[python] Bump version: 0.6.0 → 0.6.1

This will eventually replace the remote table implementations in python
and node.

.bumpversion.cfg

@@ -0,0 +1,12 @@
+[bumpversion]
+current_version = 0.4.11
+commit = True
+message = Bump version: {current_version} → {new_version}
+tag = True
+tag_name = v{new_version}
+
+[bumpversion:file:node/package.json]
+
+[bumpversion:file:rust/ffi/node/Cargo.toml]
+
+[bumpversion:file:rust/lancedb/Cargo.toml]

.bumpversion.toml

@@ -1,57 +0,0 @@
-[tool.bumpversion]
-current_version = "0.6.0"
-parse = """(?x)
-    (?P<major>0|[1-9]\\d*)\\.
-    (?P<minor>0|[1-9]\\d*)\\.
-    (?P<patch>0|[1-9]\\d*)
-    (?:-(?P<pre_l>[a-zA-Z-]+)\\.(?P<pre_n>0|[1-9]\\d*))?
-"""
-serialize = [
-    "{major}.{minor}.{patch}-{pre_l}.{pre_n}",
-    "{major}.{minor}.{patch}",
-]
-search = "{current_version}"
-replace = "{new_version}"
-regex = false
-ignore_missing_version = false
-ignore_missing_files = false
-tag = true
-sign_tags = false
-tag_name = "v{new_version}"
-tag_message = "Bump version: {current_version} → {new_version}"
-allow_dirty = true
-commit = true
-message = "Bump version: {current_version} → {new_version}"
-commit_args = ""
-
-[tool.bumpversion.parts.pre_l]
-values = ["beta", "final"]
-optional_value = "final"
-
-[[tool.bumpversion.files]]
-filename = "node/package.json"
-search = "\"version\": \"{current_version}\","
-replace = "\"version\": \"{new_version}\","
-
-[[tool.bumpversion.files]]
-filename = "nodejs/package.json"
-search = "\"version\": \"{current_version}\","
-replace = "\"version\": \"{new_version}\","
-
-# nodejs binary packages
-[[tool.bumpversion.files]]
-glob = "nodejs/npm/*/package.json"
-search = "\"version\": \"{current_version}\","
-replace = "\"version\": \"{new_version}\","
-
-# Cargo files
-# ------------
-[[tool.bumpversion.files]]
-filename = "rust/ffi/node/Cargo.toml"
-search = "\nversion = \"{current_version}\""
-replace = "\nversion = \"{new_version}\""
-
-[[tool.bumpversion.files]]
-filename = "rust/lancedb/Cargo.toml"
-search = "\nversion = \"{current_version}\""
-replace = "\nversion = \"{new_version}\""

.github/labeler.yml

@@ -1,33 +0,0 @@
-version: 1
-appendOnly: true
-# Labels are applied based on conventional commits standard
-# https://www.conventionalcommits.org/en/v1.0.0/
-# These labels are later used in release notes. See .github/release.yml
-labels:
-# If the PR title has an ! before the : it will be considered a breaking change
-# For example, `feat!: add new feature` will be considered a breaking change
-- label: breaking-change
-  title: "^[^:]+!:.*"
-- label: breaking-change
-  body: "BREAKING CHANGE"
-- label: enhancement
-  title: "^feat(\\(.+\\))?!?:.*"
-- label: bug
-  title: "^fix(\\(.+\\))?!?:.*"
-- label: documentation
-  title: "^docs(\\(.+\\))?!?:.*"
-- label: performance
-  title: "^perf(\\(.+\\))?!?:.*"
-- label: ci
-  title: "^ci(\\(.+\\))?!?:.*"
-- label: chore
-  title: "^(chore|test|build|style)(\\(.+\\))?!?:.*"
-- label: Python
-  files:
-    - "^python\\/.*"
-- label: Rust
-  files:
-    - "^rust\\/.*"
-- label: typescript
-  files:
-    - "^node\\/.*"

.github/release_notes.json

@@ -1,41 +0,0 @@
-{
-    "ignore_labels": ["chore"],
-    "pr_template": "- ${{TITLE}} by @${{AUTHOR}} in ${{URL}}",
-    "categories": [
-        {
-            "title": "## 🏆 Highlights",
-            "labels": ["highlight"]
-        },
-        {
-            "title": "## 🛠 Breaking Changes",
-            "labels": ["breaking-change"]
-        },
-        {
-            "title": "## ⚠️ Deprecations ",
-            "labels": ["deprecation"]
-        },
-        {
-            "title": "## 🎉 New Features",
-            "labels": ["enhancement"]
-        },
-        {
-            "title": "## 🐛 Bug Fixes",
-            "labels": ["bug"]
-        },
-        {
-            "title": "## 📚 Documentation",
-            "labels": ["documentation"]
-        },
-        {
-            "title": "## 🚀 Performance Improvements",
-            "labels": ["performance"]
-        },
-        {
-            "title": "## Other Changes"
-        },
-        {
-            "title": "## 🔧 Build and CI",
-            "labels": ["ci"]
-        }
-    ]
-}

.github/workflows/build_linux_wheel/action.yml

@@ -14,10 +14,6 @@ inputs:
     # 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:
@@ -32,7 +28,7 @@ runs:
         command: build
         working-directory: python
         target: x86_64-unknown-linux-gnu
-        manylinux: ${{ inputs.manylinux }}
+        manylinux: "2_17"
         args: ${{ inputs.args }}
         before-script-linux: |
           set -e
@@ -46,9 +42,8 @@ runs:
       with:
         command: build
         working-directory: python
-        docker-options: "-e PIP_EXTRA_INDEX_URL=https://pypi.fury.io/lancedb/"
         target: aarch64-unknown-linux-gnu
-        manylinux: ${{ inputs.manylinux }}
+        manylinux: "2_24"
         args: ${{ inputs.args }}
         before-script-linux: |
           set -e

.github/workflows/build_mac_wheel/action.yml

@@ -21,6 +21,5 @@ runs:
       with:
         command: build
         args: ${{ inputs.args }}
-        docker-options: "-e PIP_EXTRA_INDEX_URL=https://pypi.fury.io/lancedb/"
         working-directory: python
         interpreter: 3.${{ inputs.python-minor-version }}

.github/workflows/build_windows_wheel/action.yml

@@ -26,7 +26,6 @@ runs:
       with:
         command: build
         args: ${{ inputs.args }}
-        docker-options: "-e PIP_EXTRA_INDEX_URL=https://pypi.fury.io/lancedb/"
         working-directory: python
     - uses: actions/upload-artifact@v3
       with:

.github/workflows/cargo-publish.yml

@@ -1,20 +1,13 @@
 name: Cargo Publish
 
 on:
-  push:
+  release:
-    tags-ignore:
+    types: [ published ]
-      # We don't publish pre-releases for Rust. Crates.io is just a source
-      # distribution, so we don't need to publish pre-releases.
-      - 'v*-beta*'
-      - '*-v*' # for example, python-vX.Y.Z
 
 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:

