defined in
+
+[table.ts:157](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L157)
+
+___
+
+### display
+
+▸ **display**(): `string`
+
+Return a brief description of the table
+
+#### Returns
+
+`string`
+
+#### Defined in
+
+[table.ts:90](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L90)
+
+___
+
+### dropColumns
+
+▸ **dropColumns**(`columnNames`): `Promise`\<`void`\>
+
+Drop one or more columns from the dataset
+
+This is a metadata-only operation and does not remove the data from the
+underlying storage. In order to remove the data, you must subsequently
+call ``compact_files`` to rewrite the data without the removed columns and
+then call ``cleanup_files`` to remove the old files.
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `columnNames` | `string`[] | The names of the columns to drop. These can be nested column references (e.g. "a.b.c") or top-level column names (e.g. "a"). |
+
+#### Returns
+
+`Promise`\<`void`\>
+
+#### Defined in
+
+[table.ts:285](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L285)
+
+___
+
+### isOpen
+
+▸ **isOpen**(): `boolean`
+
+Return true if the table has not been closed
+
+#### Returns
+
+`boolean`
+
+#### Defined in
+
+[table.ts:74](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L74)
+
+___
+
+### listIndices
+
+▸ **listIndices**(): `Promise`\<[`IndexConfig`](../interfaces/IndexConfig.md)[]\>
+
+List all indices that have been created with Self::create_index
+
+#### Returns
+
+`Promise`\<[`IndexConfig`](../interfaces/IndexConfig.md)[]\>
+
+#### Defined in
+
+[table.ts:350](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L350)
+
+___
+
+### query
+
+▸ **query**(): [`Query`](Query.md)
+
+Create a [Query](Query.md) Builder.
+
+Queries allow you to search your existing data.  By default the query will
+return all the data in the table in no particular order.  The builder
+returned by this method can be used to control the query using filtering,
+vector similarity, sorting, and more.
+
+Note: By default, all columns are returned.  For best performance, you should
+only fetch the columns you need.  See [`Query::select_with_projection`] for
+more details.
+
+When appropriate, various indices and statistics based pruning will be used to
+accelerate the query.
+
+#### Returns
+
+[`Query`](Query.md)
+
+A builder that can be used to parameterize the query
+
+**`Example`**
+
+```ts
+// SQL-style filtering
+//
+// This query will return up to 1000 rows whose value in the `id` column
+// is greater than 5.  LanceDb supports a broad set of filtering functions.
+for await (const batch of table.query()
+                         .filter("id > 1").select(["id"]).limit(20)) {
+ console.log(batch);
+}
+```
+
+**`Example`**
+
+```ts
+// Vector Similarity Search
+//
+// This example will find the 10 rows whose value in the "vector" column are
+// closest to the query vector [1.0, 2.0, 3.0].  If an index has been created
+// on the "vector" column then this will perform an ANN search.
+//
+// The `refine_factor` and `nprobes` methods are used to control the recall /
+// latency tradeoff of the search.
+for await (const batch of table.query()
+                   .nearestTo([1, 2, 3])
+                   .refineFactor(5).nprobe(10)
+                   .limit(10)) {
+ console.log(batch);
+}
+```
+
+**`Example`**
+
+```ts
+// Scan the full dataset
+//
+// This query will return everything in the table in no particular order.
+for await (const batch of table.query()) {
+  console.log(batch);
+}
+```
+
+#### Defined in
+
+[table.ts:238](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L238)
+
+___
+
+### restore
+
+▸ **restore**(): `Promise`\<`void`\>
+
+Restore the table to the currently checked out version
+
+This operation will fail if checkout has not been called previously
+
+This operation will overwrite the latest version of the table with a
+previous version.  Any changes made since the checked out version will
+no longer be visible.
+
+Once the operation concludes the table will no longer be in a checked
+out state and the read_consistency_interval, if any, will apply.
+
+#### Returns
+
+`Promise`\<`void`\>
+
+#### Defined in
+
+[table.ts:343](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L343)
+
+___
+
+### schema
+
+▸ **schema**(): `Promise`\<`Schema`\<`any`\>\>
+
+Get the schema of the table.
+
+#### Returns
+
+`Promise`\<`Schema`\<`any`\>\>
+
+#### Defined in
+
+[table.ts:95](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L95)
+
+___
+
+### update
+
+▸ **update**(`updates`, `options?`): `Promise`\<`void`\>
+
+Update existing records in the Table
+
+An update operation can be used to adjust existing values.  Use the
+returned builder to specify which columns to update.  The new value
+can be a literal value (e.g. replacing nulls with some default value)
+or an expression applied to the old value (e.g. incrementing a value)
+
+An optional condition can be specified (e.g. "only update if the old
+value is 0")
+
+Note: if your condition is something like "some_id_column == 7" and
+you are updating many rows (with different ids) then you will get
+better performance with a single [`merge_insert`] call instead of
+repeatedly calilng this method.
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `updates` | `Record`\<`string`, `string`\> \| `Map`\<`string`, `string`\> | the columns to update Keys in the map should specify the name of the column to update. Values in the map provide the new value of the column. These can be SQL literal strings (e.g. "7" or "'foo'") or they can be expressions based on the row being updated (e.g. "my_col + 1") |
+| `options?` | `Partial`\<[`UpdateOptions`](../interfaces/UpdateOptions.md)\> | additional options to control the update behavior |
+
+#### Returns
+
+`Promise`\<`void`\>
+
+#### Defined in
+
+[table.ts:137](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L137)
+
+___
+
+### vectorSearch
+
+▸ **vectorSearch**(`vector`): [`VectorQuery`](VectorQuery.md)
+
+Search the table with a given query vector.
+
+This is a convenience method for preparing a vector query and
+is the same thing as calling `nearestTo` on the builder returned
+by `query`.
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `vector` | `unknown` |
+
+#### Returns
+
+[`VectorQuery`](VectorQuery.md)
+
+**`See`**
+
+[Query#nearestTo](Query.md#nearestto) for more details.
+
+#### Defined in
+
+[table.ts:249](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L249)
+
+___
+
+### version
+
+▸ **version**(): `Promise`\<`number`\>
+
+Retrieve the version of the table
+
+LanceDb supports versioning.  Every operation that modifies the table increases
+version.  As long as a version hasn't been deleted you can `[Self::checkout]` that
+version to view the data at that point.  In addition, you can `[Self::restore]` the
+version to replace the current table with a previous version.
+
+#### Returns
+
+`Promise`\<`number`\>
+
+#### Defined in
+
+[table.ts:297](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L297)

docs/src/js/classes/VectorColumnOptions.md

@@ -0,0 +1,45 @@
+[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / VectorColumnOptions
+
+# Class: VectorColumnOptions
+
+## Table of contents
+
+### Constructors
+
+- [constructor](VectorColumnOptions.md#constructor)
+
+### Properties
+
+- [type](VectorColumnOptions.md#type)
+
+## Constructors
+
+### constructor
+
+• **new VectorColumnOptions**(`values?`): [`VectorColumnOptions`](VectorColumnOptions.md)
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `values?` | `Partial`\<[`VectorColumnOptions`](VectorColumnOptions.md)\> |
+
+#### Returns
+
+[`VectorColumnOptions`](VectorColumnOptions.md)
+
+#### Defined in
+
+[arrow.ts:49](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/arrow.ts#L49)
+
+## Properties
+
+### type
+
+• **type**: `Float`\<`Floats`\>
+
+Vector column type.
+
+#### Defined in
+
+[arrow.ts:47](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/arrow.ts#L47)

docs/src/js/classes/VectorQuery.md

@@ -0,0 +1,531 @@
+[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / VectorQuery
+
+# Class: VectorQuery
+
+A builder used to construct a vector search
+
+This builder can be reused to execute the query many times.
+
+## Hierarchy
+
+- [`QueryBase`](QueryBase.md)\<`NativeVectorQuery`, [`VectorQuery`](VectorQuery.md)\>
+
+  ↳ **`VectorQuery`**
+
+## Table of contents
+
+### Constructors
+
+- [constructor](VectorQuery.md#constructor)
+
+### Properties
+
+- [inner](VectorQuery.md#inner)
+
+### Methods
+
+- [[asyncIterator]](VectorQuery.md#[asynciterator])
+- [bypassVectorIndex](VectorQuery.md#bypassvectorindex)
+- [column](VectorQuery.md#column)
+- [distanceType](VectorQuery.md#distancetype)
+- [execute](VectorQuery.md#execute)
+- [limit](VectorQuery.md#limit)
+- [nativeExecute](VectorQuery.md#nativeexecute)
+- [nprobes](VectorQuery.md#nprobes)
+- [postfilter](VectorQuery.md#postfilter)
+- [refineFactor](VectorQuery.md#refinefactor)
+- [select](VectorQuery.md#select)
+- [toArray](VectorQuery.md#toarray)
+- [toArrow](VectorQuery.md#toarrow)
+- [where](VectorQuery.md#where)
+
+## Constructors
+
+### constructor
+
+• **new VectorQuery**(`inner`): [`VectorQuery`](VectorQuery.md)
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `inner` | `VectorQuery` |
+
+#### Returns
+
+[`VectorQuery`](VectorQuery.md)
+
+#### Overrides
+
+[QueryBase](QueryBase.md).[constructor](QueryBase.md#constructor)
+
+#### Defined in
+
+[query.ts:189](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L189)
+
+## Properties
+
+### inner
+
+• `Protected` **inner**: `VectorQuery`
+
+#### Inherited from
+
+[QueryBase](QueryBase.md).[inner](QueryBase.md#inner)
+
+#### Defined in
+
+[query.ts:59](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L59)
+
+## Methods
+
+### [asyncIterator]
+
+▸ **[asyncIterator]**(): `AsyncIterator`\<`RecordBatch`\<`any`\>, `any`, `undefined`\>
+
+#### Returns
+
+`AsyncIterator`\<`RecordBatch`\<`any`\>, `any`, `undefined`\>
+
+#### Inherited from
+
+[QueryBase](QueryBase.md).[[asyncIterator]](QueryBase.md#[asynciterator])
+
+#### Defined in
+
+[query.ts:154](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L154)
+
+___
+
+### bypassVectorIndex
+
+▸ **bypassVectorIndex**(): [`VectorQuery`](VectorQuery.md)
+
+If this is called then any vector index is skipped
+
+An exhaustive (flat) search will be performed.  The query vector will
+be compared to every vector in the table.  At high scales this can be
+expensive.  However, this is often still useful.  For example, skipping
+the vector index can give you ground truth results which you can use to
+calculate your recall to select an appropriate value for nprobes.
+
+#### Returns
+
+[`VectorQuery`](VectorQuery.md)
+
+#### Defined in
+
+[query.ts:321](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L321)
+
+___
+
+### column
+
+▸ **column**(`column`): [`VectorQuery`](VectorQuery.md)
+
+Set the vector column to query
+
+This controls which column is compared to the query vector supplied in
+the call to
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `column` | `string` |
+
+#### Returns
+
+[`VectorQuery`](VectorQuery.md)
+
+**`See`**
+
+[Query#nearestTo](Query.md#nearestto)
+
+This parameter must be specified if the table has more than one column
+whose data type is a fixed-size-list of floats.
+
+#### Defined in
+
+[query.ts:229](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L229)
+
+___
+
+### distanceType
+
+▸ **distanceType**(`distanceType`): [`VectorQuery`](VectorQuery.md)
+
+Set the distance metric to use
+
+When performing a vector search we try and find the "nearest" vectors according
+to some kind of distance metric.  This parameter controls which distance metric to
+use.  See
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `distanceType` | `string` |
+
+#### Returns
+
+[`VectorQuery`](VectorQuery.md)
+
+**`See`**
+
+[IvfPqOptions.distanceType](../interfaces/IvfPqOptions.md#distancetype) for more details on the different
+distance metrics available.
+
+Note: if there is a vector index then the distance type used MUST match the distance
+type used to train the vector index.  If this is not done then the results will be
+invalid.
+
+By default "l2" is used.
+
+#### Defined in
+
+[query.ts:248](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L248)
+
+___
+
+### execute
+
+▸ **execute**(): [`RecordBatchIterator`](RecordBatchIterator.md)
+
+Execute the query and return the results as an
+
+#### Returns
+
+[`RecordBatchIterator`](RecordBatchIterator.md)
+
+**`See`**
+
+ - AsyncIterator
+of
+ - RecordBatch.
+
+By default, LanceDb will use many threads to calculate results and, when
+the result set is large, multiple batches will be processed at one time.
+This readahead is limited however and backpressure will be applied if this
+stream is consumed slowly (this constrains the maximum memory used by a
+single query)
+
+#### Inherited from
+
+[QueryBase](QueryBase.md).[execute](QueryBase.md#execute)
+
+#### Defined in
+
+[query.ts:149](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L149)
+
+___
+
+### limit
+
+▸ **limit**(`limit`): [`VectorQuery`](VectorQuery.md)
+
+Set the maximum number of results to return.
+
+By default, a plain search has no limit.  If this method is not
+called then every valid row from the table will be returned.
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `limit` | `number` |
+
+#### Returns
+
+[`VectorQuery`](VectorQuery.md)
+
+#### Inherited from
+
+[QueryBase](QueryBase.md).[limit](QueryBase.md#limit)
+
+#### Defined in
+
+[query.ts:129](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L129)
+
+___
+
+### nativeExecute
+
+▸ **nativeExecute**(): `Promise`\<`RecordBatchIterator`\>
+
+#### Returns
+
+`Promise`\<`RecordBatchIterator`\>
+
+#### Inherited from
+
+[QueryBase](QueryBase.md).[nativeExecute](QueryBase.md#nativeexecute)
+
+#### Defined in
+
+[query.ts:134](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L134)
+
+___
+
+### nprobes
+
+▸ **nprobes**(`nprobes`): [`VectorQuery`](VectorQuery.md)
+
+Set the number of partitions to search (probe)
+
+This argument is only used when the vector column has an IVF PQ index.
+If there is no index then this value is ignored.
+
+The IVF stage of IVF PQ divides the input into partitions (clusters) of
+related values.
+
+The partition whose centroids are closest to the query vector will be
+exhaustiely searched to find matches.  This parameter controls how many
+partitions should be searched.
+
+Increasing this value will increase the recall of your query but will
+also increase the latency of your query.  The default value is 20.  This
+default is good for many cases but the best value to use will depend on
+your data and the recall that you need to achieve.
+
+For best results we recommend tuning this parameter with a benchmark against
+your actual data to find the smallest possible value that will still give
+you the desired recall.
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `nprobes` | `number` |
+
+#### Returns
+
+[`VectorQuery`](VectorQuery.md)
+
+#### Defined in
+
+[query.ts:215](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L215)
+
+___
+
+### postfilter
+
+▸ **postfilter**(): [`VectorQuery`](VectorQuery.md)
+
+If this is called then filtering will happen after the vector search instead of
+before.
+
+By default filtering will be performed before the vector search.  This is how
+filtering is typically understood to work.  This prefilter step does add some
+additional latency.  Creating a scalar index on the filter column(s) can
+often improve this latency.  However, sometimes a filter is too complex or scalar
+indices cannot be applied to the column.  In these cases postfiltering can be
+used instead of prefiltering to improve latency.
+
+Post filtering applies the filter to the results of the vector search.  This means
+we only run the filter on a much smaller set of data.  However, it can cause the
+query to return fewer than `limit` results (or even no results) if none of the nearest
+results match the filter.
+
+Post filtering happens during the "refine stage" (described in more detail in
+
+#### Returns
+
+[`VectorQuery`](VectorQuery.md)
+
+**`See`**
+
+[VectorQuery#refineFactor](VectorQuery.md#refinefactor)).  This means that setting a higher refine
+factor can often help restore some of the results lost by post filtering.
+
+#### Defined in
+
+[query.ts:307](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L307)
+
+___
+
+### refineFactor
+
+▸ **refineFactor**(`refineFactor`): [`VectorQuery`](VectorQuery.md)
+
+A multiplier to control how many additional rows are taken during the refine step
+
+This argument is only used when the vector column has an IVF PQ index.
+If there is no index then this value is ignored.
+
+An IVF PQ index stores compressed (quantized) values.  They query vector is compared
+against these values and, since they are compressed, the comparison is inaccurate.
+
+This parameter can be used to refine the results.  It can improve both improve recall
+and correct the ordering of the nearest results.
+
+To refine results LanceDb will first perform an ANN search to find the nearest
+`limit` * `refine_factor` results.  In other words, if `refine_factor` is 3 and
+`limit` is the default (10) then the first 30 results will be selected.  LanceDb
+then fetches the full, uncompressed, values for these 30 results.  The results are
+then reordered by the true distance and only the nearest 10 are kept.
+
+Note: there is a difference between calling this method with a value of 1 and never
+calling this method at all.  Calling this method with any value will have an impact
+on your search latency.  When you call this method with a `refine_factor` of 1 then
+LanceDb still needs to fetch the full, uncompressed, values so that it can potentially
+reorder the results.
+
+Note: if this method is NOT called then the distances returned in the _distance column
+will be approximate distances based on the comparison of the quantized query vector
+and the quantized result vectors.  This can be considerably different than the true
+distance between the query vector and the actual uncompressed vector.
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `refineFactor` | `number` |
+
+#### Returns
+
+[`VectorQuery`](VectorQuery.md)
+
+#### Defined in
+
+[query.ts:282](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L282)
+
+___
+
+### select
+
+▸ **select**(`columns`): [`VectorQuery`](VectorQuery.md)
+
+Return only the specified columns.
+
+By default a query will return all columns from the table.  However, this can have
+a very significant impact on latency.  LanceDb stores data in a columnar fashion.  This
+means we can finely tune our I/O to select exactly the columns we need.
+
+As a best practice you should always limit queries to the columns that you need.  If you
+pass in an array of column names then only those columns will be returned.
+
+You can also use this method to create new "dynamic" columns based on your existing columns.
+For example, you may not care about "a" or "b" but instead simply want "a + b".  This is often
+seen in the SELECT clause of an SQL query (e.g. `SELECT a+b FROM my_table`).
+
+To create dynamic columns you can pass in a Map<string, string>.  A column will be returned
+for each entry in the map.  The key provides the name of the column.  The value is
+an SQL string used to specify how the column is calculated.
+
+For example, an SQL query might state `SELECT a + b AS combined, c`.  The equivalent
+input to this method would be:
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `columns` | `string`[] \| `Record`\<`string`, `string`\> \| `Map`\<`string`, `string`\> |
+
+#### Returns
+
+[`VectorQuery`](VectorQuery.md)
+
+**`Example`**
+
+```ts
+new Map([["combined", "a + b"], ["c", "c"]])
+
+Columns will always be returned in the order given, even if that order is different than
+the order used when adding the data.
+
+Note that you can pass in a `Record<string, string>` (e.g. an object literal). This method
+uses `Object.entries` which should preserve the insertion order of the object.  However,
+object insertion order is easy to get wrong and `Map` is more foolproof.
+```
+
+#### Inherited from
+
+[QueryBase](QueryBase.md).[select](QueryBase.md#select)
+
+#### Defined in
+
+[query.ts:108](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L108)
+
+___
+
+### toArray
+
+▸ **toArray**(): `Promise`\<`unknown`[]\>
+
+Collect the results as an array of objects.
+
+#### Returns
+
+`Promise`\<`unknown`[]\>
+
+#### Inherited from
+
+[QueryBase](QueryBase.md).[toArray](QueryBase.md#toarray)
+
+#### Defined in
+
+[query.ts:169](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L169)
+
+___
+
+### toArrow
+
+▸ **toArrow**(): `Promise`\<`Table`\<`any`\>\>
+
+Collect the results as an Arrow
+
+#### Returns
+
+`Promise`\<`Table`\<`any`\>\>
+
+**`See`**
+
+ArrowTable.
+
+#### Inherited from
+
+[QueryBase](QueryBase.md).[toArrow](QueryBase.md#toarrow)
+
+#### Defined in
+
+[query.ts:160](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L160)
+
+___
+
+### where
+
+▸ **where**(`predicate`): [`VectorQuery`](VectorQuery.md)
+
+A filter statement to be applied to this query.
+
+The filter should be supplied as an SQL query string.  For example:
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `predicate` | `string` |
+
+#### Returns
+
+[`VectorQuery`](VectorQuery.md)
+
+**`Example`**
+
+```ts
+x > 10
+y > 0 AND y < 100
+x > 5 OR y = 'test'
+
+Filtering performance can often be improved by creating a scalar index
+on the filter column(s).
+```
+
+#### Inherited from
+
+[QueryBase](QueryBase.md).[where](QueryBase.md#where)
+
+#### Defined in
+
+[query.ts:73](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L73)

