Bump to 0.1.11

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.4.20
+current_version = 0.1.13
 commit = True
 message = Bump version: {current_version} → {new_version}
 tag = True
@@ -7,16 +7,6 @@ tag_name = v{new_version}
 
 [bumpversion:file:node/package.json]
 
-[bumpversion:file:nodejs/package.json]
-
-[bumpversion:file:nodejs/npm/darwin-x64/package.json]
-
-[bumpversion:file:nodejs/npm/darwin-arm64/package.json]
-
-[bumpversion:file:nodejs/npm/linux-x64-gnu/package.json]
-
-[bumpversion:file:nodejs/npm/linux-arm64-gnu/package.json]
-
 [bumpversion:file:rust/ffi/node/Cargo.toml]
 
-[bumpversion:file:rust/lancedb/Cargo.toml]
+[bumpversion:file:rust/vectordb/Cargo.toml]

.cargo/config.toml

@@ -1,40 +0,0 @@
-[profile.release]
-lto = "fat"
-codegen-units = 1
-
-[profile.release-with-debug]
-inherits = "release"
-debug = true
-# Prioritize compile time over runtime performance
-codegen-units = 16
-lto = "thin"
-
-[target.'cfg(all())']
-rustflags = [
-    "-Wclippy::all",
-    "-Wclippy::style",
-    "-Wclippy::fallible_impl_from",
-    "-Wclippy::manual_let_else",
-    "-Wclippy::redundant_pub_crate",
-    "-Wclippy::string_add_assign",
-    "-Wclippy::string_add",
-    "-Wclippy::string_lit_as_bytes",
-    "-Wclippy::string_to_string",
-    "-Wclippy::use_self",
-    "-Dclippy::cargo",
-    "-Dclippy::dbg_macro",
-    # not too much we can do to avoid multiple crate versions
-    "-Aclippy::multiple-crate-versions",
-    "-Aclippy::wildcard_dependencies",
-]
-
-[target.x86_64-unknown-linux-gnu]
-rustflags = ["-C", "target-cpu=haswell", "-C", "target-feature=+avx2,+fma,+f16c"]
-
-[target.aarch64-apple-darwin]
-rustflags = ["-C", "target-cpu=apple-m1", "-C", "target-feature=+neon,+fp16,+fhm,+dotprod"]
-
-# Not all Windows systems have the C runtime installed, so this avoids library
-# not found errors on systems that are missing it.
-[target.x86_64-pc-windows-msvc]
-rustflags = ["-Ctarget-feature=+crt-static"]

.github/ISSUE_TEMPLATE/bug-node.yml

@@ -1,33 +0,0 @@
-name: Bug Report - Node / Typescript
-description: File a bug report
-title: "bug(node): "
-labels: [bug, typescript]
-body:
-  - type: markdown
-    attributes:
-      value: |
-        Thanks for taking the time to fill out this bug report!
-  - type: input
-    id: version
-    attributes:
-      label: LanceDB version
-      description: What version of LanceDB are you using? `npm list | grep vectordb`.
-      placeholder: v0.3.2
-    validations:
-      required: false
-  - type: textarea
-    id: what-happened
-    attributes:
-      label: What happened?
-      description: Also tell us, what did you expect to happen?
-    validations:
-      required: true
-  - type: textarea
-    id: reproduction
-    attributes:
-      label: Are there known steps to reproduce?
-      description: |
-        Let us know how to reproduce the bug and we may be able to fix it more
-        quickly. This is not required, but it is helpful.
-    validations:
-      required: false

.github/ISSUE_TEMPLATE/bug-python.yml

@@ -1,33 +0,0 @@
-name: Bug Report - Python
-description: File a bug report
-title: "bug(python): "
-labels: [bug, python]
-body:
-  - type: markdown
-    attributes:
-      value: |
-        Thanks for taking the time to fill out this bug report!
-  - type: input
-    id: version
-    attributes:
-      label: LanceDB version
-      description: What version of LanceDB are you using? `python -c "import lancedb; print(lancedb.__version__)"`.
-      placeholder: v0.3.2
-    validations:
-      required: false
-  - type: textarea
-    id: what-happened
-    attributes:
-      label: What happened?
-      description: Also tell us, what did you expect to happen?
-    validations:
-      required: true
-  - type: textarea
-    id: reproduction
-    attributes:
-      label: Are there known steps to reproduce?
-      description: |
-        Let us know how to reproduce the bug and we may be able to fix it more
-        quickly. This is not required, but it is helpful.
-    validations:
-      required: false

.github/ISSUE_TEMPLATE/config.yml

@@ -1,5 +0,0 @@
-blank_issues_enabled: true
-contact_links:
-  - name: Discord Community Support
-    url: https://discord.com/invite/zMM32dvNtd
-    about: Please ask and answer questions here.

.github/ISSUE_TEMPLATE/documentation.yml

@@ -1,23 +0,0 @@
-name: 'Documentation improvement'
-description: Report an issue with the documentation.
-labels: [documentation]
-
-body:
-  - type: textarea
-    id: description
-    attributes:
-      label: Description
-      description: >
-        Describe the issue with the documentation and how it can be fixed or improved.
-    validations:
-      required: true
-
-  - type: input
-    id: link
-    attributes:
-      label: Link
-      description: >
-        Provide a link to the existing documentation, if applicable.
-      placeholder: ex. https://lancedb.github.io/lancedb/guides/tables/...
-    validations:
-      required: false

.github/ISSUE_TEMPLATE/feature.yml

@@ -1,31 +0,0 @@
-name: Feature suggestion
-description: Suggestion a new feature for LanceDB
-title: "Feature: "
-labels: [enhancement]
-body:
-  - type: markdown
-    attributes:
-      value: |
-        Share a new idea for a feature or improvement. Be sure to search existing
-        issues first to avoid duplicates.
-  - type: dropdown
-    id: sdk
-    attributes:
-      label: SDK
-      description: Which SDK are you using? This helps us prioritize.
-      options:
-        - Python
-        - Node
-        - Rust
-      default: 0
-    validations:
-      required: false
-  - type: textarea
-    id: description
-    attributes:
-      label: Description
-      description: |
-        Describe the feature and why it would be useful. If applicable, consider
-        providing a code example of what it might be like to use the feature.
-    validations:
-      required: true

.github/workflows/build_linux_wheel/action.yml

@@ -1,62 +0,0 @@
-# We create a composite action to be re-used both for testing and for releasing
-name: build-linux-wheel
-description: "Build a manylinux wheel for lance"
-inputs:
-  python-minor-version:
-    description: "8, 9, 10, 11, 12"
-    required: true
-  args:
-    description: "--release"
-    required: false
-    default: ""
-  arm-build:
-    description: "Build for arm64 instead of x86_64"
-    # Note: this does *not* mean the host is arm64, since we might be cross-compiling.
-    required: false
-    default: "false"
-  manylinux:
-    description: "The manylinux version to build for"
-    required: false
-    default: "2_17"
-runs:
-  using: "composite"
-  steps:
-    - name: CONFIRM ARM BUILD
-      shell: bash
-      run: |
-        echo "ARM BUILD: ${{ inputs.arm-build }}"
-    - name: Build x86_64 Manylinux wheel
-      if: ${{ inputs.arm-build == 'false' }}
-      uses: PyO3/maturin-action@v1
-      with:
-        command: build
-        working-directory: python
-        target: x86_64-unknown-linux-gnu
-        manylinux: ${{ inputs.manylinux }}
-        args: ${{ inputs.args }}
-        before-script-linux: |
-          set -e
-          yum install -y openssl-devel \
-            && curl -L https://github.com/protocolbuffers/protobuf/releases/download/v24.4/protoc-24.4-linux-$(uname -m).zip > /tmp/protoc.zip \
-            && unzip /tmp/protoc.zip -d /usr/local \
-            && rm /tmp/protoc.zip
-    - name: Build Arm Manylinux Wheel
-      if: ${{ inputs.arm-build == 'true' }}
-      uses: PyO3/maturin-action@v1
-      with:
-        command: build
-        working-directory: python
-        target: aarch64-unknown-linux-gnu
-        manylinux: ${{ inputs.manylinux }}
-        args: ${{ inputs.args }}
-        before-script-linux: |
-          set -e
-          apt install -y unzip
-          if [ $(uname -m) = "x86_64" ]; then
-            PROTOC_ARCH="x86_64"
-          else
-            PROTOC_ARCH="aarch_64"
-          fi
-          curl -L https://github.com/protocolbuffers/protobuf/releases/download/v24.4/protoc-24.4-linux-$PROTOC_ARCH.zip > /tmp/protoc.zip \
-            && unzip /tmp/protoc.zip -d /usr/local \
-            && rm /tmp/protoc.zip

.github/workflows/build_mac_wheel/action.yml

@@ -1,25 +0,0 @@
-# We create a composite action to be re-used both for testing and for releasing
-name: build_wheel
-description: "Build a lance wheel"
-inputs:
-  python-minor-version:
-    description: "8, 9, 10, 11"
-    required: true
-  args:
-    description: "--release"
-    required: false
-    default: ""
-runs:
-  using: "composite"
-  steps:
-    - name: Install macos dependency
-      shell: bash
-      run: |
-        brew install protobuf
-    - name: Build wheel
-      uses: PyO3/maturin-action@v1
-      with:
-        command: build
-        args: ${{ inputs.args }}
-        working-directory: python
-        interpreter: 3.${{ inputs.python-minor-version }}

.github/workflows/build_windows_wheel/action.yml

@@ -1,33 +0,0 @@
-# We create a composite action to be re-used both for testing and for releasing
-name: build_wheel
-description: "Build a lance wheel"
-inputs:
-  python-minor-version:
-    description: "8, 9, 10, 11"
-    required: true
-  args:
-    description: "--release"
-    required: false
-    default: ""
-runs:
-  using: "composite"
-  steps:
-    - 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: Build wheel
-      uses: PyO3/maturin-action@v1
-      with:
-        command: build
-        args: ${{ inputs.args }}
-        working-directory: python
-    - uses: actions/upload-artifact@v3
-      with:
-        name: windows-wheels
-        path: python\target\wheels

.github/workflows/cargo-publish.yml

@@ -8,9 +8,6 @@ env:
   # This env var is used by Swatinem/rust-cache@v2 for the cache
   # key, so we set it to make sure it is always consistent.
   CARGO_TERM_COLOR: always
-  # Up-to-date compilers needed for fp16kernels.
-  CC: gcc-12
-  CXX: g++-12
 
 jobs:
   build:
@@ -19,7 +16,7 @@ jobs:
     # Only runs on tags that matches the make-release action
     if: startsWith(github.ref, 'refs/tags/v')
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - uses: Swatinem/rust-cache@v2
         with:
           workspaces: rust
@@ -29,4 +26,4 @@ jobs:
           sudo apt install -y protobuf-compiler libssl-dev
       - name: Publish the package
         run: |
-          cargo publish -p lancedb --all-features --token ${{ secrets.CARGO_REGISTRY_TOKEN }}
+          cargo publish -p vectordb --all-features --token ${{ secrets.CARGO_REGISTRY_TOKEN }}

.github/workflows/docs.yml

@@ -24,16 +24,12 @@ jobs:
     environment:
       name: github-pages
       url: ${{ steps.deployment.outputs.page_url }}
-    runs-on: buildjet-8vcpu-ubuntu-2204
+    runs-on: ubuntu-22.04
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
-      - name: Install dependecies needed for ubuntu
-        run: |
-          sudo apt install -y protobuf-compiler libssl-dev
-          rustup update && rustup default        
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v4
         with:
           python-version: "3.10"
           cache: "pip"
@@ -46,7 +42,7 @@ jobs:
       - name: Set up node
         uses: actions/setup-node@v3
         with:
-          node-version: 20
+          node-version: ${{ matrix.node-version }}
           cache: 'npm'
           cache-dependency-path: node/package-lock.json
       - uses: Swatinem/rust-cache@v2
@@ -66,9 +62,8 @@ jobs:
         run: |
           npx typedoc --plugin typedoc-plugin-markdown --out ../docs/src/javascript src/index.ts
       - name: Build docs
-        working-directory: docs
         run: |
-          PYTHONPATH=. mkdocs build
+          PYTHONPATH=. mkdocs build -f docs/mkdocs.yml
       - name: Setup Pages
         uses: actions/configure-pages@v2
       - name: Upload artifact
@@ -77,4 +72,4 @@ jobs:
           path: "docs/site"
       - name: Deploy to GitHub Pages
         id: deployment
-        uses: actions/deploy-pages@v1
+        uses: actions/deploy-pages@v1

.github/workflows/docs_test.yml

@@ -18,30 +18,26 @@ on:
 env:
   # Disable full debug symbol generation to speed up CI build and keep memory down
   # "1" means line tables only, which is useful for panic tracebacks.
-  RUSTFLAGS: "-C debuginfo=1 -C target-cpu=haswell -C target-feature=+f16c,+avx2,+fma"
+  RUSTFLAGS: "-C debuginfo=1"
   RUST_BACKTRACE: "1"
 
 jobs:
   test-python:
     name: Test doc python code
-    runs-on: "buildjet-8vcpu-ubuntu-2204"
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        python-minor-version: [ "11" ]
+        os: ["ubuntu-22.04"]
     steps:
     - name: Checkout
-      uses: actions/checkout@v4
+      uses: actions/checkout@v3
-    - name: Print CPU capabilities
-      run: cat /proc/cpuinfo
-    - name: Install dependecies needed for ubuntu
-      run: |
-        sudo apt install -y protobuf-compiler libssl-dev
-        rustup update && rustup default
     - name: Set up Python
-      uses: actions/setup-python@v5
+      uses: actions/setup-python@v4
       with:
-        python-version: 3.11
+        python-version: 3.${{ matrix.python-minor-version }}
         cache: "pip"
         cache-dependency-path: "docs/test/requirements.txt"
-    - name: Rust cache
-      uses: swatinem/rust-cache@v2
     - name: Build Python
       working-directory: docs/test
       run:
@@ -56,45 +52,42 @@ jobs:
         for d in *; do cd "$d"; echo "$d".py; python "$d".py; cd ..; done
   test-node:
     name: Test doc nodejs code
-    runs-on: "buildjet-8vcpu-ubuntu-2204"
+    runs-on: ${{ matrix.os }}
-    timeout-minutes: 60
     strategy:
-      fail-fast: false
+      matrix:
+        node-version: [ "18" ]
+        os: ["ubuntu-22.04"]
     steps:
     - name: Checkout
-      uses: actions/checkout@v4
+      uses: actions/checkout@v3
       with:
         fetch-depth: 0
         lfs: true
-    - name: Print CPU capabilities
-      run: cat /proc/cpuinfo
     - name: Set up Node
-      uses: actions/setup-node@v4
+      uses: actions/setup-node@v3
       with:
-        node-version: 20
+        node-version: ${{ matrix.node-version }}
     - name: Install dependecies needed for ubuntu
+      if: ${{ matrix.os == 'ubuntu-22.04' }}
       run: |
         sudo apt install -y protobuf-compiler libssl-dev
-        rustup update && rustup default
-    - name: Rust cache
-      uses: swatinem/rust-cache@v2
     - name: Install node dependencies
       run: |
-        sudo swapoff -a
+        cd docs/test
-        sudo fallocate -l 8G /swapfile
+        npm install 
-        sudo chmod 600 /swapfile
+    - name: Rust cache
-        sudo mkswap /swapfile
+      uses: swatinem/rust-cache@v2
-        sudo swapon /swapfile
+    - name: Install LanceDB
-        sudo swapon --show
+      run: |
-        cd node
+        cd docs/test/node_modules/vectordb 
         npm ci
         npm run build-release
-        cd ../docs
+        npm run tsc
-        npm install
+    - name: Create test files
-    - name: Test
-      env:
-        LANCEDB_URI: ${{ secrets.LANCEDB_URI }}
-        LANCEDB_DEV_API_KEY: ${{ secrets.LANCEDB_DEV_API_KEY }}
       run: |
-        cd docs
+        cd docs/test
-        npm t
+        node md_testing.js
+    - name: Test
+      run: |
+        cd docs/test/node
+        for d in *; do cd "$d"; echo "$d".js; node "$d".js; cd ..; done

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

@@ -25,35 +25,31 @@ jobs:
   bump-version:
     runs-on: ubuntu-latest
     steps:
-      - name: Check out main
+    - name: Check out main
-        uses: actions/checkout@v4
+      uses: actions/checkout@v3
-        with:
+      with:
-          ref: main
+        ref: main
-          persist-credentials: false
+        persist-credentials: false
-          fetch-depth: 0
+        fetch-depth: 0
-          lfs: true
+        lfs: true
-      - name: Set git configs for bumpversion
+    - name: Set git configs for bumpversion
-        shell: bash
+      shell: bash
-        run: |
+      run: |
-          git config user.name 'Lance Release'
+        git config user.name 'Lance Release'
-          git config user.email 'lance-dev@lancedb.com'
+        git config user.email 'lance-dev@lancedb.com'
-      - name: Set up Python 3.11
+    - name: Set up Python 3.10
-        uses: actions/setup-python@v5
+      uses: actions/setup-python@v4
-        with:
+      with:
-          python-version: "3.11"
+        python-version: "3.10"
-      - name: Bump version, create tag and commit
+    - name: Bump version, create tag and commit
-        run: |
+      run: |
-          pip install bump2version
+        pip install bump2version
-          bumpversion --verbose ${{ inputs.part }}
+        bumpversion --verbose ${{ inputs.part }}
-      - name: Push new version and tag
+    - name: Push new version and tag
-        if: ${{ inputs.dry_run }} == "false"
+      if: ${{ inputs.dry_run }} == "false"
-        uses: ad-m/github-push-action@master
+      uses: ad-m/github-push-action@master
-        with:
+      with:
-          github_token: ${{ secrets.LANCEDB_RELEASE_TOKEN }}
+        github_token: ${{ secrets.LANCEDB_RELEASE_TOKEN }}
-          branch: main
+        branch: main
-          tags: true
+        tags: true
-      - uses: ./.github/workflows/update_package_lock
-        if: ${{ inputs.dry_run }} == "false"
-        with:
-          github_token: ${{ secrets.LANCEDB_RELEASE_TOKEN }}
 

.github/workflows/node.yml

@@ -9,35 +9,48 @@ on:
       - 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.
-  #
+  RUSTFLAGS: "-C debuginfo=1"
-  # 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:
+  lint:
+    name: Lint
+    runs-on: ubuntu-22.04
+    defaults:
+      run:
+        shell: bash
+        working-directory: node
+    steps:
+    - uses: actions/checkout@v3
+      with:
+        fetch-depth: 0
+        lfs: true
+    - uses: actions/setup-node@v3
+      with:
+        node-version: 18
+        cache: 'npm'
+        cache-dependency-path: node/package-lock.json
+    - name: Lint
+      run: |
+        npm ci
+        npm run lint
   linux:
     name: Linux (Node ${{ matrix.node-version }})
     timeout-minutes: 30
     strategy:
       matrix:
-        node-version: [ "18", "20" ]
+        node-version: [ "16", "18" ]
     runs-on: "ubuntu-22.04"
     defaults:
       run:
         shell: bash
         working-directory: node
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@v3
       with:
         fetch-depth: 0
         lfs: true
@@ -54,9 +67,10 @@ jobs:
     - name: Build
       run: |
         npm ci
+        npm run tsc
         npm run build
         npm run pack-build
-        npm install --no-save ./dist/lancedb-vectordb-*.tgz
+        npm install --no-save ./dist/vectordb-*.tgz
         # Remove index.node to test with dependency installed
         rm index.node
     - name: Test
@@ -69,13 +83,13 @@ jobs:
         shell: bash
         working-directory: node
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@v3
       with:
         fetch-depth: 0
         lfs: true
     - uses: actions/setup-node@v3
       with:
-        node-version: 20
+        node-version: 18
         cache: 'npm'
         cache-dependency-path: node/package-lock.json
     - uses: Swatinem/rust-cache@v2
@@ -84,64 +98,12 @@ jobs:
     - name: Build
       run: |
         npm ci
+        npm run tsc
         npm run build
         npm run pack-build
-        npm install --no-save ./dist/lancedb-vectordb-*.tgz
+        npm install --no-save ./dist/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

@@ -1,123 +0,0 @@
-name: NodeJS (NAPI)
-
-on:
-  push:
-    branches:
-      - main
-  pull_request:
-    paths:
-      - nodejs/**
-      - .github/workflows/nodejs.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.
-  RUSTFLAGS: "-C debuginfo=1"
-  RUST_BACKTRACE: "1"
-
-jobs:
-  lint:
-    name: Lint
-    runs-on: ubuntu-22.04
-    defaults:
-      run:
-        shell: bash
-        working-directory: nodejs
-    env:
-      # Need up-to-date compilers for kernels
-      CC: gcc-12
-      CXX: g++-12
-    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: nodejs/package-lock.json
-    - uses: Swatinem/rust-cache@v2
-    - name: Install dependencies
-      run: |
-        sudo apt update
-        sudo apt install -y protobuf-compiler libssl-dev
-    - name: Lint
-      run: |
-        cargo fmt --all -- --check
-        cargo clippy --all --all-features -- -D warnings
-        npm ci
-        npm run lint
-        npm run chkformat
-  linux:
-    name: Linux (NodeJS ${{ matrix.node-version }})
-    timeout-minutes: 30
-    strategy:
-      matrix:
-        node-version: [ "18", "20" ]
-    runs-on: "ubuntu-22.04"
-    defaults:
-      run:
-        shell: bash
-        working-directory: nodejs
-    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
-        npm install -g @napi-rs/cli
-    - name: Build
-      run: |
-        npm ci
-        npm run build
-    - name: Setup localstack
-      working-directory: .
-      run: docker compose up --detach --wait
-    - name: Test
-      env:
-        S3_TEST: "1"
-      run: npm run test
-  macos:
-    timeout-minutes: 30
-    runs-on: "macos-14"
-    defaults:
-      run:
-        shell: bash
-        working-directory: nodejs
-    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
-        npm install -g @napi-rs/cli
-    - name: Build
-      run: |
-        npm ci
-        npm run build
-    - name: Test
-      run: |
-        npm run test