.github/workflows/dev.yml

@@ -1,81 +0,0 @@
-name: PR Checks
-
-on:
-  pull_request_target:
-    types: [opened, edited, synchronize, reopened]
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  labeler:
-    permissions:
-      pull-requests: write
-    name: Label PR
-    runs-on: ubuntu-latest
-    steps:
-      - uses: srvaroa/labeler@master
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-  commitlint:
-    permissions:
-      pull-requests: write
-    name: Verify PR title / description conforms to semantic-release
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/setup-node@v3
-        with:
-          node-version: "18"
-      # These rules are disabled because Github will always ensure there
-      # is a blank line between the title and the body and Github will
-      # word wrap the description field to ensure a reasonable max line
-      # length.
-      - run: npm install @commitlint/config-conventional
-      - run: >
-          echo 'module.exports = {
-            "rules": {
-              "body-max-line-length": [0, "always", Infinity],
-              "footer-max-line-length": [0, "always", Infinity],
-              "body-leading-blank": [0, "always"]
-            }
-          }' > .commitlintrc.js
-      - run: npx commitlint --extends @commitlint/config-conventional --verbose <<< $COMMIT_MSG
-        env:
-          COMMIT_MSG: >
-            ${{ github.event.pull_request.title }}
-
-            ${{ github.event.pull_request.body }}
-      - if: failure()
-        uses: actions/github-script@v6
-        with:
-          script: |
-            const message = `**ACTION NEEDED**
-              
-              Lance follows the [Conventional Commits specification](https://www.conventionalcommits.org/en/v1.0.0/) for release automation.
-
-              The PR title and description are used as the merge commit message.\
-              Please update your PR title and description to match the specification.
-
-              For details on the error please inspect the "PR Title Check" action.
-              `
-            // Get list of current comments
-            const comments = await github.paginate(github.rest.issues.listComments, {
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              issue_number: context.issue.number
-            });
-            // Check if this job already commented
-            for (const comment of comments) {
-              if (comment.body === message) {
-                return // Already commented
-              }
-            }
-            // Post the comment about Conventional Commits
-            github.rest.issues.createComment({
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              issue_number: context.issue.number,
-              body: message
-            })
-            core.setFailed(message)

.github/workflows/docs.yml

@@ -24,14 +24,10 @@ 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
-      - 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
         with:

.github/workflows/docs_test.yml

@@ -18,30 +18,22 @@ 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 -C target-cpu=native -C target-feature=+f16c,+avx2,+fma"
   RUST_BACKTRACE: "1"
 
 jobs:
   test-python:
     name: Test doc python code
-    runs-on: "warp-ubuntu-latest-x64-4x"
+    runs-on: "ubuntu-latest"
     steps:
     - name: Checkout
       uses: actions/checkout@v4
-    - name: Print CPU capabilities
-      run: cat /proc/cpuinfo
-    - name: Install dependecies needed for ubuntu
-      run: |
-        sudo apt install -y protobuf-compiler libssl-dev
-        rustup update && rustup default
     - name: Set up Python
       uses: actions/setup-python@v5
       with:
         python-version: 3.11
         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:
@@ -56,8 +48,8 @@ jobs:
         for d in *; do cd "$d"; echo "$d".py; python "$d".py; cd ..; done
   test-node:
     name: Test doc nodejs code
-    runs-on: "warp-ubuntu-latest-x64-4x"
+    runs-on: "ubuntu-latest"
-    timeout-minutes: 60
+    timeout-minutes: 45
     strategy:
       fail-fast: false
     steps:
@@ -66,8 +58,6 @@ jobs:
       with:
         fetch-depth: 0
         lfs: true
-    - name: Print CPU capabilities
-      run: cat /proc/cpuinfo
     - name: Set up Node
       uses: actions/setup-node@v4
       with:
@@ -75,7 +65,6 @@ jobs:
     - name: Install dependecies needed for ubuntu
       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

.github/workflows/java.yml

@@ -1,85 +0,0 @@
-name: Build and Run Java JNI Tests
-on:
-  push:
-    branches:
-      - main
-  pull_request:
-    paths:
-      - java/**
-      - rust/**
-      - .github/workflows/java.yml
-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
-  # 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"
-  # according to: https://matklad.github.io/2021/09/04/fast-rust-builds.html
-  # CI builds are faster with incremental disabled.
-  CARGO_INCREMENTAL: "0"
-  CARGO_BUILD_JOBS: "1"
-jobs:
-  linux-build:
-    runs-on: ubuntu-22.04
-    name: ubuntu-22.04 + Java 11 & 17
-    defaults:
-      run:
-        working-directory: ./java
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-      - uses: Swatinem/rust-cache@v2
-        with:
-          workspaces: java/core/lancedb-jni
-      - name: Run cargo fmt
-        run: cargo fmt --check
-        working-directory: ./java/core/lancedb-jni
-      - name: Install dependencies
-        run: |
-          sudo apt update
-          sudo apt install -y protobuf-compiler libssl-dev
-      - name: Install Java 17
-        uses: actions/setup-java@v4
-        with:
-          distribution: temurin
-          java-version: 17
-          cache: "maven"
-      - run: echo "JAVA_17=$JAVA_HOME" >> $GITHUB_ENV
-      - name: Install Java 11
-        uses: actions/setup-java@v4
-        with:
-          distribution: temurin
-          java-version: 11
-          cache: "maven"
-      - name: Java Style Check
-        run: mvn checkstyle:check
-      # Disable because of issues in lancedb rust core code
-      # - name: Rust Clippy
-      #   working-directory: java/core/lancedb-jni
-      #   run: cargo clippy --all-targets -- -D warnings
-      - name: Running tests with Java 11
-        run: mvn clean test
-      - name: Running tests with Java 17
-        run: |
-          export JAVA_TOOL_OPTIONS="$JAVA_TOOL_OPTIONS \
-          -XX:+IgnoreUnrecognizedVMOptions \
-          --add-opens=java.base/java.lang=ALL-UNNAMED \
-          --add-opens=java.base/java.lang.invoke=ALL-UNNAMED \
-          --add-opens=java.base/java.lang.reflect=ALL-UNNAMED \
-          --add-opens=java.base/java.io=ALL-UNNAMED \
-          --add-opens=java.base/java.net=ALL-UNNAMED \
-          --add-opens=java.base/java.nio=ALL-UNNAMED \
-          --add-opens=java.base/java.util=ALL-UNNAMED \
-          --add-opens=java.base/java.util.concurrent=ALL-UNNAMED \
-          --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED \
-          --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED \
-          --add-opens=java.base/sun.nio.ch=ALL-UNNAMED \
-          --add-opens=java.base/sun.nio.cs=ALL-UNNAMED \
-          --add-opens=java.base/sun.security.action=ALL-UNNAMED \
-          --add-opens=java.base/sun.util.calendar=ALL-UNNAMED \
-          --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED \
-          -Djdk.reflect.useDirectMethodHandle=false \
-          -Dio.netty.tryReflectionSetAccessible=true"
-          JAVA_HOME=$JAVA_17 mvn clean test

