Bump version: 0.25.3-beta.4 → 0.25.3-beta.5

Support FTS feature parity in SQL to match current Python API
capability.
Add `.to_json()` method to FTS query classes to enable usage with SQL
`fts()` UDTF.
Related: https://github.com/lancedb/blog-lancedb/pull/147

query = MatchQuery("puppy", "text", fuzziness=2)
result = client.execute(f"SELECT * FROM fts('table',
'{query.to_json()}')")

---------

Co-authored-by: Claude <noreply@anthropic.com>

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.21.2-beta.1"
+current_version = "0.22.3-beta.4"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.
@@ -50,11 +50,6 @@ 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}\","
@@ -66,39 +61,8 @@ 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/actions/create-failure-issue/action.yml

@@ -0,0 +1,45 @@
+name: Create Failure Issue
+description: Creates a GitHub issue if any jobs in the workflow failed
+
+inputs:
+  job-results:
+    description: 'JSON string of job results from needs context'
+    required: true
+  workflow-name:
+    description: 'Name of the workflow'
+    required: true
+
+runs:
+  using: composite
+  steps:
+    - name: Check for failures and create issue
+      shell: bash
+      env:
+        JOB_RESULTS: ${{ inputs.job-results }}
+        WORKFLOW_NAME: ${{ inputs.workflow-name }}
+        RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
+        GH_TOKEN: ${{ github.token }}
+      run: |
+        # Check if any job failed
+        if echo "$JOB_RESULTS" | jq -e 'to_entries | any(.value.result == "failure")' > /dev/null; then
+          echo "Detected job failures, creating issue..."
+
+          # Extract failed job names
+          FAILED_JOBS=$(echo "$JOB_RESULTS" | jq -r 'to_entries | map(select(.value.result == "failure")) | map(.key) | join(", ")')
+
+          # Create issue with workflow name, failed jobs, and run URL
+          gh issue create \
+            --title "$WORKFLOW_NAME Failed ($FAILED_JOBS)" \
+            --body "The workflow **$WORKFLOW_NAME** failed during execution.
+
+        **Failed jobs:** $FAILED_JOBS
+
+        **Run URL:** $RUN_URL
+
+        Please investigate the failed jobs and address any issues." \
+            --label "ci"
+
+          echo "Issue created successfully"
+        else
+          echo "No job failures detected, skipping issue creation"
+        fi

.github/workflows/cargo-publish.yml

@@ -38,3 +38,17 @@ jobs:
       - name: Publish the package
         run: |
           cargo publish -p lancedb --all-features --token ${{ steps.auth.outputs.token }}
+  report-failure:
+    name: Report Workflow Failure
+    runs-on: ubuntu-latest
+    needs: [build]
+    if: always() && (github.event_name == 'release' || github.event_name == 'workflow_dispatch')
+    permissions:
+      contents: read
+      issues: write
+    steps:
+      - uses: actions/checkout@v4
+      - uses: ./.github/actions/create-failure-issue
+        with:
+          job-results: ${{ toJSON(needs) }}
+          workflow-name: ${{ github.workflow }}

.github/workflows/codex-update-lance-dependency.yml

@@ -0,0 +1,107 @@
+name: Codex Update Lance Dependency
+
+on:
+  workflow_call:
+    inputs:
+      tag:
+        description: "Tag name from Lance"
+        required: true
+        type: string
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: "Tag name from Lance"
+        required: true
+        type: string
+
+permissions:
+  contents: write
+  pull-requests: write
+  actions: read
+
+jobs:
+  update:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Show inputs
+        run: |
+          echo "tag = ${{ inputs.tag }}"
+
+      - name: Checkout Repo LanceDB
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: true
+
+      - name: Set up Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 20
+
+      - name: Install Codex CLI
+        run: npm install -g @openai/codex
+
+      - name: Install Rust toolchain
+        uses: dtolnay/rust-toolchain@stable
+        with:
+          toolchain: stable
+          components: clippy, rustfmt
+
+      - name: Install system dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y protobuf-compiler libssl-dev
+
+      - name: Install cargo-info
+        run: cargo install cargo-info
+
+      - name: Install Python dependencies
+        run: python3 -m pip install --upgrade pip packaging
+
+      - name: Configure git user
+        run: |
+          git config user.name "lancedb automation"
+          git config user.email "robot@lancedb.com"
+
+      - name: Configure Codex authentication
+        env:
+          CODEX_TOKEN_B64: ${{ secrets.CODEX_TOKEN }}
+        run: |
+          if [ -z "${CODEX_TOKEN_B64}" ]; then
+            echo "Repository secret CODEX_TOKEN is not defined; skipping Codex execution."
+            exit 1
+          fi
+          mkdir -p ~/.codex
+          echo "${CODEX_TOKEN_B64}" | base64 --decode > ~/.codex/auth.json
+
+      - name: Run Codex to update Lance dependency
+        env:
+          TAG: ${{ inputs.tag }}
+          GITHUB_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+        run: |
+          set -euo pipefail
+          VERSION="${TAG#refs/tags/}"
+          VERSION="${VERSION#v}"
+          BRANCH_NAME="codex/update-lance-${VERSION//[^a-zA-Z0-9]/-}"
+          cat <<EOF >/tmp/codex-prompt.txt
+          You are running inside the lancedb repository on a GitHub Actions runner. Update the Lance dependency to version ${VERSION} and prepare a pull request for maintainers to review.
+
+          Follow these steps exactly:
+          1. Use script "ci/set_lance_version.py" to update Lance dependencies. The script already refreshes Cargo metadata, so allow it to finish even if it takes time.
+          2. Run "cargo clippy --workspace --tests --all-features -- -D warnings". If diagnostics appear, fix them yourself and rerun clippy until it exits cleanly. Do not skip any warnings.
+          3. After clippy succeeds, run "cargo fmt --all" to format the workspace.
+          4. Ensure the repository is clean except for intentional changes. Inspect "git status --short" and "git diff" to confirm the dependency update and any required fixes.
+          5. Create and switch to a new branch named "${BRANCH_NAME}" (replace any duplicated hyphens if necessary).
+          6. Stage all relevant files with "git add -A". Commit using the message "chore: update lance dependency to v${VERSION}".
+          7. Push the branch to origin. If the branch already exists, force-push your changes.
+          8. env "GH_TOKEN" is available, use "gh" tools for github related operations like creating pull request.
+          9. Create a pull request targeting "main" with title "chore: update lance dependency to v${VERSION}". In the body, summarize the dependency bump, clippy/fmt verification, and link the triggering tag (${TAG}).
+          10. After creating the PR, display the PR URL, "git status --short", and a concise summary of the commands run and their results.
+
+          Constraints:
+          - Use bash commands; avoid modifying GitHub workflow files other than through the scripted task above.
+          - Do not merge the PR.
+          - If any command fails, diagnose and fix the issue instead of aborting.
+          EOF
+          codex --config shell_environment_policy.ignore_default_excludes=true exec --dangerously-bypass-approvals-and-sandbox "$(cat /tmp/codex-prompt.txt)"

.github/workflows/docs.yml

@@ -56,22 +56,12 @@ jobs:
         with:
           node-version: 20
           cache: 'npm'
-          cache-dependency-path: node/package-lock.json
+          cache-dependency-path: docs/package-lock.json
       - name: Install node dependencies
-        working-directory: node
+        working-directory: nodejs
         run: |
           sudo apt update
           sudo apt install -y protobuf-compiler libssl-dev
-      - name: Build node
-        working-directory: node
-        run: |
-          npm ci
-          npm run build
-          npm run tsc
-      - name: Create markdown files
-        working-directory: node
-        run: |
-          npx typedoc --plugin typedoc-plugin-markdown --out ../docs/src/javascript src/index.ts
       - name: Build docs
         working-directory: docs
         run: |

.github/workflows/docs_test.yml

@@ -24,7 +24,8 @@ env:
 jobs:
   test-python:
     name: Test doc python code
-    runs-on: ubuntu-24.04
+    runs-on: warp-ubuntu-2204-x64-8x
+    timeout-minutes: 60
     steps:
     - name: Checkout
       uses: actions/checkout@v4
@@ -58,51 +59,3 @@ jobs:
       run: |
         cd docs/test/python
         for d in *; do cd "$d"; echo "$d".py; python "$d".py; cd ..; done
-  test-node:
-    name: Test doc nodejs code
-    runs-on: ubuntu-24.04
-    timeout-minutes: 60
-    strategy:
-      fail-fast: false
-    steps:
-    - name: Checkout
-      uses: actions/checkout@v4
-      with:
-        fetch-depth: 0
-        lfs: true
-    - name: Print CPU capabilities
-      run: cat /proc/cpuinfo
-    - name: Set up Node
-      uses: actions/setup-node@v4
-      with:
-        node-version: 20
-    - name: Install protobuf
-      run: |
-        sudo apt update
-        sudo apt install -y protobuf-compiler
-    - name: Install dependecies needed for ubuntu
-      run: |
-        sudo apt install -y libssl-dev
-        rustup update && rustup default
-    - name: Rust cache
-      uses: swatinem/rust-cache@v2
-    - name: Install node dependencies
-      run: |
-        sudo swapoff -a
-        sudo fallocate -l 8G /swapfile
-        sudo chmod 600 /swapfile
-        sudo mkswap /swapfile
-        sudo swapon /swapfile
-        sudo swapon --show
-        cd node
-        npm ci
-        npm run build-release
-        cd ../docs
-        npm install
-    - name: Test
-      env:
-        LANCEDB_URI: ${{ secrets.LANCEDB_URI }}
-        LANCEDB_DEV_API_KEY: ${{ secrets.LANCEDB_DEV_API_KEY }}
-      run: |
-        cd docs
-        npm t

.github/workflows/java-publish.yml

@@ -43,7 +43,6 @@ jobs:
       - uses: Swatinem/rust-cache@v2
       - uses: actions-rust-lang/setup-rust-toolchain@v1
         with:
-          toolchain: "1.81.0"
           cache-workspaces: "./java/core/lancedb-jni"
           # Disable full debug symbol generation to speed up CI build and keep memory down
           # "1" means line tables only, which is useful for panic tracebacks.
@@ -112,3 +111,17 @@ jobs:
         env:
           SONATYPE_USER: ${{ secrets.SONATYPE_USER }}
           SONATYPE_TOKEN: ${{ secrets.SONATYPE_TOKEN }}
+  report-failure:
+    name: Report Workflow Failure
+    runs-on: ubuntu-latest
+    needs: [linux-arm64, linux-x86, macos-arm64]
+    if: always() && (github.event_name == 'release' || github.event_name == 'workflow_dispatch')
+    permissions:
+      contents: read
+      issues: write
+    steps:
+      - uses: actions/checkout@v4
+      - uses: ./.github/actions/create-failure-issue
+        with:
+          job-results: ${{ toJSON(needs) }}
+          workflow-name: ${{ github.workflow }}

.github/workflows/node.yml

@@ -1,147 +0,0 @@
-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

@@ -6,6 +6,7 @@ on:
       - main
   pull_request:
     paths:
+      - Cargo.toml
       - nodejs/**
       - .github/workflows/nodejs.yml
       - docker-compose.yml
@@ -79,7 +80,7 @@ jobs:
       with:
         node-version: ${{ matrix.node-version }}
         cache: 'npm'
-        cache-dependency-path: node/package-lock.json
+        cache-dependency-path: nodejs/package-lock.json
     - uses: Swatinem/rust-cache@v2
     - name: Install dependencies
       run: |
@@ -116,7 +117,7 @@ jobs:
         set -e
         npm ci
         npm run docs
-        if ! git diff --exit-code -- . ':(exclude)Cargo.lock'; then
+        if ! git diff --exit-code -- ../ ':(exclude)Cargo.lock'; then
           echo "Docs need to be updated"
           echo "Run 'npm run docs', fix any warnings, and commit the changes."
           exit 1
@@ -137,7 +138,7 @@ jobs:
       with:
         node-version: 20
         cache: 'npm'
-        cache-dependency-path: node/package-lock.json
+        cache-dependency-path: nodejs/package-lock.json
     - uses: Swatinem/rust-cache@v2
     - name: Install dependencies
       run: |

.github/workflows/npm-publish.yml

@@ -365,200 +365,17 @@ 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]
+  report-failure:
+    name: Report Workflow Failure
     runs-on: ubuntu-latest
+    needs: [build-lancedb, test-lancedb, publish]
+    if: always() && (github.event_name == 'release' || github.event_name == 'workflow_dispatch')
     permissions:
-      contents: write
-    # Only runs on tags that matches the make-release action
-    if: startsWith(github.ref, 'refs/tags/v')
+      contents: read
+      issues: write
     steps:
-      - uses: actions/download-artifact@v4
+      - uses: actions/checkout@v4
+      - uses: ./.github/actions/create-failure-issue
         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: Checkout
-        uses: actions/checkout@v4
-        with:
-          ref: main
-      - name: Update package-lock.json
-        run: |
-          git config user.name 'Lance Release'
-          git config user.email 'lance-dev@lancedb.com'
-          bash ci/update_lockfiles.sh
-      - name: Push new commit
-        uses: ad-m/github-push-action@master
-        with:
-          github_token: ${{ secrets.LANCEDB_RELEASE_TOKEN }}
-          branch: main
-      - 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 }}
+          job-results: ${{ toJSON(needs) }}
+          workflow-name: ${{ github.workflow }}

.github/workflows/pypi-publish.yml

@@ -56,7 +56,7 @@ jobs:
           pypi_token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
           fury_token: ${{ secrets.FURY_TOKEN }}
   mac:
-    timeout-minutes: 60
+    timeout-minutes: 90
     runs-on: ${{ matrix.config.runner }}
     strategy:
       matrix:
@@ -64,7 +64,7 @@ jobs:
           - target: x86_64-apple-darwin
             runner: macos-13
           - target: aarch64-apple-darwin
-            runner: macos-14
+            runner: warp-macos-14-arm64-6x
     env:
       MACOSX_DEPLOYMENT_TARGET: 10.15
     steps:
@@ -173,3 +173,17 @@ jobs:
           generate_release_notes: false
           name: Python LanceDB v${{ steps.extract_version.outputs.version }}
           body: ${{ steps.python_release_notes.outputs.changelog }}
+  report-failure:
+    name: Report Workflow Failure
+    runs-on: ubuntu-latest
+    needs: [linux, mac, windows]
+    permissions:
+      contents: read
+      issues: write
+    if: always() && (github.event_name == 'release' || github.event_name == 'workflow_dispatch')
+    steps:
+      - uses: actions/checkout@v4
+      - uses: ./.github/actions/create-failure-issue
+        with:
+          job-results: ${{ toJSON(needs) }}
+          workflow-name: ${{ github.workflow }}

.github/workflows/python.yml

@@ -6,6 +6,7 @@ on:
       - main
   pull_request:
     paths:
+      - Cargo.toml
       - python/**
       - .github/workflows/python.yml
 

.github/workflows/rust.yml

@@ -96,6 +96,7 @@ jobs:
       # Need up-to-date compilers for kernels
       CC: clang-18
       CXX: clang++-18
+      GH_TOKEN: ${{ secrets.SOPHON_READ_TOKEN }}
     steps:
       - uses: actions/checkout@v4
         with:
@@ -117,15 +118,17 @@ jobs:
           sudo chmod 600 /swapfile
           sudo mkswap /swapfile
           sudo swapon /swapfile
-      - name: Start S3 integration test environment
-        working-directory: .
-        run: docker compose up --detach --wait
       - name: Build
         run: cargo build --all-features --tests --locked --examples
-      - name: Run tests
-        run: cargo test --all-features --locked
+      - name: Run feature tests
+        run: make -C ./lancedb feature-tests
       - name: Run examples
         run: cargo run --example simple --locked
+      - name: Run remote tests
+        # Running this requires access to secrets, so skip if this is
+        # a PR from a fork.
+        if: github.event_name != 'pull_request' || !github.event.pull_request.head.repo.fork
+        run: make -C ./lancedb remote-tests
 
   macos:
     timeout-minutes: 30

.github/workflows/trigger-vectordb-recipes.yml

@@ -1,26 +0,0 @@
-name: Trigger vectordb-recipers workflow
-on:
-  push:
-    branches: [ main ]
-  pull_request:
-    paths:
-      - .github/workflows/trigger-vectordb-recipes.yml
-  workflow_dispatch:
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Trigger vectordb-recipes workflow
-        uses: actions/github-script@v6
-        with:
-          github-token: ${{ secrets.VECTORDB_RECIPES_ACTION_TOKEN }}
-          script: |
-            const result = await github.rest.actions.createWorkflowDispatch({
-                owner: 'lancedb',
-                repo: 'vectordb-recipes',
-                workflow_id: 'examples-test.yml',
-                ref: 'main'
-            });
-            console.log(result);