docs/src/js/classes/embedding.OpenAIEmbeddingFunction.md

@@ -0,0 +1,111 @@
+[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / [embedding](../modules/embedding.md) / OpenAIEmbeddingFunction
+
+# Class: OpenAIEmbeddingFunction
+
+[embedding](../modules/embedding.md).OpenAIEmbeddingFunction
+
+An embedding function that automatically creates vector representation for a given column.
+
+## Implements
+
+- [`EmbeddingFunction`](../interfaces/embedding.EmbeddingFunction.md)\<`string`\>
+
+## Table of contents
+
+### Constructors
+
+- [constructor](embedding.OpenAIEmbeddingFunction.md#constructor)
+
+### Properties
+
+- [\_modelName](embedding.OpenAIEmbeddingFunction.md#_modelname)
+- [\_openai](embedding.OpenAIEmbeddingFunction.md#_openai)
+- [sourceColumn](embedding.OpenAIEmbeddingFunction.md#sourcecolumn)
+
+### Methods
+
+- [embed](embedding.OpenAIEmbeddingFunction.md#embed)
+
+## Constructors
+
+### constructor
+
+• **new OpenAIEmbeddingFunction**(`sourceColumn`, `openAIKey`, `modelName?`): [`OpenAIEmbeddingFunction`](embedding.OpenAIEmbeddingFunction.md)
+
+#### Parameters
+
+| Name | Type | Default value |
+| :------ | :------ | :------ |
+| `sourceColumn` | `string` | `undefined` |
+| `openAIKey` | `string` | `undefined` |
+| `modelName` | `string` | `"text-embedding-ada-002"` |
+
+#### Returns
+
+[`OpenAIEmbeddingFunction`](embedding.OpenAIEmbeddingFunction.md)
+
+#### Defined in
+
+[embedding/openai.ts:22](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/embedding/openai.ts#L22)
+
+## Properties
+
+### \_modelName
+
+• `Private` `Readonly` **\_modelName**: `string`
+
+#### Defined in
+
+[embedding/openai.ts:20](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/embedding/openai.ts#L20)
+
+___
+
+### \_openai
+
+• `Private` `Readonly` **\_openai**: `OpenAI`
+
+#### Defined in
+
+[embedding/openai.ts:19](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/embedding/openai.ts#L19)
+
+___
+
+### sourceColumn
+
+• **sourceColumn**: `string`
+
+The name of the column that will be used as input for the Embedding Function.
+
+#### Implementation of
+
+[EmbeddingFunction](../interfaces/embedding.EmbeddingFunction.md).[sourceColumn](../interfaces/embedding.EmbeddingFunction.md#sourcecolumn)
+
+#### Defined in
+
+[embedding/openai.ts:61](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/embedding/openai.ts#L61)
+
+## Methods
+
+### embed
+
+▸ **embed**(`data`): `Promise`\<`number`[][]\>
+
+Creates a vector representation for the given values.
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `data` | `string`[] |
+
+#### Returns
+
+`Promise`\<`number`[][]\>
+
+#### Implementation of
+
+[EmbeddingFunction](../interfaces/embedding.EmbeddingFunction.md).[embed](../interfaces/embedding.EmbeddingFunction.md#embed)
+
+#### Defined in
+
+[embedding/openai.ts:48](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/embedding/openai.ts#L48)

docs/src/js/enums/WriteMode.md

@@ -0,0 +1,43 @@
+[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / WriteMode
+
+# Enumeration: WriteMode
+
+Write mode for writing a table.
+
+## Table of contents
+
+### Enumeration Members
+
+- [Append](WriteMode.md#append)
+- [Create](WriteMode.md#create)
+- [Overwrite](WriteMode.md#overwrite)
+
+## Enumeration Members
+
+### Append
+
+• **Append** = ``"Append"``
+
+#### Defined in
+
+native.d.ts:69
+
+___
+
+### Create
+
+• **Create** = ``"Create"``
+
+#### Defined in
+
+native.d.ts:68
+
+___
+
+### Overwrite
+
+• **Overwrite** = ``"Overwrite"``
+
+#### Defined in
+
+native.d.ts:70

docs/src/js/interfaces/AddColumnsSql.md

@@ -0,0 +1,37 @@
+[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / AddColumnsSql
+
+# Interface: AddColumnsSql
+
+A definition of a new column to add to a table.
+
+## Table of contents
+
+### Properties
+
+- [name](AddColumnsSql.md#name)
+- [valueSql](AddColumnsSql.md#valuesql)
+
+## Properties
+
+### name
+
+• **name**: `string`
+
+The name of the new column.
+
+#### Defined in
+
+native.d.ts:43
+
+___
+
+### valueSql
+
+• **valueSql**: `string`
+
+The values to populate the new column with, as a SQL expression.
+The expression can reference other columns in the table.
+
+#### Defined in
+
+native.d.ts:48

docs/src/js/interfaces/AddDataOptions.md

@@ -0,0 +1,25 @@
+[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / AddDataOptions
+
+# Interface: AddDataOptions
+
+Options for adding data to a table.
+
+## Table of contents
+
+### Properties
+
+- [mode](AddDataOptions.md#mode)
+
+## Properties
+
+### mode
+
+• **mode**: ``"append"`` \| ``"overwrite"``
+
+If "append" (the default) then the new data will be added to the table
+
+If "overwrite" then the new data will replace the existing data in the table.
+
+#### Defined in
+
+[table.ts:36](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L36)

docs/src/js/interfaces/ColumnAlteration.md

@@ -0,0 +1,56 @@
+[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / ColumnAlteration
+
+# Interface: ColumnAlteration
+
+A definition of a column alteration. The alteration changes the column at
+`path` to have the new name `name`, to be nullable if `nullable` is true,
+and to have the data type `data_type`. At least one of `rename` or `nullable`
+must be provided.
+
+## Table of contents
+
+### Properties
+
+- [nullable](ColumnAlteration.md#nullable)
+- [path](ColumnAlteration.md#path)
+- [rename](ColumnAlteration.md#rename)
+
+## Properties
+
+### nullable
+
+• `Optional` **nullable**: `boolean`
+
+Set the new nullability. Note that a nullable column cannot be made non-nullable.
+
+#### Defined in
+
+native.d.ts:38
+
+___
+
+### path
+
+• **path**: `string`
+
+The path to the column to alter. This is a dot-separated path to the column.
+If it is a top-level column then it is just the name of the column. If it is
+a nested column then it is the path to the column, e.g. "a.b.c" for a column
+`c` nested inside a column `b` nested inside a column `a`.
+
+#### Defined in
+
+native.d.ts:31
+
+___
+
+### rename
+
+• `Optional` **rename**: `string`
+
+The new name of the column. If not provided then the name will not be changed.
+This must be distinct from the names of all other columns in the table.
+
+#### Defined in
+
+native.d.ts:36

docs/src/js/interfaces/ConnectionOptions.md

@@ -0,0 +1,51 @@
+[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / ConnectionOptions
+
+# Interface: ConnectionOptions
+
+## Table of contents
+
+### Properties
+
+- [apiKey](ConnectionOptions.md#apikey)
+- [hostOverride](ConnectionOptions.md#hostoverride)
+- [readConsistencyInterval](ConnectionOptions.md#readconsistencyinterval)
+
+## Properties
+
+### apiKey
+
+• `Optional` **apiKey**: `string`
+
+#### Defined in
+
+native.d.ts:51
+
+___
+
+### hostOverride
+
+• `Optional` **hostOverride**: `string`
+
+#### Defined in
+
+native.d.ts:52
+
+___
+
+### readConsistencyInterval
+
+• `Optional` **readConsistencyInterval**: `number`
+
+(For LanceDB OSS only): The interval, in seconds, at which to check for
+updates to the table from other processes. If None, then consistency is not
+checked. For performance reasons, this is the default. For strong
+consistency, set this to zero seconds. Then every read will check for
+updates from other processes. As a compromise, you can set this to a
+non-zero value for eventual consistency. If more than that interval
+has passed since the last check, then the table will be checked for updates.
+Note: this consistency only applies to read operations. Write operations are
+always consistent.
+
+#### Defined in
+
+native.d.ts:64

docs/src/js/interfaces/CreateTableOptions.md

@@ -0,0 +1,41 @@
+[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / CreateTableOptions
+
+# Interface: CreateTableOptions
+
+## Table of contents
+
+### Properties
+
+- [existOk](CreateTableOptions.md#existok)
+- [mode](CreateTableOptions.md#mode)
+
+## Properties
+
+### existOk
+
+• **existOk**: `boolean`
+
+If this is true and the table already exists and the mode is "create"
+then no error will be raised.
+
+#### Defined in
+
+[connection.ts:35](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/connection.ts#L35)
+
+___
+
+### mode
+
+• **mode**: ``"overwrite"`` \| ``"create"``
+
+The mode to use when creating the table.
+
+If this is set to "create" and the table already exists then either
+an error will be thrown or, if existOk is true, then nothing will
+happen.  Any provided data will be ignored.
+
+If this is set to "overwrite" then any existing table will be replaced.
+
+#### Defined in
+
+[connection.ts:30](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/connection.ts#L30)

docs/src/js/interfaces/ExecutableQuery.md

@@ -0,0 +1,7 @@
+[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / ExecutableQuery
+
+# Interface: ExecutableQuery
+
+An interface for a query that can be executed
+
+Supported by all query types

docs/src/js/interfaces/IndexConfig.md

@@ -0,0 +1,39 @@
+[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / IndexConfig
+
+# Interface: IndexConfig
+
+A description of an index currently configured on a column
+
+## Table of contents
+
+### Properties
+
+- [columns](IndexConfig.md#columns)
+- [indexType](IndexConfig.md#indextype)
+
+## Properties
+
+### columns
+
+• **columns**: `string`[]
+
+The columns in the index
+
+Currently this is always an array of size 1.  In the future there may
+be more columns to represent composite indices.
+
+#### Defined in
+
+native.d.ts:16
+
+___
+
+### indexType
+
+• **indexType**: `string`
+
+The type of the index
+
+#### Defined in
+
+native.d.ts:9

docs/src/js/interfaces/IndexOptions.md

@@ -0,0 +1,48 @@
+[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / IndexOptions
+
+# Interface: IndexOptions
+
+## Table of contents
+
+### Properties
+
+- [config](IndexOptions.md#config)
+- [replace](IndexOptions.md#replace)
+
+## Properties
+
+### config
+
+• `Optional` **config**: [`Index`](../classes/Index.md)
+
+Advanced index configuration
+
+This option allows you to specify a specfic index to create and also
+allows you to pass in configuration for training the index.
+
+See the static methods on Index for details on the various index types.
+
+If this is not supplied then column data type(s) and column statistics
+will be used to determine the most useful kind of index to create.
+
+#### Defined in
+
+[indices.ts:192](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/indices.ts#L192)
+
+___
+
+### replace
+
+• `Optional` **replace**: `boolean`
+
+Whether to replace the existing index
+
+If this is false, and another index already exists on the same columns
+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
+
+#### Defined in
+
+[indices.ts:202](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/indices.ts#L202)

docs/src/js/interfaces/IvfPqOptions.md

@@ -0,0 +1,144 @@
+[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / IvfPqOptions
+
+# Interface: IvfPqOptions
+
+Options to create an `IVF_PQ` index
+
+## Table of contents
+
+### Properties
+
+- [distanceType](IvfPqOptions.md#distancetype)
+- [maxIterations](IvfPqOptions.md#maxiterations)
+- [numPartitions](IvfPqOptions.md#numpartitions)
+- [numSubVectors](IvfPqOptions.md#numsubvectors)
+- [sampleRate](IvfPqOptions.md#samplerate)
+
+## Properties
+
+### distanceType
+
+• `Optional` **distanceType**: ``"l2"`` \| ``"cosine"`` \| ``"dot"``
+
+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) and to calculate a subvector's code during quantization.
+
+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.
+
+#### Defined in
+
+[indices.ts:83](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/indices.ts#L83)
+
+___
+
+### maxIterations
+
+• `Optional` **maxIterations**: `number`
+
+Max iteration to train IVF kmeans.
+
+When training an IVF PQ 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.
+
+#### Defined in
+
+[indices.ts:96](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/indices.ts#L96)
+
+___
+
+### numPartitions
+
+• `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.
+
+#### Defined in
+
+[indices.ts:32](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/indices.ts#L32)
+
+___
+
+### numSubVectors
+
+• `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.
+
+#### Defined in
+
+[indices.ts:48](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/indices.ts#L48)
+
+___
+
+### sampleRate
+
+• `Optional` **sampleRate**: `number`
+
+The number of vectors, per partition, to sample when training IVF kmeans.
+
+When an IVF PQ 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.
+
+#### Defined in
+
+[indices.ts:113](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/indices.ts#L113)

docs/src/js/interfaces/TableNamesOptions.md

@@ -0,0 +1,38 @@
+[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / TableNamesOptions
+
+# Interface: TableNamesOptions
+
+## Table of contents
+
+### Properties
+
+- [limit](TableNamesOptions.md#limit)
+- [startAfter](TableNamesOptions.md#startafter)
+
+## Properties
+
+### limit
+
+• `Optional` **limit**: `number`
+
+An optional limit to the number of results to return.
+
+#### Defined in
+
+[connection.ts:48](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/connection.ts#L48)
+
+___
+
+### startAfter
+
+• `Optional` **startAfter**: `string`
+
+If present, only return names that come lexicographically after the
+supplied value.
+
+This can be combined with limit to implement pagination by setting this to
+the last table name from the previous page.
+
+#### Defined in
+
+[connection.ts:46](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/connection.ts#L46)

docs/src/js/interfaces/UpdateOptions.md

@@ -0,0 +1,28 @@
+[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / UpdateOptions
+
+# Interface: UpdateOptions
+
+## Table of contents
+
+### Properties
+
+- [where](UpdateOptions.md#where)
+
+## Properties
+
+### where
+
+• **where**: `string`
+
+A filter that limits the scope of the update.
+
+This should be an SQL filter expression.
+
+Only rows that satisfy the expression will be updated.
+
+For example, this could be 'my_col == 0' to replace all instances
+of 0 in a column with some other default value.
+
+#### Defined in
+
+[table.ts:50](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L50)

docs/src/js/interfaces/WriteOptions.md

@@ -0,0 +1,21 @@
+[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / WriteOptions
+
+# Interface: WriteOptions
+
+Write options when creating a Table.
+
+## Table of contents
+
+### Properties
+
+- [mode](WriteOptions.md#mode)
+
+## Properties
+
+### mode
+
+• `Optional` **mode**: [`WriteMode`](../enums/WriteMode.md)
+
+#### Defined in
+
+native.d.ts:74

docs/src/js/interfaces/embedding.EmbeddingFunction.md

@@ -0,0 +1,129 @@
+[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / [embedding](../modules/embedding.md) / EmbeddingFunction
+
+# Interface: EmbeddingFunction\<T\>
+
+[embedding](../modules/embedding.md).EmbeddingFunction
+
+An embedding function that automatically creates vector representation for a given column.
+
+## Type parameters
+
+| Name |
+| :------ |
+| `T` |
+
+## Implemented by
+
+- [`OpenAIEmbeddingFunction`](../classes/embedding.OpenAIEmbeddingFunction.md)
+
+## Table of contents
+
+### Properties
+
+- [destColumn](embedding.EmbeddingFunction.md#destcolumn)
+- [embed](embedding.EmbeddingFunction.md#embed)
+- [embeddingDataType](embedding.EmbeddingFunction.md#embeddingdatatype)
+- [embeddingDimension](embedding.EmbeddingFunction.md#embeddingdimension)
+- [excludeSource](embedding.EmbeddingFunction.md#excludesource)
+- [sourceColumn](embedding.EmbeddingFunction.md#sourcecolumn)
+
+## Properties
+
+### destColumn
+
+• `Optional` **destColumn**: `string`
+
+The name of the column that will contain the embedding
+
+By default this is "vector"
+
+#### Defined in
+
+[embedding/embedding_function.ts:49](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/embedding/embedding_function.ts#L49)
+
+___
+
+### embed
+
+• **embed**: (`data`: `T`[]) => `Promise`\<`number`[][]\>
+
+Creates a vector representation for the given values.
+
+#### Type declaration
+
+▸ (`data`): `Promise`\<`number`[][]\>
+
+Creates a vector representation for the given values.
+
+##### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `data` | `T`[] |
+
+##### Returns
+
+`Promise`\<`number`[][]\>
+
+#### Defined in
+
+[embedding/embedding_function.ts:62](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/embedding/embedding_function.ts#L62)
+
+___
+
+### embeddingDataType
+
+• `Optional` **embeddingDataType**: `Float`\<`Floats`\>
+
+The data type of the embedding
+
+The embedding function should return `number`.  This will be converted into
+an Arrow float array.  By default this will be Float32 but this property can
+be used to control the conversion.
+
+#### Defined in
+
+[embedding/embedding_function.ts:33](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/embedding/embedding_function.ts#L33)
+
+___
+
+### embeddingDimension
+
+• `Optional` **embeddingDimension**: `number`
+
+The dimension of the embedding
+
+This is optional, normally this can be determined by looking at the results of
+`embed`.  If this is not specified, and there is an attempt to apply the embedding
+to an empty table, then that process will fail.
+
+#### Defined in
+
+[embedding/embedding_function.ts:42](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/embedding/embedding_function.ts#L42)
+
+___
+
+### excludeSource
+
+• `Optional` **excludeSource**: `boolean`
+
+Should the source column be excluded from the resulting table
+
+By default the source column is included.  Set this to true and
+only the embedding will be stored.
+
+#### Defined in
+
+[embedding/embedding_function.ts:57](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/embedding/embedding_function.ts#L57)
+
+___
+
+### sourceColumn
+
+• **sourceColumn**: `string`
+
+The name of the column that will be used as input for the Embedding Function.
+
+#### Defined in
+
+[embedding/embedding_function.ts:24](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/embedding/embedding_function.ts#L24)