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

@@ -1,62 +1,37 @@
 name: Create release commit
 
-# This workflow increments versions, tags the version, and pushes it.
-# When a tag is pushed, another workflow is triggered that creates a GH release
-# and uploads the binaries. This workflow is only for creating the tag.
-
-# This script will enforce that a minor version is incremented if there are any
-# breaking changes since the last minor increment. However, it isn't able to
-# differentiate between breaking changes in Node versus Python. If you wish to
-# bypass this check, you can manually increment the version and push the tag.
 on:
   workflow_dispatch:
     inputs:
       dry_run:
         description: 'Dry run (create the local commit/tags but do not push it)'
         required: true
-        default: false
+        default: "false"
-        type: boolean
-      type:
-        description: 'What kind of release is this?'
-        required: true
-        default: 'preview'
         type: choice
         options:
-          - preview
+          - "true"
-          - stable
+          - "false"
-      python:
+      part:
-        description: 'Make a Python release'
+        description: 'What kind of release is this?'
         required: true
-        default: true
+        default: 'patch'
-        type: boolean
+        type: choice
-      other:
+        options:
-        description: 'Make a Node/Rust release'
+          - patch
-        required: true
+          - minor
-        default: true
+          - major
-        type: boolean
-      bump-minor:
-        description: 'Bump minor version'
-        required: true
-        default: false
-        type: boolean
 
 jobs:
-  make-release:
+  bump-version:
-    # Creates tag and GH release. The GH release will trigger the build and release jobs.
     runs-on: ubuntu-latest
-    permissions:
-      contents: write
     steps:
-      - name: Output Inputs
+      - name: Check out main
-        run: echo "${{ toJSON(github.event.inputs) }}"
+        uses: actions/checkout@v4
-      - uses: actions/checkout@v4
         with:
+          ref: main
+          persist-credentials: false
           fetch-depth: 0
           lfs: true
-          # It's important we use our token here, as the default token will NOT
-          # trigger any workflows watching for new tags. See:
-          # https://docs.github.com/en/actions/using-workflows/triggering-a-workflow#triggering-a-workflow-from-a-workflow
-          token: ${{ secrets.LANCEDB_RELEASE_TOKEN }}
       - name: Set git configs for bumpversion
         shell: bash
         run: |
@@ -66,34 +41,19 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: "3.11"
-      - name: Bump Python version
+      - name: Bump version, create tag and commit
-        if: ${{ inputs.python }}
-        working-directory: python
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         run: |
-          # Need to get the commit before bumping the version, so we can
+          pip install bump2version
-          # determine if there are breaking changes in the next step as well.
+          bumpversion --verbose ${{ inputs.part }}
-          echo "COMMIT_BEFORE_BUMP=$(git rev-parse HEAD)" >> $GITHUB_ENV
+      - name: Push new version and tag
-
+        if: ${{ inputs.dry_run }} == "false"
-          pip install bump-my-version PyGithub packaging
-          bash ../ci/bump_version.sh ${{ inputs.type }} ${{ inputs.bump-minor }} python-v
-      - name: Bump Node/Rust version
-        if: ${{ inputs.other }}
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          pip install bump-my-version PyGithub packaging
-          bash ci/bump_version.sh ${{ inputs.type }} ${{ inputs.bump-minor }} v $COMMIT_BEFORE_BUMP
-      - name: Push new version tag
-        if: ${{ !inputs.dry_run }}
         uses: ad-m/github-push-action@master
         with:
-          # Need to use PAT here too to trigger next workflow. See comment above.
           github_token: ${{ secrets.LANCEDB_RELEASE_TOKEN }}
-          branch: ${{ github.ref }}
+          branch: main
           tags: true
       - uses: ./.github/workflows/update_package_lock
-        if: ${{ !inputs.dry_run && inputs.other }}
+        if: ${{ inputs.dry_run }} == "false"
         with:
-          github_token: ${{ secrets.GITHUB_TOKEN }}
+          github_token: ${{ secrets.LANCEDB_RELEASE_TOKEN }}
+

.github/workflows/node.yml

@@ -20,11 +20,31 @@ env:
   # "1" means line tables only, which is useful for panic tracebacks.
   #
   # Use native CPU to accelerate tests if possible, especially for f16
-  # target-cpu=haswell fixes failing ci build
+  RUSTFLAGS: "-C debuginfo=1 -C target-cpu=native -C target-feature=+f16c,+avx2,+fma"
-  RUSTFLAGS: "-C debuginfo=1 -C target-cpu=haswell -C target-feature=+f16c,+avx2,+fma"
   RUST_BACKTRACE: "1"
 
 jobs:
+  lint:
+    name: Lint
+    runs-on: ubuntu-22.04
+    defaults:
+      run:
+        shell: bash
+        working-directory: node
+    steps:
+    - uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+        lfs: true
+    - uses: actions/setup-node@v3
+      with:
+        node-version: 20
+        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
@@ -107,7 +127,6 @@ jobs:
       AWS_ENDPOINT: http://localhost:4566
       # this one is for dynamodb
       DYNAMODB_ENDPOINT: http://localhost:4566
-      ALLOW_HTTP: true
     steps:
     - uses: actions/checkout@v4
       with:

.github/workflows/nodejs.yml

@@ -28,10 +28,6 @@ jobs:
       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:
@@ -52,7 +48,7 @@ jobs:
         cargo fmt --all -- --check
         cargo clippy --all --all-features -- -D warnings
         npm ci
-        npm run lint-ci
+        npm run lint
   linux:
     name: Linux (NodeJS ${{ matrix.node-version }})
     timeout-minutes: 30
@@ -84,12 +80,7 @@ jobs:
       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
@@ -120,3 +111,4 @@ jobs:
     - name: Test
       run: |
         npm run test
+

.github/workflows/npm-publish.yml

@@ -1,9 +1,8 @@
 name: NPM Publish
 
 on:
-  push:
+  release:
-    tags:
+    types: [ published ]
-      - "v*"
 
 jobs:
   node:
@@ -20,7 +19,7 @@ jobs:
       - uses: actions/setup-node@v3
         with:
           node-version: 20
-          cache: "npm"
+          cache: 'npm'
           cache-dependency-path: node/package-lock.json
       - name: Install dependencies
         run: |
@@ -32,7 +31,7 @@ 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: |
@@ -62,87 +61,18 @@ jobs:
       - name: Build MacOS native node modules
         run: bash ci/build_macos_artifacts.sh ${{ matrix.config.arch }}
       - name: Upload Darwin Artifacts
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v3
         with:
-          name: node-native-darwin-${{ matrix.config.arch }}
+          name: native-darwin
           path: |
             node/dist/lancedb-vectordb-darwin*.tgz
 