.gitignore

@@ -31,9 +31,6 @@ python/dist
 *.node
 **/node_modules
 **/.DS_Store
-node/dist
-node/examples/**/package-lock.json
-node/examples/**/dist
 nodejs/lancedb/native*
 dist
 

AGENTS.md

@@ -0,0 +1,101 @@
+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
+
+Common commands:
+
+* Check for compiler errors: `cargo check --quiet --features remote --tests --examples`
+* Run tests: `cargo test --quiet --features remote --tests`
+* Run specific test: `cargo test --quiet --features remote -p <package_name> --test <test_name>`
+* Lint: `cargo clippy --quiet --features remote --tests --examples`
+* Format: `cargo fmt --all`
+
+Before committing changes, run formatting.
+
+## Coding tips
+
+* When writing Rust doctests for things that require a connection or table reference,
+  write them as a function instead of a fully executable test. This allows type checking
+  to run but avoids needing a full test environment. For example:
+    ```rust
+    /// ```
+    /// use lance_index::scalar::FullTextSearchQuery;
+    /// use lancedb::query::{QueryBase, ExecutableQuery};
+    ///
+    /// # use lancedb::Table;
+    /// # async fn query(table: &Table) -> Result<(), Box<dyn std::error::Error>> {
+    /// let results = table.query()
+    ///     .full_text_search(FullTextSearchQuery::new("hello world".into()))
+    ///     .execute()
+    ///     .await?;
+    /// # Ok(())
+    /// # }
+    /// ```
+    ```
+
+## Example plan: adding a new method on Table
+
+Adding a new method involves first adding it to the Rust core, then exposing it
+in the Python and TypeScript bindings. There are both local and remote tables.
+Remote tables are implemented via a HTTP API and require the `remote` cargo
+feature flag to be enabled. Python has both sync and async methods.
+
+Rust core changes:
+
+1. Add method on `Table` struct in `rust/lancedb/src/table.rs` (calls `BaseTable` trait).
+2. Add method to `BaseTable` trait in `rust/lancedb/src/table.rs`.
+3. Implement new trait method on `NativeTable` in `rust/lancedb/src/table.rs`.
+    * Test with unit test in `rust/lancedb/src/table.rs`.
+4. Implement new trait method on `RemoteTable` in `rust/lancedb/src/remote/table.rs`.
+    * Test with unit test in `rust/lancedb/src/remote/table.rs` against mocked endpoint.
+
+Python bindings changes:
+
+1. Add PyO3 method binding in `python/src/table.rs`. Run `make develop` to compile bindings.
+2. Add types for PyO3 method in `python/python/lancedb/_lancedb.pyi`.
+3. Add method to `AsyncTable` class in `python/python/lancedb/table.py`.
+4. Add abstract method to `Table` abstract base class in `python/python/lancedb/table.py`.
+5. Add concrete sync method to `LanceTable` class in `python/python/lancedb/table.py`.
+    * Should use `LOOP.run()` to call the corresponding `AsyncTable` method.
+6. Add concrete sync method to `RemoteTable` class in `python/python/lancedb/remote/table.py`.
+7. Add unit test in `python/tests/test_table.py`.
+
+TypeScript bindings changes:
+
+1. Add napi-rs method binding on `Table` in `nodejs/src/table.rs`.
+2. Run `npm run build` to generate TypeScript definitions.
+3. Add typescript method on abstract class `Table` in `nodejs/src/table.ts`.
+4. Add concrete method on `LocalTable` class in `nodejs/src/native_table.ts`.
+    * Note: despite the name, this class is also used for remote tables.
+5. Add test in `nodejs/__test__/table.test.ts`.
+6. Run `npm run docs` to generate TypeScript documentation.
+
+## Review Guidelines
+
+Please consider the following when reviewing code contributions.
+
+### Rust API design
+* Design public APIs so they can be evolved easily in the future without breaking
+  changes. Often this means using builder patterns or options structs instead of
+  long argument lists.
+* For public APIs, prefer inputs that use `Into<T>` or `AsRef<T>` traits to allow
+  more flexible inputs. For example, use `name: Into<String>` instead of `name: String`,
+  so we don't have to write `func("my_string".to_string())`.
+
+### Testing
+* Ensure all new public APIs have documentation and examples.
+* Ensure that all bugfixes and features have corresponding tests. **We do not merge
+  code without tests.**
+
+### Documentation
+* New features must include updates to the rust documentation comments. Link to
+  relevant structs and methods to increase the value of documentation.

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.

CLAUDE.md

@@ -0,0 +1 @@
+AGENTS.md

Cargo.toml

@@ -1,11 +1,5 @@
 [workspace]
-members = [
-    "rust/ffi/node",
-    "rust/lancedb",
-    "nodejs",
-    "python",
-    "java/core/lancedb-jni",
-]
+members = ["rust/lancedb", "nodejs", "python", "java/core/lancedb-jni"]
 # Python package needs to be built by maturin.
 exclude = ["python"]
 resolver = "2"
@@ -21,30 +15,37 @@ categories = ["database-implementations"]
 rust-version = "1.78.0"
 
 [workspace.dependencies]
-lance = { "version" = "=0.32.0", "features" = ["dynamodb"] }
-lance-io = "=0.32.0"
-lance-index = "=0.32.0"
-lance-linalg = "=0.32.0"
-lance-table = "=0.32.0"
-lance-testing = "=0.32.0"
-lance-datafusion = "=0.32.0"
-lance-encoding = "=0.32.0"
+lance = { "version" = "=0.38.3", default-features = false, "tag" = "v0.38.3", "git" = "https://github.com/lancedb/lance.git" }
+lance-core = { "version" = "=0.38.3", "tag" = "v0.38.3", "git" = "https://github.com/lancedb/lance.git" }
+lance-datagen = { "version" = "=0.38.3", "tag" = "v0.38.3", "git" = "https://github.com/lancedb/lance.git" }
+lance-file = { "version" = "=0.38.3", "tag" = "v0.38.3", "git" = "https://github.com/lancedb/lance.git" }
+lance-io = { "version" = "=0.38.3", default-features = false, "tag" = "v0.38.3", "git" = "https://github.com/lancedb/lance.git" }
+lance-index = { "version" = "=0.38.3", "tag" = "v0.38.3", "git" = "https://github.com/lancedb/lance.git" }
+lance-linalg = { "version" = "=0.38.3", "tag" = "v0.38.3", "git" = "https://github.com/lancedb/lance.git" }
+lance-namespace = { "version" = "=0.38.3", "tag" = "v0.38.3", "git" = "https://github.com/lancedb/lance.git" }
+lance-namespace-impls = { "version" = "=0.38.3", "features" = ["dir-aws", "dir-gcp", "dir-azure", "dir-oss", "rest"], "tag" = "v0.38.3", "git" = "https://github.com/lancedb/lance.git" }
+lance-table = { "version" = "=0.38.3", "tag" = "v0.38.3", "git" = "https://github.com/lancedb/lance.git" }
+lance-testing = { "version" = "=0.38.3", "tag" = "v0.38.3", "git" = "https://github.com/lancedb/lance.git" }
+lance-datafusion = { "version" = "=0.38.3", "tag" = "v0.38.3", "git" = "https://github.com/lancedb/lance.git" }
+lance-encoding = { "version" = "=0.38.3", "tag" = "v0.38.3", "git" = "https://github.com/lancedb/lance.git" }
+lance-arrow = { "version" = "=0.38.3", "tag" = "v0.38.3", "git" = "https://github.com/lancedb/lance.git" }
+ahash = "0.8"
 # 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 = "56.2", optional = false }
+arrow-array = "56.2"
+arrow-data = "56.2"
+arrow-ipc = "56.2"
+arrow-ord = "56.2"
+arrow-schema = "56.2"
+arrow-select = "56.2"
+arrow-cast = "56.2"
 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 = "50.1", default-features = false }
+datafusion-catalog = "50.1"
+datafusion-common = { version = "50.1", default-features = false }
+datafusion-execution = "50.1"
+datafusion-expr = "50.1"
+datafusion-physical-plan = "50.1"
 env_logger = "0.11"
 half = { "version" = "2.6.0", default-features = false, features = [
     "num-traits",
@@ -54,19 +55,14 @@ log = "0.4"
 moka = { version = "0.12", features = ["future"] }
 object_store = "0.12.0"
 pin-project = "1.0.7"
+rand = "0.9"
 snafu = "0.8"
 url = "2"
 num-traits = "0.2"
-rand = "0.9"
 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"
-# 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"
+crunchy = "0.2.4"
+chrono = "0.4"
 # Workaround for: https://github.com/Lokathor/bytemuck/issues/306
 bytemuck_derive = ">=1.8.1, <1.9.0"

ci/build_linux_artifacts.sh

@@ -1,22 +0,0 @@
-#!/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

@@ -1,34 +0,0 @@
-# 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

@@ -1,42 +0,0 @@
-# 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

@@ -1,42 +0,0 @@
-# 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/create_lancedb_test_connection.sh

@@ -0,0 +1,4 @@
+#!/usr/bin/env bash
+
+export RUST_LOG=info
+exec ./lancedb server --port 0 --sql-port 0  --data-dir "${1}"

ci/manylinux_node/Dockerfile

@@ -1,27 +0,0 @@
-# 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

@@ -1,13 +0,0 @@
-#!/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

@@ -1,15 +0,0 @@
-#!/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

@@ -1,21 +0,0 @@
-#!/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/run_with_docker_compose.sh

@@ -0,0 +1,18 @@
+#!/usr/bin/env bash
+
+#
+# A script for running the given command together with a docker compose environment.
+#
+
+# Bring down the docker setup once the command is done running.
+tear_down() {
+    docker compose -p fixture down
+}
+trap tear_down EXIT
+
+set +xe
+
+# Clean up any existing docker setup and bring up a new one.
+docker compose -p fixture up --detach --wait || exit 1
+
+"${@}"

ci/run_with_test_connection.sh

@@ -0,0 +1,68 @@
+#!/usr/bin/env bash
+
+#
+# A script for running the given command together with the lancedb cli.
+#
+
+die() {
+    echo $?
+    exit 1
+}
+
+check_command_exists() {
+    command="${1}"
+    which ${command} &> /dev/null || \
+        die "Unable to locate command: ${command}. Did you install it?"
+}
+
+if [[ ! -e ./lancedb ]]; then
+    if [[ -v SOPHON_READ_TOKEN ]]; then
+        INPUT="lancedb-linux-x64"
+        gh release \
+            --repo lancedb/lancedb \
+            download ci-support-binaries \
+            --pattern "${INPUT}" \
+            || die "failed to fetch cli."
+        check_command_exists openssl
+        openssl enc -aes-256-cbc \
+            -d -pbkdf2 \
+            -pass "env:SOPHON_READ_TOKEN" \
+            -in "${INPUT}" \
+            -out ./lancedb-linux-x64.tar.gz \
+            || die "openssl failed"
+        TARGET="${INPUT}.tar.gz"
+    else
+        ARCH="x64"
+        if [[ $OSTYPE == 'darwin'* ]]; then
+            UNAME=$(uname -m)
+            if [[ $UNAME == 'arm64' ]]; then
+                ARCH='arm64'
+            fi
+            OSTYPE="macos"
+        elif [[ $OSTYPE == 'linux'* ]]; then
+            if [[ $UNAME == 'aarch64' ]]; then
+                ARCH='arm64'
+            fi
+            OSTYPE="linux"
+        else
+            die "unknown OSTYPE: $OSTYPE"
+        fi
+
+        check_command_exists gh
+        TARGET="lancedb-${OSTYPE}-${ARCH}.tar.gz"
+        gh release \
+            --repo lancedb/sophon \
+            download lancedb-cli-v0.0.3 \
+            --pattern "${TARGET}" \
+            || die "failed to fetch cli."
+    fi
+
+    check_command_exists tar
+    tar xvf "${TARGET}" || die "tar failed."
+    [[ -e ./lancedb ]] || die "failed to extract lancedb."
+fi
+
+SCRIPT_DIR=$(dirname "$(readlink -f "$0")")
+export CREATE_LANCEDB_TEST_CONNECTION_SCRIPT="${SCRIPT_DIR}/create_lancedb_test_connection.sh"
+
+"${@}"

ci/set_lance_version.py

@@ -1,4 +1,5 @@
 import argparse
+import re
 import sys
 import json
 
@@ -18,8 +19,12 @@ def run_command(command: str) -> str:
 
 def get_latest_stable_version() -> str:
     version_line = run_command("cargo info lance | grep '^version:'")
-    version = version_line.split(" ")[1].strip()
-    return version
+    # Example output: "version: 0.35.0 (latest 0.37.0)"
+    match = re.search(r'\(latest ([0-9.]+)\)', version_line)
+    if match:
+        return match.group(1)
+    # Fallback: use the first version after 'version:'
+    return version_line.split("version:")[1].split()[0].strip()
 
 
 def get_latest_preview_version() -> str:
@@ -54,6 +59,52 @@ def extract_features(line: str) -> list:
     return []
 
 
+def extract_default_features(line: str) -> bool:
+    """
+    Checks if default-features = false is present in a line in Cargo.toml.
+    Example: 'lance = { "version" = "=0.29.0", default-features = false, "features" = ["dynamodb"] }'
+    Returns: True if default-features = false is present, False otherwise
+    """
+    import re
+
+    match = re.search(r'default-features\s*=\s*false', line)
+    return match is not None
+
+
+def dict_to_toml_line(package_name: str, config: dict) -> str:
+    """
+    Converts a configuration dictionary to a TOML dependency line.
+    Dictionary insertion order is preserved (Python 3.7+), so the caller
+    controls the order of fields in the output.
+
+    Args:
+        package_name: The name of the package (e.g., "lance", "lance-io")
+        config: Dictionary with keys like "version", "path", "git", "tag", "features", "default-features"
+                The order of keys in this dict determines the order in the output.
+
+    Returns:
+        A properly formatted TOML line with a trailing newline
+    """
+    # If only version is specified, use simple format
+    if len(config) == 1 and "version" in config:
+        return f'{package_name} = "{config["version"]}"\n'
+
+    # Otherwise, use inline table format
+    parts = []
+    for key, value in config.items():
+        if key == "default-features" and not value:
+            parts.append("default-features = false")
+        elif key == "features":
+            parts.append(f'"features" = {json.dumps(value)}')
+        elif isinstance(value, str):
+            parts.append(f'"{key}" = "{value}"')
+        else:
+            # This shouldn't happen with our current usage
+            parts.append(f'"{key}" = {json.dumps(value)}')
+
+    return f'{package_name} = {{ {", ".join(parts)} }}\n'
+
+
 def update_cargo_toml(line_updater):
     """
     Updates the Cargo.toml file by applying the line_updater function to each line.
@@ -67,20 +118,27 @@ def update_cargo_toml(line_updater):
     is_parsing_lance_line = False
     for line in lines:
         if line.startswith("lance"):
-            # Update the line using the provided function
-            if line.strip().endswith("}"):
+            # Check if this is a single-line or multi-line entry
+            # Single-line entries either:
+            # 1. End with } (complete inline table)
+            # 2. End with " (simple version string)
+            # Multi-line entries start with { but don't end with }
+            if line.strip().endswith("}") or line.strip().endswith('"'):
+                # Single-line entry - process immediately
                 new_lines.append(line_updater(line))
-            else:
+            elif "{" in line and not line.strip().endswith("}"):
+                # Multi-line entry - start accumulating
                 lance_line = line
                 is_parsing_lance_line = True
+            else:
+                # Single-line entry without quotes or braces (shouldn't happen but handle it)
+                new_lines.append(line_updater(line))
         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)
@@ -92,18 +150,25 @@ def update_cargo_toml(line_updater):
 def set_stable_version(version: str):
     """
     Sets lines to
-    lance = { "version" = "=0.29.0", "features" = ["dynamodb"] }
-    lance-io = "=0.29.0"
+    lance = { "version" = "=0.29.0", default-features = false, "features" = ["dynamodb"] }
+    lance-io = { "version" = "=0.29.0", default-features = false }
     ...
     """
 
     def line_updater(line: str) -> str:
         package_name = line.split("=", maxsplit=1)[0].strip()
+
+        # Build config in desired order: version, default-features, features
+        config = {"version": f"={version}"}
+
+        if extract_default_features(line):
+            config["default-features"] = False
+
         features = extract_features(line)
         if features:
-            return f'{package_name} = {{ "version" = "={version}", "features" = {json.dumps(features)} }}\n'
-        else:
-            return f'{package_name} = "={version}"\n'
+            config["features"] = features
+
+        return dict_to_toml_line(package_name, config)
 
     update_cargo_toml(line_updater)
 