docs/src/js/modules.md

@@ -0,0 +1,208 @@
+[@lancedb/lancedb](README.md) / Exports
+
+# @lancedb/lancedb
+
+## Table of contents
+
+### Namespaces
+
+- [embedding](modules/embedding.md)
+
+### Enumerations
+
+- [WriteMode](enums/WriteMode.md)
+
+### Classes
+
+- [Connection](classes/Connection.md)
+- [Index](classes/Index.md)
+- [MakeArrowTableOptions](classes/MakeArrowTableOptions.md)
+- [Query](classes/Query.md)
+- [QueryBase](classes/QueryBase.md)
+- [RecordBatchIterator](classes/RecordBatchIterator.md)
+- [Table](classes/Table.md)
+- [VectorColumnOptions](classes/VectorColumnOptions.md)
+- [VectorQuery](classes/VectorQuery.md)
+
+### Interfaces
+
+- [AddColumnsSql](interfaces/AddColumnsSql.md)
+- [AddDataOptions](interfaces/AddDataOptions.md)
+- [ColumnAlteration](interfaces/ColumnAlteration.md)
+- [ConnectionOptions](interfaces/ConnectionOptions.md)
+- [CreateTableOptions](interfaces/CreateTableOptions.md)
+- [ExecutableQuery](interfaces/ExecutableQuery.md)
+- [IndexConfig](interfaces/IndexConfig.md)
+- [IndexOptions](interfaces/IndexOptions.md)
+- [IvfPqOptions](interfaces/IvfPqOptions.md)
+- [TableNamesOptions](interfaces/TableNamesOptions.md)
+- [UpdateOptions](interfaces/UpdateOptions.md)
+- [WriteOptions](interfaces/WriteOptions.md)
+
+### Type Aliases
+
+- [Data](modules.md#data)
+
+### Functions
+
+- [connect](modules.md#connect)
+- [makeArrowTable](modules.md#makearrowtable)
+
+## Type Aliases
+
+### Data
+
+Ƭ **Data**: `Record`\<`string`, `unknown`\>[] \| `ArrowTable`
+
+Data type accepted by NodeJS SDK
+
+#### Defined in
+
+[arrow.ts:40](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/arrow.ts#L40)
+
+## Functions
+
+### connect
+
+▸ **connect**(`uri`, `opts?`): `Promise`\<[`Connection`](classes/Connection.md)\>
+
+Connect to a LanceDB instance at the given URI.
+
+Accpeted formats:
+
+- `/path/to/database` - local database
+- `s3://bucket/path/to/database` or `gs://bucket/path/to/database` - database on cloud storage
+- `db://host:port` - remote database (LanceDB cloud)
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `uri` | `string` | The uri of the database. If the database uri starts with `db://` then it connects to a remote database. |
+| `opts?` | `Partial`\<[`ConnectionOptions`](interfaces/ConnectionOptions.md)\> | - |
+
+#### Returns
+
+`Promise`\<[`Connection`](classes/Connection.md)\>
+
+**`See`**
+
+[ConnectionOptions](interfaces/ConnectionOptions.md) for more details on the URI format.
+
+#### Defined in
+
+[index.ts:62](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/index.ts#L62)
+
+___
+
+### makeArrowTable
+
+▸ **makeArrowTable**(`data`, `options?`): `ArrowTable`
+
+An enhanced version of the makeTable function from Apache Arrow
+that supports nested fields and embeddings columns.
+
+(typically you do not need to call this function.  It will be called automatically
+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.
+
+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 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
+rules are as follows:
+
+ - boolean => Bool
+ - number => Float64
+ - String => Utf8
+ - Buffer => Binary
+ - Record<String, any> => Struct
+ - Array<any> => List
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `data` | `Record`\<`string`, `unknown`\>[] |
+| `options?` | `Partial`\<[`MakeArrowTableOptions`](classes/MakeArrowTableOptions.md)\> |
+
+#### Returns
+
+`ArrowTable`
+
+**`Example`**
+
+import { fromTableToBuffer, makeArrowTable } from "../arrow";
+import { Field, FixedSizeList, Float16, Float32, Int32, Schema } from "apache-arrow";
+
+const schema = new Schema([
+  new Field("a", new Int32()),
+  new Field("b", new Float32()),
+  new Field("c", new FixedSizeList(3, new Field("item", new Float16()))),
+ ]);
+ const table = makeArrowTable([
+   { a: 1, b: 2, c: [1, 2, 3] },
+   { a: 4, b: 5, c: [4, 5, 6] },
+   { a: 7, b: 8, c: [7, 8, 9] },
+ ], { schema });
+```
+
+By default it assumes that the column named `vector` is a vector column
+and it will be converted into a fixed size list array of type float32.
+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()),
+   new Field(
+     "vector",
+     new FixedSizeList(3, new Field("item", new Float32()))
+   ),
+ ]);
+ const table = makeArrowTable([
+   { a: 1, b: 2, vector: [1, 2, 3] },
+   { a: 4, b: 5, vector: [4, 5, 6] },
+   { a: 7, b: 8, vector: [7, 8, 9] },
+ ]);
+ assert.deepEqual(table.schema, schema);
+```
+
+You can specify the vector column types and names using the options as well
+
+```typescript
+
+const schema = new Schema([
+   new Field('a', new Float64()),
+   new Field('b', new Float64()),
+   new Field('vec1', new FixedSizeList(3, new Field('item', new Float16()))),
+   new Field('vec2', new FixedSizeList(3, new Field('item', new Float16())))
+ ]);
+const table = makeArrowTable([
+   { a: 1, b: 2, vec1: [1, 2, 3], vec2: [2, 4, 6] },
+   { a: 4, b: 5, vec1: [4, 5, 6], vec2: [8, 10, 12] },
+   { a: 7, b: 8, vec1: [7, 8, 9], vec2: [14, 16, 18] }
+ ], {
+   vectorColumns: {
+     vec1: { type: new Float16() },
+     vec2: { type: new Float16() }
+   }
+ }
+assert.deepEqual(table.schema, schema)
+```
+
+#### Defined in
+
+[arrow.ts:197](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/arrow.ts#L197)

docs/src/js/modules/embedding.md

@@ -0,0 +1,45 @@
+[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / embedding
+
+# Namespace: embedding
+
+## Table of contents
+
+### Classes
+
+- [OpenAIEmbeddingFunction](../classes/embedding.OpenAIEmbeddingFunction.md)
+
+### Interfaces
+
+- [EmbeddingFunction](../interfaces/embedding.EmbeddingFunction.md)
+
+### Functions
+
+- [isEmbeddingFunction](embedding.md#isembeddingfunction)
+
+## Functions
+
+### isEmbeddingFunction
+
+▸ **isEmbeddingFunction**\<`T`\>(`value`): value is EmbeddingFunction\<T\>
+
+Test if the input seems to be an embedding function
+
+#### Type parameters
+
+| Name |
+| :------ |
+| `T` |
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `value` | `unknown` |
+
+#### Returns
+
+value is EmbeddingFunction\<T\>
+
+#### Defined in
+
+[embedding/embedding_function.ts:66](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/embedding/embedding_function.ts#L66)

docs/src/migration.md

@@ -0,0 +1,76 @@
+# Rust-backed Client Migration Guide
+
+In an effort to ensure all clients have the same set of capabilities we have begun migrating the
+python and node clients onto a common Rust base library. In python, this new client is part of
+the same lancedb package, exposed as an asynchronous client. Once the asynchronous client has
+reached full functionality we will begin migrating the synchronous library to be a thin wrapper
+around the asynchronous client.
+
+This guide describes the differences between the two APIs and will hopefully assist users
+that would like to migrate to the new API.
+
+## Closeable Connections
+
+The Connection now has a `close` method. You can call this when
+you are done with the connection to eagerly free resources. Currently
+this is limited to freeing/closing the HTTP connection for remote
+connections. In the future we may add caching or other resources to
+native connections so this is probably a good practice even if you
+aren't using remote connections.
+
+In addition, the connection can be used as a context manager which may
+be a more convenient way to ensure the connection is closed.
+
+```python
+import lancedb
+
+async def my_async_fn():
+    with await lancedb.connect_async("my_uri") as db:
+        print(await db.table_names())
+```
+
+It is not mandatory to call the `close` method. If you do not call it
+then the connection will be closed when the object is garbage collected.
+
+## Closeable Table
+
+The Table now also has a `close` method, similar to the connection. This
+can be used to eagerly free the cache used by a Table object. Similar to
+the connection, it can be used as a context manager and it is not mandatory
+to call the `close` method.
+
+### Changes to Table APIs
+
+- Previously `Table.schema` was a property. Now it is an async method.
+- The method `Table.__len__` was removed and `len(table)` will no longer
+  work. Use `Table.count_rows` instead.
+
+### Creating Indices
+
+The `Table.create_index` method is now used for creating both vector indices
+and scalar indices. It currently requires a column name to be specified (the
+column to index). Vector index defaults are now smarter and scale better with
+the size of the data.
+
+To specify index configuration details you will need to specify which kind of
+index you are using.
+
+### Querying
+
+The `Table.search` method has been renamed to `AsyncTable.vector_search` for
+clarity.
+
+## Features not yet supported
+
+The following features are not yet supported by the asynchronous API. However,
+we plan to support them soon.
+
+- You cannot specify an embedding function when creating or opening a table.
+  You must calculate embeddings yourself if using the asynchronous API
+- The merge insert operation is not supported in the asynchronous API
+- Cleanup / compact / optimize indices are not supported in the asynchronous API
+- add / alter columns is not supported in the asynchronous API
+- The asynchronous API does not yet support any full text search or reranking
+  search
+- Remote connections to LanceDb Cloud are not yet supported.
+- The method Table.head is not yet supported.