.github/workflows/npm-publish.yml

@@ -2,7 +2,7 @@ name: NPM Publish
 
 on:
   release:
-    types: [published]
+    types: [ published ]
 
 jobs:
   node:
@@ -15,11 +15,11 @@ jobs:
         working-directory: node
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
       - uses: actions/setup-node@v3
         with:
           node-version: 20
-          cache: "npm"
+          cache: 'npm'
           cache-dependency-path: node/package-lock.json
       - name: Install dependencies
         run: |
@@ -31,163 +31,90 @@ jobs:
           npm run tsc
           npm pack
       - name: Upload Linux Artifacts
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v3
         with:
           name: node-package
           path: |
             node/vectordb-*.tgz
 
   node-macos:
-    strategy:
+    runs-on: macos-12
-      matrix:
-        config:
-          - arch: x86_64-apple-darwin
-            runner: macos-13
-          - arch: aarch64-apple-darwin
-            # xlarge is implicitly arm64.
-            runner: macos-14
-    runs-on: ${{ matrix.config.runner }}
     # Only runs on tags that matches the make-release action
     if: startsWith(github.ref, 'refs/tags/v')
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-      - name: Install system dependencies
-        run: brew install protobuf
-      - name: Install npm dependencies
-        run: |
-          cd 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
-
-  nodejs-macos:
     strategy:
+      fail-fast: false
       matrix:
-        config:
+        target: [x86_64-apple-darwin, aarch64-apple-darwin]
-          - arch: x86_64-apple-darwin
-            runner: macos-13
-          - arch: aarch64-apple-darwin
-            # xlarge is implicitly arm64.
-            runner: macos-14
-    runs-on: ${{ matrix.config.runner }}
-    # Only runs on tags that matches the make-release action
-    if: startsWith(github.ref, 'refs/tags/v')
     steps:
-      - name: Checkout
+    - name: Checkout
-        uses: actions/checkout@v4
+      uses: actions/checkout@v3
-      - name: Install system dependencies
+    - name: Install system dependencies
-        run: brew install protobuf
+      run: brew install protobuf
-      - name: Install npm dependencies
+    - name: Install npm dependencies
-        run: |
+      run: |
-          cd nodejs
+        cd node
-          npm ci
+        npm ci
-      - name: Build MacOS native nodejs modules
+    - name: Install rustup target
-        run: bash ci/build_macos_artifacts_nodejs.sh ${{ matrix.config.arch }}
+      if: ${{ matrix.target == 'aarch64-apple-darwin' }}
-      - name: Upload Darwin Artifacts
+      run: rustup target add aarch64-apple-darwin
-        uses: actions/upload-artifact@v4
+    - name: Build MacOS native node modules
-        with:
+      run: bash ci/build_macos_artifacts.sh ${{ matrix.target }}
-          name: nodejs-native-darwin-${{ matrix.config.arch }}
+    - name: Upload Darwin Artifacts
-          path: |
+      uses: actions/upload-artifact@v3
-            nodejs/dist/*.node
+      with:
+        name: darwin-native
+        path: |
+          node/dist/vectordb-darwin*.tgz
 
   node-linux:
-    name: node-linux (${{ matrix.config.arch}}-unknown-linux-gnu
+    name: node-linux (${{ matrix.arch}}-unknown-linux-${{ matrix.libc }})
-    runs-on: ${{ matrix.config.runner }}
+    runs-on: ubuntu-latest
     # Only runs on tags that matches the make-release action
     if: startsWith(github.ref, 'refs/tags/v')
     strategy:
       fail-fast: false
       matrix:
-        config:
+        libc:
-          - arch: x86_64
+          - gnu
-            runner: ubuntu-latest
+          # TODO: re-enable musl once we have refactored to pre-built containers
-          - arch: aarch64
+          # Right now we have to build node from source which is too expensive.
-            # For successful fat LTO builds, we need a large runner to avoid OOM errors.
+          # - musl
-            runner: buildjet-16vcpu-ubuntu-2204-arm
+        arch:
+          - x86_64
+          # Building on aarch64 is too slow for now
+          # - aarch64
     steps:
-      - name: Checkout
+    - name: Checkout
-        uses: actions/checkout@v4
+      uses: actions/checkout@v3
-      # Buildjet aarch64 runners have only 1.5 GB RAM per core, vs 3.5 GB per core for
+    - name: Change owner to root (for npm)
-      # x86_64 runners. To avoid OOM errors on ARM, we create a swap file.
+      # The docker container is run as root, so we need the files to be owned by root
-      - name: Configure aarch64 build
+      # Otherwise npm is a nightmare: https://github.com/npm/cli/issues/3773
-        if: ${{ matrix.config.arch == 'aarch64' }}
+      run: sudo chown -R root:root .
-        run: |
+    - name: Set up QEMU
-          free -h
+      if: ${{ matrix.arch == 'aarch64' }}
-          sudo fallocate -l 16G /swapfile
+      uses: docker/setup-qemu-action@v2
-          sudo chmod 600 /swapfile
+      with:
-          sudo mkswap /swapfile
+        platforms: arm64
-          sudo swapon /swapfile
+    - name: Build Linux GNU native node modules
-          echo "/swapfile swap swap defaults 0 0" >> sudo /etc/fstab
+      if: ${{ matrix.libc == 'gnu' }}
-          # print info
+      run: |
-          swapon --show
+        docker run \
-          free -h
+          -v $(pwd):/io -w /io \
-      - name: Build Linux Artifacts
+          rust:1.70-bookworm \
-        run: |
+          bash ci/build_linux_artifacts.sh ${{ matrix.arch }}-unknown-linux-gnu
-          bash ci/build_linux_artifacts.sh ${{ matrix.config.arch }}
+    - name: Build musl Linux native node modules
-      - name: Upload Linux Artifacts
+      if: ${{ matrix.libc == 'musl' }}
-        uses: actions/upload-artifact@v4
+      run: |
-        with:
+        docker run --platform linux/arm64/v8 \
-          name: node-native-linux-${{ matrix.config.arch }}
+          -v $(pwd):/io -w /io \
-          path: |
+          quay.io/pypa/musllinux_1_1_${{ matrix.arch }} \
-            node/dist/lancedb-vectordb-linux*.tgz
+          bash ci/build_linux_artifacts.sh ${{ matrix.arch }}-unknown-linux-musl
-
+    - name: Upload Linux Artifacts
-  nodejs-linux:
+      uses: actions/upload-artifact@v3
-    name: nodejs-linux (${{ matrix.config.arch}}-unknown-linux-gnu
+      with:
-    runs-on: ${{ matrix.config.runner }}
+        name: linux-native
-    # Only runs on tags that matches the make-release action
+        path: |
-    if: startsWith(github.ref, 'refs/tags/v')
+          node/dist/vectordb-linux*.tgz
-    strategy:
-      fail-fast: false
-      matrix:
-        config:
-          - arch: x86_64
-            runner: ubuntu-latest
-          - arch: aarch64
-            # For successful fat LTO builds, we need a large runner to avoid OOM errors.
-            runner: buildjet-16vcpu-ubuntu-2204-arm
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-      # Buildjet aarch64 runners have only 1.5 GB RAM per core, vs 3.5 GB per core for
-      # x86_64 runners. To avoid OOM errors on ARM, we create a swap file.
-      - name: Configure aarch64 build
-        if: ${{ matrix.config.arch == 'aarch64' }}
-        run: |
-          free -h
-          sudo fallocate -l 16G /swapfile
-          sudo chmod 600 /swapfile
-          sudo mkswap /swapfile
-          sudo swapon /swapfile
-          echo "/swapfile swap swap defaults 0 0" >> sudo /etc/fstab
-          # print info
-          swapon --show
-          free -h
-      - name: Build Linux Artifacts
-        run: |
-          bash ci/build_linux_artifacts_nodejs.sh ${{ matrix.config.arch }}
-      - name: Upload Linux Artifacts
-        uses: actions/upload-artifact@v4
-        with:
-          name: nodejs-native-linux-${{ matrix.config.arch }}
-          path: |
-            nodejs/dist/*.node
-      # The generic files are the same in all distros so we just pick
-      # one to do the upload.
-      - name: Upload Generic Artifacts
-        if: ${{ matrix.config.arch == 'x86_64' }}
-        uses: actions/upload-artifact@v4
-        with:
-          name: nodejs-dist
-          path: |
-            nodejs/dist/*
-            !nodejs/dist/*.node
 
   node-windows:
     runs-on: windows-2022
@@ -199,7 +126,7 @@ jobs:
         target: [x86_64-pc-windows-msvc]
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
       - name: Install Protoc v21.12
         working-directory: C:\
         run: |
@@ -216,60 +143,24 @@ jobs:
       - name: Build Windows native node modules
         run: .\ci\build_windows_artifacts.ps1 ${{ matrix.target }}
       - name: Upload Windows Artifacts
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v3
         with:
-          name: node-native-windows
+          name: windows-native
           path: |
-            node/dist/lancedb-vectordb-win32*.tgz
+            node/dist/vectordb-win32*.tgz
-
-  nodejs-windows:
-    runs-on: windows-2022
-    # Only runs on tags that matches the make-release action
-    if: startsWith(github.ref, 'refs/tags/v')
-    strategy:
-      fail-fast: false
-      matrix:
-        target: [x86_64-pc-windows-msvc]
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-      - name: Install Protoc v21.12
-        working-directory: C:\
-        run: |
-          New-Item -Path 'C:\protoc' -ItemType Directory
-          Set-Location C:\protoc
-          Invoke-WebRequest https://github.com/protocolbuffers/protobuf/releases/download/v21.12/protoc-21.12-win64.zip -OutFile C:\protoc\protoc.zip
-          7z x protoc.zip
-          Add-Content $env:GITHUB_PATH "C:\protoc\bin"
-        shell: powershell
-      - name: Install npm dependencies
-        run: |
-          cd nodejs
-          npm ci
-      - name: Build Windows native node modules
-        run: .\ci\build_windows_artifacts_nodejs.ps1 ${{ matrix.target }}
-      - name: Upload Windows Artifacts
-        uses: actions/upload-artifact@v4
-        with:
-          name: nodejs-native-windows
-          path: |
-            nodejs/dist/*.node
 
   release:
-    needs: [node, node-macos, node-linux, node-windows]
+    needs: [node, node-macos, node-linux]
     runs-on: ubuntu-latest
     # Only runs on tags that matches the make-release action
     if: startsWith(github.ref, 'refs/tags/v')
     steps:
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@v3
-        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 }}
@@ -278,72 +169,3 @@ jobs:
           for filename in *.tgz; do
             npm publish $filename
           done
-
-  release-nodejs:
-    needs: [nodejs-macos, nodejs-linux, nodejs-windows]
-    runs-on: ubuntu-latest
-    # Only runs on tags that matches the make-release action
-    if: startsWith(github.ref, 'refs/tags/v')
-    defaults:
-      run:
-        shell: bash
-        working-directory: nodejs
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-      - uses: actions/download-artifact@v4
-        with:
-          name: nodejs-dist
-          path: nodejs/dist
-      - uses: actions/download-artifact@v4
-        name: Download arch-specific binaries
-        with:
-          pattern: nodejs-*
-          path: nodejs/nodejs-artifacts
-          merge-multiple: true
-      - name: Display structure of downloaded files
-        run: find .
-      - uses: actions/setup-node@v3
-        with:
-          node-version: 20
-          registry-url: "https://registry.npmjs.org"
-      - name: Install napi-rs
-        run: npm install -g @napi-rs/cli
-      - name: Prepare artifacts
-        run: npx napi artifacts -d nodejs-artifacts
-      - name: Display structure of staged files
-        run: find npm
-      - name: Publish to NPM
-        env:
-          NODE_AUTH_TOKEN: ${{ secrets.LANCEDB_NPM_REGISTRY_TOKEN }}
-        run: npm publish --access public
-
-  update-package-lock:
-    needs: [release]
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-        with:
-          ref: main
-          persist-credentials: false
-          fetch-depth: 0
-          lfs: true
-      - uses: ./.github/workflows/update_package_lock
-        with:
-          github_token: ${{ secrets.LANCEDB_RELEASE_TOKEN }}
-
-  update-package-lock-nodejs:
-    needs: [release-nodejs]
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-        with:
-          ref: main
-          persist-credentials: false
-          fetch-depth: 0
-          lfs: true
-      - uses: ./.github/workflows/update_package_lock_nodejs
-        with:
-          github_token: ${{ secrets.LANCEDB_RELEASE_TOKEN }}

.github/workflows/pypi-publish.yml

@@ -2,108 +2,30 @@ name: PyPI Publish
 
 on:
   release:
-    types: [published]
+    types: [ published ]
 
 jobs:
-  linux:
+  publish:
+    runs-on: ubuntu-latest
     # Only runs on tags that matches the python-make-release action
     if: startsWith(github.ref, 'refs/tags/python-v')
-    name: Python ${{ matrix.config.platform }} manylinux${{ matrix.config.manylinux }}
+    defaults:
-    timeout-minutes: 60
+      run:
-    strategy:
+        shell: bash
-      matrix:
+        working-directory: python
-        python-minor-version: ["8"]
-        config:
-          - platform: x86_64
-            manylinux: "2_17"
-            extra_args: ""
-          - platform: x86_64
-            manylinux: "2_28"
-            extra_args: "--features fp16kernels"
-          - platform: aarch64
-            manylinux: "2_24"
-            extra_args: ""
-          # We don't build fp16 kernels for aarch64, because it uses 
-          # cross compilation image, which doesn't have a new enough compiler.
-    runs-on: "ubuntu-22.04"
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
-          lfs: true
       - name: Set up Python
         uses: actions/setup-python@v4
         with:
-          python-version: 3.${{ matrix.python-minor-version }}
+          python-version: "3.8"
-      - uses: ./.github/workflows/build_linux_wheel
+      - name: Build distribution
+        run: |
+          ls -la
+          pip install wheel setuptools --upgrade
+          python setup.py sdist bdist_wheel
+      - name: Publish
+        uses: pypa/gh-action-pypi-publish@v1.8.5
         with:
-          python-minor-version: ${{ matrix.python-minor-version }}
+          password: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
-          args: "--release --strip ${{ matrix.config.extra_args }}"
+          packages-dir: python/dist
-          arm-build: ${{ matrix.config.platform == 'aarch64' }}
-          manylinux: ${{ matrix.config.manylinux }}
-      - uses: ./.github/workflows/upload_wheel
-        with:
-          token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
-          repo: "pypi"
-  mac:
-    # Only runs on tags that matches the python-make-release action
-    if: startsWith(github.ref, 'refs/tags/python-v')
-    timeout-minutes: 60
-    runs-on: ${{ matrix.config.runner }}
-    strategy:
-      matrix:
-        python-minor-version: ["8"]
-        config:
-          - target: x86_64-apple-darwin
-            runner: macos-13
-          - target: aarch64-apple-darwin
-            runner: macos-14
-    env:
-      MACOSX_DEPLOYMENT_TARGET: 10.15
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          ref: ${{ inputs.ref }}
-          fetch-depth: 0
-          lfs: true
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: 3.12
-      - uses: ./.github/workflows/build_mac_wheel
-        with:
-          python-minor-version: ${{ matrix.python-minor-version }}
-          args: "--release --strip --target ${{ matrix.config.target }} --features fp16kernels"
-      - uses: ./.github/workflows/upload_wheel
-        with:
-          python-minor-version: ${{ matrix.python-minor-version }}
-          token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
-          repo: "pypi"
-  windows:
-    # Only runs on tags that matches the python-make-release action
-    if: startsWith(github.ref, 'refs/tags/python-v')
-    timeout-minutes: 60
-    runs-on: windows-latest
-    strategy:
-      matrix:
-        python-minor-version: ["8"]
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          ref: ${{ inputs.ref }}
-          fetch-depth: 0
-          lfs: true
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: 3.${{ matrix.python-minor-version }}
-      - uses: ./.github/workflows/build_windows_wheel
-        with:
-          python-minor-version: ${{ matrix.python-minor-version }}
-          args: "--release --strip"
-          vcpkg_token: ${{ secrets.VCPKG_GITHUB_PACKAGES }}
-      - uses: ./.github/workflows/upload_wheel
-        with:
-          python-minor-version: ${{ matrix.python-minor-version }}
-          token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
-          repo: "pypi"

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

@@ -26,7 +26,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
     - name: Check out main
-      uses: actions/checkout@v4
+      uses: actions/checkout@v3
       with:
         ref: main
         persist-credentials: false
@@ -37,10 +37,10 @@ jobs:
       run: |
         git config user.name 'Lance Release'
         git config user.email 'lance-dev@lancedb.com'
-    - name: Set up Python
+    - name: Set up Python 3.10
-      uses: actions/setup-python@v5
+      uses: actions/setup-python@v4
       with:
-        python-version: "3.11"
+        python-version: "3.10"
     - name: Bump version, create tag and commit
       working-directory: python
       run: |

.github/workflows/python.yml

@@ -8,188 +8,61 @@ on:
     paths:
       - python/**
       - .github/workflows/python.yml
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
 jobs:
-  lint:
-    name: "Lint"
-    timeout-minutes: 30
-    runs-on: "ubuntu-22.04"
-    defaults:
-      run:
-        shell: bash
-        working-directory: python
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-          lfs: true
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.11"
-      - name: Install ruff
-        run: |
-          pip install ruff==0.2.2
-      - name: Format check
-        run: ruff format --check .
-      - name: Lint
-        run: ruff .
-  doctest:
-    name: "Doctest"
-    timeout-minutes: 30
-    runs-on: "ubuntu-22.04"
-    defaults:
-      run:
-        shell: bash
-        working-directory: python
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-          lfs: true
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.11"
-          cache: "pip"
-      - name: Install protobuf
-        run: |
-          sudo apt update
-          sudo apt install -y protobuf-compiler
-      - uses: Swatinem/rust-cache@v2
-        with:
-          workspaces: python
-      - name: Install
-        run: |
-          pip install -e .[tests,dev,embeddings]
-          pip install tantivy
-          pip install mlx
-      - name: Doctest
-        run: pytest --doctest-modules python/lancedb
   linux:
-    name: "Linux: python-3.${{ matrix.python-minor-version }}"
     timeout-minutes: 30
     strategy:
       matrix:
-        python-minor-version: ["8", "11"]
+        python-minor-version: [ "8", "9", "10", "11" ]
     runs-on: "ubuntu-22.04"
     defaults:
       run:
         shell: bash
         working-directory: python
     steps:
-      - uses: actions/checkout@v4
+    - uses: actions/checkout@v3
-        with:
+      with:
-          fetch-depth: 0
+        fetch-depth: 0
-          lfs: true
+        lfs: true
-      - name: Install protobuf
+    - name: Set up Python
-        run: |
+      uses: actions/setup-python@v4
-          sudo apt update
+      with:
-          sudo apt install -y protobuf-compiler
+        python-version: 3.${{ matrix.python-minor-version }}
-      - name: Set up Python
+    - name: Install lancedb
-        uses: actions/setup-python@v5
+      run: |
-        with:
+        pip install -e .
-          python-version: 3.${{ matrix.python-minor-version }}
+        pip install tantivy@git+https://github.com/quickwit-oss/tantivy-py#164adc87e1a033117001cf70e38c82a53014d985
-      - uses: Swatinem/rust-cache@v2
+        pip install pytest pytest-mock black isort
-        with:
+    - name: Black
-          workspaces: python
+      run: black --check --diff --no-color --quiet .
-      - uses: ./.github/workflows/build_linux_wheel
+    - name: isort
-      - uses: ./.github/workflows/run_tests
+      run: isort --check --diff --quiet .
-        with:
+    - name: Run tests
-          integration: true
+      run: pytest -x -v --durations=30 tests
-      # Make sure wheels are not included in the Rust cache
+    - name: doctest
-      - name: Delete wheels
+      run: pytest --doctest-modules lancedb
-        run: rm -rf target/wheels
+  mac:
-  platform:
-    name: "Mac: ${{ matrix.config.name }}"
     timeout-minutes: 30
-    strategy:
+    runs-on: "macos-12"
-      matrix:
-        config:
-          - name: x86
-            runner: macos-13
-          - name: Arm
-            runner: macos-14
-    runs-on: "${{ matrix.config.runner }}"
     defaults:
       run:
         shell: bash
         working-directory: python
     steps:
-      - uses: actions/checkout@v4
+    - uses: actions/checkout@v3
-        with:
+      with:
-          fetch-depth: 0
+        fetch-depth: 0
-          lfs: true
+        lfs: true
-      - name: Set up Python
+    - name: Set up Python
-        uses: actions/setup-python@v5
+      uses: actions/setup-python@v4
-        with:
+      with:
-          python-version: "3.11"
+        python-version: "3.11"
-      - uses: Swatinem/rust-cache@v2
+    - name: Install lancedb
-        with:
+      run: |
-          workspaces: python
+        pip install -e .
-      - uses: ./.github/workflows/build_mac_wheel
+        pip install tantivy@git+https://github.com/quickwit-oss/tantivy-py#164adc87e1a033117001cf70e38c82a53014d985
-      - uses: ./.github/workflows/run_tests
+        pip install pytest pytest-mock black
-      # Make sure wheels are not included in the Rust cache
+    - name: Black
-      - name: Delete wheels
+      run: black --check --diff --no-color --quiet .
-        run: rm -rf target/wheels
+    - name: Run tests
-  windows:
+      run: pytest -x -v --durations=30 tests
-    name: "Windows: ${{ matrix.config.name }}"
-    timeout-minutes: 30
-    strategy:
-      matrix:
-        config:
-          - name: x86
-            runner: windows-latest
-    runs-on: "${{ matrix.config.runner }}"
-    defaults:
-      run:
-        shell: bash
-        working-directory: python
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-          lfs: true
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.11"
-      - uses: Swatinem/rust-cache@v2
-        with:
-          workspaces: python
-      - uses: ./.github/workflows/build_windows_wheel
-      - uses: ./.github/workflows/run_tests
-      # Make sure wheels are not included in the Rust cache
-      - name: Delete wheels
-        run: rm -rf target/wheels
-  pydantic1x:
-    timeout-minutes: 30
-    runs-on: "ubuntu-22.04"
-    defaults:
-      run:
-        shell: bash
-        working-directory: python
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-          lfs: true
-      - name: Install dependencies
-        run: |
-          sudo apt update
-          sudo apt install -y protobuf-compiler
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: 3.9
-      - name: Install lancedb
-        run: |
-          pip install "pydantic<2"
-          pip install -e .[tests]
-          pip install tantivy
-      - name: Run tests
-        run: pytest -m "not slow and not s3_test" -x -v --durations=30 python/tests

.github/workflows/run_tests/action.yml

@@ -1,31 +0,0 @@
-name: run-tests
-
-description: "Install lance wheel and run unit tests"
-inputs:
-  python-minor-version:
-    required: true
-    description: "8 9 10 11 12"
-  integration:
-    required: false
-    description: "Run integration tests"
-    default: "false"
-runs:
-  using: "composite"
-  steps:
-    - name: Install lancedb
-      shell: bash
-      run: |
-        pip3 install $(ls target/wheels/lancedb-*.whl)[tests,dev]
-    - name: Setup localstack for integration tests
-      if: ${{ inputs.integration == 'true' }}
-      shell: bash
-      working-directory: .
-      run: docker compose up --detach --wait
-    - name: pytest (with integration)
-      shell: bash
-      if: ${{ inputs.integration == 'true' }}
-      run: pytest -m "not slow" -x -v --durations=30 python/python/tests
-    - name: pytest (no integration tests)
-      shell: bash
-      if: ${{ inputs.integration != 'true' }}
-      run: pytest -m "not slow and not s3_test" -x -v --durations=30 python/python/tests

.github/workflows/rust.yml

@@ -10,10 +10,6 @@ on:
       - rust/**
       - .github/workflows/rust.yml
 
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
 env:
   # This env var is used by Swatinem/rust-cache@v2 for the cache
   # key, so we set it to make sure it is always consistent.
@@ -24,33 +20,6 @@ env:
   RUST_BACKTRACE: "1"
 
 jobs:
-  lint:
-    timeout-minutes: 30
-    runs-on: ubuntu-22.04
-    defaults:
-      run:
-        shell: bash
-        working-directory: rust
-    env:
-      # Need up-to-date compilers for kernels
-      CC: gcc-12
-      CXX: g++-12
-    steps:
-    - uses: actions/checkout@v4
-      with:
-          fetch-depth: 0
-          lfs: true
-    - uses: Swatinem/rust-cache@v2
-      with:
-        workspaces: rust
-    - name: Install dependencies
-      run: |
-          sudo apt update
-          sudo apt install -y protobuf-compiler libssl-dev
-    - name: Run format
-      run: cargo fmt --all -- --check
-    - name: Run clippy
-      run: cargo clippy --all --all-features -- -D warnings
   linux:
     timeout-minutes: 30
     runs-on: ubuntu-22.04
@@ -58,12 +27,8 @@ jobs:
       run:
         shell: bash
         working-directory: rust
-    env:
-      # Need up-to-date compilers for kernels
-      CC: gcc-12
-      CXX: g++-12
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@v3
       with:
           fetch-depth: 0
           lfs: true
@@ -76,25 +41,17 @@ jobs:
           sudo apt install -y protobuf-compiler libssl-dev
     - name: Build
       run: cargo build --all-features
-    - name: Start S3 integration test environment
-      working-directory: .
-      run: docker compose up --detach --wait
     - name: Run tests
       run: cargo test --all-features
-    - name: Run examples
-      run: cargo run --example simple
   macos:
+    runs-on: macos-12
     timeout-minutes: 30
-    strategy:
-      matrix:
-        mac-runner: [ "macos-13", "macos-14" ]
-    runs-on: "${{ matrix.mac-runner }}"
     defaults:
       run:
         shell: bash
         working-directory: rust
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
         with:
             fetch-depth: 0
             lfs: true
@@ -108,12 +65,11 @@ jobs:
       - name: Build
         run: cargo build --all-features
       - name: Run tests
-        # Run with everything except the integration tests.
+        run: cargo test --all-features
-        run: cargo test --features remote,fp16kernels
   windows:
     runs-on: windows-2022
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - uses: Swatinem/rust-cache@v2
         with:
           workspaces: rust
@@ -131,4 +87,3 @@ jobs:
           $env:VCPKG_ROOT = $env:VCPKG_INSTALLATION_ROOT
           cargo build
           cargo test
-  

.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);

.github/workflows/update_package_lock/action.yml

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

.github/workflows/update_package_lock_nodejs/action.yml

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

.github/workflows/update_package_lock_run.yml

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

.github/workflows/update_package_lock_run_nodejs.yml

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

.github/workflows/upload_wheel/action.yml

@@ -1,29 +0,0 @@
-name: upload-wheel
-
-description: "Upload wheels to Pypi"
-inputs:
-  os:
-    required: true
-    description: "ubuntu-22.04 or macos-13"
-  repo:
-    required: false
-    description: "pypi or testpypi"
-    default: "pypi"
-  token:
-    required: true
-    description: "release token for the repo"
-
-runs:
-  using: "composite"
-  steps:
-    - name: Install dependencies
-      shell: bash
-      run: |
-        python -m pip install --upgrade pip
-        pip install twine
-    - name: Publish wheel
-      env:
-        TWINE_USERNAME: __token__
-        TWINE_PASSWORD: ${{ inputs.token }}
-      shell: bash
-      run: twine upload --repository ${{ inputs.repo }} target/wheels/lancedb-*.whl

.gitignore

@@ -6,7 +6,7 @@
 venv
 
 .vscode
-.zed
+
 rust/target
 rust/Cargo.lock
 
@@ -22,11 +22,6 @@ python/dist
 
 **/.hypothesis
 
-# Compiled Dynamic libraries
-*.so
-*.dylib
-*.dll
-
 ## Javascript
 *.node
 **/node_modules
@@ -34,12 +29,8 @@ python/dist
 node/dist
 node/examples/**/package-lock.json
 node/examples/**/dist
-nodejs/lancedb/native*
-dist
 
 ## Rust
 target
 
-**/sccache.log
+Cargo.lock
-
-Cargo.lock

.pre-commit-config.yaml

@@ -5,14 +5,17 @@ repos:
     -   id: check-yaml
     -   id: end-of-file-fixer
     -   id: trailing-whitespace
+-   repo: https://github.com/psf/black
+    rev: 22.12.0
+    hooks:
+    -   id: black
 -   repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: v0.2.2
+    rev: v0.0.277
     hooks:
     - id: ruff
-- repo: https://github.com/pre-commit/mirrors-prettier
+-   repo: https://github.com/pycqa/isort
-  rev: v3.1.0
+    rev: 5.12.0
-  hooks:
+    hooks:
-    - id: prettier
+    - id: isort
-      files: "nodejs/.*"
+      name: isort (python)
-      exclude: nodejs/lancedb/native.d.ts|nodejs/dist/.*

Cargo.toml

@@ -1,43 +1,16 @@
 [workspace]
-members = ["rust/ffi/node", "rust/lancedb", "nodejs", "python"]
+members = [
-# Python package needs to be built by maturin.
+    "rust/vectordb",
-exclude = ["python"]
+    "rust/ffi/node"
+]
 resolver = "2"
 