@@ -111,19 +176,27 @@ def set_stable_version(version: str):
 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" }
+    lance = { "version" = "=0.29.0", default-features = false, "features" = ["dynamodb"], "tag" = "v0.29.0-beta.2", "git" = "https://github.com/lancedb/lance.git" }
+    lance-io = { "version" = "=0.29.0", default-features = false, "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()
+        # Build config in desired order: version, default-features, features, tag, git
+        config = {"version": f"={version}"}
+
+        if extract_default_features(line):
+            config["default-features"] = False
+
         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'
+            config["features"] = features
+
+        config["tag"] = f"v{version}"
+        config["git"] = "https://github.com/lancedb/lance.git"
+
+        return dict_to_toml_line(package_name, config)
 
     update_cargo_toml(line_updater)
 
@@ -131,18 +204,25 @@ def set_preview_version(version: str):
 def set_local_version():
     """
     Sets lines to
-    lance = { path = "../lance/rust/lance", features = ["dynamodb"] }
-    lance-io = { path = "../lance/rust/lance-io" }
+    lance = { "path" = "../lance/rust/lance", default-features = false, "features" = ["dynamodb"] }
+    lance-io = { "path" = "../lance/rust/lance-io", default-features = false }
     ...
     """
 
     def line_updater(line: str) -> str:
         package_name = line.split("=", maxsplit=1)[0].strip()
+
+        # Build config in desired order: path, default-features, features
+        config = {"path": f"../lance/rust/{package_name}"}
+
+        if extract_default_features(line):
+            config["default-features"] = False
+
         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'
+            config["features"] = features
+
+        return dict_to_toml_line(package_name, config)
 
     update_cargo_toml(line_updater)
 

ci/update_lockfiles.sh

@@ -15,16 +15,13 @@ 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 add Cargo.lock nodejs/package-lock.json
   git commit --amend --no-edit
 else
-  git add Cargo.lock nodejs/package-lock.json node/package-lock.json
+  git add Cargo.lock nodejs/package-lock.json
   git commit -m "Update lockfiles"
 fi

docs/mkdocs.yml

@@ -70,6 +70,23 @@ plugins:
   - mkdocs-jupyter
   - render_swagger:
       allow_arbitrary_locations: true
+  - redirects:
+      redirect_maps:
+        # Redirect the home page and other top-level markdown files. This enables maximum SEO benefit
+        # other sub-pages are handled by the ingected js in overrides/partials/header.html
+        'index.md': 'https://lancedb.com/docs/'
+        'guides/tables.md': 'https://lancedb.com/docs/tables/'
+        'ann_indexes.md': 'https://lancedb.com/docs/indexing/'
+        'basic.md': 'https://lancedb.com/docs/quickstart/'
+        'faq.md': 'https://lancedb.com/docs/faq/'
+        'embeddings/understanding_embeddings.md': 'https://lancedb.com/docs/embedding/'
+        'integrations.md': 'https://lancedb.com/docs/integrations/'
+        'examples.md': 'https://lancedb.com/docs/tutorials/'
+        'concepts/vector_search.md': 'https://lancedb.com/docs/search/vector-search/'
+        'troubleshooting.md': 'https://lancedb.com/docs/troubleshooting/'
+        'guides/storage.md': 'https://lancedb.com/docs/storage/integrations'
+
+
 
 markdown_extensions:
   - admonition

docs/overrides/partials/header.html

@@ -19,7 +19,13 @@
   FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
   IN THE SOFTWARE.
 -->
-
+<div id="deprecation-banner" style="background-color: #f8d7da; color: #721c24; padding: 1em; text-align: center;">                                                           
+    <p style="margin: 0; font-size: 1.1em;">                                                                                                           
+        <strong>This documentation site is deprecated.</strong>                                                                           
+        Please visit our new documentation site at <a href="https://lancedb.com/docs" style="color: #721c24; text-decoration: underline;">
+          lancedb.com/docs</a> for the latest information.                                                                                        
+    </p>                                                                                                                                               
+  </div>  
 {% set class = "md-header" %}
 {% if "navigation.tabs.sticky" in features %}
   {% set class = class ~ " md-header--shadow md-header--lifted" %}
@@ -150,9 +156,9 @@
 
     <div style="margin-left: 10px; margin-right: 5px;">
         <a href="https://discord.com/invite/zMM32dvNtd" target="_blank" rel="noopener noreferrer">
-            <svg fill="#FFFFFF" xmlns="http://www.w3.org/2000/svg"  viewBox="0 0 50 50" width="25px" height="25px"><path d="M 41.625 10.769531 C 37.644531 7.566406 31.347656 7.023438 31.078125 7.003906 C 30.660156 6.96875 30.261719 7.203125 30.089844 7.589844 C 30.074219 7.613281 29.9375 7.929688 29.785156 8.421875 C 32.417969 8.867188 35.652344 9.761719 38.578125 11.578125 C 39.046875 11.867188 39.191406 12.484375 38.902344 12.953125 C 38.710938 13.261719 38.386719 13.429688 38.050781 13.429688 C 37.871094 13.429688 37.6875 13.378906 37.523438 13.277344 C 32.492188 10.15625 26.210938 10 25 10 C 23.789063 10 17.503906 10.15625 12.476563 13.277344 C 12.007813 13.570313 11.390625 13.425781 11.101563 12.957031 C 10.808594 12.484375 10.953125 11.871094 11.421875 11.578125 C 14.347656 9.765625 17.582031 8.867188 20.214844 8.425781 C 20.0625 7.929688 19.925781 7.617188 19.914063 7.589844 C 19.738281 7.203125 19.34375 6.960938 18.921875 7.003906 C 18.652344 7.023438 12.355469 7.566406 8.320313 10.8125 C 6.214844 12.761719 2 24.152344 2 34 C 2 34.175781 2.046875 34.34375 2.132813 34.496094 C 5.039063 39.605469 12.972656 40.941406 14.78125 41 C 14.789063 41 14.800781 41 14.8125 41 C 15.132813 41 15.433594 40.847656 15.621094 40.589844 L 17.449219 38.074219 C 12.515625 36.800781 9.996094 34.636719 9.851563 34.507813 C 9.4375 34.144531 9.398438 33.511719 9.765625 33.097656 C 10.128906 32.683594 10.761719 32.644531 11.175781 33.007813 C 11.234375 33.0625 15.875 37 25 37 C 34.140625 37 38.78125 33.046875 38.828125 33.007813 C 39.242188 32.648438 39.871094 32.683594 40.238281 33.101563 C 40.601563 33.515625 40.5625 34.144531 40.148438 34.507813 C 40.003906 34.636719 37.484375 36.800781 32.550781 38.074219 L 34.378906 40.589844 C 34.566406 40.847656 34.867188 41 35.1875 41 C 35.199219 41 35.210938 41 35.21875 41 C 37.027344 40.941406 44.960938 39.605469 47.867188 34.496094 C 47.953125 34.34375 48 34.175781 48 34 C 48 24.152344 43.785156 12.761719 41.625 10.769531 Z M 18.5 30 C 16.566406 30 15 28.210938 15 26 C 15 23.789063 16.566406 22 18.5 22 C 20.433594 22 22 23.789063 22 26 C 22 28.210938 20.433594 30 18.5 30 Z M 31.5 30 C 29.566406 30 28 28.210938 28 26 C 28 23.789063 29.566406 22 31.5 22 C 33.433594 22 35 23.789063 35 26 C 35 28.210938 33.433594 30 31.5 30 Z"/></svg>
-        </a>
-    </div>
+          <svg fill="#FFFFFF" xmlns="http://www.w3.org/2000/svg"  viewBox="0 0 50 50" width="25px" height="25px"><path d="M 41.625 10.769531 C 37.644531 7.566406 31.347656 7.023438 31.078125 7.003906 C 30.660156 6.96875 30.261719 7.203125 30.089844 7.589844 C 30.074219 7.613281 29.9375 7.929688 29.785156 8.421875 C 32.417969 8.867188 35.652344 9.761719 38.578125 11.578125 C 39.046875 11.867188 39.191406 12.484375 38.902344 12.953125 C 38.710938 13.261719 38.386719 13.429688 38.050781 13.429688 C 37.871094 13.429688 37.6875 13.378906 37.523438 13.277344 C 32.492188 10.15625 26.210938 10 25 10 C 23.789063 10 17.503906 10.15625 12.476563 13.277344 C 12.007813 13.570313 11.390625 13.425781 11.101563 12.957031 C 10.808594 12.484375 10.953125 11.871094 11.421875 11.578125 C 14.347656 9.765625 17.582031 8.867188 20.214844 8.425781 C 20.0625 7.929688 19.925781 7.617188 19.914063 7.589844 C 19.738281 7.203125 19.34375 6.960938 18.921875 7.003906 C 18.652344 7.023438 12.355469 7.566406 8.320313 10.8125 C 6.214844 12.761719 2 24.152344 2 34 C 2 34.175781 2.046875 34.34375 2.132813 34.496094 C 5.039063 39.605469 12.972656 40.941406 14.78125 41 C 14.789063 41 14.800781 41 14.8125 41 C 15.132813 41 15.433594 40.847656 15.621094 40.589844 L 17.449219 38.074219 C 12.515625 36.800781 9.996094 34.636719 9.851563 34.507813 C 9.4375 34.144531 9.398438 33.511719 9.765625 33.097656 C 10.128906 32.683594 10.761719 32.644531 11.175781 33.007813 C 11.234375 33.0625 15.875 37 25 37 C 34.140625 37 38.78125 33.046875 38.828125 33.007813 C 39.242188 32.648438 39.871094 32.683594 40.238281 33.101563 C 40.601563 33.515625 40.5625 34.144531 40.148438 34.507813 C 40.003906 34.636719 37.484375 36.800781 32.550781 38.074219 L 34.378906 40.589844 C 34.566406 40.847656 34.867188 41 35.1875 41 C 35.199219 41 35.210938 41 35.21875 41 C 37.027344 40.941406 44.960938 39.605469 47.867188 34.496094 C 47.953125 34.34375 48 34.175781 48 34 C 48 24.152344 43.785156 12.761719 41.625 10.769531 Z M 18.5 30 C 16.566406 30 15 28.210938 15 26 C 15 23.789063 16.566406 22 18.5 22 C 20.433594 22 22 23.789063 22 26 C 22 28.210938 20.433594 30 18.5 30 Z M 31.5 30 C 29.566406 30 28 28.210938 28 26 C 28 23.789063 29.566406 22 31.5 22 C 33.433594 22 35 23.789063 35 26 C 35 28.210938 33.433594 30 31.5 30 Z"/></svg>
+      </a>
+  </div>
     <div style="margin-left: 5px; margin-right: 5px;">
         <a href="https://twitter.com/lancedb" target="_blank" rel="noopener noreferrer">
             <svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" viewBox="0,0,256,256" width="25px" height="25px" fill-rule="nonzero"><g fill-opacity="0" fill="#ffffff" fill-rule="nonzero" stroke="none" stroke-width="1" stroke-linecap="butt" stroke-linejoin="miter" stroke-miterlimit="10" stroke-dasharray="" stroke-dashoffset="0" font-family="none" font-weight="none" font-size="none" text-anchor="none" style="mix-blend-mode: normal"><path d="M0,256v-256h256v256z" id="bgRectangle"></path></g><g fill="#ffffff" fill-rule="nonzero" stroke="none" stroke-width="1" stroke-linecap="butt" stroke-linejoin="miter" stroke-miterlimit="10" stroke-dasharray="" stroke-dashoffset="0" font-family="none" font-weight="none" font-size="none" text-anchor="none" style="mix-blend-mode: normal"><g transform="scale(4,4)"><path d="M57,17.114c-1.32,1.973 -2.991,3.707 -4.916,5.097c0.018,0.423 0.028,0.847 0.028,1.274c0,13.013 -9.902,28.018 -28.016,28.018c-5.562,0 -12.81,-1.948 -15.095,-4.423c0.772,0.092 1.556,0.138 2.35,0.138c4.615,0 8.861,-1.575 12.23,-4.216c-4.309,-0.079 -7.946,-2.928 -9.199,-6.84c1.96,0.308 4.447,-0.17 4.447,-0.17c0,0 -7.7,-1.322 -7.899,-9.779c2.226,1.291 4.46,1.231 4.46,1.231c0,0 -4.441,-2.734 -4.379,-8.195c0.037,-3.221 1.331,-4.953 1.331,-4.953c8.414,10.361 20.298,10.29 20.298,10.29c0,0 -0.255,-1.471 -0.255,-2.243c0,-5.437 4.408,-9.847 9.847,-9.847c2.832,0 5.391,1.196 7.187,3.111c2.245,-0.443 4.353,-1.263 6.255,-2.391c-0.859,3.44 -4.329,5.448 -4.329,5.448c0,0 2.969,-0.329 5.655,-1.55z"></path></g></g></svg>
@@ -173,4 +179,77 @@
       {% include "partials/tabs.html" %}
     {% endif %}
   {% endif %}
-</header>
+</header>
+
+<script>
+  (function() {
+    function checkPathAndRedirect() {
+      var banner = document.getElementById('deprecation-banner');
+
+      if (document.querySelector('meta[http-equiv="refresh"]')) {
+        return; // The redirects plugin is already handling this page.
+      }
+
+      var currentPath = window.location.pathname;
+
+      var cleanPath = currentPath.endsWith('/') && currentPath.length > 1
+        ? currentPath.slice(0, -1)
+        : currentPath;
+
+      // These are the ONLY paths that should remain on the old site
+      var apiPaths = [
+        '/lancedb/python', 
+        '/lancedb/javascript', 
+        '/lancedb/js',
+        '/lancedb/api_reference'
+      ];
+      
+      var isApiPage = apiPaths.some(function(apiPath) {
+        return cleanPath.startsWith(apiPath);
+      });
+
+      if (isApiPage) {
+        if (banner) {
+          banner.style.display = 'none';
+        }
+      } else {
+        if (banner) {
+          banner.style.display = 'block';
+        }
+        
+        // Add noindex meta tag to prevent indexing of old docs for seo
+        var noindexMeta = document.createElement('meta');
+        noindexMeta.setAttribute('name', 'robots');
+        noindexMeta.setAttribute('content', 'noindex, follow');
+        document.head.appendChild(noindexMeta);
+
+        // Add canonical link to point to the new docs to reward new site for seo
+        var canonicalLink = document.createElement('link');
+        canonicalLink.setAttribute('rel', 'canonical');
+        canonicalLink.setAttribute('href', 'https://lancedb.com/docs');
+        document.head.appendChild(canonicalLink);
+        
+        window.location.replace('https://lancedb.com/docs');
+      }
+    }
+
+    // Run the check only if doc is ready. This makes sure we catch the initial load
+    // and redirect.
+    if (document.readyState === 'loading') {
+      document.addEventListener('DOMContentLoaded', checkPathAndRedirect);
+    } else {
+      checkPathAndRedirect();
+    }
+
+    // Use an interval to handle subsequent navigation clicks.
+    var lastPath = window.location.pathname;
+    setInterval(function() {
+      if (window.location.pathname !== lastPath) {
+        lastPath = window.location.pathname;
+        checkPathAndRedirect();
+      }
+    }, 2000); // keeping it 2 second to make it easy for user to understand
+              // what's happening
+
+  })();
+</script>

docs/requirements.txt

@@ -5,3 +5,4 @@ mkdocstrings[python]==0.25.2
 griffe
 mkdocs-render-swagger-plugin
 pydantic
+mkdocs-redirects

docs/src/concepts/data_management.md

@@ -13,7 +13,7 @@ The following concepts are important to keep in mind:
 - Data is versioned, with each insert operation creating a new version of the dataset and an update to the manifest that tracks versions via metadata
 
 !!! note
-    1. First, each version contains metadata and just the new/updated data in your transaction. So if you have 100 versions, they aren't 100 duplicates of the same data. However, they do have 100x the metadata overhead of a single version, which can result in slower queries.  
+    1. First, each version contains metadata and just the new/updated data in your transaction. So if you have 100 versions, they aren't 100 duplicates of the same data. However, they do have 100x the metadata overhead of a single version, which can result in slower queries.
     2. Second, these versions exist to keep LanceDB scalable and consistent. We do not immediately blow away old versions when creating new ones because other clients might be in the middle of querying the old version. It's important to retain older versions for as long as they might be queried.
 
