fix small details

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.21.2"
+current_version = "0.19.1-beta.1"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.
@@ -50,6 +50,11 @@ pre_commit_hooks = [
 optional_value = "final"
 values = ["beta", "final"]
 
+[[tool.bumpversion.files]]
+filename = "node/package.json"
+replace = "\"version\": \"{new_version}\","
+search = "\"version\": \"{current_version}\","
+
 [[tool.bumpversion.files]]
 filename = "nodejs/package.json"
 replace = "\"version\": \"{new_version}\","
@@ -61,8 +66,39 @@ glob = "nodejs/npm/*/package.json"
 replace = "\"version\": \"{new_version}\","
 search = "\"version\": \"{current_version}\","
 
+# vectodb node binary packages
+[[tool.bumpversion.files]]
+glob = "node/package.json"
+replace = "\"@lancedb/vectordb-darwin-arm64\": \"{new_version}\""
+search = "\"@lancedb/vectordb-darwin-arm64\": \"{current_version}\""
+
+[[tool.bumpversion.files]]
+glob = "node/package.json"
+replace = "\"@lancedb/vectordb-darwin-x64\": \"{new_version}\""
+search = "\"@lancedb/vectordb-darwin-x64\": \"{current_version}\""
+
+[[tool.bumpversion.files]]
+glob = "node/package.json"
+replace = "\"@lancedb/vectordb-linux-arm64-gnu\": \"{new_version}\""
+search = "\"@lancedb/vectordb-linux-arm64-gnu\": \"{current_version}\""
+
+[[tool.bumpversion.files]]
+glob = "node/package.json"
+replace = "\"@lancedb/vectordb-linux-x64-gnu\": \"{new_version}\""
+search = "\"@lancedb/vectordb-linux-x64-gnu\": \"{current_version}\""
+
+[[tool.bumpversion.files]]
+glob = "node/package.json"
+replace = "\"@lancedb/vectordb-win32-x64-msvc\": \"{new_version}\""
+search = "\"@lancedb/vectordb-win32-x64-msvc\": \"{current_version}\""
+
 # Cargo files
 # ------------
+[[tool.bumpversion.files]]
+filename = "rust/ffi/node/Cargo.toml"
+replace = "\nversion = \"{new_version}\""
+search = "\nversion = \"{current_version}\""
+
 [[tool.bumpversion.files]]
 filename = "rust/lancedb/Cargo.toml"
 replace = "\nversion = \"{new_version}\""

.github/workflows/cargo-publish.yml

@@ -5,8 +5,8 @@ on:
     tags-ignore:
       # We don't publish pre-releases for Rust. Crates.io is just a source
       # distribution, so we don't need to publish pre-releases.
-      - "v*-beta*"
-      - "*-v*" # for example, python-vX.Y.Z
+      - 'v*-beta*'
+      - '*-v*' # for example, python-vX.Y.Z
 
 env:
   # This env var is used by Swatinem/rust-cache@v2 for the cache
@@ -19,8 +19,6 @@ env:
 jobs:
   build:
     runs-on: ubuntu-22.04
-    permissions:
-      id-token: write
     timeout-minutes: 30
     # Only runs on tags that matches the make-release action
     if: startsWith(github.ref, 'refs/tags/v')
@@ -33,8 +31,6 @@ jobs:
         run: |
           sudo apt update
           sudo apt install -y protobuf-compiler libssl-dev
-      - uses: rust-lang/crates-io-auth-action@v1
-        id: auth
       - name: Publish the package
         run: |
-          cargo publish -p lancedb --all-features --token ${{ steps.auth.outputs.token }}
+          cargo publish -p lancedb --all-features --token ${{ secrets.CARGO_REGISTRY_TOKEN }}

.github/workflows/java.yml

@@ -35,9 +35,6 @@ jobs:
       - uses: Swatinem/rust-cache@v2
         with:
           workspaces: java/core/lancedb-jni
-      - uses: actions-rust-lang/setup-rust-toolchain@v1
-        with:
-          components: rustfmt
       - name: Run cargo fmt
         run: cargo fmt --check
         working-directory: ./java/core/lancedb-jni
@@ -71,9 +68,6 @@ jobs:
       - uses: Swatinem/rust-cache@v2
         with:
           workspaces: java/core/lancedb-jni
-      - uses: actions-rust-lang/setup-rust-toolchain@v1
-        with:
-          components: rustfmt
       - name: Run cargo fmt
         run: cargo fmt --check
         working-directory: ./java/core/lancedb-jni
@@ -116,3 +110,4 @@ jobs:
           -Djdk.reflect.useDirectMethodHandle=false \
           -Dio.netty.tryReflectionSetAccessible=true"
           JAVA_HOME=$JAVA_17 mvn clean test
+  

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

@@ -84,7 +84,6 @@ jobs:
         run: |
           pip install bump-my-version PyGithub packaging
           bash ci/bump_version.sh ${{ inputs.type }} ${{ inputs.bump-minor }} v $COMMIT_BEFORE_BUMP
-          bash ci/update_lockfiles.sh --amend
       - name: Push new version tag
         if: ${{ !inputs.dry_run }}
         uses: ad-m/github-push-action@master
@@ -93,3 +92,11 @@ jobs:
           github_token: ${{ secrets.LANCEDB_RELEASE_TOKEN }}
           branch: ${{ github.ref }}
           tags: true
+      - uses: ./.github/workflows/update_package_lock
+        if: ${{ !inputs.dry_run && inputs.other }}
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+      - uses: ./.github/workflows/update_package_lock_nodejs
+        if: ${{ !inputs.dry_run && inputs.other }}
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/node.yml

@@ -0,0 +1,147 @@
+name: Node
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    paths:
+      - node/**
+      - rust/ffi/node/**
+      - .github/workflows/node.yml
+      - docker-compose.yml
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+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.
+  #
+  # Use native CPU to accelerate tests if possible, especially for f16
+  # 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:
+  linux:
+    name: Linux (Node ${{ matrix.node-version }})
+    timeout-minutes: 30
+    strategy:
+      matrix:
+        node-version: [ "18", "20" ]
+    runs-on: "ubuntu-22.04"
+    defaults:
+      run:
+        shell: bash
+        working-directory: node
+    steps:
+    - uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+        lfs: true
+    - uses: actions/setup-node@v3
+      with:
+        node-version: ${{ matrix.node-version }}
+        cache: 'npm'
+        cache-dependency-path: node/package-lock.json
+    - uses: Swatinem/rust-cache@v2
+    - name: Install dependencies
+      run: |
+        sudo apt update
+        sudo apt install -y protobuf-compiler libssl-dev
+    - name: Build
+      run: |
+        npm ci
+        npm run build
+        npm run pack-build
+        npm install --no-save ./dist/lancedb-vectordb-*.tgz
+        # Remove index.node to test with dependency installed
+        rm index.node
+    - name: Test
+      run: npm run test
+  macos:
+    timeout-minutes: 30
+    runs-on: "macos-13"
+    defaults:
+      run:
+        shell: bash
+        working-directory: node
+    steps:
+    - uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+        lfs: true
+    - uses: actions/setup-node@v3
+      with:
+        node-version: 20
+        cache: 'npm'
+        cache-dependency-path: node/package-lock.json
+    - uses: Swatinem/rust-cache@v2
+    - name: Install dependencies
+      run: brew install protobuf
+    - name: Build
+      run: |
+        npm ci
+        npm run build
+        npm run pack-build
+        npm install --no-save ./dist/lancedb-vectordb-*.tgz
+        # Remove index.node to test with dependency installed
+        rm index.node
+    - name: Test
+      run: |
+        npm run test
+  aws-integtest:
+    timeout-minutes: 45
+    runs-on: "ubuntu-22.04"
+    defaults:
+      run:
+        shell: bash
+        working-directory: node
+    env:
+      AWS_ACCESS_KEY_ID: ACCESSKEY
+      AWS_SECRET_ACCESS_KEY: SECRETKEY
+      AWS_DEFAULT_REGION: us-west-2
+      # this one is for s3
+      AWS_ENDPOINT: http://localhost:4566
+      # this one is for dynamodb
+      DYNAMODB_ENDPOINT: http://localhost:4566
+      ALLOW_HTTP: true
+    steps:
+    - uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+        lfs: true
+    - uses: actions/setup-node@v3
+      with:
+        node-version: 20
+        cache: 'npm'
+        cache-dependency-path: node/package-lock.json
+    - name: start local stack
+      run: docker compose -f ../docker-compose.yml up -d --wait
+    - name: create s3
+      run: aws s3 mb s3://lancedb-integtest --endpoint $AWS_ENDPOINT
+    - name: create ddb
+      run: |
+        aws dynamodb create-table \
+          --table-name lancedb-integtest \
+          --attribute-definitions '[{"AttributeName": "base_uri", "AttributeType": "S"}, {"AttributeName": "version", "AttributeType": "N"}]' \
+          --key-schema '[{"AttributeName": "base_uri", "KeyType": "HASH"}, {"AttributeName": "version", "KeyType": "RANGE"}]' \
+          --provisioned-throughput '{"ReadCapacityUnits": 10, "WriteCapacityUnits": 10}' \
+          --endpoint-url $DYNAMODB_ENDPOINT
+    - uses: Swatinem/rust-cache@v2
+    - name: Install dependencies
+      run: |
+        sudo apt update
+        sudo apt install -y protobuf-compiler libssl-dev
+    - name: Build
+      run: |
+        npm ci
+        npm run build
+        npm run pack-build
+        npm install --no-save ./dist/lancedb-vectordb-*.tgz
+        # Remove index.node to test with dependency installed
+        rm index.node
+    - name: Test
+      run: npm run integration-test

.github/workflows/nodejs.yml

@@ -47,9 +47,6 @@ jobs:
       run: |
         sudo apt update
         sudo apt install -y protobuf-compiler libssl-dev
-    - uses: actions-rust-lang/setup-rust-toolchain@v1
-      with:
-        components: rustfmt, clippy
     - name: Lint
       run: |
         cargo fmt --all -- --check
@@ -116,7 +113,7 @@ jobs:
         set -e
         npm ci
         npm run docs
-        if ! git diff --exit-code -- . ':(exclude)Cargo.lock'; then
+        if ! git diff --exit-code; then
           echo "Docs need to be updated"
           echo "Run 'npm run docs', fix any warnings, and commit the changes."
           exit 1

.github/workflows/npm-publish.yml

@@ -365,3 +365,202 @@ jobs:
             ARGS="$ARGS --tag preview"
           fi
           npm publish $ARGS
+
+
+  # ----------------------------------------------------------------------------
+  # vectordb release (legacy)
+  # ----------------------------------------------------------------------------
+  # TODO: delete this when we drop vectordb
+  node:
+    name: vectordb Typescript
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        shell: bash
+        working-directory: node
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - uses: actions/setup-node@v3
+        with:
+          node-version: 20
+          cache: "npm"
+          cache-dependency-path: node/package-lock.json
+      - name: Install dependencies
+        run: |
+          sudo apt update
+          sudo apt install -y protobuf-compiler libssl-dev
+      - name: Build
+        run: |
+          npm ci
+          npm run tsc
+          npm pack
+      - name: Upload Linux Artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: node-package
+          path: |
+            node/vectordb-*.tgz
+
+  node-macos:
+    name: vectordb ${{ matrix.config.arch }}
+    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 }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Install system dependencies
+        run: brew install protobuf
+      - name: Install npm dependencies
+        run: |
+          cd node
+          npm ci
+      - name: Build MacOS native node modules
+        run: bash ci/build_macos_artifacts.sh ${{ matrix.config.arch }}
+      - name: Upload Darwin Artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: node-native-darwin-${{ matrix.config.arch }}
+          path: |
+            node/dist/lancedb-vectordb-darwin*.tgz
+
+  node-linux-gnu:
+    name: vectordb (${{ matrix.config.arch}}-unknown-linux-gnu)
+    runs-on: ${{ matrix.config.runner }}
+    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: warp-ubuntu-latest-arm64-4x
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      # 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.sh ${{ matrix.config.arch }} ${{ matrix.config.arch }}-unknown-linux-gnu
+      - name: Upload Linux Artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: node-native-linux-${{ matrix.config.arch }}-gnu
+          path: |
+            node/dist/lancedb-vectordb-linux*.tgz
+
+  node-windows:
+    name: vectordb ${{ matrix.target }}
+    runs-on: windows-2022
+    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 node
+          npm ci
+      - name: Build Windows native node modules
+        run: .\ci\build_windows_artifacts.ps1 ${{ matrix.target }}
+      - name: Upload Windows Artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: node-native-windows
+          path: |
+            node/dist/lancedb-vectordb-win32*.tgz
+
+  release:
+    name: vectordb NPM Publish
+    needs: [node, node-macos, node-linux-gnu, 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@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"
+      - name: Publish to NPM
+        env:
+          NODE_AUTH_TOKEN: ${{ secrets.LANCEDB_NPM_REGISTRY_TOKEN }}
+        run: |
+          # Tag beta as "preview" instead of default "latest". See lancedb
+          # npm publish step for more info.
+          if [[ $GITHUB_REF =~ refs/tags/v(.*)-beta.* ]]; then
+            PUBLISH_ARGS="--tag preview"
+          fi
+
+          mv */*.tgz .
+          for filename in *.tgz; do
+            npm publish $PUBLISH_ARGS $filename
+          done
+      - name: Deprecate
+        env:
+          NODE_AUTH_TOKEN: ${{ secrets.LANCEDB_NPM_REGISTRY_TOKEN }}
+        # We need to deprecate the old package to avoid confusion.
+        # Each time we publish a new version, it gets undeprecated.
+        run: npm deprecate vectordb "Use @lancedb/lancedb instead."
+      - name: Notify Slack Action
+        uses: ravsamhq/notify-slack-action@2.3.0
+        if: ${{ always() }}
+        with:
+          status: ${{ job.status }}
+          notify_when: "failure"
+          notification_title: "{workflow} is failing"
+        env:
+          SLACK_WEBHOOK_URL: ${{ secrets.ACTION_MONITORING_SLACK }}
+
+  update-package-lock:
+    if: startsWith(github.ref, 'refs/tags/v')
+    needs: [release]
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          ref: main
+          token: ${{ secrets.LANCEDB_RELEASE_TOKEN }}
+          fetch-depth: 0
+          lfs: true
+      - uses: ./.github/workflows/update_package_lock
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/run_tests/action.yml

@@ -24,8 +24,8 @@ runs:
     - name: pytest (with integration)
       shell: bash
       if: ${{ inputs.integration == 'true' }}
-      run: pytest -m "not slow" -vv --durations=30 python/python/tests
+      run: pytest -m "not slow" -x -v --durations=30 python/python/tests
     - name: pytest (no integration tests)
       shell: bash
       if: ${{ inputs.integration != 'true' }}
-      run: pytest -m "not slow and not s3_test" -vv --durations=30 python/python/tests
+      run: pytest -m "not slow and not s3_test" -x -v --durations=30 python/python/tests

.github/workflows/rust.yml

@@ -40,9 +40,6 @@ jobs:
         with:
           fetch-depth: 0
           lfs: true
-      - uses: actions-rust-lang/setup-rust-toolchain@v1
-        with:
-          components: rustfmt, clippy
       - uses: Swatinem/rust-cache@v2
         with:
           workspaces: rust
@@ -163,8 +160,8 @@ jobs:
     strategy:
       matrix:
         target:
-          - x86_64-pc-windows-msvc
-          - aarch64-pc-windows-msvc
+        - x86_64-pc-windows-msvc
+        - aarch64-pc-windows-msvc
     defaults:
       run:
         working-directory: rust/lancedb

.github/workflows/update_package_lock/action.yml

@@ -0,0 +1,33 @@
+name: update_package_lock
+description: "Update node'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: ./node
+      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_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

CLAUDE.md

@@ -1,24 +0,0 @@
-LanceDB is a database designed for retrieval, including vector, full-text, and hybrid search.
-It is a wrapper around Lance. There are two backends: local (in-process like SQLite) and
-remote (against LanceDB Cloud).
-
-The core of LanceDB is written in Rust. There are bindings in Python, Typescript, and Java.
-
-Project layout:
-
-* `rust/lancedb`: The LanceDB core Rust implementation.
-* `python`: The Python bindings, using PyO3.
-* `nodejs`: The Typescript bindings, using napi-rs
-* `java`: The Java bindings
-
-(`rust/ffi` and `node/` are for a deprecated package. You can ignore them.)
-
-Common commands:
-
-* Check for compiler errors: `cargo check --features remote --tests --examples`
-* Run tests: `cargo test --features remote --tests`
-* Run specific test: `cargo test --features remote -p <package_name> --test <test_name>`
-* Lint: `cargo clippy --features remote --tests --examples`
-* Format: `cargo fmt --all`
-
-Before committing changes, run formatting.

Cargo.toml

@@ -1,5 +1,6 @@
 [workspace]
 members = [
+    "rust/ffi/node",
     "rust/lancedb",
     "nodejs",
     "python",
@@ -20,54 +21,55 @@ categories = ["database-implementations"]
 rust-version = "1.78.0"
 
 [workspace.dependencies]
-lance = { "version" = "=0.32.1", "features" = [
-    "dynamodb",
-], "tag" = "v0.32.1-beta.2", "git" = "https://github.com/lancedb/lance.git" }
-lance-io = { "version" = "=0.32.1", "tag" = "v0.32.1-beta.2", "git" = "https://github.com/lancedb/lance.git" }
-lance-index = { "version" = "=0.32.1", "tag" = "v0.32.1-beta.2", "git" = "https://github.com/lancedb/lance.git" }
-lance-linalg = { "version" = "=0.32.1", "tag" = "v0.32.1-beta.2", "git" = "https://github.com/lancedb/lance.git" }
-lance-table = { "version" = "=0.32.1", "tag" = "v0.32.1-beta.2", "git" = "https://github.com/lancedb/lance.git" }
-lance-testing = { "version" = "=0.32.1", "tag" = "v0.32.1-beta.2", "git" = "https://github.com/lancedb/lance.git" }
-lance-datafusion = { "version" = "=0.32.1", "tag" = "v0.32.1-beta.2", "git" = "https://github.com/lancedb/lance.git" }
-lance-encoding = { "version" = "=0.32.1", "tag" = "v0.32.1-beta.2", "git" = "https://github.com/lancedb/lance.git" }
+lance = { "version" = "=0.27.0", "features" = ["dynamodb"], tag = "v0.27.0-beta.2", git="https://github.com/lancedb/lance.git" }
+lance-io = { version = "=0.27.0", tag = "v0.27.0-beta.2", git="https://github.com/lancedb/lance.git" }
+lance-index = { version = "=0.27.0", tag = "v0.27.0-beta.2", git="https://github.com/lancedb/lance.git" }
+lance-linalg = { version = "=0.27.0", tag = "v0.27.0-beta.2", git="https://github.com/lancedb/lance.git" }
+lance-table = { version = "=0.27.0", tag = "v0.27.0-beta.2", git="https://github.com/lancedb/lance.git" }
+lance-testing = { version = "=0.27.0", tag = "v0.27.0-beta.2", git="https://github.com/lancedb/lance.git" }
+lance-datafusion = { version = "=0.27.0", tag = "v0.27.0-beta.2", git="https://github.com/lancedb/lance.git" }
+lance-encoding = { version = "=0.27.0", tag = "v0.27.0-beta.2", git="https://github.com/lancedb/lance.git" }
 # Note that this one does not include pyarrow
-arrow = { version = "55.1", optional = false }
-arrow-array = "55.1"
-arrow-data = "55.1"
-arrow-ipc = "55.1"
-arrow-ord = "55.1"
-arrow-schema = "55.1"
-arrow-arith = "55.1"
-arrow-cast = "55.1"
+arrow = { version = "54.1", optional = false }
+arrow-array = "54.1"
+arrow-data = "54.1"
+arrow-ipc = "54.1"
+arrow-ord = "54.1"
+arrow-schema = "54.1"
+arrow-arith = "54.1"
+arrow-cast = "54.1"
 async-trait = "0"
-datafusion = { version = "48.0", default-features = false }
-datafusion-catalog = "48.0"
-datafusion-common = { version = "48.0", default-features = false }
-datafusion-execution = "48.0"
-datafusion-expr = "48.0"
-datafusion-physical-plan = "48.0"
+datafusion = { version = "46.0", default-features = false }
+datafusion-catalog = "46.0"
+datafusion-common = { version = "46.0", default-features = false }
+datafusion-execution = "46.0"
+datafusion-expr = "46.0"
+datafusion-physical-plan = "46.0"
 env_logger = "0.11"
-half = { "version" = "2.6.0", default-features = false, features = [
+half = { "version" = "=2.4.1", default-features = false, features = [
     "num-traits",
 ] }
 futures = "0"
 log = "0.4"
 moka = { version = "0.12", features = ["future"] }
-object_store = "0.12.0"
+object_store = "0.11.0"
 pin-project = "1.0.7"
 snafu = "0.8"
 url = "2"
 num-traits = "0.2"
-rand = "0.9"
+rand = "0.8"
 regex = "1.10"
 lazy_static = "1"
 semver = "1.0.25"
+
 # Temporary pins to work around downstream issues
 # https://github.com/apache/arrow-rs/commit/2fddf85afcd20110ce783ed5b4cdeb82293da30b
-chrono = "=0.4.41"
+chrono = "=0.4.39"
 # https://github.com/RustCrypto/formats/issues/1684
 base64ct = "=1.6.0"
+
 # Workaround for: https://github.com/eira-fransham/crunchy/issues/13
 crunchy = "=0.2.2"
+
 # Workaround for: https://github.com/Lokathor/bytemuck/issues/306
 bytemuck_derive = ">=1.8.1, <1.9.0"

README.md

@@ -1,97 +1,94 @@
 <a href="https://cloud.lancedb.com" target="_blank">
   <img src="https://github.com/user-attachments/assets/92dad0a2-2a37-4ce1-b783-0d1b4f30a00c" alt="LanceDB Cloud Public Beta" width="100%" style="max-width: 100%;">
 </a>
+
 <div align="center">
+<p align="center">
 
-[![LanceDB](docs/src/assets/hero-header.png)](https://lancedb.com)
-[![Website](https://img.shields.io/badge/-Website-100000?style=for-the-badge&labelColor=645cfb&color=645cfb)](https://lancedb.com/)
-[![Blog](https://img.shields.io/badge/Blog-100000?style=for-the-badge&labelColor=645cfb&color=645cfb)](https://blog.lancedb.com/)
-[![Discord](https://img.shields.io/badge/-Discord-100000?style=for-the-badge&logo=discord&logoColor=white&labelColor=645cfb&color=645cfb)](https://discord.gg/zMM32dvNtd)
-[![Twitter](https://img.shields.io/badge/-Twitter-100000?style=for-the-badge&logo=x&logoColor=white&labelColor=645cfb&color=645cfb)](https://twitter.com/lancedb)
-[![LinkedIn](https://img.shields.io/badge/-LinkedIn-100000?style=for-the-badge&logo=linkedin&logoColor=white&labelColor=645cfb&color=645cfb)](https://www.linkedin.com/company/lancedb/)
+<picture>
+  <source media="(prefers-color-scheme: dark)" srcset="https://github.com/user-attachments/assets/ac270358-333e-4bea-a132-acefaa94040e">
+  <source media="(prefers-color-scheme: light)" srcset="https://github.com/user-attachments/assets/b864d814-0d29-4784-8fd9-807297c758c0">
+  <img alt="LanceDB Logo" src="https://github.com/user-attachments/assets/b864d814-0d29-4784-8fd9-807297c758c0" width=300>
+</picture>
 