-  nodejs-macos:
-    strategy:
-      matrix:
-        config:
-          - arch: x86_64-apple-darwin
-            runner: macos-13
-          - arch: aarch64-apple-darwin
-            # xlarge is implicitly arm64.
-            runner: macos-14
-    runs-on: ${{ matrix.config.runner }}
-    # Only runs on tags that matches the make-release action
-    if: startsWith(github.ref, 'refs/tags/v')
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-      - name: Install system dependencies
-        run: brew install protobuf
-      - name: Install npm dependencies
-        run: |
-          cd nodejs
-          npm ci
-      - name: Build MacOS native nodejs modules
-        run: bash ci/build_macos_artifacts_nodejs.sh ${{ matrix.config.arch }}
-      - name: Upload Darwin Artifacts
-        uses: actions/upload-artifact@v4
-        with:
-          name: nodejs-native-darwin-${{ matrix.config.arch }}
-          path: |
-            nodejs/dist/*.node
 
   node-linux:
     name: node-linux (${{ matrix.config.arch}}-unknown-linux-gnu
     runs-on: ${{ matrix.config.runner }}
     # Only runs on tags that matches the make-release action
     if: startsWith(github.ref, 'refs/tags/v')
-    strategy:
-      fail-fast: false
-      matrix:
-        config:
-          - arch: x86_64
-            runner: ubuntu-latest
-          - arch: aarch64
-            # For successful fat LTO builds, we need a large runner to avoid OOM errors.
-            runner: warp-ubuntu-latest-arm64-4x
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-      # To avoid OOM errors on ARM, we create a swap file.
-      - name: Configure aarch64 build
-        if: ${{ matrix.config.arch == 'aarch64' }}
-        run: |
-          free -h
-          sudo fallocate -l 16G /swapfile
-          sudo chmod 600 /swapfile
-          sudo mkswap /swapfile
-          sudo swapon /swapfile
-          echo "/swapfile swap swap defaults 0 0" >> sudo /etc/fstab
-          # print info
-          swapon --show
-          free -h
-      - name: Build Linux Artifacts
-        run: |
-          bash ci/build_linux_artifacts.sh ${{ matrix.config.arch }}
-      - name: Upload Linux Artifacts
-        uses: actions/upload-artifact@v4
-        with:
-          name: node-native-linux-${{ matrix.config.arch }}
-          path: |
-            node/dist/lancedb-vectordb-linux*.tgz
-
-  nodejs-linux:
-    name: nodejs-linux (${{ matrix.config.arch}}-unknown-linux-gnu
-    runs-on: ${{ matrix.config.runner }}
-    # Only runs on tags that matches the make-release action
-    if: startsWith(github.ref, 'refs/tags/v')
     strategy:
       fail-fast: false
       matrix:
@@ -171,23 +101,13 @@ jobs:
           free -h
       - name: Build Linux Artifacts
         run: |
-          bash ci/build_linux_artifacts_nodejs.sh ${{ matrix.config.arch }}
+          bash ci/build_linux_artifacts.sh ${{ matrix.config.arch }}
       - name: Upload Linux Artifacts
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v3
         with:
-          name: nodejs-native-linux-${{ matrix.config.arch }}
+          name: native-linux
           path: |
-            nodejs/dist/*.node
+            node/dist/lancedb-vectordb-linux*.tgz
-      # 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
@@ -216,129 +136,37 @@ 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: native-windows
           path: |
             node/dist/lancedb-vectordb-win32*.tgz
 
-  nodejs-windows:
-    runs-on: windows-2022
-    # Only runs on tags that matches the make-release action
-    if: startsWith(github.ref, 'refs/tags/v')
-    strategy:
-      fail-fast: false
-      matrix:
-        target: [x86_64-pc-windows-msvc]
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-      - name: Install Protoc v21.12
-        working-directory: C:\
-        run: |
-          New-Item -Path 'C:\protoc' -ItemType Directory
-          Set-Location C:\protoc
-          Invoke-WebRequest https://github.com/protocolbuffers/protobuf/releases/download/v21.12/protoc-21.12-win64.zip -OutFile C:\protoc\protoc.zip
-          7z x protoc.zip
-          Add-Content $env:GITHUB_PATH "C:\protoc\bin"
-        shell: powershell
-      - name: Install npm dependencies
-        run: |
-          cd nodejs
-          npm ci
-      - name: Build Windows native node modules
-        run: .\ci\build_windows_artifacts_nodejs.ps1 ${{ matrix.target }}
-      - name: Upload Windows Artifacts
-        uses: actions/upload-artifact@v4
-        with:
-          name: nodejs-native-windows
-          path: |
-            nodejs/dist/*.node
-
   release:
     needs: [node, node-macos, node-linux, node-windows]
     runs-on: ubuntu-latest
     # Only runs on tags that matches the make-release action
     if: startsWith(github.ref, 'refs/tags/v')
     steps:
-      - uses: actions/download-artifact@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"
+          registry-url: 'https://registry.npmjs.org'
       - name: Publish to NPM
         env:
           NODE_AUTH_TOKEN: ${{ secrets.LANCEDB_NPM_REGISTRY_TOKEN }}
         run: |
-          # Tag beta as "preview" instead of default "latest". See lancedb 
-          # npm publish step for more info.
-          if [[ $GITHUB_REF =~ refs/tags/v(.*)-beta.* ]]; then
-            PUBLISH_ARGS="--tag preview"
-          fi
-
           mv */*.tgz .
           for filename in *.tgz; do
-            npm publish $PUBLISH_ARGS $filename
+            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 }}
-        # By default, things are published to the latest tag. This is what is
-        # installed by default if the user does not specify a version. This is
-        # good for stable releases, but for pre-releases, we want to publish to
-        # the "preview" tag so they can install with `npm install lancedb@preview`.
-        # See: https://medium.com/@mbostock/prereleases-and-npm-e778fc5e2420
-        run: |
-          if [[ $GITHUB_REF =~ refs/tags/v(.*)-beta.* ]]; then
-            npm publish --access public --tag preview
-          else
-            npm publish --access public
-          fi
-
   update-package-lock:
     needs: [release]
     runs-on: ubuntu-latest
-    permissions:
-      contents: write
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -349,87 +177,4 @@ jobs:
           lfs: true
       - uses: ./.github/workflows/update_package_lock
         with:
-          github_token: ${{ secrets.GITHUB_TOKEN }}
+          github_token: ${{ secrets.LANCEDB_RELEASE_TOKEN }}
-
-  update-package-lock-nodejs:
-    needs: [release-nodejs]
-    runs-on: ubuntu-latest
-    permissions:
-      contents: write
-    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.GITHUB_TOKEN }}
-
-  gh-release:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: write
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-          lfs: true
-      - name: Extract version
-        id: extract_version
-        env:
-          GITHUB_REF: ${{ github.ref }}
-        run: |
-          set -e
-          echo "Extracting tag and version from $GITHUB_REF"
-          if [[ $GITHUB_REF =~ refs/tags/v(.*) ]]; then
-            VERSION=${BASH_REMATCH[1]}
-            TAG=v$VERSION
-            echo "tag=$TAG" >> $GITHUB_OUTPUT
-            echo "version=$VERSION" >> $GITHUB_OUTPUT
-          else
-            echo "Failed to extract version from $GITHUB_REF"
-            exit 1
-          fi
-          echo "Extracted version $VERSION from $GITHUB_REF"
-          if [[ $VERSION =~ beta ]]; then
-            echo "This is a beta release"
-
-            # Get last release (that is not this one)
-            FROM_TAG=$(git tag --sort='version:refname' \
-              | grep ^v \
-              | grep -vF "$TAG" \
-              | python ci/semver_sort.py v \
-              | tail -n 1)
-          else
-            echo "This is a stable release"
-            # Get last stable tag (ignore betas)
-            FROM_TAG=$(git tag --sort='version:refname' \
-              | grep ^v \
-              | grep -vF "$TAG" \
-              | grep -v beta \
-              | python ci/semver_sort.py v \
-              | tail -n 1)
-          fi
-          echo "Found from tag $FROM_TAG"
-          echo "from_tag=$FROM_TAG" >> $GITHUB_OUTPUT
-      - name: Create Release Notes
-        id: release_notes
-        uses: mikepenz/release-changelog-builder-action@v4
-        with:
-          configuration: .github/release_notes.json
-          toTag: ${{ steps.extract_version.outputs.tag }}
-          fromTag: ${{ steps.extract_version.outputs.from_tag }}
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      - name: Create GH release
-        uses: softprops/action-gh-release@v2
-        with:
-          prerelease: ${{ contains('beta', github.ref) }}
-          tag_name: ${{ steps.extract_version.outputs.tag }}
-          token: ${{ secrets.GITHUB_TOKEN }}
-          generate_release_notes: false
-          name: Node/Rust LanceDB v${{ steps.extract_version.outputs.version }}
-          body: ${{ steps.release_notes.outputs.changelog }}