 ## What are fragments?
@@ -37,6 +37,10 @@ Depending on the use case and dataset, optimal compaction will have different re
 - It’s always better to use *batch* inserts rather than adding 1 row at a time (to avoid too small fragments). If single-row inserts are unavoidable, run compaction on a regular basis to merge them into larger fragments.
 - Keep the number of fragments under 100, which is suitable for most use cases (for *really* large datasets of >500M rows, more fragments might be needed)
 
+!!! note
+
+    LanceDB Cloud/Enterprise supports [auto-compaction](https://docs.lancedb.com/enterprise/architecture/architecture#write-path) which automatically optimizes fragments in the background as data changes.
+
 ## Deletion
 
 Although Lance allows you to delete rows from a dataset, it does not actually delete the data immediately. It simply marks the row as deleted in the `DataFile` that represents a fragment. For a given version of the dataset, each fragment can have up to one deletion file (if no rows were ever deleted from that fragment, it will not have a deletion file). This is important to keep in mind because it means that the data is still there, and can be recovered if needed, as long as that version still exists based on your backup policy.
@@ -50,13 +54,9 @@ Reindexing is the process of updating the index to account for new data, keeping
 
 Both LanceDB OSS and Cloud support reindexing, but the process (at least for now) is different for each, depending on the type of index.
 
-When a reindex job is triggered in the background, the entire data is reindexed, but in the interim as new queries come in, LanceDB will combine results from the existing index with exhaustive kNN search on the new data. This is done to ensure that you're still searching on all your data, but it does come at a performance cost. The more data that you add without reindexing, the impact on latency (due to exhaustive search) can be noticeable.
+In LanceDB OSS, re-indexing happens synchronously when you call either `create_index` or `optimize` on a table. In LanceDB Cloud, re-indexing happens asynchronously as you add and update data in your table.
 
-### Vector reindex
+By default, queries will search new data even if it has yet to be indexed. This is done using brute-force methods, such as kNN for vector search, and combined with the fast index search results. This is done to ensure that you're always searching over all your data, but it does come at a performance cost. Without reindexing, adding more data to a table will make queries slower and more expensive. This behavior can be disabled by setting the [fast_search](https://lancedb.github.io/lancedb/python/python/#lancedb.query.AsyncQuery.fast_search) parameter which will instruct the query to ignore un-indexed data.
 
-* LanceDB Cloud supports incremental reindexing, where a background process will trigger a new index build for you automatically when new data is added to a dataset
+* LanceDB Cloud/Enterprise supports [automatic incremental reindexing](https://docs.lancedb.com/core#vector-index) for vector, scalar, and FTS indices, where a background process will trigger a new index build for you automatically when new data is added or modified in a dataset
 * LanceDB OSS requires you to manually trigger a reindex operation -- we are working on adding incremental reindexing to LanceDB OSS as well
-
-### FTS reindex
-
-FTS reindexing is supported in both LanceDB OSS and Cloud, but requires that it's manually rebuilt once you have a significant enough amount of new data added that needs to be reindexed. We [updated](https://github.com/lancedb/lancedb/pull/762) Tantivy's default heap size from 128MB to 1GB in LanceDB to make it much faster to reindex, by up to 10x from the default settings.

docs/src/embeddings/available_embedding_models/multimodal_embedding_functions/voyageai_multimodal_embedding.md

@@ -0,0 +1,97 @@
+# VoyageAI Embeddings : Multimodal
+
+VoyageAI embeddings can also be used to embed both text and image data, only some of the models support image data and you can check the list
+under [https://docs.voyageai.com/docs/multimodal-embeddings](https://docs.voyageai.com/docs/multimodal-embeddings)
+
+Supported parameters (to be passed in `create` method) are:
+
+| Parameter | Type | Default Value           | Description                               |
+|---|---|-------------------------|-------------------------------------------|
+| `name` | `str` | `"voyage-multimodal-3"` | The model ID of the VoyageAI model to use |
+
+Usage Example:
+
+```python
+import base64
+import os
+from io import BytesIO
+
+import requests
+import lancedb
+from lancedb.pydantic import LanceModel, Vector
+from lancedb.embeddings import get_registry
+import pandas as pd
+
+os.environ['VOYAGE_API_KEY'] = 'YOUR_VOYAGE_API_KEY'
+
+db = lancedb.connect(".lancedb")
+func = get_registry().get("voyageai").create(name="voyage-multimodal-3")
+
+
+def image_to_base64(image_bytes: bytes):
+    buffered = BytesIO(image_bytes)
+    img_str = base64.b64encode(buffered.getvalue())
+    return img_str.decode("utf-8")
+
+
+class Images(LanceModel):
+    label: str
+    image_uri: str = func.SourceField()  # image uri as the source
+    image_bytes: str = func.SourceField()  # image bytes base64 encoded as the source
+    vector: Vector(func.ndims()) = func.VectorField()  # vector column
+    vec_from_bytes: Vector(func.ndims()) = func.VectorField()  # Another vector column
+
+
+if "images" in db.table_names():
+    db.drop_table("images")
+table = db.create_table("images", schema=Images)
+labels = ["cat", "cat", "dog", "dog", "horse", "horse"]
+uris = [
+    "http://farm1.staticflickr.com/53/167798175_7c7845bbbd_z.jpg",
+    "http://farm1.staticflickr.com/134/332220238_da527d8140_z.jpg",
+    "http://farm9.staticflickr.com/8387/8602747737_2e5c2a45d4_z.jpg",
+    "http://farm5.staticflickr.com/4092/5017326486_1f46057f5f_z.jpg",
+    "http://farm9.staticflickr.com/8216/8434969557_d37882c42d_z.jpg",
+    "http://farm6.staticflickr.com/5142/5835678453_4f3a4edb45_z.jpg",
+]
+# get each uri as bytes
+images_bytes = [image_to_base64(requests.get(uri).content) for uri in uris]
+table.add(
+    pd.DataFrame({"label": labels, "image_uri": uris, "image_bytes": images_bytes})
+)
+```
+Now we can search using text from both the default vector column and the custom vector column
+```python
+
+# text search
+actual = table.search("man's best friend", "vec_from_bytes").limit(1).to_pydantic(Images)[0]
+print(actual.label) # prints "dog"
+
+frombytes = (
+    table.search("man's best friend", vector_column_name="vec_from_bytes")
+    .limit(1)
+    .to_pydantic(Images)[0]
+)
+print(frombytes.label)
+
+```
+
+Because we're using a multi-modal embedding function, we can also search using images
+
+```python
+# image search
+query_image_uri = "http://farm1.staticflickr.com/200/467715466_ed4a31801f_z.jpg"
+image_bytes = requests.get(query_image_uri).content
+query_image = Image.open(BytesIO(image_bytes))
+actual = table.search(query_image, "vec_from_bytes").limit(1).to_pydantic(Images)[0]
+print(actual.label == "dog")
+
+# image search using a custom vector column
+other = (
+    table.search(query_image, vector_column_name="vec_from_bytes")
+    .limit(1)
+    .to_pydantic(Images)[0]
+)
+print(actual.label)
+
+```

docs/src/guides/storage.md

@@ -397,117 +397,6 @@ For **read-only access**, LanceDB will need a policy such as:
 }
 ```
 
-#### DynamoDB Commit Store for concurrent writes
-
-By default, S3 does not support concurrent writes. Having two or more processes
-writing to the same table at the same time can lead to data corruption. This is
-because S3, unlike other object stores, does not have any atomic put or copy
-operation.
-
-To enable concurrent writes, you can configure LanceDB to use a DynamoDB table
-as a commit store. This table will be used to coordinate writes between
-different processes. To enable this feature, you must modify your connection
-URI to use the `s3+ddb` scheme and add a query parameter `ddbTableName` with the
-name of the table to use.
-
-=== "Python"
-
-    === "Sync API"
-
-        ```python
-        import lancedb
-        db = lancedb.connect(
-            "s3+ddb://bucket/path?ddbTableName=my-dynamodb-table",
-        )
-        ```
-    === "Async API"
-
-        ```python
-        import lancedb
-        async_db = await lancedb.connect_async(
-            "s3+ddb://bucket/path?ddbTableName=my-dynamodb-table",
-        )    
-        ```
-
-=== "JavaScript"
-
-    ```javascript
-    const lancedb = require("lancedb");
-
-    const db = await lancedb.connect(
-        "s3+ddb://bucket/path?ddbTableName=my-dynamodb-table",
-    );
-    ```
-
-The DynamoDB table must be created with the following schema:
-
-- Hash key: `base_uri` (string)
-- Range key: `version` (number)
-
-You can create this programmatically with:
-
-=== "Python"
-
-    <!-- skip-test -->
-    ```python
-    import boto3
-
-    dynamodb = boto3.client("dynamodb")
-    table = dynamodb.create_table(
-        TableName=table_name,
-        KeySchema=[
-            {"AttributeName": "base_uri", "KeyType": "HASH"},
-            {"AttributeName": "version", "KeyType": "RANGE"},
-        ],
-        AttributeDefinitions=[
-            {"AttributeName": "base_uri", "AttributeType": "S"},
-            {"AttributeName": "version", "AttributeType": "N"},
-        ],
-        ProvisionedThroughput={"ReadCapacityUnits": 1, "WriteCapacityUnits": 1},
-    )
-    ```
-
-=== "JavaScript"
-
-    <!-- skip-test -->
-    ```javascript
-    import {
-      CreateTableCommand,
-      DynamoDBClient,
-    } from "@aws-sdk/client-dynamodb";
-
-    const dynamodb = new DynamoDBClient({
-      region: CONFIG.awsRegion,
-      credentials: {
-        accessKeyId: CONFIG.awsAccessKeyId,
-        secretAccessKey: CONFIG.awsSecretAccessKey,
-      },
-      endpoint: CONFIG.awsEndpoint,
-    });
-    const command = new CreateTableCommand({
-      TableName: table_name,
-      AttributeDefinitions: [
-        {
-          AttributeName: "base_uri",
-          AttributeType: "S",
-        },
-        {
-          AttributeName: "version",
-          AttributeType: "N",
-        },
-      ],
-      KeySchema: [
-        { AttributeName: "base_uri", KeyType: "HASH" },
-        { AttributeName: "version", KeyType: "RANGE" },
-      ],
-      ProvisionedThroughput: {
-        ReadCapacityUnits: 1,
-        WriteCapacityUnits: 1,
-      },
-    });
-    await client.send(command);
-    ```
-
 
 #### S3-compatible stores
 

docs/src/js/classes/Connection.md

@@ -25,6 +25,51 @@ the underlying connection has been closed.
 
 ## Methods
 
+### cloneTable()
+
+```ts
+abstract cloneTable(
+   targetTableName,
+   sourceUri,
+   options?): Promise<Table>
+```
+
+Clone a table from a source table.
+
+A shallow clone creates a new table that shares the underlying data files
+with the source table but has its own independent manifest. This allows
+both the source and cloned tables to evolve independently while initially
+sharing the same data, deletion, and index files.
+
+#### Parameters
+
+* **targetTableName**: `string`
+    The name of the target table to create.
+
+* **sourceUri**: `string`
+    The URI of the source table to clone from.
+
+* **options?**
+    Clone options.
+
+* **options.isShallow?**: `boolean`
+    Whether to perform a shallow clone (defaults to true).
+
+* **options.sourceTag?**: `string`
+    The tag of the source table to clone.
+
+* **options.sourceVersion?**: `number`
+    The version of the source table to clone.
+
+* **options.targetNamespace?**: `string`[]
+    The namespace for the target table (defaults to root namespace).
+
+#### Returns
+
+`Promise`&lt;[`Table`](Table.md)&gt;
+
+***
+
 ### close()
 
 ```ts
@@ -45,6 +90,8 @@ Any attempt to use the connection after it is closed will result in an error.
 
 ### createEmptyTable()
 
+#### createEmptyTable(name, schema, options)
+
 ```ts
 abstract createEmptyTable(
    name,
@@ -54,7 +101,7 @@ abstract createEmptyTable(
 
 Creates a new empty Table
 
-#### Parameters
+##### Parameters
 
 * **name**: `string`
     The name of the table.
@@ -63,8 +110,39 @@ Creates a new empty Table
     The schema of the table
 
 * **options?**: `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
+    Additional options (backwards compatibility)
 
-#### Returns
+##### Returns
+
+`Promise`&lt;[`Table`](Table.md)&gt;
+
+#### createEmptyTable(name, schema, namespace, options)
+
+```ts
+abstract createEmptyTable(
+   name,
+   schema,
+   namespace?,
+   options?): Promise<Table>
+```
+
+Creates a new empty Table
+
+##### Parameters
+
+* **name**: `string`
+    The name of the table.
+
+* **schema**: [`SchemaLike`](../type-aliases/SchemaLike.md)
+    The schema of the table
+
+* **namespace?**: `string`[]
+    The namespace to create the table in (defaults to root namespace)
+
+* **options?**: `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
+    Additional options
+
+##### Returns
 
 `Promise`&lt;[`Table`](Table.md)&gt;
 
@@ -72,10 +150,10 @@ Creates a new empty Table
 
 ### createTable()
 
-#### createTable(options)
+#### createTable(options, namespace)
 
 ```ts
-abstract createTable(options): Promise<Table>
+abstract createTable(options, namespace?): Promise<Table>
 ```
 
 Creates a new Table and initialize it with new data.
@@ -85,6 +163,9 @@ Creates a new Table and initialize it with new data.
 * **options**: `object` & `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
     The options object.
 
+* **namespace?**: `string`[]
+    The namespace to create the table in (defaults to root namespace)
+
 ##### Returns
 
 `Promise`&lt;[`Table`](Table.md)&gt;
@@ -110,6 +191,38 @@ Creates a new Table and initialize it with new data.
     to be inserted into the table
 
 * **options?**: `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
+    Additional options (backwards compatibility)
+
+##### Returns
+
+`Promise`&lt;[`Table`](Table.md)&gt;
+
+#### createTable(name, data, namespace, options)
+
+```ts
+abstract createTable(
+   name,
+   data,
+   namespace?,
+   options?): Promise<Table>
+```
+
+Creates a new Table and initialize it with new data.
+
+##### Parameters
+
+* **name**: `string`
+    The name of the table.
+
+* **data**: [`TableLike`](../type-aliases/TableLike.md) \| `Record`&lt;`string`, `unknown`&gt;[]
+    Non-empty Array of Records
+    to be inserted into the table
+
+* **namespace?**: `string`[]
+    The namespace to create the table in (defaults to root namespace)
+
+* **options?**: `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
+    Additional options
 
 ##### Returns
 
@@ -134,11 +247,16 @@ Return a brief description of the connection
 ### dropAllTables()
 