+**Search More, Manage Less**
 
-<img src="docs/src/assets/lancedb.png" alt="LanceDB" width="50%">
+<a href='https://github.com/lancedb/vectordb-recipes/tree/main' target="_blank"><img alt='LanceDB' src='https://img.shields.io/badge/VectorDB_Recipes-100000?style=for-the-badge&logo=LanceDB&logoColor=white&labelColor=645cfb&color=645cfb'/></a>
+<a href='https://lancedb.github.io/lancedb/' target="_blank"><img alt='lancdb' src='https://img.shields.io/badge/DOCS-100000?style=for-the-badge&logo=lancdb&logoColor=white&labelColor=645cfb&color=645cfb'/></a>
+[![Blog](https://img.shields.io/badge/Blog-12100E?style=for-the-badge&logoColor=white)](https://blog.lancedb.com/)
+[![Discord](https://img.shields.io/badge/Discord-%235865F2.svg?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/zMM32dvNtd)
+[![Twitter](https://img.shields.io/badge/Twitter-%231DA1F2.svg?style=for-the-badge&logo=Twitter&logoColor=white)](https://twitter.com/lancedb)
+[![Gurubase](https://img.shields.io/badge/Gurubase-Ask%20LanceDB%20Guru-006BFF?style=for-the-badge)](https://gurubase.io/g/lancedb)
 
-# **The Multimodal AI Lakehouse**
+</p>
 
-[**How to Install** ](#how-to-install) ✦ [**Detailed Documentation**](https://lancedb.github.io/lancedb/) ✦ [**Tutorials and Recipes**](https://github.com/lancedb/vectordb-recipes/tree/main) ✦  [**Contributors**](#contributors) 
-
-**The ultimate multimodal data platform for AI/ML applications.** 
-
-LanceDB is designed for fast, scalable, and production-ready vector search. It is built on top of the Lance columnar format. You can store, index, and search over petabytes of multimodal data and vectors with ease. 
-LanceDB is a central location where developers can build, train and analyze their AI workloads.
-
-</div>
-
-<br>
-
-## **Demo: Multimodal Search by Keyword, Vector or with SQL**
 <img max-width="750px" alt="LanceDB Multimodal Search" src="https://github.com/lancedb/lancedb/assets/917119/09c5afc5-7816-4687-bae4-f2ca194426ec">
 
-## **Star LanceDB to get updates!**
-
-<details>
-<summary>⭐ Click here ⭐  to see how fast we're growing!</summary>
-<picture>
-  <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=lancedb/lancedb&theme=dark&type=Date">
-  <img width="100%" src="https://api.star-history.com/svg?repos=lancedb/lancedb&theme=dark&type=Date">
-</picture>
-</details>
-
-## **Key Features**:
-
-- **Fast Vector Search**: Search billions of vectors in milliseconds with state-of-the-art indexing.
-- **Comprehensive Search**: Support for vector similarity search, full-text search and SQL.
-- **Multimodal Support**: Store, query and filter vectors, metadata and multimodal data (text, images, videos, point clouds, and more).
-- **Advanced Features**: Zero-copy, automatic versioning, manage versions of your data without needing extra infrastructure. GPU support in building vector index.
-
-### **Products**:
-- **Open Source & Local**: 100% open source, runs locally or in your cloud. No vendor lock-in.
-- **Cloud and Enterprise**: Production-scale vector search with no servers to manage. Complete data sovereignty and security.
-
-### **Ecosystem**:
-- **Columnar Storage**: Built on the Lance columnar format for efficient storage and analytics.
-- **Seamless Integration**: Python, Node.js, Rust, and REST APIs for easy integration. Native Python and Javascript/Typescript support.
-- **Rich Ecosystem**: Integrations with [**LangChain** 🦜️🔗](https://python.langchain.com/docs/integrations/vectorstores/lancedb/), [**LlamaIndex** 🦙](https://gpt-index.readthedocs.io/en/latest/examples/vector_stores/LanceDBIndexDemo.html), Apache-Arrow, Pandas, Polars, DuckDB and more on the way.
-
-## **How to Install**:
-
-Follow the [Quickstart](https://lancedb.github.io/lancedb/basic/) doc to set up LanceDB locally. 
-
-**API & SDK:** We also support Python, Typescript and Rust SDKs
-
-| Interface | Documentation |
-|-----------|---------------|
-| Python SDK | https://lancedb.github.io/lancedb/python/python/ |
-| Typescript SDK | https://lancedb.github.io/lancedb/js/globals/ |
-| Rust SDK | https://docs.rs/lancedb/latest/lancedb/index.html |
-| REST API | https://docs.lancedb.com/api-reference/introduction |
-
-## **Join Us and Contribute**
-
-We welcome contributions from everyone! Whether you're a developer, researcher, or just someone who wants to help out. 
-
-If you have any suggestions or feature requests, please feel free to open an issue on GitHub or discuss it on our [**Discord**](https://discord.gg/G5DcmnZWKB) server.
-
-[**Check out the GitHub Issues**](https://github.com/lancedb/lancedb/issues) if you would like to work on the features that are planned for the future. If you have any suggestions or feature requests, please feel free to open an issue on GitHub. 
-
-## **Contributors**
-
-<a href="https://github.com/lancedb/lancedb/graphs/contributors">
-  <img src="https://contrib.rocks/image?repo=lancedb/lancedb" />
-</a>
-
-
-## **Stay in Touch With Us**
-<div align="center">
-
-</br>
-
-[![Website](https://img.shields.io/badge/-Website-100000?style=for-the-badge&labelColor=645cfb&color=645cfb)](https://lancedb.com/)
-[![Blog](https://img.shields.io/badge/Blog-100000?style=for-the-badge&labelColor=645cfb&color=645cfb)](https://blog.lancedb.com/)
-[![Discord](https://img.shields.io/badge/-Discord-100000?style=for-the-badge&logo=discord&logoColor=white&labelColor=645cfb&color=645cfb)](https://discord.gg/zMM32dvNtd)
-[![Twitter](https://img.shields.io/badge/-Twitter-100000?style=for-the-badge&logo=x&logoColor=white&labelColor=645cfb&color=645cfb)](https://twitter.com/lancedb)
-[![LinkedIn](https://img.shields.io/badge/-LinkedIn-100000?style=for-the-badge&logo=linkedin&logoColor=white&labelColor=645cfb&color=645cfb)](https://www.linkedin.com/company/lancedb/)
-
+</p>
 </div>
+
+<hr />
+
+LanceDB is an open-source database for vector-search built with persistent storage, which greatly simplifies retrieval, filtering and management of embeddings.
+
+The key features of LanceDB include:
+
+* Production-scale vector search with no servers to manage.
+
+* Store, query and filter vectors, metadata and multi-modal data (text, images, videos, point clouds, and more).
+
+* Support for vector similarity search, full-text search and SQL.
+
+* Native Python and Javascript/Typescript support.
+
+* Zero-copy, automatic versioning, manage versions of your data without needing extra infrastructure.
+
+* GPU support in building vector index(*).
+
+* Ecosystem integrations with [LangChain 🦜️🔗](https://python.langchain.com/docs/integrations/vectorstores/lancedb/), [LlamaIndex 🦙](https://gpt-index.readthedocs.io/en/latest/examples/vector_stores/LanceDBIndexDemo.html), Apache-Arrow, Pandas, Polars, DuckDB and more on the way.
+
+LanceDB's core is written in Rust 🦀 and is built using <a href="https://github.com/lancedb/lance">Lance</a>, an open-source columnar format designed for performant ML workloads.
+
+## Quick Start
+
+**Javascript**
+```shell
+npm install @lancedb/lancedb
+```
+
+```javascript
+import * as lancedb from "@lancedb/lancedb";
+
+const db = await lancedb.connect("data/sample-lancedb");
+const table = await db.createTable("vectors", [
+	{ id: 1, vector: [0.1, 0.2], item: "foo", price: 10 },
+	{ id: 2, vector: [1.1, 1.2], item: "bar", price: 50 },
+], {mode: 'overwrite'});
+
+
+const query = table.vectorSearch([0.1, 0.3]).limit(2);
+const results = await query.toArray();
+
+// You can also search for rows by specific criteria without involving a vector search.
+const rowsByCriteria = await table.query().where("price >= 10").toArray();
+```
+
+**Python**
+```shell
+pip install lancedb
+```
+
+```python
+import lancedb
+
+uri = "data/sample-lancedb"
+db = lancedb.connect(uri)
+table = 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}])
+result = table.search([100, 100]).limit(2).to_pandas()
+```
+
+## Blogs, Tutorials & Videos
+* 📈 <a href="https://blog.lancedb.com/benchmarking-random-access-in-lance/">2000x better performance with Lance over Parquet</a>
+* 🤖 <a href="https://github.com/lancedb/vectordb-recipes/tree/main/examples/Youtube-Search-QA-Bot">Build a question and answer bot with LanceDB</a>

ci/build_linux_artifacts.sh

@@ -0,0 +1,22 @@
+#!/bin/bash
+set -e
+ARCH=${1:-x86_64}
+TARGET_TRIPLE=${2:-x86_64-unknown-linux-gnu}
+
+# We pass down the current user so that when we later mount the local files
+# into the container, the files are accessible by the current user.
+pushd ci/manylinux_node
+docker build \
+    -t lancedb-node-manylinux \
+    --build-arg="ARCH=$ARCH" \
+    --build-arg="DOCKER_USER=$(id -u)" \
+    --progress=plain \
+    .
+popd
+
+# We turn on memory swap to avoid OOM killer
+docker run \
+    -v $(pwd):/io -w /io \
+    --memory-swap=-1 \
+    lancedb-node-manylinux \
+    bash ci/manylinux_node/build_vectordb.sh $ARCH $TARGET_TRIPLE

ci/build_macos_artifacts.sh

@@ -0,0 +1,34 @@
+# Builds the macOS artifacts (node binaries).
+# Usage: ./ci/build_macos_artifacts.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/ffi/node
+    echo "Building rust library for $1"
+    export RUST_BACKTRACE=1
+    cargo build --release --target $1
+    popd
+}
+
+build_node_binaries() {
+    pushd node
+    echo "Building node library for $1"
+    npm run build-release -- --target $1
+    npm run pack-build -- --target $1
+    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.ps1

@@ -0,0 +1,42 @@
+# Builds the Windows artifacts (node binaries).
+# Usage:  .\ci\build_windows_artifacts.ps1 [target]
+# Targets supported:
+# - x86_64-pc-windows-msvc
+# - i686-pc-windows-msvc
+# - aarch64-pc-windows-msvc
+
+function Prebuild-Rust {
+    param (
+        [string]$target
+    )
+
+    # Building here for the sake of easier debugging.
+    Push-Location -Path "rust/ffi/node"
+    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 "node"
+    Write-Host "Building node library for $target"
+    npm run build-release -- --target $target
+    npm run pack-build -- --target $target
+    Pop-Location
+}
+
+$targets = $args[0]
+if (-not $targets) {
+    $targets = "x86_64-pc-windows-msvc", "aarch64-pc-windows-msvc"
+}
+
+Write-Host "Building artifacts for targets: $targets"
+foreach ($target in $targets) {
+    Prebuild-Rust $target
+    Build-NodeBinaries $target
+}

ci/build_windows_artifacts_nodejs.ps1

@@ -0,0 +1,42 @@
+# 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
+# - aarch64-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", "aarch64-pc-windows-msvc"
+}
+
+Write-Host "Building artifacts for targets: $targets"
+foreach ($target in $targets) {
+    Prebuild-Rust $target
+    Build-NodeBinaries $target
+}

ci/manylinux_node/Dockerfile

@@ -0,0 +1,27 @@
+# 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/manylinux_2_28_${ARCH}
+
+ARG ARCH=x86_64
+ARG DOCKER_USER=default_user
+
+# 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, but only if it doesn't exist
+RUN echo ${ARCH} && id -u ${DOCKER_USER} >/dev/null 2>&1 || 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_node/build_vectordb.sh

@@ -0,0 +1,13 @@
+#!/bin/bash
+# Builds the node module for manylinux. Invoked by ci/build_linux_artifacts.sh.
+set -e
+ARCH=${1:-x86_64}
+TARGET_TRIPLE=${2:-x86_64-unknown-linux-gnu}
+
+#Alpine doesn't have .bashrc
+FILE=$HOME/.bashrc && test -f $FILE && source $FILE
+
+cd node
+npm ci
+npm run build-release
+npm run pack-build -- -t $TARGET_TRIPLE

ci/manylinux_node/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_node/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 "$HOME"/.bashrc
+
+    nvm install --no-progress 18
+}
+
+install_rust() {
+    echo "Installing rust..."
+    curl https://sh.rustup.rs -sSf | bash -s -- -y
+    export PATH="$PATH:/root/.cargo/bin"
+}
+
+install_node
+install_rust

ci/set_lance_version.py

@@ -1,188 +0,0 @@
-import argparse
-import sys
-import json
-
-
-def run_command(command: str) -> str:
-    """
-    Run a shell command and return stdout as a string.
-    If exit code is not 0, raise an exception with the stderr output.
-    """
-    import subprocess
-
-    result = subprocess.run(command, shell=True, capture_output=True, text=True)
-    if result.returncode != 0:
-        raise Exception(f"Command failed with error: {result.stderr.strip()}")
-    return result.stdout.strip()
-
-
-def get_latest_stable_version() -> str:
-    version_line = run_command("cargo info lance | grep '^version:'")
-    version = version_line.split(" ")[1].strip()
-    return version
-
-
-def get_latest_preview_version() -> str:
-    lance_tags = run_command(
-        "git ls-remote --tags https://github.com/lancedb/lance.git | grep 'refs/tags/v[0-9beta.-]\\+$'"
-    ).splitlines()
-    lance_tags = (
-        tag.split("refs/tags/")[1]
-        for tag in lance_tags
-        if "refs/tags/" in tag and "beta" in tag
-    )
-    from packaging.version import Version
-
-    latest = max(
-        (tag[1:] for tag in lance_tags if tag.startswith("v")), key=lambda t: Version(t)
-    )
-    return str(latest)
-
-
-def extract_features(line: str) -> list:
-    """
-    Extracts the features from a line in Cargo.toml.
-    Example: 'lance = { "version" = "=0.29.0", "features" = ["dynamodb"] }'
-    Returns: ['dynamodb']
-    """
-    import re
-
-    match = re.search(r'"features"\s*=\s*\[\s*(.*?)\s*\]', line, re.DOTALL)
-    if match:
-        features_str = match.group(1)
-        return [f.strip('"') for f in features_str.split(",") if len(f) > 0]
-    return []
-
-
-def update_cargo_toml(line_updater):
-    """
-    Updates the Cargo.toml file by applying the line_updater function to each line.
-    The line_updater function should take a line as input and return the updated line.
-    """
-    with open("Cargo.toml", "r") as f:
-        lines = f.readlines()
-
-    new_lines = []
-    lance_line = ""
-    is_parsing_lance_line = False
-    for line in lines:
-        if line.startswith("lance"):
-            # Update the line using the provided function
-            if line.strip().endswith("}"):
-                new_lines.append(line_updater(line))
-            else:
-                lance_line = line
-                is_parsing_lance_line = True
-        elif is_parsing_lance_line:
-            lance_line += line
-            if line.strip().endswith("}"):
-                new_lines.append(line_updater(lance_line))
-                lance_line = ""
-                is_parsing_lance_line = False
-            else:
-                print("doesn't end with }:", line)
-        else:
-            # Keep the line unchanged
-            new_lines.append(line)
-
-    with open("Cargo.toml", "w") as f:
-        f.writelines(new_lines)
-
-
-def set_stable_version(version: str):
-    """
-    Sets lines to
-    lance = { "version" = "=0.29.0", "features" = ["dynamodb"] }
-    lance-io = "=0.29.0"
-    ...
-    """
-
-    def line_updater(line: str) -> str:
-        package_name = line.split("=", maxsplit=1)[0].strip()
-        features = extract_features(line)
-        if features:
-            return f'{package_name} = {{ "version" = "={version}", "features" = {json.dumps(features)} }}\n'
-        else:
-            return f'{package_name} = "={version}"\n'
-
-    update_cargo_toml(line_updater)
-
-
-def set_preview_version(version: str):
-    """
-    Sets lines to
-    lance = { "version" = "=0.29.0", "features" = ["dynamodb"], tag = "v0.29.0-beta.2", git="https://github.com/lancedb/lance.git" }
-    lance-io = { version = "=0.29.0", tag = "v0.29.0-beta.2", git="https://github.com/lancedb/lance.git" }
-    ...
-    """
-
-    def line_updater(line: str) -> str:
-        package_name = line.split("=", maxsplit=1)[0].strip()
-        features = extract_features(line)
-        base_version = version.split("-")[0]  # Get the base version without beta suffix
-        if features:
-            return f'{package_name} = {{ "version" = "={base_version}", "features" = {json.dumps(features)}, "tag" = "v{version}", "git" = "https://github.com/lancedb/lance.git" }}\n'
-        else:
-            return f'{package_name} = {{ "version" = "={base_version}", "tag" = "v{version}", "git" = "https://github.com/lancedb/lance.git" }}\n'
-
-    update_cargo_toml(line_updater)
-
-
-def set_local_version():
-    """
-    Sets lines to
-    lance = { path = "../lance/rust/lance", features = ["dynamodb"] }
-    lance-io = { path = "../lance/rust/lance-io" }
-    ...
-    """
-
-    def line_updater(line: str) -> str:
-        package_name = line.split("=", maxsplit=1)[0].strip()
-        features = extract_features(line)
-        if features:
-            return f'{package_name} = {{ "path" = "../lance/rust/{package_name}", "features" = {json.dumps(features)} }}\n'
-        else:
-            return f'{package_name} = {{ "path" = "../lance/rust/{package_name}" }}\n'
-
-    update_cargo_toml(line_updater)
-
-
-parser = argparse.ArgumentParser(description="Set the version of the Lance package.")
-parser.add_argument(
-    "version",
-    type=str,
-    help="The version to set for the Lance package. Use 'stable' for the latest stable version, 'preview' for latest preview version, or a specific version number (e.g., '0.1.0'). You can also specify 'local' to use a local path.",
-)
-args = parser.parse_args()
-
-if args.version == "stable":
-    latest_stable_version = get_latest_stable_version()
-    print(
-        f"Found latest stable version: \033[1mv{latest_stable_version}\033[0m",
-        file=sys.stderr,
-    )
-    set_stable_version(latest_stable_version)
-elif args.version == "preview":
-    latest_preview_version = get_latest_preview_version()
-    print(
-        f"Found latest preview version: \033[1mv{latest_preview_version}\033[0m",
-        file=sys.stderr,
-    )
-    set_preview_version(latest_preview_version)
-elif args.version == "local":
-    set_local_version()
-else:
-    # Parse the version number.
-    version = args.version
-    # Ignore initial v if present.
-    if version.startswith("v"):
-        version = version[1:]
-
-    if "beta" in version:
-        set_preview_version(version)
-    else:
-        set_stable_version(version)
-
-print("Updating lockfiles...", file=sys.stderr, end="")
-run_command("cargo metadata > /dev/null")
-print(" done.", file=sys.stderr)

ci/update_lockfiles.sh

@@ -1,30 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-AMEND=false
-
-for arg in "$@"; do
-  if [[ "$arg" == "--amend" ]]; then
-    AMEND=true
-  fi
-done
-
-# This updates the lockfile without building
-cargo metadata --quiet > /dev/null
-
-pushd nodejs || exit 1
-npm install --package-lock-only --silent
-popd
-pushd node || exit 1
-npm install --package-lock-only --silent
-popd
-
-if git diff --quiet --exit-code; then
-  echo "No lockfile changes to commit; skipping amend."
-elif $AMEND; then
-  git add Cargo.lock nodejs/package-lock.json node/package-lock.json
-  git commit --amend --no-edit
-else
-  git add Cargo.lock nodejs/package-lock.json node/package-lock.json
-  git commit -m "Update lockfiles"
-fi

docs/mkdocs.yml

@@ -103,6 +103,262 @@ markdown_extensions:
       permalink: ""
 