.github/workflows/pypi-publish.yml

@@ -1,28 +1,18 @@
 name: PyPI Publish
 
 on:
-  push:
+  release:
-    tags:
+    types: [published]
-      - 'python-v*'
 
 jobs:
   linux:
-    name: Python ${{ matrix.config.platform }} manylinux${{ matrix.config.manylinux }}
     timeout-minutes: 60
     strategy:
       matrix:
-        config:
+        python-minor-version: ["8"]
-          - platform: x86_64
+        platform:
-            manylinux: "2_17"
+          - x86_64
-            extra_args: ""
+          - aarch64
-          - 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
@@ -32,22 +22,22 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v4
         with:
-          python-version: 3.8
+          python-version: 3.${{ matrix.python-minor-version }}
       - uses: ./.github/workflows/build_linux_wheel
         with:
-          python-minor-version: 8
+          python-minor-version: ${{ matrix.python-minor-version }}
-          args: "--release --strip ${{ matrix.config.extra_args }}"
+          args: "--release --strip"
-          arm-build: ${{ matrix.config.platform == 'aarch64' }}
+          arm-build: ${{ matrix.platform == 'aarch64' }}
-          manylinux: ${{ matrix.config.manylinux }}
       - uses: ./.github/workflows/upload_wheel
         with:
-          pypi_token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
+          token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
-          fury_token: ${{ secrets.FURY_TOKEN }}
+          repo: "pypi"
   mac:
     timeout-minutes: 60
     runs-on: ${{ matrix.config.runner }}
     strategy:
       matrix:
+        python-minor-version: ["8"]
         config:
           - target: x86_64-apple-darwin
             runner: macos-13
@@ -58,6 +48,7 @@ jobs:
     steps:
       - uses: actions/checkout@v4
         with:
+          ref: ${{ inputs.ref }}
           fetch-depth: 0
           lfs: true
       - name: Set up Python
@@ -66,95 +57,36 @@ jobs:
           python-version: 3.12
       - uses: ./.github/workflows/build_mac_wheel
         with:
-          python-minor-version: 8
+          python-minor-version: ${{ matrix.python-minor-version }}
-          args: "--release --strip --target ${{ matrix.config.target }} --features fp16kernels"
+          args: "--release --strip --target ${{ matrix.config.target }}"
       - uses: ./.github/workflows/upload_wheel
         with:
-          pypi_token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
+          python-minor-version: ${{ matrix.python-minor-version }}
-          fury_token: ${{ secrets.FURY_TOKEN }}
+          token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
+          repo: "pypi"
   windows:
     timeout-minutes: 60
     runs-on: windows-latest
+    strategy:
+      matrix:
+        python-minor-version: ["8"]
     steps:
       - uses: actions/checkout@v4
         with:
+          ref: ${{ inputs.ref }}
           fetch-depth: 0
           lfs: true
       - name: Set up Python
         uses: actions/setup-python@v4
         with:
-          python-version: 3.8
+          python-version: 3.${{ matrix.python-minor-version }}
       - uses: ./.github/workflows/build_windows_wheel
         with:
-          python-minor-version: 8
+          python-minor-version: ${{ matrix.python-minor-version }}
           args: "--release --strip"
           vcpkg_token: ${{ secrets.VCPKG_GITHUB_PACKAGES }}
       - uses: ./.github/workflows/upload_wheel
         with:
-          pypi_token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
+          python-minor-version: ${{ matrix.python-minor-version }}
-          fury_token: ${{ secrets.FURY_TOKEN }}
+          token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
-  gh-release:
+          repo: "pypi"
-    runs-on: ubuntu-latest
-    permissions:
-      contents: write
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-          lfs: true
-      - name: Extract version
-        id: extract_version
-        env:
-          GITHUB_REF: ${{ github.ref }}
-        run: |
-          set -e
-          echo "Extracting tag and version from $GITHUB_REF"
-          if [[ $GITHUB_REF =~ refs/tags/python-v(.*) ]]; then
-            VERSION=${BASH_REMATCH[1]}
-            TAG=python-v$VERSION
-            echo "tag=$TAG" >> $GITHUB_OUTPUT
-            echo "version=$VERSION" >> $GITHUB_OUTPUT
-          else
-            echo "Failed to extract version from $GITHUB_REF"
-            exit 1
-          fi
-          echo "Extracted version $VERSION from $GITHUB_REF"
-          if [[ $VERSION =~ beta ]]; then
-            echo "This is a beta release"
-
-            # Get last release (that is not this one)
-            FROM_TAG=$(git tag --sort='version:refname' \
-              | grep ^python-v \
-              | grep -vF "$TAG" \
-              | python ci/semver_sort.py python-v \
-              | tail -n 1)
-          else
-            echo "This is a stable release"
-            # Get last stable tag (ignore betas)
-            FROM_TAG=$(git tag --sort='version:refname' \
-              | grep ^python-v \
-              | grep -vF "$TAG" \
-              | grep -v beta \
-              | python ci/semver_sort.py python-v \
-              | tail -n 1)
-          fi
-          echo "Found from tag $FROM_TAG"
-          echo "from_tag=$FROM_TAG" >> $GITHUB_OUTPUT
-      - name: Create Python Release Notes
-        id: python_release_notes
-        uses: mikepenz/release-changelog-builder-action@v4
-        with:
-          configuration: .github/release_notes.json
-          toTag: ${{ steps.extract_version.outputs.tag }}
-          fromTag: ${{ steps.extract_version.outputs.from_tag }}
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      - name: Create Python GH release
-        uses: softprops/action-gh-release@v2
-        with:
-          prerelease: ${{ contains('beta', github.ref) }}
-          tag_name: ${{ steps.extract_version.outputs.tag }}
-          token: ${{ secrets.GITHUB_TOKEN }}
-          generate_release_notes: false
-          name: Python LanceDB v${{ steps.extract_version.outputs.version }}
-          body: ${{ steps.python_release_notes.outputs.changelog }}