 ```ts
-abstract dropAllTables(): Promise<void>
+abstract dropAllTables(namespace?): Promise<void>
 ```
 
 Drop all tables in the database.
 
+#### Parameters
+
+* **namespace?**: `string`[]
+    The namespace to drop tables from (defaults to root namespace).
+
 #### Returns
 
 `Promise`&lt;`void`&gt;
@@ -148,7 +266,7 @@ Drop all tables in the database.
 ### dropTable()
 
 ```ts
-abstract dropTable(name): Promise<void>
+abstract dropTable(name, namespace?): Promise<void>
 ```
 
 Drop an existing table.
@@ -158,6 +276,9 @@ Drop an existing table.
 * **name**: `string`
     The name of the table to drop.
 
+* **namespace?**: `string`[]
+    The namespace of the table (defaults to root namespace).
+
 #### Returns
 
 `Promise`&lt;`void`&gt;
@@ -181,7 +302,10 @@ Return true if the connection has not been closed
 ### openTable()
 
 ```ts
-abstract openTable(name, options?): Promise<Table>
+abstract openTable(
+   name,
+   namespace?,
+   options?): Promise<Table>
 ```
 
 Open a table in the database.
@@ -191,7 +315,11 @@ Open a table in the database.
 * **name**: `string`
     The name of the table
 
+* **namespace?**: `string`[]
+    The namespace of the table (defaults to root namespace)
+
 * **options?**: `Partial`&lt;[`OpenTableOptions`](../interfaces/OpenTableOptions.md)&gt;
+    Additional options
 
 #### Returns
 
@@ -201,6 +329,8 @@ Open a table in the database.
 
 ### tableNames()
 
+#### tableNames(options)
+
 ```ts
 abstract tableNames(options?): Promise<string[]>
 ```
@@ -209,12 +339,35 @@ List all the table names in this database.
 
 Tables will be returned in lexicographical order.
 
-#### Parameters
+##### Parameters
+
+* **options?**: `Partial`&lt;[`TableNamesOptions`](../interfaces/TableNamesOptions.md)&gt;
+    options to control the
+    paging / start point (backwards compatibility)
+
+##### Returns
+
+`Promise`&lt;`string`[]&gt;
+
+#### tableNames(namespace, options)
+
+```ts
+abstract tableNames(namespace?, options?): Promise<string[]>
+```
+
+List all the table names in this database.
+
+Tables will be returned in lexicographical order.
+
+##### Parameters
+
+* **namespace?**: `string`[]
+    The namespace to list tables from (defaults to root namespace)
 
 * **options?**: `Partial`&lt;[`TableNamesOptions`](../interfaces/TableNamesOptions.md)&gt;
     options to control the
     paging / start point
 
-#### Returns
+##### Returns
 
 `Promise`&lt;`string`[]&gt;

docs/src/js/classes/HeaderProvider.md

@@ -0,0 +1,85 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / HeaderProvider
+
+# Class: `abstract` HeaderProvider
+
+Abstract base class for providing custom headers for each request.
+
+Users can implement this interface to provide dynamic headers for various purposes
+such as authentication (OAuth tokens, API keys), request tracking (correlation IDs),
+custom metadata, or any other header-based requirements. The provider is called
+before each request to ensure fresh header values are always used.
+
+## Examples
+
+Simple JWT token provider:
+```typescript
+class JWTProvider extends HeaderProvider {
+  constructor(private token: string) {
+    super();
+  }
+
+  getHeaders(): Record<string, string> {
+    return { authorization: `Bearer ${this.token}` };
+  }
+}
+```
+
+Provider with request tracking:
+```typescript
+class RequestTrackingProvider extends HeaderProvider {
+  constructor(private sessionId: string) {
+    super();
+  }
+
+  getHeaders(): Record<string, string> {
+    return {
+      "X-Session-Id": this.sessionId,
+      "X-Request-Id": `req-${Date.now()}`
+    };
+  }
+}
+```
+
+## Extended by
+
+- [`StaticHeaderProvider`](StaticHeaderProvider.md)
+- [`OAuthHeaderProvider`](OAuthHeaderProvider.md)
+
+## Constructors
+
+### new HeaderProvider()
+
+```ts
+new HeaderProvider(): HeaderProvider
+```
+
+#### Returns
+
+[`HeaderProvider`](HeaderProvider.md)
+
+## Methods
+
+### getHeaders()
+
+```ts
+abstract getHeaders(): Record<string, string>
+```
+
+Get the latest headers to be added to requests.
+
+This method is called before each request to the remote LanceDB server.
+Implementations should return headers that will be merged with existing headers.
+
+#### Returns
+
+`Record`&lt;`string`, `string`&gt;
+
+Dictionary of header names to values to add to the request.
+
+#### Throws
+
+If unable to fetch headers, the exception will be propagated and the request will fail.

docs/src/js/classes/Index.md

@@ -194,6 +194,37 @@ currently is also a memory intensive operation.
 
 ***
 
+### ivfRq()
+
+```ts
+static ivfRq(options?): Index
+```
+
+Create an IvfRq index
+
+IVF-RQ (RabitQ Quantization) compresses vectors using RabitQ quantization
+and organizes them into IVF partitions.
+
+The compression scheme is called RabitQ quantization. Each dimension is quantized into a small number of bits.
+The parameters `num_bits` and `num_partitions` control this process, providing a tradeoff
+between index size (and thus search speed) and index accuracy.
+
+The partitioning process is called IVF and the `num_partitions` parameter controls how
+many groups to create.
+
+Note that training an IVF RQ index on a large dataset is a slow operation and
+currently is also a memory intensive operation.
+
+#### Parameters
+
+* **options?**: `Partial`<[`IvfRqOptions`](../interfaces/IvfRqOptions.md)>
+
+#### Returns
+
+[`Index`](Index.md)
+
+***
+
 ### labelList()
 
 ```ts

docs/src/js/classes/MergeInsertBuilder.md

@@ -52,6 +52,30 @@ the merge result
 
 ***
 
+### useIndex()
+
+```ts
+useIndex(useIndex): MergeInsertBuilder
+```
+
+Controls whether to use indexes for the merge operation.
+
+When set to `true` (the default), the operation will use an index if available
+on the join key for improved performance. When set to `false`, it forces a full
+table scan even if an index exists. This can be useful for benchmarking or when
+the query optimizer chooses a suboptimal path.
+
+#### Parameters
+
+* **useIndex**: `boolean`
+    Whether to use indices for the merge operation. Defaults to `true`.
+
+#### Returns
+
+[`MergeInsertBuilder`](MergeInsertBuilder.md)
+
+***
+
 ### whenMatchedUpdateAll()
 
 ```ts

docs/src/js/classes/NativeJsHeaderProvider.md

@@ -0,0 +1,29 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / NativeJsHeaderProvider
+
+# Class: NativeJsHeaderProvider
+
+JavaScript HeaderProvider implementation that wraps a JavaScript callback.
+This is the only native header provider - all header provider implementations
+should provide a JavaScript function that returns headers.
+
+## Constructors
+
+### new NativeJsHeaderProvider()
+
+```ts
+new NativeJsHeaderProvider(getHeadersCallback): NativeJsHeaderProvider
+```
+
+Create a new JsHeaderProvider from a JavaScript callback
+
+#### Parameters
+
+* **getHeadersCallback**
+
+#### Returns
+
+[`NativeJsHeaderProvider`](NativeJsHeaderProvider.md)

docs/src/js/classes/OAuthHeaderProvider.md

@@ -0,0 +1,108 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / OAuthHeaderProvider
+
+# Class: OAuthHeaderProvider
+
+Example implementation: OAuth token provider with automatic refresh.
+
+This is an example implementation showing how to manage OAuth tokens
+with automatic refresh when they expire.
+
+## Example
+
+```typescript
+async function fetchToken(): Promise<TokenResponse> {
+  const response = await fetch("https://oauth.example.com/token", {
+    method: "POST",
+    body: JSON.stringify({
+      grant_type: "client_credentials",
+      client_id: "your-client-id",
+      client_secret: "your-client-secret"
+    }),
+    headers: { "Content-Type": "application/json" }
+  });
+  const data = await response.json();
+  return {
+    accessToken: data.access_token,
+    expiresIn: data.expires_in
+  };
+}
+
+const provider = new OAuthHeaderProvider(fetchToken);
+const headers = provider.getHeaders();
+// Returns: {"authorization": "Bearer <your-token>"}
+```
+
+## Extends
+
+- [`HeaderProvider`](HeaderProvider.md)
+
+## Constructors
+
+### new OAuthHeaderProvider()
+
+```ts
+new OAuthHeaderProvider(tokenFetcher, refreshBufferSeconds): OAuthHeaderProvider
+```
+
+Initialize the OAuth provider.
+
+#### Parameters
+
+* **tokenFetcher**
+    Function to fetch new tokens. Should return object with 'accessToken' and optionally 'expiresIn'.
+
+* **refreshBufferSeconds**: `number` = `300`
+    Seconds before expiry to refresh token. Default 300 (5 minutes).
+
+#### Returns
+
+[`OAuthHeaderProvider`](OAuthHeaderProvider.md)
+
+#### Overrides
+
+[`HeaderProvider`](HeaderProvider.md).[`constructor`](HeaderProvider.md#constructors)
+
+## Methods
+
+### getHeaders()
+
+```ts
+getHeaders(): Record<string, string>
+```
+
+Get OAuth headers, refreshing token if needed.
+Note: This is synchronous for now as the Rust implementation expects sync.
+In a real implementation, this would need to handle async properly.
+
+#### Returns
+
+`Record`&lt;`string`, `string`&gt;
+
+Headers with Bearer token authorization.
+
+#### Throws
+
+If unable to fetch or refresh token.
+
+#### Overrides
+
+[`HeaderProvider`](HeaderProvider.md).[`getHeaders`](HeaderProvider.md#getheaders)
+
+***
+
+### refreshToken()
+
+```ts
+refreshToken(): Promise<void>
+```
+
+Manually refresh the token.
+Call this before using getHeaders() to ensure token is available.
+
+#### Returns
+
+`Promise`&lt;`void`&gt;

docs/src/js/classes/PermutationBuilder.md

@@ -0,0 +1,220 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / PermutationBuilder
+
+# Class: PermutationBuilder
+
+A PermutationBuilder for creating data permutations with splits, shuffling, and filtering.
+
+This class provides a TypeScript wrapper around the native Rust PermutationBuilder,
+offering methods to configure data splits, shuffling, and filtering before executing
+the permutation to create a new table.
+
+## Methods
+
+### execute()
+
+```ts
+execute(): Promise<Table>
+```
+
+Execute the permutation and create the destination table.
+
+#### Returns
+
+`Promise`&lt;[`Table`](Table.md)&gt;
+
+A Promise that resolves to the new Table instance
+
+#### Example
+
+```ts
+const permutationTable = await builder.execute();
+console.log(`Created table: ${permutationTable.name}`);
+```
+
+***
+
+### filter()
+
+```ts
+filter(filter): PermutationBuilder
+```
+
+Configure filtering for the permutation.
+
+#### Parameters
+
+* **filter**: `string`
+    SQL filter expression
+
+#### Returns
+
+[`PermutationBuilder`](PermutationBuilder.md)
+
+A new PermutationBuilder instance
+
+#### Example
+
+```ts
+builder.filter("age > 18 AND status = 'active'");
+```
+
+***
+
+### shuffle()
+
+```ts
+shuffle(options): PermutationBuilder
+```
+
+Configure shuffling for the permutation.
+
+#### Parameters
+
+* **options**: [`ShuffleOptions`](../interfaces/ShuffleOptions.md)
+    Configuration for shuffling
+
+#### Returns
+
+[`PermutationBuilder`](PermutationBuilder.md)
+
+A new PermutationBuilder instance
+
+#### Example
+
+```ts
+// Basic shuffle
+builder.shuffle({ seed: 42 });
+
+// Shuffle with clump size
+builder.shuffle({ seed: 42, clumpSize: 10 });
+```
+
+***
+
+### splitCalculated()
+
+```ts
+splitCalculated(calculation): PermutationBuilder
+```
+
+Configure calculated splits for the permutation.
+
+#### Parameters
+
+* **calculation**: `string`
+    SQL expression for calculating splits
+
+#### Returns
+
+[`PermutationBuilder`](PermutationBuilder.md)
+
+A new PermutationBuilder instance
+
+#### Example
+
+```ts
+builder.splitCalculated("user_id % 3");
+```
+
+***
+
+### splitHash()
+
+```ts
+splitHash(options): PermutationBuilder
+```
+
+Configure hash-based splits for the permutation.
+
+#### Parameters
+
+* **options**: [`SplitHashOptions`](../interfaces/SplitHashOptions.md)
+    Configuration for hash-based splitting
+
+#### Returns
+
+[`PermutationBuilder`](PermutationBuilder.md)
+
+A new PermutationBuilder instance
+
+#### Example
+
+```ts
+builder.splitHash({
+  columns: ["user_id"],
+  splitWeights: [70, 30],
+  discardWeight: 0
+});
+```
+
+***
+
+### splitRandom()
+
+```ts
+splitRandom(options): PermutationBuilder
+```
+
+Configure random splits for the permutation.
+
+#### Parameters
+
+* **options**: [`SplitRandomOptions`](../interfaces/SplitRandomOptions.md)
+    Configuration for random splitting
+
+#### Returns
+
+[`PermutationBuilder`](PermutationBuilder.md)
+
+A new PermutationBuilder instance
+
+#### Example
+
+```ts
+// Split by ratios
+builder.splitRandom({ ratios: [0.7, 0.3], seed: 42 });
+
+// Split by counts
+builder.splitRandom({ counts: [1000, 500], seed: 42 });
+
+// Split with fixed size
+builder.splitRandom({ fixed: 100, seed: 42 });
+```
+
+***
+
+### splitSequential()
+
+```ts
+splitSequential(options): PermutationBuilder
+```
+
+Configure sequential splits for the permutation.
+
+#### Parameters
+
+* **options**: [`SplitSequentialOptions`](../interfaces/SplitSequentialOptions.md)
+    Configuration for sequential splitting
+
+#### Returns
+
+[`PermutationBuilder`](PermutationBuilder.md)
+
+A new PermutationBuilder instance
+
+#### Example
+
+```ts
+// Split by ratios
+builder.splitSequential({ ratios: [0.8, 0.2] });
+
+// Split by counts
+builder.splitSequential({ counts: [800, 200] });
+
+// Split with fixed size
+builder.splitSequential({ fixed: 1000 });
+```

docs/src/js/classes/Query.md

@@ -14,7 +14,7 @@ A builder for LanceDB queries.
 
 ## Extends
 
-- [`QueryBase`](QueryBase.md)<`NativeQuery`>
+- `StandardQueryBase`<`NativeQuery`>
 
 ## Properties
 
@@ -26,7 +26,7 @@ protected inner: Query | Promise<Query>;
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`inner`](QueryBase.md#inner)
+`StandardQueryBase.inner`
 
 ## Methods
 
@@ -73,14 +73,14 @@ AnalyzeExec verbose=true, metrics=[]
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`analyzePlan`](QueryBase.md#analyzeplan)
+`StandardQueryBase.analyzePlan`
 
 ***
 
 ### execute()
 