-[workspace.package]
-edition = "2021"
-authors = ["LanceDB Devs <dev@lancedb.com>"]
-license = "Apache-2.0"
-repository = "https://github.com/lancedb/lancedb"
-description = "Serverless, low-latency vector database for AI applications"
-keywords = ["lancedb", "lance", "database", "vector", "search"]
-categories = ["database-implementations"]
-
 [workspace.dependencies]
-lance = { "version" = "=0.10.18", "features" = ["dynamodb"] }
+lance = "=0.5.8"
-lance-index = { "version" = "=0.10.18" }
+arrow-array = "42.0"
-lance-linalg = { "version" = "=0.10.18" }
+arrow-data = "42.0"
-lance-testing = { "version" = "=0.10.18" }
+arrow-schema = "42.0"
-# Note that this one does not include pyarrow
+arrow-ipc = "42.0"
-arrow = { version = "51.0", optional = false }
+half = { "version" = "2.2.1", default-features = false }
-arrow-array = "51.0"
+object_store = "0.6.1"
-arrow-data = "51.0"
+
-arrow-ipc = "51.0"
-arrow-ord = "51.0"
-arrow-schema = "51.0"
-arrow-arith = "51.0"
-arrow-cast = "51.0"
-async-trait = "0"
-chrono = "0.4.35"
-half = { "version" = "=2.4.1", default-features = false, features = [
-    "num-traits",
-] }
-futures = "0"
-log = "0.4"
-object_store = "0.9.0"
-pin-project = "1.0.7"
-snafu = "0.7.4"
-url = "2"
-num-traits = "0.2"
-regex = "1.10"
-lazy_static = "1"

README.md

@@ -1,87 +1,78 @@
-<div align="center">
+<div align="center">
-<p align="center">
+<p align="center">
-
+
-<img width="275" alt="LanceDB Logo" src="https://github.com/lancedb/lancedb/assets/5846846/37d7c7ad-c2fd-4f56-9f16-fffb0d17c73a">
+<img width="275" alt="LanceDB Logo" src="https://user-images.githubusercontent.com/917119/226205734-6063d87a-1ecc-45fe-85be-1dea6383a3d8.png">
-
+
-**Developer-friendly, database for multimodal AI**
+**Developer-friendly, serverless vector database for AI applications**
-
+
-<a href='https://github.com/lancedb/vectordb-recipes/tree/main' target="_blank"><img alt='LanceDB' src='https://img.shields.io/badge/VectorDB_Recipes-100000?style=for-the-badge&logo=LanceDB&logoColor=white&labelColor=645cfb&color=645cfb'/></a>
+<a href="https://lancedb.github.io/lancedb/">Documentation</a> •
-<a href='https://lancedb.github.io/lancedb/' target="_blank"><img alt='lancdb' src='https://img.shields.io/badge/DOCS-100000?style=for-the-badge&logo=lancdb&logoColor=white&labelColor=645cfb&color=645cfb'/></a>
+<a href="https://blog.lancedb.com/">Blog</a> •
-[![Blog](https://img.shields.io/badge/Blog-12100E?style=for-the-badge&logoColor=white)](https://blog.lancedb.com/) 
+<a href="https://discord.gg/zMM32dvNtd">Discord</a> •
-[![Discord](https://img.shields.io/badge/Discord-%235865F2.svg?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/zMM32dvNtd) 
+<a href="https://twitter.com/lancedb">Twitter</a>
-[![Twitter](https://img.shields.io/badge/Twitter-%231DA1F2.svg?style=for-the-badge&logo=Twitter&logoColor=white)](https://twitter.com/lancedb)
+
-
+</p>
-</p>
+
-
+<img max-width="750px" alt="LanceDB Multimodal Search" src="https://github.com/lancedb/lancedb/assets/917119/09c5afc5-7816-4687-bae4-f2ca194426ec">
-<img max-width="750px" alt="LanceDB Multimodal Search" src="https://github.com/lancedb/lancedb/assets/917119/09c5afc5-7816-4687-bae4-f2ca194426ec">
+
-
+</p>
-</p>
+</div>
-</div>
+
-
+<hr />
-<hr />
+
-
+LanceDB is an open-source database for vector-search built with persistent storage, which greatly simplifies retrevial, filtering and management of embeddings.
-LanceDB is an open-source database for vector-search built with persistent storage, which greatly simplifies retrieval, filtering and management of embeddings.
+
-
+The key features of LanceDB include:
-The key features of LanceDB include:
+
-
+* Production-scale vector search with no servers to manage.
-* Production-scale vector search with no servers to manage.
+
-
+* Store, query and filter vectors, metadata and multi-modal data (text, images, videos, point clouds, and more).
-* Store, query and filter vectors, metadata and multi-modal data (text, images, videos, point clouds, and more).
+
-
+* Support for vector similarity search, full-text search and SQL.
-* Support for vector similarity search, full-text search and SQL.
+
-
+* Native Python and Javascript/Typescript support.
-* Native Python and Javascript/Typescript support.
+
-
+* Zero-copy, automatic versioning, manage versions of your data without needing extra infrastructure.
-* Zero-copy, automatic versioning, manage versions of your data without needing extra infrastructure.
+
-
+* Ecosystem integrations with [LangChain 🦜️🔗](https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/lanecdb.html), [LlamaIndex 🦙](https://gpt-index.readthedocs.io/en/latest/examples/vector_stores/LanceDBIndexDemo.html), Apache-Arrow, Pandas, Polars, DuckDB and more on the way.
-* GPU support in building vector index(*).
+
-
+LanceDB's core is written in Rust 🦀 and is built using <a href="https://github.com/lancedb/lance">Lance</a>, an open-source columnar format designed for performant ML workloads.
-* Ecosystem integrations with [LangChain 🦜️🔗](https://python.langchain.com/docs/integrations/vectorstores/lancedb/), [LlamaIndex 🦙](https://gpt-index.readthedocs.io/en/latest/examples/vector_stores/LanceDBIndexDemo.html), Apache-Arrow, Pandas, Polars, DuckDB and more on the way.
+
-
+## Quick Start
-LanceDB's core is written in Rust 🦀 and is built using <a href="https://github.com/lancedb/lance">Lance</a>, an open-source columnar format designed for performant ML workloads.
+
-
+**Javascript**
-## Quick Start
+```shell
-
+npm install vectordb
-**Javascript**
+```
-```shell
+
-npm install vectordb
+```javascript
-```
+const lancedb = require('vectordb');
-
+const db = await lancedb.connect('data/sample-lancedb');
-```javascript
+
-const lancedb = require('vectordb');
+const table = await db.createTable('vectors', 
-const db = await lancedb.connect('data/sample-lancedb');
+      [{ id: 1, vector: [0.1, 0.2], item: "foo", price: 10 },
-
+       { id: 2, vector: [1.1, 1.2], item: "bar", price: 50 }])
-const table = await db.createTable({
+
-  name: 'vectors',
+const query = table.search([0.1, 0.3]);
-  data:  [
+query.limit = 20;
-    { id: 1, vector: [0.1, 0.2], item: "foo", price: 10 },
+const results = await query.execute();
-    { id: 2, vector: [1.1, 1.2], item: "bar", price: 50 }
+```
-  ]
+
-})
+**Python**
-
+```shell
-const query = table.search([0.1, 0.3]).limit(2);
+pip install lancedb
-const results = await query.execute();
+```
-
+
-// You can also search for rows by specific criteria without involving a vector search.
+```python
-const rowsByCriteria = await table.search(undefined).where("price >= 10").execute();
+import lancedb
-```
+
-
+uri = "data/sample-lancedb"
-**Python**
+db = lancedb.connect(uri)
-```shell
+table = db.create_table("my_table",
-pip install lancedb
+                         data=[{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
-```
+                               {"vector": [5.9, 26.5], "item": "bar", "price": 20.0}])
-
+result = table.search([100, 100]).limit(2).to_df()
-```python
+```
-import lancedb
+
-
+## Blogs, Tutorials & Videos
-uri = "data/sample-lancedb"
+* 📈 <a href="https://blog.eto.ai/benchmarking-random-access-in-lance-ed690757a826">2000x better performance with Lance over Parquet</a>
-db = lancedb.connect(uri)
+* 🤖 <a href="https://github.com/lancedb/lancedb/blob/main/docs/src/notebooks/youtube_transcript_search.ipynb">Build a question and answer bot with LanceDB</a>
-table = db.create_table("my_table",
-                         data=[{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
-                               {"vector": [5.9, 26.5], "item": "bar", "price": 20.0}])
-result = table.search([100, 100]).limit(2).to_pandas()
-```
-
-## Blogs, Tutorials & Videos
-* 📈 <a href="https://blog.eto.ai/benchmarking-random-access-in-lance-ed690757a826">2000x better performance with Lance over Parquet</a>
-* 🤖 <a href="https://github.com/lancedb/lancedb/blob/main/docs/src/notebooks/youtube_transcript_search.ipynb">Build a question and answer bot with LanceDB</a>

ci/build_linux_artifacts.sh

@@ -1,21 +1,72 @@
 #!/bin/bash
+# Builds the Linux artifacts (node binaries).
+# Usage: ./build_linux_artifacts.sh [target]
+# Targets supported: 
+# - x86_64-unknown-linux-gnu:centos
+# - aarch64-unknown-linux-gnu:centos
+# - aarch64-unknown-linux-musl
+# - x86_64-unknown-linux-musl
+
+# TODO: refactor this into a Docker container we can pull
+
 set -e
-ARCH=${1:-x86_64}
 
-# We pass down the current user so that when we later mount the local files 
+setup_dependencies() {
-# into the container, the files are accessible by the current user.
+    echo "Installing system dependencies..."
-pushd ci/manylinux_node
+    if [[ $1 == *musl ]]; then
-docker build \
+        # musllinux
-    -t lancedb-node-manylinux \
+        apk add openssl-dev
-    --build-arg="ARCH=$ARCH" \
+    else
-    --build-arg="DOCKER_USER=$(id -u)" \
+        # rust / debian
-    --progress=plain \
+        apt update
-    .
+        apt install -y libssl-dev protobuf-compiler
-popd
+    fi
+}
 
-# We turn on memory swap to avoid OOM killer
+install_node() {
-docker run \
+    echo "Installing node..."
-    -v $(pwd):/io -w /io \
+    curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.34.0/install.sh | bash
-    --memory-swap=-1 \
+    source "$HOME"/.bashrc
-    lancedb-node-manylinux \
+
-    bash ci/manylinux_node/build.sh $ARCH
+    if [[ $1 == *musl ]]; then
+        # This node version is 15, we need 16 or higher:
+        # apk add nodejs-current npm 
+        # So instead we install from source (nvm doesn't provide binaries for musl):
+        nvm install -s --no-progress 17
+    else
+        nvm install --no-progress 17 # latest that supports glibc 2.17
+    fi
+}
+
+build_node_binary() {
+    echo "Building node library for $1..."
+    pushd node
+
+    npm ci
+    
+    if [[ $1 == *musl ]]; then
+        # This is needed for cargo to allow build cdylibs with musl
+        export RUSTFLAGS="-C target-feature=-crt-static"
+    fi
+
+    # Cargo can run out of memory while pulling dependencies, especially when running
+    # in QEMU. This is a workaround for that.
+    export CARGO_NET_GIT_FETCH_WITH_CLI=true
+
+    # We don't pass in target, since the native target here already matches
+    # We need to pass OPENSSL_LIB_DIR and OPENSSL_INCLUDE_DIR for static build to work https://github.com/sfackler/rust-openssl/issues/877
+    OPENSSL_STATIC=1 OPENSSL_LIB_DIR=/usr/lib/x86_64-linux-gnu OPENSSL_INCLUDE_DIR=/usr/include/openssl/ npm run build-release
+    npm run pack-build
+
+    popd
+}
+
+TARGET=${1:-x86_64-unknown-linux-gnu}
+# Others:
+# aarch64-unknown-linux-gnu
+# x86_64-unknown-linux-musl
+# aarch64-unknown-linux-musl
+
+setup_dependencies $TARGET
+install_node $TARGET
+build_node_binary $TARGET

ci/build_linux_artifacts_nodejs.sh

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

ci/build_macos_artifacts.sh

@@ -1,7 +1,6 @@
 # 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.

ci/build_macos_artifacts_nodejs.sh

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

ci/build_windows_artifacts_nodejs.ps1

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

ci/manylinux_node/Dockerfile

@@ -1,31 +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/manylinux2014_${ARCH}
-
-ARG ARCH=x86_64
-ARG DOCKER_USER=default_user
-
-# Install static openssl
-COPY install_openssl.sh install_openssl.sh
-RUN ./install_openssl.sh ${ARCH} > /dev/null
-
-# Protobuf is also installed as root.
-COPY install_protobuf.sh install_protobuf.sh
-RUN ./install_protobuf.sh ${ARCH}
-
-ENV DOCKER_USER=${DOCKER_USER}
-# Create a group and user
-RUN echo ${ARCH} && adduser --user-group --create-home --uid ${DOCKER_USER} build_user
-
-# We switch to the user to install Rust and Node, since those like to be 
-# installed at the user level.
-USER ${DOCKER_USER}
-
-COPY prepare_manylinux_node.sh prepare_manylinux_node.sh
-RUN cp /prepare_manylinux_node.sh $HOME/ && \
-    cd $HOME && \
-    ./prepare_manylinux_node.sh ${ARCH}

ci/manylinux_node/build.sh

@@ -1,19 +0,0 @@
-#!/bin/bash
-# Builds the node module for manylinux. Invoked by ci/build_linux_artifacts.sh.
-set -e
-ARCH=${1:-x86_64}
-
-if [ "$ARCH" = "x86_64" ]; then
-    export OPENSSL_LIB_DIR=/usr/local/lib64/
-else 
-    export OPENSSL_LIB_DIR=/usr/local/lib/
-fi
-export OPENSSL_STATIC=1
-export OPENSSL_INCLUDE_DIR=/usr/local/include/openssl
-
-source $HOME/.bashrc
-
-cd node
-npm ci
-npm run build-release
-npm run pack-build

ci/manylinux_node/install_openssl.sh

@@ -1,26 +0,0 @@
-#!/bin/bash
-# Builds openssl from source so we can statically link to it
-
-# this is to avoid the error we get with the system installation:
-# /usr/bin/ld: <library>: version node not found for symbol SSLeay@@OPENSSL_1.0.1
-# /usr/bin/ld: failed to set dynamic section sizes: Bad value
-set -e
-
-git clone -b OpenSSL_1_1_1u \
-    --single-branch \
-    https://github.com/openssl/openssl.git
-
-pushd openssl
-
-if [[ $1 == x86_64* ]]; then
-    ARCH=linux-x86_64
-else
-    # gnu target
-    ARCH=linux-aarch64
-fi
-
-./Configure no-shared $ARCH
-
-make
-
-make install

ci/manylinux_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 "$HOME"/.bashrc
-
-    nvm install --no-progress 16
-}
-
-install_rust() {
-    echo "Installing rust..."
-    curl https://sh.rustup.rs -sSf | bash -s -- -y
-    export PATH="$PATH:/root/.cargo/bin"
-}
-
-install_node
-install_rust

ci/manylinux_nodejs/Dockerfile

@@ -1,31 +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/manylinux2014_${ARCH}
-
-ARG ARCH=x86_64
-ARG DOCKER_USER=default_user
-
-# Install static openssl
-COPY install_openssl.sh install_openssl.sh
-RUN ./install_openssl.sh ${ARCH} > /dev/null
-
-# Protobuf is also installed as root.
-COPY install_protobuf.sh install_protobuf.sh
-RUN ./install_protobuf.sh ${ARCH}
-
-ENV DOCKER_USER=${DOCKER_USER}
-# Create a group and user
-RUN echo ${ARCH} && adduser --user-group --create-home --uid ${DOCKER_USER} build_user
-
-# We switch to the user to install Rust and Node, since those like to be
-# installed at the user level.
-USER ${DOCKER_USER}
-
-COPY prepare_manylinux_node.sh prepare_manylinux_node.sh
-RUN cp /prepare_manylinux_node.sh $HOME/ && \
-    cd $HOME && \
-    ./prepare_manylinux_node.sh ${ARCH}

ci/manylinux_nodejs/build.sh

@@ -1,18 +0,0 @@
-#!/bin/bash
-# Builds the nodejs module for manylinux. Invoked by ci/build_linux_artifacts_nodejs.sh.
-set -e
-ARCH=${1:-x86_64}
-
-if [ "$ARCH" = "x86_64" ]; then
-    export OPENSSL_LIB_DIR=/usr/local/lib64/
-else
-    export OPENSSL_LIB_DIR=/usr/local/lib/
-fi
-export OPENSSL_STATIC=1
-export OPENSSL_INCLUDE_DIR=/usr/local/include/openssl
-
-source $HOME/.bashrc
-
-cd nodejs
-npm ci
-npm run build-release

ci/manylinux_nodejs/install_openssl.sh

@@ -1,26 +0,0 @@
-#!/bin/bash
-# Builds openssl from source so we can statically link to it
-
-# this is to avoid the error we get with the system installation:
-# /usr/bin/ld: <library>: version node not found for symbol SSLeay@@OPENSSL_1.0.1
-# /usr/bin/ld: failed to set dynamic section sizes: Bad value
-set -e
-
-git clone -b OpenSSL_1_1_1u \
-    --single-branch \
-    https://github.com/openssl/openssl.git
-
-pushd openssl
-
-if [[ $1 == x86_64* ]]; then
-    ARCH=linux-x86_64
-else
-    # gnu target
-    ARCH=linux-aarch64
-fi
-
-./Configure no-shared $ARCH
-
-make
-
-make install

ci/manylinux_nodejs/install_protobuf.sh

@@ -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_nodejs/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 "$HOME"/.bashrc
-
-    nvm install --no-progress 16
-}
-
-install_rust() {
-    echo "Installing rust..."
-    curl https://sh.rustup.rs -sSf | bash -s -- -y
-    export PATH="$PATH:/root/.cargo/bin"
-}
-
-install_node
-install_rust

docker-compose.yml

@@ -1,18 +0,0 @@
-version: "3.9"
-services:
-  localstack:
-    image: localstack/localstack:3.3
-    ports:
-      - 4566:4566
-    environment:
-      - SERVICES=s3,dynamodb,kms
-      - DEBUG=1
-      - LS_LOG=trace
-      - DOCKER_HOST=unix:///var/run/docker.sock
-      - AWS_ACCESS_KEY_ID=ACCESSKEY
-      - AWS_SECRET_ACCESS_KEY=SECRETKEY
-    healthcheck:
-      test: [ "CMD", "curl", "-s", "http://localhost:4566/_localstack/health" ]
-      interval: 5s
-      retries: 3
-      start_period: 10s

dockerfiles/Dockerfile

@@ -1,27 +0,0 @@
-#Simple base dockerfile that supports basic dependencies required to run lance with FTS and Hybrid Search
-#Usage docker build -t lancedb:latest -f Dockerfile .
-FROM python:3.10-slim-buster
-
-# Install Rust
-RUN apt-get update && apt-get install -y curl build-essential && \
-  curl https://sh.rustup.rs -sSf | sh -s -- -y
-
-# Set the environment variable for Rust
-ENV PATH="/root/.cargo/bin:${PATH}"
-
-# Install protobuf compiler
-RUN apt-get install -y protobuf-compiler && \
-  apt-get clean && \
-  rm -rf /var/lib/apt/lists/*
-
-RUN apt-get -y update &&\
-  apt-get -y upgrade && \
-  apt-get -y install git
-
-
-# Verify installations
-RUN python --version && \
-  rustc --version && \
-  protoc --version
-
-RUN pip install tantivy lancedb

docs/README.md

@@ -1,44 +0,0 @@
-# LanceDB Documentation
-
-LanceDB docs are deployed to https://lancedb.github.io/lancedb/.
-
-Docs is built and deployed automatically by [Github Actions](.github/workflows/docs.yml)
-whenever a commit is pushed to the `main` branch. So it is possible for the docs to show
-unreleased features.
-
-## Building the docs
-
-### Setup
-1. Install LanceDB. From LanceDB repo root: `pip install -e python`
-2. Install dependencies. From LanceDB repo root: `pip install -r docs/requirements.txt`
-3. Make sure you have node and npm setup
-4. Make sure protobuf and libssl are installed
-
-### Building node module and create markdown files
-
-See [Javascript docs README](./src/javascript/README.md)
-
-### Build docs
-From LanceDB repo root:
-
-Run: `PYTHONPATH=. mkdocs build -f docs/mkdocs.yml`
-
-If successful, you should see a `docs/site` directory that you can verify locally.
-
-### Run local server
-
-You can run a local server to test the docs prior to deployment by navigating to the `docs` directory and running the following command:
-
-```bash
-cd docs
-mkdocs serve
-```
-
-### Run doctest for typescript example
-
-```bash
-cd lancedb/docs
-npm i
-npm run build
-npm run all
-```

docs/mkdocs.yml

@@ -1,7 +1,5 @@
-site_name: LanceDB
+site_name: LanceDB Docs
-site_url: https://lancedb.github.io/lancedb/
 repo_url: https://github.com/lancedb/lancedb
-edit_uri: https://github.com/lancedb/lancedb/tree/main/docs/src
 repo_name: lancedb/lancedb
 docs_dir: src
 
@@ -9,233 +7,78 @@ theme:
   name: "material"
   logo: assets/logo.png
   favicon: assets/logo.png
-  palette:
-    # Palette toggle for light mode
-    - scheme: lancedb
-      primary: custom
-      toggle:
-        icon: material/weather-night
-        name: Switch to dark mode
-    # Palette toggle for dark mode
-    - scheme: slate
-      primary: custom
-      toggle:
-        icon: material/weather-sunny
-        name: Switch to light mode
   features:
     - content.code.copy
     - content.tabs.link
-    - content.action.edit
-    - toc.follow
-    - navigation.top
-    - navigation.tabs
-    - navigation.tabs.sticky
-    - navigation.footer
-    - navigation.tracking
-    - navigation.instant
   icon:
     repo: fontawesome/brands/github
   custom_dir: overrides
 
 plugins:
-  - search
+- search
-  - autorefs
+- autorefs
-  - mkdocstrings:
+- mkdocstrings:
-      handlers:
+    handlers:
-        python:
+      python:
-          paths: [../python]
+        paths: [../python]
-          options:
+        selection:
-            docstring_style: numpy
+          docstring_style: numpy
-            heading_level: 3
+        rendering:
-            show_source: true
+          heading_level: 4
-            show_symbol_type_in_heading: true
+          show_source: false
-            show_signature_annotations: true
+          show_symbol_type_in_heading: true
-            show_root_heading: true
+          show_signature_annotations: true
-            members_order: source
+          show_root_heading: true
-          import:
+          members_order: source
-            # for cross references
+        import:
-            - https://arrow.apache.org/docs/objects.inv
+          # for cross references
-            - https://pandas.pydata.org/docs/objects.inv
+          - https://arrow.apache.org/docs/objects.inv
-  - mkdocs-jupyter
+          - https://pandas.pydata.org/docs/objects.inv
+- mkdocs-jupyter
 
 markdown_extensions:
-  - admonition
+- admonition
-  - footnotes
+- footnotes
-  - pymdownx.details
+- pymdownx.superfences
-  - pymdownx.highlight:
+- pymdownx.details
-      anchor_linenums: true
+- pymdownx.highlight:
-      line_spans: __span
+    anchor_linenums: true
-      pygments_lang_class: true
+    line_spans: __span
-  - pymdownx.inlinehilite
+    pygments_lang_class: true
-  - pymdownx.snippets:
+- pymdownx.inlinehilite
-      base_path: ..
+- pymdownx.snippets
-      dedent_subsections: true
+- pymdownx.superfences
-  - pymdownx.superfences
+- pymdownx.tabbed:
-  - pymdownx.tabbed:
+    alternate_style: true
-      alternate_style: true
+- md_in_html
-  - md_in_html
-  - attr_list
 
