Merge branch 'main' into docs_march

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.4.13
+current_version = 0.4.14
 commit = True
 message = Bump version: {current_version} → {new_version}
 tag = True

.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
           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
           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

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

@@ -38,52 +38,53 @@ 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:
@@ -139,13 +140,10 @@ nav:
       - 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

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"
 
@@ -82,15 +91,14 @@ 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 +108,8 @@ 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 +144,14 @@ 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 +173,8 @@ 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 +194,8 @@ 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 +217,8 @@ 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 +240,8 @@ 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 +275,8 @@ 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 +288,15 @@ 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 +307,8 @@ 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 +325,7 @@ 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 +347,8 @@ 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/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": "0.4.14",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "vectordb",
-      "version": "0.4.13",
+      "version": "0.4.14",
       "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": "0.4.14",
+        "@lancedb/vectordb-darwin-x64": "0.4.14",
+        "@lancedb/vectordb-linux-arm64-gnu": "0.4.14",
+        "@lancedb/vectordb-linux-x64-gnu": "0.4.14",
+        "@lancedb/vectordb-win32-x64-msvc": "0.4.14"
       },
       "peerDependencies": {
         "@apache-arrow/ts": "^14.0.2",
@@ -334,9 +334,9 @@
       }
     },
     "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==",
+      "version": "0.4.14",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.4.14.tgz",
+      "integrity": "sha512-fw6mf6UhFf4j2kKdFcw0P+SOiIqmRbt+YQSgDbF4BFU3OUSW0XyfETIj9cUMQbSwPFsofhlGp5BRpCd7W9noew==",
       "cpu": [
         "arm64"
       ],
@@ -345,22 +345,10 @@
         "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==",
+      "version": "0.4.14",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.4.14.tgz",
+      "integrity": "sha512-1+LFI8vU+f/lnGy1s3XCySuV4oj3ZUW03xtmedGBW8nv/Y/jWXP0OYJCRI72eu+dLIdu0tCPsEiu8Hl+o02t9g==",
       "cpu": [
         "arm64"
       ],
@@ -369,22 +357,10 @@
         "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==",
+      "version": "0.4.14",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.4.14.tgz",
+      "integrity": "sha512-fpuNMZ4aHSpZC3ztp5a0Wh18N6DpCx5EPWhS7bGA5XulGc0l+sZAJHfHwalx76ys//0Ns1z7cuKJhZpSa4SrdQ==",
       "cpu": [
         "x64"
       ],

node/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vectordb",
-  "version": "0.4.13",
+  "version": "0.4.14",
   "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": "0.4.14",
+    "@lancedb/vectordb-darwin-x64": "0.4.14",
+    "@lancedb/vectordb-linux-arm64-gnu": "0.4.14",
+    "@lancedb/vectordb-linux-x64-gnu": "0.4.14",
+    "@lancedb/vectordb-win32-x64-msvc": "0.4.14"
   }
 }

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

@@ -1,5 +1,5 @@
 {
-  "name": "lancedb-darwin-arm64",
+  "name": "@lancedb/lancedb-darwin-arm64",
   "version": "0.4.3",
   "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

@@ -1,5 +1,5 @@
 {
-  "name": "lancedb-darwin-x64",
+  "name": "@lancedb/lancedb-darwin-x64",
   "version": "0.4.3",
   "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

@@ -1,5 +1,5 @@
 {
-  "name": "lancedb-linux-arm64-gnu",
+  "name": "@lancedb/lancedb-linux-arm64-gnu",
   "version": "0.4.3",
   "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

@@ -1,5 +1,5 @@
 {
-  "name": "lancedb-linux-x64-gnu",
+  "name": "@lancedb/lancedb-linux-x64-gnu",
   "version": "0.4.3",
   "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": "0.4.3",
+  "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",
+  "name": "@lancedb/lancedb",
   "version": "0.4.3",
   "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",
@@ -48,13 +50,14 @@
   "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",
     "lint": "eslint lancedb && eslint __test__",
@@ -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": "0.4.3",
+    "@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"
   },
-  "peerDependencies": {
+  "dependencies": {
+    "openai": "^4.29.2",
     "apache-arrow": "^15.0.0"
   }
 }

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

@@ -25,7 +25,6 @@ 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
@@ -451,16 +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
@@ -471,10 +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
@@ -535,9 +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
         ----------
@@ -576,7 +574,7 @@ class AsyncConnection(object):
 
         Returns
         -------
-        LanceTable
+        AsyncTable
             A reference to the newly created table.
 
         !!! note
@@ -590,12 +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
@@ -614,9 +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
@@ -636,9 +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
@@ -670,9 +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
@@ -681,12 +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.
@@ -767,11 +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/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/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/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/table.rs

@@ -80,6 +80,13 @@ impl Table {
         })
     }
 
+    pub fn delete<'a>(self_: PyRef<'a, Self>, condition: String) -> PyResult<&'a 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,

rust/ffi/node/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-node"
-version = "0.4.13"
+version = "0.4.14"
 description = "Serverless, low-latency vector database for AI applications"
 license.workspace = true
 edition.workspace = true

rust/lancedb/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.4.13"
+version = "0.4.14"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true