 ```ts
-protected execute(options?): RecordBatchIterator
+protected execute(options?): AsyncGenerator<RecordBatch<any>, void, unknown>
 ```
 
 Execute the query and return the results as an
@@ -91,7 +91,7 @@ Execute the query and return the results as an
 
 #### Returns
 
-[`RecordBatchIterator`](RecordBatchIterator.md)
+`AsyncGenerator`&lt;`RecordBatch`&lt;`any`&gt;, `void`, `unknown`&gt;
 
 #### See
 
@@ -107,7 +107,7 @@ single query)
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`execute`](QueryBase.md#execute)
+`StandardQueryBase.execute`
 
 ***
 
@@ -143,7 +143,7 @@ const plan = await table.query().nearestTo([0.5, 0.2]).explainPlan();
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`explainPlan`](QueryBase.md#explainplan)
+`StandardQueryBase.explainPlan`
 
 ***
 
@@ -164,7 +164,7 @@ Use [Table#optimize](Table.md#optimize) to index all un-indexed data.
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`fastSearch`](QueryBase.md#fastsearch)
+`StandardQueryBase.fastSearch`
 
 ***
 
@@ -194,7 +194,7 @@ Use `where` instead
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`filter`](QueryBase.md#filter)
+`StandardQueryBase.filter`
 
 ***
 
@@ -216,7 +216,7 @@ fullTextSearch(query, options?): this
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`fullTextSearch`](QueryBase.md#fulltextsearch)
+`StandardQueryBase.fullTextSearch`
 
 ***
 
@@ -241,7 +241,7 @@ called then every valid row from the table will be returned.
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`limit`](QueryBase.md#limit)
+`StandardQueryBase.limit`
 
 ***
 
@@ -325,6 +325,10 @@ nearestToText(query, columns?): Query
 offset(offset): this
 ```
 
+Set the number of rows to skip before returning results.
+
+This is useful for pagination.
+
 #### Parameters
 
 * **offset**: `number`
@@ -335,7 +339,30 @@ offset(offset): this
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`offset`](QueryBase.md#offset)
+`StandardQueryBase.offset`
+
+***
+
+### outputSchema()
+
+```ts
+outputSchema(): Promise<Schema<any>>
+```
+
+Returns the schema of the output that will be returned by this query.
+
+This can be used to inspect the types and names of the columns that will be
+returned by the query before executing it.
+
+#### Returns
+
+`Promise`&lt;`Schema`&lt;`any`&gt;&gt;
+
+An Arrow Schema describing the output columns.
+
+#### Inherited from
+
+`StandardQueryBase.outputSchema`
 
 ***
 
@@ -388,7 +415,7 @@ object insertion order is easy to get wrong and `Map` is more foolproof.
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`select`](QueryBase.md#select)
+`StandardQueryBase.select`
 
 ***
 
@@ -410,7 +437,7 @@ Collect the results as an array of objects.
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`toArray`](QueryBase.md#toarray)
+`StandardQueryBase.toArray`
 
 ***
 
@@ -436,7 +463,7 @@ ArrowTable.
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`toArrow`](QueryBase.md#toarrow)
+`StandardQueryBase.toArrow`
 
 ***
 
@@ -471,7 +498,7 @@ on the filter column(s).
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`where`](QueryBase.md#where)
+`StandardQueryBase.where`
 
 ***
 
@@ -493,4 +520,4 @@ order to perform hybrid search.
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`withRowId`](QueryBase.md#withrowid)
+`StandardQueryBase.withRowId`

docs/src/js/classes/QueryBase.md

@@ -15,12 +15,11 @@ Common methods supported by all query types
 
 ## Extended by
 
-- [`Query`](Query.md)
-- [`VectorQuery`](VectorQuery.md)
+- [`TakeQuery`](TakeQuery.md)
 
 ## Type Parameters
 
-• **NativeQueryType** *extends* `NativeQuery` \| `NativeVectorQuery`
+• **NativeQueryType** *extends* `NativeQuery` \| `NativeVectorQuery` \| `NativeTakeQuery`
 
 ## Implements
 
@@ -82,7 +81,7 @@ AnalyzeExec verbose=true, metrics=[]
 ### execute()
 
 ```ts
-protected execute(options?): RecordBatchIterator
+protected execute(options?): AsyncGenerator<RecordBatch<any>, void, unknown>
 ```
 
 Execute the query and return the results as an
@@ -93,7 +92,7 @@ Execute the query and return the results as an
 
 #### Returns
 
-[`RecordBatchIterator`](RecordBatchIterator.md)
+`AsyncGenerator`&lt;`RecordBatch`&lt;`any`&gt;, `void`, `unknown`&gt;
 
 #### See
 
@@ -141,101 +140,22 @@ const plan = await table.query().nearestTo([0.5, 0.2]).explainPlan();
 
 ***
 
-### fastSearch()
+### outputSchema()
 
 ```ts
-fastSearch(): this
+outputSchema(): Promise<Schema<any>>
 ```
 
-Skip searching un-indexed data. This can make search faster, but will miss
-any data that is not yet indexed.
+Returns the schema of the output that will be returned by this query.
 
-Use [Table#optimize](Table.md#optimize) to index all un-indexed data.
+This can be used to inspect the types and names of the columns that will be
+returned by the query before executing it.
 
 #### Returns
 
-`this`
+`Promise`&lt;`Schema`&lt;`any`&gt;&gt;
 
-***
-
-### ~~filter()~~
-
-```ts
-filter(predicate): this
-```
-
-A filter statement to be applied to this query.
-
-#### Parameters
-
-* **predicate**: `string`
-
-#### Returns
-
-`this`
-
-#### See
-
-where
-
-#### Deprecated
-
-Use `where` instead
-
-***
-
-### fullTextSearch()
-
-```ts
-fullTextSearch(query, options?): this
-```
-
-#### Parameters
-
-* **query**: `string` \| [`FullTextQuery`](../interfaces/FullTextQuery.md)
-
-* **options?**: `Partial`&lt;[`FullTextSearchOptions`](../interfaces/FullTextSearchOptions.md)&gt;
-
-#### Returns
-
-`this`
-
-***
-
-### limit()
-
-```ts
-limit(limit): this
-```
-
-Set the maximum number of results to return.
-
-By default, a plain search has no limit.  If this method is not
-called then every valid row from the table will be returned.
-
-#### Parameters
-
-* **limit**: `number`
-
-#### Returns
-
-`this`
-
-***
-
-### offset()
-
-```ts
-offset(offset): this
-```
-
-#### Parameters
-
-* **offset**: `number`
-
-#### Returns
-
-`this`
+An Arrow Schema describing the output columns.
 
 ***
 
@@ -328,37 +248,6 @@ ArrowTable.
 
 ***
 
-### where()
-
-```ts
-where(predicate): this
-```
-
-A filter statement to be applied to this query.
-
-The filter should be supplied as an SQL query string.  For example:
-
-#### Parameters
-
-* **predicate**: `string`
-
-#### Returns
-
-`this`
-
-#### Example
-
-```ts
-x > 10
-y > 0 AND y < 100
-x > 5 OR y = 'test'
-
-Filtering performance can often be improved by creating a scalar index
-on the filter column(s).
-```
-
-***
-
 ### withRowId()
 
 ```ts

docs/src/js/classes/RecordBatchIterator.md

@@ -1,43 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / RecordBatchIterator
-
-# Class: RecordBatchIterator
-
-## Implements
-
-- `AsyncIterator`<`RecordBatch`>
-
-## Constructors
-
-### new RecordBatchIterator()
-
-```ts
-new RecordBatchIterator(promise?): RecordBatchIterator
-```
-
-#### Parameters
-
-* **promise?**: `Promise`<`RecordBatchIterator`>
-
-#### Returns
-
-[`RecordBatchIterator`](RecordBatchIterator.md)
-
-## Methods
-
-### next()
-
-```ts
-next(): Promise<IteratorResult<RecordBatch<any>, any>>
-```
-
-#### Returns
-
-`Promise`&lt;`IteratorResult`&lt;`RecordBatch`&lt;`any`&gt;, `any`&gt;&gt;
-
-#### Implementation of
-
-`AsyncIterator.next`

docs/src/js/classes/Session.md

@@ -9,7 +9,8 @@
 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.
+which can significantly impact memory use and performance. They can
+also be re-used across multiple connections to share the same cache state.
 
 ## Constructors
 
@@ -24,8 +25,11 @@ Create a new session with custom cache sizes.
 # Parameters
 
 - `index_cache_size_bytes`: The size of the index cache in bytes.
+  Index data is stored in memory in this cache to speed up queries.
   Defaults to 6GB if not specified.
 - `metadata_cache_size_bytes`: The size of the metadata cache in bytes.
+  The metadata cache stores file metadata and schema information in memory.
+  This cache improves scan and write performance.
   Defaults to 1GB if not specified.
 
 #### Parameters

docs/src/js/classes/StaticHeaderProvider.md

@@ -0,0 +1,70 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / StaticHeaderProvider
+
+# Class: StaticHeaderProvider
+
+Example implementation: A simple header provider that returns static headers.
+
+This is an example implementation showing how to create a HeaderProvider
+for cases where headers don't change during the session.
+
+## Example
+
+```typescript
+const provider = new StaticHeaderProvider({
+  authorization: "Bearer my-token",
+  "X-Custom-Header": "custom-value"
+});
+const headers = provider.getHeaders();
+// Returns: {authorization: 'Bearer my-token', 'X-Custom-Header': 'custom-value'}
+```
+
+## Extends
+
+- [`HeaderProvider`](HeaderProvider.md)
+
+## Constructors
+
+### new StaticHeaderProvider()
+
+```ts
+new StaticHeaderProvider(headers): StaticHeaderProvider
+```
+
+Initialize with static headers.
+
+#### Parameters
+
+* **headers**: `Record`<`string`, `string`>
+    Headers to return for every request.
+
+#### Returns
+
+[`StaticHeaderProvider`](StaticHeaderProvider.md)
+
+#### Overrides
+
+[`HeaderProvider`](HeaderProvider.md).[`constructor`](HeaderProvider.md#constructors)
+
+## Methods
+
+### getHeaders()
+
+```ts
+getHeaders(): Record<string, string>
+```
+
+Return the static headers.
+
+#### Returns
+
+`Record`&lt;`string`, `string`&gt;
+
+Copy of the static headers.
+
+#### Overrides
+
+[`HeaderProvider`](HeaderProvider.md).[`getHeaders`](HeaderProvider.md#getheaders)

docs/src/js/classes/Table.md

@@ -674,6 +674,48 @@ console.log(tags); // { "v1": { version: 1, manifestSize: ... } }
 
 ***
 
+### takeOffsets()
+
+```ts
+abstract takeOffsets(offsets): TakeQuery
+```
+
+Create a query that returns a subset of the rows in the table.
+
+#### Parameters
+
+* **offsets**: `number`[]
+    The offsets of the rows to return.
+
+#### Returns
+
+[`TakeQuery`](TakeQuery.md)
+
+A builder that can be used to parameterize the query.
+
+***
+
+### takeRowIds()
+
+```ts
+abstract takeRowIds(rowIds): TakeQuery
+```
+
+Create a query that returns a subset of the rows in the table.
+
+#### Parameters
+
+* **rowIds**: `number`[]
+    The row ids of the rows to return.
+
+#### Returns
+
+[`TakeQuery`](TakeQuery.md)
+
+A builder that can be used to parameterize the query.
+
+***
+
 ### toArrow()
 
 ```ts

docs/src/js/classes/TakeQuery.md

@@ -0,0 +1,288 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / TakeQuery
+
+# Class: TakeQuery
+
+A query that returns a subset of the rows in the table.
+
+## Extends
+
+- [`QueryBase`](QueryBase.md)<`NativeTakeQuery`>
+
+## Properties
+
+### inner
+
+```ts
+protected inner: TakeQuery | Promise<TakeQuery>;
+```
+
+#### Inherited from
+
+[`QueryBase`](QueryBase.md).[`inner`](QueryBase.md#inner)
+
+## Methods
+
+### analyzePlan()
+
+```ts
+analyzePlan(): Promise<string>
+```
+
+Executes the query and returns the physical query plan annotated with runtime metrics.
+
+This is useful for debugging and performance analysis, as it shows how the query was executed
+and includes metrics such as elapsed time, rows processed, and I/O statistics.
+
+#### Returns
+
+`Promise`&lt;`string`&gt;
+
+A query execution plan with runtime metrics for each step.
+
+#### Example
+
+```ts
+import * as lancedb from "@lancedb/lancedb"
+
+const db = await lancedb.connect("./.lancedb");
+const table = await db.createTable("my_table", [
+  { vector: [1.1, 0.9], id: "1" },
+]);
+
+const plan = await table.query().nearestTo([0.5, 0.2]).analyzePlan();
+
+Example output (with runtime metrics inlined):
+AnalyzeExec verbose=true, metrics=[]
+ ProjectionExec: expr=[id@3 as id, vector@0 as vector, _distance@2 as _distance], metrics=[output_rows=1, elapsed_compute=3.292µs]
+  Take: columns="vector, _rowid, _distance, (id)", metrics=[output_rows=1, elapsed_compute=66.001µs, batches_processed=1, bytes_read=8, iops=1, requests=1]
+   CoalesceBatchesExec: target_batch_size=1024, metrics=[output_rows=1, elapsed_compute=3.333µs]
+    GlobalLimitExec: skip=0, fetch=10, metrics=[output_rows=1, elapsed_compute=167ns]
+     FilterExec: _distance@2 IS NOT NULL, metrics=[output_rows=1, elapsed_compute=8.542µs]
+      SortExec: TopK(fetch=10), expr=[_distance@2 ASC NULLS LAST], metrics=[output_rows=1, elapsed_compute=63.25µs, row_replacements=1]
+       KNNVectorDistance: metric=l2, metrics=[output_rows=1, elapsed_compute=114.333µs, output_batches=1]
+        LanceScan: uri=/path/to/data, projection=[vector], row_id=true, row_addr=false, ordered=false, metrics=[output_rows=1, elapsed_compute=103.626µs, bytes_read=549, iops=2, requests=2]
+```
+
+#### Inherited from
+
+[`QueryBase`](QueryBase.md).[`analyzePlan`](QueryBase.md#analyzeplan)
+
+***
+
+### execute()
+
+```ts
+protected execute(options?): AsyncGenerator<RecordBatch<any>, void, unknown>
+```
+
+Execute the query and return the results as an
+
+#### Parameters
+
+* **options?**: `Partial`&lt;[`QueryExecutionOptions`](../interfaces/QueryExecutionOptions.md)&gt;
+
+#### Returns
+
+`AsyncGenerator`&lt;`RecordBatch`&lt;`any`&gt;, `void`, `unknown`&gt;
+
+#### See
+
+ - AsyncIterator
+of
+ - RecordBatch.
+
+By default, LanceDb will use many threads to calculate results and, when
+the result set is large, multiple batches will be processed at one time.
+This readahead is limited however and backpressure will be applied if this
+stream is consumed slowly (this constrains the maximum memory used by a
+single query)
+
+#### Inherited from
+
+[`QueryBase`](QueryBase.md).[`execute`](QueryBase.md#execute)
+
+***
+
+### explainPlan()
+
+```ts
+explainPlan(verbose): Promise<string>
+```
+
+Generates an explanation of the query execution plan.
+
+#### Parameters
+
+* **verbose**: `boolean` = `false`
+    If true, provides a more detailed explanation. Defaults to false.
+
+#### Returns
+
+`Promise`&lt;`string`&gt;
+
+A Promise that resolves to a string containing the query execution plan explanation.
+
+#### Example
+
+```ts
+import * as lancedb from "@lancedb/lancedb"
+const db = await lancedb.connect("./.lancedb");
+const table = await db.createTable("my_table", [
+  { vector: [1.1, 0.9], id: "1" },
+]);
+const plan = await table.query().nearestTo([0.5, 0.2]).explainPlan();
+```
+
+#### Inherited from
+
+[`QueryBase`](QueryBase.md).[`explainPlan`](QueryBase.md#explainplan)
+
+***
+
+### outputSchema()
+
+```ts
+outputSchema(): Promise<Schema<any>>
+```
+
+Returns the schema of the output that will be returned by this query.
+
+This can be used to inspect the types and names of the columns that will be
+returned by the query before executing it.
+
+#### Returns
+
+`Promise`&lt;`Schema`&lt;`any`&gt;&gt;
+
+An Arrow Schema describing the output columns.
+
+#### Inherited from
+
+[`QueryBase`](QueryBase.md).[`outputSchema`](QueryBase.md#outputschema)
+
+***
+
+### select()
+
+```ts
+select(columns): this
+```
+
+Return only the specified columns.
+
+By default a query will return all columns from the table.  However, this can have
+a very significant impact on latency.  LanceDb stores data in a columnar fashion.  This
+means we can finely tune our I/O to select exactly the columns we need.
+
+As a best practice you should always limit queries to the columns that you need.  If you
+pass in an array of column names then only those columns will be returned.
+
+You can also use this method to create new "dynamic" columns based on your existing columns.
+For example, you may not care about "a" or "b" but instead simply want "a + b".  This is often
+seen in the SELECT clause of an SQL query (e.g. `SELECT a+b FROM my_table`).
+
+To create dynamic columns you can pass in a Map<string, string>.  A column will be returned
+for each entry in the map.  The key provides the name of the column.  The value is
+an SQL string used to specify how the column is calculated.
+
+For example, an SQL query might state `SELECT a + b AS combined, c`.  The equivalent
+input to this method would be:
+
+#### Parameters
+
+* **columns**: `string` \| `string`[] \| `Record`&lt;`string`, `string`&gt; \| `Map`&lt;`string`, `string`&gt;
+
+#### Returns
+
+`this`
+
+#### Example
+
+```ts
+new Map([["combined", "a + b"], ["c", "c"]])
+
+Columns will always be returned in the order given, even if that order is different than
+the order used when adding the data.
+
+Note that you can pass in a `Record<string, string>` (e.g. an object literal). This method
+uses `Object.entries` which should preserve the insertion order of the object.  However,
+object insertion order is easy to get wrong and `Map` is more foolproof.
+```
+
+#### Inherited from
+
+[`QueryBase`](QueryBase.md).[`select`](QueryBase.md#select)
+
+***
+
+### toArray()
+
+```ts
+toArray(options?): Promise<any[]>
+```
+
+Collect the results as an array of objects.
+
+#### Parameters
+
+* **options?**: `Partial`&lt;[`QueryExecutionOptions`](../interfaces/QueryExecutionOptions.md)&gt;
+
+#### Returns
+
+`Promise`&lt;`any`[]&gt;
+
+#### Inherited from
+
+[`QueryBase`](QueryBase.md).[`toArray`](QueryBase.md#toarray)
+
+***
+
+### toArrow()
+
+```ts
+toArrow(options?): Promise<Table<any>>
+```
+
+Collect the results as an Arrow
+
+#### Parameters
+
+* **options?**: `Partial`&lt;[`QueryExecutionOptions`](../interfaces/QueryExecutionOptions.md)&gt;
+
+#### Returns
+
+`Promise`&lt;`Table`&lt;`any`&gt;&gt;
+
+#### See
+
+ArrowTable.
+
+#### Inherited from
+
+[`QueryBase`](QueryBase.md).[`toArrow`](QueryBase.md#toarrow)
+
+***
+
+### withRowId()
+
+```ts
+withRowId(): this
+```
+
+Whether to return the row id in the results.
+
+This column can be used to match results between different queries. For
+example, to match results from a full text search and a vector search in
+order to perform hybrid search.
+
+#### Returns
+
+`this`
+
+#### Inherited from
+
+[`QueryBase`](QueryBase.md).[`withRowId`](QueryBase.md#withrowid)