 nav:
-  - Home:
+- Home: index.md
-      - LanceDB: index.md
+- Basics: basic.md
-      - 🏃🏼‍♂️ Quick start: basic.md
+- Embeddings: embedding.md
-      - 📚 Concepts:
+- Python full-text search: fts.md
-          - Vector search: concepts/vector_search.md
+- Python integrations:
-          - Indexing: concepts/index_ivfpq.md
+  - Pandas and PyArrow: python/arrow.md
-          - Storage: concepts/storage.md
+  - DuckDB: python/duckdb.md
-          - Data management: concepts/data_management.md
+  - LangChain 🦜️🔗: https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/lancedb.html
-      - 🔨 Guides:
+  - LlamaIndex 🦙: https://gpt-index.readthedocs.io/en/latest/examples/vector_stores/LanceDBIndexDemo.html
-          - Working with tables: guides/tables.md
+  - Pydantic: python/pydantic.md
-          - Building an ANN index: ann_indexes.md
+- Python examples:
-          - Vector Search: search.md
+  - YouTube Transcript Search: notebooks/youtube_transcript_search.ipynb
-          - Full-text search: fts.md
+  - Documentation QA Bot using LangChain: notebooks/code_qa_bot.ipynb
-          - Hybrid search:
+  - Multimodal search using CLIP: notebooks/multimodal_search.ipynb
-              - Overview: hybrid_search/hybrid_search.md
+  - Serverless QA Bot with S3 and Lambda: examples/serverless_lancedb_with_s3_and_lambda.md
-              - Comparing Rerankers: hybrid_search/eval.md
+  - Serverless QA Bot with Modal: examples/serverless_qa_bot_with_modal_and_langchain.md
-              - Airbnb financial data example: notebooks/hybrid_search.ipynb
+- Javascript examples:
-          - Reranking:
+  - YouTube Transcript Search: examples/youtube_transcript_bot_with_nodejs.md
-              - Quickstart: reranking/index.md
+  - TransformersJS Embedding Search: examples/transformerjs_embedding_search_nodejs.md
-              - Cohere Reranker: reranking/cohere.md
+- References:
-              - Linear Combination Reranker: reranking/linear_combination.md
+  - Vector Search: search.md
-              - Cross Encoder Reranker: reranking/cross_encoder.md
+  - SQL filters: sql.md
-              - ColBERT Reranker: reranking/colbert.md
+  - Indexing: ann_indexes.md
-              - OpenAI Reranker: reranking/openai.md
+- API references:
-              - Building Custom Rerankers: reranking/custom_reranker.md
+  - Python API: python/python.md
-          - Filtering: sql.md
+  - Javascript API: javascript/modules.md
-          - Versioning & Reproducibility: notebooks/reproducibility.ipynb
-          - Configuring Storage: guides/storage.md
-          - Sync -> Async Migration Guide: migration.md
-      - 🧬 Managing embeddings:
-          - Overview: embeddings/index.md
-          - Embedding functions: embeddings/embedding_functions.md
-          - Available models: embeddings/default_embedding_functions.md
-          - User-defined embedding functions: embeddings/custom_embedding_function.md
-          - "Example: Multi-lingual semantic search": notebooks/multi_lingual_example.ipynb
-          - "Example: MultiModal CLIP Embeddings": notebooks/DisappearingEmbeddingFunction.ipynb
-      - 🔌 Integrations:
-          - Tools and data formats: integrations/index.md
-          - Pandas and PyArrow: python/pandas_and_pyarrow.md
-          - Polars: python/polars_arrow.md
-          - DuckDB: python/duckdb.md
-          - LangChain:
-            - LangChain 🔗: https://python.langchain.com/docs/integrations/vectorstores/lancedb/
-            - LangChain JS/TS 🔗: https://js.langchain.com/docs/integrations/vectorstores/lancedb
-          - LlamaIndex 🦙: https://docs.llamaindex.ai/en/stable/examples/vector_stores/LanceDBIndexDemo/
-          - Pydantic: python/pydantic.md
-          - Voxel51: integrations/voxel51.md
-          - PromptTools: integrations/prompttools.md
-      - 🎯 Examples:
-          - Overview: examples/index.md
-          - 🐍 Python:
-              - Overview: examples/examples_python.md
-              - YouTube Transcript Search: notebooks/youtube_transcript_search.ipynb
-              - Documentation QA Bot using LangChain: notebooks/code_qa_bot.ipynb
-              - Multimodal search using CLIP: notebooks/multimodal_search.ipynb
-              - Example - Calculate CLIP Embeddings with Roboflow Inference: examples/image_embeddings_roboflow.md
-              - Serverless QA Bot with S3 and Lambda: examples/serverless_lancedb_with_s3_and_lambda.md
-              - Serverless QA Bot with Modal: examples/serverless_qa_bot_with_modal_and_langchain.md
-          - 👾 JavaScript:
-              - Overview: examples/examples_js.md
-              - Serverless Website Chatbot: examples/serverless_website_chatbot.md
-              - YouTube Transcript Search: examples/youtube_transcript_bot_with_nodejs.md
-              - TransformersJS Embedding Search: examples/transformerjs_embedding_search_nodejs.md
-          - 🦀 Rust:
-              - Overview: examples/examples_rust.md
-      - 💭 FAQs: faq.md
-      - ⚙️ API reference:
-          - 🐍 Python: python/python.md
-          - 👾 JavaScript (vectordb): javascript/modules.md
-          - 👾 JavaScript (lancedb): javascript/modules.md
-          - 🦀 Rust: https://docs.rs/lancedb/latest/lancedb/
-      - ☁️ LanceDB Cloud:
-          - Overview: cloud/index.md
-          - API reference:
-              - 🐍 Python: python/saas-python.md
-              - 👾 JavaScript: javascript/saas-modules.md
-
-  - Quick start: basic.md
-  - Concepts:
-      - Vector search: concepts/vector_search.md
-      - Indexing: concepts/index_ivfpq.md
-      - Storage: concepts/storage.md
-      - Data management: concepts/data_management.md
-  - Guides:
-      - Working with tables: guides/tables.md
-      - Building an ANN index: ann_indexes.md
-      - Vector Search: search.md
-      - Full-text search: fts.md
-      - Hybrid search:
-          - Overview: hybrid_search/hybrid_search.md
-          - Comparing Rerankers: hybrid_search/eval.md
-          - Airbnb financial data example: notebooks/hybrid_search.ipynb
-      - Reranking:
-          - Quickstart: reranking/index.md
-          - Cohere Reranker: reranking/cohere.md
-          - Linear Combination Reranker: reranking/linear_combination.md
-          - Cross Encoder Reranker: reranking/cross_encoder.md
-          - ColBERT Reranker: reranking/colbert.md
-          - OpenAI Reranker: reranking/openai.md
-          - Building Custom Rerankers: reranking/custom_reranker.md
-      - Filtering: sql.md
-      - Versioning & Reproducibility: notebooks/reproducibility.ipynb
-      - Configuring Storage: guides/storage.md
-      - Sync -> Async Migration Guide: migration.md
-  - Managing Embeddings:
-      - Overview: embeddings/index.md
-      - Embedding functions: embeddings/embedding_functions.md
-      - Available models: embeddings/default_embedding_functions.md
-      - User-defined embedding functions: embeddings/custom_embedding_function.md
-      - "Example: Multi-lingual semantic search": notebooks/multi_lingual_example.ipynb
-      - "Example: MultiModal CLIP Embeddings": notebooks/DisappearingEmbeddingFunction.ipynb
-  - Integrations:
-      - Overview: integrations/index.md
-      - Pandas and PyArrow: python/pandas_and_pyarrow.md
-      - Polars: python/polars_arrow.md
-      - DuckDB: python/duckdb.md
-      - LangChain 🦜️🔗↗: https://python.langchain.com/docs/integrations/vectorstores/lancedb
-      - LangChain.js 🦜️🔗↗: https://js.langchain.com/docs/integrations/vectorstores/lancedb
-      - LlamaIndex 🦙↗: https://gpt-index.readthedocs.io/en/latest/examples/vector_stores/LanceDBIndexDemo.html
-      - Pydantic: python/pydantic.md
-      - Voxel51: integrations/voxel51.md
-      - PromptTools: integrations/prompttools.md
-  - Examples:
-      - examples/index.md
-      - YouTube Transcript Search: notebooks/youtube_transcript_search.ipynb
-      - Documentation QA Bot using LangChain: notebooks/code_qa_bot.ipynb
-      - Multimodal search using CLIP: notebooks/multimodal_search.ipynb
-      - Serverless QA Bot with S3 and Lambda: examples/serverless_lancedb_with_s3_and_lambda.md
-      - Serverless QA Bot with Modal: examples/serverless_qa_bot_with_modal_and_langchain.md
-      - YouTube Transcript Search (JS): examples/youtube_transcript_bot_with_nodejs.md
-      - Serverless Chatbot from any website: examples/serverless_website_chatbot.md
-      - TransformersJS Embedding Search: examples/transformerjs_embedding_search_nodejs.md
-  - API reference:
-      - Overview: api_reference.md
-      - Python: python/python.md
-      - Javascript (vectordb): javascript/modules.md
-      - Javascript (lancedb): js/modules.md
-      - Rust: https://docs.rs/lancedb/latest/lancedb/index.html
-  - LanceDB Cloud:
-      - Overview: cloud/index.md
-      - API reference:
-          - 🐍 Python: python/saas-python.md
-          - 👾 JavaScript: javascript/saas-modules.md
 
 extra_css:
   - styles/global.css
-  - styles/extra.css
-
-extra_javascript:
-  - "extra_js/init_ask_ai_widget.js"
-
-extra:
-  analytics:
-    provider: google
-    property: G-B7NFM40W74
-  social:
-    - icon: fontawesome/brands/github
-      link: https://github.com/lancedb/lancedb
-    - icon: fontawesome/brands/x-twitter
-      link: https://twitter.com/lancedb
-    - icon: fontawesome/brands/linkedin
-      link: https://www.linkedin.com/company/lancedb

docs/package-lock.json

@@ -1,132 +0,0 @@
-{
-  "name": "lancedb-docs-test",
-  "version": "1.0.0",
-  "lockfileVersion": 3,
-  "requires": true,
-  "packages": {
-    "": {
-      "name": "lancedb-docs-test",
-      "version": "1.0.0",
-      "license": "Apache 2",
-      "dependencies": {
-        "apache-arrow": "file:../node/node_modules/apache-arrow",
-        "vectordb": "file:../node"
-      },
-      "devDependencies": {
-        "@types/node": "^20.11.8",
-        "typescript": "^5.3.3"
-      }
-    },
-    "../node": {
-      "name": "vectordb",
-      "version": "0.4.6",
-      "cpu": [
-        "x64",
-        "arm64"
-      ],
-      "license": "Apache-2.0",
-      "os": [
-        "darwin",
-        "linux",
-        "win32"
-      ],
-      "dependencies": {
-        "@apache-arrow/ts": "^14.0.2",
-        "@neon-rs/load": "^0.0.74",
-        "apache-arrow": "^14.0.2",
-        "axios": "^1.4.0"
-      },
-      "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",
-        "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": "*",
-        "uuid": "^9.0.0"
-      },
-      "optionalDependencies": {
-        "@lancedb/vectordb-darwin-arm64": "0.4.6",
-        "@lancedb/vectordb-darwin-x64": "0.4.6",
-        "@lancedb/vectordb-linux-arm64-gnu": "0.4.6",
-        "@lancedb/vectordb-linux-x64-gnu": "0.4.6",
-        "@lancedb/vectordb-win32-x64-msvc": "0.4.6"
-      }
-    },
-    "../node/node_modules/apache-arrow": {
-      "version": "14.0.2",
-      "license": "Apache-2.0",
-      "dependencies": {
-        "@types/command-line-args": "5.2.0",
-        "@types/command-line-usage": "5.0.2",
-        "@types/node": "20.3.0",
-        "@types/pad-left": "2.1.1",
-        "command-line-args": "5.2.1",
-        "command-line-usage": "7.0.1",
-        "flatbuffers": "23.5.26",
-        "json-bignum": "^0.0.3",
-        "pad-left": "^2.1.0",
-        "tslib": "^2.5.3"
-      },
-      "bin": {
-        "arrow2csv": "bin/arrow2csv.js"
-      }
-    },
-    "node_modules/@types/node": {
-      "version": "20.11.8",
-      "resolved": "https://registry.npmjs.org/@types/node/-/node-20.11.8.tgz",
-      "integrity": "sha512-i7omyekpPTNdv4Jb/Rgqg0RU8YqLcNsI12quKSDkRXNfx7Wxdm6HhK1awT3xTgEkgxPn3bvnSpiEAc7a7Lpyow==",
-      "dev": true,
-      "dependencies": {
-        "undici-types": "~5.26.4"
-      }
-    },
-    "node_modules/apache-arrow": {
-      "resolved": "../node/node_modules/apache-arrow",
-      "link": true
-    },
-    "node_modules/typescript": {
-      "version": "5.3.3",
-      "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.3.3.tgz",
-      "integrity": "sha512-pXWcraxM0uxAS+tN0AG/BF2TyqmHO014Z070UsJ+pFvYuRSq8KH8DmWpnbXe0pEPDHXZV3FcAbJkijJ5oNEnWw==",
-      "dev": true,
-      "bin": {
-        "tsc": "bin/tsc",
-        "tsserver": "bin/tsserver"
-      },
-      "engines": {
-        "node": ">=14.17"
-      }
-    },
-    "node_modules/undici-types": {
-      "version": "5.26.5",
-      "resolved": "https://registry.npmjs.org/undici-types/-/undici-types-5.26.5.tgz",
-      "integrity": "sha512-JlCMO+ehdEIKqlFxk6IfVoAUVmgz7cU7zD/h9XZ0qzeosSHmUJVOzSQvvYSYWXkFXC+IfLKSIffhv0sVZup6pA==",
-      "dev": true
-    },
-    "node_modules/vectordb": {
-      "resolved": "../node",
-      "link": true
-    }
-  }
-}

docs/package.json

@@ -1,20 +0,0 @@
-{
-  "name": "lancedb-docs-test",
-  "version": "1.0.0",
-  "description": "auto-generated tests from doc",
-  "author": "dev@lancedb.com",
-  "license": "Apache 2",
-  "dependencies": {
-    "apache-arrow": "file:../node/node_modules/apache-arrow",
-    "vectordb": "file:../node"
-  },
-  "scripts": {
-    "build": "tsc -b && cd ../node && npm run build-release",
-    "example": "npm run build && node",
-    "test": "npm run build && ls dist/*.js | xargs -n 1 node"
-  },
-  "devDependencies": {
-    "@types/node": "^20.11.8",
-    "typescript": "^5.3.3"
-  }
-}

docs/requirements.txt

@@ -1,5 +1,4 @@
-mkdocs==1.5.3
+mkdocs==1.4.2
 mkdocs-jupyter==0.24.1
-mkdocs-material==9.5.3
+mkdocs-material==9.1.3
 mkdocstrings[python]==0.20.0
-pydantic

docs/src/ann_indexes.md

@@ -1,122 +1,73 @@
-# Approximate Nearest Neighbor (ANN) Indexes
+# ANN (Approximate Nearest Neighbor) Indexes
 
-An ANN or a vector index is a data structure specifically designed to efficiently organize and
+You can create an index over your vector data to make search faster.
-search vector data based on their similarity via the chosen distance metric.
+Vector indexes are faster but less accurate than exhaustive search (KNN or Flat Search).
-By constructing a vector index, the search space is effectively narrowed down, avoiding the need
-for brute-force scanning of the entire vector space.
-A vector index is faster but less accurate than exhaustive search (kNN or flat search).
 LanceDB provides many parameters to fine-tune the index's size, the speed of queries, and the accuracy of results.
 
-## Disk-based Index
+Currently, LanceDB does *not* automatically create the ANN index.
+LanceDB has optimized code for KNN as well. For many use-cases, datasets under 100K vectors won't require index creation at all.
+If you can live with <100ms latency, skipping index creation is a simpler workflow while guaranteeing 100% recall.
 
-Lance provides an `IVF_PQ` disk-based index. It uses **Inverted File Index (IVF)** to first divide
+In the future we will look to automatically create and configure the ANN index.
-the dataset into `N` partitions, and then applies **Product Quantization** to compress vectors in each partition.
+
-See the [indexing](concepts/index_ivfpq.md) concepts guide for more information on how this works.
+## Types of Index
+
+Lance can support multiple index types, the most widely used one is `IVF_PQ`.
+
+* `IVF_PQ`: use **Inverted File Index (IVF)** to first divide the dataset into `N` partitions,
+   and then use **Product Quantization** to compress vectors in each partition.
+* `DISKANN` (**Experimental**): organize the vector as a on-disk graph, where the vertices approximately
+   represent the nearest neighbors of each vector.
 
 ## Creating an IVF_PQ Index
 
 Lance supports `IVF_PQ` index type by default.
 
 === "Python"
+     Creating indexes is done via the [create_index](https://lancedb.github.io/lancedb/python/#lancedb.table.LanceTable.create_index) method.
 
-    Creating indexes is done via the [create_index](https://lancedb.github.io/lancedb/python/#lancedb.table.LanceTable.create_index) method.
+     ```python
+     import lancedb
+     import numpy as np
+     uri = "data/sample-lancedb"
+     db = lancedb.connect(uri)
 
-    ```python
+     # Create 10,000 sample vectors
-    import lancedb
+     data = [{"vector": row, "item": f"item {i}"}
-    import numpy as np
-    uri = "data/sample-lancedb"
-    db = lancedb.connect(uri)
-
-    # Create 10,000 sample vectors
-    data = [{"vector": row, "item": f"item {i}"}
         for i, row in enumerate(np.random.random((10_000, 1536)).astype('float32'))]
 
-    # Add the vectors to a table
+     # Add the vectors to a table
-    tbl = db.create_table("my_vectors", data=data)
+     tbl = db.create_table("my_vectors", data=data)
 
-    # Create and train the index - you need to have enough data in the table for an effective training step
+     # Create and train the index - you need to have enough data in the table for an effective training step
-    tbl.create_index(num_partitions=256, num_sub_vectors=96)
+     tbl.create_index(num_partitions=256, num_sub_vectors=96)
-    ```
+     ```
 
-=== "Typescript"
+=== "Javascript"
+     ```javascript
+     const vectordb = require('vectordb')
+     const db = await vectordb.connect('data/sample-lancedb')
 
-    ```typescript
+     let data = []
-    --8<--- "docs/src/ann_indexes.ts:import"
+     for (let i = 0; i < 10_000; i++) {
+         data.push({vector: Array(1536).fill(i), id: `${i}`, content: "", longId: `${i}`},)
+     }
+     const table = await db.createTable('my_vectors', data)
+     await table.createIndex({ type: 'ivf_pq', column: 'vector', num_partitions: 256, num_sub_vectors: 96 })
+     ```
 
-    --8<-- "docs/src/ann_indexes.ts:ingest"
+- **metric** (default: "L2"): The distance metric to use. By default it uses euclidean distance "`L2`".
-    ```
+We also support "cosine" and "dot" distance as well.
-
+- **num_partitions** (default: 256): The number of partitions of the index.
-=== "Rust"
+- **num_sub_vectors** (default: 96): The number of sub-vectors (M) that will be created during Product Quantization (PQ).
-
+For D dimensional vector, it will be divided into `M` of `D/M` sub-vectors, each of which is presented by
-    ```rust
+a single PQ code.
-    --8<-- "rust/lancedb/examples/ivf_pq.rs:create_index"
-    ```
-
-    IVF_PQ index parameters are more fully defined in the [crate docs](https://docs.rs/lancedb/latest/lancedb/index/vector/struct.IvfPqIndexBuilder.html).
-
-The following IVF_PQ paramters can be specified:
-
-- **distance_type**: The distance metric to use. By default it uses euclidean distance "`L2`".
-  We also support "cosine" and "dot" distance as well.
-- **num_partitions**: The number of partitions in the index. The default is the square root
-  of the number of rows.
-
-!!! note
-
-    In the synchronous python SDK and node's `vectordb` the default is 256. This default has
-    changed in the asynchronous python SDK and node's `lancedb`.
-
-- **num_sub_vectors**: The number of sub-vectors (M) that will be created during Product Quantization (PQ).
-  For D dimensional vector, it will be divided into `M` subvectors with dimension `D/M`, each of which is replaced by
-  a single PQ code. The default is the dimension of the vector divided by 16.
-
-!!! note
-
-    In the synchronous python SDK and node's `vectordb` the default is currently 96. This default has
-    changed in the asynchronous python SDK and node's `lancedb`.
 
 <figure markdown>
   ![IVF PQ](./assets/ivf_pq.png)
   <figcaption>IVF_PQ index with <code>num_partitions=2, num_sub_vectors=4</code></figcaption>
 </figure>
 
-### Use GPU to build vector index
-
-Lance Python SDK has experimental GPU support for creating IVF index.
-Using GPU for index creation requires [PyTorch>2.0](https://pytorch.org/) being installed.
-
-You can specify the GPU device to train IVF partitions via
-
-- **accelerator**: Specify to `cuda` or `mps` (on Apple Silicon) to enable GPU training.
-
-=== "Linux"
-
-     <!-- skip-test -->
-     ``` { .python .copy }
-     # Create index using CUDA on Nvidia GPUs.
-     tbl.create_index(
-          num_partitions=256,
-          num_sub_vectors=96,
-          accelerator="cuda"
-     )
-     ```
-
-=== "MacOS"
-
-     <!-- skip-test -->
-     ```python
-     # Create index using MPS on Apple Silicon.
-     tbl.create_index(
-          num_partitions=256,
-          num_sub_vectors=96,
-          accelerator="mps"
-     )
-     ```
-
-Troubleshooting:
-
-If you see `AssertionError: Torch not compiled with CUDA enabled`, you need to [install
-PyTorch with CUDA support](https://pytorch.org/get-started/locally/).
 
 ## Querying an ANN Index
 
@@ -135,51 +86,48 @@ There are a couple of parameters that can be used to fine-tune the search:
   Note: refine_factor is only applicable if an ANN index is present. If specified on a table without an ANN index, it is ignored.
 
 === "Python"
+     ```python
+     tbl.search(np.random.random((1536))) \
+         .limit(2) \
+         .nprobes(20) \
+         .refine_factor(10) \
+         .to_df()
+     ```
+     ```
+                                              vector       item       score
+     0  [0.44949695, 0.8444449, 0.06281311, 0.23338133...  item 1141  103.575333
+     1  [0.48587373, 0.269207, 0.15095535, 0.65531915,...  item 3953  108.393867
+     ```
 
-    ```python
+=== "Javascript"
-    tbl.search(np.random.random((1536))) \
+     ```javascript
-        .limit(2) \
+     const results_1 = await table
-        .nprobes(20) \
+         .search(Array(1536).fill(1.2))
-        .refine_factor(10) \
+         .limit(2)
-        .to_pandas()
+         .nprobes(20)
-    ```
+         .refineFactor(10)
+         .execute()
+     ```
 
-    ```text
+The search will return the data requested in addition to the score of each item.
-                                              vector       item       _distance
-    0  [0.44949695, 0.8444449, 0.06281311, 0.23338133...  item 1141  103.575333
-    1  [0.48587373, 0.269207, 0.15095535, 0.65531915,...  item 3953  108.393867
-    ```
 
-=== "Typescript"
+**Note:** The score is the distance between the query vector and the element. A lower number means that the result is more relevant.
-
-    ```typescript
-    --8<-- "docs/src/ann_indexes.ts:search1"
-    ```
-
-=== "Rust"
-
-    ```rust
-    --8<-- "rust/lancedb/examples/ivf_pq.rs:search1"
-    ```
-
-    Vector search options are more fully defined in the [crate docs](https://docs.rs/lancedb/latest/lancedb/query/struct.Query.html#method.nearest_to).
-
-The search will return the data requested in addition to the distance of each item.
 
 ### Filtering (where clause)
 
 You can further filter the elements returned by a search using a where clause.
 
 === "Python"
-
      ```python
-     tbl.search(np.random.random((1536))).where("item != 'item 1141'").to_pandas()
+     tbl.search(np.random.random((1536))).where("item != 'item 1141'").to_df()
      ```
 
-=== "Typescript"
+=== "Javascript"
-
      ```javascript
-     --8<-- "docs/src/ann_indexes.ts:search2"
+     const results_2 = await table
+         .search(Array(1536).fill(1.2))
+         .where("id != '1141'")
+         .execute()
      ```
 
 ### Projections (select clause)
@@ -187,57 +135,48 @@ You can further filter the elements returned by a search using a where clause.
 You can select the columns returned by the query using a select clause.
 
 === "Python"
-
      ```python
-     tbl.search(np.random.random((1536))).select(["vector"]).to_pandas()
+     tbl.search(np.random.random((1536))).select(["vector"]).to_df()
      ```
-
+     ```
-
+     vector      score
-     ```text
-                                                   vector _distance
      0  [0.30928212, 0.022668175, 0.1756372, 0.4911822...  93.971092
      1  [0.2525465, 0.01723831, 0.261568, 0.002007689,...  95.173485
      ...
      ```
 
-=== "Typescript"
+=== "Javascript"
-
+     ```javascript
-     ```typescript
+     const results_3 = await table
-     --8<-- "docs/src/ann_indexes.ts:search3"
+         .search(Array(1536).fill(1.2))
+         .select(["id"])
+         .execute()
      ```
 
 ## FAQ
 
-### Why do I need to manually create an index?
+### When is it necessary to create an ANN vector index.
 
-Currently, LanceDB does _not_ automatically create the ANN index.
+`LanceDB` has manually tuned SIMD code for computing vector distances.
-LanceDB is well-optimized for kNN (exhaustive search) via a disk-based index. For many use-cases,
+In our benchmarks, computing 100K pairs of 1K dimension vectors only take less than 20ms.
-datasets of the order of ~100K vectors don't require index creation. If you can live with up to
+For small dataset (<100K rows) or the applications which can accept 100ms latency, vector indices are usually not necessary.
-100ms latency, skipping index creation is a simpler workflow while guaranteeing 100% recall.
 
-### When is it necessary to create an ANN vector index?
+For large-scale or higher dimension vectors, it is beneficial to create vector index.
 
-`LanceDB` comes out-of-the-box with highly optimized SIMD code for computing vector similarity.
+### How big is my index, and how many memory will it take.
-In our benchmarks, computing distances for 100K pairs of 1K dimension vectors takes **less than 20ms**.
-We observe that for small datasets (~100K rows) or for applications that can accept 100ms latency,
-vector indices are usually not necessary.
 
-For large-scale or higher dimension vectors, it can beneficial to create vector index for performance.
+In LanceDB, all vector indices are disk-based, meaning that when responding to a vector query, only the relevant pages from the index file are loaded from disk and cached in memory. Additionally, each sub-vector is usually encoded into 1 byte PQ code.
-
-### How big is my index, and how many memory will it take?
-
-In LanceDB, all vector indices are **disk-based**, meaning that when responding to a vector query, only the relevant pages from the index file are loaded from disk and cached in memory. Additionally, each sub-vector is usually encoded into 1 byte PQ code.
 
 For example, with a 1024-dimension dataset, if we choose `num_sub_vectors=64`, each sub-vector has `1024 / 64 = 16` float32 numbers.
 Product quantization can lead to approximately `16 * sizeof(float32) / 1 = 64` times of space reduction.
 
-### How to choose `num_partitions` and `num_sub_vectors` for `IVF_PQ` index?
+### How to choose `num_partitions` and `num_sub_vectors` for `IVF_PQ` index.
 
 `num_partitions` is used to decide how many partitions the first level `IVF` index uses.
 Higher number of partitions could lead to more efficient I/O during queries and better accuracy, but it takes much more time to train.
 On `SIFT-1M` dataset, our benchmark shows that keeping each partition 1K-4K rows lead to a good latency / recall.
 
-`num_sub_vectors` specifies how many Product Quantization (PQ) short codes to generate on each vector. Because
+`num_sub_vectors` decides how many Product Quantization code to generate on each vector. Because
-PQ is a lossy compression of the original vector, a higher `num_sub_vectors` usually results in
+Product Quantization is a lossy compression of the original vector, the more `num_sub_vectors` usually results to
-less space distortion, and thus yields better accuracy. However, a higher `num_sub_vectors` also causes heavier I/O and
+less space distortion, and thus yield better accuracy. However, similarly, more `num_sub_vectors` causes heavier I/O and
-more PQ computation, and thus, higher latency. `dimension / num_sub_vectors` should be a multiple of 8 for optimum SIMD efficiency.
+more PQ computation, thus, higher latency. `dimension / num_sub_vectors` should be aligned with 8 for better SIMD efficiency.

docs/src/ann_indexes.ts

@@ -1,53 +0,0 @@
-// --8<-- [start:import]
-import * as vectordb from "vectordb";
-// --8<-- [end:import]
-
-(async () => {
-  // --8<-- [start:ingest]
-  const db = await vectordb.connect("data/sample-lancedb");
-
-  let data = [];
-  for (let i = 0; i < 10_000; i++) {
-    data.push({
-      vector: Array(1536).fill(i),
-      id: `${i}`,
-      content: "",
-      longId: `${i}`,
-    });
-  }
-  const table = await db.createTable("my_vectors", data);
-  await table.createIndex({
-    type: "ivf_pq",
-    column: "vector",
-    num_partitions: 16,
-    num_sub_vectors: 48,
-  });
-  // --8<-- [end:ingest]
-
-  // --8<-- [start:search1]
-  const results_1 = await table
-    .search(Array(1536).fill(1.2))
-    .limit(2)
-    .nprobes(20)
-    .refineFactor(10)
-    .execute();
-  // --8<-- [end:search1]
-
-  // --8<-- [start:search2]
-  const results_2 = await table
-    .search(Array(1536).fill(1.2))
-    .where("id != '1141'")
-    .limit(2)
-    .execute();
-  // --8<-- [end:search2]
-
-  // --8<-- [start:search3]
-  const results_3 = await table
-    .search(Array(1536).fill(1.2))
-    .select(["id"])
-    .limit(2)
-    .execute();
-  // --8<-- [end:search3]
-
-  console.log("Ann indexes: done");
-})();

docs/src/api_reference.md

@@ -1,8 +0,0 @@
-# API Reference
-
-The API reference for the LanceDB client SDKs are available at the following locations:
-
-- [Python](python/python.md)
-- [JavaScript (legacy vectordb package)](javascript/modules.md)
-- [JavaScript (newer @lancedb/lancedb package)](js/modules.md)
-- [Rust](https://docs.rs/lancedb/latest/lancedb/index.html)

docs/src/basic.md

@@ -1,401 +1,145 @@
-# Quick start
+# Basic LanceDB Functionality
 
-!!! info "LanceDB can be run in a number of ways:"
+We'll cover the basics of using LanceDB on your local machine in this section.
 
-    * Embedded within an existing backend (like your Django, Flask, Node.js or FastAPI application)
+??? info "LanceDB runs embedded on your backend application, so there is no need to run a separate server."
-    * Directly from a client application like a Jupyter notebook for analytical workloads
-    * Deployed as a remote serverless database
 
-![](assets/lancedb_embedded_explanation.png)
+      <img src="../assets/lancedb_embedded_explanation.png" width="650px" />
 
 ## Installation
 
 === "Python"
-
       ```shell
       pip install lancedb
       ```
 