docs/src/python/python.md

@@ -8,17 +8,20 @@ This section contains the API reference for the OSS Python API.
 pip install lancedb
 ```
 
-## Connection
+The following methods describe the synchronous API client. There
+is also an [asynchronous API client](#connections-asynchronous).
+
+## Connections (Synchronous)
 
 ::: lancedb.connect
 
 ::: lancedb.db.DBConnection
 
-## Table
+## Tables (Synchronous)
 
 ::: lancedb.table.Table
 
-## Querying
+## Querying (Synchronous)
 
 ::: lancedb.query.Query
 
@@ -86,4 +89,42 @@ pip install lancedb
 
 ::: lancedb.rerankers.cross_encoder.CrossEncoderReranker
 
-::: lancedb.rerankers.openai.OpenaiReranker
+::: lancedb.rerankers.openai.OpenaiReranker
+
+## Connections (Asynchronous)
+
+Connections represent a connection to a LanceDb database and
+can be used to create, list, or open tables.
+
+::: lancedb.connect_async
+
+::: lancedb.db.AsyncConnection
+
+## Tables (Asynchronous)
+
+Table hold your actual data as a collection of records / rows.
+
+::: lancedb.table.AsyncTable
+
+## Indices (Asynchronous)
+
+Indices can be created on a table to speed up queries. This section
+lists the indices that LanceDb supports.
+
+::: lancedb.index.BTree
+
+::: lancedb.index.IvfPq
+
+## Querying (Asynchronous)
+
+Queries allow you to return data from your database. Basic queries can be
+created with the [AsyncTable.query][lancedb.table.AsyncTable.query] method
+to return the entire (typically filtered) table. Vector searches return the
+rows nearest to a query vector and can be created with the
+[AsyncTable.vector_search][lancedb.table.AsyncTable.vector_search] method.
+
+::: lancedb.query.AsyncQueryBase
+
+::: lancedb.query.AsyncQuery
+
+::: lancedb.query.AsyncVectorQuery

node/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "vectordb",
-  "version": "0.4.13",
+  "version": "0.4.15",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "vectordb",
-      "version": "0.4.13",
+      "version": "0.4.15",
       "cpu": [
         "x64",
         "arm64"
@@ -52,11 +52,11 @@
         "uuid": "^9.0.0"
       },
       "optionalDependencies": {
-        "@lancedb/vectordb-darwin-arm64": "0.4.13",
-        "@lancedb/vectordb-darwin-x64": "0.4.13",
-        "@lancedb/vectordb-linux-arm64-gnu": "0.4.13",
-        "@lancedb/vectordb-linux-x64-gnu": "0.4.13",
-        "@lancedb/vectordb-win32-x64-msvc": "0.4.13"
+        "@lancedb/vectordb-darwin-arm64": "0.4.15",
+        "@lancedb/vectordb-darwin-x64": "0.4.15",
+        "@lancedb/vectordb-linux-arm64-gnu": "0.4.15",
+        "@lancedb/vectordb-linux-x64-gnu": "0.4.15",
+        "@lancedb/vectordb-win32-x64-msvc": "0.4.15"
       },
       "peerDependencies": {
         "@apache-arrow/ts": "^14.0.2",
@@ -333,66 +333,6 @@
         "@jridgewell/sourcemap-codec": "^1.4.10"
       }
     },
-    "node_modules/@lancedb/vectordb-darwin-arm64": {
-      "version": "0.4.13",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.4.13.tgz",
-      "integrity": "sha512-JfroNCG8yKIU931Y+x8d0Fp8C9DHUSC5j+CjI+e5err7rTWtie4j3JbsXlWAnPFaFEOg0Xk3BWkSikCvhPGJGg==",
-      "cpu": [
-        "arm64"
-      ],
-      "optional": true,
-      "os": [
-        "darwin"
-      ]
-    },
-    "node_modules/@lancedb/vectordb-darwin-x64": {
-      "version": "0.4.13",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.4.13.tgz",
-      "integrity": "sha512-dG6IMvfpHpnHdbJ0UffzJ7cZfMiC02MjIi6YJzgx+hKz2UNXWNBIfTvvhqli85mZsGRXL1OYDdYv0K1YzNjXlA==",
-      "cpu": [
-        "x64"
-      ],
-      "optional": true,
-      "os": [
-        "darwin"
-      ]
-    },
-    "node_modules/@lancedb/vectordb-linux-arm64-gnu": {
-      "version": "0.4.13",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.4.13.tgz",
-      "integrity": "sha512-BRR1VzaMviXby7qmLm0axNZM8eUZF3ZqfvnDKdVRpC3LaRueD6pMXHuC2IUKaFkn7xktf+8BlDZb6foFNEj8bQ==",
-      "cpu": [
-        "arm64"
-      ],
-      "optional": true,
-      "os": [
-        "linux"
-      ]
-    },
-    "node_modules/@lancedb/vectordb-linux-x64-gnu": {
-      "version": "0.4.13",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.4.13.tgz",
-      "integrity": "sha512-WnekZ7ZMlria+NODZ6aBCljCFQSe2bBNUS9ZpyFl/Y1vHduSQPuBxM6V7vp2QubC0daq/rifgjDob89DF+x3xw==",
-      "cpu": [
-        "x64"
-      ],
-      "optional": true,
-      "os": [
-        "linux"
-      ]
-    },
-    "node_modules/@lancedb/vectordb-win32-x64-msvc": {
-      "version": "0.4.13",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.4.13.tgz",
-      "integrity": "sha512-3NDpMWBL2ksDHXAraXhowiLqQcNWM5bdbeHwze4+InYMD54hyQ2ODNc+4usxp63Nya9biVnFS27yXULqkzIEqQ==",
-      "cpu": [
-        "x64"
-      ],
-      "optional": true,
-      "os": [
-        "win32"
-      ]
-    },
     "node_modules/@neon-rs/cli": {
       "version": "0.0.160",
       "resolved": "https://registry.npmjs.org/@neon-rs/cli/-/cli-0.0.160.tgz",

node/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vectordb",
-  "version": "0.4.13",
+  "version": "0.4.15",
   "description": " Serverless, low-latency vector database for AI applications",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
@@ -88,10 +88,10 @@
     }
   },
   "optionalDependencies": {
-    "@lancedb/vectordb-darwin-arm64": "0.4.13",
-    "@lancedb/vectordb-darwin-x64": "0.4.13",
-    "@lancedb/vectordb-linux-arm64-gnu": "0.4.13",
-    "@lancedb/vectordb-linux-x64-gnu": "0.4.13",
-    "@lancedb/vectordb-win32-x64-msvc": "0.4.13"
+    "@lancedb/vectordb-darwin-arm64": "0.4.15",
+    "@lancedb/vectordb-darwin-x64": "0.4.15",
+    "@lancedb/vectordb-linux-arm64-gnu": "0.4.15",
+    "@lancedb/vectordb-linux-x64-gnu": "0.4.15",
+    "@lancedb/vectordb-win32-x64-msvc": "0.4.15"
   }
 }

node/src/index.ts

@@ -24,6 +24,7 @@ import { RemoteConnection } from './remote'
 import { Query } from './query'
 import { isEmbeddingFunction } from './embedding/embedding_function'
 import { type Literal, toSQL } from './util'
+import { type HttpMiddleware } from './middleware'
 
 const {
   databaseNew,
@@ -302,6 +303,18 @@ export interface Connection {
    * @param name The name of the table to drop.
    */
   dropTable(name: string): Promise<void>
+
+  /**
+   * Instrument the behavior of this Connection with middleware.
+   *
+   * The middleware will be called in the order they are added.
+   *
+   * Currently this functionality is only supported for remote Connections.
+   *
+   * @param {HttpMiddleware} - Middleware which will instrument the Connection.
+   * @returns - this Connection instrumented by the passed middleware
+   */
+  withMiddleware(middleware: HttpMiddleware): Connection
 }
 
 /**
@@ -541,6 +554,18 @@ export interface Table<T = number[]> {
    *                    names (e.g. "a").
    */
   dropColumns(columnNames: string[]): Promise<void>
+
+  /**
+   * Instrument the behavior of this Table with middleware.
+   *
+   * The middleware will be called in the order they are added.
+   *
+   * Currently this functionality is only supported for remote tables.
+   *
+   * @param {HttpMiddleware} - Middleware which will instrument the Table.
+   * @returns - this Table instrumented by the passed middleware
+   */
+  withMiddleware(middleware: HttpMiddleware): Table<T>
 }
 
 /**
@@ -795,6 +820,10 @@ export class LocalConnection implements Connection {
   async dropTable (name: string): Promise<void> {
     await databaseDropTable.call(this._db, name)
   }
+
+  withMiddleware (middleware: HttpMiddleware): Connection {
+    return this
+  }
 }
 
 export class LocalTable<T = number[]> implements Table<T> {
@@ -1105,6 +1134,10 @@ export class LocalTable<T = number[]> implements Table<T> {
   async dropColumns (columnNames: string[]): Promise<void> {
     return tableDropColumns.call(this._tbl, columnNames)
   }
+
+  withMiddleware (middleware: HttpMiddleware): Table<T> {
+    return this
+  }
 }
 
 export interface CleanupStats {

node/src/middleware.ts

@@ -0,0 +1,58 @@
+// Copyright 2024 LanceDB Developers.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+/**
+ * Middleware for Remote LanceDB Connection or Table
+ */
+export interface HttpMiddleware {
+  /**
+   * A callback that can be used to instrument the behavior of http requests to remote
+   * tables. It can be used to add headers, modify the request, or even short-circuit
+   * the request and return a response without making the request to the remote endpoint.
+   * It can also be used to modify the response from the remote endpoint.
+   *
+   * @param {RemoteResponse} res - Request to the remote endpoint
+   * @param {onRemoteRequestNext} next - Callback to advance the middleware chain
+   */
+  onRemoteRequest(
+    req: RemoteRequest,
+    next: (req: RemoteRequest) => Promise<RemoteResponse>,
+  ): Promise<RemoteResponse>
+};
+
+export enum Method {
+  GET,
+  POST
+}
+
+/**
+ * A LanceDB Remote HTTP Request
+ */
+export interface RemoteRequest {
+  uri: string
+  method: Method
+  headers: Map<string, string>
+  params?: Map<string, string>
+  body?: any
+}
+
+/**
+ * A LanceDB Remote HTTP Response
+ */
+export interface RemoteResponse {
+  status: number
+  statusText: string
+  headers: Map<string, string>
+  body: () => Promise<any>
+}

node/src/remote/client.ts

@@ -12,13 +12,101 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-import axios, { type AxiosResponse } from 'axios'
+import axios, { type AxiosResponse, type ResponseType } from 'axios'
 
 import { tableFromIPC, type Table as ArrowTable } from 'apache-arrow'
 
+import { type RemoteResponse, type RemoteRequest, Method } from '../middleware'
+
+interface HttpLancedbClientMiddleware {
+  onRemoteRequest(
+    req: RemoteRequest,
+    next: (req: RemoteRequest) => Promise<RemoteResponse>,
+  ): Promise<RemoteResponse>
+}
+
+/**
+ * Invoke the middleware chain and at the end call the remote endpoint
+ */
+async function callWithMiddlewares (
+  req: RemoteRequest,
+  middlewares: HttpLancedbClientMiddleware[],
+  opts?: MiddlewareInvocationOptions
+): Promise<RemoteResponse> {
+  async function call (
+    i: number,
+    req: RemoteRequest
+  ): Promise<RemoteResponse> {
+    // if we have reached the end of the middleware chain, make the request
+    if (i > middlewares.length) {
+      const headers = Object.fromEntries(req.headers.entries())
+      const params = Object.fromEntries(req.params?.entries() ?? [])
+      const timeout = 10000
+      let res
+      if (req.method === Method.POST) {
+        res = await axios.post(
+          req.uri,
+          req.body,
+          {
+            headers,
+            params,
+            timeout,
+            responseType: opts?.responseType
+          }
+        )
+      } else {
+        res = await axios.get(
+          req.uri,
+          {
+            headers,
+            params,
+            timeout
+          }
+        )
+      }
+
+      return toLanceRes(res)
+    }
+
+    // call next middleware in chain
+    return await middlewares[i - 1].onRemoteRequest(
+      req,
+      async (req) => {
+        return await call(i + 1, req)
+      }
+    )
+  }
+
+  return await call(1, req)
+}
+
+interface MiddlewareInvocationOptions {
+  responseType?: ResponseType
+}
+
+/**
+ * Marshall the library response into a LanceDB response
+ */
+function toLanceRes (res: AxiosResponse): RemoteResponse {
+  const headers = new Map()
+  for (const h in res.headers) {
+    headers.set(h, res.headers[h])
+  }
+
+  return {
+    status: res.status,
+    statusText: res.statusText,
+    headers,
+    body: async () => {
+      return res.data
+    }
+  }
+}
+
 export class HttpLancedbClient {
   private readonly _url: string
   private readonly _apiKey: () => string
+  private readonly _middlewares: HttpLancedbClientMiddleware[]
 
   public constructor (
     url: string,
@@ -27,6 +115,7 @@ export class HttpLancedbClient {
   ) {
     this._url = url
     this._apiKey = () => apiKey
+    this._middlewares = []
   }
 
   get uri (): string {
@@ -43,74 +132,61 @@ export class HttpLancedbClient {
     columns?: string[],
     filter?: string
   ): Promise<ArrowTable<any>> {
-    const response = await axios.post(
-              `${this._url}/v1/table/${tableName}/query/`,
-              {
-                vector,
-                k,
-                nprobes,
-                refineFactor,
-                columns,
-                filter,
-                prefilter
-              },
-              {
-                headers: {
-                  'Content-Type': 'application/json',
-                  'x-api-key': this._apiKey(),
-                  ...(this._dbName !== undefined ? { 'x-lancedb-database': this._dbName } : {})
-                },
-                responseType: 'arraybuffer',
-                timeout: 10000
-              }
-    ).catch((err) => {
-      console.error('error: ', err)
-      if (err.response === undefined) {
-        throw new Error(`Network Error: ${err.message as string}`)
-      }
-      return err.response
-    })
-    if (response.status !== 200) {
-      const errorData = new TextDecoder().decode(response.data)
-      throw new Error(
-        `Server Error, status: ${response.status as number}, ` +
-        `message: ${response.statusText as string}: ${errorData}`
-      )
-    }
-
-    const table = tableFromIPC(response.data)
+    const result = await this.post(
+      `/v1/table/${tableName}/query/`,
+      {
+        vector,
+        k,
+        nprobes,
+        refineFactor,
+        columns,
+        filter,
+        prefilter
+      },
+      undefined,
+      undefined,
+      'arraybuffer'
+    )
+    const table = tableFromIPC(await result.body())
     return table
   }
 
   /**
    * Sent GET request.
    */
-  public async get (path: string, params?: Record<string, string | number>): Promise<AxiosResponse> {
-    const response = await axios.get(
-      `${this._url}${path}`,
-      {
-        headers: {
-          'Content-Type': 'application/json',
-          'x-api-key': this._apiKey(),
-          ...(this._dbName !== undefined ? { 'x-lancedb-database': this._dbName } : {})
-        },
-        params,
-        timeout: 10000
-      }
-    ).catch((err) => {
+  public async get (path: string, params?: Record<string, string>): Promise<RemoteResponse> {
+    const req = {
+      uri: `${this._url}${path}`,
+      method: Method.GET,
+      headers: new Map(Object.entries({
+        'Content-Type': 'application/json',
+        'x-api-key': this._apiKey(),
+        ...(this._dbName !== undefined ? { 'x-lancedb-database': this._dbName } : {})
+      })),
+      params: new Map(Object.entries(params ?? {}))
+    }
+
+    let response
+    try {
+      response = await callWithMiddlewares(req, this._middlewares)
+      return response
+    } catch (err: any) {
       console.error('error: ', err)
       if (err.response === undefined) {
         throw new Error(`Network Error: ${err.message as string}`)
       }
-      return err.response
-    })
+
+      response = toLanceRes(err.response)
+    }
+
     if (response.status !== 200) {
-      const errorData = new TextDecoder().decode(response.data)
+      const errorData = new TextDecoder().decode(await response.body())
       throw new Error(
-        `Server Error, status: ${response.status as number}, ` +
-        `message: ${response.statusText as string}: ${errorData}`
+        `Server Error, status: ${response.status}, ` +
+        `message: ${response.statusText}: ${errorData}`
       )
     }
+
     return response
   }
 
@@ -120,35 +196,65 @@ export class HttpLancedbClient {
   public async post (
     path: string,
     data?: any,
-    params?: Record<string, string | number>,
-    content?: string | undefined
-  ): Promise<AxiosResponse> {
-    const response = await axios.post(
-        `${this._url}${path}`,
-        data,
-        {
-          headers: {
-            'Content-Type': content ?? 'application/json',
-            'x-api-key': this._apiKey(),
-            ...(this._dbName !== undefined ? { 'x-lancedb-database': this._dbName } : {})
-          },
-          params,
-          timeout: 30000
-        }
-    ).catch((err) => {
+    params?: Record<string, string>,
+    content?: string | undefined,
+    responseType?: ResponseType | undefined
+  ): Promise<RemoteResponse> {
+    const req = {
+      uri: `${this._url}${path}`,
+      method: Method.POST,
+      headers: new Map(Object.entries({
+        'Content-Type': content ?? 'application/json',
+        'x-api-key': this._apiKey(),
+        ...(this._dbName !== undefined ? { 'x-lancedb-database': this._dbName } : {})
+      })),
+      params: new Map(Object.entries(params ?? {})),
+      body: data
+    }
+
+    let response
+    try {
+      response = await callWithMiddlewares(req, this._middlewares, { responseType })
+
+      // return response
+    } catch (err: any) {
       console.error('error: ', err)
       if (err.response === undefined) {
         throw new Error(`Network Error: ${err.message as string}`)
       }
-      return err.response
-    })
+      response = toLanceRes(err.response)
+    }
+
     if (response.status !== 200) {
-      const errorData = new TextDecoder().decode(response.data)
+      const errorData = new TextDecoder().decode(await response.body())
       throw new Error(
-          `Server Error, status: ${response.status as number}, ` +
-          `message: ${response.statusText as string}: ${errorData}`
+        `Server Error, status: ${response.status}, ` +
+        `message: ${response.statusText}: ${errorData}`
       )
     }
+
     return response
   }
+
+  /**
+   * Instrument this client with middleware
+   * @param mw - The middleware that instruments the client
+   * @returns - an instance of this client instrumented with the middleware
+   */
+  public withMiddleware (mw: HttpLancedbClientMiddleware): HttpLancedbClient {
+    const wrapped = this.clone()
+    wrapped._middlewares.push(mw)
+    return wrapped
+  }
+
+  /**
+   * Make a clone of this client
+   */
+  private clone (): HttpLancedbClient {
+    const clone = new HttpLancedbClient(this._url, this._apiKey(), this._dbName)
+    for (const mw of this._middlewares) {
+      clone._middlewares.push(mw)
+    }
+    return clone
+  }
 }

node/src/remote/index.ts

@@ -39,12 +39,13 @@ import {
   fromTableToStreamBuffer
 } from '../arrow'
 import { toSQL } from '../util'
+import { type HttpMiddleware } from '../middleware'
 
 /**
  * Remote connection.
  */
 export class RemoteConnection implements Connection {
-  private readonly _client: HttpLancedbClient
+  private _client: HttpLancedbClient
   private readonly _dbName: string
 
   constructor (opts: ConnectionOptions) {
@@ -84,10 +85,11 @@ export class RemoteConnection implements Connection {
     limit: number = 10
   ): Promise<string[]> {
     const response = await this._client.get('/v1/table/', {
-      limit,
+      limit: `${limit}`,
       page_token: pageToken
     })
-    return response.data.tables
+    const body = await response.body()
+    return body.tables
   }
 
   async openTable (name: string): Promise<Table>
@@ -163,7 +165,7 @@ export class RemoteConnection implements Connection {
       throw new Error(
         `Server Error, status: ${res.status}, ` +
           // eslint-disable-next-line @typescript-eslint/restrict-template-expressions
-          `message: ${res.statusText}: ${res.data}`
+          `message: ${res.statusText}: ${await res.body()}`
       )
     }
 
@@ -177,6 +179,17 @@ export class RemoteConnection implements Connection {
   async dropTable (name: string): Promise<void> {
     await this._client.post(`/v1/table/${name}/drop/`)
   }
+
+  withMiddleware (middleware: HttpMiddleware): Connection {
+    const wrapped = this.clone()
+    wrapped._client = wrapped._client.withMiddleware(middleware)
+    return wrapped
+  }
+
+  private clone (): RemoteConnection {
+    const clone: RemoteConnection = Object.create(RemoteConnection.prototype)
+    return Object.assign(clone, this)
+  }
 }
 
 export class RemoteQuery<T = number[]> extends Query<T> {
@@ -229,7 +242,7 @@ export class RemoteQuery<T = number[]> extends Query<T> {
 // we are using extend until we have next next version release
 // Table and Connection has both been refactored to interfaces
 export class RemoteTable<T = number[]> implements Table<T> {
-  private readonly _client: HttpLancedbClient
+  private _client: HttpLancedbClient
   private readonly _embeddings?: EmbeddingFunction<T>
   private readonly _name: string
 
@@ -256,15 +269,15 @@ export class RemoteTable<T = number[]> implements Table<T> {
   get schema (): Promise<any> {
     return this._client
       .post(`/v1/table/${this._name}/describe/`)
-      .then((res) => {
+      .then(async (res) => {
         if (res.status !== 200) {
           throw new Error(
             `Server Error, status: ${res.status}, ` +
               // eslint-disable-next-line @typescript-eslint/restrict-template-expressions
-              `message: ${res.statusText}: ${res.data}`
+              `message: ${res.statusText}: ${await res.body()}`
           )
         }
-        return res.data?.schema
+        return (await res.body())?.schema
       })
   }
 
@@ -320,7 +333,7 @@ export class RemoteTable<T = number[]> implements Table<T> {
       throw new Error(
         `Server Error, status: ${res.status}, ` +
           // eslint-disable-next-line @typescript-eslint/restrict-template-expressions
-          `message: ${res.statusText}: ${res.data}`
+          `message: ${res.statusText}: ${await res.body()}`
       )
     }
   }
@@ -346,7 +359,7 @@ export class RemoteTable<T = number[]> implements Table<T> {
       throw new Error(
         `Server Error, status: ${res.status}, ` +
           // eslint-disable-next-line @typescript-eslint/restrict-template-expressions
-          `message: ${res.statusText}: ${res.data}`
+          `message: ${res.statusText}: ${await res.body()}`
       )
     }
     return tbl.numRows
@@ -372,7 +385,7 @@ export class RemoteTable<T = number[]> implements Table<T> {
       throw new Error(
         `Server Error, status: ${res.status}, ` +
           // eslint-disable-next-line @typescript-eslint/restrict-template-expressions
-          `message: ${res.statusText}: ${res.data}`
+          `message: ${res.statusText}: ${await res.body()}`
       )
     }
     return tbl.numRows
@@ -415,7 +428,7 @@ export class RemoteTable<T = number[]> implements Table<T> {
       throw new Error(
         `Server Error, status: ${res.status}, ` +
           // eslint-disable-next-line @typescript-eslint/restrict-template-expressions
-          `message: ${res.statusText}: ${res.data}`
+          `message: ${res.statusText}: ${await res.body()}`
       )
     }
   }
@@ -436,14 +449,14 @@ export class RemoteTable<T = number[]> implements Table<T> {
       throw new Error(
         `Server Error, status: ${res.status}, ` +
           // eslint-disable-next-line @typescript-eslint/restrict-template-expressions
-          `message: ${res.statusText}: ${res.data}`
+          `message: ${res.statusText}: ${await res.body()}`
       )
     }
   }
 
   async countRows (): Promise<number> {
     const result = await this._client.post(`/v1/table/${this._name}/describe/`)
-    return result.data?.stats?.num_rows
+    return (await result.body())?.stats?.num_rows
   }
 
   async delete (filter: string): Promise<void> {
@@ -476,7 +489,7 @@ export class RemoteTable<T = number[]> implements Table<T> {
     const results = await this._client.post(
       `/v1/table/${this._name}/index/list/`
     )
-    return results.data.indexes?.map((index: any) => ({
+    return (await results.body()).indexes?.map((index: any) => ({
       columns: index.columns,
       name: index.index_name,
       uuid: index.index_uuid
@@ -487,9 +500,10 @@ export class RemoteTable<T = number[]> implements Table<T> {
     const results = await this._client.post(
       `/v1/table/${this._name}/index/${indexUuid}/stats/`
     )
+    const body = await results.body()
     return {
-      numIndexedRows: results.data.num_indexed_rows,
-      numUnindexedRows: results.data.num_unindexed_rows
+      numIndexedRows: body?.num_indexed_rows,
+      numUnindexedRows: body?.num_unindexed_rows
     }
   }
 
@@ -504,4 +518,15 @@ export class RemoteTable<T = number[]> implements Table<T> {
   async dropColumns (columnNames: string[]): Promise<void> {
     throw new Error('Drop columns is not yet supported in LanceDB Cloud.')
   }
+
+  withMiddleware(middleware: HttpMiddleware): Table<T> {
+    const wrapped = this.clone()
+    wrapped._client = wrapped._client.withMiddleware(middleware)
+    return wrapped
+  }
+
+  private clone (): RemoteTable<T> {
+    const clone: RemoteTable<T> = Object.create(RemoteTable.prototype)
+    return Object.assign(clone, this)
+  }
 }

nodejs/README.md

@@ -1,12 +1,44 @@
-# (New) LanceDB NodeJS SDK
+# LanceDB JavaScript SDK
 
-It will replace the NodeJS SDK when it is ready.
+A JavaScript library for [LanceDB](https://github.com/lancedb/lancedb).
+
+## Installation
+
+```bash
+npm install @lancedb/lancedb
+```
+
+This will download the appropriate native library for your platform. We currently
+support:
+
+- Linux (x86_64 and aarch64)
+- MacOS (Intel and ARM/M1/M2)
+- Windows (x86_64 only)
+
+We do not yet support musl-based Linux (such as Alpine Linux) or aarch64 Windows.
+
+## Usage
+
+### Basic Example
+
+```javascript
+import * as lancedb from "@lancedb/lancedb";
+const db = await lancedb.connect("data/sample-lancedb");
+const table = await db.createTable("my_table", [
+  { id: 1, vector: [0.1, 1.0], item: "foo", price: 10.0 },
+  { id: 2, vector: [3.9, 0.5], item: "bar", price: 20.0 },
+]);
+const results = await table.vectorSearch([0.1, 0.3]).limit(20).toArray();
+console.log(results);
+```
+
+The [quickstart](../basic.md) contains a more complete example.
 
 ## Development
 