 nav:
+  - Home:
+      - LanceDB: index.md
+      - 👉 Quickstart: quickstart.md
+      - 🏃🏼‍♂️ Basic Usage: basic.md
+      - 📚 Concepts:
+          - Vector search: concepts/vector_search.md
+          - Indexing:
+              - IVFPQ: concepts/index_ivfpq.md
+              - HNSW: concepts/index_hnsw.md
+          - Storage: concepts/storage.md
+          - Data management: concepts/data_management.md
+      - 🔨 Guides:
+          - Working with tables: guides/tables.md
+          - Building a vector index: ann_indexes.md
+          - Vector Search: search.md
+          - Full-text search (native): fts.md
+          - Full-text search (tantivy-based): fts_tantivy.md
+          - Building a scalar index: guides/scalar_index.md
+          - Hybrid search:
+              - Overview: hybrid_search/hybrid_search.md
+              - Comparing Rerankers: hybrid_search/eval.md
+              - Airbnb financial data example: notebooks/hybrid_search.ipynb
+          - Late interaction with MultiVector search:
+              - Overview: guides/multi-vector.md
+              - Example: notebooks/Multivector_on_LanceDB.ipynb
+          - RAG:
+              - Vanilla RAG: rag/vanilla_rag.md
+              - Multi-head RAG: rag/multi_head_rag.md
+              - Corrective RAG: rag/corrective_rag.md
+              - Agentic RAG: rag/agentic_rag.md
+              - Graph RAG: rag/graph_rag.md
+              - Self RAG: rag/self_rag.md
+              - Adaptive RAG: rag/adaptive_rag.md
+              - SFR RAG: rag/sfr_rag.md
+              - Advanced Techniques:
+                  - HyDE: rag/advanced_techniques/hyde.md
+                  - FLARE: rag/advanced_techniques/flare.md
+          - Reranking:
+              - Quickstart: reranking/index.md
+              - Cohere Reranker: reranking/cohere.md
+              - Linear Combination Reranker: reranking/linear_combination.md
+              - Reciprocal Rank Fusion Reranker: reranking/rrf.md
+              - Cross Encoder Reranker: reranking/cross_encoder.md
+              - ColBERT Reranker: reranking/colbert.md
+              - Jina Reranker: reranking/jina.md
+              - OpenAI Reranker: reranking/openai.md
+              - AnswerDotAi Rerankers: reranking/answerdotai.md
+              - Voyage AI Rerankers: reranking/voyageai.md
+              - Building Custom Rerankers: reranking/custom_reranker.md
+              - Example: notebooks/lancedb_reranking.ipynb
+          - Filtering: sql.md
+          - Versioning & Reproducibility:
+              - sync API: notebooks/reproducibility.ipynb
+              - async API: notebooks/reproducibility_async.ipynb
+          - Configuring Storage: guides/storage.md
+          - Migration Guide: migration.md
+          - Tuning retrieval performance:
+              - Choosing right query type: guides/tuning_retrievers/1_query_types.md
+              - Reranking: guides/tuning_retrievers/2_reranking.md
+              - Embedding fine-tuning: guides/tuning_retrievers/3_embed_tuning.md
+      - 🧬 Managing embeddings:
+          - Understand Embeddings: embeddings/understanding_embeddings.md
+          - Get Started: embeddings/index.md
+          - Embedding functions: embeddings/embedding_functions.md
+          - Available models:
+              - Overview: embeddings/default_embedding_functions.md
+              - Text Embedding Functions:
+                  - Sentence Transformers: embeddings/available_embedding_models/text_embedding_functions/sentence_transformers.md
+                  - Huggingface Embedding Models: embeddings/available_embedding_models/text_embedding_functions/huggingface_embedding.md
+                  - Ollama Embeddings: embeddings/available_embedding_models/text_embedding_functions/ollama_embedding.md
+                  - OpenAI Embeddings: embeddings/available_embedding_models/text_embedding_functions/openai_embedding.md
+                  - Instructor Embeddings: embeddings/available_embedding_models/text_embedding_functions/instructor_embedding.md
+                  - Gemini Embeddings: embeddings/available_embedding_models/text_embedding_functions/gemini_embedding.md
+                  - Cohere Embeddings: embeddings/available_embedding_models/text_embedding_functions/cohere_embedding.md
+                  - Jina Embeddings: embeddings/available_embedding_models/text_embedding_functions/jina_embedding.md
+                  - AWS Bedrock Text Embedding Functions: embeddings/available_embedding_models/text_embedding_functions/aws_bedrock_embedding.md
+                  - IBM watsonx.ai Embeddings: embeddings/available_embedding_models/text_embedding_functions/ibm_watsonx_ai_embedding.md
+                  - Voyage AI Embeddings: embeddings/available_embedding_models/text_embedding_functions/voyageai_embedding.md
+              - Multimodal Embedding Functions:
+                  - OpenClip embeddings: embeddings/available_embedding_models/multimodal_embedding_functions/openclip_embedding.md
+                  - Imagebind embeddings: embeddings/available_embedding_models/multimodal_embedding_functions/imagebind_embedding.md
+                  - Jina Embeddings: embeddings/available_embedding_models/multimodal_embedding_functions/jina_multimodal_embedding.md
+          - User-defined embedding functions: embeddings/custom_embedding_function.md
+          - Variables and secrets: embeddings/variables_and_secrets.md
+          - "Example: Multi-lingual semantic search": notebooks/multi_lingual_example.ipynb
+          - "Example: MultiModal CLIP Embeddings": notebooks/DisappearingEmbeddingFunction.ipynb
+      - 🔌 Integrations:
+          - Tools and data formats: integrations/index.md
+          - Pandas and PyArrow: python/pandas_and_pyarrow.md
+          - Polars: python/polars_arrow.md
+          - DuckDB: python/duckdb.md
+          - LangChain:
+              - LangChain 🔗: integrations/langchain.md
+              - LangChain demo: notebooks/langchain_demo.ipynb
+              - LangChain JS/TS 🔗: https://js.langchain.com/docs/integrations/vectorstores/lancedb
+          - LlamaIndex 🦙:
+              - LlamaIndex docs: integrations/llamaIndex.md
+              - LlamaIndex demo: notebooks/llamaIndex_demo.ipynb
+          - Pydantic: python/pydantic.md
+          - Voxel51: integrations/voxel51.md
+          - PromptTools: integrations/prompttools.md
+          - dlt: integrations/dlt.md
+          - phidata: integrations/phidata.md
+      - 🎯 Examples:
+          - Overview: examples/index.md
+          - 🐍 Python:
+              - Overview: examples/examples_python.md
+              - Build From Scratch: examples/python_examples/build_from_scratch.md
+              - Multimodal: examples/python_examples/multimodal.md
+              - Rag: examples/python_examples/rag.md
+              - Vector Search: examples/python_examples/vector_search.md
+              - Chatbot: examples/python_examples/chatbot.md
+              - Evaluation: examples/python_examples/evaluations.md
+              - AI Agent: examples/python_examples/aiagent.md
+              - Recommender System: examples/python_examples/recommendersystem.md
+              - Miscellaneous:
+                  - Serverless QA Bot with S3 and Lambda: examples/serverless_lancedb_with_s3_and_lambda.md
+                  - Serverless QA Bot with Modal: examples/serverless_qa_bot_with_modal_and_langchain.md
+          - 👾 JavaScript:
+              - Overview: examples/examples_js.md
+              - Serverless Website Chatbot: examples/serverless_website_chatbot.md
+              - YouTube Transcript Search: examples/youtube_transcript_bot_with_nodejs.md
+              - TransformersJS Embedding Search: examples/transformerjs_embedding_search_nodejs.md
+          - 🦀 Rust:
+              - Overview: examples/examples_rust.md
+      - 📓 Studies:
+          - ↗Improve retrievers with hybrid search and reranking: https://blog.lancedb.com/hybrid-search-and-reranking-report/
+      - 💭 FAQs: faq.md
+      - 🔍 Troubleshooting: troubleshooting.md
+      - ⚙️ API reference:
+          - 🐍 Python: python/python.md
+          - 👾 JavaScript (vectordb): javascript/modules.md
+          - 👾 JavaScript (lancedb): js/globals.md
+          - 🦀 Rust: https://docs.rs/lancedb/latest/lancedb/
+
+  - Getting Started:
+      - Quickstart: quickstart.md
+      - Basic Usage: basic.md
+  - Concepts:
+      - Vector search: concepts/vector_search.md
+      - Indexing:
+          - IVFPQ: concepts/index_ivfpq.md
+          - HNSW: concepts/index_hnsw.md
+      - Storage: concepts/storage.md
+      - Data management: concepts/data_management.md
+  - Guides:
+      - Working with tables: guides/tables.md
+      - Building an ANN index: ann_indexes.md
+      - Vector Search: search.md
+      - Full-text search (native): fts.md
+      - Full-text search (tantivy-based): fts_tantivy.md
+      - Building a scalar index: guides/scalar_index.md
+      - Hybrid search:
+          - Overview: hybrid_search/hybrid_search.md
+          - Comparing Rerankers: hybrid_search/eval.md
+          - Airbnb financial data example: notebooks/hybrid_search.ipynb
+      - Late interaction with MultiVector search:
+          - Overview: guides/multi-vector.md
+          - Document search Example: notebooks/Multivector_on_LanceDB.ipynb
+      - RAG:
+          - Vanilla RAG: rag/vanilla_rag.md
+          - Multi-head RAG: rag/multi_head_rag.md
+          - Corrective RAG: rag/corrective_rag.md
+          - Agentic RAG: rag/agentic_rag.md
+          - Graph RAG: rag/graph_rag.md
+          - Self RAG: rag/self_rag.md
+          - Adaptive RAG: rag/adaptive_rag.md
+          - SFR RAG: rag/sfr_rag.md
+          - Advanced Techniques:
+              - HyDE: rag/advanced_techniques/hyde.md
+              - FLARE: rag/advanced_techniques/flare.md
+      - Reranking:
+          - Quickstart: reranking/index.md
+          - Cohere Reranker: reranking/cohere.md
+          - Linear Combination Reranker: reranking/linear_combination.md
+          - Reciprocal Rank Fusion Reranker: reranking/rrf.md
+          - Cross Encoder Reranker: reranking/cross_encoder.md
+          - ColBERT Reranker: reranking/colbert.md
+          - Jina Reranker: reranking/jina.md
+          - OpenAI Reranker: reranking/openai.md
+          - AnswerDotAi Rerankers: reranking/answerdotai.md
+          - Building Custom Rerankers: reranking/custom_reranker.md
+          - Example: notebooks/lancedb_reranking.ipynb
+      - Filtering: sql.md
+      - Versioning & Reproducibility:
+          - sync API: notebooks/reproducibility.ipynb
+          - async API: notebooks/reproducibility_async.ipynb
+      - Configuring Storage: guides/storage.md
+      - Migration Guide: migration.md
+      - Tuning retrieval performance:
+          - Choosing right query type: guides/tuning_retrievers/1_query_types.md
+          - Reranking: guides/tuning_retrievers/2_reranking.md
+          - Embedding fine-tuning: guides/tuning_retrievers/3_embed_tuning.md
+  - Managing Embeddings:
+      - Understand Embeddings: embeddings/understanding_embeddings.md
+      - Get Started: embeddings/index.md
+      - Embedding functions: embeddings/embedding_functions.md
+      - Available models:
+          - Overview: embeddings/default_embedding_functions.md
+          - Text Embedding Functions:
+              - Sentence Transformers: embeddings/available_embedding_models/text_embedding_functions/sentence_transformers.md
+              - Huggingface Embedding Models: embeddings/available_embedding_models/text_embedding_functions/huggingface_embedding.md
+              - Ollama Embeddings: embeddings/available_embedding_models/text_embedding_functions/ollama_embedding.md
+              - OpenAI Embeddings: embeddings/available_embedding_models/text_embedding_functions/openai_embedding.md
+              - Instructor Embeddings: embeddings/available_embedding_models/text_embedding_functions/instructor_embedding.md
+              - Gemini Embeddings: embeddings/available_embedding_models/text_embedding_functions/gemini_embedding.md
+              - Cohere Embeddings: embeddings/available_embedding_models/text_embedding_functions/cohere_embedding.md
+              - Jina Embeddings: embeddings/available_embedding_models/text_embedding_functions/jina_embedding.md
+              - AWS Bedrock Text Embedding Functions: embeddings/available_embedding_models/text_embedding_functions/aws_bedrock_embedding.md
+              - IBM watsonx.ai Embeddings: embeddings/available_embedding_models/text_embedding_functions/ibm_watsonx_ai_embedding.md
+          - Multimodal Embedding Functions:
+              - OpenClip embeddings: embeddings/available_embedding_models/multimodal_embedding_functions/openclip_embedding.md
+              - Imagebind embeddings: embeddings/available_embedding_models/multimodal_embedding_functions/imagebind_embedding.md
+              - Jina Embeddings: embeddings/available_embedding_models/multimodal_embedding_functions/jina_multimodal_embedding.md
+      - User-defined embedding functions: embeddings/custom_embedding_function.md
+      - Variables and secrets: embeddings/variables_and_secrets.md
+      - "Example: Multi-lingual semantic search": notebooks/multi_lingual_example.ipynb
+      - "Example: MultiModal CLIP Embeddings": notebooks/DisappearingEmbeddingFunction.ipynb
+  - Integrations:
+      - Overview: integrations/index.md
+      - Pandas and PyArrow: python/pandas_and_pyarrow.md
+      - Polars: python/polars_arrow.md
+      - DuckDB: python/duckdb.md
+      - LangChain 🦜️🔗↗: integrations/langchain.md
+      - LangChain.js 🦜️🔗↗: https://js.langchain.com/docs/integrations/vectorstores/lancedb
+      - LlamaIndex 🦙↗: integrations/llamaIndex.md
+      - Pydantic: python/pydantic.md
+      - Voxel51: integrations/voxel51.md
+      - PromptTools: integrations/prompttools.md
+      - dlt: integrations/dlt.md
+      - phidata: integrations/phidata.md
+  - Examples:
+      - examples/index.md
+      - 🐍 Python:
+          - Overview: examples/examples_python.md
+          - Build From Scratch: examples/python_examples/build_from_scratch.md
+          - Multimodal: examples/python_examples/multimodal.md
+          - Rag: examples/python_examples/rag.md
+          - Vector Search: examples/python_examples/vector_search.md
+          - Chatbot: examples/python_examples/chatbot.md
+          - Evaluation: examples/python_examples/evaluations.md
+          - AI Agent: examples/python_examples/aiagent.md
+          - Recommender System: examples/python_examples/recommendersystem.md
+          - Miscellaneous:
+              - Serverless QA Bot with S3 and Lambda: examples/serverless_lancedb_with_s3_and_lambda.md
+              - Serverless QA Bot with Modal: examples/serverless_qa_bot_with_modal_and_langchain.md
+      - 👾 JavaScript:
+          - Overview: examples/examples_js.md
+          - Serverless Website Chatbot: examples/serverless_website_chatbot.md
+          - YouTube Transcript Search: examples/youtube_transcript_bot_with_nodejs.md
+          - TransformersJS Embedding Search: examples/transformerjs_embedding_search_nodejs.md
+      - 🦀 Rust:
+          - Overview: examples/examples_rust.md
+  - Studies:
+      - studies/overview.md
+      - ↗Improve retrievers with hybrid search and reranking: https://blog.lancedb.com/hybrid-search-and-reranking-report/
   - API reference:
       - Overview: api_reference.md
       - Python: python/python.md

docs/overrides/partials/main.html

@@ -1,5 +0,0 @@
-{% extends "base.html" %}
-
-{% block announce %}
-  📚 Starting June 1st, 2025, please use <a href="https://lancedb.github.io/documentation" target="_blank" rel="noopener noreferrer">lancedb.github.io/documentation</a> for the latest docs.
-{% endblock %}

docs/package-lock.json

@@ -19,7 +19,7 @@
     },
     "../node": {
       "name": "vectordb",
-      "version": "0.21.2-beta.0",
+      "version": "0.12.0",
       "cpu": [
         "x64",
         "arm64"
@@ -65,11 +65,11 @@
         "uuid": "^9.0.0"
       },
       "optionalDependencies": {
-        "@lancedb/vectordb-darwin-arm64": "0.21.2-beta.0",
-        "@lancedb/vectordb-darwin-x64": "0.21.2-beta.0",
-        "@lancedb/vectordb-linux-arm64-gnu": "0.21.2-beta.0",
-        "@lancedb/vectordb-linux-x64-gnu": "0.21.2-beta.0",
-        "@lancedb/vectordb-win32-x64-msvc": "0.21.2-beta.0"
+        "@lancedb/vectordb-darwin-arm64": "0.12.0",
+        "@lancedb/vectordb-darwin-x64": "0.12.0",
+        "@lancedb/vectordb-linux-arm64-gnu": "0.12.0",
+        "@lancedb/vectordb-linux-x64-gnu": "0.12.0",
+        "@lancedb/vectordb-win32-x64-msvc": "0.12.0"
       },
       "peerDependencies": {
         "@apache-arrow/ts": "^14.0.2",

docs/src/ann_indexes.md

@@ -291,7 +291,7 @@ Product quantization can lead to approximately `16 * sizeof(float32) / 1 = 64` t
 
 `num_partitions` is used to decide how many partitions the first level `IVF` index uses.
 Higher number of partitions could lead to more efficient I/O during queries and better accuracy, but it takes much more time to train.
-On `SIFT-1M` dataset, our benchmark shows that keeping each partition 4K-8K rows lead to a good latency / recall.
+On `SIFT-1M` dataset, our benchmark shows that keeping each partition 1K-4K rows lead to a good latency / recall.
 
 `num_sub_vectors` specifies how many Product Quantization (PQ) short codes to generate on each vector. The number should be a factor of the vector dimension. Because
 PQ is a lossy compression of the original vector, a higher `num_sub_vectors` usually results in

docs/src/basic.md

@@ -1,4 +1,4 @@
-# Quick start
+# Basic Usage
 
 !!! info "LanceDB can be run in a number of ways:"
 

docs/src/guides/sql_querying.md

@@ -1,60 +0,0 @@
-# SQL Querying
-
-You can use DuckDB and Apache Datafusion to query your LanceDB tables using SQL.
-This guide will show how to query Lance tables them using both.
-
-We will re-use the dataset [created previously](./tables.md):
-
-```python
-import lancedb
-
-db = lancedb.connect("data/sample-lancedb")
-data = [
-    {"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
-    {"vector": [5.9, 26.5], "item": "bar", "price": 20.0}
-]
-table = db.create_table("pd_table", data=data)
-```
-
-## Querying a LanceDB Table with DuckDb
-
-The `to_lance` method converts the LanceDB table to a `LanceDataset`, which is accessible to DuckDB through the Arrow compatibility layer.
-To query the resulting Lance dataset in DuckDB, all you need to do is reference the dataset by the same name in your SQL query.
-
-```python
-import duckdb
-
-arrow_table = table.to_lance()
-
-duckdb.query("SELECT * FROM arrow_table")
-```
-
-| vector      | item | price |
-| ----------- | ---- | ----- |
-| [3.1, 4.1]  | foo  | 10.0  |
-| [5.9, 26.5] | bar  | 20.0  |
-
-## Querying a LanceDB Table with Apache Datafusion
-
-Have the required imports before doing any querying.
-
-=== "Python"
-
-    ```python
-    --8<-- "python/python/tests/docs/test_guide_tables.py:import-lancedb"
-    --8<-- "python/python/tests/docs/test_guide_tables.py:import-session-context"
-    --8<-- "python/python/tests/docs/test_guide_tables.py:import-ffi-dataset"
-    ```
-
-Register the table created with the Datafusion session context.
-
-=== "Python"
-
-    ```python
-    --8<-- "python/python/tests/docs/test_guide_tables.py:lance_sql_basic"
-    ```
-
-| vector      | item | price |
-| ----------- | ---- | ----- |
-| [3.1, 4.1]  | foo  | 10.0  |
-| [5.9, 26.5] | bar  | 20.0  |

docs/src/guides/tables.md

@@ -765,7 +765,7 @@ This can be used to update zero to all rows depending on how many rows match the
         ];
         const tbl = await db.createTable("my_table", data)
 
-        await tbl.update({
+        await tbl.update({ 
             values: { vector: [10, 10] },
             where: "x = 2"
         });
@@ -787,9 +787,9 @@ This can be used to update zero to all rows depending on how many rows match the
         ];
         const tbl = await db.createTable("my_table", data)
 
-        await tbl.update({
-            where: "x = 2",
-            values: { vector: [10, 10] }
+        await tbl.update({ 
+            where: "x = 2", 
+            values: { vector: [10, 10] } 
         });
         ```
 

docs/src/integrations/genkit.md

@@ -1,183 +0,0 @@
-### genkitx-lancedb
-This is a lancedb plugin for genkit framework. It allows you to use LanceDB for ingesting and rereiving data using genkit framework.
-
-![integration-banner-genkit](https://github.com/user-attachments/assets/a6cc28af-98e9-4425-b87c-7ab139bd7893)
-
-### Installation
-```bash
-pnpm install genkitx-lancedb
-```
-
-### Usage
-
-Adding LanceDB plugin to your genkit instance.
-
-```ts
-import { lancedbIndexerRef, lancedb, lancedbRetrieverRef, WriteMode } from 'genkitx-lancedb';
-import { textEmbedding004, vertexAI } from '@genkit-ai/vertexai';
-import { gemini } from '@genkit-ai/vertexai';
-import { z, genkit } from 'genkit';
-import { Document } from 'genkit/retriever';
-import { chunk } from 'llm-chunk';
-import { readFile } from 'fs/promises';
-import path from 'path';
-import pdf from 'pdf-parse/lib/pdf-parse';
-
-const ai = genkit({
-  plugins: [
-    // vertexAI provides the textEmbedding004 embedder
-    vertexAI(),
-
-    // the local vector store requires an embedder to translate from text to vector
-    lancedb([
-      {
-        dbUri: '.db', // optional lancedb uri, default to .db
-        tableName: 'table', // optional table name, default to table
-        embedder: textEmbedding004,
-      },
-    ]),
-  ],
-});
-```
-
-You can run this app with the following command:
-```bash
-genkit start -- tsx --watch src/index.ts
-```
-
-This'll add LanceDB as a retriever and indexer to the genkit instance. You can see it in the GUI view
-<img width="1710" alt="Screenshot 2025-05-11 at 7 21 05 PM" src="https://github.com/user-attachments/assets/e752f7f4-785b-4797-a11e-72ab06a531b7" />
-
-**Testing retrieval on a sample table**
-Let's see the raw retrieval results
-
-<img width="1710" alt="Screenshot 2025-05-11 at 7 21 05 PM" src="https://github.com/user-attachments/assets/b8d356ed-8421-4790-8fc0-d6af563b9657" />
-On running this query, you'll 5 results fetched from the lancedb table, where each result looks something like this:
-<img width="1417" alt="Screenshot 2025-05-11 at 7 21 18 PM" src="https://github.com/user-attachments/assets/77429525-36e2-4da6-a694-e58c1cf9eb83" />
-
-
-
-## Creating a custom RAG flow
-
-Now that we've seen how you can use LanceDB for in a genkit pipeline, let's refine the flow and create a RAG. A RAG flow will consist of an index and a retreiver with its outputs postprocessed an fed into an LLM for final response
-
-### Creating custom indexer flows
-You can also create custom indexer flows, utilizing more options and features provided by LanceDB.
-
-```ts
-export const menuPdfIndexer = lancedbIndexerRef({
-   // Using all defaults, for dbUri, tableName, and embedder, etc
-});
-
-const chunkingConfig = {
-  minLength: 1000,
-  maxLength: 2000,
-  splitter: 'sentence',
-  overlap: 100,
-  delimiters: '',
-} as any;
-
-
-async function extractTextFromPdf(filePath: string) {
-  const pdfFile = path.resolve(filePath);
-  const dataBuffer = await readFile(pdfFile);
-  const data = await pdf(dataBuffer);
-  return data.text;
-}
-
-export const indexMenu = ai.defineFlow(
-  {
-    name: 'indexMenu',
-    inputSchema: z.string().describe('PDF file path'),
-    outputSchema: z.void(),
-  },
-  async (filePath: string) => {
-    filePath = path.resolve(filePath);
-
-    // Read the pdf.
-    const pdfTxt = await ai.run('extract-text', () =>
-      extractTextFromPdf(filePath)
-    );
-
-    // Divide the pdf text into segments.
-    const chunks = await ai.run('chunk-it', async () =>
-      chunk(pdfTxt, chunkingConfig)
-    );
-
-    // Convert chunks of text into documents to store in the index.
-    const documents = chunks.map((text) => {
-      return Document.fromText(text, { filePath });
-    });
-
-    // Add documents to the index.
-    await ai.index({
-      indexer: menuPdfIndexer,
-      documents,
-      options: {
-        writeMode: WriteMode.Overwrite,
-      } as any
-    });
-  }
-);
-```
-
-<img width="1316" alt="Screenshot 2025-05-11 at 8 35 56 PM" src="https://github.com/user-attachments/assets/e2a20ce4-d1d0-4fa2-9a84-f2cc26e3a29f" />
-
-In your console, you can see the logs
-
-<img width="511" alt="Screenshot 2025-05-11 at 7 19 14 PM" src="https://github.com/user-attachments/assets/243f26c5-ed38-40b6-b661-002f40f0423a" />
-
-### Creating custom retriever flows
-You can also create custom retriever flows, utilizing more options and features provided by LanceDB.
-```ts
-export const menuRetriever = lancedbRetrieverRef({
-  tableName: "table", // Use the same table name as the indexer.
-  displayName: "Menu", // Use a custom display name.
-
-export const menuQAFlow = ai.defineFlow(
-  { name: "Menu", inputSchema: z.string(), outputSchema: z.string() },
-  async (input: string) => {
-    // retrieve relevant documents
-    const docs = await ai.retrieve({
-      retriever: menuRetriever,
-      query: input,
-      options: { 
-        k: 3,
-      },
-    });
-
-    const extractedContent = docs.map(doc => {
-      if (doc.content && Array.isArray(doc.content) && doc.content.length > 0) {
-        if (doc.content[0].media && doc.content[0].media.url) {
-          return doc.content[0].media.url;
-        }
-      }
-      return "No content found";
-    });
-
-    console.log("Extracted content:", extractedContent);
-
-    const { text } = await ai.generate({
-      model: gemini('gemini-2.0-flash'),
-      prompt: `
-You are acting as a helpful AI assistant that can answer 
-questions about the food available on the menu at Genkit Grub Pub.
-
-Use only the context provided to answer the question.
-If you don't know, do not make up an answer.
-Do not add or change items on the menu.
-
-Context:
-${extractedContent.join('\n\n')}
-
-Question: ${input}`,
-      docs,
-    });
-    
-    return text;
-  }
-);
-```
-Now using our retrieval flow, we can ask question about the ingsted PDF
-<img width="1306" alt="Screenshot 2025-05-11 at 7 18 45 PM" src="https://github.com/user-attachments/assets/86c66b13-7c12-4d5f-9d81-ae36bfb1c346" />
-