-=== "Typescript"
+=== "Javascript"
-
       ```shell
       npm install vectordb
       ```
 
-=== "Rust"
+## How to connect to a database
-
-    ```shell
-    cargo add lancedb
-    ```
-
-    !!! info "To use the lancedb create, you first need to install protobuf."
-
-    === "macOS"
-
-        ```shell
-        brew install protobuf
-        ```
-
-    === "Ubuntu/Debian"
-
-        ```shell
-        sudo apt install -y protobuf-compiler libssl-dev
-        ```
-
-    !!! info "Please also make sure you're using the same version of Arrow as in the [lancedb crate](https://github.com/lancedb/lancedb/blob/main/Cargo.toml)"
-
-## Connect to a database
 
 === "Python"
-
-    ```python
-    --8<-- "python/python/tests/docs/test_basic.py:imports"
-    --8<-- "python/python/tests/docs/test_basic.py:connect"
-
-    --8<-- "python/python/tests/docs/test_basic.py:connect_async"
-    ```
-
-    !!! note "Asynchronous Python API"
-
-        The asynchronous Python API is new and has some slight differences compared
-        to the synchronous API.  Feel free to start using the asynchronous version.
-        Once all features have migrated we will start to move the synchronous API to
-        use the same syntax as the asynchronous API.  To help with this migration we
-        have created a [migration guide](migration.md) detailing the differences.
-
-=== "Typescript"
-
-    ```typescript
-    --8<-- "docs/src/basic_legacy.ts:import"
-
-    --8<-- "docs/src/basic_legacy.ts:open_db"
-    ```
-
-    !!! note "`@lancedb/lancedb` vs. `vectordb`"
-
-        The Javascript SDK was originally released as `vectordb`.  In an effort to
-        reduce maintenance we are aligning our SDKs.  The new, aligned, Javascript
-        API is being released as `lancedb`.  If you are starting new work we encourage
-        you to try out `lancedb`.  Once the new API is feature complete we will begin
-        slowly deprecating `vectordb` in favor of `lancedb`. There is a
-        [migration guide](migration.md) detailing the differences which will assist
-        you in this process.
-
-=== "Rust"
-
-    ```rust
-    #[tokio::main]
-    async fn main() -> Result<()> {
-        --8<-- "rust/lancedb/examples/simple.rs:connect"
-    }
-    ```
-
-    !!! info "See [examples/simple.rs](https://github.com/lancedb/lancedb/tree/main/rust/lancedb/examples/simple.rs) for a full working example."
-
-LanceDB will create the directory if it doesn't exist (including parent directories).
-
-If you need a reminder of the uri, you can call `db.uri()`.
-
-## Create a table
-
-### Create a table from initial data
-
-If you have data to insert into the table at creation time, you can simultaneously create a
-table and insert the data into it. The schema of the data will be used as the schema of the
-table.
-
-=== "Python"
-
-    ```python
-    --8<-- "python/python/tests/docs/test_basic.py:create_table"
-    --8<-- "python/python/tests/docs/test_basic.py:create_table_async"
-    ```
-
-    If the table already exists, LanceDB will raise an error by default.
-    If you want to overwrite the table, you can pass in `mode="overwrite"`
-    to the `create_table` method.
-
-    You can also pass in a pandas DataFrame directly:
-
-    ```python
-    --8<-- "python/python/tests/docs/test_basic.py:create_table_pandas"
-    --8<-- "python/python/tests/docs/test_basic.py:create_table_async_pandas"
-    ```
-
-=== "Typescript"
-
-    ```typescript
-    --8<-- "docs/src/basic_legacy.ts:create_table"
-    ```
-
-    If the table already exists, LanceDB will raise an error by default.
-    If you want to overwrite the table, you can pass in `mode="overwrite"`
-    to the `createTable` function.
-
-=== "Rust"
-
-    ```rust
-    --8<-- "rust/lancedb/examples/simple.rs:create_table"
-    ```
-
-    If the table already exists, LanceDB will raise an error by default.  See
-    [the mode option](https://docs.rs/lancedb/latest/lancedb/connection/struct.CreateTableBuilder.html#method.mode)
-    for details on how to overwrite (or open) existing tables instead.
-
-    !!! Providing table records in Rust
-
-        The Rust SDK currently expects data to be provided as an Arrow
-        [RecordBatchReader](https://docs.rs/arrow-array/latest/arrow_array/trait.RecordBatchReader.html)
-        Support for additional formats (such as serde or polars) is on the roadmap.
-
-!!! info "Under the hood, LanceDB reads in the Apache Arrow data and persists it to disk using the [Lance format](https://www.github.com/lancedb/lance)."
-
-### Create an empty table
-
-Sometimes you may not have the data to insert into the table at creation time.
-In this case, you can create an empty table and specify the schema, so that you can add
-data to the table at a later time (as long as it conforms to the schema). This is
-similar to a `CREATE TABLE` statement in SQL.
-
-=== "Python"
-
       ```python
-      --8<-- "python/python/tests/docs/test_basic.py:create_empty_table"
+      import lancedb
-      --8<-- "python/python/tests/docs/test_basic.py:create_empty_table_async"
+      uri = "data/sample-lancedb"
+      db = lancedb.connect(uri)
       ```
 
-=== "Typescript"
+      LanceDB will create the directory if it doesn't exist (including parent directories).
 
-    ```typescript
+      If you need a reminder of the uri, use the `db.uri` property.
-    --8<-- "docs/src/basic_legacy.ts:create_empty_table"
-    ```
-
-=== "Rust"
-
-    ```rust
-    --8<-- "rust/lancedb/examples/simple.rs:create_empty_table"
-    ```
-
-## Open an existing table
-
-Once created, you can open a table as follows:
-
-=== "Python"
-
-    ```python
-    --8<-- "python/python/tests/docs/test_basic.py:open_table"
-    --8<-- "python/python/tests/docs/test_basic.py:open_table_async"
-    ```
-
-=== "Typescript"
-
-    ```typescript
-    const tbl = await db.openTable("myTable");
-    ```
-
-=== "Rust"
-
-    ```rust
-    --8<-- "rust/lancedb/examples/simple.rs:open_existing_tbl"
-    ```
-
-If you forget the name of your table, you can always get a listing of all table names:
-
-=== "Python"
-
-    ```python
-    --8<-- "python/python/tests/docs/test_basic.py:table_names"
-    --8<-- "python/python/tests/docs/test_basic.py:table_names_async"
-    ```
 
 === "Javascript"
+      ```javascript
+      const lancedb = require("vectordb");
 
-    ```javascript
+      const uri = "data/sample-lancedb";
-    console.log(await db.tableNames());
+      const db = await lancedb.connect(uri);
-    ```
+      ```
+      
+      LanceDB will create the directory if it doesn't exist (including parent directories).
 
-=== "Rust"
+      If you need a reminder of the uri, you can call `db.uri()`.
 
-    ```rust
+## How to create a table
-    --8<-- "rust/lancedb/examples/simple.rs:list_names"
-    ```
-
-## Add data to a table
-
-After a table has been created, you can always add more data to it as follows:
 
 === "Python"
+      ```python
+      tbl = db.create_table("my_table",
+                        data=[{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
+                              {"vector": [5.9, 26.5], "item": "bar", "price": 20.0}])
+      ```
 
-    ```python
+      If the table already exists, LanceDB will raise an error by default.
-    --8<-- "python/python/tests/docs/test_basic.py:add_data"
+      If you want to overwrite the table, you can pass in `mode="overwrite"`
-    --8<-- "python/python/tests/docs/test_basic.py:add_data_async"
+      to the `create_table` method.
-    ```
 
-=== "Typescript"
+      You can also pass in a pandas DataFrame directly:
-
+      ```python
-    ```typescript
+      import pandas as pd
-    --8<-- "docs/src/basic_legacy.ts:add"
+      df = pd.DataFrame([{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
-    ```
+                        {"vector": [5.9, 26.5], "item": "bar", "price": 20.0}])
-
+      tbl = db.create_table("table_from_df", data=df)
-=== "Rust"
+      ```
-
-    ```rust
-    --8<-- "rust/lancedb/examples/simple.rs:add"
-    ```
-
-## Search for nearest neighbors
-
-Once you've embedded the query, you can find its nearest neighbors as follows:
-
-=== "Python"
-
-    ```python
-    --8<-- "python/python/tests/docs/test_basic.py:vector_search"
-    --8<-- "python/python/tests/docs/test_basic.py:vector_search_async"
-    ```
-
-    This returns a pandas DataFrame with the results.
-
-=== "Typescript"
-
-    ```typescript
-    --8<-- "docs/src/basic_legacy.ts:search"
-    ```
-
-=== "Rust"
-
-    ```rust
-    use futures::TryStreamExt;
-
-    --8<-- "rust/lancedb/examples/simple.rs:search"
-    ```
-
-    !!! Query vectors in Rust
-        Rust does not yet support automatic execution of embedding functions.  You will need to
-        calculate embeddings yourself.  Support for this is on the roadmap and can be tracked at
-        https://github.com/lancedb/lancedb/issues/994
-
-        Query vectors can be provided as Arrow arrays or a Vec/slice of Rust floats.
-        Support for additional formats (e.g. `polars::series::Series`) is on the roadmap.
-
-By default, LanceDB runs a brute-force scan over dataset to find the K nearest neighbours (KNN).
-For tables with more than 50K vectors, creating an ANN index is recommended to speed up search performance.
-LanceDB allows you to create an ANN index on a table as follows:
-
-=== "Python"
-
-    ```py
-    --8<-- "python/python/tests/docs/test_basic.py:create_index"
-    --8<-- "python/python/tests/docs/test_basic.py:create_index_async"
-    ```
-
-=== "Typescript"
-
-    ```{.typescript .ignore}
-    --8<-- "docs/src/basic_legacy.ts:create_index"
-    ```
-
-=== "Rust"
-
-    ```rust
-    --8<-- "rust/lancedb/examples/simple.rs:create_index"
-    ```
-
-!!! note "Why do I need to create an index manually?"
-LanceDB does not automatically create the ANN index for two reasons. The first is that it's optimized
-for really fast retrievals via a disk-based index, and the second is that data and query workloads can
-be very diverse, so there's no one-size-fits-all index configuration. LanceDB provides many parameters
-to fine-tune index size, query latency and accuracy. See the section on
-[ANN indexes](ann_indexes.md) for more details.
-
-## Delete rows from a table
-
-Use the `delete()` method on tables to delete rows from a table. To choose
-which rows to delete, provide a filter that matches on the metadata columns.
-This can delete any number of rows that match the filter.
-
-=== "Python"
-
-    ```python
-    --8<-- "python/python/tests/docs/test_basic.py:delete_rows"
-    --8<-- "python/python/tests/docs/test_basic.py:delete_rows_async"
-    ```
-
-=== "Typescript"
-
-    ```typescript
-    --8<-- "docs/src/basic_legacy.ts:delete"
-    ```
-
-=== "Rust"
-
-    ```rust
-    --8<-- "rust/lancedb/examples/simple.rs:delete"
-    ```
-
-The deletion predicate is a SQL expression that supports the same expressions
-as the `where()` clause (`only_if()` in Rust) on a search. They can be as
-simple or complex as needed. To see what expressions are supported, see the
-[SQL filters](sql.md) section.
-
-=== "Python"
-
-      Read more: [lancedb.table.Table.delete][]
 
 === "Javascript"
+      ```javascript
+      const tb = await db.createTable("my_table",
+                        data=[{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
+                              {"vector": [5.9, 26.5], "item": "bar", "price": 20.0}])
+      ```
+      
+!!! warning
 
-      Read more: [vectordb.Table.delete](javascript/interfaces/Table.md#delete)
+      If the table already exists, LanceDB will raise an error by default.
+      If you want to overwrite the table, you can pass in `mode="overwrite"`
+      to the `createTable` function.
 
-=== "Rust"
+??? info "Under the hood, LanceDB is converting the input data into an Apache Arrow table and persisting it to disk in [Lance format](https://www.github.com/lancedb/lance)."
 
-      Read more: [lancedb::Table::delete](https://docs.rs/lancedb/latest/lancedb/table/struct.Table.html#method.delete)
+## How to open an existing table
 
-## Drop a table
+Once created, you can open a table using the following code:
-
-Use the `drop_table()` method on the database to remove a table.
 
 === "Python"
+      ```python
+      tbl = db.open_table("my_table")
+      ```
+
+      If you forget the name of your table, you can always get a listing of all table names:
 
       ```python
-      --8<-- "python/python/tests/docs/test_basic.py:drop_table"
+      print(db.table_names())
-      --8<-- "python/python/tests/docs/test_basic.py:drop_table_async"
       ```
 
-      This permanently removes the table and is not recoverable, unlike deleting rows.
+=== "Javascript"
-      By default, if the table does not exist an exception is raised. To suppress this,
+      ```javascript
-      you can pass in `ignore_missing=True`.
+      const tbl = await db.openTable("my_table");
-
-=== "Typescript"
-
-      ```typescript
-      --8<-- "docs/src/basic_legacy.ts:drop_table"
       ```
 
-      This permanently removes the table and is not recoverable, unlike deleting rows.
+      If you forget the name of your table, you can always get a listing of all table names:
-      If the table does not exist an exception is raised.
 
-=== "Rust"
+      ```javascript
+      console.log(await db.tableNames());
+      ```
 
-    ```rust
+## How to add data to a table
-    --8<-- "rust/lancedb/examples/simple.rs:drop_table"
-    ```
 
-!!! note "Bundling `vectordb` apps with Webpack"
+After a table has been created, you can always add more data to it using
 
-    If you're using the `vectordb` module in JavaScript, since LanceDB contains a prebuilt Node binary, you must configure `next.config.js` to exclude it from webpack. This is required for both using Next.js and deploying a LanceDB app on Vercel.
+=== "Python"
+      ```python
+      df = pd.DataFrame([{"vector": [1.3, 1.4], "item": "fizz", "price": 100.0},
+                        {"vector": [9.5, 56.2], "item": "buzz", "price": 200.0}])
+      tbl.add(df)
+      ```
 
-    ```javascript
+=== "Javascript"
-    /** @type {import('next').NextConfig} */
+      ```javascript
-    module.exports = ({
+      await tbl.add([{vector: [1.3, 1.4], item: "fizz", price: 100.0},
-    webpack(config) {
+              {vector: [9.5, 56.2], item: "buzz", price: 200.0}])
-        config.externals.push({ vectordb: 'vectordb' })
+      ```
-        return config;
+
-    }
+## How to search for (approximate) nearest neighbors
-    })
+
-    ```
+Once you've embedded the query, you can find its nearest neighbors using the following code:
+
+=== "Python"
+      ```python
+      tbl.search([100, 100]).limit(2).to_df()
+      ```
+
+      This returns a pandas DataFrame with the results.
+
+=== "Javascript"
+      ```javascript
+      const query = await tbl.search([100, 100]).limit(2).execute();
+      ```
 
 ## What's next
 
-This section covered the very basics of using LanceDB. If you're learning about vector databases for the first time, you may want to read the page on [indexing](concepts/index_ivfpq.md) to get familiar with the concepts.
+This section covered the very basics of the LanceDB API.
-
+LanceDB supports many additional features when creating indices to speed up search and options for search.
-If you've already worked with other vector databases, you may want to read the [guides](guides/tables.md) to learn how to work with LanceDB in more detail.
+These are contained in the next section of the documentation.

docs/src/basic_legacy.ts

@@ -1,92 +0,0 @@
-// --8<-- [start:import]
-import * as lancedb from "vectordb";
-import { Schema, Field, Float32, FixedSizeList, Int32, Float16 } from "apache-arrow";
-// --8<-- [end:import]
-import * as fs from "fs";
-import { Table as ArrowTable, Utf8 } from "apache-arrow";
-
-const example = async () => {
-  fs.rmSync("data/sample-lancedb", { recursive: true, force: true });
-  // --8<-- [start:open_db]
-  const lancedb = require("vectordb");
-  const uri = "data/sample-lancedb";
-  const db = await lancedb.connect(uri);
-  // --8<-- [end:open_db]
-
-  // --8<-- [start:create_table]
-  const tbl = await db.createTable(
-    "myTable",
-    [
-      { vector: [3.1, 4.1], item: "foo", price: 10.0 },
-      { vector: [5.9, 26.5], item: "bar", price: 20.0 },
-    ],
-    { writeMode: lancedb.WriteMode.Overwrite }
-  );
-  // --8<-- [end:create_table]
-
-  // --8<-- [start:add]
-  const newData = Array.from({ length: 500 }, (_, i) => ({
-    vector: [i, i + 1],
-    item: "fizz",
-    price: i * 0.1,
-  }));
-  await tbl.add(newData);
-  // --8<-- [end:add]
-
-  // --8<-- [start:create_index]
-  await tbl.createIndex({
-    type: "ivf_pq",
-    num_partitions: 2,
-    num_sub_vectors: 2,
-  });
-  // --8<-- [end:create_index]
-
-  // --8<-- [start:create_empty_table]
-  const schema = new Schema([
-    new Field("id", new Int32()),
-    new Field("name", new Utf8()),
-  ]);
-  const empty_tbl = await db.createTable({ name: "empty_table", schema });
-  // --8<-- [end:create_empty_table]
-
-  // --8<-- [start:create_f16_table]
-  const dim = 16
-  const total = 10
-  const f16_schema = new Schema([
-      new Field('id', new Int32()),
-      new Field(
-        'vector',
-        new FixedSizeList(dim, new Field('item', new Float16(), true)),
-        false
-      )
-    ])
-  const data = lancedb.makeArrowTable(
-      Array.from(Array(total), (_, i) => ({
-        id: i,
-        vector: Array.from(Array(dim), Math.random)
-      })),
-      { f16_schema }
-    )
-  const table = await db.createTable('f16_tbl', data)
-  // --8<-- [end:create_f16_table]
-
-  // --8<-- [start:search]
-  const query = await tbl.search([100, 100]).limit(2).execute();
-  // --8<-- [end:search]
-  console.log(query);
-
-  // --8<-- [start:delete]
-  await tbl.delete('item = "fizz"');
-  // --8<-- [end:delete]
-
-  // --8<-- [start:drop_table]
-  await db.dropTable("myTable");
-  // --8<-- [end:drop_table]
-};
-
-async function main() {
-  await example();
-  console.log("Basic example: done");
-}
-
-main();

docs/src/cloud/index.md

@@ -1,17 +0,0 @@
-# About LanceDB Cloud
-
-LanceDB Cloud is a SaaS (software-as-a-service) solution that runs serverless in the cloud, clearly separating storage from compute. It's designed to be highly scalable without breaking the bank. LanceDB Cloud is currently in private beta with general availability coming soon, but you can apply for early access with the private beta release by signing up below.
-
-[Try out LanceDB Cloud](https://noteforms.com/forms/lancedb-mailing-list-cloud-kty1o5?notionforms=1&utm_source=notionforms){ .md-button .md-button--primary }
-
-## Architecture
-
-LanceDB Cloud provides the same underlying fast vector store that powers the OSS version, but without the need to maintain your own infrastructure. Because it's serverless, you only pay for the storage you use, and you can scale compute up and down as needed depending on the size of your data and its associated index.
-
-![](../assets/lancedb_cloud.png)
-
-## Transitioning from the OSS to the Cloud version
-
-The OSS version of LanceDB is designed to be embedded in your application, and it runs in-process. This makes it incredibly simple to self-host your own AI retrieval workflows for RAG and more and build and test out your concepts on your own infrastructure. The OSS version is forever free, and you can continue to build and integrate LanceDB into your existing backend applications without any added costs.
-
-Should you decide that you need a managed deployment in production, it's possible to seamlessly transition from the OSS to the cloud version by changing the connection string to point to a remote database instead of a local one. With LanceDB Cloud, you can take your AI application from development to production without major code changes or infrastructure burden.

docs/src/concepts/data_management.md

@@ -1,62 +0,0 @@
-# Data management
-
-This section covers concepts related to managing your data over time in LanceDB.
-
-## A primer on Lance
-
-Because LanceDB is built on top of the [Lance](https://lancedb.github.io/lance/) data format, it helps to understand some of its core ideas. Just like Apache Arrow, Lance is a fast columnar data format, but it has the added benefit of being versionable, query and train ML models on. Lance is designed to be used with simple and complex data types, like tabular data, images, videos audio, 3D point clouds (which are deeply nested) and more.
-
-The following concepts are important to keep in mind:
-
-- Data storage is columnar and is interoperable with other columnar formats (such as Parquet) via Arrow
-- Data is divided into fragments that represent a subset of the data
-- 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.  
-    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?
-
-Fragments are chunks of data in a Lance dataset. Each fragment includes multiple files that contain several columns in the chunk of data that it represents.
-
-## Compaction
-
-As you insert more data, your dataset will grow and you'll need to perform *compaction* to maintain query throughput (i.e., keep latencies down to a minimum). Compaction is the process of merging fragments together to reduce the amount of metadata that needs to be managed, and to reduce the number of files that need to be opened while scanning the dataset.
-
-### How does compaction improve performance?
-
-Compaction performs the following tasks in the background:
-
-- Removes deleted rows from fragments
-- Removes dropped columns from fragments
-- Merges small fragments into larger ones
-
-Depending on the use case and dataset, optimal compaction will have different requirements. As a rule of thumb:
-
-- 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)
-
-## 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.
-
-## Reindexing
-
-Reindexing is the process of updating the index to account for new data, keeping good performance for queries. This applies to either a full-text search (FTS) index or a vector index. For ANN search, new data will always be included in query results, but queries on tables with unindexed data will fallback to slower search methods for the new parts of the table. This is another important operation to run periodically as your data grows, as it also improves performance. This is especially important if you're appending large amounts of data to an existing dataset.
-
-!!! tip
-    When adding new data to a dataset that has an existing index (either FTS or vector), LanceDB doesn't immediately update the index until a reindex operation is complete.
-
-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.
-
-### Vector reindex
-
-* 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 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/concepts/index_ivfpq.md