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

@@ -0,0 +1,56 @@
+name: Python - Create release commit
+
+on:
+  workflow_dispatch:
+    inputs:
+      dry_run:
+        description: 'Dry run (create the local commit/tags but do not push it)'
+        required: true
+        default: "false"
+        type: choice
+        options:
+          - "true"
+          - "false"
+      part:
+        description: 'What kind of release is this?'
+        required: true
+        default: 'patch'
+        type: choice
+        options:
+          - patch
+          - minor
+          - major
+
+jobs:
+  bump-version:
+    runs-on: ubuntu-latest
+    steps:
+    - name: Check out main
+      uses: actions/checkout@v4
+      with:
+        ref: main
+        persist-credentials: false
+        fetch-depth: 0
+        lfs: true
+    - name: Set git configs for bumpversion
+      shell: bash
+      run: |
+        git config user.name 'Lance Release'
+        git config user.email 'lance-dev@lancedb.com'
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: "3.11"
+    - name: Bump version, create tag and commit
+      working-directory: python
+      run: |
+        pip install bump2version
+        bumpversion --verbose ${{ inputs.part }}
+    - name: Push new version and tag
+      if: ${{ inputs.dry_run }} == "false"
+      uses: ad-m/github-push-action@master
+      with:
+        github_token: ${{ secrets.LANCEDB_RELEASE_TOKEN }}
+        branch: main
+        tags: true
+

.github/workflows/python.yml

@@ -65,8 +65,8 @@ jobs:
           workspaces: python
       - name: Install
         run: |
-          pip install --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests,dev,embeddings]
+          pip install -e .[tests,dev,embeddings]
-          pip install tantivy
+          pip install tantivy@git+https://github.com/quickwit-oss/tantivy-py#164adc87e1a033117001cf70e38c82a53014d985
           pip install mlx
       - name: Doctest
         run: pytest --doctest-modules python/lancedb
@@ -75,7 +75,7 @@ jobs:
     timeout-minutes: 30
     strategy:
       matrix:
-        python-minor-version: ["9", "11"]
+        python-minor-version: ["8", "11"]
     runs-on: "ubuntu-22.04"
     defaults:
       run:
@@ -99,8 +99,6 @@ jobs:
           workspaces: python
       - uses: ./.github/workflows/build_linux_wheel
       - uses: ./.github/workflows/run_tests
-        with:
-          integration: true
       # Make sure wheels are not included in the Rust cache
       - name: Delete wheels
         run: rm -rf target/wheels
@@ -189,7 +187,7 @@ jobs:
       - name: Install lancedb
         run: |
           pip install "pydantic<2"
-          pip install --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests]
+          pip install -e .[tests]
-          pip install tantivy
+          pip install tantivy@git+https://github.com/quickwit-oss/tantivy-py#164adc87e1a033117001cf70e38c82a53014d985
       - name: Run tests
-        run: pytest -m "not slow and not s3_test" -x -v --durations=30 python/tests
+        run: pytest -m "not slow" -x -v --durations=30 python/tests

.github/workflows/remote-integration.yml

@@ -0,0 +1,37 @@
+name: LanceDb Cloud Integration Test
+
+on:
+  workflow_run:
+    workflows: [Rust]
+    types:
+      - completed
+
+env:
+  LANCEDB_PROJECT: ${{ secrets.LANCEDB_PROJECT }}
+  LANCEDB_API_KEY: ${{ secrets.LANCEDB_API_KEY }}
+  LANCEDB_REGION: ${{ secrets.LANCEDB_REGION }}
+
+jobs:
+  test:
+    timeout-minutes: 30
+    runs-on: ubuntu-22.04
+    defaults:
+      run:
+        shell: bash
+        working-directory: rust
+    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: Build
+      run: cargo build --all-features
+    - name: Run Integration test
+      run: cargo test --tests -- --ignored

.github/workflows/run_tests/action.yml

@@ -5,27 +5,13 @@ 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 --extra-index-url https://pypi.fury.io/lancedb/ $(ls target/wheels/lancedb-*.whl)[tests,dev]
+        pip3 install $(ls target/wheels/lancedb-*.whl)[tests,dev]
-    - name: Setup localstack for integration tests
+    - name: pytest
-      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

@@ -31,10 +31,6 @@ 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
       with:
@@ -58,10 +54,6 @@ 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
       with:
@@ -74,9 +66,6 @@ jobs:
       run: |
           sudo apt update
           sudo apt install -y protobuf-compiler libssl-dev
-    - name: Start S3 integration test environment
-      working-directory: .
-      run: docker compose up --detach --wait
     - name: Build
       run: cargo build --all-features
     - name: Run tests
@@ -108,8 +97,7 @@ 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:

.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_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

@@ -2,43 +2,28 @@ name: upload-wheel
 
 description: "Upload wheels to Pypi"
 inputs:
-  pypi_token:
+  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"
-  fury_token:
-    required: true
-    description: "release token for the fury repo"
 
 runs:
   using: "composite"
   steps:
-  - name: Install dependencies
+    - name: Install dependencies
-    shell: bash
+      shell: bash
-    run: |
+      run: |
-      python -m pip install --upgrade pip
+        python -m pip install --upgrade pip
-      pip install twine
+        pip install twine
-  - name: Choose repo
+    - name: Publish wheel
-    shell: bash
+      env:
-    id: choose_repo
+        TWINE_USERNAME: __token__
-    run: |
+        TWINE_PASSWORD: ${{ inputs.token }}
-      if [ ${{ github.ref }} == "*beta*" ]; then
+      shell: bash
-        echo "repo=fury" >> $GITHUB_OUTPUT
+      run: twine upload --repository ${{ inputs.repo }} target/wheels/lancedb-*.whl
-      else
-        echo "repo=pypi" >> $GITHUB_OUTPUT
-      fi
-  - name: Publish to PyPI
-    shell: bash
-    env:
-      FURY_TOKEN: ${{ inputs.fury_token }}
-      PYPI_TOKEN: ${{ inputs.pypi_token }}
-    run: |
-      if [ ${{ steps.choose_repo.outputs.repo }} == "fury" ]; then
-        WHEEL=$(ls target/wheels/lancedb-*.whl 2> /dev/null | head -n 1)
-        echo "Uploading $WHEEL to Fury"
-        curl -f -F package=@$WHEEL https://$FURY_TOKEN@push.fury.io/lancedb/
-      else
-        twine upload --repository ${{ steps.choose_repo.outputs.repo }} \
-          --username __token__ \
-          --password $PYPI_TOKEN \
-          target/wheels/lancedb-*.whl
-      fi

.gitignore

@@ -4,10 +4,9 @@
 **/__pycache__
 .DS_Store
 venv
-.venv
 
 .vscode
-.zed
+
 rust/target
 rust/Cargo.lock
 
@@ -35,7 +34,6 @@ python/dist
 node/dist
 node/examples/**/package-lock.json
 node/examples/**/dist
-nodejs/lancedb/native*
 dist
 
 ## Rust

.pre-commit-config.yaml

@@ -10,12 +10,3 @@ repos:
     rev: v0.2.2
     hooks:
     - id: ruff
-- repo: local
-  hooks:
-    - id: local-biome-check
-      name: biome check
-      entry: npx @biomejs/biome@1.8.3 check --config-path nodejs/biome.json nodejs/
-      language: system
-      types: [text]
-      files: "nodejs/.*"
-      exclude: nodejs/lancedb/native.d.ts|nodejs/dist/.*|nodejs/examples/.*