 ```sh
 npm run build
-npm t
+npm run test
 ```
 
 ### Running lint / format

nodejs/lancedb/arrow.ts

@@ -106,6 +106,9 @@ export class MakeArrowTableOptions {
  * An enhanced version of the {@link makeTable} function from Apache Arrow
  * that supports nested fields and embeddings columns.
  *
+ * (typically you do not need to call this function.  It will be called automatically
+ * 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)
  *

nodejs/lancedb/embedding/index.ts

@@ -0,0 +1,2 @@
+export { EmbeddingFunction, isEmbeddingFunction } from "./embedding_function";
+export { OpenAIEmbeddingFunction } from "./openai";

nodejs/lancedb/index.ts

@@ -18,9 +18,34 @@ import {
   ConnectionOptions,
 } from "./native.js";
 
-export { ConnectionOptions, WriteOptions, Query } from "./native.js";
-export { Connection, CreateTableOptions } from "./connection";
-export { Table, AddDataOptions } from "./table";
+export {
+  WriteOptions,
+  WriteMode,
+  AddColumnsSql,
+  ColumnAlteration,
+  ConnectionOptions,
+} from "./native.js";
+export {
+  makeArrowTable,
+  MakeArrowTableOptions,
+  Data,
+  VectorColumnOptions,
+} from "./arrow";
+export {
+  Connection,
+  CreateTableOptions,
+  TableNamesOptions,
+} from "./connection";
+export {
+  ExecutableQuery,
+  Query,
+  QueryBase,
+  VectorQuery,
+  RecordBatchIterator,
+} from "./query";
+export { Index, IndexOptions, IvfPqOptions } from "./indices";
+export { Table, AddDataOptions, IndexConfig, UpdateOptions } from "./table";
+export * as embedding from "./embedding";
 
 /**
  * Connect to a LanceDB instance at the given URI.

nodejs/lancedb/native.d.ts

@@ -1,147 +0,0 @@
-/* tslint:disable */
-/* eslint-disable */
-
-/* auto-generated by NAPI-RS */
-
-/** A description of an index currently configured on a column */
-export interface IndexConfig {
-  /** The type of the index */
-  indexType: string
-  /**
-   * The columns in the index
-   *
-   * Currently this is always an array of size 1.  In the future there may
-   * be more columns to represent composite indices.
-   */
-  columns: Array<string>
-}
-/**
- *  A definition of a column alteration. The alteration changes the column at
- * `path` to have the new name `name`, to be nullable if `nullable` is true,
- * and to have the data type `data_type`. At least one of `rename` or `nullable`
- * must be provided.
- */
-export interface ColumnAlteration {
-  /**
-   * The path to the column to alter. This is a dot-separated path to the column.
-   * If it is a top-level column then it is just the name of the column. If it is
-   * a nested column then it is the path to the column, e.g. "a.b.c" for a column
-   * `c` nested inside a column `b` nested inside a column `a`.
-   */
-  path: string
-  /**
-   * The new name of the column. If not provided then the name will not be changed.
-   * This must be distinct from the names of all other columns in the table.
-   */
-  rename?: string
-  /** Set the new nullability. Note that a nullable column cannot be made non-nullable. */
-  nullable?: boolean
-}
-/** A definition of a new column to add to a table. */
-export interface AddColumnsSql {
-  /** The name of the new column. */
-  name: string
-  /**
-   * The values to populate the new column with, as a SQL expression.
-   * The expression can reference other columns in the table.
-   */
-  valueSql: string
-}
-export interface ConnectionOptions {
-  apiKey?: string
-  hostOverride?: string
-  /**
-   * (For LanceDB OSS only): The interval, in seconds, at which to check for
-   * updates to the table from other processes. If None, then consistency is not
-   * checked. For performance reasons, this is the default. For strong
-   * consistency, set this to zero seconds. Then every read will check for
-   * updates from other processes. As a compromise, you can set this to a
-   * non-zero value for eventual consistency. If more than that interval
-   * has passed since the last check, then the table will be checked for updates.
-   * Note: this consistency only applies to read operations. Write operations are
-   * always consistent.
-   */
-  readConsistencyInterval?: number
-}
-/** Write mode for writing a table. */
-export const enum WriteMode {
-  Create = 'Create',
-  Append = 'Append',
-  Overwrite = 'Overwrite'
-}
-/** Write options when creating a Table. */
-export interface WriteOptions {
-  mode?: WriteMode
-}
-export function connect(uri: string, options: ConnectionOptions): Promise<Connection>
-export class Connection {
-  /** Create a new Connection instance from the given URI. */
-  static new(uri: string, options: ConnectionOptions): Promise<Connection>
-  display(): string
-  isOpen(): boolean
-  close(): void
-  /** List all tables in the dataset. */
-  tableNames(startAfter?: string | undefined | null, limit?: number | undefined | null): Promise<Array<string>>
-  /**
-   * Create table from a Apache Arrow IPC (file) buffer.
-   *
-   * Parameters:
-   * - name: The name of the table.
-   * - buf: The buffer containing the IPC file.
-   *
-   */
-  createTable(name: string, buf: Buffer, mode: string): Promise<Table>
-  createEmptyTable(name: string, schemaBuf: Buffer, mode: string): Promise<Table>
-  openTable(name: string): Promise<Table>
-  /** Drop table with the name. Or raise an error if the table does not exist. */
-  dropTable(name: string): Promise<void>
-}
-export class Index {
-  static ivfPq(distanceType?: string | undefined | null, numPartitions?: number | undefined | null, numSubVectors?: number | undefined | null, maxIterations?: number | undefined | null, sampleRate?: number | undefined | null): Index
-  static btree(): Index
-}
-/** Typescript-style Async Iterator over RecordBatches  */
-export class RecordBatchIterator {
-  next(): Promise<Buffer | null>
-}
-export class Query {
-  onlyIf(predicate: string): void
-  select(columns: Array<[string, string]>): void
-  limit(limit: number): void
-  nearestTo(vector: Float32Array): VectorQuery
-  execute(): Promise<RecordBatchIterator>
-}
-export class VectorQuery {
-  column(column: string): void
-  distanceType(distanceType: string): void
-  postfilter(): void
-  refineFactor(refineFactor: number): void
-  nprobes(nprobe: number): void
-  bypassVectorIndex(): void
-  onlyIf(predicate: string): void
-  select(columns: Array<[string, string]>): void
-  limit(limit: number): void
-  execute(): Promise<RecordBatchIterator>
-}
-export class Table {
-  display(): string
-  isOpen(): boolean
-  close(): void
-  /** Return Schema as empty Arrow IPC file. */
-  schema(): Promise<Buffer>
-  add(buf: Buffer, mode: string): Promise<void>
-  countRows(filter?: string | undefined | null): Promise<number>
-  delete(predicate: string): Promise<void>
-  createIndex(index: Index | undefined | null, column: string, replace?: boolean | undefined | null): Promise<void>
-  update(onlyIf: string | undefined | null, columns: Array<[string, string]>): Promise<void>
-  query(): Query
-  vectorSearch(vector: Float32Array): VectorQuery
-  addColumns(transforms: Array<AddColumnsSql>): Promise<void>
-  alterColumns(alterations: Array<ColumnAlteration>): Promise<void>
-  dropColumns(columns: Array<string>): Promise<void>
-  version(): Promise<number>
-  checkout(version: number): Promise<void>
-  checkoutLatest(): Promise<void>
-  restore(): Promise<void>
-  listIndices(): Promise<Array<IndexConfig>>
-}

nodejs/lancedb/native.js

@@ -1,329 +0,0 @@
-/* tslint:disable */
-/* eslint-disable */
-/* prettier-ignore */
-
-/* auto-generated by NAPI-RS */
-
-const { existsSync, readFileSync } = require('fs')
-const { join } = require("path");
-
-const { platform, arch } = process;
-
-let nativeBinding = null;
-let localFileExisted = false;
-let loadError = null;
-
-function isMusl() {
-  // For Node 10
-  if (!process.report || typeof process.report.getReport !== "function") {
-    try {
-      const lddPath = require("child_process")
-        .execSync("which ldd")
-        .toString()
-        .trim();
-      return readFileSync(lddPath, "utf8").includes("musl");
-    } catch (e) {
-      return true;
-    }
-  } else {
-    const { glibcVersionRuntime } = process.report.getReport().header;
-    return !glibcVersionRuntime;
-  }
-}
-
-switch (platform) {
-  case "android":
-    switch (arch) {
-      case "arm64":
-        localFileExisted = existsSync(
-          join(__dirname, "lancedb-nodejs.android-arm64.node"),
-        );
-        try {
-          if (localFileExisted) {
-            nativeBinding = require("./lancedb-nodejs.android-arm64.node");
-          } else {
-            nativeBinding = require("lancedb-android-arm64");
-          }
-        } catch (e) {
-          loadError = e;
-        }
-        break;
-      case "arm":
-        localFileExisted = existsSync(
-          join(__dirname, "lancedb-nodejs.android-arm-eabi.node"),
-        );
-        try {
-          if (localFileExisted) {
-            nativeBinding = require("./lancedb-nodejs.android-arm-eabi.node");
-          } else {
-            nativeBinding = require("lancedb-android-arm-eabi");
-          }
-        } catch (e) {
-          loadError = e;
-        }
-        break;
-      default:
-        throw new Error(`Unsupported architecture on Android ${arch}`);
-    }
-    break;
-  case "win32":
-    switch (arch) {
-      case "x64":
-        localFileExisted = existsSync(
-          join(__dirname, "lancedb-nodejs.win32-x64-msvc.node"),
-        );
-        try {
-          if (localFileExisted) {
-            nativeBinding = require("./lancedb-nodejs.win32-x64-msvc.node");
-          } else {
-            nativeBinding = require("lancedb-win32-x64-msvc");
-          }
-        } catch (e) {
-          loadError = e;
-        }
-        break;
-      case "ia32":
-        localFileExisted = existsSync(
-          join(__dirname, "lancedb-nodejs.win32-ia32-msvc.node"),
-        );
-        try {
-          if (localFileExisted) {
-            nativeBinding = require("./lancedb-nodejs.win32-ia32-msvc.node");
-          } else {
-            nativeBinding = require("lancedb-win32-ia32-msvc");
-          }
-        } catch (e) {
-          loadError = e;
-        }
-        break;
-      case "arm64":
-        localFileExisted = existsSync(
-          join(__dirname, "lancedb-nodejs.win32-arm64-msvc.node"),
-        );
-        try {
-          if (localFileExisted) {
-            nativeBinding = require("./lancedb-nodejs.win32-arm64-msvc.node");
-          } else {
-            nativeBinding = require("lancedb-win32-arm64-msvc");
-          }
-        } catch (e) {
-          loadError = e;
-        }
-        break;
-      default:
-        throw new Error(`Unsupported architecture on Windows: ${arch}`);
-    }
-    break;
-  case "darwin":
-    localFileExisted = existsSync(
-      join(__dirname, "lancedb-nodejs.darwin-universal.node"),
-    );
-    try {
-      if (localFileExisted) {
-        nativeBinding = require("./lancedb-nodejs.darwin-universal.node");
-      } else {
-        nativeBinding = require("lancedb-darwin-universal");
-      }
-      break;
-    } catch {}
-    switch (arch) {
-      case "x64":
-        localFileExisted = existsSync(
-          join(__dirname, "lancedb-nodejs.darwin-x64.node"),
-        );
-        try {
-          if (localFileExisted) {
-            nativeBinding = require("./lancedb-nodejs.darwin-x64.node");
-          } else {
-            nativeBinding = require("lancedb-darwin-x64");
-          }
-        } catch (e) {
-          loadError = e;
-        }
-        break;
-      case "arm64":
-        localFileExisted = existsSync(
-          join(__dirname, "lancedb-nodejs.darwin-arm64.node"),
-        );
-        try {
-          if (localFileExisted) {
-            nativeBinding = require("./lancedb-nodejs.darwin-arm64.node");
-          } else {
-            nativeBinding = require("lancedb-darwin-arm64");
-          }
-        } catch (e) {
-          loadError = e;
-        }
-        break;
-      default:
-        throw new Error(`Unsupported architecture on macOS: ${arch}`);
-    }
-    break;
-  case "freebsd":
-    if (arch !== "x64") {
-      throw new Error(`Unsupported architecture on FreeBSD: ${arch}`);
-    }
-    localFileExisted = existsSync(
-      join(__dirname, "lancedb-nodejs.freebsd-x64.node"),
-    );
-    try {
-      if (localFileExisted) {
-        nativeBinding = require("./lancedb-nodejs.freebsd-x64.node");
-      } else {
-        nativeBinding = require("lancedb-freebsd-x64");
-      }
-    } catch (e) {
-      loadError = e;
-    }
-    break;
-  case "linux":
-    switch (arch) {
-      case "x64":
-        if (isMusl()) {
-          localFileExisted = existsSync(
-            join(__dirname, "lancedb-nodejs.linux-x64-musl.node"),
-          );
-          try {
-            if (localFileExisted) {
-              nativeBinding = require("./lancedb-nodejs.linux-x64-musl.node");
-            } else {
-              nativeBinding = require("lancedb-linux-x64-musl");
-            }
-          } catch (e) {
-            loadError = e;
-          }
-        } else {
-          localFileExisted = existsSync(
-            join(__dirname, "lancedb-nodejs.linux-x64-gnu.node"),
-          );
-          try {
-            if (localFileExisted) {
-              nativeBinding = require("./lancedb-nodejs.linux-x64-gnu.node");
-            } else {
-              nativeBinding = require("lancedb-linux-x64-gnu");
-            }
-          } catch (e) {
-            loadError = e;
-          }
-        }
-        break;
-      case "arm64":
-        if (isMusl()) {
-          localFileExisted = existsSync(
-            join(__dirname, "lancedb-nodejs.linux-arm64-musl.node"),
-          );
-          try {
-            if (localFileExisted) {
-              nativeBinding = require("./lancedb-nodejs.linux-arm64-musl.node");
-            } else {
-              nativeBinding = require("lancedb-linux-arm64-musl");
-            }
-          } catch (e) {
-            loadError = e;
-          }
-        } else {
-          localFileExisted = existsSync(
-            join(__dirname, "lancedb-nodejs.linux-arm64-gnu.node"),
-          );
-          try {
-            if (localFileExisted) {
-              nativeBinding = require("./lancedb-nodejs.linux-arm64-gnu.node");
-            } else {
-              nativeBinding = require("lancedb-linux-arm64-gnu");
-            }
-          } catch (e) {
-            loadError = e;
-          }
-        }
-        break;
-      case "arm":
-        localFileExisted = existsSync(
-          join(__dirname, "lancedb-nodejs.linux-arm-gnueabihf.node"),
-        );
-        try {
-          if (localFileExisted) {
-            nativeBinding = require("./lancedb-nodejs.linux-arm-gnueabihf.node");
-          } else {
-            nativeBinding = require("lancedb-linux-arm-gnueabihf");
-          }
-        } catch (e) {
-          loadError = e;
-        }
-        break;
-      case "riscv64":
-        if (isMusl()) {
-          localFileExisted = existsSync(
-            join(__dirname, "lancedb-nodejs.linux-riscv64-musl.node"),
-          );
-          try {
-            if (localFileExisted) {
-              nativeBinding = require("./lancedb-nodejs.linux-riscv64-musl.node");
-            } else {
-              nativeBinding = require("lancedb-linux-riscv64-musl");
-            }
-          } catch (e) {
-            loadError = e;
-          }
-        } else {
-          localFileExisted = existsSync(
-            join(__dirname, "lancedb-nodejs.linux-riscv64-gnu.node"),
-          );
-          try {
-            if (localFileExisted) {
-              nativeBinding = require("./lancedb-nodejs.linux-riscv64-gnu.node");
-            } else {
-              nativeBinding = require("lancedb-linux-riscv64-gnu");
-            }
-          } catch (e) {
-            loadError = e;
-          }
-        }
-        break;
-      case "s390x":
-        localFileExisted = existsSync(
-          join(__dirname, "lancedb-nodejs.linux-s390x-gnu.node"),
-        );
-        try {
-          if (localFileExisted) {
-            nativeBinding = require("./lancedb-nodejs.linux-s390x-gnu.node");
-          } else {
-            nativeBinding = require("lancedb-linux-s390x-gnu");
-          }
-        } catch (e) {
-          loadError = e;
-        }
-        break;
-      default:
-        throw new Error(`Unsupported architecture on Linux: ${arch}`);
-    }
-    break;
-  default:
-    throw new Error(`Unsupported OS: ${platform}, architecture: ${arch}`);
-}
-
-if (!nativeBinding) {
-  if (loadError) {
-    throw loadError;
-  }
-  throw new Error(`Failed to load native binding`);
-}
-
-const {
-  Connection,
-  Index,
-  RecordBatchIterator,
-  Query,
-  VectorQuery,
-  Table,
-  WriteMode,
-  connect,
-} = nativeBinding;
-
-module.exports.Connection = Connection;
-module.exports.Index = Index;
-module.exports.RecordBatchIterator = RecordBatchIterator;
-module.exports.Query = Query;
-module.exports.VectorQuery = VectorQuery;
-module.exports.Table = Table;
-module.exports.WriteMode = WriteMode;
-module.exports.connect = connect;

nodejs/lancedb/query.ts

@@ -20,7 +20,7 @@ import {
   VectorQuery as NativeVectorQuery,
 } from "./native";
 import { type IvfPqOptions } from "./indices";
-class RecordBatchIterator implements AsyncIterator<RecordBatch> {
+export class RecordBatchIterator implements AsyncIterator<RecordBatch> {
   private promisedInner?: Promise<NativeBatchIterator>;
   private inner?: NativeBatchIterator;
 

nodejs/npm/darwin-arm64/README.md

@@ -1,3 +1,3 @@
-# `lancedb-darwin-arm64`
+# `@lancedb/lancedb-darwin-arm64`
 
-This is the **aarch64-apple-darwin** binary for `lancedb`
+This is the **aarch64-apple-darwin** binary for `@lancedb/lancedb`

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
-  "name": "lancedb-darwin-arm64",
-  "version": "0.4.3",
+  "name": "@lancedb/lancedb-darwin-arm64",
+  "version": "0.4.15",
   "os": [
     "darwin"
   ],
@@ -11,7 +11,7 @@
   "files": [
     "lancedb.darwin-arm64.node"
   ],
-  "license": "MIT",
+  "license": "Apache 2.0",
   "engines": {
     "node": ">= 18"
   }

nodejs/npm/darwin-x64/README.md

@@ -1,3 +1,3 @@
-# `lancedb-darwin-x64`
+# `@lancedb/lancedb-darwin-x64`
 
-This is the **x86_64-apple-darwin** binary for `lancedb`
+This is the **x86_64-apple-darwin** binary for `@lancedb/lancedb`

nodejs/npm/darwin-x64/package.json

@@ -1,6 +1,6 @@
 {
-  "name": "lancedb-darwin-x64",
-  "version": "0.4.3",
+  "name": "@lancedb/lancedb-darwin-x64",
+  "version": "0.4.15",
   "os": [
     "darwin"
   ],
@@ -11,7 +11,7 @@
   "files": [
     "lancedb.darwin-x64.node"
   ],
-  "license": "MIT",
+  "license": "Apache 2.0",
   "engines": {
     "node": ">= 18"
   }

nodejs/npm/linux-arm64-gnu/README.md

@@ -1,3 +1,3 @@
-# `lancedb-linux-arm64-gnu`