@@ -1,84 +0,0 @@
-# Understanding LanceDB's IVF-PQ index
-
-An ANN (Approximate Nearest Neighbors) index is a data structure that represents data in a way that makes it more efficient to search and retrieve. Using an ANN index is faster, but less accurate than kNN or brute force search because, in essence, the index is a lossy representation of the data.
-
-LanceDB is fundamentally different from other vector databases in that it is built on top of [Lance](https://github.com/lancedb/lance), an open-source columnar data format designed for performant ML workloads and fast random access. Due to the design of Lance, LanceDB's indexing philosophy adopts a primarily *disk-based* indexing philosophy.
-
-## IVF-PQ
-
-IVF-PQ is a composite index that combines inverted file index (IVF) and product quantization (PQ). The implementation in LanceDB provides several parameters to fine-tune the index's size, query throughput, latency and recall, which are described later in this section.
-
-### Product quantization
-
-Quantization is a compression technique used to reduce the dimensionality of an embedding to speed up search.
-
-Product quantization (PQ) works by dividing a large, high-dimensional vector of size into equally sized subvectors. Each subvector is assigned a "reproduction value" that maps to the nearest centroid of points for that subvector. The reproduction values are then assigned to a codebook using unique IDs, which can be used to reconstruct the original vector.
-
-![](../assets/ivfpq_pq_desc.png)
-
-It's important to remember that quantization is a *lossy process*, i.e., the reconstructed vector is not identical to the original vector. This results in a trade-off between the size of the index and the accuracy of the search results.
-
-As an example, consider starting with 128-dimensional vector consisting of 32-bit floats. Quantizing it to an 8-bit integer vector with 4 dimensions as in the image above, we can significantly reduce memory requirements.
-
-!!! example "Effect of quantization"
-
-    Original: `128 × 32 = 4096` bits
-    Quantized: `4 × 8 = 32` bits
-
-    Quantization results in a **128x** reduction in memory requirements for each vector in the index, which is substantial.
-
-### Inverted file index
-
-While PQ helps with reducing the size of the index, IVF primarily addresses search performance. The primary purpose of an inverted file index is to facilitate rapid and effective nearest neighbor search by narrowing down the search space.
-
-In IVF, the PQ vector space is divided into *Voronoi cells*, which are essentially partitions that consist of all the points in the space that are within a threshold distance of the given region's seed point. These seed points are initialized by running K-means over the stored vectors. The centroids of K-means turn into the seed points which then each define a region. These regions are then are used to create an inverted index that correlates each centroid with a list of vectors in the space, allowing a search to be restricted to just a subset of vectors in the index.
-
-![](../assets/ivfpq_ivf_desc.webp)
-
-During query time, depending on where the query lands in vector space, it may be close to the border of multiple Voronoi cells, which could make the top-k results ambiguous and span across multiple cells. To address this, the IVF-PQ introduces the `nprobe` parameter, which controls the number of Voronoi cells to search during a query. The higher the `nprobe`, the more accurate the results, but the slower the query.
-
-![](../assets/ivfpq_query_vector.webp)
-
-## Putting it all together
-
-We can combine the above concepts to understand how to build and query an IVF-PQ index in LanceDB.
-
-### Construct index
-
-There are three key parameters to set when constructing an IVF-PQ index:
-
-* `metric`: Use an `L2` euclidean distance metric. We also support `dot` and `cosine` distance.
-* `num_partitions`: The number of partitions in the IVF portion of the index.
-* `num_sub_vectors`: The number of sub-vectors that will be created during Product Quantization (PQ).
-
-In Python, the index can be created as follows:
-
-```python
-# Create and train the index for a 1536-dimensional vector
-# Make sure you have enough data in the table for an effective training step
-tbl.create_index(metric="L2", num_partitions=256, num_sub_vectors=96)
-```
-
-The `num_partitions` is usually chosen to target a particular number of vectors per partition. `num_sub_vectors` is typically chosen based on the desired recall and the dimensionality of the vector. See the [FAQs](#faq) below for best practices on choosing these parameters.
-
-
-### Query the index
-
-```python
-# Search using a random 1536-dimensional embedding
-tbl.search(np.random.random((1536))) \
-    .limit(2) \
-    .nprobes(20) \
-    .refine_factor(10) \
-    .to_pandas()
-```
-
-The above query will perform a search on the table `tbl` using the given query vector, with the following parameters:
-
-* `limit`: The number of results to return
-* `nprobes`: The number of probes determines the distribution of vector space. While a higher number enhances search accuracy, it also results in slower performance. Typically, setting `nprobes` to cover 5–10% of the dataset proves effective in achieving high recall with minimal latency.
-* `refine_factor`: Refine the results by reading extra elements and re-ranking them in memory. A higher number makes the search more accurate but also slower (see the [FAQ](../faq.md#do-i-need-to-set-a-refine-factor-when-using-an-index) page for more details on this).
-* `to_pandas()`: Convert the results to a pandas DataFrame
-
-And there you have it! You now understand what an IVF-PQ index is, and how to create and query it in LanceDB.
-To see how to create an IVF-PQ index in LanceDB, take a look at the [ANN indexes](../ann_indexes.md) section.

docs/src/concepts/storage.md

@@ -1,80 +0,0 @@
-# Storage
-
-LanceDB is among the only vector databases built on top of multiple modular components designed from the ground-up to be efficient on disk. This gives it the unique benefit of being flexible enough to support multiple storage backends, including local NVMe, EBS, EFS and many other third-party APIs that connect to the cloud.
-
-It is important to understand the tradeoffs between cost and latency for your specific application and use case. This section will help you understand the tradeoffs between the different storage backends.
-
-## Storage options
-
-We've prepared a simple diagram to showcase the thought process that goes into choosing a storage backend when using LanceDB OSS, Cloud or Enterprise.
-
-![](../assets/lancedb_storage_tradeoffs.png)
-
-When architecting your system, you'd typically ask yourself the following questions to decide on a storage option:
-
-1. **Latency**: How fast do I need results? What do the p50 and also p95 look like?
-2. **Scalability**: Can I scale up the amount of data and QPS easily?
-3. **Cost**: To serve my application, what’s the all-in cost of *both* storage and serving infra?
-4. **Reliability/Availability**: How does replication work? Is disaster recovery addressed?
-
-## Tradeoffs
-
-This section reviews the characteristics of each storage option in four dimensions: latency, scalability, cost and reliability.
-
-**We begin with the lowest cost option, and end with the lowest latency option.**
-
-### 1. S3 / GCS / Azure Blob Storage
-
-!!! tip "Lowest cost, highest latency"
-
-    - **Latency** ⇒ Has the highest latency. p95 latency is also substantially worse than p50. In general you get results in the order of several hundred milliseconds
-    - **Scalability** ⇒ Infinite on storage, however, QPS will be limited by S3 concurrency limits
-    - **Cost** ⇒ Lowest (order of magnitude cheaper than other options)
-    - **Reliability/Availability** ⇒ Highly available, as blob storage like S3 are critical infrastructure that form the backbone of the internet.
-
-Another important point to note is that LanceDB is designed to separate storage from compute, and the underlying Lance format stores the data in numerous immutable fragments. Due to these factors, LanceDB is a great storage option that addresses the _N + 1_ query problem. i.e., when a high query throughput is required, query processes can run in a stateless manner and be scaled up and down as needed.
-
-### 2. EFS / GCS Filestore / Azure File Storage
-
-!!! info "Moderately low cost, moderately low latency (<100ms)"
-
-    - **Latency** ⇒ Much better than object/blob storage but not as good as EBS/Local disk; < 100ms p95 achievable
-    - **Scalability** ⇒ High, but the bottleneck will be the IOPs limit, but when scaling you can provision multiple EFS volumes
-    - **Cost** ⇒ Significantly more expensive than S3 but still very cost effective compared to in-memory dbs. Inactive data in EFS is also automatically tiered to S3-level costs.
-    - **Reliability/Availability** ⇒ Highly available, as query nodes can go down without affecting EFS.  However, EFS does not provide replication / backup - this must be managed manually.
-
-A recommended best practice is to keep a copy of the data on S3 for disaster recovery scenarios. If any downtime is unacceptable, then you would need another EFS with a copy of the data. This is still much cheaper than EC2 instances holding multiple copies of the data.
-
-### 3. Third-party storage solutions
-
-Solutions like [MinIO](https://blog.min.io/lancedb-trusted-steed-against-data-complexity/), WekaFS, etc. that deliver S3 compatible API with much better performance than S3.
-
-!!! info "Moderately low cost, moderately low latency (<100ms)"
-
-    - **Latency** ⇒ Should be similar latency to EFS, better than S3 (<100ms)
-    - **Scalability** ⇒ Up to the solutions architect, who can add as many nodes to their MinIO or other third-party provider's cluster as needed
-    - **Cost** ⇒ Definitely higher than S3. The cost can be marginally higher than EFS until you get to maybe >10TB scale with high utilization
-    - **Reliability/Availability** ⇒ These are all shareable by lots of nodes, quality/cost of replication/backup depends on the vendor
-
-
-### 4. EBS / GCP Persistent Disk / Azure Managed Disk
-
-!!! info "Very low latency (<30ms), higher cost"
-
-    - **Latency** ⇒ Very good, pretty close to local disk. You’re looking at <30ms latency in most cases
-    - **Scalability** ⇒ EBS is not shareable between instances. If deployed via k8s, it can be shared between pods that live on the same instance, but beyond that you would need to shard data or make an additional copy
-    - **Cost** ⇒ Higher than EFS. There are some hidden costs to EBS as well if you’re paying for IO.
-    - **Reliability/Availability** ⇒ Not shareable between instances but can be shared between pods on the same instance. Survives instance termination. No automatic backups.
-
-Just like EFS, an EBS or persistent disk setup requires more manual work to manage data sharding, backups and capacity.
-
-### 5. Local disk (SSD/NVMe)
-
-!!! danger "Lowest latency (<10ms), highest cost"
-
-    - **Latency** ⇒ Lowest latency with modern NVMe drives, <10ms p95
-    - **Scalability** ⇒ Difficult to scale on cloud. Also need additional copies / sharding if QPS needs to be higher
-    - **Cost** ⇒ Highest cost; the main issue with keeping your application and storage tightly integrated is that it’s just not really possible to scale this up in cloud environments
-    - **Reliability/Availability** ⇒ If the instance goes down, so does your data. You have to be _very_ diligent about backing up your data
-
-As a rule of thumb, local disk should be your storage option if you require absolutely *crazy low* latency and you’re willing to do a bunch of data management work to make it happen.

docs/src/concepts/vector_search.md

@@ -1,36 +0,0 @@
-# Vector search
-
-Vector search is a technique used to search for similar items based on their vector representations, called embeddings. It is also known as similarity search, nearest neighbor search, or approximate nearest neighbor search.
-
-Raw data (e.g. text, images, audio, etc.) is converted into embeddings via an embedding model, which are then stored in a vector database like LanceDB. To perform similarity search at scale, an index is created on the stored embeddings, which can then used to perform fast lookups.
-
-![](../assets/vector-db-basics.png)
-
-## Embeddings
-
-Modern machine learning models can be trained to convert raw data into embeddings, represented as arrays (or vectors) of floating point numbers of fixed dimensionality. What makes embeddings useful in practice is that the position of an embedding in vector space captures some of the semantics of the data, depending on the type of model and how it was trained. Points that are close to each other in vector space are considered similar (or appear in similar contexts), and points that are far away are considered dissimilar.
-
-Large datasets of multi-modal data (text, audio, images, etc.) can be converted into embeddings with the appropriate model. Projecting the vectors' principal components in 2D space results in groups of vectors that represent similar concepts clustering together, as shown below.
-
-![](../assets/embedding_intro.png)
-
-## Indexes
-
-Embeddings for a given dataset are made searchable via an **index**. The index is constructed by using data structures that store the embeddings such that it's very efficient to perform scans and lookups on them. A key distinguishing feature of LanceDB is it uses a disk-based index: IVF-PQ, which is a variant of the Inverted File Index (IVF) that uses Product Quantization (PQ) to compress the embeddings.
-
-See the [IVF-PQ](./index_ivfpq.md) page for more details on how it works.
-
-## Brute force search
-
-The simplest way to perform vector search is to perform a brute force search, without an index, where the distance between the query vector and all the vectors in the database are computed, with the top-k closest vectors returned. This is equivalent to a k-nearest neighbours (kNN) search in vector space.
-
-![](../assets/knn_search.png)
-
-As you can imagine, the brute force approach is not scalable for datasets larger than a few hundred thousand vectors, as the latency of the search grows linearly with the size of the dataset. This is where approximate nearest neighbour (ANN) algorithms come in.
-
-## Approximate nearest neighbour (ANN) search
-
-Instead of performing an exhaustive search on the entire database for each and every query, approximate nearest neighbour (ANN) algorithms use an index to narrow down the search space, which significantly reduces query latency. The trade-off is that the results are not guaranteed to be the true nearest neighbors of the query, but are usually "good enough" for most use cases.
-
-
-

docs/src/embedding.md

@@ -0,0 +1,142 @@
+# Embedding Functions
+
+Embeddings are high dimensional floating-point vector representations of your data or query.
+Anything can be embedded using some embedding model or function.
+For a given embedding function, the output will always have the same number of dimensions.
+
+## Creating an embedding function
+
+Any function that takes as input a batch (list) of data and outputs a batch (list) of embeddings
+can be used by LanceDB as an embedding function. The input and output batch sizes should be the same.
+
+### HuggingFace example
+
+One popular free option would be to use the [sentence-transformers](https://www.sbert.net/) library from HuggingFace.
+You can install this using pip: `pip install sentence-transformers`.
+
+```python
+from sentence_transformers import SentenceTransformer
+
+name="paraphrase-albert-small-v2"
+model = SentenceTransformer(name)
+
+# used for both training and querying
+def embed_func(batch):
+    return [model.encode(sentence) for sentence in batch]
+```
+
+Please note that currently HuggingFace is only supported in the Python SDK.
+
+### OpenAI example
+
+You can also use an external API like OpenAI to generate embeddings
+
+=== "Python"
+      ```python
+        import openai
+        import os
+
+        # Configuring the environment variable OPENAI_API_KEY
+        if "OPENAI_API_KEY" not in os.environ:
+        # OR set the key here as a variable
+        openai.api_key = "sk-..."
+
+        # verify that the API key is working
+        assert len(openai.Model.list()["data"]) > 0
+
+        def embed_func(c):
+            rs = openai.Embedding.create(input=c, engine="text-embedding-ada-002")
+            return [record["embedding"] for record in rs["data"]]
+      ```
+
+=== "Javascript"
+      ```javascript
+        const lancedb = require("vectordb");
+
+        // You need to provide an OpenAI API key
+        const apiKey = "sk-..."
+        // The embedding function will create embeddings for the 'text' column
+        const embedding = new lancedb.OpenAIEmbeddingFunction('text', apiKey)
+      ```
+
+## Applying an embedding function
+
+=== "Python"
+    Using an embedding function, you can apply it to raw data
+    to generate embeddings for each row.
+
+    Say if you have a pandas DataFrame with a `text` column that you want to be embedded,
+    you can use the [with_embeddings](https://lancedb.github.io/lancedb/python/#lancedb.embeddings.with_embeddings)
+    function to generate embeddings and add create a combined pyarrow table:
+
+
+     ```python
+     import pandas as pd
+     from lancedb.embeddings import with_embeddings
+
+     df = pd.DataFrame([{"text": "pepperoni"},
+                        {"text": "pineapple"}])
+     data = with_embeddings(embed_func, df)
+
+     # The output is used to create / append to a table
+     # db.create_table("my_table", data=data)
+     ```
+
+     If your data is in a different column, you can specify the `column` kwarg to `with_embeddings`.
+
+     By default, LanceDB calls the function with batches of 1000 rows. This can be configured
+     using the `batch_size` parameter to `with_embeddings`.
+
+     LanceDB automatically wraps the function with retry and rate-limit logic to ensure the OpenAI
+     API call is reliable.
+
+=== "Javascript"
+     Using an embedding function, you can apply it to raw data
+     to generate embeddings for each row.
+
+     You can just pass the embedding function created previously and LanceDB will automatically generate
+     embededings for your data.
+
+      ```javascript
+      const db = await lancedb.connect("data/sample-lancedb");
+      const data = [
+        { text: 'pepperoni'  },
+        { text: 'pineapple' }
+      ]
+
+      const table = await db.createTable('vectors', data, embedding)
+      ```
+
+
+## Searching with an embedding function
+
+At inference time, you also need the same embedding function to embed your query text.
+It's important that you use the same model / function otherwise the embedding vectors don't
+belong in the same latent space and your results will be nonsensical.
+
+=== "Python"
+     ```python
+     query = "What's the best pizza topping?"
+     query_vector = embed_func([query])[0]
+     tbl.search(query_vector).limit(10).to_df()
+     ```
+
+     The above snippet returns a pandas DataFrame with the 10 closest vectors to the query.
+
+=== "Javascript"
+     ```javascript
+      const results = await table
+        .search("What's the best pizza topping?")
+        .limit(10)
+        .execute()
+     ```
+
+     The above snippet returns an array of records with the 10 closest vectors to the query.
+
+
+## Roadmap
+
+In the near future, we'll be integrating the embedding functions deeper into LanceDB<br/>.
+The goal is that you just have to configure the function once when you create the table,
+and then you'll never have to deal with embeddings / vectors after that unless you want to.
+We'll also integrate more popular models and APIs.

docs/src/embeddings/custom_embedding_function.md

@@ -1,212 +0,0 @@
-To use your own custom embedding function, you can follow these 2 simple steps:
-
-1. Create your embedding function by implementing the `EmbeddingFunction` interface
-2. Register your embedding function in the global `EmbeddingFunctionRegistry`.
-
-Let us see how this looks like in action.
-
-![](../assets/embeddings_api.png)
-
-`EmbeddingFunction` and `EmbeddingFunctionRegistry` handle low-level details for serializing schema and model information as metadata. To build a custom embedding function, you don't have to worry about the finer details - simply focus on setting up the model and leave the rest to LanceDB.
-
-## `TextEmbeddingFunction` interface
-
-There is another optional layer of abstraction available: `TextEmbeddingFunction`. You can use this abstraction if your model isn't multi-modal in nature and only needs to operate on text. In such cases, both the source and vector fields will have the same work for vectorization, so you simply just need to setup the model and rest is handled by `TextEmbeddingFunction`. You can read more about the class and its attributes in the class reference.
-
-Let's implement `SentenceTransformerEmbeddings` class. All you need to do is implement the `generate_embeddings()` and `ndims` function to handle the input types you expect and register the class in the global `EmbeddingFunctionRegistry`
-
-```python
-from lancedb.embeddings import register
-from lancedb.util import attempt_import_or_raise
-
-@register("sentence-transformers")
-class SentenceTransformerEmbeddings(TextEmbeddingFunction):
-    name: str = "all-MiniLM-L6-v2"
-    # set more default instance vars like device, etc.
-
-    def __init__(self, **kwargs):
-        super().__init__(**kwargs)
-        self._ndims = None
-    
-    def generate_embeddings(self, texts):
-        return self._embedding_model().encode(list(texts), ...).tolist()
-
-    def ndims(self):
-        if self._ndims is None:
-            self._ndims = len(self.generate_embeddings("foo")[0])
-        return self._ndims
-
-    @cached(cache={}) 
-    def _embedding_model(self):
-        return sentence_transformers.SentenceTransformer(name)
-```
-
-This is a stripped down version of our implementation of `SentenceTransformerEmbeddings` that removes certain optimizations and defaul settings.
-
-Now you can use this embedding function to create your table schema and that's it! you can then ingest data and run queries without manually vectorizing the inputs.
-
-```python
-from lancedb.pydantic import LanceModel, Vector
-
-registry = EmbeddingFunctionRegistry.get_instance()
-stransformer = registry.get("sentence-transformers").create()
-
-class TextModelSchema(LanceModel):
-    vector: Vector(stransformer.ndims) = stransformer.VectorField()
-    text: str = stransformer.SourceField()
-
-tbl = db.create_table("table", schema=TextModelSchema)
-
-tbl.add(pd.DataFrame({"text": ["halo", "world"]}))
-result = tbl.search("world").limit(5)
-```
-
-NOTE:
-
-You can always implement the `EmbeddingFunction` interface directly if you want or need to, `TextEmbeddingFunction` just makes it much simpler and faster for you to do so, by setting up the boiler plat for text-specific use case
-
-## Multi-modal embedding function example
-You can also use the `EmbeddingFunction` interface to implement more complex workflows such as multi-modal embedding function support. LanceDB implements `OpenClipEmeddingFunction` class that suppports multi-modal seach. Here's the implementation that you can use as a reference to build your own multi-modal embedding functions.
-
-```python
-@register("open-clip")
-class OpenClipEmbeddings(EmbeddingFunction):
-    name: str = "ViT-B-32"
-    pretrained: str = "laion2b_s34b_b79k"
-    device: str = "cpu"
-    batch_size: int = 64
-    normalize: bool = True
-    _model = PrivateAttr()
-    _preprocess = PrivateAttr()
-    _tokenizer = PrivateAttr()
-
-    def __init__(self, *args, **kwargs):
-        super().__init__(*args, **kwargs)
-        open_clip = attempt_import_or_raise("open_clip", "open-clip") # EmbeddingFunction util to import external libs and raise if not found
-        model, _, preprocess = open_clip.create_model_and_transforms(
-            self.name, pretrained=self.pretrained
-        )
-        model.to(self.device)
-        self._model, self._preprocess = model, preprocess
-        self._tokenizer = open_clip.get_tokenizer(self.name)
-        self._ndims = None
-
-    def ndims(self):
-        if self._ndims is None:
-            self._ndims = self.generate_text_embeddings("foo").shape[0]
-        return self._ndims
-
-    def compute_query_embeddings(
-        self, query: Union[str, "PIL.Image.Image"], *args, **kwargs
-    ) -> List[np.ndarray]:
-        """
-        Compute the embeddings for a given user query
-
-        Parameters
-        ----------
-        query : Union[str, PIL.Image.Image]
-            The query to embed. A query can be either text or an image.
-        """
-        if isinstance(query, str):
-            return [self.generate_text_embeddings(query)]
-        else:
-            PIL = attempt_import_or_raise("PIL", "pillow")
-            if isinstance(query, PIL.Image.Image):
-                return [self.generate_image_embedding(query)]
-            else:
-                raise TypeError("OpenClip supports str or PIL Image as query")
-
-    def generate_text_embeddings(self, text: str) -> np.ndarray:
-        torch = attempt_import_or_raise("torch")
-        text = self.sanitize_input(text)
-        text = self._tokenizer(text)
-        text.to(self.device)
-        with torch.no_grad():
-            text_features = self._model.encode_text(text.to(self.device))
-            if self.normalize:
-                text_features /= text_features.norm(dim=-1, keepdim=True)
-            return text_features.cpu().numpy().squeeze()
-
-    def sanitize_input(self, images: IMAGES) -> Union[List[bytes], np.ndarray]:
-        """
-        Sanitize the input to the embedding function.
-        """
-        if isinstance(images, (str, bytes)):
-            images = [images]
-        elif isinstance(images, pa.Array):
-            images = images.to_pylist()
-        elif isinstance(images, pa.ChunkedArray):
-            images = images.combine_chunks().to_pylist()
-        return images
-
-    def compute_source_embeddings(
-        self, images: IMAGES, *args, **kwargs
-    ) -> List[np.array]:
-        """
-        Get the embeddings for the given images
-        """
-        images = self.sanitize_input(images)
-        embeddings = []
-        for i in range(0, len(images), self.batch_size):
-            j = min(i + self.batch_size, len(images))
-            batch = images[i:j]
-            embeddings.extend(self._parallel_get(batch))
-        return embeddings
-
-    def _parallel_get(self, images: Union[List[str], List[bytes]]) -> List[np.ndarray]:
-        """
-        Issue concurrent requests to retrieve the image data
-        """
-        with concurrent.futures.ThreadPoolExecutor() as executor:
-            futures = [
-                executor.submit(self.generate_image_embedding, image)
-                for image in images
-            ]
-            return [future.result() for future in futures]
-
-    def generate_image_embedding(
-        self, image: Union[str, bytes, "PIL.Image.Image"]
-    ) -> np.ndarray:
-        """
-        Generate the embedding for a single image
-
-        Parameters
-        ----------
-        image : Union[str, bytes, PIL.Image.Image]
-            The image to embed. If the image is a str, it is treated as a uri.
-            If the image is bytes, it is treated as the raw image bytes.
-        """
-        torch = attempt_import_or_raise("torch")
-        # TODO handle retry and errors for https
-        image = self._to_pil(image)
-        image = self._preprocess(image).unsqueeze(0)
-        with torch.no_grad():
-            return self._encode_and_normalize_image(image)
-
-    def _to_pil(self, image: Union[str, bytes]):
-        PIL = attempt_import_or_raise("PIL", "pillow")
-        if isinstance(image, bytes):
-            return PIL.Image.open(io.BytesIO(image))
-        if isinstance(image, PIL.Image.Image):
-            return image
-        elif isinstance(image, str):
-            parsed = urlparse.urlparse(image)
-            # TODO handle drive letter on windows.
-            if parsed.scheme == "file":
-                return PIL.Image.open(parsed.path)
-            elif parsed.scheme == "":
-                return PIL.Image.open(image if os.name == "nt" else parsed.path)
-            elif parsed.scheme.startswith("http"):
-                return PIL.Image.open(io.BytesIO(url_retrieve(image)))
-            else:
-                raise NotImplementedError("Only local and http(s) urls are supported")
-
-    def _encode_and_normalize_image(self, image_tensor: "torch.Tensor"):
-        """
-        encode a single image tensor and optionally normalize the output
-        """
-        image_features = self._model.encode_image(image_tensor)
-        if self.normalize:
-            image_features /= image_features.norm(dim=-1, keepdim=True)
-        return image_features.cpu().numpy().squeeze()
-```