Cargo.toml

@@ -1,11 +1,5 @@
 [workspace]
-members = [
+members = ["rust/ffi/node", "rust/lancedb", "nodejs", "python"]
-    "rust/ffi/node",
-    "rust/lancedb",
-    "nodejs",
-    "python",
-    "java/core/lancedb-jni",
-]
 # Python package needs to be built by maturin.
 exclude = ["python"]
 resolver = "2"
@@ -20,32 +14,27 @@ keywords = ["lancedb", "lance", "database", "vector", "search"]
 categories = ["database-implementations"]
 
 [workspace.dependencies]
-lance = { "version" = "=0.14.1", "features" = ["dynamodb"] }
+lance = { "version" = "=0.10.1", "features" = ["dynamodb"] }
-lance-index = { "version" = "=0.14.1" }
+lance-index = { "version" = "=0.10.1" }
-lance-linalg = { "version" = "=0.14.1" }
+lance-linalg = { "version" = "=0.10.1" }
-lance-testing = { "version" = "=0.14.1" }
+lance-testing = { "version" = "=0.10.1" }
-lance-datafusion = { "version" = "=0.14.1" }
 # Note that this one does not include pyarrow
-arrow = { version = "51.0", optional = false }
+arrow = { version = "50.0", optional = false }
-arrow-array = "51.0"
+arrow-array = "50.0"
-arrow-data = "51.0"
+arrow-data = "50.0"
-arrow-ipc = "51.0"
+arrow-ipc = "50.0"
-arrow-ord = "51.0"
+arrow-ord = "50.0"
-arrow-schema = "51.0"
+arrow-schema = "50.0"
-arrow-arith = "51.0"
+arrow-arith = "50.0"
-arrow-cast = "51.0"
+arrow-cast = "50.0"
 async-trait = "0"
-chrono = "0.4.35"
+chrono = "0.4.23"
-datafusion-physical-plan = "37.1"
+half = { "version" = "=2.3.1", default-features = false, features = [
-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

@@ -1,13 +1,13 @@
 <div 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/' target="_blank"><img alt='lancdb' src='https://img.shields.io/badge/DOCS-100000?style=for-the-badge&logo=lancdb&logoColor=white&labelColor=645cfb&color=645cfb'/></a>
-[![Blog](https://img.shields.io/badge/Blog-12100E?style=for-the-badge&logoColor=white)](https://blog.lancedb.com/) 
+[![Medium](https://img.shields.io/badge/Medium-12100E?style=for-the-badge&logo=medium&logoColor=white)](https://blog.lancedb.com/) 
 [![Discord](https://img.shields.io/badge/Discord-%235865F2.svg?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/zMM32dvNtd) 
 [![Twitter](https://img.shields.io/badge/Twitter-%231DA1F2.svg?style=for-the-badge&logo=Twitter&logoColor=white)](https://twitter.com/lancedb)
 
@@ -20,7 +20,7 @@
 
 <hr />
 
-LanceDB is an open-source database for vector-search built with persistent storage, which greatly simplifies retrieval, filtering and management of embeddings.
+LanceDB is an open-source database for vector-search built with persistent storage, which greatly simplifies retrevial, filtering and management of embeddings.
 
 The key features of LanceDB include:
 
@@ -36,7 +36,7 @@ The key features of LanceDB include:
 
 * GPU support in building vector index(*).
 
-* Ecosystem integrations with [LangChain 🦜️🔗](https://python.langchain.com/docs/integrations/vectorstores/lancedb/), [LlamaIndex 🦙](https://gpt-index.readthedocs.io/en/latest/examples/vector_stores/LanceDBIndexDemo.html), Apache-Arrow, Pandas, Polars, DuckDB and more on the way.
+* 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.
 
 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.
 