docs/src/js/classes/BooleanQuery.md

@@ -1,53 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / BooleanQuery
-
-# Class: BooleanQuery
-
-Represents a full-text query interface.
-This interface defines the structure and behavior for full-text queries,
-including methods to retrieve the query type and convert the query to a dictionary format.
-
-## Implements
-
-- [`FullTextQuery`](../interfaces/FullTextQuery.md)
-
-## Constructors
-
-### new BooleanQuery()
-
-```ts
-new BooleanQuery(queries): BooleanQuery
-```
-
-Creates an instance of BooleanQuery.
-
-#### Parameters
-
-* **queries**: [[`Occur`](../enumerations/Occur.md), [`FullTextQuery`](../interfaces/FullTextQuery.md)][]
-    An array of (Occur, FullTextQuery objects) to combine.
-    Occur specifies whether the query must match, or should match.
-
-#### Returns
-
-[`BooleanQuery`](BooleanQuery.md)
-
-## Methods
-
-### queryType()
-
-```ts
-queryType(): FullTextQueryType
-```
-
-The type of the full-text query.
-
-#### Returns
-
-[`FullTextQueryType`](../enumerations/FullTextQueryType.md)
-
-#### Implementation of
-
-[`FullTextQuery`](../interfaces/FullTextQuery.md).[`queryType`](../interfaces/FullTextQuery.md#querytype)

docs/src/js/classes/MatchQuery.md

@@ -40,8 +40,6 @@ Creates an instance of MatchQuery.
     - `boost`: The boost factor for the query (default is 1.0).
     - `fuzziness`: The fuzziness level for the query (default is 0).
     - `maxExpansions`: The maximum number of terms to consider for fuzzy matching (default is 50).
-    - `operator`: The logical operator to use for combining terms in the query (default is "OR").
-    - `prefixLength`: The number of beginning characters being unchanged for fuzzy matching.
 
 * **options.boost?**: `number`
 
@@ -49,10 +47,6 @@ Creates an instance of MatchQuery.
 
 * **options.maxExpansions?**: `number`
 
-* **options.operator?**: [`Operator`](../enumerations/Operator.md)
-
-* **options.prefixLength?**: `number`
-
 #### Returns
 
 [`MatchQuery`](MatchQuery.md)

docs/src/js/classes/MergeInsertBuilder.md

@@ -33,7 +33,7 @@ Construct a MergeInsertBuilder. __Internal use only.__
 ### execute()
 
 ```ts
-execute(data, execOptions?): Promise<MergeResult>
+execute(data): Promise<MergeStats>
 ```
 
 Executes the merge insert operation
@@ -42,13 +42,11 @@ Executes the merge insert operation
 
 * **data**: [`Data`](../type-aliases/Data.md)
 
-* **execOptions?**: `Partial`&lt;[`WriteExecutionOptions`](../interfaces/WriteExecutionOptions.md)&gt;
-
 #### Returns
 
-`Promise`&lt;[`MergeResult`](../interfaces/MergeResult.md)&gt;
+`Promise`&lt;[`MergeStats`](../interfaces/MergeStats.md)&gt;
 
-the merge result
+Statistics about the merge operation: counts of inserted, updated, and deleted rows
 
 ***
 

docs/src/js/classes/MultiMatchQuery.md

@@ -38,12 +38,9 @@ Creates an instance of MultiMatchQuery.
 * **options?**
     Optional parameters for the multi-match query.
     - `boosts`: An array of boost factors for each column (default is 1.0 for all).
-    - `operator`: The logical operator to use for combining terms in the query (default is "OR").
 
 * **options.boosts?**: `number`[]
 
-* **options.operator?**: [`Operator`](../enumerations/Operator.md)
-
 #### Returns
 
 [`MultiMatchQuery`](MultiMatchQuery.md)

docs/src/js/classes/PhraseQuery.md

@@ -19,10 +19,7 @@ including methods to retrieve the query type and convert the query to a dictiona
 ### new PhraseQuery()
 
 ```ts
-new PhraseQuery(
-   query,
-   column,
-   options?): PhraseQuery
+new PhraseQuery(query, column): PhraseQuery
 ```
 
 Creates an instance of `PhraseQuery`.
@@ -35,12 +32,6 @@ Creates an instance of `PhraseQuery`.
 * **column**: `string`
     The name of the column to search within.
 
-* **options?**
-    Optional parameters for the phrase query.
-    - `slop`: The maximum number of intervening unmatched positions allowed between words in the phrase (default is 0).
-
-* **options.slop?**: `number`
-
 #### Returns
 
 [`PhraseQuery`](PhraseQuery.md)

docs/src/js/classes/Session.md

@@ -1,84 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / Session
-
-# Class: Session
-
-A session for managing caches and object stores across LanceDB operations.
-
-Sessions allow you to configure cache sizes for index and metadata caches,
-which can significantly impact performance for large datasets.
-
-## Constructors
-
-### new Session()
-
-```ts
-new Session(indexCacheSizeBytes?, metadataCacheSizeBytes?): Session
-```
-
-Create a new session with custom cache sizes.
-
-# Parameters
-
-- `index_cache_size_bytes`: The size of the index cache in bytes.
-  Defaults to 6GB if not specified.
-- `metadata_cache_size_bytes`: The size of the metadata cache in bytes.
-  Defaults to 1GB if not specified.
-
-#### Parameters
-
-* **indexCacheSizeBytes?**: `null` \| `bigint`
-
-* **metadataCacheSizeBytes?**: `null` \| `bigint`
-
-#### Returns
-
-[`Session`](Session.md)
-
-## Methods
-
-### approxNumItems()
-
-```ts
-approxNumItems(): number
-```
-
-Get the approximate number of items cached in the session.
-
-#### Returns
-
-`number`
-
-***
-
-### sizeBytes()
-
-```ts
-sizeBytes(): bigint
-```
-
-Get the current size of the session caches in bytes.
-
-#### Returns
-
-`bigint`
-
-***
-
-### default()
-
-```ts
-static default(): Session
-```
-
-Create a session with default cache sizes.
-
-This is equivalent to creating a session with 6GB index cache
-and 1GB metadata cache.
-
-#### Returns
-
-[`Session`](Session.md)

docs/src/js/classes/Table.md

@@ -40,7 +40,7 @@ Returns the name of the table
 ### add()
 
 ```ts
-abstract add(data, options?): Promise<AddResult>
+abstract add(data, options?): Promise<void>
 ```
 
 Insert records into this Table.
@@ -54,17 +54,14 @@ Insert records into this Table.
 
 #### Returns
 
-`Promise`&lt;[`AddResult`](../interfaces/AddResult.md)&gt;
-
-A promise that resolves to an object
-containing the new version number of the table
+`Promise`&lt;`void`&gt;
 
 ***
 
 ### addColumns()
 
 ```ts
-abstract addColumns(newColumnTransforms): Promise<AddColumnsResult>
+abstract addColumns(newColumnTransforms): Promise<void>
 ```
 
 Add new columns with defined values.
@@ -79,17 +76,14 @@ Add new columns with defined values.
 
 #### Returns
 
-`Promise`&lt;[`AddColumnsResult`](../interfaces/AddColumnsResult.md)&gt;
-
-A promise that resolves to an object
-containing the new version number of the table after adding the columns.
+`Promise`&lt;`void`&gt;
 
 ***
 
 ### alterColumns()
 
 ```ts
-abstract alterColumns(columnAlterations): Promise<AlterColumnsResult>
+abstract alterColumns(columnAlterations): Promise<void>
 ```
 
 Alter the name or nullability of columns.
@@ -102,10 +96,7 @@ Alter the name or nullability of columns.
 
 #### Returns
 
-`Promise`&lt;[`AlterColumnsResult`](../interfaces/AlterColumnsResult.md)&gt;
-
-A promise that resolves to an object
-containing the new version number of the table after altering the columns.
+`Promise`&lt;`void`&gt;
 
 ***
 
@@ -261,7 +252,7 @@ await table.createIndex("my_float_col");
 ### delete()
 
 ```ts
-abstract delete(predicate): Promise<DeleteResult>
+abstract delete(predicate): Promise<void>
 ```
 
 Delete the rows that satisfy the predicate.
@@ -272,10 +263,7 @@ Delete the rows that satisfy the predicate.
 
 #### Returns
 
-`Promise`&lt;[`DeleteResult`](../interfaces/DeleteResult.md)&gt;
-
-A promise that resolves to an object
-containing the new version number of the table
+`Promise`&lt;`void`&gt;
 
 ***
 
@@ -296,7 +284,7 @@ Return a brief description of the table
 ### dropColumns()
 
 ```ts
-abstract dropColumns(columnNames): Promise<DropColumnsResult>
+abstract dropColumns(columnNames): Promise<void>
 ```
 
 Drop one or more columns from the dataset
@@ -315,10 +303,7 @@ then call ``cleanup_files`` to remove the old files.
 
 #### Returns
 
-`Promise`&lt;[`DropColumnsResult`](../interfaces/DropColumnsResult.md)&gt;
-
-A promise that resolves to an object
-containing the new version number of the table after dropping the columns.
+`Promise`&lt;`void`&gt;
 
 ***
 
@@ -612,7 +597,7 @@ of the given query
 
 #### Parameters
 
-* **query**: `string` \| [`IntoVector`](../type-aliases/IntoVector.md) \| [`MultiVector`](../type-aliases/MultiVector.md) \| [`FullTextQuery`](../interfaces/FullTextQuery.md)
+* **query**: `string` \| [`IntoVector`](../type-aliases/IntoVector.md) \| [`FullTextQuery`](../interfaces/FullTextQuery.md)
     the query, a vector or string
 
 * **queryType?**: `string`
@@ -693,7 +678,7 @@ Return the table as an arrow table
 #### update(opts)
 
 ```ts
-abstract update(opts): Promise<UpdateResult>
+abstract update(opts): Promise<void>
 ```
 
 Update existing records in the Table
@@ -704,10 +689,7 @@ Update existing records in the Table
 
 ##### Returns
 
-`Promise`&lt;[`UpdateResult`](../interfaces/UpdateResult.md)&gt;
-
-A promise that resolves to an object containing
-the number of rows updated and the new version number
+`Promise`&lt;`void`&gt;
 
 ##### Example
 
@@ -718,7 +700,7 @@ table.update({where:"x = 2", values:{"vector": [10, 10]}})
 #### update(opts)
 
 ```ts
-abstract update(opts): Promise<UpdateResult>
+abstract update(opts): Promise<void>
 ```
 
 Update existing records in the Table
@@ -729,10 +711,7 @@ Update existing records in the Table
 
 ##### Returns
 
-`Promise`&lt;[`UpdateResult`](../interfaces/UpdateResult.md)&gt;
-
-A promise that resolves to an object containing
-the number of rows updated and the new version number
+`Promise`&lt;`void`&gt;
 
 ##### Example
 
@@ -743,7 +722,7 @@ table.update({where:"x = 2", valuesSql:{"x": "x + 1"}})
 #### update(updates, options)
 
 ```ts
-abstract update(updates, options?): Promise<UpdateResult>
+abstract update(updates, options?): Promise<void>
 ```
 
 Update existing records in the Table
@@ -766,6 +745,10 @@ repeatedly calilng this method.
 * **updates**: `Record`&lt;`string`, `string`&gt; \| `Map`&lt;`string`, `string`&gt;
     the
     columns to update
+    Keys in the map should specify the name of the column to update.
+    Values in the map provide the new value of the column.  These can
+    be SQL literal strings (e.g. "7" or "'foo'") or they can be expressions
+    based on the row being updated (e.g. "my_col + 1")
 
 * **options?**: `Partial`&lt;[`UpdateOptions`](../interfaces/UpdateOptions.md)&gt;
     additional options to control
@@ -773,15 +756,7 @@ repeatedly calilng this method.
 
 ##### Returns
 
-`Promise`&lt;[`UpdateResult`](../interfaces/UpdateResult.md)&gt;
-
-A promise that resolves to an object
-containing the number of rows updated and the new version number
-
-Keys in the map should specify the name of the column to update.
-Values in the map provide the new value of the column.  These can
-be SQL literal strings (e.g. "7" or "'foo'") or they can be expressions
-based on the row being updated (e.g. "my_col + 1")
+`Promise`&lt;`void`&gt;
 
 ***
 
@@ -799,7 +774,7 @@ by `query`.
 
 #### Parameters
 
-* **vector**: [`IntoVector`](../type-aliases/IntoVector.md) \| [`MultiVector`](../type-aliases/MultiVector.md)
+* **vector**: [`IntoVector`](../type-aliases/IntoVector.md)
 
 #### Returns
 

docs/src/js/classes/VectorQuery.md

@@ -386,53 +386,6 @@ called then every valid row from the table will be returned.
 
 ***
 
-### maximumNprobes()
-
-```ts
-maximumNprobes(maximumNprobes): VectorQuery
-```
-
-Set the maximum number of probes used.
-
-This controls the maximum number of partitions that will be searched.  If this
-number is greater than minimumNprobes then the excess partitions will _only_ be
-searched if we have not found enough results.  This can be useful when there is
-a narrow filter to allow these queries to spend more time searching and avoid
-potential false negatives.
-
-#### Parameters
-
-* **maximumNprobes**: `number`
-
-#### Returns
-
-[`VectorQuery`](VectorQuery.md)
-
-***
-
-### minimumNprobes()
-
-```ts
-minimumNprobes(minimumNprobes): VectorQuery
-```
-
-Set the minimum number of probes used.
-
-This controls the minimum number of partitions that will be searched.  This
-parameter will impact every query against a vector index, regardless of the
-filter.  See `nprobes` for more details.  Higher values will increase recall
-but will also increase latency.
-
-#### Parameters
-
-* **minimumNprobes**: `number`
-
-#### Returns
-
-[`VectorQuery`](VectorQuery.md)
-
-***
-
 ### nprobes()
 
 ```ts
@@ -460,10 +413,6 @@ For best results we recommend tuning this parameter with a benchmark against
 your actual data to find the smallest possible value that will still give
 you the desired recall.
 
-For more fine grained control over behavior when you have a very narrow filter
-you can use `minimumNprobes` and `maximumNprobes`.  This method sets both
-the minimum and maximum to the same value.
-
 #### Parameters
 
 * **nprobes**: `number`

docs/src/js/enumerations/FullTextQueryType.md

@@ -15,14 +15,6 @@ Enum representing the types of full-text queries supported.
 
 ## Enumeration Members
 
-### Boolean
-
-```ts
-Boolean: "boolean";
-```
-
-***
-
 ### Boost
 
 ```ts

docs/src/js/enumerations/Occur.md

@@ -1,37 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / Occur
-
-# Enumeration: Occur
-
-Enum representing the occurrence of terms in full-text queries.
-
-- `Must`: The term must be present in the document.
-- `Should`: The term should contribute to the document score, but is not required.
-- `MustNot`: The term must not be present in the document.
-
-## Enumeration Members
-
-### Must
-
-```ts
-Must: "MUST";
-```
-
-***
-
-### MustNot
-
-```ts
-MustNot: "MUST_NOT";
-```
-
-***
-
-### Should
-
-```ts
-Should: "SHOULD";
-```

docs/src/js/enumerations/Operator.md

@@ -1,28 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / Operator
-
-# Enumeration: Operator
-
-Enum representing the logical operators used in full-text queries.
-
-- `And`: All terms must match.
-- `Or`: At least one term must match.
-
-## Enumeration Members
-
-### And
-
-```ts
-And: "AND";
-```
-
-***
-
-### Or
-
-```ts
-Or: "OR";
-```

docs/src/js/functions/connect.md

@@ -6,13 +6,10 @@
 
 # Function: connect()
 
-## connect(uri, options, session)
+## connect(uri, options)
 
 ```ts
-function connect(
-   uri,
-   options?,
-   session?): Promise<Connection>
+function connect(uri, options?): Promise<Connection>
 ```
 
 Connect to a LanceDB instance at the given URI.
@@ -32,8 +29,6 @@ Accepted formats:
 * **options?**: `Partial`&lt;[`ConnectionOptions`](../interfaces/ConnectionOptions.md)&gt;
     The options to use when connecting to the database
 
-* **session?**: [`Session`](../classes/Session.md)
-
 ### Returns
 
 `Promise`&lt;[`Connection`](../classes/Connection.md)&gt;
@@ -82,7 +77,7 @@ Accepted formats:
 
 [ConnectionOptions](../interfaces/ConnectionOptions.md) for more details on the URI format.
 
-### Examples
+### Example
 
 ```ts
 const conn = await connect({
@@ -90,11 +85,3 @@ const conn = await connect({
   storageOptions: {timeout: "60s"}
 });
 ```
-
-```ts
-const session = Session.default();
-const conn = await connect({
-  uri: "/path/to/database",
-  session: session
-});
-```

docs/src/js/globals.md

@@ -12,12 +12,9 @@
 ## Enumerations
 
 - [FullTextQueryType](enumerations/FullTextQueryType.md)
-- [Occur](enumerations/Occur.md)
-- [Operator](enumerations/Operator.md)
 
 ## Classes
 
-- [BooleanQuery](classes/BooleanQuery.md)
 - [BoostQuery](classes/BoostQuery.md)
 - [Connection](classes/Connection.md)
 - [Index](classes/Index.md)
@@ -29,7 +26,6 @@
 - [Query](classes/Query.md)
 - [QueryBase](classes/QueryBase.md)
 - [RecordBatchIterator](classes/RecordBatchIterator.md)
-- [Session](classes/Session.md)
 - [Table](classes/Table.md)
 - [TagContents](classes/TagContents.md)
 - [Tags](classes/Tags.md)
@@ -38,18 +34,13 @@
 
 ## Interfaces
 
-- [AddColumnsResult](interfaces/AddColumnsResult.md)
 - [AddColumnsSql](interfaces/AddColumnsSql.md)
 - [AddDataOptions](interfaces/AddDataOptions.md)
-- [AddResult](interfaces/AddResult.md)
-- [AlterColumnsResult](interfaces/AlterColumnsResult.md)
 - [ClientConfig](interfaces/ClientConfig.md)
 - [ColumnAlteration](interfaces/ColumnAlteration.md)
 - [CompactionStats](interfaces/CompactionStats.md)
 - [ConnectionOptions](interfaces/ConnectionOptions.md)
 - [CreateTableOptions](interfaces/CreateTableOptions.md)
-- [DeleteResult](interfaces/DeleteResult.md)
-- [DropColumnsResult](interfaces/DropColumnsResult.md)
 - [ExecutableQuery](interfaces/ExecutableQuery.md)
 - [FragmentStatistics](interfaces/FragmentStatistics.md)
 - [FragmentSummaryStats](interfaces/FragmentSummaryStats.md)
@@ -63,7 +54,7 @@
 - [IndexStatistics](interfaces/IndexStatistics.md)
 - [IvfFlatOptions](interfaces/IvfFlatOptions.md)
 - [IvfPqOptions](interfaces/IvfPqOptions.md)
-- [MergeResult](interfaces/MergeResult.md)
+- [MergeStats](interfaces/MergeStats.md)
 - [OpenTableOptions](interfaces/OpenTableOptions.md)
 - [OptimizeOptions](interfaces/OptimizeOptions.md)
 - [OptimizeStats](interfaces/OptimizeStats.md)
@@ -74,9 +65,7 @@
 - [TableStatistics](interfaces/TableStatistics.md)
 - [TimeoutConfig](interfaces/TimeoutConfig.md)
 - [UpdateOptions](interfaces/UpdateOptions.md)
-- [UpdateResult](interfaces/UpdateResult.md)
 - [Version](interfaces/Version.md)
-- [WriteExecutionOptions](interfaces/WriteExecutionOptions.md)
 
 ## Type Aliases
 
@@ -85,7 +74,6 @@
 - [FieldLike](type-aliases/FieldLike.md)
 - [IntoSql](type-aliases/IntoSql.md)
 - [IntoVector](type-aliases/IntoVector.md)
-- [MultiVector](type-aliases/MultiVector.md)
 - [RecordBatchLike](type-aliases/RecordBatchLike.md)
 - [SchemaLike](type-aliases/SchemaLike.md)
 - [TableLike](type-aliases/TableLike.md)

docs/src/js/interfaces/AddColumnsResult.md

@@ -1,15 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / AddColumnsResult
-
-# Interface: AddColumnsResult
-
-## Properties
-
-### version
-
-```ts
-version: number;
-```

docs/src/js/interfaces/AddResult.md

@@ -1,15 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / AddResult
-
-# Interface: AddResult
-
-## Properties
-
-### version
-
-```ts
-version: number;
-```

docs/src/js/interfaces/AlterColumnsResult.md

@@ -1,15 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / AlterColumnsResult
-
-# Interface: AlterColumnsResult
-
-## Properties
-
-### version
-
-```ts
-version: number;
-```

docs/src/js/interfaces/ConnectionOptions.md

@@ -70,17 +70,6 @@ Defaults to 'us-east-1'.
 