docs/src/embeddings/default_embedding_functions.md

@@ -1,532 +0,0 @@
-There are various embedding functions available out of the box with LanceDB to manage your embeddings implicitly. We're actively working on adding other popular embedding APIs and models.
-
-## Text embedding functions
-Contains the text embedding functions registered by default.
-
-* Embedding functions have an inbuilt rate limit handler wrapper for source and query embedding function calls that retry with exponential backoff. 
-* Each `EmbeddingFunction` implementation automatically takes `max_retries` as an argument which has the default value of 7.
-
-### Sentence transformers
-Allows you to set parameters when registering a `sentence-transformers` object.
-
-!!! info
-    Sentence transformer embeddings are normalized by default. It is recommended to use normalized embeddings for similarity search.
-
-| Parameter | Type | Default Value | Description |
-|---|---|---|---|
-| `name` | `str` | `all-MiniLM-L6-v2` | The name of the model |
-| `device` | `str` | `cpu` | The device to run the model on (can be `cpu` or `gpu`) |
-| `normalize` | `bool` | `True` | Whether to normalize the input text before feeding it to the model |
-
-
-??? "Check out available sentence-transformer models here!"
-    ```markdown
-    - sentence-transformers/all-MiniLM-L12-v2
-    - sentence-transformers/paraphrase-mpnet-base-v2
-    - sentence-transformers/gtr-t5-base
-    - sentence-transformers/LaBSE
-    - sentence-transformers/all-MiniLM-L6-v2
-    - sentence-transformers/bert-base-nli-max-tokens
-    - sentence-transformers/bert-base-nli-mean-tokens
-    - sentence-transformers/bert-base-nli-stsb-mean-tokens
-    - sentence-transformers/bert-base-wikipedia-sections-mean-tokens
-    - sentence-transformers/bert-large-nli-cls-token
-    - sentence-transformers/bert-large-nli-max-tokens
-    - sentence-transformers/bert-large-nli-mean-tokens
-    - sentence-transformers/bert-large-nli-stsb-mean-tokens
-    - sentence-transformers/distilbert-base-nli-max-tokens
-    - sentence-transformers/distilbert-base-nli-mean-tokens
-    - sentence-transformers/distilbert-base-nli-stsb-mean-tokens
-    - sentence-transformers/distilroberta-base-msmarco-v1
-    - sentence-transformers/distilroberta-base-msmarco-v2
-    - sentence-transformers/nli-bert-base-cls-pooling
-    - sentence-transformers/nli-bert-base-max-pooling
-    - sentence-transformers/nli-bert-base
-    - sentence-transformers/nli-bert-large-cls-pooling
-    - sentence-transformers/nli-bert-large-max-pooling
-    - sentence-transformers/nli-bert-large
-    - sentence-transformers/nli-distilbert-base-max-pooling
-    - sentence-transformers/nli-distilbert-base
-    - sentence-transformers/nli-roberta-base
-    - sentence-transformers/nli-roberta-large
-    - sentence-transformers/roberta-base-nli-mean-tokens
-    - sentence-transformers/roberta-base-nli-stsb-mean-tokens
-    - sentence-transformers/roberta-large-nli-mean-tokens
-    - sentence-transformers/roberta-large-nli-stsb-mean-tokens
-    - sentence-transformers/stsb-bert-base
-    - sentence-transformers/stsb-bert-large
-    - sentence-transformers/stsb-distilbert-base
-    - sentence-transformers/stsb-roberta-base
-    - sentence-transformers/stsb-roberta-large
-    - sentence-transformers/xlm-r-100langs-bert-base-nli-mean-tokens
-    - sentence-transformers/xlm-r-100langs-bert-base-nli-stsb-mean-tokens
-    - sentence-transformers/xlm-r-base-en-ko-nli-ststb
-    - sentence-transformers/xlm-r-bert-base-nli-mean-tokens
-    - sentence-transformers/xlm-r-bert-base-nli-stsb-mean-tokens
-    - sentence-transformers/xlm-r-large-en-ko-nli-ststb
-    - sentence-transformers/bert-base-nli-cls-token
-    - sentence-transformers/all-distilroberta-v1
-    - sentence-transformers/multi-qa-MiniLM-L6-dot-v1
-    - sentence-transformers/multi-qa-distilbert-cos-v1
-    - sentence-transformers/multi-qa-distilbert-dot-v1
-    - sentence-transformers/multi-qa-mpnet-base-cos-v1
-    - sentence-transformers/multi-qa-mpnet-base-dot-v1
-    - sentence-transformers/nli-distilroberta-base-v2
-    - sentence-transformers/all-MiniLM-L6-v1
-    - sentence-transformers/all-mpnet-base-v1
-    - sentence-transformers/all-mpnet-base-v2
-    - sentence-transformers/all-roberta-large-v1
-    - sentence-transformers/allenai-specter
-    - sentence-transformers/average_word_embeddings_glove.6B.300d
-    - sentence-transformers/average_word_embeddings_glove.840B.300d
-    - sentence-transformers/average_word_embeddings_komninos
-    - sentence-transformers/average_word_embeddings_levy_dependency
-    - sentence-transformers/clip-ViT-B-32-multilingual-v1
-    - sentence-transformers/clip-ViT-B-32
-    - sentence-transformers/distilbert-base-nli-stsb-quora-ranking
-    - sentence-transformers/distilbert-multilingual-nli-stsb-quora-ranking
-    - sentence-transformers/distilroberta-base-paraphrase-v1
-    - sentence-transformers/distiluse-base-multilingual-cased-v1
-    - sentence-transformers/distiluse-base-multilingual-cased-v2
-    - sentence-transformers/distiluse-base-multilingual-cased
-    - sentence-transformers/facebook-dpr-ctx_encoder-multiset-base
-    - sentence-transformers/facebook-dpr-ctx_encoder-single-nq-base
-    - sentence-transformers/facebook-dpr-question_encoder-multiset-base
-    - sentence-transformers/facebook-dpr-question_encoder-single-nq-base
-    - sentence-transformers/gtr-t5-large
-    - sentence-transformers/gtr-t5-xl
-    - sentence-transformers/gtr-t5-xxl
-    - sentence-transformers/msmarco-MiniLM-L-12-v3
-    - sentence-transformers/msmarco-MiniLM-L-6-v3
-    - sentence-transformers/msmarco-MiniLM-L12-cos-v5
-    - sentence-transformers/msmarco-MiniLM-L6-cos-v5
-    - sentence-transformers/msmarco-bert-base-dot-v5
-    - sentence-transformers/msmarco-bert-co-condensor
-    - sentence-transformers/msmarco-distilbert-base-dot-prod-v3
-    - sentence-transformers/msmarco-distilbert-base-tas-b
-    - sentence-transformers/msmarco-distilbert-base-v2
-    - sentence-transformers/msmarco-distilbert-base-v3
-    - sentence-transformers/msmarco-distilbert-base-v4
-    - sentence-transformers/msmarco-distilbert-cos-v5
-    - sentence-transformers/msmarco-distilbert-dot-v5
-    - sentence-transformers/msmarco-distilbert-multilingual-en-de-v2-tmp-lng-aligned
-    - sentence-transformers/msmarco-distilbert-multilingual-en-de-v2-tmp-trained-scratch
-    - sentence-transformers/msmarco-distilroberta-base-v2
-    - sentence-transformers/msmarco-roberta-base-ance-firstp
-    - sentence-transformers/msmarco-roberta-base-v2
-    - sentence-transformers/msmarco-roberta-base-v3
-    - sentence-transformers/multi-qa-MiniLM-L6-cos-v1
-    - sentence-transformers/nli-mpnet-base-v2
-    - sentence-transformers/nli-roberta-base-v2
-    - sentence-transformers/nq-distilbert-base-v1
-    - sentence-transformers/paraphrase-MiniLM-L12-v2
-    - sentence-transformers/paraphrase-MiniLM-L3-v2
-    - sentence-transformers/paraphrase-MiniLM-L6-v2
-    - sentence-transformers/paraphrase-TinyBERT-L6-v2
-    - sentence-transformers/paraphrase-albert-base-v2
-    - sentence-transformers/paraphrase-albert-small-v2
-    - sentence-transformers/paraphrase-distilroberta-base-v1
-    - sentence-transformers/paraphrase-distilroberta-base-v2
-    - sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
-    - sentence-transformers/paraphrase-multilingual-mpnet-base-v2
-    - sentence-transformers/paraphrase-xlm-r-multilingual-v1
-    - sentence-transformers/quora-distilbert-base
-    - sentence-transformers/quora-distilbert-multilingual
-    - sentence-transformers/sentence-t5-base
-    - sentence-transformers/sentence-t5-large
-    - sentence-transformers/sentence-t5-xxl
-    - sentence-transformers/sentence-t5-xl
-    - sentence-transformers/stsb-distilroberta-base-v2
-    - sentence-transformers/stsb-mpnet-base-v2
-    - sentence-transformers/stsb-roberta-base-v2
-    - sentence-transformers/stsb-xlm-r-multilingual
-    - sentence-transformers/xlm-r-distilroberta-base-paraphrase-v1
-    - sentence-transformers/clip-ViT-L-14
-    - sentence-transformers/clip-ViT-B-16
-    - sentence-transformers/use-cmlm-multilingual
-    - sentence-transformers/all-MiniLM-L12-v1
-    ```
-
-!!! info
-    You can also load many other model architectures from the library. For example models from sources such as BAAI, nomic, salesforce research, etc.
-    See this HF hub page for all [supported models](https://huggingface.co/models?library=sentence-transformers).
-
-!!! note "BAAI Embeddings example"
-    Here is an example that uses BAAI embedding model from the HuggingFace Hub [supported models](https://huggingface.co/models?library=sentence-transformers)
-    ```python
-    import lancedb
-    from lancedb.pydantic import LanceModel, Vector
-    from lancedb.embeddings import get_registry
-
-    db = lancedb.connect("/tmp/db")
-    model = get_registry().get("sentence-transformers").create(name="BAAI/bge-small-en-v1.5", device="cpu")
-
-    class Words(LanceModel):
-        text: str = model.SourceField()
-        vector: Vector(model.ndims()) = model.VectorField()
-
-    table = db.create_table("words", schema=Words)
-    table.add(
-        [
-            {"text": "hello world"},
-            {"text": "goodbye world"}
-        ]
-    )
-
-    query = "greetings"
-    actual = table.search(query).limit(1).to_pydantic(Words)[0]
-    print(actual.text)
-    ```
-Visit sentence-transformers [HuggingFace HUB](https://huggingface.co/sentence-transformers) page for more information on the available models.
-
-
-### Huggingface embedding models
-We offer support for all huggingface models (which can be loaded via [transformers](https://huggingface.co/docs/transformers/en/index) library). The default model is `colbert-ir/colbertv2.0` which also has its own special callout - `registry.get("colbert")` 
-
-Example usage - 
-```python
-import lancedb
-import pandas as pd
-
-from lancedb.embeddings import get_registry
-from lancedb.pydantic import LanceModel, Vector
-
-model = get_registry().get("huggingface").create(name='facebook/bart-base')
-
-class TextModel(LanceModel):
-    text: str = model.SourceField()
-    vector: Vector(model.ndims()) = model.VectorField()
-
-df = pd.DataFrame({"text": ["hi hello sayonara", "goodbye world"]})
-table = db.create_table("greets", schema=Words)
-table.add()
-query = "old greeting"
-actual = table.search(query).limit(1).to_pydantic(Words)[0]
-print(actual.text)
-```
-
-
-### OpenAI embeddings
-LanceDB registers the OpenAI embeddings function in the registry by default, as `openai`. Below are the parameters that you can customize when creating the instances:
-
-| Parameter | Type | Default Value | Description |
-|---|---|---|---|
-| `name` | `str` | `"text-embedding-ada-002"` | The name of the model. |
-| `dim` | `int` |  Model default   | For OpenAI's newer text-embedding-3 model, we can specify a dimensionality that is smaller than the 1536 size. This feature supports it |
-
-
-```python
-import lancedb
-from lancedb.pydantic import LanceModel, Vector
-from lancedb.embeddings import get_registry
-
-db = lancedb.connect("/tmp/db")
-func = get_registry().get("openai").create(name="text-embedding-ada-002")
-
-class Words(LanceModel):
-    text: str = func.SourceField()
-    vector: Vector(func.ndims()) = func.VectorField()
-
-table = db.create_table("words", schema=Words, mode="overwrite")
-table.add(
-    [
-        {"text": "hello world"},
-        {"text": "goodbye world"}
-    ]
-    )
-
-query = "greetings"
-actual = table.search(query).limit(1).to_pydantic(Words)[0]
-print(actual.text)
-```
-
-### Instructor Embeddings
-[Instructor](https://instructor-embedding.github.io/) is an instruction-finetuned text embedding model that can generate text embeddings tailored to any task (e.g. classification, retrieval, clustering, text evaluation, etc.) and domains (e.g. science, finance, etc.) by simply providing the task instruction, without any finetuning.
-
-If you want to calculate customized embeddings for specific sentences, you can follow the unified template to write instructions.
-
-!!! info
-    Represent the `domain` `text_type` for `task_objective`:
-
-    * `domain` is optional, and it specifies the domain of the text, e.g. science, finance, medicine, etc.
-    * `text_type` is required, and it specifies the encoding unit, e.g. sentence, document, paragraph, etc.
-    * `task_objective` is optional, and it specifies the objective of embedding, e.g. retrieve a document, classify the sentence, etc.
-
-More information about the model can be found at the [source URL](https://github.com/xlang-ai/instructor-embedding).
-
-| Argument | Type | Default | Description |
-|---|---|---|---|
-| `name` | `str` | "hkunlp/instructor-base" | The name of the model to use |
-| `batch_size` | `int` | `32` | The batch size to use when generating embeddings |
-| `device` | `str` | `"cpu"` | The device to use when generating embeddings |
-| `show_progress_bar` | `bool` | `True` | Whether to show a progress bar when generating embeddings |
-| `normalize_embeddings` | `bool` | `True` | Whether to normalize the embeddings |
-| `quantize` | `bool` | `False` | Whether to quantize the model |
-| `source_instruction` | `str` | `"represent the docuement for retreival"` | The instruction for the source column |
-| `query_instruction` | `str` | `"represent the document for retreiving the most similar documents"` | The instruction for the query |
-
-
-
-```python
-import lancedb
-from lancedb.pydantic import LanceModel, Vector
-from lancedb.embeddings import get_registry, InstuctorEmbeddingFunction
-
-instructor = get_registry().get("instructor").create(
-                            source_instruction="represent the docuement for retreival",
-                            query_instruction="represent the document for retreiving the most similar documents"
-                            )
-
-class Schema(LanceModel):
-    vector: Vector(instructor.ndims()) = instructor.VectorField()
-    text: str = instructor.SourceField()
-
-db = lancedb.connect("~/.lancedb")
-tbl = db.create_table("test", schema=Schema, mode="overwrite")
-
-texts = [{"text": "Capitalism has been dominant in the Western world since the end of feudalism, but most feel[who?] that..."},
-        {"text": "The disparate impact theory is especially controversial under the Fair Housing Act because the Act..."},
-        {"text": "Disparate impact in United States labor law refers to practices in employment, housing, and other areas that.."}]
-
-tbl.add(texts)
-```
-
-### Gemini Embeddings
-With Google's Gemini, you can represent text (words, sentences, and blocks of text) in a vectorized form, making it easier to compare and contrast embeddings. For example, two texts that share a similar subject matter or sentiment should have similar embeddings, which can be identified through mathematical comparison techniques such as cosine similarity. For more on how and why you should use embeddings, refer to the Embeddings guide.
-The Gemini Embedding Model API supports various task types:
-
-| Task Type               | Description                                                                                                                                                |
-|-------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| "`retrieval_query`"     | Specifies the given text is a query in a search/retrieval setting.                                                                                         |
-| "`retrieval_document`"  | Specifies the given text is a document in a search/retrieval setting. Using this task type requires a title but is automatically proided by Embeddings API |
-| "`semantic_similarity`" | Specifies the given text will be used for Semantic Textual Similarity (STS).                                                                               |
-| "`classification`"      | Specifies that the embeddings will be used for classification.                                                                                             |
-| "`clusering`"           | Specifies that the embeddings will be used for clustering.                                                                                                 |
-
-
-Usage Example:
-
-```python
-import lancedb
-import pandas as pd
-from lancedb.pydantic import LanceModel, Vector
-from lancedb.embeddings import get_registry
-
-
-model = get_registry().get("gemini-text").create()
-
-class TextModel(LanceModel):
-    text: str = model.SourceField()
-    vector: Vector(model.ndims()) = model.VectorField()
-
-df = pd.DataFrame({"text": ["hello world", "goodbye world"]})
-db = lancedb.connect("~/.lancedb")
-tbl = db.create_table("test", schema=TextModel, mode="overwrite")
-
-tbl.add(df)
-rs = tbl.search("hello").limit(1).to_pandas()
-```
-
-### AWS Bedrock Text Embedding Functions
-AWS Bedrock supports multiple base models for generating text embeddings. You need to setup the AWS credentials to use this embedding function.
-You can do so by using `awscli` and also add your session_token:
-```shell
-aws configure
-aws configure set aws_session_token "<your_session_token>"
-```
-to ensure that the credentials are set up correctly, you can run the following command:
-```shell
-aws sts get-caller-identity
-```
-
-Supported Embedding modelIDs are:
-* `amazon.titan-embed-text-v1`
-* `cohere.embed-english-v3`
-* `cohere.embed-multilingual-v3`
-
-Supported parameters (to be passed in `create` method) are:
-
-| Parameter | Type | Default Value | Description |
-|---|---|---|---|
-| **name** | str | "amazon.titan-embed-text-v1" | The model ID of the bedrock model to use. Supported base models for Text Embeddings: amazon.titan-embed-text-v1, cohere.embed-english-v3, cohere.embed-multilingual-v3 |
-| **region** | str | "us-east-1" | Optional name of the AWS Region in which the service should be called (e.g., "us-east-1"). |
-| **profile_name** | str | None | Optional name of the AWS profile to use for calling the Bedrock service. If not specified, the default profile will be used. |
-| **assumed_role** | str | None | Optional ARN of an AWS IAM role to assume for calling the Bedrock service. If not specified, the current active credentials will be used. |
-| **role_session_name** | str | "lancedb-embeddings" | Optional name of the AWS IAM role session to use for calling the Bedrock service. If not specified, a "lancedb-embeddings" name will be used. |
-| **runtime** | bool | True | Optional choice of getting different client to perform operations with the Amazon Bedrock service. |
-| **max_retries** | int | 7 | Optional number of retries to perform when a request fails. |
-
-Usage Example:
-
-```python
-import lancedb
-from lancedb.pydantic import LanceModel, Vector
-from lancedb.embeddings import get_registry
-
-model = get_registry().get("bedrock-text").create()
-
-class TextModel(LanceModel):
-    text: str = model.SourceField()
-    vector: Vector(model.ndims()) = model.VectorField()
-
-df = pd.DataFrame({"text": ["hello world", "goodbye world"]})
-db = lancedb.connect("tmp_path")
-tbl = db.create_table("test", schema=TextModel, mode="overwrite")
-
-tbl.add(df)
-rs = tbl.search("hello").limit(1).to_pandas()
-```
-
-## Multi-modal embedding functions
-Multi-modal embedding functions allow you to query your table using both images and text.
-
-### OpenClip embeddings
-We support CLIP model embeddings using the open source alternative, [open-clip](https://github.com/mlfoundations/open_clip) which supports various customizations. It is registered as `open-clip` and supports the following customizations:
-
-| Parameter | Type | Default Value | Description |
-|---|---|---|---|
-| `name` | `str` | `"ViT-B-32"` | The name of the model. |
-| `pretrained` | `str` | `"laion2b_s34b_b79k"` | The name of the pretrained model to load. |
-| `device` | `str` | `"cpu"` | The device to run the model on. Can be `"cpu"` or `"gpu"`. |
-| `batch_size` | `int` | `64` | The number of images to process in a batch. |
-| `normalize` | `bool` | `True` | Whether to normalize the input images before feeding them to the model. |
-
-This embedding function supports ingesting images as both bytes and urls. You can query them using both test and other images.
-
-!!! info
-    LanceDB supports ingesting images directly from accessible links.
-
-```python
-import lancedb
-from lancedb.pydantic import LanceModel, Vector
-from lancedb.embeddings import get_registry
-
-db = lancedb.connect(tmp_path)
-func = get_registry.get("open-clip").create()
-
-class Images(LanceModel):
-    label: str
-    image_uri: str = func.SourceField() # image uri as the source
-    image_bytes: bytes = func.SourceField() # image bytes as the source
-    vector: Vector(func.ndims()) = func.VectorField() # vector column 
-    vec_from_bytes: Vector(func.ndims()) = func.VectorField() # Another vector column 
-
-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
-image_bytes = [requests.get(uri).content for uri in uris]
-table.add(
-    [{"label": labels, "image_uri": uris, "image_bytes": image_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").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(io.BytesIO(image_bytes))
-actual = table.search(query_image).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)
-
-```
-
-### Imagebind embeddings
-We have support for [imagebind](https://github.com/facebookresearch/ImageBind) model embeddings. You can download our version of the packaged model via - `pip install imagebind-packaged==0.1.2`.
-
-This function is registered as `imagebind` and supports Audio, Video and Text modalities(extending to Thermal,Depth,IMU data):
-
-| Parameter | Type | Default Value | Description |
-|---|---|---|---|
-| `name` | `str` | `"imagebind_huge"` | Name of the model. |
-| `device` | `str` | `"cpu"` | The device to run the model on. Can be `"cpu"` or `"gpu"`. |
-| `normalize` | `bool` | `False` | set to `True` to normalize your inputs before model ingestion. |
-
-Below is an example demonstrating how the API works:
-
-```python
-import lancedb
-from lancedb.pydantic import LanceModel, Vector
-from lancedb.embeddings import get_registry
-
-db = lancedb.connect(tmp_path)
-func = get_registry.get("imagebind").create()
-
-class ImageBindModel(LanceModel):
-    text: str
-    image_uri: str = func.SourceField()
-    audio_path: str
-    vector: Vector(func.ndims()) = func.VectorField()
-
-# add locally accessible image paths
-text_list=["A dog.", "A car", "A bird"]
-image_paths=[".assets/dog_image.jpg", ".assets/car_image.jpg", ".assets/bird_image.jpg"]
-audio_paths=[".assets/dog_audio.wav", ".assets/car_audio.wav", ".assets/bird_audio.wav"]
-
-# Load data
-inputs = [
-    {"text": a, "audio_path": b, "image_uri": c}
-    for a, b, c in zip(text_list, audio_paths, image_paths)
-]
-
-#create table and add data
-table = db.create_table("img_bind", schema=ImageBindModel)
-table.add(inputs)
-```
-
-Now, we can search using any modality:
-
-#### image search
-```python
-query_image = "./assets/dog_image2.jpg" #download an image and enter that path here
-actual = table.search(query_image).limit(1).to_pydantic(ImageBindModel)[0]
-print(actual.text == "dog")
-```
-#### audio search
-
-```python
-query_audio = "./assets/car_audio2.wav" #download an audio clip and enter path here
-actual = table.search(query_audio).limit(1).to_pydantic(ImageBindModel)[0]
-print(actual.text == "car")
-```
-#### Text search
-You can add any input query and fetch the result as follows:
-```python
-query = "an animal which flies and tweets" 
-actual = table.search(query).limit(1).to_pydantic(ImageBindModel)[0]
-print(actual.text == "bird")
-```
-
-If you have any questions about the embeddings API, supported models, or see a relevant model missing, please raise an issue [on GitHub](https://github.com/lancedb/lancedb/issues).

docs/src/embeddings/embedding_functions.md

@@ -1,169 +0,0 @@
-Representing multi-modal data as vector embeddings is becoming a standard practice. Embedding functions can themselves be thought of as key part of the data processing pipeline that each request has to be passed through. The assumption here is: after initial setup, these components and the underlying methodology are not expected to change for a particular project.
-
-For this purpose, LanceDB introduces an **embedding functions API**, that allow you simply set up once, during the configuration stage of your project. After this, the table remembers it, effectively making the embedding functions *disappear in the background* so you don't have to worry about manually passing callables, and instead, simply focus on the rest of your data engineering pipeline.
-
-!!! warning
-    Using the embedding function registry means that you don't have to explicitly generate the embeddings yourself. 
-    However, if your embedding function changes, you'll have to re-configure your table with the new embedding function 
-    and regenerate the embeddings. In the future, we plan to support the ability to change the embedding function via
-    table metadata and have LanceDB automatically take care of regenerating the embeddings.
-
-
-## 1. Define the embedding function
-
-=== "Python"
-    In the LanceDB python SDK, we define a global embedding function registry with
-    many different embedding models and even more coming soon. 
-    Here's let's an implementation of CLIP as example.
-
-    ```python
-    from lancedb.embeddings import get_registry
-
-    registry = get_registry()
-    clip = registry.get("open-clip").create()
-    ```
-
-    You can also define your own embedding function by implementing the `EmbeddingFunction` 
-    abstract base interface. It subclasses Pydantic Model which can be utilized to write complex schemas simply as we'll see next!
-
-=== "JavaScript""
-    In the TypeScript SDK, the choices are more limited. For now, only the OpenAI
-    embedding function is available.
-
-    ```javascript
-    const lancedb = require("vectordb");
-
-    // You need to provide an OpenAI API key
-    const apiKey = "sk-..."
-    // The embedding function will create embeddings for the 'text' column
-    const embedding = new lancedb.OpenAIEmbeddingFunction('text', apiKey)
-    ```
-
-## 2. Define the data model or schema
-
-=== "Python"
-    The embedding function defined above abstracts away all the details about the models and dimensions required to define the schema. You can simply set a field as **source** or **vector** column. Here's how:
-
-    ```python
-    class Pets(LanceModel):
-        vector: Vector(clip.ndims()) = clip.VectorField()
-        image_uri: str = clip.SourceField()
-    ```
-
-    `VectorField` tells LanceDB to use the clip embedding function to generate query embeddings for the `vector` column and `SourceField` ensures that when adding data, we automatically use the specified embedding function to encode `image_uri`.
-
-=== "JavaScript"
-
-    For the TypeScript SDK, a schema can be inferred from input data, or an explicit
-    Arrow schema can be provided.
-
-## 3. Create table and add data
-
-Now that we have chosen/defined our embedding function and the schema, 
-we can create the table and ingest data without needing to explicitly generate
-the embeddings at all:
-
-=== "Python"
-    ```python
-    db = lancedb.connect("~/lancedb")
-    table = db.create_table("pets", schema=Pets)
-
-    table.add([{"image_uri": u} for u in uris])
-    ```
-
-=== "JavaScript"
-
-    ```javascript
-    const db = await lancedb.connect("data/sample-lancedb");
-    const data = [
-    { text: "pepperoni"},
-    { text: "pineapple"}
-    ]
-
-    const table = await db.createTable("vectors", data, embedding)
-    ```
-
-## 4. Querying your table
-Not only can you forget about the embeddings during ingestion, you also don't
-need to worry about it when you query the table:
-
-=== "Python"
-
-    Our OpenCLIP query embedding function supports querying via both text and images:
-
-    ```python
-    results = (
-        table.search("dog")
-        .limit(10)
-        .to_pandas()
-    )
-    ```
-
-    Or we can search using an image:
-
-    ```python
-    p = Path("path/to/images/samoyed_100.jpg")
-    query_image = Image.open(p)
-    results = (
-        table.search(query_image)
-        .limit(10)
-        .to_pandas()
-    )
-    ```
-
-    Both of the above snippet returns a pandas DataFrame with the 10 closest vectors to the query.
-
-=== "JavaScript"
-
-    ```javascript
-    const results = await table
-    .search("What's the best pizza topping?")
-    .limit(10)
-    .execute()
-    ```    
-    
-    The above snippet returns an array of records with the top 10 nearest neighbors to the query.
-
----
-
-## Rate limit Handling
-`EmbeddingFunction` class wraps the calls for source and query embedding generation inside a rate limit handler that retries the requests with exponential backoff after successive failures. By default, the maximum retires is set to 7. You can tune it by setting it to a different number, or disable it by setting it to 0.
-
-An example of how to do this is shown below:
-
-```python
-clip = registry.get("open-clip").create() # Defaults to 7 max retries
-clip = registry.get("open-clip").create(max_retries=10) # Increase max retries to 10
-clip = registry.get("open-clip").create(max_retries=0) # Retries disabled
-```
-
-!!! note
-    Embedding functions can also fail due to other errors that have nothing to do with rate limits.
-    This is why the error is also logged.
-
-## Some fun with Pydantic
-
-LanceDB is integrated with Pydantic, which was used in the example above to define the schema in Python. It's also used behind the scenes by the embedding function API to ingest useful information as table metadata.
-
-You can also use the integration for adding utility operations in the schema. For example, in our multi-modal example, you can search images using text or another image. Let's define a utility function to plot the image.
-
-```python
-class Pets(LanceModel):
-    vector: Vector(clip.ndims()) = clip.VectorField()
-    image_uri: str = clip.SourceField()
-
-    @property
-    def image(self):
-        return Image.open(self.image_uri)
-```
-Now, you can covert your search results to a Pydantic model and use this property.
-
-```python
-rs = table.search(query_image).limit(3).to_pydantic(Pets)
-rs[2].image
-```
-
-![](../assets/dog_clip_output.png)
-
-Now that you have the basic idea about LanceDB embedding functions and the embedding function registry,
-let's dive deeper into defining your own [custom functions](./custom_embedding_function.md).