+# `@lancedb/lancedb-linux-arm64-gnu`
 
-This is the **aarch64-unknown-linux-gnu** binary for `lancedb`
+This is the **aarch64-unknown-linux-gnu** binary for `@lancedb/lancedb`

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

@@ -1,6 +1,6 @@
 {
-  "name": "lancedb-linux-arm64-gnu",
-  "version": "0.4.3",
+  "name": "@lancedb/lancedb-linux-arm64-gnu",
+  "version": "0.4.15",
   "os": [
     "linux"
   ],
@@ -11,9 +11,9 @@
   "files": [
     "lancedb.linux-arm64-gnu.node"
   ],
-  "license": "MIT",
+  "license": "Apache 2.0",
   "engines": {
-    "node": ">= 10"
+    "node": ">= 18"
   },
   "libc": [
     "glibc"

nodejs/npm/linux-x64-gnu/README.md

@@ -1,3 +1,3 @@
-# `lancedb-linux-x64-gnu`
+# `@lancedb/lancedb-linux-x64-gnu`
 
-This is the **x86_64-unknown-linux-gnu** binary for `lancedb`
+This is the **x86_64-unknown-linux-gnu** binary for `@lancedb/lancedb`

nodejs/npm/linux-x64-gnu/package.json

@@ -1,6 +1,6 @@
 {
-  "name": "lancedb-linux-x64-gnu",
-  "version": "0.4.3",
+  "name": "@lancedb/lancedb-linux-x64-gnu",
+  "version": "0.4.15",
   "os": [
     "linux"
   ],
@@ -11,9 +11,9 @@
   "files": [
     "lancedb.linux-x64-gnu.node"
   ],
-  "license": "MIT",
+  "license": "Apache 2.0",
   "engines": {
-    "node": ">= 10"
+    "node": ">= 18"
   },
   "libc": [
     "glibc"

nodejs/npm/win32-x64-msvc/README.md

@@ -0,0 +1,3 @@
+# `@lancedb/lancedb-win32-x64-msvc`
+
+This is the **x86_64-pc-windows-msvc** binary for `@lancedb/lancedb`

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

@@ -0,0 +1,18 @@
+{
+  "name": "@lancedb/lancedb-win32-x64-msvc",
+  "version": "0.4.14",
+  "os": [
+    "win32"
+  ],
+  "cpu": [
+    "x64"
+  ],
+  "main": "lancedb.win32-x64-msvc.node",
+  "files": [
+    "lancedb.win32-x64-msvc.node"
+  ],
+  "license": "Apache 2.0",
+  "engines": {
+    "node": ">= 18"
+  }
+}

nodejs/package-lock.json

@@ -1,11 +1,11 @@
 {
-  "name": "lancedb",
+  "name": "@lancedb/lancedb",
   "version": "0.4.3",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
-      "name": "lancedb",
+      "name": "@lancedb/lancedb",
       "version": "0.4.3",
       "cpu": [
         "x64",
@@ -15,8 +15,12 @@
       "os": [
         "darwin",
         "linux",
-        "windows"
+        "win32"
       ],
+      "dependencies": {
+        "apache-arrow": "^15.0.0",
+        "openai": "^4.29.2"
+      },
       "devDependencies": {
         "@napi-rs/cli": "^2.18.0",
         "@types/jest": "^29.1.2",
@@ -29,6 +33,7 @@
         "eslint-plugin-jsdoc": "^48.2.1",
         "jest": "^29.7.0",
         "prettier": "^3.1.0",
+        "shx": "^0.3.4",
         "tmp": "^0.2.3",
         "ts-jest": "^29.1.2",
         "typedoc": "^0.25.7",
@@ -40,14 +45,11 @@
         "node": ">= 18"
       },
       "optionalDependencies": {
-        "lancedb-darwin-arm64": "0.4.3",
-        "lancedb-darwin-x64": "0.4.3",
-        "lancedb-linux-arm64-gnu": "0.4.3",
-        "lancedb-linux-x64-gnu": "0.4.3",
-        "openai": "^4.28.4"
-      },
-      "peerDependencies": {
-        "apache-arrow": "^15.0.0"
+        "@lancedb/lancedb-darwin-arm64": "0.4.3",
+        "@lancedb/lancedb-darwin-x64": "0.4.3",
+        "@lancedb/lancedb-linux-arm64-gnu": "0.4.3",
+        "@lancedb/lancedb-linux-x64-gnu": "0.4.3",
+        "@lancedb/lancedb-win32-x64-msvc": "0.4.3"
       }
     },
     "node_modules/@75lb/deep-merge": {
@@ -1317,6 +1319,66 @@
         "@jridgewell/sourcemap-codec": "^1.4.14"
       }
     },
+    "node_modules/@lancedb/lancedb-darwin-arm64": {
+      "version": "0.4.3",
+      "resolved": "https://registry.npmjs.org/@lancedb/lancedb-darwin-arm64/-/lancedb-darwin-arm64-0.4.3.tgz",
+      "integrity": "sha512-+kxuWUK9vtLBbjFMkIKeQ32kxK2tgvZRCQaU1I3RJ3+dLmDIVeIj+KJSlMelkKa2QC4JoyHQi9Ty1PdS2DojmQ==",
+      "cpu": [
+        "arm64"
+      ],
+      "optional": true,
+      "os": [
+        "darwin"
+      ],
+      "engines": {
+        "node": ">= 18"
+      }
+    },
+    "node_modules/@lancedb/lancedb-darwin-x64": {
+      "version": "0.4.3",
+      "resolved": "https://registry.npmjs.org/@lancedb/lancedb-darwin-x64/-/lancedb-darwin-x64-0.4.3.tgz",
+      "integrity": "sha512-JYvsSYxTOa/7OMojulz9h0gN2FwvypG/6l6dpLkViZ5LDvRcfVyDTzOLcOJkFn+db4TKeBOVyMWnnpDKaB+jLA==",
+      "cpu": [
+        "x64"
+      ],
+      "optional": true,
+      "os": [
+        "darwin"
+      ],
+      "engines": {
+        "node": ">= 18"
+      }
+    },
+    "node_modules/@lancedb/lancedb-linux-x64-gnu": {
+      "version": "0.4.3",
+      "resolved": "https://registry.npmjs.org/@lancedb/lancedb-linux-x64-gnu/-/lancedb-linux-x64-gnu-0.4.3.tgz",
+      "integrity": "sha512-jDANHchWNGmu1wfAyBk0apoFlLxtJ7FRc31pAQ3tKE4fwlgG7bUcaTX6s5C3vMNWXnyQLQtVuWZNXi2nVj879g==",
+      "cpu": [
+        "x64"
+      ],
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">= 18"
+      }
+    },
+    "node_modules/@lancedb/lancedb-win32-x64-msvc": {
+      "version": "0.4.3",
+      "resolved": "https://registry.npmjs.org/@lancedb/lancedb-win32-x64-msvc/-/lancedb-win32-x64-msvc-0.4.3.tgz",
+      "integrity": "sha512-qADveXyv4YzllIbOOq8soqFfL7p7I35uhrD3PcTvj4Qxuo6q7pgQWQz2Mt3kGBpyPkH2yE4wWAGJhayShLRbiQ==",
+      "cpu": [
+        "x64"
+      ],
+      "optional": true,
+      "os": [
+        "win32"
+      ],
+      "engines": {
+        "node": ">= 18"
+      }
+    },
     "node_modules/@napi-rs/cli": {
       "version": "2.18.0",
       "resolved": "https://registry.npmjs.org/@napi-rs/cli/-/cli-2.18.0.tgz",
@@ -1396,7 +1458,6 @@
       "version": "0.5.6",
       "resolved": "https://registry.npmjs.org/@swc/helpers/-/helpers-0.5.6.tgz",
       "integrity": "sha512-aYX01Ke9hunpoCexYAgQucEpARGQ5w/cqHFrIR+e9gdKb1QWTsVJuTJ2ozQzIAxLyRQe/m+2RqzkyOOGiMKRQA==",
-      "peer": true,
       "dependencies": {
         "tslib": "^2.4.0"
       }
@@ -1445,8 +1506,7 @@
     "node_modules/@types/command-line-args": {
       "version": "5.2.3",
       "resolved": "https://registry.npmjs.org/@types/command-line-args/-/command-line-args-5.2.3.tgz",
-      "integrity": "sha512-uv0aG6R0Y8WHZLTamZwtfsDLVRnOa+n+n5rEvFWL5Na5gZ8V2Teab/duDPFzIIIhs9qizDpcavCusCLJZu62Kw==",
-      "peer": true
+      "integrity": "sha512-uv0aG6R0Y8WHZLTamZwtfsDLVRnOa+n+n5rEvFWL5Na5gZ8V2Teab/duDPFzIIIhs9qizDpcavCusCLJZu62Kw=="
     },
     "node_modules/@types/command-line-usage": {
       "version": "5.0.2",
@@ -1514,7 +1574,6 @@
       "version": "2.6.11",
       "resolved": "https://registry.npmjs.org/@types/node-fetch/-/node-fetch-2.6.11.tgz",
       "integrity": "sha512-24xFj9R5+rfQJLRyM56qh+wnVSYhyXC2tkoBndtY0U+vubqNsYXGjufB2nn8Q6gt0LrARwL6UBtMCSVCwl4B1g==",
-      "optional": true,
       "dependencies": {
         "@types/node": "*",
         "form-data": "^4.0.0"
@@ -1783,7 +1842,6 @@
       "version": "3.0.0",
       "resolved": "https://registry.npmjs.org/abort-controller/-/abort-controller-3.0.0.tgz",
       "integrity": "sha512-h8lQ8tacZYnR3vNQTgibj+tODHI5/+l06Au2Pcriv/Gmet0eaj4TwWH41sO9wnHDiQsEj19q0drzdWdeAHtweg==",
-      "optional": true,
       "dependencies": {
         "event-target-shim": "^5.0.0"
       },
@@ -1816,7 +1874,6 @@
       "version": "4.5.0",
       "resolved": "https://registry.npmjs.org/agentkeepalive/-/agentkeepalive-4.5.0.tgz",
       "integrity": "sha512-5GG/5IbQQpC9FpkRGsSvZI5QYeSCzlJHdpBQntCsuTOxhKD8lqKhrleg2Yi7yvMIf82Ycmmqln9U8V9qwEiJew==",
-      "optional": true,
       "dependencies": {
         "humanize-ms": "^1.2.1"
       },
@@ -1913,7 +1970,6 @@
       "version": "15.0.0",
       "resolved": "https://registry.npmjs.org/apache-arrow/-/apache-arrow-15.0.0.tgz",
       "integrity": "sha512-e6aunxNKM+woQf137ny3tp/xbLjFJS2oGQxQhYGqW6dGeIwNV1jOeEAeR6sS2jwAI2qLO83gYIP2MBz02Gw5Xw==",
-      "peer": true,
       "dependencies": {
         "@swc/helpers": "^0.5.2",
         "@types/command-line-args": "^5.2.1",
@@ -2001,8 +2057,7 @@
     "node_modules/asynckit": {
       "version": "0.4.0",
       "resolved": "https://registry.npmjs.org/asynckit/-/asynckit-0.4.0.tgz",
-      "integrity": "sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q==",
-      "optional": true
+      "integrity": "sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q=="
     },
     "node_modules/babel-jest": {
       "version": "29.7.0",
@@ -2129,8 +2184,7 @@
     "node_modules/base-64": {
       "version": "0.1.0",
       "resolved": "https://registry.npmjs.org/base-64/-/base-64-0.1.0.tgz",
-      "integrity": "sha512-Y5gU45svrR5tI2Vt/X9GPd3L0HNIKzGu202EjxrXMpuc2V2CiKgemAbUUsqYmZJvPtCXoUKjNZwBJzsNScUbXA==",
-      "optional": true
+      "integrity": "sha512-Y5gU45svrR5tI2Vt/X9GPd3L0HNIKzGu202EjxrXMpuc2V2CiKgemAbUUsqYmZJvPtCXoUKjNZwBJzsNScUbXA=="
     },
     "node_modules/brace-expansion": {
       "version": "1.1.11",
@@ -2296,7 +2350,6 @@
       "version": "0.0.2",
       "resolved": "https://registry.npmjs.org/charenc/-/charenc-0.0.2.tgz",
       "integrity": "sha512-yrLQ/yVUFXkzg7EDQsPieE/53+0RlaWTs+wBrvW36cyilJ2SaDWfl4Yj7MtLTXleV9uEKefbAGUPv2/iWSooRA==",
-      "optional": true,
       "engines": {
         "node": "*"
       }
@@ -2357,7 +2410,6 @@
       "version": "1.0.8",
       "resolved": "https://registry.npmjs.org/combined-stream/-/combined-stream-1.0.8.tgz",
       "integrity": "sha512-FQN4MRfuJeHf7cBbBMJFXhKSDq+2kAArBlmRBvcvFE5BB1HZKXtSFASDhdlz9zOYwxh8lDdnvmMOe/+5cdoEdg==",
-      "optional": true,
       "dependencies": {
         "delayed-stream": "~1.0.0"
       },
@@ -2469,7 +2521,6 @@
       "version": "0.0.2",
       "resolved": "https://registry.npmjs.org/crypt/-/crypt-0.0.2.tgz",
       "integrity": "sha512-mCxBlsHFYh9C+HVpiEacem8FEBnMXgU9gy4zmNC+SXAZNB/1idgp/aulFJ4FgCi7GPEVbfyng092GqL2k2rmow==",
-      "optional": true,
       "engines": {
         "node": "*"
       }
@@ -2530,7 +2581,6 @@
       "version": "1.0.0",
       "resolved": "https://registry.npmjs.org/delayed-stream/-/delayed-stream-1.0.0.tgz",
       "integrity": "sha512-ZySD7Nf91aLB0RxL4KGrKHBXl7Eds1DAmEdcoVawXnLD7SDhpNgtuII2aAkg7a7QS41jxPSZ17p4VdGnMHk3MQ==",
-      "optional": true,
       "engines": {
         "node": ">=0.4.0"
       }
@@ -2557,7 +2607,6 @@
       "version": "1.3.0",
       "resolved": "https://registry.npmjs.org/digest-fetch/-/digest-fetch-1.3.0.tgz",
       "integrity": "sha512-CGJuv6iKNM7QyZlM2T3sPAdZWd/p9zQiRNS9G+9COUCwzWFTs0Xp8NF5iePx7wtvhDykReiRRrSeNb4oMmB8lA==",
-      "optional": true,
       "dependencies": {
         "base-64": "^0.1.0",
         "md5": "^2.3.0"
@@ -2862,7 +2911,6 @@
       "version": "5.0.1",
       "resolved": "https://registry.npmjs.org/event-target-shim/-/event-target-shim-5.0.1.tgz",
       "integrity": "sha512-i/2XbnSz/uxRCU6+NdVJgKWDTM427+MqYbkQzD321DuCQJUqOuJKIA0IM2+W2xtYHdKOmZ4dR6fExsd4SXL+WQ==",
-      "optional": true,
       "engines": {
         "node": ">=6"
       }
@@ -3024,7 +3072,6 @@
       "version": "4.0.0",
       "resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.0.tgz",
       "integrity": "sha512-ETEklSGi5t0QMZuiXoA/Q6vcnxcLQP5vdugSpuAyi6SVGi2clPPp+xgEhuMaHC+zGgn31Kd235W35f7Hykkaww==",
-      "optional": true,
       "dependencies": {
         "asynckit": "^0.4.0",
         "combined-stream": "^1.0.8",
@@ -3037,14 +3084,12 @@
     "node_modules/form-data-encoder": {
       "version": "1.7.2",
       "resolved": "https://registry.npmjs.org/form-data-encoder/-/form-data-encoder-1.7.2.tgz",
-      "integrity": "sha512-qfqtYan3rxrnCk1VYaA4H+Ms9xdpPqvLZa6xmMgFvhO32x7/3J/ExcTd6qpxM0vH2GdMI+poehyBZvqfMTto8A==",
-      "optional": true
+      "integrity": "sha512-qfqtYan3rxrnCk1VYaA4H+Ms9xdpPqvLZa6xmMgFvhO32x7/3J/ExcTd6qpxM0vH2GdMI+poehyBZvqfMTto8A=="
     },
     "node_modules/formdata-node": {
       "version": "4.4.1",
       "resolved": "https://registry.npmjs.org/formdata-node/-/formdata-node-4.4.1.tgz",
       "integrity": "sha512-0iirZp3uVDjVGt9p49aTaqjk84TrglENEDuqfdlZQ1roC9CWlPk6Avf8EEnZNcAqPonwkG35x4n3ww/1THYAeQ==",
-      "optional": true,
       "dependencies": {
         "node-domexception": "1.0.0",
         "web-streams-polyfill": "4.0.0-beta.3"
@@ -3057,7 +3102,6 @@
       "version": "4.0.0-beta.3",
       "resolved": "https://registry.npmjs.org/web-streams-polyfill/-/web-streams-polyfill-4.0.0-beta.3.tgz",
       "integrity": "sha512-QW95TCTaHmsYfHDybGMwO5IJIM93I/6vTRk+daHTWFPhwh+C8Cg7j7XyKrwrj8Ib6vYXe0ocYNrmzY4xAAN6ug==",
-      "optional": true,
       "engines": {
         "node": ">= 14"
       }
@@ -3272,7 +3316,6 @@
       "version": "1.2.1",
       "resolved": "https://registry.npmjs.org/humanize-ms/-/humanize-ms-1.2.1.tgz",
       "integrity": "sha512-Fl70vYtsAFb/C06PTS9dZBo7ihau+Tu/DNCk/OyHhea07S+aeMWpFFkUaXRa8fI+ScZbEI8dfSxwY7gxZ9SAVQ==",
-      "optional": true,
       "dependencies": {
         "ms": "^2.0.0"
       }
@@ -3355,6 +3398,15 @@
       "integrity": "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ==",
       "dev": true
     },
+    "node_modules/interpret": {
+      "version": "1.4.0",
+      "resolved": "https://registry.npmjs.org/interpret/-/interpret-1.4.0.tgz",
+      "integrity": "sha512-agE4QfB2Lkp9uICn7BAqoscw4SZP9kTE2hxiFI3jBPmXJfdqiahTbUuKGsMoN2GtqL9AxhYioAcVvgsb1HvRbA==",
+      "dev": true,
+      "engines": {
+        "node": ">= 0.10"
+      }
+    },
     "node_modules/is-arrayish": {
       "version": "0.2.1",
       "resolved": "https://registry.npmjs.org/is-arrayish/-/is-arrayish-0.2.1.tgz",
@@ -3364,8 +3416,7 @@
     "node_modules/is-buffer": {
       "version": "1.1.6",
       "resolved": "https://registry.npmjs.org/is-buffer/-/is-buffer-1.1.6.tgz",
-      "integrity": "sha512-NcdALwpXkTm5Zvvbk7owOUSvVvBKDgKP5/ewfXEznmQFfs4ZRmanOeKBTjRVjka3QFoN6XJ+9F3USqfHqTaU5w==",
-      "optional": true
+      "integrity": "sha512-NcdALwpXkTm5Zvvbk7owOUSvVvBKDgKP5/ewfXEznmQFfs4ZRmanOeKBTjRVjka3QFoN6XJ+9F3USqfHqTaU5w=="
     },
     "node_modules/is-builtin-module": {
       "version": "3.2.1",
@@ -4458,7 +4509,6 @@
       "version": "2.3.0",
       "resolved": "https://registry.npmjs.org/md5/-/md5-2.3.0.tgz",
       "integrity": "sha512-T1GITYmFaKuO91vxyoQMFETst+O71VUPEU3ze5GNzDm0OWdP8v1ziTaAEPUr/3kLsY3Sftgz242A1SetQiDL7g==",
-      "optional": true,
       "dependencies": {
         "charenc": "0.0.2",
         "crypt": "0.0.2",
@@ -4497,7 +4547,6 @@
       "version": "1.52.0",
       "resolved": "https://registry.npmjs.org/mime-db/-/mime-db-1.52.0.tgz",
       "integrity": "sha512-sPU4uV7dYlvtWJxwwxHD0PuihVNiE7TyAbQ5SWxDCB9mUYvOgroQOwYQQOKPJ8CIbE+1ETVlOoK1UC2nU3gYvg==",
-      "optional": true,
       "engines": {
         "node": ">= 0.6"
       }
@@ -4506,7 +4555,6 @@
       "version": "2.1.35",
       "resolved": "https://registry.npmjs.org/mime-types/-/mime-types-2.1.35.tgz",
       "integrity": "sha512-ZDY+bPm5zTTF+YpCrAU9nK0UgICYPT0QtT1NZWFv4s++TNkcgVaT0g6+4R2uI4MjQjzysHB1zxuWL50hzaeXiw==",
-      "optional": true,
       "dependencies": {
         "mime-db": "1.52.0"
       },
@@ -4538,8 +4586,7 @@
     "node_modules/ms": {
       "version": "2.1.3",
       "resolved": "https://registry.npmjs.org/ms/-/ms-2.1.3.tgz",
-      "integrity": "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA==",
-      "optional": true
+      "integrity": "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA=="
     },
     "node_modules/natural-compare": {
       "version": "1.4.0",
@@ -4567,7 +4614,6 @@
           "url": "https://paypal.me/jimmywarting"
         }
       ],
-      "optional": true,
       "engines": {
         "node": ">=10.5.0"
       }
@@ -4576,7 +4622,6 @@
       "version": "2.7.0",
       "resolved": "https://registry.npmjs.org/node-fetch/-/node-fetch-2.7.0.tgz",
       "integrity": "sha512-c4FRfUm/dbcWZ7U+1Wq0AwCyFL+3nt2bEw05wfxSz+DWpWsitgmSgYmy2dQdWyKC1694ELPqMs/YzUSNozLt8A==",
-      "optional": true,
       "dependencies": {
         "whatwg-url": "^5.0.0"
       },
@@ -4623,10 +4668,9 @@
       }
     },
     "node_modules/openai": {
-      "version": "4.28.4",
-      "resolved": "https://registry.npmjs.org/openai/-/openai-4.28.4.tgz",
-      "integrity": "sha512-RNIwx4MT/F0zyizGcwS+bXKLzJ8QE9IOyigDG/ttnwB220d58bYjYFp0qjvGwEFBO6+pvFVIDABZPGDl46RFsg==",
-      "optional": true,
+      "version": "4.29.2",
+      "resolved": "https://registry.npmjs.org/openai/-/openai-4.29.2.tgz",
+      "integrity": "sha512-cPkT6zjEcE4qU5OW/SoDDuXEsdOLrXlAORhzmaguj5xZSPlgKvLhi27sFWhLKj07Y6WKNWxcwIbzm512FzTBNQ==",
       "dependencies": {
         "@types/node": "^18.11.18",
         "@types/node-fetch": "^2.6.4",
@@ -4643,10 +4687,9 @@
       }
     },
     "node_modules/openai/node_modules/@types/node": {
-      "version": "18.19.20",
-      "resolved": "https://registry.npmjs.org/@types/node/-/node-18.19.20.tgz",
-      "integrity": "sha512-SKXZvI375jkpvAj8o+5U2518XQv76mAsixqfXiVyWyXZbVWQK25RurFovYpVIxVzul0rZoH58V/3SkEnm7s3qA==",
-      "optional": true,
+      "version": "18.19.26",
+      "resolved": "https://registry.npmjs.org/@types/node/-/node-18.19.26.tgz",
+      "integrity": "sha512-+wiMJsIwLOYCvUqSdKTrfkS8mpTp+MPINe6+Np4TAGFWWRWiBQ5kSq9nZGCSPkzx9mvT+uEukzpX4MOSCydcvw==",
       "dependencies": {
         "undici-types": "~5.26.4"
       }
@@ -4996,6 +5039,18 @@
       "integrity": "sha512-xWGDIW6x921xtzPkhiULtthJHoJvBbF3q26fzloPCK0hsvxtPVelvftw3zjbHWSkR2km9Z+4uxbDDK/6Zw9B8w==",
       "dev": true
     },
+    "node_modules/rechoir": {
+      "version": "0.6.2",
+      "resolved": "https://registry.npmjs.org/rechoir/-/rechoir-0.6.2.tgz",
+      "integrity": "sha512-HFM8rkZ+i3zrV+4LQjwQ0W+ez98pApMGM3HUrN04j3CqzPOzl9nmP15Y8YXNm8QHGv/eacOVEjqhmWpkRV0NAw==",
+      "dev": true,
+      "dependencies": {
+        "resolve": "^1.1.6"
+      },
+      "engines": {
+        "node": ">= 0.10"
+      }
+    },
     "node_modules/repeat-string": {
       "version": "1.6.1",
       "resolved": "https://registry.npmjs.org/repeat-string/-/repeat-string-1.6.1.tgz",
@@ -5145,6 +5200,23 @@
         "node": ">=8"
       }
     },
+    "node_modules/shelljs": {
+      "version": "0.8.5",
+      "resolved": "https://registry.npmjs.org/shelljs/-/shelljs-0.8.5.tgz",
+      "integrity": "sha512-TiwcRcrkhHvbrZbnRcFYMLl30Dfov3HKqzp5tO5b4pt6G/SezKcYhmDg15zXVBswHmctSAQKznqNW2LO5tTDow==",
+      "dev": true,
+      "dependencies": {
+        "glob": "^7.0.0",
+        "interpret": "^1.0.0",
+        "rechoir": "^0.6.2"
+      },
+      "bin": {
+        "shjs": "bin/shjs"
+      },
+      "engines": {
+        "node": ">=4"
+      }
+    },
     "node_modules/shiki": {
       "version": "0.14.7",
       "resolved": "https://registry.npmjs.org/shiki/-/shiki-0.14.7.tgz",
@@ -5157,6 +5229,22 @@
         "vscode-textmate": "^8.0.0"
       }
     },
+    "node_modules/shx": {
+      "version": "0.3.4",
+      "resolved": "https://registry.npmjs.org/shx/-/shx-0.3.4.tgz",
+      "integrity": "sha512-N6A9MLVqjxZYcVn8hLmtneQWIJtp8IKzMP4eMnx+nqkvXoqinUPCbUFLp2UcWTEIUONhlk0ewxr/jaVGlc+J+g==",
+      "dev": true,
+      "dependencies": {