docs/src/js/classes/VectorQuery.md

@@ -16,7 +16,7 @@ This builder can be reused to execute the query many times.
 
 ## Extends
 
-- [`QueryBase`](QueryBase.md)<`NativeVectorQuery`>
+- `StandardQueryBase`<`NativeVectorQuery`>
 
 ## Properties
 
@@ -28,7 +28,7 @@ protected inner: VectorQuery | Promise<VectorQuery>;
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`inner`](QueryBase.md#inner)
+`StandardQueryBase.inner`
 
 ## Methods
 
@@ -91,7 +91,7 @@ AnalyzeExec verbose=true, metrics=[]
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`analyzePlan`](QueryBase.md#analyzeplan)
+`StandardQueryBase.analyzePlan`
 
 ***
 
@@ -221,7 +221,7 @@ also increase the latency of your query. The default value is 1.5*limit.
 ### execute()
 
 ```ts
-protected execute(options?): RecordBatchIterator
+protected execute(options?): AsyncGenerator<RecordBatch<any>, void, unknown>
 ```
 
 Execute the query and return the results as an
@@ -232,7 +232,7 @@ Execute the query and return the results as an
 
 #### Returns
 
-[`RecordBatchIterator`](RecordBatchIterator.md)
+`AsyncGenerator`&lt;`RecordBatch`&lt;`any`&gt;, `void`, `unknown`&gt;
 
 #### See
 
@@ -248,7 +248,7 @@ single query)
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`execute`](QueryBase.md#execute)
+`StandardQueryBase.execute`
 
 ***
 
@@ -284,7 +284,7 @@ const plan = await table.query().nearestTo([0.5, 0.2]).explainPlan();
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`explainPlan`](QueryBase.md#explainplan)
+`StandardQueryBase.explainPlan`
 
 ***
 
@@ -305,7 +305,7 @@ Use [Table#optimize](Table.md#optimize) to index all un-indexed data.
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`fastSearch`](QueryBase.md#fastsearch)
+`StandardQueryBase.fastSearch`
 
 ***
 
@@ -335,7 +335,7 @@ Use `where` instead
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`filter`](QueryBase.md#filter)
+`StandardQueryBase.filter`
 
 ***
 
@@ -357,7 +357,7 @@ fullTextSearch(query, options?): this
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`fullTextSearch`](QueryBase.md#fulltextsearch)
+`StandardQueryBase.fullTextSearch`
 
 ***
 
@@ -382,7 +382,7 @@ called then every valid row from the table will be returned.
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`limit`](QueryBase.md#limit)
+`StandardQueryBase.limit`
 
 ***
 
@@ -480,6 +480,10 @@ the minimum and maximum to the same value.
 offset(offset): this
 ```
 
+Set the number of rows to skip before returning results.
+
+This is useful for pagination.
+
 #### Parameters
 
 * **offset**: `number`
@@ -490,7 +494,30 @@ offset(offset): this
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`offset`](QueryBase.md#offset)
+`StandardQueryBase.offset`
+
+***
+
+### outputSchema()
+
+```ts
+outputSchema(): Promise<Schema<any>>
+```
+
+Returns the schema of the output that will be returned by this query.
+
+This can be used to inspect the types and names of the columns that will be
+returned by the query before executing it.
+
+#### Returns
+
+`Promise`&lt;`Schema`&lt;`any`&gt;&gt;
+
+An Arrow Schema describing the output columns.
+
+#### Inherited from
+
+`StandardQueryBase.outputSchema`
 
 ***
 
@@ -637,7 +664,7 @@ object insertion order is easy to get wrong and `Map` is more foolproof.
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`select`](QueryBase.md#select)
+`StandardQueryBase.select`
 
 ***
 
@@ -659,7 +686,7 @@ Collect the results as an array of objects.
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`toArray`](QueryBase.md#toarray)
+`StandardQueryBase.toArray`
 
 ***
 
@@ -685,7 +712,7 @@ ArrowTable.
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`toArrow`](QueryBase.md#toarrow)
+`StandardQueryBase.toArrow`
 
 ***
 
@@ -720,7 +747,7 @@ on the filter column(s).
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`where`](QueryBase.md#where)
+`StandardQueryBase.where`
 
 ***
 
@@ -742,4 +769,4 @@ order to perform hybrid search.
 
 #### Inherited from
 
-[`QueryBase`](QueryBase.md).[`withRowId`](QueryBase.md#withrowid)
+`StandardQueryBase.withRowId`

docs/src/js/functions/RecordBatchIterator.md

@@ -0,0 +1,19 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / RecordBatchIterator
+
+# Function: RecordBatchIterator()
+
+```ts
+function RecordBatchIterator(promisedInner): AsyncGenerator<RecordBatch<any>, void, unknown>
+```
+
+## Parameters
+
+* **promisedInner**: `Promise`&lt;`RecordBatchIterator`&gt;
+
+## Returns
+
+`AsyncGenerator`&lt;`RecordBatch`&lt;`any`&gt;, `void`, `unknown`&gt;

docs/src/js/functions/connect.md

@@ -6,13 +6,14 @@
 
 # Function: connect()
 
-## connect(uri, options, session)
+## connect(uri, options, session, headerProvider)
 
 ```ts
 function connect(
    uri,
    options?,
-   session?): Promise<Connection>
+   session?,
+   headerProvider?): Promise<Connection>
 ```
 
 Connect to a LanceDB instance at the given URI.
@@ -34,6 +35,8 @@ Accepted formats:
 
 * **session?**: [`Session`](../classes/Session.md)
 
+* **headerProvider?**: [`HeaderProvider`](../classes/HeaderProvider.md) \| () => `Record`&lt;`string`, `string`&gt; \| () => `Promise`&lt;`Record`&lt;`string`, `string`&gt;&gt;
+
 ### Returns
 
 `Promise`&lt;[`Connection`](../classes/Connection.md)&gt;
@@ -55,6 +58,18 @@ const conn = await connect(
 });
 ```
 
+Using with a header provider for per-request authentication:
+```ts
+const provider = new StaticHeaderProvider({
+  "X-API-Key": "my-key"
+});
+const conn = await connectWithHeaderProvider(
+  "db://host:port",
+  options,
+  provider
+);
+```
+
 ## connect(options)
 
 ```ts

docs/src/js/functions/makeArrowTable.md

@@ -13,7 +13,7 @@ function makeArrowTable(
    metadata?): ArrowTable
 ```
 
-An enhanced version of the makeTable function from Apache Arrow
+An enhanced version of the apache-arrow makeTable function from Apache Arrow
 that supports nested fields and embeddings columns.
 
 (typically you do not need to call this function.  It will be called automatically

docs/src/js/functions/permutationBuilder.md

@@ -0,0 +1,34 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / permutationBuilder
+
+# Function: permutationBuilder()
+
+```ts
+function permutationBuilder(table): PermutationBuilder
+```
+
+Create a permutation builder for the given table.
+
+## Parameters
+
+* **table**: [`Table`](../classes/Table.md)
+    The source table to create a permutation from
+
+## Returns
+
+[`PermutationBuilder`](../classes/PermutationBuilder.md)
+
+A PermutationBuilder instance
+
+## Example
+
+```ts
+const builder = permutationBuilder(sourceTable, "training_data")
+  .splitRandom({ ratios: [0.8, 0.2], seed: 42 })
+  .shuffle({ seed: 123 });
+
+const trainingTable = await builder.execute();
+```

docs/src/js/globals.md

@@ -20,19 +20,24 @@
 - [BooleanQuery](classes/BooleanQuery.md)
 - [BoostQuery](classes/BoostQuery.md)
 - [Connection](classes/Connection.md)
+- [HeaderProvider](classes/HeaderProvider.md)
 - [Index](classes/Index.md)
 - [MakeArrowTableOptions](classes/MakeArrowTableOptions.md)
 - [MatchQuery](classes/MatchQuery.md)
 - [MergeInsertBuilder](classes/MergeInsertBuilder.md)
 - [MultiMatchQuery](classes/MultiMatchQuery.md)
+- [NativeJsHeaderProvider](classes/NativeJsHeaderProvider.md)
+- [OAuthHeaderProvider](classes/OAuthHeaderProvider.md)
+- [PermutationBuilder](classes/PermutationBuilder.md)
 - [PhraseQuery](classes/PhraseQuery.md)
 - [Query](classes/Query.md)
 - [QueryBase](classes/QueryBase.md)
-- [RecordBatchIterator](classes/RecordBatchIterator.md)
 - [Session](classes/Session.md)
+- [StaticHeaderProvider](classes/StaticHeaderProvider.md)
 - [Table](classes/Table.md)
 - [TagContents](classes/TagContents.md)
 - [Tags](classes/Tags.md)
+- [TakeQuery](classes/TakeQuery.md)
 - [VectorColumnOptions](classes/VectorColumnOptions.md)
 - [VectorQuery](classes/VectorQuery.md)
 
@@ -63,6 +68,7 @@
 - [IndexStatistics](interfaces/IndexStatistics.md)
 - [IvfFlatOptions](interfaces/IvfFlatOptions.md)
 - [IvfPqOptions](interfaces/IvfPqOptions.md)
+- [IvfRqOptions](interfaces/IvfRqOptions.md)
 - [MergeResult](interfaces/MergeResult.md)
 - [OpenTableOptions](interfaces/OpenTableOptions.md)
 - [OptimizeOptions](interfaces/OptimizeOptions.md)
@@ -70,9 +76,15 @@
 - [QueryExecutionOptions](interfaces/QueryExecutionOptions.md)
 - [RemovalStats](interfaces/RemovalStats.md)
 - [RetryConfig](interfaces/RetryConfig.md)
+- [ShuffleOptions](interfaces/ShuffleOptions.md)
+- [SplitHashOptions](interfaces/SplitHashOptions.md)
+- [SplitRandomOptions](interfaces/SplitRandomOptions.md)
+- [SplitSequentialOptions](interfaces/SplitSequentialOptions.md)
 - [TableNamesOptions](interfaces/TableNamesOptions.md)
 - [TableStatistics](interfaces/TableStatistics.md)
 - [TimeoutConfig](interfaces/TimeoutConfig.md)
+- [TlsConfig](interfaces/TlsConfig.md)
+- [TokenResponse](interfaces/TokenResponse.md)
 - [UpdateOptions](interfaces/UpdateOptions.md)
 - [UpdateResult](interfaces/UpdateResult.md)
 - [Version](interfaces/Version.md)
@@ -92,6 +104,8 @@
 
 ## Functions
 
+- [RecordBatchIterator](functions/RecordBatchIterator.md)
 - [connect](functions/connect.md)
 - [makeArrowTable](functions/makeArrowTable.md)
 - [packBits](functions/packBits.md)
+- [permutationBuilder](functions/permutationBuilder.md)

docs/src/js/interfaces/ClientConfig.md

@@ -16,6 +16,14 @@ optional extraHeaders: Record<string, string>;
 
 ***
 
+### idDelimiter?
+
+```ts
+optional idDelimiter: string;
+```
+
+***
+
 ### retryConfig?
 
 ```ts
@@ -32,6 +40,14 @@ optional timeoutConfig: TimeoutConfig;
 
 ***
 
+### tlsConfig?
+
+```ts
+optional tlsConfig: TlsConfig;
+```
+
+***
+
 ### userAgent?
 
 ```ts

docs/src/js/interfaces/IndexOptions.md

@@ -26,6 +26,18 @@ will be used to determine the most useful kind of index to create.
 
 ***
 
+### name?
+
+```ts
+optional name: string;
+```
+
+Optional custom name for the index.
+
+If not provided, a default name will be generated based on the column name.
+
+***
+
 ### replace?
 
 ```ts
@@ -42,8 +54,27 @@ The default is true
 
 ***
 
+### train?
+
+```ts
+optional train: boolean;
+```
+
+Whether to train the index with existing data.
+
+If true (default), the index will be trained with existing data in the table.
+If false, the index will be created empty and populated as new data is added.
+
+Note: This option is only supported for scalar indices. Vector indices always train.
+
+***
+
 ### waitTimeoutSeconds?
 