 ***
 
-### session?
-
-```ts
-optional session: Session;
-```
-
-(For LanceDB OSS only): the session to use for this connection. Holds
-shared caches and other session-specific state.
-
-***
-
 ### storageOptions?
 
 ```ts

docs/src/js/interfaces/DeleteResult.md

@@ -1,15 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / DeleteResult
-
-# Interface: DeleteResult
-
-## Properties
-
-### version
-
-```ts
-version: number;
-```

docs/src/js/interfaces/DropColumnsResult.md

@@ -1,15 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / DropColumnsResult
-
-# Interface: DropColumnsResult
-
-## Properties
-
-### version
-
-```ts
-version: number;
-```

docs/src/js/interfaces/FtsOptions.md

@@ -23,7 +23,7 @@ whether to remove punctuation
 ### baseTokenizer?
 
 ```ts
-optional baseTokenizer: "raw" | "simple" | "whitespace" | "ngram";
+optional baseTokenizer: "raw" | "simple" | "whitespace";
 ```
 
 The tokenizer to use when building the index.
@@ -71,36 +71,6 @@ tokens longer than this length will be ignored
 
 ***
 
-### ngramMaxLength?
-
-```ts
-optional ngramMaxLength: number;
-```
-
-ngram max length
-
-***
-
-### ngramMinLength?
-
-```ts
-optional ngramMinLength: number;
-```
-
-ngram min length
-
-***
-
-### prefixOnly?
-
-```ts
-optional prefixOnly: boolean;
-```
-
-whether to only index the prefix of the token for ngram tokenizer
-
-***
-
 ### removeStopWords?
 
 ```ts

docs/src/js/interfaces/MergeResult.md

@@ -1,39 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / MergeResult
-
-# Interface: MergeResult
-
-## Properties
-
-### numDeletedRows
-
-```ts
-numDeletedRows: number;
-```
-
-***
-
-### numInsertedRows
-
-```ts
-numInsertedRows: number;
-```
-
-***
-
-### numUpdatedRows
-
-```ts
-numUpdatedRows: number;
-```
-
-***
-
-### version
-
-```ts
-version: number;
-```

docs/src/js/interfaces/MergeStats.md

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

docs/src/js/interfaces/OpenTableOptions.md

@@ -8,7 +8,7 @@
 
 ## Properties
 
-### ~~indexCacheSize?~~
+### indexCacheSize?
 
 ```ts
 optional indexCacheSize: number;
@@ -16,11 +16,6 @@ optional indexCacheSize: number;
 
 Set the size of the index cache, specified as a number of entries
 
-#### Deprecated
-
-Use session-level cache configuration instead.
-Create a Session with custom cache sizes and pass it to the connect() function.
-
 The exact meaning of an "entry" will depend on the type of index:
 - IVF: there is one entry for each IVF partition
 - BTREE: there is one entry for the entire index

docs/src/js/interfaces/OptimizeOptions.md

@@ -24,10 +24,10 @@ The default is 7 days
 // Delete all versions older than 1 day
 const olderThan = new Date();
 olderThan.setDate(olderThan.getDate() - 1));
-tbl.optimize({cleanupOlderThan: olderThan});
+tbl.cleanupOlderVersions(olderThan);
 
 // Delete all versions except the current version
-tbl.optimize({cleanupOlderThan: new Date()});
+tbl.cleanupOlderVersions(new Date());
 ```
 
 ***

docs/src/js/interfaces/UpdateResult.md

@@ -1,23 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / UpdateResult
-
-# Interface: UpdateResult
-
-## Properties
-
-### rowsUpdated
-
-```ts
-rowsUpdated: number;
-```
-
-***
-
-### version
-
-```ts
-version: number;
-```

docs/src/js/interfaces/WriteExecutionOptions.md

@@ -1,26 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / WriteExecutionOptions
-
-# Interface: WriteExecutionOptions
-
-## Properties
-
-### timeoutMs?
-
-```ts
-optional timeoutMs: number;
-```
-
-Maximum time to run the operation before cancelling it.
-
-By default, there is a 30-second timeout that is only enforced after the
-first attempt. This is to prevent spending too long retrying to resolve
-conflicts. For example, if a write attempt takes 20 seconds and fails,
-the second attempt will be cancelled after 10 seconds, hitting the
-30-second timeout. However, a write that takes one hour and succeeds on the
-first attempt will not be cancelled.
-
-When this is set, the timeout is enforced on all attempts, including the first.

docs/src/js/type-aliases/MultiVector.md

@@ -1,11 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / MultiVector
-
-# Type Alias: MultiVector
-
-```ts
-type MultiVector: IntoVector[];
-```

docs/src/notebooks/Multivector_on_LanceDB.ipynb

@@ -428,7 +428,7 @@
         "\n",
         "**Why?**  \n",
         "Embedding the UFO dataset and ingesting it into LanceDB takes **~2 hours on a T4 GPU**. To save time:  \n",
-        "- **Use the pre-prepared table with index created** (provided below) to proceed directly to **Step 7**: search.  \n",
+        "- **Use the pre-prepared table with index created ** (provided below) to proceed directly to step7: search.  \n",
         "- **Step 5a** contains the full ingestion code for reference (run it only if necessary).  \n",
         "- **Step 6** contains the details on creating the index on the multivector column"
       ]

docs/src/python/datafusion.md

@@ -1,53 +0,0 @@
-# Apache Datafusion
-
-In Python, LanceDB tables can also be queried with [Apache Datafusion](https://datafusion.apache.org/), an extensible query engine written in Rust that uses Apache Arrow as its in-memory format. This means you can write complex SQL queries to analyze your data in LanceDB.
-
-This integration is done via [Datafusion FFI](https://docs.rs/datafusion-ffi/latest/datafusion_ffi/), which provides a native integration between LanceDB and Datafusion.
-The Datafusion FFI allows to pass down column selections and basic filters to LanceDB, reducing the amount of scanned data when executing your query. Additionally, the integration allows streaming data from LanceDB tables which allows to do aggregation larger-than-memory.
-
-We can demonstrate this by first installing `datafusion` and `lancedb`.
-
-```shell
-pip install datafusion lancedb
-```
-
-We will re-use the dataset [created previously](./pandas_and_pyarrow.md):
-
-```python
-import lancedb
-
-from datafusion import SessionContext
-from lance import FFILanceTableProvider
-
-db = lancedb.connect("data/sample-lancedb")
-data = [
-    {"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
-    {"vector": [5.9, 26.5], "item": "bar", "price": 20.0}
-]
-lance_table = db.create_table("lance_table", data)
-
-ctx = SessionContext()
-
-ffi_lance_table = FFILanceTableProvider(
-    lance_table.to_lance(), with_row_id=True, with_row_addr=True
-)
-ctx.register_table_provider("ffi_lance_table", ffi_lance_table)
-```
-
-The `to_lance` method converts the LanceDB table to a `LanceDataset`, which is accessible to Datafusion through the Datafusion FFI integration layer.
-To query the resulting Lance dataset in Datafusion, you first need to register the dataset with Datafusion and then just reference it by the same name in your SQL query.
-
-```python
-ctx.table("ffi_lance_table")
-ctx.sql("SELECT * FROM ffi_lance_table")
-```
-
-```
-┌─────────────┬─────────┬────────┬─────────────────┬─────────────────┐
-│   vector    │  item   │ price  │ _rowid          │ _rowaddr        │
-│   float[]   │ varchar │ double │ bigint unsigned │ bigint unsigned │
-├─────────────┼─────────┼────────┼─────────────────┼─────────────────┤
-│ [3.1, 4.1]  │ foo     │   10.0 │               0 │               0 │
-│ [5.9, 26.5] │ bar     │   20.0 │               1 │               1 │
-└─────────────┴─────────┴────────┴─────────────────┴─────────────────┘
-```

docs/src/quickstart.md

@@ -0,0 +1,101 @@
+
+# Getting Started with LanceDB: A Minimal Vector Search Tutorial
+
+Let's set up a LanceDB database, insert vector data, and perform a simple vector search. We'll use simple character classes like "knight" and "rogue" to illustrate semantic relevance.
+
+## 1. Install Dependencies
+
+Before starting, make sure you have the necessary packages:
+
+```bash
+pip install lancedb pandas numpy
+```
+
+## 2. Import Required Libraries
+
+```python
+import lancedb
+import pandas as pd
+import numpy as np
+```
+
+## 3. Connect to LanceDB
+
+You can use a local directory to store your database:
+
+```python
+db = lancedb.connect("./lancedb")
+```
+
+## 4. Create Sample Data
+
+Add sample text data and corresponding 4D vectors:
+
+```python
+data = pd.DataFrame([
+    {"id": "1", "vector": [1.0, 0.0, 0.0, 0.0], "text": "knight"},
+    {"id": "2", "vector": [0.9, 0.1, 0.0, 0.0], "text": "warrior"},
+    {"id": "3", "vector": [0.0, 1.0, 0.0, 0.0], "text": "rogue"},
+    {"id": "4", "vector": [0.0, 0.9, 0.1, 0.0], "text": "thief"},
+    {"id": "5", "vector": [0.5, 0.5, 0.0, 0.0], "text": "ranger"},
+])
+```
+
+## 5. Create a Table in LanceDB
+
+```python
+table = db.create_table("rpg_classes", data=data, mode="overwrite")
+```
+
+Let's see how the table looks:
+```python
+print(data)
+```
+
+| id | vector | text |
+|----|--------|------|
+| 1 | [1.0, 0.0, 0.0, 0.0] | knight |
+| 2 | [0.9, 0.1, 0.0, 0.0] | warrior |
+| 3 | [0.0, 1.0, 0.0, 0.0] | rogue |
+| 4 | [0.0, 0.9, 0.1, 0.0] | thief |
+| 5 | [0.5, 0.5, 0.0, 0.0] | ranger |
+
+
+
+## 6. Perform a Vector Search
+
+Search for the most similar character classes to our query vector:
+
+```python
+# Query as if we are searching for "rogue"
+results = table.search([0.95, 0.05, 0.0, 0.0]).limit(3).to_df()
+print(results)
+```
+
+This will return the top 3 closest classes to the vector, effectively showing how LanceDB can be used for semantic search.
+
+|  id  |          vector         |   text   | _distance |
+|------|------------------------|----------|-----------|
+|  3   | [0.0, 1.0, 0.0, 0.0]  |  rogue   |   0.00   |
+|  4   | [0.0, 0.9, 0.1, 0.0]  | thief |   0.02   |
+|  5   | [0.5, 0.5, 0.0, 0.0]  |  ranger  |   0.50   |
+
+Let's try searching for "knight"
+
+```python
+query_vector = [1.0, 0.0, 0.0, 0.0]
+results = table.search(query_vector).limit(3).to_pandas()
+print(results)
+```
+
+|  id  |          vector         |   text   | _distance |
+|------|------------------------|----------|-----------|
+|  1   | [1.0, 0.0, 0.0, 0.0]  |  knight  |   0.00   |
+|  2   | [0.9, 0.1, 0.0, 0.0]  | warrior  |   0.02   |
+|  5   | [0.5, 0.5, 0.0, 0.0]  |  ranger  |   0.50   |
+
+## Next Steps
+
+That's it - you just conducted vector search!
+
+For more beginner tips, check out the [Basic Usage](basic.md) guide.

docs/test/md_testing.py

@@ -30,8 +30,7 @@ excluded_globs = [
     "../src/rag/advanced_techniques/*.md",
     "../src/guides/scalar_index.md",
     "../src/guides/storage.md",
-    "../src/search.md",
-    "../src/guides/sql_querying.md",
+    "../src/search.md"
 ]
 
 python_prefix = "py"

docs/test/requirements.txt

@@ -7,4 +7,3 @@ tantivy==0.20.1
 --extra-index-url https://download.pytorch.org/whl/cpu
 torch
 polars>=0.19, <=1.3.0
-datafusion

java/.mvn/wrapper/maven-wrapper.properties

@@ -1,19 +0,0 @@
-# Licensed to the Apache Software Foundation (ASF) under one
-# or more contributor license agreements.  See the NOTICE file
-# distributed with this work for additional information
-# regarding copyright ownership.  The ASF licenses this file
-# to you under the Apache License, Version 2.0 (the
-# "License"); you may not use this file except in compliance
-# with the License.  You may obtain a copy of the License at
-#
-#   http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing,
-# software distributed under the License is distributed on an
-# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
-# KIND, either express or implied.  See the License for the
-# specific language governing permissions and limitations
-# under the License.
-wrapperVersion=3.3.2
-distributionType=only-script
-distributionUrl=https://repo.maven.apache.org/maven2/org/apache/maven/apache-maven/3.9.9/apache-maven-3.9.9-bin.zip

java/README.md

@@ -1,37 +0,0 @@
-# LanceDB Java SDK
-
-## Configuration and Initialization
-
-### LanceDB Cloud
-
-For LanceDB Cloud, use the simplified builder API:
-
-```java
-import com.lancedb.lance.namespace.LanceRestNamespace;
-
-// If your DB url is db://example-db, then your database here is example-db
-LanceRestNamespace namespace = LanceDBRestNamespaces.builder()
-    .apiKey("your_lancedb_cloud_api_key")
-    .database("your_database_name")
-    .build();
-```
-
-### LanceDB Enterprise
-
-For Enterprise deployments, use your VPC endpoint:
-
-```java
-LanceRestNamespace namespace = LanceDBRestNamespaces.builder()
-    .apiKey("your_lancedb_enterprise_api_key")
-    .database("your-top-dir") // Your top level folder under your cloud bucket, e.g. s3://your-bucket/your-top-dir/
-    .hostOverride("http://<vpc_endpoint_dns_name>:80")
-    .build();
-```
-
-## Development
-
-Build:
-
-```shell
-./mvnw install
-```

java/core/lancedb-jni/Cargo.toml

@@ -19,7 +19,7 @@ lancedb = { path = "../../../rust/lancedb" }
 lance = { workspace = true }
 arrow = { workspace = true, features = ["ffi"] }
 arrow-schema.workspace = true
-tokio = "1.46"
+tokio = "1.23"
 jni = "0.21.1"
 snafu.workspace = true
 lazy_static.workspace = true

java/core/pom.xml

@@ -8,24 +8,18 @@
     <parent>
         <groupId>com.lancedb</groupId>
         <artifactId>lancedb-parent</artifactId>
-        <version>0.21.2-final.0</version>
+        <version>0.19.1-beta.1</version>
         <relativePath>../pom.xml</relativePath>
     </parent>
 
     <artifactId>lancedb-core</artifactId>
-    <name>${project.artifactId}</name>
-    <description>LanceDB Core</description>
+    <name>LanceDB Core</name>
     <packaging>jar</packaging>
     <properties>
         <rust.release.build>false</rust.release.build>
     </properties>
 
     <dependencies>
-        <dependency>
-            <groupId>com.lancedb</groupId>
-            <artifactId>lance-namespace-core</artifactId>
-            <version>0.0.1</version>
-        </dependency>
         <dependency>
             <groupId>org.apache.arrow</groupId>
             <artifactId>arrow-vector</artifactId>

java/lance-namespace/pom.xml

@@ -1,26 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-
-<project xmlns="http://maven.apache.org/POM/4.0.0"
-    xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
-    xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
-    <modelVersion>4.0.0</modelVersion>
-
-    <parent>
-        <groupId>com.lancedb</groupId>
-        <artifactId>lancedb-parent</artifactId>
-        <version>0.21.2-final.0</version>
-        <relativePath>../pom.xml</relativePath>
-    </parent>
-
-    <artifactId>lancedb-lance-namespace</artifactId>
-    <name>${project.artifactId}</name>
-    <description>LanceDB Java Integration with Lance Namespace</description>
-    <packaging>jar</packaging>
-
-    <dependencies>
-        <dependency>
-            <groupId>com.lancedb</groupId>
-            <artifactId>lance-namespace-core</artifactId>
-        </dependency>
-    </dependencies>
-</project>

java/lance-namespace/src/main/java/com/lancedb/lancedb/LanceDbRestNamespaces.java

@@ -1,146 +0,0 @@
-/*
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- *     http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-package com.lancedb.lancedb;
-
-import com.lancedb.lance.namespace.LanceRestNamespace;
-import com.lancedb.lance.namespace.client.apache.ApiClient;
-
-import java.util.HashMap;
-import java.util.Map;
-import java.util.Optional;
-
-/** Util class to help construct a {@link LanceRestNamespace} for LanceDB. */
-public class LanceDbRestNamespaces {
-  private static final String DEFAULT_REGION = "us-east-1";
-  private static final String CLOUD_URL_PATTERN = "https://%s.%s.api.lancedb.com";
-
-  private String apiKey;
-  private String database;
-  private Optional<String> hostOverride = Optional.empty();
-  private Optional<String> region = Optional.empty();
-  private Map<String, String> additionalConfig = new HashMap<>();
-
-  private LanceDbRestNamespaces() {}
-
-  /**
-   * Create a new builder instance.
-   *
-   * @return A new LanceRestNamespaceBuilder
-   */
-  public static LanceDbRestNamespaces builder() {
-    return new LanceDbRestNamespaces();
-  }
-
-  /**
-   * Set the API key (required).
-   *
-   * @param apiKey The LanceDB API key
-   * @return This builder
-   */
-  public LanceDbRestNamespaces apiKey(String apiKey) {
-    if (apiKey == null || apiKey.trim().isEmpty()) {
-      throw new IllegalArgumentException("API key cannot be null or empty");
-    }
-    this.apiKey = apiKey;
-    return this;
-  }
-
-  /**
-   * Set the database name (required).
-   *
-   * @param database The database name
-   * @return This builder
-   */
-  public LanceDbRestNamespaces database(String database) {
-    if (database == null || database.trim().isEmpty()) {
-      throw new IllegalArgumentException("Database cannot be null or empty");
-    }
-    this.database = database;
-    return this;
-  }
-
-  /**
-   * Set a custom host override (optional). When set, this overrides the default LanceDB Cloud URL
-   * construction. Use this for LanceDB Enterprise deployments.
-   *
-   * @param hostOverride The complete base URL (e.g., "http://your-vpc-endpoint:80")
-   * @return This builder
-   */
-  public LanceDbRestNamespaces hostOverride(String hostOverride) {
-    this.hostOverride = Optional.ofNullable(hostOverride);
-    return this;
-  }
-
-  /**
-   * Set the region for LanceDB Cloud (optional). Defaults to "us-east-1" if not specified. This is
-   * ignored when hostOverride is set.
-   *
-   * @param region The AWS region (e.g., "us-east-1", "eu-west-1")
-   * @return This builder
-   */
-  public LanceDbRestNamespaces region(String region) {
-    this.region = Optional.ofNullable(region);
-    return this;
-  }
-
-  /**
-   * Add additional configuration parameters.
-   *
-   * @param key The configuration key
-   * @param value The configuration value
-   * @return This builder
-   */
-  public LanceDbRestNamespaces config(String key, String value) {
-    this.additionalConfig.put(key, value);
-    return this;
-  }
-
-  /**
-   * Build the LanceRestNamespace instance.
-   *
-   * @return A configured LanceRestNamespace
-   * @throws IllegalStateException if required parameters are missing
-   */
-  public LanceRestNamespace build() {
-    // Validate required fields
-    if (apiKey == null) {
-      throw new IllegalStateException("API key is required");
-    }
-    if (database == null) {
-      throw new IllegalStateException("Database is required");
-    }
-
-    // Build configuration map
-    Map<String, String> config = new HashMap<>(additionalConfig);
-    config.put("headers.x-lancedb-database", database);
-    config.put("headers.x-api-key", apiKey);
-
-    // Determine base URL
-    String baseUrl;
-    if (hostOverride.isPresent()) {
-      baseUrl = hostOverride.get();
-      config.put("host_override", hostOverride.get());
-    } else {
-      String effectiveRegion = region.orElse(DEFAULT_REGION);
-      baseUrl = String.format(CLOUD_URL_PATTERN, database, effectiveRegion);
-      config.put("region", effectiveRegion);
-    }
-
-    // Create and configure ApiClient
-    ApiClient apiClient = new ApiClient();
-    apiClient.setBasePath(baseUrl);
-
-    return new LanceRestNamespace(apiClient, config);
-  }
-}