+        "minimist": "^1.2.3",
+        "shelljs": "^0.8.5"
+      },
+      "bin": {
+        "shx": "lib/cli.js"
+      },
+      "engines": {
+        "node": ">=6"
+      }
+    },
     "node_modules/signal-exit": {
       "version": "3.0.7",
       "resolved": "https://registry.npmjs.org/signal-exit/-/signal-exit-3.0.7.tgz",
@@ -5432,8 +5520,7 @@
     "node_modules/tr46": {
       "version": "0.0.3",
       "resolved": "https://registry.npmjs.org/tr46/-/tr46-0.0.3.tgz",
-      "integrity": "sha512-N3WMsuqV66lT30CrXNbEjx4GEwlow3v6rr4mCcv6prnfwhS01rkgyFdjPNBYd9br7LpXV1+Emh01fHnq2Gdgrw==",
-      "optional": true
+      "integrity": "sha512-N3WMsuqV66lT30CrXNbEjx4GEwlow3v6rr4mCcv6prnfwhS01rkgyFdjPNBYd9br7LpXV1+Emh01fHnq2Gdgrw=="
     },
     "node_modules/ts-api-utils": {
       "version": "1.0.3",
@@ -5929,7 +6016,6 @@
       "version": "3.3.3",
       "resolved": "https://registry.npmjs.org/web-streams-polyfill/-/web-streams-polyfill-3.3.3.tgz",
       "integrity": "sha512-d2JWLCivmZYTSIoge9MsgFCZrt571BikcWGYkjC1khllbTeDlGqZ2D8vD8E/lJa8WGWbb7Plm8/XJYV7IJHZZw==",
-      "optional": true,
       "engines": {
         "node": ">= 8"
       }
@@ -5937,14 +6023,12 @@
     "node_modules/webidl-conversions": {
       "version": "3.0.1",
       "resolved": "https://registry.npmjs.org/webidl-conversions/-/webidl-conversions-3.0.1.tgz",
-      "integrity": "sha512-2JAn3z8AR6rjK8Sm8orRC0h/bcl/DqL7tRPdGZ4I1CjdF+EaMLmYxBHyXuKL849eucPFhvBoxMsflfOb8kxaeQ==",
-      "optional": true
+      "integrity": "sha512-2JAn3z8AR6rjK8Sm8orRC0h/bcl/DqL7tRPdGZ4I1CjdF+EaMLmYxBHyXuKL849eucPFhvBoxMsflfOb8kxaeQ=="
     },
     "node_modules/whatwg-url": {
       "version": "5.0.0",
       "resolved": "https://registry.npmjs.org/whatwg-url/-/whatwg-url-5.0.0.tgz",
       "integrity": "sha512-saE57nupxk6v3HY35+jzBwYa0rKSy0XR8JSxZPwgLr7ys0IBzhGviA1/TUGJLmSVqs8pb9AnvICXEuOHLprYTw==",
-      "optional": true,
       "dependencies": {
         "tr46": "~0.0.3",
         "webidl-conversions": "^3.0.0"

nodejs/package.json

@@ -1,17 +1,18 @@
 {
-  "name": "lancedb",
-  "version": "0.4.3",
+  "name": "@lancedb/lancedb",
+  "version": "0.4.15",
   "main": "./dist/index.js",
   "types": "./dist/index.d.ts",
   "napi": {
-    "name": "lancedb-nodejs",
+    "name": "lancedb",
     "triples": {
       "defaults": false,
       "additional": [
         "aarch64-apple-darwin",
         "aarch64-unknown-linux-gnu",
         "x86_64-apple-darwin",
-        "x86_64-unknown-linux-gnu"
+        "x86_64-unknown-linux-gnu",
+        "x86_64-pc-windows-msvc"
       ]
     }
   },
@@ -28,6 +29,7 @@
     "eslint-plugin-jsdoc": "^48.2.1",
     "jest": "^29.7.0",
     "prettier": "^3.1.0",
+    "shx": "^0.3.4",
     "tmp": "^0.2.3",
     "ts-jest": "^29.1.2",
     "typedoc": "^0.25.7",
@@ -48,15 +50,16 @@
   "os": [
     "darwin",
     "linux",
-    "windows"
+    "win32"
   ],
   "scripts": {
     "artifacts": "napi artifacts",
-    "build:native": "napi build --platform --release --js lancedb/native.js --dts lancedb/native.d.ts dist/",
     "build:debug": "napi build --platform --dts ../lancedb/native.d.ts --js ../lancedb/native.js dist/",
-    "build": "npm run build:debug && tsc -b",
+    "build:release": "napi build --platform --release --dts ../lancedb/native.d.ts --js ../lancedb/native.js dist/",
+    "build": "npm run build:debug && tsc -b && shx cp lancedb/native.d.ts dist/native.d.ts",
+    "build-release": "npm run build:release && tsc -b && shx cp lancedb/native.d.ts dist/native.d.ts",
     "chkformat": "prettier . --check",
-    "docs": "typedoc --plugin typedoc-plugin-markdown lancedb/index.ts",
+    "docs": "typedoc --plugin typedoc-plugin-markdown --out ../docs/src/js lancedb/index.ts",
     "lint": "eslint lancedb && eslint __test__",
     "prepublishOnly": "napi prepublish -t npm",
     "test": "npm run build && jest --verbose",
@@ -64,13 +67,14 @@
     "version": "napi version"
   },
   "optionalDependencies": {
-    "lancedb-darwin-arm64": "0.4.3",
-    "lancedb-darwin-x64": "0.4.3",
-    "lancedb-linux-arm64-gnu": "0.4.3",
-    "lancedb-linux-x64-gnu": "0.4.3",
-    "openai": "^4.28.4"
+    "@lancedb/lancedb-darwin-arm64": "0.4.15",
+    "@lancedb/lancedb-darwin-x64": "0.4.15",
+    "@lancedb/lancedb-linux-arm64-gnu": "0.4.15",
+    "@lancedb/lancedb-linux-x64-gnu": "0.4.15",
+    "@lancedb/lancedb-win32-x64-msvc": "0.4.15"
   },
-  "peerDependencies": {
+  "dependencies": {
+    "openai": "^4.29.2",
     "apache-arrow": "^15.0.0"
   }
 }

nodejs/typedoc.json

@@ -0,0 +1,10 @@
+{
+  "intentionallyNotExported": [
+    "lancedb/native.d.ts:Connection",
+    "lancedb/native.d.ts:Index",
+    "lancedb/native.d.ts:Query",
+    "lancedb/native.d.ts:VectorQuery",
+    "lancedb/native.d.ts:RecordBatchIterator",
+    "lancedb/native.d.ts:Table"
+  ]
+}

python/.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.6.5
+current_version = 0.6.6
 commit = True
 message = [python] Bump version: {current_version} → {new_version}
 tag = True

python/pyproject.toml

@@ -1,9 +1,9 @@
 [project]
 name = "lancedb"
-version = "0.6.5"
+version = "0.6.6"
 dependencies = [
     "deprecation",
-    "pylance==0.10.5",
+    "pylance==0.10.6",
     "ratelimiter~=1.0",
     "retry>=0.9.2",
     "tqdm>=4.27.0",

python/python/lancedb/__init__.py

@@ -145,34 +145,20 @@ async def connect_async(
         the last check, then the table will be checked for updates. Note: this
         consistency only applies to read operations. Write operations are
         always consistent.
-    request_thread_pool: int or ThreadPoolExecutor, optional
-        The thread pool to use for making batch requests to the LanceDB Cloud API.
-        If an integer, then a ThreadPoolExecutor will be created with that
-        number of threads. If None, then a ThreadPoolExecutor will be created
-        with the default number of threads. If a ThreadPoolExecutor, then that
-        executor will be used for making requests. This is for LanceDB Cloud
-        only and is only used when making batch requests (i.e., passing in
-        multiple queries to the search method at once).
 
     Examples
     --------
 
-    For a local directory, provide a path for the database:
-
     >>> import lancedb
-    >>> db = lancedb.connect("~/.lancedb")
-
-    For object storage, use a URI prefix:
-
-    >>> db = lancedb.connect("s3://my-bucket/lancedb")
-
-    Connect to LancdDB cloud:
-
-    >>> db = lancedb.connect("db://my_database", api_key="ldb_...")
+    >>> async def doctest_example():
+    ...     # For a local directory, provide a path to the database
+    ...     db = await lancedb.connect_async("~/.lancedb")
+    ...     # For object storage, use a URI prefix
+    ...     db = await lancedb.connect_async("s3://my-bucket/lancedb")
 
     Returns
     -------
-    conn : DBConnection
+    conn : AsyncConnection
         A connection to a LanceDB database.
     """
     if read_consistency_interval is not None:

python/python/lancedb/db.py

@@ -25,13 +25,18 @@ from overrides import EnforceOverrides, override
 from pyarrow import fs
 
 from lancedb.common import data_to_reader, validate_schema
-from lancedb.embeddings.registry import EmbeddingFunctionRegistry
 from lancedb.utils.events import register_event
 
 from ._lancedb import connect as lancedb_connect
 from .pydantic import LanceModel
 from .table import AsyncTable, LanceTable, Table, _sanitize_data
-from .util import fs_from_uri, get_uri_location, get_uri_scheme, join_uri
+from .util import (
+    fs_from_uri,
+    get_uri_location,
+    get_uri_scheme,
+    join_uri,
+    validate_table_name,
+)
 
 if TYPE_CHECKING:
     from datetime import timedelta
@@ -387,6 +392,7 @@ class LanceDBConnection(DBConnection):
         """
         if mode.lower() not in ["create", "overwrite"]:
             raise ValueError("mode must be either 'create' or 'overwrite'")
+        validate_table_name(name)
 
         tbl = LanceTable.create(
             self,
@@ -444,16 +450,17 @@ class LanceDBConnection(DBConnection):
 class AsyncConnection(object):
     """An active LanceDB connection
 
-    To obtain a connection you can use the [connect] function.
+    To obtain a connection you can use the [connect_async][lancedb.connect_async]
+    function.
 
     This could be a native connection (using lance) or a remote connection (e.g. for
     connecting to LanceDb Cloud)
 
     Local connections do not currently hold any open resources but they may do so in the
     future (for example, for shared cache or connections to catalog services) Remote
-    connections represent an open connection to the remote server.  The [close] method
-    can be used to release any underlying resources eagerly.  The connection can also
-    be used as a context manager:
+    connections represent an open connection to the remote server.  The
+    [close][lancedb.db.AsyncConnection.close] method can be used to release any
+    underlying resources eagerly.  The connection can also be used as a context manager.
 
     Connections can be shared on multiple threads and are expected to be long lived.
     Connections can also be used as a context manager, however, in many cases a single
@@ -464,10 +471,9 @@ class AsyncConnection(object):
     Examples
     --------
 
-    >>> import asyncio
     >>> import lancedb
-    >>> async def my_connect():
-    ...   with await lancedb.connect("/tmp/my_dataset") as conn:
+    >>> async def doctest_example():
+    ...   with await lancedb.connect_async("/tmp/my_dataset") as conn:
     ...     # do something with the connection
     ...     pass
     ...   # conn is closed here
@@ -528,9 +534,8 @@ class AsyncConnection(object):
         exist_ok: Optional[bool] = None,
         on_bad_vectors: Optional[str] = None,
         fill_value: Optional[float] = None,
-        embedding_functions: Optional[List[EmbeddingFunctionConfig]] = None,
     ) -> AsyncTable:
-        """Create a [Table][lancedb.table.Table] in the database.
+        """Create an [AsyncTable][lancedb.table.AsyncTable] in the database.
 
         Parameters
         ----------
@@ -569,7 +574,7 @@ class AsyncConnection(object):
 
         Returns
         -------
-        LanceTable
+        AsyncTable
             A reference to the newly created table.
 
         !!! note
@@ -583,12 +588,14 @@ class AsyncConnection(object):
         Can create with list of tuples or dictionaries:
 
         >>> import lancedb
-        >>> db = lancedb.connect("./.lancedb")
-        >>> 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)
-        LanceTable(connection=..., name="my_table")
-        >>> db["my_table"].head()
+        >>> async def doctest_example():
+        ...     db = await lancedb.connect_async("./.lancedb")
+        ...     data = [{"vector": [1.1, 1.2], "lat": 45.5, "long": -122.7},
+        ...             {"vector": [0.2, 1.8], "lat": 40.1, "long":  -74.1}]
+        ...     my_table = await db.create_table("my_table", data)
+        ...     print(await my_table.query().limit(5).to_arrow())
+        >>> import asyncio
+        >>> asyncio.run(doctest_example())
         pyarrow.Table
         vector: fixed_size_list<item: float>[2]
           child 0, item: float
@@ -607,9 +614,11 @@ class AsyncConnection(object):
         ...    "lat": [45.5, 40.1],
         ...    "long": [-122.7, -74.1]
         ... })
-        >>> db.create_table("table2", data)
-        LanceTable(connection=..., name="table2")
-        >>> db["table2"].head()
+        >>> async def pandas_example():
+        ...     db = await lancedb.connect_async("./.lancedb")
+        ...     my_table = await db.create_table("table2", data)
+        ...     print(await my_table.query().limit(5).to_arrow())
+        >>> asyncio.run(pandas_example())
         pyarrow.Table
         vector: fixed_size_list<item: float>[2]
           child 0, item: float
@@ -629,9 +638,11 @@ class AsyncConnection(object):
         ...   pa.field("lat", pa.float32()),
         ...   pa.field("long", pa.float32())
         ... ])
-        >>> db.create_table("table3", data, schema = custom_schema)
-        LanceTable(connection=..., name="table3")
-        >>> db["table3"].head()
+        >>> async def with_schema():
+        ...     db = await lancedb.connect_async("./.lancedb")
+        ...     my_table = await db.create_table("table3", data, schema = custom_schema)
+        ...     print(await my_table.query().limit(5).to_arrow())
+        >>> asyncio.run(with_schema())
         pyarrow.Table
         vector: fixed_size_list<item: float>[2]
           child 0, item: float
@@ -663,9 +674,10 @@ class AsyncConnection(object):
         ...     pa.field("item", pa.utf8()),
         ...     pa.field("price", pa.float32()),
         ... ])
-        >>> db.create_table("table4", make_batches(), schema=schema)
-        LanceTable(connection=..., name="table4")
-
+        >>> async def iterable_example():
+        ...     db = await lancedb.connect_async("./.lancedb")
+        ...     await db.create_table("table4", make_batches(), schema=schema)
+        >>> asyncio.run(iterable_example())
         """
         if inspect.isclass(schema) and issubclass(schema, LanceModel):
             # convert LanceModel to pyarrow schema
@@ -674,12 +686,6 @@ class AsyncConnection(object):
             schema = schema.to_arrow_schema()
 
         metadata = None
-        if embedding_functions is not None:
-            # If we passed in embedding functions explicitly
-            # then we'll override any schema metadata that
-            # may was implicitly specified by the LanceModel schema
-            registry = EmbeddingFunctionRegistry.get_instance()
-            metadata = registry.get_table_metadata(embedding_functions)
 
         # Defining defaults here and not in function prototype.  In the future
         # these defaults will move into rust so better to keep them as None.
@@ -760,11 +766,11 @@ class AsyncConnection(object):
         name: str
             The name of the table.
         """
-        raise NotImplementedError
+        await self._inner.drop_table(name)
 
     async def drop_database(self):
         """
         Drop database
         This is the same thing as dropping all the tables
         """
-        raise NotImplementedError
+        await self._inner.drop_db()

python/python/lancedb/query.py

@@ -1033,7 +1033,7 @@ class AsyncQueryBase(object):
         Construct an AsyncQueryBase
 
         This method is not intended to be called directly.  Instead, use the
-        [Table.query][] method to create a query.
+        [AsyncTable.query][lancedb.table.AsyncTable.query] method to create a query.
         """
         self._inner = inner
 
@@ -1041,7 +1041,10 @@ class AsyncQueryBase(object):
         """
         Only return rows matching the given predicate
 
-        The predicate should be supplied as an SQL query string.  For example:
+        The predicate should be supplied as an SQL query string.
+
+        Examples
+        --------
 
         >>> predicate = "x > 10"
         >>> predicate = "y > 0 AND y < 100"
@@ -1112,7 +1115,8 @@ class AsyncQueryBase(object):
         Execute the query and collect the results into an Apache Arrow Table.
 
         This method will collect all results into memory before returning.  If
-        you expect a large number of results, you may want to use [to_batches][]
+        you expect a large number of results, you may want to use
+        [to_batches][lancedb.query.AsyncQueryBase.to_batches]
         """
         batch_iter = await self.to_batches()
         return pa.Table.from_batches(
@@ -1123,12 +1127,13 @@ class AsyncQueryBase(object):
         """
         Execute the query and collect the results into a pandas DataFrame.
 
-        This method will collect all results into memory before returning.  If
-        you expect a large number of results, you may want to use [to_batches][]
-        and convert each batch to pandas separately.
+        This method will collect all results into memory before returning.  If you
+        expect a large number of results, you may want to use
+        [to_batches][lancedb.query.AsyncQueryBase.to_batches] and convert each batch to
+        pandas separately.
 
-        Example
-        -------
+        Examples
+        --------
 
         >>> import asyncio
         >>> from lancedb import connect_async
@@ -1148,7 +1153,7 @@ class AsyncQuery(AsyncQueryBase):
         Construct an AsyncQuery
 
         This method is not intended to be called directly.  Instead, use the
-        [Table.query][] method to create a query.
+        [AsyncTable.query][lancedb.table.AsyncTable.query] method to create a query.
         """
         super().__init__(inner)
         self._inner = inner
@@ -1189,8 +1194,8 @@ class AsyncQuery(AsyncQueryBase):
         If there is only one vector column (a column whose data type is a
         fixed size list of floats) then the column does not need to be specified.
         If there is more than one vector column you must use
-        [AsyncVectorQuery::column][] to specify which column you would like to
-        compare with.
+        [AsyncVectorQuery.column][lancedb.query.AsyncVectorQuery.column] to specify
+        which column you would like to compare with.
 
         If no index has been created on the vector column then a vector query
         will perform a distance comparison between the query vector and every
@@ -1221,8 +1226,10 @@ class AsyncVectorQuery(AsyncQueryBase):
         Construct an AsyncVectorQuery
 
         This method is not intended to be called directly.  Instead, create
-        a query first with [Table.query][] and then use [AsyncQuery.nearest_to][]
-        to convert to a vector query.
+        a query first with [AsyncTable.query][lancedb.table.AsyncTable.query] and then
+        use [AsyncQuery.nearest_to][lancedb.query.AsyncQuery.nearest_to]] to convert to
+        a vector query.  Or you can use
+        [AsyncTable.vector_search][lancedb.table.AsyncTable.vector_search]
         """
         super().__init__(inner)
         self._inner = inner
@@ -1232,7 +1239,7 @@ class AsyncVectorQuery(AsyncQueryBase):
         Set the vector column to query
 
         This controls which column is compared to the query vector supplied in
-        the call to [Query.nearest_to][].
+        the call to [AsyncQuery.nearest_to][lancedb.query.AsyncQuery.nearest_to].
 
         This parameter must be specified if the table has more than one column
         whose data type is a fixed-size-list of floats.

python/python/lancedb/remote/db.py

@@ -26,6 +26,7 @@ from ..db import DBConnection
 from ..embeddings import EmbeddingFunctionConfig
 from ..pydantic import LanceModel
 from ..table import Table, _sanitize_data
+from ..util import validate_table_name
 from .arrow import to_ipc_binary