 ```ts
 optional waitTimeoutSeconds: number;
 ```
+
+Timeout in seconds to wait for index creation to complete.
+
+If not specified, the method will return immediately after starting the index creation.

docs/src/js/interfaces/IvfRqOptions.md

@@ -0,0 +1,101 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / IvfRqOptions
+
+# Interface: IvfRqOptions
+
+## Properties
+
+### distanceType?
+
+```ts
+optional distanceType: "l2" | "cosine" | "dot";
+```
+
+Distance type to use to build the index.
+
+Default value is "l2".
+
+This is used when training the index to calculate the IVF partitions
+(vectors are grouped in partitions with similar vectors according to this
+distance type) and during quantization.
+
+The distance type used to train an index MUST match the distance type used
+to search the index. Failure to do so will yield inaccurate results.
+
+The following distance types are available:
+
+"l2" - Euclidean distance.
+"cosine" - Cosine distance.
+"dot" - Dot product.
+
+***
+
+### maxIterations?
+
+```ts
+optional maxIterations: number;
+```
+
+Max iterations to train IVF kmeans.
+
+When training an IVF index we use kmeans to calculate the partitions. This parameter
+controls how many iterations of kmeans to run.
+
+The default value is 50.
+
+***
+
+### numBits?
+
+```ts
+optional numBits: number;
+```
+
+Number of bits per dimension for residual quantization.
+
+This value controls how much each residual component is compressed. The more
+bits, the more accurate the index will be but the slower search. Typical values
+are small integers; the default is 1 bit per dimension.
+
+***
+
+### numPartitions?
+
+```ts
+optional numPartitions: number;
+```
+
+The number of IVF partitions to create.
+
+This value should generally scale with the number of rows in the dataset.
+By default the number of partitions is the square root of the number of
+rows.
+
+If this value is too large then the first part of the search (picking the
+right partition) will be slow. If this value is too small then the second
+part of the search (searching within a partition) will be slow.
+
+***
+
+### sampleRate?
+
+```ts
+optional sampleRate: number;
+```
+
+The number of vectors, per partition, to sample when training IVF kmeans.
+
+When an IVF index is trained, we need to calculate partitions. These are groups
+of vectors that are similar to each other. To do this we use an algorithm called kmeans.
+
+Running kmeans on a large dataset can be slow. To speed this up we run kmeans on a
+random sample of the data. This parameter controls the size of the sample. The total
+number of vectors used to train the index is `sample_rate * num_partitions`.
+
+Increasing this value might improve the quality of the index but in most cases the
+default should be sufficient.
+
+The default value is 256.

docs/src/js/interfaces/ShuffleOptions.md

@@ -0,0 +1,23 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / ShuffleOptions
+
+# Interface: ShuffleOptions
+
+## Properties
+
+### clumpSize?
+
+```ts
+optional clumpSize: number;
+```
+
+***
+
+### seed?
+
+```ts
+optional seed: number;
+```

docs/src/js/interfaces/SplitHashOptions.md

@@ -0,0 +1,31 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / SplitHashOptions
+
+# Interface: SplitHashOptions
+
+## Properties
+
+### columns
+
+```ts
+columns: string[];
+```
+
+***
+
+### discardWeight?
+
+```ts
+optional discardWeight: number;
+```
+
+***
+
+### splitWeights
+
+```ts
+splitWeights: number[];
+```

docs/src/js/interfaces/SplitRandomOptions.md

@@ -0,0 +1,39 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / SplitRandomOptions
+
+# Interface: SplitRandomOptions
+
+## Properties
+
+### counts?
+
+```ts
+optional counts: number[];
+```
+
+***
+
+### fixed?
+
+```ts
+optional fixed: number;
+```
+
+***
+
+### ratios?
+
+```ts
+optional ratios: number[];
+```
+
+***
+
+### seed?
+
+```ts
+optional seed: number;
+```

docs/src/js/interfaces/SplitSequentialOptions.md

@@ -0,0 +1,31 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / SplitSequentialOptions
+
+# Interface: SplitSequentialOptions
+
+## Properties
+
+### counts?
+
+```ts
+optional counts: number[];
+```
+
+***
+
+### fixed?
+
+```ts
+optional fixed: number;
+```
+
+***
+
+### ratios?
+
+```ts
+optional ratios: number[];
+```

docs/src/js/interfaces/TimeoutConfig.md

@@ -44,3 +44,17 @@ optional readTimeout: number;
 The timeout for reading data from the server in seconds. Default is 300
 seconds (5 minutes). This can also be set via the environment variable
 `LANCE_CLIENT_READ_TIMEOUT`, as an integer number of seconds.
+
+***
+
+### timeout?
+
+```ts
+optional timeout: number;
+```
+
+The overall timeout for the entire request in seconds. This includes
+connection, send, and read time. If the entire request doesn't complete
+within this time, it will fail. Default is None (no overall timeout).
+This can also be set via the environment variable `LANCE_CLIENT_TIMEOUT`,
+as an integer number of seconds.

docs/src/js/interfaces/TlsConfig.md

@@ -0,0 +1,49 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / TlsConfig
+
+# Interface: TlsConfig
+
+TLS/mTLS configuration for the remote HTTP client.
+
+## Properties
+
+### assertHostname?
+
+```ts
+optional assertHostname: boolean;
+```
+
+Whether to verify the hostname in the server's certificate.
+
+***
+
+### certFile?
+
+```ts
+optional certFile: string;
+```
+
+Path to the client certificate file (PEM format) for mTLS authentication.
+
+***
+
+### keyFile?
+
+```ts
+optional keyFile: string;
+```
+
+Path to the client private key file (PEM format) for mTLS authentication.
+
+***
+
+### sslCaCert?
+
+```ts
+optional sslCaCert: string;
+```
+
+Path to the CA certificate file (PEM format) for server verification.

docs/src/js/interfaces/TokenResponse.md

@@ -0,0 +1,25 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / TokenResponse
+
+# Interface: TokenResponse
+
+Token response from OAuth provider.
+
+## Properties
+
+### accessToken
+
+```ts
+accessToken: string;
+```
+
+***
+
+### expiresIn?
+
+```ts
+optional expiresIn: number;
+```

java/core/lancedb-jni/Cargo.toml

@@ -15,7 +15,7 @@ publish = false
 crate-type = ["cdylib"]
 
 [dependencies]
-lancedb = { path = "../../../rust/lancedb" }
+lancedb = { path = "../../../rust/lancedb", default-features = false }
 lance = { workspace = true }
 arrow = { workspace = true, features = ["ffi"] }
 arrow-schema.workspace = true
@@ -25,3 +25,6 @@ snafu.workspace = true
 lazy_static.workspace = true
 serde = { version = "^1" }
 serde_json = { version = "1" }
+
+[features]
+default = ["lancedb/default"]

java/core/lancedb-jni/src/ffi.rs

@@ -16,6 +16,7 @@ pub trait JNIEnvExt {
     fn get_integers(&mut self, obj: &JObject) -> Result<Vec<i32>>;
 
     /// Get strings from Java List<String> object.
+    #[allow(dead_code)]
     fn get_strings(&mut self, obj: &JObject) -> Result<Vec<String>>;
 
     /// Get strings from Java String[] object.

java/core/lancedb-jni/src/traits.rs

@@ -6,6 +6,7 @@ use jni::JNIEnv;
 
 use crate::Result;
 
+#[allow(dead_code)]
 pub trait FromJObject<T> {
     fn extract(&self) -> Result<T>;
 }
@@ -39,6 +40,7 @@ impl FromJObject<f64> for JObject<'_> {
     }
 }
 
+#[allow(dead_code)]
 pub trait FromJString {
     fn extract(&self, env: &mut JNIEnv) -> Result<String>;
 }
@@ -66,6 +68,7 @@ pub trait JMapExt {
     fn get_f64(&self, env: &mut JNIEnv, key: &str) -> Result<Option<f64>>;
 }
 
+#[allow(dead_code)]
 fn get_map_value<T>(env: &mut JNIEnv, map: &JMap, key: &str) -> Result<Option<T>>
 where
     for<'a> JObject<'a>: FromJObject<T>,

java/core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
         <groupId>com.lancedb</groupId>
         <artifactId>lancedb-parent</artifactId>
-        <version>0.21.2-beta.1</version>
+        <version>0.22.3-beta.4</version>
         <relativePath>../pom.xml</relativePath>
     </parent>
 

java/lance-namespace/pom.xml

@@ -8,7 +8,7 @@
     <parent>
         <groupId>com.lancedb</groupId>
         <artifactId>lancedb-parent</artifactId>
-        <version>0.21.2-beta.1</version>
+        <version>0.22.3-beta.4</version>
         <relativePath>../pom.xml</relativePath>
     </parent>
 

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.21.2-beta.1</version>
+    <version>0.22.3-beta.4</version>
     <packaging>pom</packaging>
     <name>${project.artifactId}</name>
     <description>LanceDB Java SDK Parent POM</description>

node/.eslintrc.js

@@ -1,22 +0,0 @@
-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

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

node/CHANGELOG.md

@@ -1,64 +0,0 @@
-# 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

@@ -1,66 +0,0 @@
-# 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

@@ -1,41 +0,0 @@
-// 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

@@ -1,15 +0,0 @@
-{
-  "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

@@ -1,66 +0,0 @@
-// 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

@@ -1,16 +0,0 @@
-{
-  "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

@@ -1,122 +0,0 @@
-// 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

@@ -1,15 +0,0 @@
-{
-  "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

@@ -1,36 +0,0 @@
-// 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

@@ -1,14 +0,0 @@
-{
-  "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

@@ -1,22 +0,0 @@
-{
-  "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

@@ -1,35 +0,0 @@
-// 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

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

node/native.js

@@ -1,36 +0,0 @@
-// 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

@@ -1,98 +0,0 @@
-{
-  "name": "vectordb",
-  "version": "0.21.2-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": "0.21.2-beta.1",
-    "@lancedb/vectordb-darwin-arm64": "0.21.2-beta.1",
-    "@lancedb/vectordb-linux-x64-gnu": "0.21.2-beta.1",
-    "@lancedb/vectordb-linux-arm64-gnu": "0.21.2-beta.1",
-    "@lancedb/vectordb-win32-x64-msvc": "0.21.2-beta.1"
-  }
-}

node/src/arrow.ts

@@ -1,635 +0,0 @@
-// 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

@@ -1,68 +0,0 @@
-// 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

@@ -1,57 +0,0 @@
-// 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

@@ -1,155 +0,0 @@
-// 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 = await fs.promises.mkdtemp(path.join(tmpdir(), 'lancedb-mirror-'))
-    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`)
-
-    const files = await fs.promises.readdir(mirroredPath, { withFileTypes: true })
-    // there should be three dirs
-    assert.equal(files.length, 3, 'files after table creation')
-    assert.isTrue(files[0].isDirectory())
-    assert.isTrue(files[1].isDirectory())
-
-    const transactionFiles = await fs.promises.readdir(path.join(mirroredPath, '_transactions'), { withFileTypes: true })
-    assert.equal(transactionFiles.length, 1, 'transactionFiles after table creation')
-    assert.isTrue(transactionFiles[0].name.endsWith('.txn'))
-
-    const versionFiles = await fs.promises.readdir(path.join(mirroredPath, '_versions'), { withFileTypes: true })
-    assert.equal(versionFiles.length, 1, 'versionFiles after table creation')
-    assert.isTrue(versionFiles[0].name.endsWith('.manifest'))
-
-    const dataFiles = await fs.promises.readdir(path.join(mirroredPath, 'data'), { withFileTypes: true })
-    assert.equal(dataFiles.length, 1, 'dataFiles after table creation')
-    assert.isTrue(dataFiles[0].name.endsWith('.lance'))
-
-    // try create index and check if it's mirrored
-    await t.createIndex({ column: 'vector', type: 'ivf_pq' })
-
-    const filesAfterIndex = await fs.promises.readdir(mirroredPath, { withFileTypes: true })
-    // there should be four dirs
-    assert.equal(filesAfterIndex.length, 4, 'filesAfterIndex')
-    assert.isTrue(filesAfterIndex[0].isDirectory())
-    assert.isTrue(filesAfterIndex[1].isDirectory())
-    assert.isTrue(filesAfterIndex[2].isDirectory())
-
-    // Two TXs now
-    const transactionFilesAfterIndex = await fs.promises.readdir(path.join(mirroredPath, '_transactions'), { withFileTypes: true })
-    assert.equal(transactionFilesAfterIndex.length, 2, 'transactionFilesAfterIndex')
-    assert.isTrue(transactionFilesAfterIndex[0].name.endsWith('.txn'))
-    assert.isTrue(transactionFilesAfterIndex[1].name.endsWith('.txn'))
-
-    const dataFilesAfterIndex = await fs.promises.readdir(path.join(mirroredPath, 'data'), { withFileTypes: true })
-    assert.equal(dataFilesAfterIndex.length, 1, 'dataFilesAfterIndex')
-    assert.isTrue(dataFilesAfterIndex[0].name.endsWith('.lance'))
-
-    const indicesFiles = await fs.promises.readdir(path.join(mirroredPath, '_indices'), { withFileTypes: true })
-    assert.equal(indicesFiles.length, 1, 'indicesFiles')
-    assert.isTrue(indicesFiles[0].isDirectory())
-
-    const indexFiles = await fs.promises.readdir(path.join(mirroredPath, '_indices', indicesFiles[0].name), { withFileTypes: true })
-    console.log(`DEBUG indexFiles in ${indicesFiles[0].name}:`, indexFiles.map(f => `${f.name} (${f.isFile() ? 'file' : 'dir'})`))
-    assert.equal(indexFiles.length, 2, 'indexFiles')
-    const fileNames = indexFiles.map(f => f.name).sort()
-    assert.isTrue(fileNames.includes('auxiliary.idx'), 'auxiliary.idx should be present')
-    assert.isTrue(fileNames.includes('index.idx'), 'index.idx should be present')
-    assert.isTrue(indexFiles.every(f => f.isFile()), 'all index files should be files')
-
-    // try delete and check if it's mirrored
-    await t.delete('id = 0')
-
-    const filesAfterDelete = await fs.promises.readdir(mirroredPath, { withFileTypes: true })
-    // there should be five dirs
-    assert.equal(filesAfterDelete.length, 5, 'filesAfterDelete')
-    assert.isTrue(filesAfterDelete[0].isDirectory())
-    assert.isTrue(filesAfterDelete[1].isDirectory())
-    assert.isTrue(filesAfterDelete[2].isDirectory())
-    assert.isTrue(filesAfterDelete[3].isDirectory())
-    assert.isTrue(filesAfterDelete[4].isDirectory())
-
-    // Three TXs now
-    const transactionFilesAfterDelete = await fs.promises.readdir(path.join(mirroredPath, '_transactions'), { withFileTypes: true })
-    assert.equal(transactionFilesAfterDelete.length, 3, 'transactionFilesAfterDelete')
-    assert.isTrue(transactionFilesAfterDelete[0].name.endsWith('.txn'))
-    assert.isTrue(transactionFilesAfterDelete[1].name.endsWith('.txn'))
-
-    const dataFilesAfterDelete = await fs.promises.readdir(path.join(mirroredPath, 'data'), { withFileTypes: true })
-    assert.equal(dataFilesAfterDelete.length, 1, 'dataFilesAfterDelete')
-    assert.isTrue(dataFilesAfterDelete[0].name.endsWith('.lance'))
-
-    const indicesFilesAfterDelete = await fs.promises.readdir(path.join(mirroredPath, '_indices'), { withFileTypes: true })
-    assert.equal(indicesFilesAfterDelete.length, 1, 'indicesFilesAfterDelete')
-    assert.isTrue(indicesFilesAfterDelete[0].isDirectory())
-
-    const indexFilesAfterDelete = await fs.promises.readdir(path.join(mirroredPath, '_indices', indicesFilesAfterDelete[0].name), { withFileTypes: true })
-    console.log(`DEBUG indexFilesAfterDelete in ${indicesFilesAfterDelete[0].name}:`, indexFilesAfterDelete.map(f => `${f.name} (${f.isFile() ? 'file' : 'dir'})`))
-    assert.equal(indexFilesAfterDelete.length, 2, 'indexFilesAfterDelete')
-    const fileNamesAfterDelete = indexFilesAfterDelete.map(f => f.name).sort()
-    assert.isTrue(fileNamesAfterDelete.includes('auxiliary.idx'), 'auxiliary.idx should be present after delete')
-    assert.isTrue(fileNamesAfterDelete.includes('index.idx'), 'index.idx should be present after delete')
-    assert.isTrue(indexFilesAfterDelete.every(f => f.isFile()), 'all index files should be files after delete')
-
-    const deletionFiles = await fs.promises.readdir(path.join(mirroredPath, '_deletions'), { withFileTypes: true })
-    assert.equal(deletionFiles.length, 1, 'deletionFiles')
-    assert.isTrue(deletionFiles[0].name.endsWith('.arrow'))
-  })
-})

node/src/middleware.ts

@@ -1,58 +0,0 @@
-// 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

@@ -1,163 +0,0 @@
-// 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
-    }
-  }
-}