java/mvnw

@@ -1,259 +0,0 @@
-#!/bin/sh
-# ----------------------------------------------------------------------------
-# Licensed to the Apache Software Foundation (ASF) under one
-# or more contributor license agreements.  See the NOTICE file
-# distributed with this work for additional information
-# regarding copyright ownership.  The ASF licenses this file
-# to you under the Apache License, Version 2.0 (the
-# "License"); you may not use this file except in compliance
-# with the License.  You may obtain a copy of the License at
-#
-#    http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing,
-# software distributed under the License is distributed on an
-# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
-# KIND, either express or implied.  See the License for the
-# specific language governing permissions and limitations
-# under the License.
-# ----------------------------------------------------------------------------
-
-# ----------------------------------------------------------------------------
-# Apache Maven Wrapper startup batch script, version 3.3.2
-#
-# Optional ENV vars
-# -----------------
-#   JAVA_HOME - location of a JDK home dir, required when download maven via java source
-#   MVNW_REPOURL - repo url base for downloading maven distribution
-#   MVNW_USERNAME/MVNW_PASSWORD - user and password for downloading maven
-#   MVNW_VERBOSE - true: enable verbose log; debug: trace the mvnw script; others: silence the output
-# ----------------------------------------------------------------------------
-
-set -euf
-[ "${MVNW_VERBOSE-}" != debug ] || set -x
-
-# OS specific support.
-native_path() { printf %s\\n "$1"; }
-case "$(uname)" in
-CYGWIN* | MINGW*)
-  [ -z "${JAVA_HOME-}" ] || JAVA_HOME="$(cygpath --unix "$JAVA_HOME")"
-  native_path() { cygpath --path --windows "$1"; }
-  ;;
-esac
-
-# set JAVACMD and JAVACCMD
-set_java_home() {
-  # For Cygwin and MinGW, ensure paths are in Unix format before anything is touched
-  if [ -n "${JAVA_HOME-}" ]; then
-    if [ -x "$JAVA_HOME/jre/sh/java" ]; then
-      # IBM's JDK on AIX uses strange locations for the executables
-      JAVACMD="$JAVA_HOME/jre/sh/java"
-      JAVACCMD="$JAVA_HOME/jre/sh/javac"
-    else
-      JAVACMD="$JAVA_HOME/bin/java"
-      JAVACCMD="$JAVA_HOME/bin/javac"
-
-      if [ ! -x "$JAVACMD" ] || [ ! -x "$JAVACCMD" ]; then
-        echo "The JAVA_HOME environment variable is not defined correctly, so mvnw cannot run." >&2
-        echo "JAVA_HOME is set to \"$JAVA_HOME\", but \"\$JAVA_HOME/bin/java\" or \"\$JAVA_HOME/bin/javac\" does not exist." >&2
-        return 1
-      fi
-    fi
-  else
-    JAVACMD="$(
-      'set' +e
-      'unset' -f command 2>/dev/null
-      'command' -v java
-    )" || :
-    JAVACCMD="$(
-      'set' +e
-      'unset' -f command 2>/dev/null
-      'command' -v javac
-    )" || :
-
-    if [ ! -x "${JAVACMD-}" ] || [ ! -x "${JAVACCMD-}" ]; then
-      echo "The java/javac command does not exist in PATH nor is JAVA_HOME set, so mvnw cannot run." >&2
-      return 1
-    fi
-  fi
-}
-
-# hash string like Java String::hashCode
-hash_string() {
-  str="${1:-}" h=0
-  while [ -n "$str" ]; do
-    char="${str%"${str#?}"}"
-    h=$(((h * 31 + $(LC_CTYPE=C printf %d "'$char")) % 4294967296))
-    str="${str#?}"
-  done
-  printf %x\\n $h
-}
-
-verbose() { :; }
-[ "${MVNW_VERBOSE-}" != true ] || verbose() { printf %s\\n "${1-}"; }
-
-die() {
-  printf %s\\n "$1" >&2
-  exit 1
-}
-
-trim() {
-  # MWRAPPER-139:
-  #   Trims trailing and leading whitespace, carriage returns, tabs, and linefeeds.
-  #   Needed for removing poorly interpreted newline sequences when running in more
-  #   exotic environments such as mingw bash on Windows.
-  printf "%s" "${1}" | tr -d '[:space:]'
-}
-
-# parse distributionUrl and optional distributionSha256Sum, requires .mvn/wrapper/maven-wrapper.properties
-while IFS="=" read -r key value; do
-  case "${key-}" in
-  distributionUrl) distributionUrl=$(trim "${value-}") ;;
-  distributionSha256Sum) distributionSha256Sum=$(trim "${value-}") ;;
-  esac
-done <"${0%/*}/.mvn/wrapper/maven-wrapper.properties"
-[ -n "${distributionUrl-}" ] || die "cannot read distributionUrl property in ${0%/*}/.mvn/wrapper/maven-wrapper.properties"
-
-case "${distributionUrl##*/}" in
-maven-mvnd-*bin.*)
-  MVN_CMD=mvnd.sh _MVNW_REPO_PATTERN=/maven/mvnd/
-  case "${PROCESSOR_ARCHITECTURE-}${PROCESSOR_ARCHITEW6432-}:$(uname -a)" in
-  *AMD64:CYGWIN* | *AMD64:MINGW*) distributionPlatform=windows-amd64 ;;
-  :Darwin*x86_64) distributionPlatform=darwin-amd64 ;;
-  :Darwin*arm64) distributionPlatform=darwin-aarch64 ;;
-  :Linux*x86_64*) distributionPlatform=linux-amd64 ;;
-  *)
-    echo "Cannot detect native platform for mvnd on $(uname)-$(uname -m), use pure java version" >&2
-    distributionPlatform=linux-amd64
-    ;;
-  esac
-  distributionUrl="${distributionUrl%-bin.*}-$distributionPlatform.zip"
-  ;;
-maven-mvnd-*) MVN_CMD=mvnd.sh _MVNW_REPO_PATTERN=/maven/mvnd/ ;;
-*) MVN_CMD="mvn${0##*/mvnw}" _MVNW_REPO_PATTERN=/org/apache/maven/ ;;
-esac
-
-# apply MVNW_REPOURL and calculate MAVEN_HOME
-# maven home pattern: ~/.m2/wrapper/dists/{apache-maven-<version>,maven-mvnd-<version>-<platform>}/<hash>
-[ -z "${MVNW_REPOURL-}" ] || distributionUrl="$MVNW_REPOURL$_MVNW_REPO_PATTERN${distributionUrl#*"$_MVNW_REPO_PATTERN"}"
-distributionUrlName="${distributionUrl##*/}"
-distributionUrlNameMain="${distributionUrlName%.*}"
-distributionUrlNameMain="${distributionUrlNameMain%-bin}"
-MAVEN_USER_HOME="${MAVEN_USER_HOME:-${HOME}/.m2}"
-MAVEN_HOME="${MAVEN_USER_HOME}/wrapper/dists/${distributionUrlNameMain-}/$(hash_string "$distributionUrl")"
-
-exec_maven() {
-  unset MVNW_VERBOSE MVNW_USERNAME MVNW_PASSWORD MVNW_REPOURL || :
-  exec "$MAVEN_HOME/bin/$MVN_CMD" "$@" || die "cannot exec $MAVEN_HOME/bin/$MVN_CMD"
-}
-
-if [ -d "$MAVEN_HOME" ]; then
-  verbose "found existing MAVEN_HOME at $MAVEN_HOME"
-  exec_maven "$@"
-fi
-
-case "${distributionUrl-}" in
-*?-bin.zip | *?maven-mvnd-?*-?*.zip) ;;
-*) die "distributionUrl is not valid, must match *-bin.zip or maven-mvnd-*.zip, but found '${distributionUrl-}'" ;;
-esac
-
-# prepare tmp dir
-if TMP_DOWNLOAD_DIR="$(mktemp -d)" && [ -d "$TMP_DOWNLOAD_DIR" ]; then
-  clean() { rm -rf -- "$TMP_DOWNLOAD_DIR"; }
-  trap clean HUP INT TERM EXIT
-else
-  die "cannot create temp dir"
-fi
-
-mkdir -p -- "${MAVEN_HOME%/*}"
-
-# Download and Install Apache Maven
-verbose "Couldn't find MAVEN_HOME, downloading and installing it ..."
-verbose "Downloading from: $distributionUrl"
-verbose "Downloading to: $TMP_DOWNLOAD_DIR/$distributionUrlName"
-
-# select .zip or .tar.gz
-if ! command -v unzip >/dev/null; then
-  distributionUrl="${distributionUrl%.zip}.tar.gz"
-  distributionUrlName="${distributionUrl##*/}"
-fi
-
-# verbose opt
-__MVNW_QUIET_WGET=--quiet __MVNW_QUIET_CURL=--silent __MVNW_QUIET_UNZIP=-q __MVNW_QUIET_TAR=''
-[ "${MVNW_VERBOSE-}" != true ] || __MVNW_QUIET_WGET='' __MVNW_QUIET_CURL='' __MVNW_QUIET_UNZIP='' __MVNW_QUIET_TAR=v
-
-# normalize http auth
-case "${MVNW_PASSWORD:+has-password}" in
-'') MVNW_USERNAME='' MVNW_PASSWORD='' ;;
-has-password) [ -n "${MVNW_USERNAME-}" ] || MVNW_USERNAME='' MVNW_PASSWORD='' ;;
-esac
-
-if [ -z "${MVNW_USERNAME-}" ] && command -v wget >/dev/null; then
-  verbose "Found wget ... using wget"
-  wget ${__MVNW_QUIET_WGET:+"$__MVNW_QUIET_WGET"} "$distributionUrl" -O "$TMP_DOWNLOAD_DIR/$distributionUrlName" || die "wget: Failed to fetch $distributionUrl"
-elif [ -z "${MVNW_USERNAME-}" ] && command -v curl >/dev/null; then
-  verbose "Found curl ... using curl"
-  curl ${__MVNW_QUIET_CURL:+"$__MVNW_QUIET_CURL"} -f -L -o "$TMP_DOWNLOAD_DIR/$distributionUrlName" "$distributionUrl" || die "curl: Failed to fetch $distributionUrl"
-elif set_java_home; then
-  verbose "Falling back to use Java to download"
-  javaSource="$TMP_DOWNLOAD_DIR/Downloader.java"
-  targetZip="$TMP_DOWNLOAD_DIR/$distributionUrlName"
-  cat >"$javaSource" <<-END
-	public class Downloader extends java.net.Authenticator
-	{
-	  protected java.net.PasswordAuthentication getPasswordAuthentication()
-	  {
-	    return new java.net.PasswordAuthentication( System.getenv( "MVNW_USERNAME" ), System.getenv( "MVNW_PASSWORD" ).toCharArray() );
-	  }
-	  public static void main( String[] args ) throws Exception
-	  {
-	    setDefault( new Downloader() );
-	    java.nio.file.Files.copy( java.net.URI.create( args[0] ).toURL().openStream(), java.nio.file.Paths.get( args[1] ).toAbsolutePath().normalize() );
-	  }
-	}
-	END
-  # For Cygwin/MinGW, switch paths to Windows format before running javac and java
-  verbose " - Compiling Downloader.java ..."
-  "$(native_path "$JAVACCMD")" "$(native_path "$javaSource")" || die "Failed to compile Downloader.java"
-  verbose " - Running Downloader.java ..."
-  "$(native_path "$JAVACMD")" -cp "$(native_path "$TMP_DOWNLOAD_DIR")" Downloader "$distributionUrl" "$(native_path "$targetZip")"
-fi
-
-# If specified, validate the SHA-256 sum of the Maven distribution zip file
-if [ -n "${distributionSha256Sum-}" ]; then
-  distributionSha256Result=false
-  if [ "$MVN_CMD" = mvnd.sh ]; then
-    echo "Checksum validation is not supported for maven-mvnd." >&2
-    echo "Please disable validation by removing 'distributionSha256Sum' from your maven-wrapper.properties." >&2
-    exit 1
-  elif command -v sha256sum >/dev/null; then
-    if echo "$distributionSha256Sum  $TMP_DOWNLOAD_DIR/$distributionUrlName" | sha256sum -c >/dev/null 2>&1; then
-      distributionSha256Result=true
-    fi
-  elif command -v shasum >/dev/null; then
-    if echo "$distributionSha256Sum  $TMP_DOWNLOAD_DIR/$distributionUrlName" | shasum -a 256 -c >/dev/null 2>&1; then
-      distributionSha256Result=true
-    fi
-  else
-    echo "Checksum validation was requested but neither 'sha256sum' or 'shasum' are available." >&2
-    echo "Please install either command, or disable validation by removing 'distributionSha256Sum' from your maven-wrapper.properties." >&2
-    exit 1
-  fi
-  if [ $distributionSha256Result = false ]; then
-    echo "Error: Failed to validate Maven distribution SHA-256, your Maven distribution might be compromised." >&2
-    echo "If you updated your Maven version, you need to update the specified distributionSha256Sum property." >&2
-    exit 1
-  fi
-fi
-
-# unzip and move
-if command -v unzip >/dev/null; then
-  unzip ${__MVNW_QUIET_UNZIP:+"$__MVNW_QUIET_UNZIP"} "$TMP_DOWNLOAD_DIR/$distributionUrlName" -d "$TMP_DOWNLOAD_DIR" || die "failed to unzip"
-else
-  tar xzf${__MVNW_QUIET_TAR:+"$__MVNW_QUIET_TAR"} "$TMP_DOWNLOAD_DIR/$distributionUrlName" -C "$TMP_DOWNLOAD_DIR" || die "failed to untar"
-fi
-printf %s\\n "$distributionUrl" >"$TMP_DOWNLOAD_DIR/$distributionUrlNameMain/mvnw.url"
-mv -- "$TMP_DOWNLOAD_DIR/$distributionUrlNameMain" "$MAVEN_HOME" || [ -d "$MAVEN_HOME" ] || die "fail to move MAVEN_HOME"
-
-clean || :
-exec_maven "$@"

java/pom.xml

@@ -6,10 +6,11 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.21.2-final.0</version>
+    <version>0.19.1-beta.1</version>
     <packaging>pom</packaging>
-    <name>${project.artifactId}</name>
-    <description>LanceDB Java SDK Parent POM</description>
+
+    <name>LanceDB Parent</name>
+    <description>LanceDB vector database Java API</description>
     <url>http://lancedb.com/</url>
 
     <developers>
@@ -28,7 +29,6 @@
     <properties>
         <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
         <arrow.version>15.0.0</arrow.version>
-        <lance-namespace.verison>0.0.1</lance-namespace.verison>
         <spotless.skip>false</spotless.skip>
         <spotless.version>2.30.0</spotless.version>
         <spotless.java.googlejavaformat.version>1.7</spotless.java.googlejavaformat.version>
@@ -52,7 +52,6 @@
 
     <modules>
         <module>core</module>
-        <module>lance-namespace</module>
     </modules>
 
     <scm>
@@ -63,11 +62,6 @@
 
     <dependencyManagement>
         <dependencies>
-            <dependency>
-                <groupId>com.lancedb</groupId>
-                <artifactId>lance-namespace-core</artifactId>
-                <version>${lance-namespace.verison}</version>
-            </dependency>
             <dependency>
                 <groupId>org.apache.arrow</groupId>
                 <artifactId>arrow-vector</artifactId>

node/.eslintrc.js

@@ -0,0 +1,22 @@
+module.exports = {
+  env: {
+    browser: true,
+    es2021: true
+  },
+  extends: 'standard-with-typescript',
+  overrides: [
+  ],
+  parserOptions: {
+    project: './tsconfig.json',
+    ecmaVersion: 'latest',
+    sourceType: 'module'
+  },
+  rules: {
+    "@typescript-eslint/method-signature-style": "off",
+    "@typescript-eslint/quotes": "off",
+    "@typescript-eslint/semi": "off",
+    "@typescript-eslint/explicit-function-return-type": "off",
+    "@typescript-eslint/space-before-function-paren": "off",
+    "@typescript-eslint/indent": "off",
+  }
+}

node/.npmignore

@@ -0,0 +1,4 @@
+gen_test_data.py
+index.node
+dist/lancedb*.tgz
+vectordb*.tgz

node/CHANGELOG.md

@@ -0,0 +1,64 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [0.1.5] - 2023-06-00
+
+### Added
+
+- Support for macOS X86
+
+## [0.1.4] - 2023-06-03
+
+### Added
+
+- Select / Project query API
+
+### Changed
+
+-  Deprecated created_index in favor of createIndex
+
+## [0.1.3] - 2023-06-01
+
+### Added
+
+- Support S3 and Google Cloud Storage
+- Embedding functions support
+- OpenAI embedding function
+
+## [0.1.2] - 2023-05-27
+
+### Added
+
+- Append records API
+- Extra query params to to nodejs client
+- Create_index API
+ 
+### Fixed
+
+- bugfix: string columns should be converted to Utf8Array (#94)
+
+## [0.1.1] - 2023-05-16
+
+### Added
+
+- create_table API
+- limit parameter for queries
+- Typescript / JavaScript examples
+- Linux support
+
+## [0.1.0] - 2023-05-16
+
+### Added
+
+- Initial  JavaScript / Node.js library for LanceDB
+- Read-only api to query LanceDB datasets
+- Supports macOS arm only
+
+## [pre-0.1.0]
+
+- Various prototypes / test builds
+

node/README.md

@@ -0,0 +1,66 @@
+# LanceDB
+
+A JavaScript / Node.js library for [LanceDB](https://github.com/lancedb/lancedb).
+
+**DEPRECATED: This library is deprecated. Please use the new client,
+[@lancedb/lancedb](https://www.npmjs.com/package/@lancedb/lancedb).**
+
+## Installation
+
+```bash
+npm install vectordb
+```
+
+This will download the appropriate native library for your platform. We currently
+support:
+
+* Linux (x86_64 and aarch64)
+* MacOS (Intel and ARM/M1/M2)
+* Windows (x86_64 only)
+
+We do not yet support musl-based Linux (such as Alpine Linux) or aarch64 Windows.
+
+## Usage
+
+### Basic Example
+
+```javascript
+const lancedb = require('vectordb');
+const db = await lancedb.connect('data/sample-lancedb');
+const table = await db.createTable("my_table",
+      [{ id: 1, vector: [0.1, 1.0], item: "foo", price: 10.0 },
+      { id: 2, vector: [3.9, 0.5], item: "bar", price: 20.0 }])
+const results = await table.search([0.1, 0.3]).limit(20).execute();
+console.log(results);
+```
+
+The [examples](./examples) folder contains complete examples.
+
+## Development
+
+To build everything fresh:
+
+```bash
+npm install
+npm run build
+```
+
+Then you should be able to run the tests with:
+
+```bash
+npm test
+```
+
+### Fix lints
+
+To run the linter and have it automatically fix all errors
+
+```bash
+npm run lint -- --fix
+```
+
+To build documentation
+
+```bash
+npx typedoc --plugin typedoc-plugin-markdown --out ../docs/src/javascript src/index.ts
+```

node/examples/js-openai/index.js

@@ -0,0 +1,41 @@
+// Copyright 2023 Lance Developers.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+'use strict'
+
+async function example () {
+  const lancedb = require('vectordb')
+  // You need to provide an OpenAI API key, here we read it from the OPENAI_API_KEY environment variable
+  const apiKey = process.env.OPENAI_API_KEY
+  // The embedding function will create embeddings for the 'text' column(text in this case)
+  const embedding = new lancedb.OpenAIEmbeddingFunction('text', apiKey)
+
+  const db = await lancedb.connect('data/sample-lancedb')
+
+  const data = [
+    { id: 1, text: 'Black T-Shirt', price: 10 },
+    { id: 2, text: 'Leather Jacket', price: 50 }
+  ]
+
+  const table = await db.createTable('vectors', data, embedding)
+  console.log(await db.tableNames())
+
+  const results = await table
+    .search('keeps me warm')
+    .limit(1)
+    .execute()
+  console.log(results[0].text)
+}
+
+example().then(_ => { console.log('All done!') })

node/examples/js-openai/package.json

@@ -0,0 +1,15 @@
+{
+  "name": "vectordb-example-js-openai",
+  "version": "1.0.0",
+  "description": "",
+  "main": "index.js",
+  "scripts": {
+    "test": "echo \"Error: no test specified\" && exit 1"
+  },
+  "author": "Lance Devs",
+  "license": "Apache-2.0",
+  "dependencies": {
+    "vectordb": "file:../..",
+    "openai": "^3.2.1"
+  }
+}

node/examples/js-transformers/index.js

@@ -0,0 +1,66 @@
+// Copyright 2023 Lance Developers.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+'use strict'
+
+
+async function example() {
+
+    const lancedb = require('vectordb')
+
+    // Import transformers and the all-MiniLM-L6-v2 model (https://huggingface.co/Xenova/all-MiniLM-L6-v2)
+    const { pipeline } = await import('@xenova/transformers')
+    const pipe = await pipeline('feature-extraction', 'Xenova/all-MiniLM-L6-v2');
+
+
+    // Create embedding function from pipeline which returns a list of vectors from batch
+    // sourceColumn is the name of the column in the data to be embedded
+    //
+    // Output of pipe is a Tensor { data: Float32Array(384) }, so filter for the vector
+    const embed_fun = {}
+    embed_fun.sourceColumn = 'text'
+    embed_fun.embed = async function (batch) {
+        let result = []
+        for (let text of batch) {
+            const res = await pipe(text, { pooling: 'mean', normalize: true })
+            result.push(Array.from(res['data']))
+        }
+        return (result)
+    }
+
+    // Link a folder and create a table with data
+    const db = await lancedb.connect('data/sample-lancedb')
+
+    const data = [
+        { id: 1, text: 'Cherry', type: 'fruit' },
+        { id: 2, text: 'Carrot', type: 'vegetable' },
+        { id: 3, text: 'Potato', type: 'vegetable' },
+        { id: 4, text: 'Apple', type: 'fruit' },
+        { id: 5, text: 'Banana', type: 'fruit' }
+    ]
+
+    const table = await db.createTable('food_table', data, embed_fun)
+
+
+    // Query the table
+    const results = await table
+        .search("a sweet fruit to eat")
+        .metricType("cosine")
+        .limit(2)
+        .execute()
+    console.log(results.map(r => r.text))
+
+}
+
+example().then(_ => { console.log("Done!") })

node/examples/js-transformers/package.json

@@ -0,0 +1,16 @@
+{
+  "name": "vectordb-example-js-transformers",
+  "version": "1.0.0",
+  "description": "Example for using transformers.js with lancedb",
+  "main": "index.js",
+  "scripts": {
+    "test": "echo \"Error: no test specified\" && exit 1"
+  },
+  "author": "Lance Devs",
+  "license": "Apache-2.0",
+  "dependencies": {
+    "@xenova/transformers": "^2.4.1",
+    "vectordb": "file:../.."
+  }
+
+}

node/examples/js-youtube-transcripts/index.js

@@ -0,0 +1,122 @@
+// Copyright 2023 Lance Developers.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+'use strict'
+
+const lancedb = require('vectordb')
+const fs = require('fs/promises')
+const readline = require('readline/promises')
+const { stdin: input, stdout: output } = require('process')
+const { Configuration, OpenAIApi } = require('openai')
+
+// Download file from XYZ
+const INPUT_FILE_NAME = 'data/youtube-transcriptions_sample.jsonl';
+
+(async () => {
+  // You need to provide an OpenAI API key, here we read it from the OPENAI_API_KEY environment variable
+  const apiKey = process.env.OPENAI_API_KEY
+  // The embedding function will create embeddings for the 'context' column
+  const embedFunction = new lancedb.OpenAIEmbeddingFunction('context', apiKey)
+
+  // Connects to LanceDB
+  const db = await lancedb.connect('data/youtube-lancedb')
+
+  // Open the vectors table or create one if it does not exist
+  let tbl
+  if ((await db.tableNames()).includes('vectors')) {
+    tbl = await db.openTable('vectors', embedFunction)
+  } else {
+    tbl = await createEmbeddingsTable(db, embedFunction)
+  }
+
+  // Use OpenAI Completion API to generate and answer based on the context that LanceDB provides
+  const configuration = new Configuration({ apiKey })
+  const openai = new OpenAIApi(configuration)
+  const rl = readline.createInterface({ input, output })
+  try {
+    while (true) {
+      const query = await rl.question('Prompt: ')
+      const results = await tbl
+        .search(query)
+        .select(['title', 'text', 'context'])
+        .limit(3)
+        .execute()
+
+      // console.table(results)
+
+      const response = await openai.createCompletion({
+        model: 'text-davinci-003',
+        prompt: createPrompt(query, results),
+        max_tokens: 400,
+        temperature: 0,
+        top_p: 1,
+        frequency_penalty: 0,
+        presence_penalty: 0
+      })
+      console.log(response.data.choices[0].text)
+    }
+  } catch (err) {
+    console.log('Error: ', err)
+  } finally {
+    rl.close()
+  }
+  process.exit(1)
+})()
+
+async function createEmbeddingsTable (db, embedFunction) {
+  console.log(`Creating embeddings from ${INPUT_FILE_NAME}`)
+  // read the input file into a JSON array, skipping empty lines
+  const lines = (await fs.readFile(INPUT_FILE_NAME, 'utf-8'))
+    .toString()
+    .split('\n')
+    .filter(line => line.length > 0)
+    .map(line => JSON.parse(line))
+
+  const data = contextualize(lines, 20, 'video_id')
+  return await db.createTable('vectors', data, embedFunction)
+}
+
+// Each transcript has a small text column, we include previous transcripts in order to
+// have more context information when creating embeddings
+function contextualize (rows, contextSize, groupColumn) {
+  const grouped = []
+  rows.forEach(row => {
+    if (!grouped[row[groupColumn]]) {
+      grouped[row[groupColumn]] = []
+    }
+    grouped[row[groupColumn]].push(row)
+  })
+
+  const data = []
+  Object.keys(grouped).forEach(key => {
+    for (let i = 0; i < grouped[key].length; i++) {
+      const start = i - contextSize > 0 ? i - contextSize : 0
+      grouped[key][i].context = grouped[key].slice(start, i + 1).map(r => r.text).join(' ')
+    }
+    data.push(...grouped[key])
+  })
+  return data
+}
+
+// Creates a prompt by aggregating all relevant contexts
+function createPrompt (query, context) {
+  let prompt =
+      'Answer the question based on the context below.\n\n' +
+      'Context:\n'
+
+  // need to make sure our prompt is not larger than max size
+  prompt = prompt + context.map(c => c.context).join('\n\n---\n\n').substring(0, 3750)
+  prompt = prompt + `\n\nQuestion: ${query}\nAnswer:`
+  return prompt
+}