docs/src/embeddings/index.md

@@ -1,74 +0,0 @@
-Due to the nature of vector embeddings, they can be used to represent any kind of data, from text to images to audio. 
-This makes them a very powerful tool for machine learning practitioners. 
-However, there's no one-size-fits-all solution for generating embeddings - there are many different libraries and APIs 
-(both commercial and open source) that can be used to generate embeddings from structured/unstructured data.
-
-LanceDB supports 3 methods of working with embeddings.
-
-1. You can manually generate embeddings for the data and queries. This is done outside of LanceDB.
-2. You can use the built-in [embedding functions](./embedding_functions.md) to embed the data and queries in the background.
-3. For python users, you can define your own [custom embedding function](./custom_embedding_function.md)
-   that extends the default embedding functions.
-
-For python users, there is also a legacy [with_embeddings API](./legacy.md).
-It is retained for compatibility and will be removed in a future version.
-
-## Quickstart
-
-To get started with embeddings, you can use the built-in embedding functions.
-
-### OpenAI Embedding function
-LanceDB registers the OpenAI embeddings function in the registry as `openai`. You can pass any supported model name to the `create`. By default it uses `"text-embedding-ada-002"`.
-
-```python
-import lancedb
-from lancedb.pydantic import LanceModel, Vector
-from lancedb.embeddings import get_registry
-
-db = lancedb.connect("/tmp/db")
-func = get_registry().get("openai").create(name="text-embedding-ada-002")
-
-class Words(LanceModel):
-    text: str = func.SourceField()
-    vector: Vector(func.ndims()) = func.VectorField()
-
-table = db.create_table("words", schema=Words, mode="overwrite")
-table.add(
-    [
-        {"text": "hello world"},
-        {"text": "goodbye world"}
-    ]
-    )
-
-query = "greetings"
-actual = table.search(query).limit(1).to_pydantic(Words)[0]
-print(actual.text)
-```
-
-### Sentence Transformers Embedding function
-LanceDB registers the Sentence Transformers embeddings function in the registry as `sentence-transformers`. You can pass any supported model name to the `create`. By default it uses `"sentence-transformers/paraphrase-MiniLM-L6-v2"`.
-
-```python
-import lancedb
-from lancedb.pydantic import LanceModel, Vector
-from lancedb.embeddings import get_registry
-
-db = lancedb.connect("/tmp/db")
-model = get_registry().get("sentence-transformers").create(name="BAAI/bge-small-en-v1.5", device="cpu")
-
-class Words(LanceModel):
-    text: str = model.SourceField()
-    vector: Vector(model.ndims()) = model.VectorField()
-
-table = db.create_table("words", schema=Words)
-table.add(
-    [
-        {"text": "hello world"},
-        {"text": "goodbye world"}
-    ]
-)
-
-query = "greetings"
-actual = table.search(query).limit(1).to_pydantic(Words)[0]
-print(actual.text)
-```

docs/src/embeddings/legacy.md

@@ -1,99 +0,0 @@
-The legacy `with_embeddings` API is for Python only and is deprecated.
-
-### Hugging Face
-
-The most popular open source option is to use the [sentence-transformers](https://www.sbert.net/) 
-library, which can be installed via pip.
-
-```bash
-pip install sentence-transformers
-```
-
-The example below shows how to use the `paraphrase-albert-small-v2` model to generate embeddings 
-for a given document.
-
-```python
-from sentence_transformers import SentenceTransformer
-
-name="paraphrase-albert-small-v2"
-model = SentenceTransformer(name)
-
-# used for both training and querying
-def embed_func(batch):
-    return [model.encode(sentence) for sentence in batch]
-```
-
-
-### OpenAI
-
-Another popular alternative is to use an external API like OpenAI's [embeddings API](https://platform.openai.com/docs/guides/embeddings/what-are-embeddings).
-
-```python
-import openai
-import os
-
-# Configuring the environment variable OPENAI_API_KEY
-if "OPENAI_API_KEY" not in os.environ:
-# OR set the key here as a variable
-openai.api_key = "sk-..."
-
-client = openai.OpenAI()
-
-def embed_func(c):    
-    rs = client.embeddings.create(input=c, model="text-embedding-ada-002")
-    return [record.embedding for record in rs["data"]]
-```
-
-
-## Applying an embedding function to data
-
-Using an embedding function, you can apply it to raw data
-to generate embeddings for each record.
-
-Say you have a pandas DataFrame with a `text` column that you want embedded,
-you can use the `with_embeddings` function to generate embeddings and add them to 
-an existing table.
-
-```python
-    import pandas as pd
-    from lancedb.embeddings import with_embeddings
-
-    df = pd.DataFrame(
-        [
-            {"text": "pepperoni"},
-            {"text": "pineapple"}
-        ]
-    )
-    data = with_embeddings(embed_func, df)
-
-    # The output is used to create / append to a table
-    tbl = db.create_table("my_table", data=data)
-```
-
-If your data is in a different column, you can specify the `column` kwarg to `with_embeddings`.
-
-By default, LanceDB calls the function with batches of 1000 rows. This can be configured
-using the `batch_size` parameter to `with_embeddings`.
-
-LanceDB automatically wraps the function with retry and rate-limit logic to ensure the OpenAI
-API call is reliable.
-
-## Querying using an embedding function
-
-!!! warning
-    At query time, you **must** use the same embedding function you used to vectorize your data.
-    If you use a different embedding function, the embeddings will not reside in the same vector
-    space and the results will be nonsensical.
-
-=== "Python"
-     ```python
-     query = "What's the best pizza topping?"
-     query_vector = embed_func([query])[0]
-     results = (
-        tbl.search(query_vector)
-        .limit(10)
-        .to_pandas()
-     )
-     ```
-
-     The above snippet returns a pandas DataFrame with the 10 closest vectors to the query.

docs/src/examples/examples_js.md

@@ -1,11 +0,0 @@
-# Examples: JavaScript
-
-To help you get started, we provide some examples, projects and applications that use the LanceDB JavaScript API. You can always find the latest examples in our [VectorDB Recipes](https://github.com/lancedb/vectordb-recipes) repository.
-
-| Example | Scripts  |
-|-------- | ------   |
-| | |
-| [Youtube transcript search bot](https://github.com/lancedb/vectordb-recipes/tree/main/examples/youtube_bot/) | [![JavaScript](https://img.shields.io/badge/javascript-%23323330.svg?style=for-the-badge&logo=javascript&logoColor=%23F7DF1E)](https://github.com/lancedb/vectordb-recipes/tree/main/examples/youtube_bot/index.js)|
-| [Langchain: Code Docs QA bot](https://github.com/lancedb/vectordb-recipes/tree/main/examples/Code-Documentation-QA-Bot/) | [![JavaScript](https://img.shields.io/badge/javascript-%23323330.svg?style=for-the-badge&logo=javascript&logoColor=%23F7DF1E)](https://github.com/lancedb/vectordb-recipes/tree/main/examples/Code-Documentation-QA-Bot/index.js)|
-| [AI Agents: Reducing Hallucination](https://github.com/lancedb/vectordb-recipes/tree/main/examples/reducing_hallucinations_ai_agents/) | [![JavaScript](https://img.shields.io/badge/javascript-%23323330.svg?style=for-the-badge&logo=javascript&logoColor=%23F7DF1E)](https://github.com/lancedb/vectordb-recipes/tree/main/examples/reducing_hallucinations_ai_agents/index.js)|
-| [TransformersJS Embedding example](https://github.com/lancedb/vectordb-recipes/tree/main/examples/js-transformers/) | [![JavaScript](https://img.shields.io/badge/javascript-%23323330.svg?style=for-the-badge&logo=javascript&logoColor=%23F7DF1E)](https://github.com/lancedb/vectordb-recipes/tree/main/examples/js-transformers/index.js)  |

docs/src/examples/examples_python.md

@@ -1,17 +0,0 @@
-# Examples: Python
-
-To help you get started, we provide some examples, projects and applications that use the LanceDB Python API. You can always find the latest examples in our [VectorDB Recipes](https://github.com/lancedb/vectordb-recipes) repository.
-
-| Example | Interactive Envs | Scripts  |
-|-------- | ---------------- | ------   |
-| | | |
-| [Youtube transcript search bot](https://github.com/lancedb/vectordb-recipes/tree/main/examples/youtube_bot/) | <a href="https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/youtube_bot/main.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>| [![Python](https://img.shields.io/badge/python-3670A0?style=for-the-badge&logo=python&logoColor=ffdd54)](https://github.com/lancedb/vectordb-recipes/tree/main/examples/youtube_bot/main.py)|
-| [Langchain: Code Docs QA bot](https://github.com/lancedb/vectordb-recipes/tree/main/examples/Code-Documentation-QA-Bot/) | <a href="https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/Code-Documentation-QA-Bot/main.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>| [![Python](https://img.shields.io/badge/python-3670A0?style=for-the-badge&logo=python&logoColor=ffdd54)](https://github.com/lancedb/vectordb-recipes/tree/main/examples/Code-Documentation-QA-Bot/main.py) |
-| [AI Agents: Reducing Hallucination](https://github.com/lancedb/vectordb-recipes/tree/main/examples/reducing_hallucinations_ai_agents/) | <a href="https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/reducing_hallucinations_ai_agents/main.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>| [![Python](https://img.shields.io/badge/python-3670A0?style=for-the-badge&logo=python&logoColor=ffdd54)](https://github.com/lancedb/vectordb-recipes/tree/main/examples/reducing_hallucinations_ai_agents/main.py)|
-| [Multimodal CLIP: DiffusionDB](https://github.com/lancedb/vectordb-recipes/tree/main/examples/multimodal_clip/) | <a href="https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/multimodal_clip/main.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>| [![Python](https://img.shields.io/badge/python-3670A0?style=for-the-badge&logo=python&logoColor=ffdd54)](https://github.com/lancedb/vectordb-recipes/tree/main/examples/multimodal_clip/main.py)  |
-| [Multimodal CLIP: Youtube videos](https://github.com/lancedb/vectordb-recipes/tree/main/examples/multimodal_video_search/) | <a href="https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/multimodal_video_search/main.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>| [![Python](https://img.shields.io/badge/python-3670A0?style=for-the-badge&logo=python&logoColor=ffdd54)](https://github.com/lancedb/vectordb-recipes/tree/main/examples/multimodal_video_search/main.py)  |
-| [Movie Recommender](https://github.com/lancedb/vectordb-recipes/tree/main/examples/movie-recommender/) | <a href="https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/movie-recommender/main.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> | [![Python](https://img.shields.io/badge/python-3670A0?style=for-the-badge&logo=python&logoColor=ffdd54)](https://github.com/lancedb/vectordb-recipes/tree/main/examples/movie-recommender/main.py)  |
-| [Audio Search](https://github.com/lancedb/vectordb-recipes/tree/main/examples/audio_search/) | <a href="https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/audio_search/main.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> | [![Python](https://img.shields.io/badge/python-3670A0?style=for-the-badge&logo=python&logoColor=ffdd54)](https://github.com/lancedb/vectordb-recipes/tree/main/examples/audio_search/main.py)  |
-| [Multimodal Image + Text Search](https://github.com/lancedb/vectordb-recipes/tree/main/examples/multimodal_search/) | <a href="https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/multimodal_search/main.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> | [![Python](https://img.shields.io/badge/python-3670A0?style=for-the-badge&logo=python&logoColor=ffdd54)](https://github.com/lancedb/vectordb-recipes/tree/main/examples/multimodal_search/main.py)  |
-| [Evaluating Prompts with Prompttools](https://github.com/lancedb/vectordb-recipes/tree/main/examples/prompttools-eval-prompts/) | <a href="https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/prompttools-eval-prompts/main.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |  |
-

docs/src/examples/examples_rust.md

@@ -1,3 +0,0 @@
-# Examples: Rust
-
-Our Rust SDK is now stable. Examples are coming soon.

docs/src/examples/image_embeddings_roboflow.md

@@ -1,165 +0,0 @@
-# How to Load Image Embeddings into LanceDB
-
-With the rise of Large Multimodal Models (LMMs) such as [GPT-4 Vision](https://blog.roboflow.com/gpt-4-vision/), the need for storing image embeddings is growing. The most effective way to store text and image embeddings is in a vector database such as LanceDB. Vector databases are a special kind of data store that enables efficient search over stored embeddings. 
-
-[CLIP](https://blog.roboflow.com/openai-clip/), a multimodal model developed by OpenAI, is commonly used to calculate image embeddings. These embeddings can then be used with a vector database to build a semantic search engine that you can query using images or text. For example, you could use LanceDB and CLIP embeddings to build a search engine for a database of folders.
-
-In this guide, we are going to show you how to use Roboflow Inference to load image embeddings into LanceDB. Without further ado, let’s get started!
-
-## Step #1: Install Roboflow Inference
-
-[Roboflow Inference](https://inference.roboflow.com) enables you to run state-of-the-art computer vision models with minimal configuration. Inference supports a range of models, from fine-tuned object detection, classification, and segmentation models to foundation models like CLIP. We will use Inference to calculate CLIP image embeddings.
-
-Inference provides a HTTP API through which you can run vision models.
-
-Inference powers the Roboflow hosted API, and is available as an open source utility. In this guide, we are going to run Inference locally, which enables you to calculate CLIP embeddings on your own hardware. We will also show you how to use the hosted Roboflow CLIP API, which is ideal if you need to scale and do not want to manage a system for calculating embeddings.
-
-To get started, first install the Inference CLI:
-
-```
-pip install inference-cli
-```
-
-Next, install Docker. Refer to the official Docker installation instructions for your operating system to get Docker set up. Once Docker is ready, you can start Inference using the following command:
-
-```
-inference server start
-```
-
-An Inference server will start running at ‘http://localhost:9001’.
-
-## Step #2: Set Up a LanceDB Vector Database
-
-Now that we have Inference running, we can set up a LanceDB vector database. You can run LanceDB in JavaScript and Python. For this guide, we will use the Python API. But, you can take the HTTP requests we make below and change them to JavaScript if required.
-
-For this guide, we are going to search the [COCO 128 dataset](https://universe.roboflow.com/team-roboflow/coco-128), which contains a wide range of objects. The variability in objects present in this dataset makes it a good dataset to demonstrate the capabilities of vector search. If you want to use this dataset, you can download [COCO 128 from Roboflow Universe](https://universe.roboflow.com/team-roboflow/coco-128). With that said, you can search whatever folder of images you want.
-
-Once you have a dataset ready, install LanceDB with the following command:
-
-```
-pip install lancedb
-```
-
-We also need to install a specific commit of `tantivy`, a dependency of the LanceDB full text search engine we will use later in this guide:
-
-```
-pip install tantivy
-```
-
-Create a new Python file and add the following code:
-
-```python
-import cv2
-import supervision as sv
-import requests
-
-import lancedb
-
-db = lancedb.connect("./embeddings")
-
-IMAGE_DIR = "images/"
-API_KEY = os.environ.get("ROBOFLOW_API_KEY")
-SERVER_URL = "http://localhost:9001"
-
-results = []
-
-for i, image in enumerate(os.listdir(IMAGE_DIR)):
-    infer_clip_payload = {
-        #Images can be provided as urls or as base64 encoded strings
-        "image": {
-            "type": "base64",
-            "value": base64.b64encode(open(IMAGE_DIR + image, "rb").read()).decode("utf-8"),
-        },
-    }
-
-    res = requests.post(
-        f"{SERVER_URL}/clip/embed_image?api_key={API_KEY}",
-        json=infer_clip_payload,
-    )
-
-    embeddings = res.json()['embeddings']
-
-    print("Calculated embedding for image: ", image)
-
-    image = {"vector": embeddings[0], "name": os.path.join(IMAGE_DIR, image)}
-
-    results.append(image)
-
-tbl = db.create_table("images", data=results)
-
-tbl.create_fts_index("name")
-```
-
-To use the code above, you will need a Roboflow API key. [Learn how to retrieve a Roboflow API key](https://docs.roboflow.com/api-reference/authentication#retrieve-an-api-key). Run the following command to set up your API key in your environment:
-
-```
-export ROBOFLOW_API_KEY=""
-```
-
-Replace the `IMAGE_DIR` value with the folder in which you are storing the images for which you want to calculate embeddings. If you want to use the Roboflow CLIP API to calculate embeddings, replace the `SERVER_URL` value with `https://infer.roboflow.com`.
-
-Run the script above to create a new LanceDB database. This database will be stored on your local machine. The database will be called `embeddings` and the table will be called `images`.
-
-The script above calculates all embeddings for a folder then creates a new table. To add additional images, use the following code:
-
-```python
-def make_batches():
-    for i in range(5):
-        yield [
-                {"vector": [3.1, 4.1], "name": "image1.png"},
-                {"vector": [5.9, 26.5], "name": "image2.png"}
-            ]
-
-tbl = db.open_table("images")
-tbl.add(make_batches())
-```
-
-Replacing the `make_batches()` function with code to load embeddings for images.
-
-## Step #3: Run a Search Query
-
-We are now ready to run a search query. To run a search query, we need a text embedding that represents a text query. We can use this embedding to search our LanceDB database for an entry.
-
-Let’s calculate a text embedding for the query “cat”, then run a search query:
-
-```python
-infer_clip_payload = {
-    "text": "cat",
-}
-
-res = requests.post(
-    f"{SERVER_URL}/clip/embed_text?api_key={API_KEY}",
-    json=infer_clip_payload,
-)
-
-embeddings = res.json()['embeddings']
-
-df = tbl.search(embeddings[0]).limit(3).to_list()
-
-print("Results:")
-
-for i in df:
-    print(i["name"])
-```
-
-This code will search for the three images most closely related to the prompt “cat”. The names of the most similar three images will be printed to the console. Here are the three top results:
-
-```
-dataset/images/train/000000000650_jpg.rf.1b74ba165c5a3513a3211d4a80b69e1c.jpg
-dataset/images/train/000000000138_jpg.rf.af439ef1c55dd8a4e4b142d186b9c957.jpg
-dataset/images/train/000000000165_jpg.rf.eae14d5509bf0c9ceccddbb53a5f0c66.jpg
-```
-
-Let’s open the top image:
-
-![Cat](https://media.roboflow.com/cat_lancedb.jpg)
-
-The top image was a cat. Our search was successful.
-
-## Conclusion
-
-LanceDB is a vector database that you can use to store and efficiently search your image embeddings. You can use Roboflow Inference, a scalable computer vision inference server, to calculate CLIP embeddings that you can store in LanceDB.
-
-You can use Inference and LanceDB together to build a range of applications with image embeddings, from a media search engine to a retrieval-augmented generation pipeline for use with LMMs.
-
-To learn more about Inference and its capabilities, refer to the Inference documentation.

docs/src/examples/index.md

@@ -1,16 +0,0 @@
-# Example projects and recipes
-
-## Recipes and example code
-
-LanceDB provides language APIs, allowing you to embed a database in your language of choice.
-
-* 🐍 [Python](examples_python.md) examples
-* 👾 [JavaScript](examples_js.md) examples
-* 🦀 Rust examples (coming soon)
-
-## Applications powered by LanceDB
-
-| Project Name                                        | Description                                                                                                          | Screenshot                                |
-|-----------------------------------------------------|----------------------------------------------------------------------------------------------------------------------|-------------------------------------------|
-| [YOLOExplorer](https://github.com/lancedb/yoloexplorer) | Iterate on your YOLO / CV datasets using SQL, Vector semantic search, and more within seconds                  | ![YOLOExplorer](https://github.com/lancedb/vectordb-recipes/assets/15766192/ae513a29-8f15-4e0b-99a1-ccd8272b6131) |
-| [Website Chatbot (Deployable Vercel Template)](https://github.com/lancedb/lancedb-vercel-chatbot) | Create a chatbot from the sitemap of any website/docs of your choice. Built using vectorDB serverless native javascript package. | ![Chatbot](../assets/vercel-template.gif)    |

docs/src/examples/modal_langchain.py

@@ -1,5 +1,6 @@
 import pickle
 import re
+import sys
 import zipfile
 from pathlib import Path
 
@@ -78,10 +79,7 @@ def qanda_langchain(query):
     download_docs()
     docs = store_docs()
 
-    text_splitter = RecursiveCharacterTextSplitter(
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200,)
-        chunk_size=1000,
-        chunk_overlap=200,
-    )
     documents = text_splitter.split_documents(docs)
     embeddings = OpenAIEmbeddings()
 

docs/src/examples/serverless_lancedb_with_s3_and_lambda.md

@@ -80,14 +80,14 @@ def handler(event, context):
     # Shape of SIFT is (128,1M), d=float32
     query_vector = np.array(event['query_vector'], dtype=np.float32)
 
-    rs = table.search(query_vector).limit(2).to_list()
+    rs = table.search(query_vector).limit(2).to_df()
 
     return {
         "statusCode": status_code,
         "headers": {
             "Content-Type": "application/json"
         },
-        "body": json.dumps(rs)
+        "body": rs.to_json()
     }
 ``` 
 

docs/src/examples/serverless_website_chatbot.md

@@ -1,61 +0,0 @@
-# LanceDB Chatbot - Vercel Next.js Template
-Use an AI chatbot with website context retrieved from a vector store like LanceDB. LanceDB is lightweight and can be embedded directly into Next.js, with data stored on-prem.
-
-## One click deploy on Vercel
-[![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2Flancedb%2Flancedb-vercel-chatbot&env=OPENAI_API_KEY&envDescription=OpenAI%20API%20Key%20for%20chat%20completion.&project-name=lancedb-vercel-chatbot&repository-name=lancedb-vercel-chatbot&demo-title=LanceDB%20Chatbot%20Demo&demo-description=Demo%20website%20chatbot%20with%20LanceDB.&demo-url=https%3A%2F%2Flancedb.vercel.app&demo-image=https%3A%2F%2Fi.imgur.com%2FazVJtvr.png)
-
-![Demo website landing page](../assets/vercel-template.gif)
-
-## Development
-
-First, rename `.env.example` to `.env.local`, and fill out `OPENAI_API_KEY` with your OpenAI API key. You can get one [here](https://openai.com/blog/openai-api).
-
-Run the development server:
-
-```bash
-npm run dev
-# or
-yarn dev
-# or
-pnpm dev
-```
-
-Open [http://localhost:3000](http://localhost:3000) with your browser to see the result.
-
-This project uses [`next/font`](https://nextjs.org/docs/basic-features/font-optimization) to automatically optimize and load Inter, a custom Google Font.
-
-## Learn More
-
-To learn more about LanceDB or Next.js, take a look at the following resources:
-
-- [LanceDB Documentation](https://lancedb.github.io/lancedb/) - learn about LanceDB, the developer-friendly serverless vector database.
-- [Next.js Documentation](https://nextjs.org/docs) - learn about Next.js features and API.
-- [Learn Next.js](https://nextjs.org/learn) - an interactive Next.js tutorial.
-
-## LanceDB on Next.js and Vercel
-
-FYI: these configurations have been pre-implemented in this template.
-
-Since LanceDB contains a prebuilt Node binary, you must configure `next.config.js` to exclude it from webpack. This is required for both using Next.js and deploying on Vercel.
-```js
-/** @type {import('next').NextConfig} */
-module.exports = ({
-  webpack(config) {
-    config.externals.push({ vectordb: 'vectordb' })
-    return config;
-  }
-})
-```
-
-To deploy on Vercel, we need to make sure that the NodeJS runtime static file analysis for Vercel can find the binary, since LanceDB uses dynamic imports by default. We can do this by modifying `package.json` in the `scripts` section.
-```json
-{
-  ...
-  "scripts": {
-    ...
-    "vercel-build": "sed -i 's/nativeLib = require(`@lancedb\\/vectordb-\\${currentTarget()}`);/nativeLib = require(`@lancedb\\/vectordb-linux-x64-gnu`);/' node_modules/vectordb/native.js && next build",
-    ...
-  },
-  ...
-}
-```