 from .client import ARROW_STREAM_CONTENT_TYPE, RestfulLanceDBClient
 from .errors import LanceDBClientError
@@ -223,6 +224,7 @@ class RemoteDBConnection(DBConnection):
         LanceTable(table4)
 
         """
+        validate_table_name(name)
         if data is None and schema is None:
             raise ValueError("Either data or schema must be provided.")
         if embedding_functions is not None:

python/python/lancedb/rerankers/cross_encoder.py

@@ -14,7 +14,7 @@ class CrossEncoderReranker(Reranker):
 
     Parameters
     ----------
-    model : str, default "cross-encoder/ms-marco-TinyBERT-L-6"
+    model_name : str, default "cross-encoder/ms-marco-TinyBERT-L-6"
         The name of the cross encoder model to use. See the sentence transformers
         documentation for a list of available models.
     column : str, default "text"

python/python/lancedb/table.py

@@ -1893,8 +1893,8 @@ class AsyncTable:
     An AsyncTable object is expected to be long lived and reused for multiple
     operations. AsyncTable objects will cache a certain amount of index data in memory.
     This cache will be freed when the Table is garbage collected.  To eagerly free the
-    cache you can call the [close][AsyncTable.close] method.  Once the AsyncTable is
-    closed, it cannot be used for any further operations.
+    cache you can call the [close][lancedb.AsyncTable.close] method.  Once the
+    AsyncTable is closed, it cannot be used for any further operations.
 
     An AsyncTable can also be used as a context manager, and will automatically close
     when the context is exited.  Closing a table is optional.  If you do not close the
@@ -1903,13 +1903,17 @@ class AsyncTable:
     Examples
     --------
 
-    Create using [DBConnection.create_table][lancedb.DBConnection.create_table]
+    Create using [AsyncConnection.create_table][lancedb.AsyncConnection.create_table]
     (more examples in that method's documentation).
 
     >>> import lancedb
-    >>> db = lancedb.connect("./.lancedb")
-    >>> table = db.create_table("my_table", data=[{"vector": [1.1, 1.2], "b": 2}])
-    >>> table.head()
+    >>> async def create_a_table():
+    ...     db = await lancedb.connect_async("./.lancedb")
+    ...     data = [{"vector": [1.1, 1.2], "b": 2}]
+    ...     table = await db.create_table("my_table", data=data)
+    ...     print(await table.query().limit(5).to_arrow())
+    >>> import asyncio
+    >>> asyncio.run(create_a_table())
     pyarrow.Table
     vector: fixed_size_list<item: float>[2]
       child 0, item: float
@@ -1918,25 +1922,37 @@ class AsyncTable:
     vector: [[[1.1,1.2]]]
     b: [[2]]
 
-    Can append new data with [Table.add()][lancedb.table.Table.add].
+    Can append new data with [AsyncTable.add()][lancedb.table.AsyncTable.add].
 
-    >>> table.add([{"vector": [0.5, 1.3], "b": 4}])
+    >>> async def add_to_table():
+    ...     db = await lancedb.connect_async("./.lancedb")
+    ...     table = await db.open_table("my_table")
+    ...     await table.add([{"vector": [0.5, 1.3], "b": 4}])
+    >>> asyncio.run(add_to_table())
 
-    Can query the table with [Table.search][lancedb.table.Table.search].
+    Can query the table with
+    [AsyncTable.vector_search][lancedb.table.AsyncTable.vector_search].
 
-    >>> table.search([0.4, 0.4]).select(["b", "vector"]).to_pandas()
+    >>> async def search_table_for_vector():
+    ...     db = await lancedb.connect_async("./.lancedb")
+    ...     table = await db.open_table("my_table")
+    ...     results = (
+    ...       await table.vector_search([0.4, 0.4]).select(["b", "vector"]).to_pandas()
+    ...     )
+    ...     print(results)
+    >>> asyncio.run(search_table_for_vector())
        b      vector  _distance
     0  4  [0.5, 1.3]       0.82
     1  2  [1.1, 1.2]       1.13
 
     Search queries are much faster when an index is created. See
-    [Table.create_index][lancedb.table.Table.create_index].
+    [AsyncTable.create_index][lancedb.table.AsyncTable.create_index].
     """
 
     def __init__(self, table: LanceDBTable):
-        """Create a new Table object.
+        """Create a new AsyncTable object.
 
-        You should not create Table objects directly.
+        You should not create AsyncTable objects directly.
 
         Use [AsyncConnection.create_table][lancedb.AsyncConnection.create_table] and
         [AsyncConnection.open_table][lancedb.AsyncConnection.open_table] to obtain
@@ -1988,6 +2004,14 @@ class AsyncTable:
         return await self._inner.count_rows(filter)
 
     def query(self) -> AsyncQuery:
+        """
+        Returns an [AsyncQuery][lancedb.query.AsyncQuery] that can be used
+        to search the table.
+
+        Use methods on the returned query to control query behavior.  The query
+        can be executed with methods like [to_arrow][lancedb.query.AsyncQuery.to_arrow],
+        [to_pandas][lancedb.query.AsyncQuery.to_pandas] and more.
+        """
         return AsyncQuery(self._inner.query())
 
     async def to_pandas(self) -> "pd.DataFrame":
@@ -2024,20 +2048,8 @@ class AsyncTable:
 
         Parameters
         ----------
-        index: Index
-            The index to create.
-
-            LanceDb supports multiple types of indices.  See the static methods on
-            the Index class for more details.
-        column: str, default None
+        column: str
             The column to index.
-
-            When building a scalar index this must be set.
-
-            When building a vector index, this is optional.  The default will look
-            for any columns of type fixed-size-list with floating point values.  If
-            there is only one column of this type then it will be used.  Otherwise
-            an error will be returned.
         replace: bool, default True
             Whether to replace the existing index
 
@@ -2046,6 +2058,10 @@ class AsyncTable:
             that index is out of date.
 
             The default is True
+        config: Union[IvfPq, BTree], default None
+            For advanced configuration you can specify the type of index you would
+            like to create.   You can also specify index-specific parameters when
+            creating an index object.
         """
         index = None
         if config is not None:
@@ -2167,7 +2183,8 @@ class AsyncTable:
         Search the table with a given query vector.
         This is a convenience method for preparing a vector query and
         is the same thing as calling `nearestTo` on the builder returned
-        by `query`.  Seer [nearest_to][AsyncQuery.nearest_to] for more details.
+        by `query`.  Seer [nearest_to][lancedb.query.AsyncQuery.nearest_to] for more
+        details.
         """
         return self.query().nearest_to(query_vector)
 
@@ -2233,7 +2250,7 @@ class AsyncTable:
            x      vector
         0  3  [5.0, 6.0]
         """
-        raise NotImplementedError
+        return await self._inner.delete(where)
 
     async def update(
         self,
@@ -2289,102 +2306,6 @@ class AsyncTable:
 
         return await self._inner.update(updates_sql, where)
 
-    async def cleanup_old_versions(
-        self,
-        older_than: Optional[timedelta] = None,
-        *,
-        delete_unverified: bool = False,
-    ) -> CleanupStats:
-        """
-        Clean up old versions of the table, freeing disk space.
-
-        Note: This function is not available in LanceDb Cloud (since LanceDb
-        Cloud manages cleanup for you automatically)
-
-        Parameters
-        ----------
-        older_than: timedelta, default None
-            The minimum age of the version to delete. If None, then this defaults
-            to two weeks.
-        delete_unverified: bool, default False
-            Because they may be part of an in-progress transaction, files newer
-            than 7 days old are not deleted by default. If you are sure that
-            there are no in-progress transactions, then you can set this to True
-            to delete all files older than `older_than`.
-
-        Returns
-        -------
-        CleanupStats
-            The stats of the cleanup operation, including how many bytes were
-            freed.
-        """
-        raise NotImplementedError
-
-    async def compact_files(self, *args, **kwargs):
-        """
-        Run the compaction process on the table.
-
-        Note: This function is not available in LanceDb Cloud (since LanceDb
-        Cloud manages compaction for you automatically)
-
-        This can be run after making several small appends to optimize the table
-        for faster reads.
-
-        Arguments are passed onto :meth:`lance.dataset.DatasetOptimizer.compact_files`.
-        For most cases, the default should be fine.
-        """
-        raise NotImplementedError
-
-    async def add_columns(self, transforms: Dict[str, str]):
-        """
-        Add new columns with defined values.
-
-        This is not yet available in LanceDB Cloud.
-
-        Parameters
-        ----------
-        transforms: Dict[str, str]
-            A map of column name to a SQL expression to use to calculate the
-            value of the new column. These expressions will be evaluated for
-            each row in the table, and can reference existing columns.
-        """
-        raise NotImplementedError
-
-    async def alter_columns(self, alterations: Iterable[Dict[str, str]]):
-        """
-        Alter column names and nullability.
-
-        This is not yet available in LanceDB Cloud.
-
-        alterations : Iterable[Dict[str, Any]]
-            A sequence of dictionaries, each with the following keys:
-            - "path": str
-                The column path to alter. For a top-level column, this is the name.
-                For a nested column, this is the dot-separated path, e.g. "a.b.c".
-            - "name": str, optional
-                The new name of the column. If not specified, the column name is
-                not changed.
-            - "nullable": bool, optional
-                Whether the column should be nullable. If not specified, the column
-                nullability is not changed. Only non-nullable columns can be changed
-                to nullable. Currently, you cannot change a nullable column to
-                non-nullable.
-        """
-        raise NotImplementedError
-
-    async def drop_columns(self, columns: Iterable[str]):
-        """
-        Drop columns from the table.
-
-        This is not yet available in LanceDB Cloud.
-
-        Parameters
-        ----------
-        columns : Iterable[str]
-            The names of the columns to drop.
-        """
-        raise NotImplementedError
-
     async def version(self) -> int:
         """
         Retrieve the version of the table

python/python/lancedb/util.py

@@ -25,6 +25,8 @@ import numpy as np
 import pyarrow as pa
 import pyarrow.fs as pa_fs
 
+from ._lancedb import validate_table_name as native_validate_table_name
+
 
 def safe_import_adlfs():
     try:
@@ -286,3 +288,8 @@ def deprecated(func):
         return func(*args, **kwargs)
 
     return new_func
+
+
+def validate_table_name(name: str):
+    """Verify the table name is valid."""
+    native_validate_table_name(name)

python/python/tests/docs/test_basic.py

@@ -0,0 +1,162 @@
+import shutil
+
+# --8<-- [start:imports]
+import lancedb
+import pandas as pd
+import pyarrow as pa
+
+# --8<-- [end:imports]
+import pytest
+from numpy.random import randint, random
+
+shutil.rmtree("data/sample-lancedb", ignore_errors=True)
+
+
+def test_quickstart():
+    # --8<-- [start:connect]
+    uri = "data/sample-lancedb"
+    db = lancedb.connect(uri)
+    # --8<-- [end:connect]
+
+    # --8<-- [start:create_table]
+    data = [
+        {"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
+        {"vector": [5.9, 26.5], "item": "bar", "price": 20.0},
+    ]
+
+    # Synchronous client
+    tbl = db.create_table("my_table", data=data)
+    # --8<-- [end:create_table]
+
+    # --8<-- [start:create_table_pandas]
+    df = pd.DataFrame(
+        [
+            {"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
+            {"vector": [5.9, 26.5], "item": "bar", "price": 20.0},
+        ]
+    )
+    # Synchronous client
+    tbl = db.create_table("table_from_df", data=df)
+    # --8<-- [end:create_table_pandas]
+
+    # --8<-- [start:create_empty_table]
+    schema = pa.schema([pa.field("vector", pa.list_(pa.float32(), list_size=2))])
+    # Synchronous client
+    tbl = db.create_table("empty_table", schema=schema)
+    # --8<-- [end:create_empty_table]
+    # --8<-- [start:open_table]
+    # Synchronous client
+    tbl = db.open_table("my_table")
+    # --8<-- [end:open_table]
+    # --8<-- [start:table_names]
+    # Synchronous client
+    print(db.table_names())
+    # --8<-- [end:table_names]
+    # Synchronous client
+    # --8<-- [start:add_data]
+    # Option 1: Add a list of dicts to a table
+    data = [
+        {"vector": [1.3, 1.4], "item": "fizz", "price": 100.0},
+        {"vector": [9.5, 56.2], "item": "buzz", "price": 200.0},
+    ]
+    tbl.add(data)
+
+    # Option 2: Add a pandas DataFrame to a table
+    df = pd.DataFrame(data)
+    tbl.add(data)
+    # --8<-- [end:add_data]
+    # --8<-- [start:vector_search]
+    # Synchronous client
+    tbl.search([100, 100]).limit(2).to_pandas()
+    # --8<-- [end:vector_search]
+    tbl.add(
+        [
+            {"vector": random(2), "item": "autogen", "price": randint(100)}
+            for _ in range(1000)
+        ]
+    )
+    # --8<-- [start:create_index]
+    # Synchronous client
+    tbl.create_index(num_sub_vectors=1)
+    # --8<-- [end:create_index]
+    # --8<-- [start:delete_rows]
+    # Synchronous client
+    tbl.delete('item = "fizz"')
+    # --8<-- [end:delete_rows]
+    # --8<-- [start:drop_table]
+    # Synchronous client
+    db.drop_table("my_table")
+    # --8<-- [end:drop_table]
+
+
+@pytest.mark.asyncio
+async def test_quickstart_async():
+    # --8<-- [start:connect_async]
+    # LanceDb offers both a synchronous and an asynchronous client.  There are still a
+    # few operations that are only supported by the synchronous client (e.g. embedding
+    # functions, full text search) but both APIs should soon be equivalent
+
+    # In this guide we will give examples of both clients.  In other guides we will
+    # typically only provide examples with one client or the other.
+    uri = "data/sample-lancedb"
+    async_db = await lancedb.connect_async(uri)
+    # --8<-- [end:connect_async]
+
+    data = [
+        {"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
+        {"vector": [5.9, 26.5], "item": "bar", "price": 20.0},
+    ]
+
+    # --8<-- [start:create_table_async]
+    # Asynchronous client
+    async_tbl = await async_db.create_table("my_table2", data=data)
+    # --8<-- [end:create_table_async]
+
+    df = pd.DataFrame(
+        [
+            {"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
+            {"vector": [5.9, 26.5], "item": "bar", "price": 20.0},
+        ]
+    )
+
+    # --8<-- [start:create_table_async_pandas]
+    # Asynchronous client
+    async_tbl = await async_db.create_table("table_from_df2", df)
+    # --8<-- [end:create_table_async_pandas]
+
+    schema = pa.schema([pa.field("vector", pa.list_(pa.float32(), list_size=2))])
+    # --8<-- [start:create_empty_table_async]
+    # Asynchronous client
+    async_tbl = await async_db.create_table("empty_table2", schema=schema)
+    # --8<-- [end:create_empty_table_async]
+    # --8<-- [start:open_table_async]
+    # Asynchronous client
+    async_tbl = await async_db.open_table("my_table2")
+    # --8<-- [end:open_table_async]
+    # --8<-- [start:table_names_async]
+    # Asynchronous client
+    print(await async_db.table_names())
+    # --8<-- [end:table_names_async]
+    # --8<-- [start:add_data_async]
+    # Asynchronous client
+    await async_tbl.add(data)
+    # --8<-- [end:add_data_async]
+    # Add sufficient data for training
+    data = [{"vector": [x, x], "item": "filler", "price": x * x} for x in range(1000)]
+    await async_tbl.add(data)
+    # --8<-- [start:vector_search_async]
+    # Asynchronous client
+    await async_tbl.vector_search([100, 100]).limit(2).to_pandas()
+    # --8<-- [end:vector_search_async]
+    # --8<-- [start:create_index_async]
+    # Asynchronous client (must specify column to index)
+    await async_tbl.create_index("vector")
+    # --8<-- [end:create_index_async]
+    # --8<-- [start:delete_rows_async]
+    # Asynchronous client
+    await async_tbl.delete('item = "fizz"')
+    # --8<-- [end:delete_rows_async]
+    # --8<-- [start:drop_table_async]
+    # Asynchronous client
+    await async_db.drop_table("my_table2")
+    # --8<-- [end:drop_table_async]

python/python/tests/test_db.py

@@ -521,3 +521,15 @@ def test_prefilter_with_index(tmp_path):
         .to_arrow()
     )
     assert table.num_rows == 1
+
+
+def test_create_table_with_invalid_names(tmp_path):
+    db = lancedb.connect(uri=tmp_path)
+    data = [{"vector": np.random.rand(128), "item": "foo"} for i in range(10)]
+    with pytest.raises(ValueError):
+        db.create_table("foo/bar", data)
+    with pytest.raises(ValueError):
+        db.create_table("foo bar", data)
+    with pytest.raises(ValueError):
+        db.create_table("foo$$bar", data)
+    db.create_table("foo.bar", data)

python/src/connection.rs

@@ -137,6 +137,21 @@ impl Connection {
             Ok(Table::new(table))
         })
     }
+
+    pub fn drop_table(self_: PyRef<'_, Self>, name: String) -> PyResult<&PyAny> {
+        let inner = self_.get_inner()?.clone();
+        future_into_py(self_.py(), async move {
+            inner.drop_table(name).await.infer_error()
+        })
+    }
+
+    pub fn drop_db(self_: PyRef<'_, Self>) -> PyResult<&PyAny> {
+        let inner = self_.get_inner()?.clone();
+        future_into_py(
+            self_.py(),
+            async move { inner.drop_db().await.infer_error() },
+        )
+    }
 }
 
 #[pyfunction]

python/src/lib.rs

@@ -42,6 +42,7 @@ pub fn _lancedb(_py: Python, m: &PyModule) -> PyResult<()> {
     m.add_class::<VectorQuery>()?;
     m.add_class::<RecordBatchStream>()?;
     m.add_function(wrap_pyfunction!(connect, m)?)?;
+    m.add_function(wrap_pyfunction!(util::validate_table_name, m)?)?;
     m.add("__version__", env!("CARGO_PKG_VERSION"))?;
     Ok(())
 }

python/src/table.rs

@@ -80,6 +80,13 @@ impl Table {
         })
     }
 
+    pub fn delete(self_: PyRef<'_, Self>, condition: String) -> PyResult<&PyAny> {
+        let inner = self_.inner_ref()?.clone();
+        future_into_py(self_.py(), async move {
+            inner.delete(&condition).await.infer_error()
+        })
+    }
+
     pub fn update<'a>(
         self_: PyRef<'a, Self>,
         updates: &PyDict,