node/examples/js-youtube-transcripts/package.json

@@ -0,0 +1,15 @@
+{
+  "name": "vectordb-example-js-openai",
+  "version": "1.0.0",
+  "description": "",
+  "main": "index.js",
+  "scripts": {
+    "test": "echo \"Error: no test specified\" && exit 1"
+  },
+  "author": "Lance Devs",
+  "license": "Apache-2.0",
+  "dependencies": {
+    "vectordb": "file:../..",
+    "openai": "^3.2.1"
+  }
+}

node/examples/js/index.js

@@ -0,0 +1,36 @@
+// Copyright 2023 Lance Developers.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+'use strict'
+
+async function example () {
+  const lancedb = require('vectordb')
+  const db = await lancedb.connect('data/sample-lancedb')
+
+  const data = [
+    { id: 1, vector: [0.1, 0.2], price: 10 },
+    { id: 2, vector: [1.1, 1.2], price: 50 }
+  ]
+
+  const table = await db.createTable('vectors', data)
+  console.log(await db.tableNames())
+
+  const results = await table
+      .search([0.1, 0.3])
+      .limit(20)
+      .execute()
+  console.log(results)
+}
+
+example()

node/examples/js/package.json

@@ -0,0 +1,14 @@
+{
+  "name": "vectordb-example-js",
+  "version": "1.0.0",
+  "description": "",
+  "main": "index.js",
+  "scripts": {
+    "test": "echo \"Error: no test specified\" && exit 1"
+  },
+  "author": "Lance Devs",
+  "license": "Apache-2.0",
+  "dependencies": {
+    "vectordb": "file:../.."
+  }
+}

node/examples/ts/package.json

@@ -0,0 +1,22 @@
+{
+  "name": "vectordb-example-ts",
+  "version": "1.0.0",
+  "description": "",
+  "main": "dist/index.js",
+  "types": "dist/index.d.ts",
+  "scripts": {
+    "tsc": "tsc -b",
+    "build": "tsc"
+  },
+  "author": "Lance Devs",
+  "license": "Apache-2.0",
+  "devDependencies": {
+    "@types/node": "^18.16.2",
+    "ts-node": "^10.9.1",
+    "ts-node-dev": "^2.0.0",
+    "typescript": "*"
+  },
+  "dependencies": {
+    "vectordb": "file:../.."
+  }
+}

node/examples/ts/src/index.ts

@@ -0,0 +1,35 @@
+// Copyright 2023 Lance Developers.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+import * as vectordb from 'vectordb';
+
+async function example () {
+    const db = await vectordb.connect('data/sample-lancedb')
+
+    const data = [
+        { id: 1, vector: [0.1, 0.2], price: 10 },
+        { id: 2, vector: [1.1, 1.2], price: 50 }
+    ]
+
+    const table = await db.createTable('vectors', data)
+    console.log(await db.tableNames())
+
+    const results = await table
+        .search([0.1, 0.3])
+        .limit(20)
+        .execute()
+    console.log(results)
+}
+
+example().then(_ => { console.log ("All done!") })

node/examples/ts/tsconfig.json

@@ -0,0 +1,10 @@
+{
+  "include": ["src/**/*.ts"],
+  "compilerOptions": {
+    "target": "es2016",
+    "module": "commonjs",
+    "declaration": true,
+    "outDir": "./dist",
+    "strict": true
+  }
+}

node/native.js

@@ -0,0 +1,36 @@
+// Copyright 2023 Lance Developers.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+const { currentTarget } = require('@neon-rs/load')
+
+let nativeLib
+
+try {
+  // When developing locally, give preference to the local built library
+  nativeLib = require('./index.node')
+} catch {
+  try {
+    nativeLib = require(`@lancedb/vectordb-${currentTarget()}`)
+  } catch (e) {
+    throw new Error(`vectordb: failed to load native library.
+  You may need to run \`npm install @lancedb/vectordb-${currentTarget()}\`.
+
+  If that does not work, please file a bug report at https://github.com/lancedb/lancedb/issues
+      
+  Source error: ${e}`)
+  }
+}
+
+// Dynamic require for runtime.
+module.exports = nativeLib

node/package.json

@@ -0,0 +1,98 @@
+{
+  "name": "vectordb",
+  "version": "0.19.1-beta.1",
+  "description": " Serverless, low-latency vector database for AI applications",
+  "private": false,
+  "main": "dist/index.js",
+  "types": "dist/index.d.ts",
+  "scripts": {
+    "tsc": "tsc -b",
+    "build": "npm run tsc && cargo-cp-artifact --artifact cdylib lancedb_node index.node -- cargo build -p lancedb-node --message-format=json",
+    "build-release": "npm run build -- --release",
+    "test": "npm run tsc && mocha -recursive dist/test",
+    "integration-test": "npm run tsc && mocha -recursive dist/integration_test",
+    "lint": "eslint native.js src --ext .js,.ts",
+    "clean": "rm -rf node_modules *.node dist/",
+    "pack-build": "neon pack-build",
+    "check-npm": "printenv && which node && which npm && npm --version"
+  },
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/lancedb/lancedb.git"
+  },
+  "homepage": "https://lancedb.github.io/lancedb/",
+  "bugs": {
+    "url": "https://github.com/lancedb/lancedb/issues"
+  },
+  "keywords": [
+    "data-format",
+    "data-science",
+    "machine-learning",
+    "data-analytics"
+  ],
+  "author": "Lance Devs",
+  "license": "Apache-2.0",
+  "devDependencies": {
+    "@neon-rs/cli": "^0.0.160",
+    "@types/chai": "^4.3.4",
+    "@types/chai-as-promised": "^7.1.5",
+    "@types/mocha": "^10.0.1",
+    "@types/node": "^18.16.2",
+    "@types/sinon": "^10.0.15",
+    "@types/temp": "^0.9.1",
+    "@types/uuid": "^9.0.3",
+    "@typescript-eslint/eslint-plugin": "^5.59.1",
+    "apache-arrow-old": "npm:apache-arrow@13.0.0",
+    "cargo-cp-artifact": "^0.1",
+    "chai": "^4.3.7",
+    "chai-as-promised": "^7.1.1",
+    "eslint": "^8.39.0",
+    "eslint-config-standard-with-typescript": "^34.0.1",
+    "eslint-plugin-import": "^2.26.0",
+    "eslint-plugin-n": "^15.7.0",
+    "eslint-plugin-promise": "^6.1.1",
+    "mocha": "^10.2.0",
+    "openai": "^4.24.1",
+    "sinon": "^15.1.0",
+    "temp": "^0.9.4",
+    "ts-node": "^10.9.1",
+    "ts-node-dev": "^2.0.0",
+    "typedoc": "^0.24.7",
+    "typedoc-plugin-markdown": "^3.15.3",
+    "typescript": "^5.1.0",
+    "uuid": "^9.0.0"
+  },
+  "dependencies": {
+    "@neon-rs/load": "^0.0.74",
+    "axios": "^1.4.0"
+  },
+  "peerDependencies": {
+    "@apache-arrow/ts": "^14.0.2",
+    "apache-arrow": "^14.0.2"
+  },
+  "os": [
+    "darwin",
+    "linux",
+    "win32"
+  ],
+  "cpu": [
+    "x64",
+    "arm64"
+  ],
+  "neon": {
+    "targets": {
+      "x86_64-apple-darwin": "@lancedb/vectordb-darwin-x64",
+      "aarch64-apple-darwin": "@lancedb/vectordb-darwin-arm64",
+      "x86_64-unknown-linux-gnu": "@lancedb/vectordb-linux-x64-gnu",
+      "aarch64-unknown-linux-gnu": "@lancedb/vectordb-linux-arm64-gnu",
+      "x86_64-pc-windows-msvc": "@lancedb/vectordb-win32-x64-msvc"
+    }
+  },
+  "optionalDependencies": {
+    "@lancedb/vectordb-darwin-x64": "0.19.1-beta.1",
+    "@lancedb/vectordb-darwin-arm64": "0.19.1-beta.1",
+    "@lancedb/vectordb-linux-x64-gnu": "0.19.1-beta.1",
+    "@lancedb/vectordb-linux-arm64-gnu": "0.19.1-beta.1",
+    "@lancedb/vectordb-win32-x64-msvc": "0.19.1-beta.1"
+  }
+}

node/src/arrow.ts

@@ -0,0 +1,635 @@
+// Copyright 2023 Lance Developers.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+import {
+  Field,
+  makeBuilder,
+  RecordBatchFileWriter,
+  Utf8,
+  type Vector,
+  FixedSizeList,
+  vectorFromArray,
+  Schema,
+  Table as ArrowTable,
+  RecordBatchStreamWriter,
+  List,
+  RecordBatch,
+  makeData,
+  Struct,
+  type Float,
+  DataType,
+  Binary,
+  Float32
+} from "apache-arrow";
+import { type EmbeddingFunction } from "./index";
+import { sanitizeSchema } from "./sanitize";
+
+/*
+ * Options to control how a column should be converted to a vector array
+ */
+export class VectorColumnOptions {
+  /** Vector column type. */
+  type: Float = new Float32();
+
+  constructor(values?: Partial<VectorColumnOptions>) {
+    Object.assign(this, values);
+  }
+}
+
+/** Options to control the makeArrowTable call. */
+export class MakeArrowTableOptions {
+  /*
+   * Schema of the data.
+   *
+   * If this is not provided then the data type will be inferred from the
+   * JS type.  Integer numbers will become int64, floating point numbers
+   * will become float64 and arrays will become variable sized lists with
+   * the data type inferred from the first element in the array.
+   *
+   * The schema must be specified if there are no records (e.g. to make
+   * an empty table)
+   */
+  schema?: Schema;
+
+  /*
+   * Mapping from vector column name to expected type
+   *
+   * Lance expects vector columns to be fixed size list arrays (i.e. tensors)
+   * However, `makeArrowTable` will not infer this by default (it creates
+   * variable size list arrays).  This field can be used to indicate that a column
+   * should be treated as a vector column and converted to a fixed size list.
+   *
+   * The keys should be the names of the vector columns.  The value specifies the
+   * expected data type of the vector columns.
+   *
+   * If `schema` is provided then this field is ignored.
+   *
+   * By default, the column named "vector" will be assumed to be a float32
+   * vector column.
+   */
+  vectorColumns: Record<string, VectorColumnOptions> = {
+    vector: new VectorColumnOptions()
+  };
+
+  embeddings?: EmbeddingFunction<any>;
+
+  /**
+   * If true then string columns will be encoded with dictionary encoding
+   *
+   * Set this to true if your string columns tend to repeat the same values
+   * often.  For more precise control use the `schema` property to specify the
+   * data type for individual columns.
+   *
+   * If `schema` is provided then this property is ignored.
+   */
+  dictionaryEncodeStrings: boolean = false;
+
+  constructor(values?: Partial<MakeArrowTableOptions>) {
+    Object.assign(this, values);
+  }
+}
+
+/**
+ * An enhanced version of the {@link makeTable} function from Apache Arrow
+ * that supports nested fields and embeddings columns.
+ *
+ * This function converts an array of Record<String, any> (row-major JS objects)
+ * to an Arrow Table (a columnar structure)
+ *
+ * Note that it currently does not support nulls.
+ *
+ * If a schema is provided then it will be used to determine the resulting array
+ * types.  Fields will also be reordered to fit the order defined by the schema.
+ *
+ * If a schema is not provided then the types will be inferred and the field order
+ * will be controlled by the order of properties in the first record.
+ *
+ * If the input is empty then a schema must be provided to create an empty table.
+ *
+ * When a schema is not specified then data types will be inferred.  The inference
+ * rules are as follows:
+ *
+ *  - boolean => Bool
+ *  - number => Float64
+ *  - String => Utf8
+ *  - Buffer => Binary
+ *  - Record<String, any> => Struct
+ *  - Array<any> => List
+ *
+ * @param data input data
+ * @param options options to control the makeArrowTable call.
+ *
+ * @example
+ *
+ * ```ts
+ *
+ * import { fromTableToBuffer, makeArrowTable } from "../arrow";
+ * import { Field, FixedSizeList, Float16, Float32, Int32, Schema } from "apache-arrow";
+ *
+ * const schema = new Schema([
+ *   new Field("a", new Int32()),
+ *   new Field("b", new Float32()),
+ *   new Field("c", new FixedSizeList(3, new Field("item", new Float16()))),
+ *  ]);
+ *  const table = makeArrowTable([
+ *    { a: 1, b: 2, c: [1, 2, 3] },
+ *    { a: 4, b: 5, c: [4, 5, 6] },
+ *    { a: 7, b: 8, c: [7, 8, 9] },
+ *  ], { schema });
+ * ```
+ *
+ * By default it assumes that the column named `vector` is a vector column
+ * and it will be converted into a fixed size list array of type float32.
+ * The `vectorColumns` option can be used to support other vector column
+ * names and data types.
+ *
+ * ```ts
+ *
+ * const schema = new Schema([
+    new Field("a", new Float64()),
+    new Field("b", new Float64()),
+    new Field(
+      "vector",
+      new FixedSizeList(3, new Field("item", new Float32()))
+    ),
+  ]);
+  const table = makeArrowTable([
+    { a: 1, b: 2, vector: [1, 2, 3] },
+    { a: 4, b: 5, vector: [4, 5, 6] },
+    { a: 7, b: 8, vector: [7, 8, 9] },
+  ]);
+  assert.deepEqual(table.schema, schema);
+ * ```
+ *
+ * You can specify the vector column types and names using the options as well
+ *
+ * ```typescript
+ *
+ * const schema = new Schema([
+    new Field('a', new Float64()),
+    new Field('b', new Float64()),
+    new Field('vec1', new FixedSizeList(3, new Field('item', new Float16()))),
+    new Field('vec2', new FixedSizeList(3, new Field('item', new Float16())))
+  ]);
+ * const table = makeArrowTable([
+    { a: 1, b: 2, vec1: [1, 2, 3], vec2: [2, 4, 6] },
+    { a: 4, b: 5, vec1: [4, 5, 6], vec2: [8, 10, 12] },
+    { a: 7, b: 8, vec1: [7, 8, 9], vec2: [14, 16, 18] }
+  ], {
+    vectorColumns: {
+      vec1: { type: new Float16() },
+      vec2: { type: new Float16() }
+    }
+  }
+ * assert.deepEqual(table.schema, schema)
+ * ```
+ */
+export function makeArrowTable(
+  data: Array<Record<string, any>>,
+  options?: Partial<MakeArrowTableOptions>
+): ArrowTable {
+  if (
+    data.length === 0 &&
+    (options?.schema === undefined || options?.schema === null)
+  ) {
+    throw new Error("At least one record or a schema needs to be provided");
+  }
+
+  const opt = new MakeArrowTableOptions(options !== undefined ? options : {});
+  if (opt.schema !== undefined && opt.schema !== null) {
+    opt.schema = sanitizeSchema(opt.schema);
+    opt.schema = validateSchemaEmbeddings(opt.schema, data, opt.embeddings);
+  }
+
+  const columns: Record<string, Vector> = {};
+  // TODO: sample dataset to find missing columns
+  // Prefer the field ordering of the schema, if present
+  const columnNames =
+    opt.schema != null ? (opt.schema.names as string[]) : Object.keys(data[0]);
+  for (const colName of columnNames) {
+    if (
+      data.length !== 0 &&
+      !Object.prototype.hasOwnProperty.call(data[0], colName)
+    ) {
+      // The field is present in the schema, but not in the data, skip it
+      continue;
+    }
+    // Extract a single column from the records (transpose from row-major to col-major)
+    let values = data.map((datum) => datum[colName]);
+
+    // By default (type === undefined) arrow will infer the type from the JS type
+    let type;
+    if (opt.schema !== undefined) {
+      // If there is a schema provided, then use that for the type instead
+      type = opt.schema?.fields.filter((f) => f.name === colName)[0]?.type;
+      if (DataType.isInt(type) && type.bitWidth === 64) {
+        // wrap in BigInt to avoid bug: https://github.com/apache/arrow/issues/40051
+        values = values.map((v) => {
+          if (v === null) {
+            return v;
+          }
+          return BigInt(v);
+        });
+      }
+    } else {
+      // Otherwise, check to see if this column is one of the vector columns
+      // defined by opt.vectorColumns and, if so, use the fixed size list type
+      const vectorColumnOptions = opt.vectorColumns[colName];
+      if (vectorColumnOptions !== undefined) {
+        type = newVectorType(values[0].length, vectorColumnOptions.type);
+      }
+    }
+
+    try {
+      // Convert an Array of JS values to an arrow vector
+      columns[colName] = makeVector(values, type, opt.dictionaryEncodeStrings);
+    } catch (error: unknown) {
+      // eslint-disable-next-line @typescript-eslint/restrict-template-expressions
+      throw Error(`Could not convert column "${colName}" to Arrow: ${error}`);
+    }
+  }
+
+  if (opt.schema != null) {
+    // `new ArrowTable(columns)` infers a schema which may sometimes have
+    // incorrect nullability (it assumes nullable=true if there are 0 rows)
+    //
+    // `new ArrowTable(schema, columns)` will also fail because it will create a
+    // batch with an inferred schema and then complain that the batch schema
+    // does not match the provided schema.
+    //
+    // To work around this we first create a table with the wrong schema and
+    // then patch the schema of the batches so we can use
+    // `new ArrowTable(schema, batches)` which does not do any schema inference
+    const firstTable = new ArrowTable(columns);
+    const batchesFixed = firstTable.batches.map(
+      // eslint-disable-next-line @typescript-eslint/no-non-null-assertion
+      (batch) => new RecordBatch(opt.schema!, batch.data)
+    );
+    return new ArrowTable(opt.schema, batchesFixed);
+  } else {
+    return new ArrowTable(columns);
+  }
+}
+
+/**
+ * Create an empty Arrow table with the provided schema
+ */
+export function makeEmptyTable(schema: Schema): ArrowTable {
+  return makeArrowTable([], { schema });
+}
+
+// Helper function to convert Array<Array<any>> to a variable sized list array
+function makeListVector(lists: any[][]): Vector<any> {
+  if (lists.length === 0 || lists[0].length === 0) {
+    throw Error("Cannot infer list vector from empty array or empty list");
+  }
+  const sampleList = lists[0];
+  let inferredType;
+  try {
+    const sampleVector = makeVector(sampleList);
+    inferredType = sampleVector.type;
+  } catch (error: unknown) {
+    // eslint-disable-next-line @typescript-eslint/restrict-template-expressions
+    throw Error(`Cannot infer list vector.  Cannot infer inner type: ${error}`);
+  }
+
+  const listBuilder = makeBuilder({
+    type: new List(new Field("item", inferredType, true))
+  });
+  for (const list of lists) {
+    listBuilder.append(list);
+  }
+  return listBuilder.finish().toVector();
+}
+
+// Helper function to convert an Array of JS values to an Arrow Vector
+function makeVector(
+  values: any[],
+  type?: DataType,
+  stringAsDictionary?: boolean
+): Vector<any> {
+  if (type !== undefined) {
+    // No need for inference, let Arrow create it
+    return vectorFromArray(values, type);
+  }
+  if (values.length === 0) {
+    throw Error(
+      "makeVector requires at least one value or the type must be specfied"
+    );
+  }
+  const sampleValue = values.find((val) => val !== null && val !== undefined);
+  if (sampleValue === undefined) {
+    throw Error(
+      "makeVector cannot infer the type if all values are null or undefined"
+    );
+  }
+  if (Array.isArray(sampleValue)) {
+    // Default Arrow inference doesn't handle list types
+    return makeListVector(values);
+  } else if (Buffer.isBuffer(sampleValue)) {
+    // Default Arrow inference doesn't handle Buffer
+    return vectorFromArray(values, new Binary());
+  } else if (
+    !(stringAsDictionary ?? false) &&
+    (typeof sampleValue === "string" || sampleValue instanceof String)
+  ) {
+    // If the type is string then don't use Arrow's default inference unless dictionaries are requested
+    // because it will always use dictionary encoding for strings
+    return vectorFromArray(values, new Utf8());
+  } else {
+    // Convert a JS array of values to an arrow vector
+    return vectorFromArray(values);
+  }
+}
+
+async function applyEmbeddings<T>(
+  table: ArrowTable,
+  embeddings?: EmbeddingFunction<T>,
+  schema?: Schema
+): Promise<ArrowTable> {
+  if (embeddings == null) {
+    return table;
+  }
+  if (schema !== undefined && schema !== null) {
+    schema = sanitizeSchema(schema);
+  }
+
+  // Convert from ArrowTable to Record<String, Vector>
+  const colEntries = [...Array(table.numCols).keys()].map((_, idx) => {
+    const name = table.schema.fields[idx].name;
+    // eslint-disable-next-line @typescript-eslint/no-non-null-assertion
+    const vec = table.getChildAt(idx)!;
+    return [name, vec];
+  });
+  const newColumns = Object.fromEntries(colEntries);
+
+  const sourceColumn = newColumns[embeddings.sourceColumn];
+  const destColumn = embeddings.destColumn ?? "vector";
+  const innerDestType = embeddings.embeddingDataType ?? new Float32();
+  if (sourceColumn === undefined) {
+    throw new Error(
+      `Cannot apply embedding function because the source column '${embeddings.sourceColumn}' was not present in the data`
+    );
+  }
+
+  if (table.numRows === 0) {
+    if (Object.prototype.hasOwnProperty.call(newColumns, destColumn)) {
+      // We have an empty table and it already has the embedding column so no work needs to be done
+      // Note: we don't return an error like we did below because this is a common occurrence.  For example,
+      // if we call convertToTable with 0 records and a schema that includes the embedding
+      return table;
+    }
+    if (embeddings.embeddingDimension !== undefined) {
+      const destType = newVectorType(
+        embeddings.embeddingDimension,
+        innerDestType
+      );
+      newColumns[destColumn] = makeVector([], destType);
+    } else if (schema != null) {
+      const destField = schema.fields.find((f) => f.name === destColumn);
+      if (destField != null) {
+        newColumns[destColumn] = makeVector([], destField.type);
+      } else {
+        throw new Error(
+          `Attempt to apply embeddings to an empty table failed because schema was missing embedding column '${destColumn}'`
+        );
+      }
+    } else {
+      throw new Error(
+        "Attempt to apply embeddings to an empty table when the embeddings function does not specify `embeddingDimension`"
+      );
+    }
+  } else {
+    if (Object.prototype.hasOwnProperty.call(newColumns, destColumn)) {
+      throw new Error(
+        `Attempt to apply embeddings to table failed because column ${destColumn} already existed`
+      );
+    }
+    if (table.batches.length > 1) {
+      throw new Error(
+        "Internal error: `makeArrowTable` unexpectedly created a table with more than one batch"
+      );
+    }
+    const values = sourceColumn.toArray();
+    const vectors = await embeddings.embed(values as T[]);
+    if (vectors.length !== values.length) {
+      throw new Error(
+        "Embedding function did not return an embedding for each input element"
+      );
+    }
+    const destType = newVectorType(vectors[0].length, innerDestType);
+    newColumns[destColumn] = makeVector(vectors, destType);
+  }
+
+  const newTable = new ArrowTable(newColumns);
+  if (schema != null) {
+    if (schema.fields.find((f) => f.name === destColumn) === undefined) {
+      throw new Error(
+        `When using embedding functions and specifying a schema the schema should include the embedding column but the column ${destColumn} was missing`
+      );
+    }
+    return alignTable(newTable, schema);
+  }
+  return newTable;
+}
+
+/*
+ * Convert an Array of records into an Arrow Table, optionally applying an
+ * embeddings function to it.
+ *
+ * This function calls `makeArrowTable` first to create the Arrow Table.
+ * Any provided `makeTableOptions` (e.g. a schema) will be passed on to
+ * that call.
+ *
+ * The embedding function will be passed a column of values (based on the
+ * `sourceColumn` of the embedding function) and expects to receive back
+ * number[][] which will be converted into a fixed size list column.  By
+ * default this will be a fixed size list of Float32 but that can be
+ * customized by the `embeddingDataType` property of the embedding function.
+ *
+ * If a schema is provided in `makeTableOptions` then it should include the
+ * embedding columns.  If no schema is provded then embedding columns will
+ * be placed at the end of the table, after all of the input columns.
+ */
+export async function convertToTable<T>(
+  data: Array<Record<string, unknown>>,
+  embeddings?: EmbeddingFunction<T>,
+  makeTableOptions?: Partial<MakeArrowTableOptions>
+): Promise<ArrowTable> {
+  const table = makeArrowTable(data, makeTableOptions);
+  return await applyEmbeddings(table, embeddings, makeTableOptions?.schema);
+}
+
+// Creates the Arrow Type for a Vector column with dimension `dim`
+function newVectorType<T extends Float>(
+  dim: number,
+  innerType: T
+): FixedSizeList<T> {
+  // Somewhere we always default to have the elements nullable, so we need to set it to true
+  // otherwise we often get schema mismatches because the stored data always has schema with nullable elements
+  const children = new Field<T>("item", innerType, true);
+  return new FixedSizeList(dim, children);
+}
+
+/**
+ * Serialize an Array of records into a buffer using the Arrow IPC File serialization
+ *
+ * This function will call `convertToTable` and pass on `embeddings` and `schema`
+ *
+ * `schema` is required if data is empty
+ */
+export async function fromRecordsToBuffer<T>(
+  data: Array<Record<string, unknown>>,
+  embeddings?: EmbeddingFunction<T>,
+  schema?: Schema
+): Promise<Buffer> {
+  if (schema !== undefined && schema !== null) {
+    schema = sanitizeSchema(schema);
+  }
+  const table = await convertToTable(data, embeddings, { schema, embeddings });
+  const writer = RecordBatchFileWriter.writeAll(table);
+  return Buffer.from(await writer.toUint8Array());
+}
+
+/**
+ * Serialize an Array of records into a buffer using the Arrow IPC Stream serialization
+ *
+ * This function will call `convertToTable` and pass on `embeddings` and `schema`
+ *
+ * `schema` is required if data is empty
+ */
+export async function fromRecordsToStreamBuffer<T>(
+  data: Array<Record<string, unknown>>,
+  embeddings?: EmbeddingFunction<T>,
+  schema?: Schema
+): Promise<Buffer> {
+  if (schema !== null && schema !== undefined) {
+    schema = sanitizeSchema(schema);
+  }
+  const table = await convertToTable(data, embeddings, { schema });
+  const writer = RecordBatchStreamWriter.writeAll(table);
+  return Buffer.from(await writer.toUint8Array());
+}
+
+/**
+ * Serialize an Arrow Table into a buffer using the Arrow IPC File serialization
+ *
+ * This function will apply `embeddings` to the table in a manner similar to
+ * `convertToTable`.
+ *
+ * `schema` is required if the table is empty
+ */
+export async function fromTableToBuffer<T>(
+  table: ArrowTable,
+  embeddings?: EmbeddingFunction<T>,
+  schema?: Schema
+): Promise<Buffer> {
+  if (schema !== null && schema !== undefined) {
+    schema = sanitizeSchema(schema);
+  }
+  const tableWithEmbeddings = await applyEmbeddings(table, embeddings, schema);
+  const writer = RecordBatchFileWriter.writeAll(tableWithEmbeddings);
+  return Buffer.from(await writer.toUint8Array());
+}
+
+/**
+ * Serialize an Arrow Table into a buffer using the Arrow IPC Stream serialization
+ *
+ * This function will apply `embeddings` to the table in a manner similar to
+ * `convertToTable`.
+ *
+ * `schema` is required if the table is empty
+ */
+export async function fromTableToStreamBuffer<T>(
+  table: ArrowTable,
+  embeddings?: EmbeddingFunction<T>,
+  schema?: Schema
+): Promise<Buffer> {
+  if (schema !== null && schema !== undefined) {
+    schema = sanitizeSchema(schema);
+  }
+  const tableWithEmbeddings = await applyEmbeddings(table, embeddings, schema);
+  const writer = RecordBatchStreamWriter.writeAll(tableWithEmbeddings);
+  return Buffer.from(await writer.toUint8Array());
+}
+
+function alignBatch(batch: RecordBatch, schema: Schema): RecordBatch {
+  const alignedChildren = [];
+  for (const field of schema.fields) {
+    const indexInBatch = batch.schema.fields?.findIndex(
+      (f) => f.name === field.name
+    );
+    if (indexInBatch < 0) {
+      throw new Error(
+        `The column ${field.name} was not found in the Arrow Table`
+      );
+    }
+    alignedChildren.push(batch.data.children[indexInBatch]);
+  }
+  const newData = makeData({
+    type: new Struct(schema.fields),
+    length: batch.numRows,
+    nullCount: batch.nullCount,
+    children: alignedChildren
+  });
+  return new RecordBatch(schema, newData);
+}
+
+function alignTable(table: ArrowTable, schema: Schema): ArrowTable {
+  const alignedBatches = table.batches.map((batch) =>
+    alignBatch(batch, schema)
+  );
+  return new ArrowTable(schema, alignedBatches);
+}
+
+// Creates an empty Arrow Table
+export function createEmptyTable(schema: Schema): ArrowTable {
+  return new ArrowTable(sanitizeSchema(schema));
+}
+
+function validateSchemaEmbeddings(
+  schema: Schema<any>,
+  data: Array<Record<string, unknown>>,
+  embeddings: EmbeddingFunction<any> | undefined
+) {
+  const fields = [];
+  const missingEmbeddingFields = [];
+
+  // First we check if the field is a `FixedSizeList`
+  // Then we check if the data contains the field
+  // if it does not, we add it to the list of missing embedding fields
+  // Finally, we check if those missing embedding fields are `this._embeddings`
+  // if they are not, we throw an error
+  for (const field of schema.fields) {
+    if (field.type instanceof FixedSizeList) {
+      if (data.length !== 0 && data?.[0]?.[field.name] === undefined) {
+        missingEmbeddingFields.push(field);
+      } else {
+        fields.push(field);
+      }
+    } else {
+      fields.push(field);
+    }
+  }
+
+  if (missingEmbeddingFields.length > 0 && embeddings === undefined) {
+    throw new Error(
+      `Table has embeddings: "${missingEmbeddingFields
+        .map((f) => f.name)
+        .join(",")}", but no embedding function was provided`
+    );
+  }
+
+  return new Schema(fields, schema.metadata);
+}

node/src/embedding/embedding_function.ts

@@ -0,0 +1,68 @@
+// Copyright 2023 Lance Developers.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+import { type Float } from 'apache-arrow'
+
+/**
+ * An embedding function that automatically creates vector representation for a given column.
+ */
+export interface EmbeddingFunction<T> {
+  /**
+   * The name of the column that will be used as input for the Embedding Function.
+   */
+  sourceColumn: string
+
+  /**
+   * The data type of the embedding
+   *
+   * The embedding function should return `number`.  This will be converted into
+   * an Arrow float array.  By default this will be Float32 but this property can
+   * be used to control the conversion.
+   */
+  embeddingDataType?: Float
+
+  /**
+   * The dimension of the embedding
+   *
+   * This is optional, normally this can be determined by looking at the results of
+   * `embed`.  If this is not specified, and there is an attempt to apply the embedding
+   * to an empty table, then that process will fail.
+   */
+  embeddingDimension?: number
+
+  /**
+   * The name of the column that will contain the embedding
+   *
+   * By default this is "vector"
+   */
+  destColumn?: string
+
+  /**
+   * Should the source column be excluded from the resulting table
+   *
+   * By default the source column is included.  Set this to true and
+   * only the embedding will be stored.
+   */
+  excludeSource?: boolean
+
+  /**
+   * Creates a vector representation for the given values.
+   */
+  embed: (data: T[]) => Promise<number[][]>
+}
+
+export function isEmbeddingFunction<T> (value: any): value is EmbeddingFunction<T> {
+  return typeof value.sourceColumn === 'string' &&
+      typeof value.embed === 'function'
+}

node/src/embedding/openai.ts

@@ -0,0 +1,57 @@
+// Copyright 2023 Lance Developers.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+import { type EmbeddingFunction } from '../index'
+import type OpenAI from 'openai'
+
+export class OpenAIEmbeddingFunction implements EmbeddingFunction<string> {
+  private readonly _openai: OpenAI
+  private readonly _modelName: string
+
+  constructor (sourceColumn: string, openAIKey: string, modelName: string = 'text-embedding-ada-002') {
+    /**
+     * @type {import("openai").default}
+     */
+    let Openai
+    try {
+      // eslint-disable-next-line @typescript-eslint/no-var-requires
+      Openai = require('openai')
+    } catch {
+      throw new Error('please install openai@^4.24.1 using npm install openai')
+    }
+
+    this.sourceColumn = sourceColumn
+    const configuration = {
+      apiKey: openAIKey
+    }
+
+    this._openai = new Openai(configuration)
+    this._modelName = modelName
+  }
+
+  async embed (data: string[]): Promise<number[][]> {
+    const response = await this._openai.embeddings.create({
+      model: this._modelName,
+      input: data
+    })
+
+    const embeddings: number[][] = []
+    for (let i = 0; i < response.data.length; i++) {
+      embeddings.push(response.data[i].embedding)
+    }
+    return embeddings
+  }
+
+  sourceColumn: string
+}

node/src/integration_test/test.ts

@@ -0,0 +1,180 @@
+// Copyright 2023 LanceDB Developers.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+import { describe } from 'mocha'
+import * as chai from 'chai'
+import { assert } from 'chai'
+import * as chaiAsPromised from 'chai-as-promised'
+import { v4 as uuidv4 } from 'uuid'
+
+import * as lancedb from '../index'
+import { tmpdir } from 'os'
+import * as fs from 'fs'
+import * as path from 'path'
+
+chai.use(chaiAsPromised)
+
+describe('LanceDB AWS Integration test', function () {
+  it('s3+ddb schema is processed correctly', async function () {
+    this.timeout(15000)
+
+    // WARNING: specifying engine is NOT a publicly supported feature in lancedb yet
+    // THE API WILL CHANGE
+    const conn = await lancedb.connect('s3://lancedb-integtest?engine=ddb&ddbTableName=lancedb-integtest')
+    const data = [{ vector: Array(128).fill(1.0) }]
+
+    const tableName = uuidv4()
+    let table = await conn.createTable(tableName, data, { writeMode: lancedb.WriteMode.Overwrite })
+
+    const futs = [table.add(data), table.add(data), table.add(data), table.add(data), table.add(data)]
+    await Promise.allSettled(futs)
+
+    table = await conn.openTable(tableName)
+    assert.equal(await table.countRows(), 6)
+  })
+})
+
+describe('LanceDB Mirrored Store Integration test', function () {
+  it('s3://...?mirroredStore=... param is processed correctly', async function () {
+    this.timeout(600000)
+
+    const dir = tmpdir()
+    console.log(dir)
+    const conn = await lancedb.connect({ uri: `s3://lancedb-integtest?mirroredStore=${dir}`, storageOptions: { allowHttp: 'true' } })
+    const data = Array(200).fill({ vector: Array(128).fill(1.0), id: 0 })
+    data.push(...Array(200).fill({ vector: Array(128).fill(1.0), id: 1 }))
+    data.push(...Array(200).fill({ vector: Array(128).fill(1.0), id: 2 }))
+    data.push(...Array(200).fill({ vector: Array(128).fill(1.0), id: 3 }))
+
+    const tableName = uuidv4()
+
+    // try create table and check if it's mirrored
+    const t = await conn.createTable(tableName, data, { writeMode: lancedb.WriteMode.Overwrite })
+
+    const mirroredPath = path.join(dir, `${tableName}.lance`)
+    fs.readdir(mirroredPath, { withFileTypes: true }, (err, files) => {
+      if (err != null) throw err
+      // there should be three dirs
+      assert.equal(files.length, 3)
+      assert.isTrue(files[0].isDirectory())
+      assert.isTrue(files[1].isDirectory())
+
+      fs.readdir(path.join(mirroredPath, '_transactions'), { withFileTypes: true }, (err, files) => {
+        if (err != null) throw err
+        assert.equal(files.length, 1)
+        assert.isTrue(files[0].name.endsWith('.txn'))
+      })
+
+      fs.readdir(path.join(mirroredPath, '_versions'), { withFileTypes: true }, (err, files) => {
+        if (err != null) throw err
+        assert.equal(files.length, 1)
+        assert.isTrue(files[0].name.endsWith('.manifest'))
+      })
+
+      fs.readdir(path.join(mirroredPath, 'data'), { withFileTypes: true }, (err, files) => {
+        if (err != null) throw err
+        assert.equal(files.length, 1)
+        assert.isTrue(files[0].name.endsWith('.lance'))
+      })
+    })
+
+    // try create index and check if it's mirrored
+    await t.createIndex({ column: 'vector', type: 'ivf_pq' })
+
+    fs.readdir(mirroredPath, { withFileTypes: true }, (err, files) => {
+      if (err != null) throw err
+      // there should be four dirs
+      assert.equal(files.length, 4)
+      assert.isTrue(files[0].isDirectory())
+      assert.isTrue(files[1].isDirectory())
+      assert.isTrue(files[2].isDirectory())
+
+      // Two TXs now
+      fs.readdir(path.join(mirroredPath, '_transactions'), { withFileTypes: true }, (err, files) => {
+        if (err != null) throw err
+        assert.equal(files.length, 2)
+        assert.isTrue(files[0].name.endsWith('.txn'))
+        assert.isTrue(files[1].name.endsWith('.txn'))
+      })
+
+      fs.readdir(path.join(mirroredPath, 'data'), { withFileTypes: true }, (err, files) => {
+        if (err != null) throw err
+        assert.equal(files.length, 1)
+        assert.isTrue(files[0].name.endsWith('.lance'))
+      })
+
+      fs.readdir(path.join(mirroredPath, '_indices'), { withFileTypes: true }, (err, files) => {
+        if (err != null) throw err
+        assert.equal(files.length, 1)
+        assert.isTrue(files[0].isDirectory())
+
+        fs.readdir(path.join(mirroredPath, '_indices', files[0].name), { withFileTypes: true }, (err, files) => {
+          if (err != null) throw err
+
+          assert.equal(files.length, 1)
+          assert.isTrue(files[0].isFile())
+          assert.isTrue(files[0].name.endsWith('.idx'))
+        })
+      })
+    })
+
+    // try delete and check if it's mirrored
+    await t.delete('id = 0')
+
+    fs.readdir(mirroredPath, { withFileTypes: true }, (err, files) => {
+      if (err != null) throw err
+      // there should be five dirs
+      assert.equal(files.length, 5)
+      assert.isTrue(files[0].isDirectory())
+      assert.isTrue(files[1].isDirectory())
+      assert.isTrue(files[2].isDirectory())
+      assert.isTrue(files[3].isDirectory())
+      assert.isTrue(files[4].isDirectory())
+
+      // Three TXs now
+      fs.readdir(path.join(mirroredPath, '_transactions'), { withFileTypes: true }, (err, files) => {
+        if (err != null) throw err
+        assert.equal(files.length, 3)
+        assert.isTrue(files[0].name.endsWith('.txn'))
+        assert.isTrue(files[1].name.endsWith('.txn'))
+      })
+
+      fs.readdir(path.join(mirroredPath, 'data'), { withFileTypes: true }, (err, files) => {
+        if (err != null) throw err
+        assert.equal(files.length, 1)
+        assert.isTrue(files[0].name.endsWith('.lance'))
+      })
+
+      fs.readdir(path.join(mirroredPath, '_indices'), { withFileTypes: true }, (err, files) => {
+        if (err != null) throw err
+        assert.equal(files.length, 1)
+        assert.isTrue(files[0].isDirectory())
+
+        fs.readdir(path.join(mirroredPath, '_indices', files[0].name), { withFileTypes: true }, (err, files) => {
+          if (err != null) throw err
+
+          assert.equal(files.length, 1)
+          assert.isTrue(files[0].isFile())
+          assert.isTrue(files[0].name.endsWith('.idx'))
+        })
+      })
+
+      fs.readdir(path.join(mirroredPath, '_deletions'), { withFileTypes: true }, (err, files) => {
+        if (err != null) throw err
+        assert.equal(files.length, 1)
+        assert.isTrue(files[0].name.endsWith('.arrow'))
+      })
+    })
+  })
+})

node/src/middleware.ts

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

node/src/query.ts

@@ -0,0 +1,163 @@
+// Copyright 2023 LanceDB Developers.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+import { Vector, tableFromIPC } from 'apache-arrow'
+import { type EmbeddingFunction } from './embedding/embedding_function'
+import { type MetricType } from '.'
+
+// eslint-disable-next-line @typescript-eslint/no-var-requires
+const { tableSearch } = require('../native.js')
+
+/**
+ * A builder for nearest neighbor queries for LanceDB.
+ */
+export class Query<T = number[]> {
+  private readonly _query?: T
+  private readonly _tbl?: any
+  private _queryVector?: number[]
+  private _limit?: number
+  private _refineFactor?: number
+  private _nprobes: number
+  private _select?: string[]
+  private _filter?: string
+  private _metricType?: MetricType
+  private _prefilter: boolean
+  private _fastSearch: boolean
+  protected readonly _embeddings?: EmbeddingFunction<T>
+
+  constructor (query?: T, tbl?: any, embeddings?: EmbeddingFunction<T>) {
+    this._tbl = tbl
+    this._query = query
+    this._limit = 10
+    this._nprobes = 20
+    this._refineFactor = undefined
+    this._select = undefined
+    this._filter = undefined
+    this._metricType = undefined
+    this._embeddings = embeddings
+    this._prefilter = false
+    this._fastSearch = false
+  }
+
+  /***
+     * Sets the number of results that will be returned
+     * default value is 10
+     * @param value number of results
+     */
+  limit (value: number): Query<T> {
+    this._limit = value
+    return this
+  }
+
+  /**
+     * Refine the results by reading extra elements and re-ranking them in memory.
+     * @param value refine factor to use in this query.
+     */
+  refineFactor (value: number): Query<T> {
+    this._refineFactor = value
+    return this
+  }
+
+  /**
+     * The number of probes used. A higher number makes search more accurate but also slower.
+     * @param value The number of probes used.
+     */
+  nprobes (value: number): Query<T> {
+    this._nprobes = value
+    return this
+  }
+
+  /**
+     * A filter statement to be applied to this query.
+     * @param value A filter in the same format used by a sql WHERE clause.
+     */
+  filter (value: string): Query<T> {
+    this._filter = value
+    return this
+  }
+
+  where = this.filter
+
+  /** Return only the specified columns.
+     *
+     * @param value Only select the specified columns. If not specified, all columns will be returned.
+     */
+  select (value: string[]): Query<T> {
+    this._select = value
+    return this
+  }
+
+  /**
+     * The MetricType used for this Query.
+     * @param value The metric to the. @see MetricType for the different options
+     */
+  metricType (value: MetricType): Query<T> {
+    this._metricType = value
+    return this
+  }
+
+  prefilter (value: boolean): Query<T> {
+    this._prefilter = value
+    return this
+  }
+
+  /**
+   * Skip searching un-indexed data. This can make search faster, but will miss
+   * any data that is not yet indexed.
+   */
+  fastSearch (value: boolean): Query<T> {
+    this._fastSearch = value
+    return this
+  }
+
+  /**
+     * Execute the query and return the results as an Array of Objects
+     */
+  async execute<T = Record<string, unknown>> (): Promise<T[]> {
+    if (this._query !== undefined) {
+      if (this._embeddings !== undefined) {
+        this._queryVector = (await this._embeddings.embed([this._query]))[0]
+      } else {
+        this._queryVector = this._query as number[]
+      }
+    }
+
+    const isElectron = this.isElectron()
+    const buffer = await tableSearch.call(this._tbl, this, isElectron)
+    const data = tableFromIPC(buffer)
+
+    return data.toArray().map((entry: Record<string, unknown>) => {
+      const newObject: Record<string, unknown> = {}
+      Object.keys(entry).forEach((key: string) => {
+        if (entry[key] instanceof Vector) {
+          // toJSON() returns f16 array correctly
+          newObject[key] = (entry[key] as any).toJSON()
+        } else {
+          newObject[key] = entry[key] as any
+        }
+      })
+      return newObject as unknown as T
+    })
+  }
+
+  // See https://github.com/electron/electron/issues/2288
+  private isElectron (): boolean {
+    try {
+      // eslint-disable-next-line no-prototype-builtins
+      return (process?.versions?.hasOwnProperty('electron') || navigator?.userAgent?.toLowerCase()?.includes(' electron'))
+    } catch (e) {
+      return false
+    }
+  }
+}