@@ -83,5 +83,5 @@ result = table.search([100, 100]).limit(2).to_pandas()
 ```
 
 ## Blogs, Tutorials & Videos
-* 📈 <a href="https://blog.lancedb.com/benchmarking-random-access-in-lance/">2000x better performance with Lance over Parquet</a>
+* 📈 <a href="https://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_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_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/bump_version.sh

@@ -1,51 +0,0 @@
-set -e
-
-RELEASE_TYPE=${1:-"stable"}
-BUMP_MINOR=${2:-false}
-TAG_PREFIX=${3:-"v"} # Such as "python-v"
-HEAD_SHA=${4:-$(git rev-parse HEAD)}
-
-readonly SELF_DIR=$(cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )
-
-PREV_TAG=$(git tag --sort='version:refname' | grep ^$TAG_PREFIX | python $SELF_DIR/semver_sort.py $TAG_PREFIX | tail -n 1)
-echo "Found previous tag $PREV_TAG"
-
-# Initially, we don't want to tag if we are doing stable, because we will bump
-# again later. See comment at end for why.
-if [[ "$RELEASE_TYPE" == 'stable' ]]; then 
-  BUMP_ARGS="--no-tag"
-fi
-
-# If last is stable and not bumping minor
-if [[ $PREV_TAG != *beta* ]]; then
-    if [[ "$BUMP_MINOR" != "false" ]]; then
-      # X.Y.Z -> X.(Y+1).0-beta.0
-      bump-my-version bump -vv $BUMP_ARGS minor
-    else
-      # X.Y.Z -> X.Y.(Z+1)-beta.0
-      bump-my-version bump -vv $BUMP_ARGS patch
-    fi
-else
-  if [[ "$BUMP_MINOR" != "false" ]]; then
-    # X.Y.Z-beta.N -> X.(Y+1).0-beta.0
-    bump-my-version bump -vv $BUMP_ARGS minor
-  else
-    # X.Y.Z-beta.N -> X.Y.Z-beta.(N+1)
-    bump-my-version bump -vv $BUMP_ARGS pre_n
-  fi
-fi
-
-# The above bump will always bump to a pre-release version. If we are releasing
-# a stable version, bump the pre-release level ("pre_l") to make it stable.
-if [[ $RELEASE_TYPE == 'stable' ]]; then
-  # X.Y.Z-beta.N -> X.Y.Z
-  bump-my-version bump -vv pre_l
-fi
-
-# Validate that we have incremented version appropriately for breaking changes
-NEW_TAG=$(git describe --tags --exact-match HEAD)
-NEW_VERSION=$(echo $NEW_TAG | sed "s/^$TAG_PREFIX//")
-LAST_STABLE_RELEASE=$(git tag --sort='version:refname' | grep ^$TAG_PREFIX | grep -v beta | grep -vF "$NEW_TAG" | python $SELF_DIR/semver_sort.py $TAG_PREFIX | tail -n 1)
-LAST_STABLE_VERSION=$(echo $LAST_STABLE_RELEASE | sed "s/^$TAG_PREFIX//")
-
-python $SELF_DIR/check_breaking_changes.py $LAST_STABLE_RELEASE $HEAD_SHA $LAST_STABLE_VERSION $NEW_VERSION

ci/check_breaking_changes.py

@@ -1,35 +0,0 @@
-"""
-Check whether there are any breaking changes in the PRs between the base and head commits.
-If there are, assert that we have incremented the minor version.
-"""
-import argparse
-import os
-from packaging.version import parse
-
-from github import Github
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument("base")
-    parser.add_argument("head")
-    parser.add_argument("last_stable_version")
-    parser.add_argument("current_version")
-    args = parser.parse_args()
-
-    repo = Github(os.environ["GITHUB_TOKEN"]).get_repo(os.environ["GITHUB_REPOSITORY"])
-    commits = repo.compare(args.base, args.head).commits
-    prs = (pr for commit in commits for pr in commit.get_pulls())
-
-    for pr in prs:
-        if any(label.name == "breaking-change" for label in pr.labels):
-            print(f"Breaking change in PR: {pr.html_url}")
-            break
-    else:
-        print("No breaking changes found.")
-        exit(0)
-    
-    last_stable_version = parse(args.last_stable_version)
-    current_version = parse(args.current_version)
-    if current_version.minor <= last_stable_version.minor:
-        print("Minor version is not greater than the last stable version.")
-        exit(1)

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

ci/semver_sort.py

@@ -1,35 +0,0 @@
-"""
-Takes a list of semver strings and sorts them in ascending order.
-"""
-
-import sys
-from packaging.version import parse, InvalidVersion
-
-if __name__ == "__main__":
-    import argparse
-    parser = argparse.ArgumentParser()
-    parser.add_argument("prefix", default="v")
-    args = parser.parse_args()
-
-    # Read the input from stdin
-    lines = sys.stdin.readlines()
-
-    # Parse the versions
-    versions = []
-    for line in lines:
-        line = line.strip()
-        try:
-            version_str = line.removeprefix(args.prefix)
-            version = parse(version_str)
-        except InvalidVersion:
-            # There are old tags that don't follow the semver format
-            print(f"Invalid version: {line}", file=sys.stderr)
-            continue
-        versions.append((line, version))
-
-    # Sort the versions
-    versions.sort(key=lambda x: x[1])
-
-    # Print the sorted versions as original strings
-    for line, _ in versions:
-        print(line)

docker-compose.yml

@@ -1,18 +1,18 @@
 version: "3.9"
 services:
   localstack:
-    image: localstack/localstack:3.3
+    image: localstack/localstack:0.14
     ports:
       - 4566:4566
     environment:
-      - SERVICES=s3,dynamodb,kms
+      - SERVICES=s3,dynamodb
       - 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" ]
+      test: [ "CMD", "curl", "-f", "http://localhost:4566/health" ]
       interval: 5s
       retries: 3
       start_period: 10s

docs/mkdocs.yml

@@ -27,6 +27,7 @@ theme:
     - content.tabs.link
     - content.action.edit
     - toc.follow
+    # - toc.integrate
     - navigation.top
     - navigation.tabs
     - navigation.tabs.sticky
@@ -38,207 +39,176 @@ theme:
   custom_dir: overrides
 
 plugins:
-  - search
+- search
-  - autorefs
+- autorefs
-  - mkdocstrings:
+- mkdocstrings:
-      handlers:
+    handlers:
-        python:
+      python:
-          paths: [../python]
+        paths: [../python]
-          options:
+        options:
-            docstring_style: numpy
+          docstring_style: numpy
-            heading_level: 3
+          heading_level: 4
-            show_source: true
+          show_source: true
-            show_symbol_type_in_heading: true
+          show_symbol_type_in_heading: true
-            show_signature_annotations: true
+          show_signature_annotations: true
-            show_root_heading: true
+          members_order: source
-            members_order: source
+        import:
-          import:
+          # for cross references
-            # for cross references
+          - https://arrow.apache.org/docs/objects.inv
-            - https://arrow.apache.org/docs/objects.inv
+          - https://pandas.pydata.org/docs/objects.inv
-            - https://pandas.pydata.org/docs/objects.inv
+- mkdocs-jupyter
-  - mkdocs-jupyter
+- ultralytics:
-  - render_swagger:
+    verbose: True
-      allow_arbitrary_locations : true
+    enabled: True
+    default_image: "assets/lancedb_and_lance.png" # Default image for all pages
+    add_image: True # Automatically add meta image
+    add_keywords: True # Add page keywords in the header tag
+    add_share_buttons: True # Add social share buttons
+    add_authors: False # Display page authors 
+    add_desc: False
+    add_dates: False
 
 markdown_extensions:
-  - admonition
+- admonition
-  - footnotes
+- footnotes
-  - pymdownx.details
+- pymdownx.details
-  - pymdownx.highlight:
+- pymdownx.highlight:
-      anchor_linenums: true
+    anchor_linenums: true
-      line_spans: __span
+    line_spans: __span
-      pygments_lang_class: true
+    pygments_lang_class: true
-  - pymdownx.inlinehilite
+- pymdownx.inlinehilite
-  - pymdownx.snippets:
+- pymdownx.snippets:
-      base_path: ..
+    base_path: ..
-      dedent_subsections: true
+    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
+- attr_list
 
 nav:
-  - Home:
+- Home:
-      - LanceDB: index.md
+  - LanceDB: index.md
-      - 🏃🏼‍♂️ Quick start: basic.md
+  - 🏃🏼‍♂️ Quick start: basic.md
-      - 📚 Concepts:
+  - 📚 Concepts:
-          - Vector search: concepts/vector_search.md
+    - Vector search: concepts/vector_search.md
-          - Indexing: concepts/index_ivfpq.md
+    - Indexing: concepts/index_ivfpq.md
-          - Storage: concepts/storage.md
+    - Storage: concepts/storage.md
-          - Data management: concepts/data_management.md
+    - Data management: concepts/data_management.md
-      - 🔨 Guides:
+  - 🔨 Guides:
-          - Working with tables: guides/tables.md
+    - Working with tables: guides/tables.md
-          - Building an ANN index: ann_indexes.md
+    - Building an ANN index: ann_indexes.md
-          - Vector Search: search.md
+    - Vector Search: search.md
-          - Full-text search: fts.md
+    - Full-text search: fts.md
-          - Hybrid search:
+    - Hybrid search:
-              - Overview: hybrid_search/hybrid_search.md
+      - Overview: hybrid_search/hybrid_search.md
-              - Comparing Rerankers: hybrid_search/eval.md
+      - Comparing Rerankers: hybrid_search/eval.md
-              - Airbnb financial data example: notebooks/hybrid_search.ipynb
+      - Airbnb financial data example: notebooks/hybrid_search.ipynb
-          - Reranking:
+    - Filtering: sql.md
-              - Quickstart: reranking/index.md
+    - Versioning & Reproducibility: notebooks/reproducibility.ipynb
-              - Cohere Reranker: reranking/cohere.md
+    - Configuring Storage: guides/storage.md
-              - Linear Combination Reranker: reranking/linear_combination.md
+  - 🧬 Managing embeddings:
-              - Cross Encoder Reranker: reranking/cross_encoder.md
+    - Overview: embeddings/index.md
-              - ColBERT Reranker: reranking/colbert.md
+    - Embedding functions: embeddings/embedding_functions.md
-              - Jina Reranker: reranking/jina.md
+    - Available models: embeddings/default_embedding_functions.md
-              - OpenAI Reranker: reranking/openai.md
+    - User-defined embedding functions: embeddings/custom_embedding_function.md
-              - Building Custom Rerankers: reranking/custom_reranker.md
+    - "Example: Multi-lingual semantic search": notebooks/multi_lingual_example.ipynb
-              - Example: notebooks/lancedb_reranking.ipynb
+    - "Example: MultiModal CLIP Embeddings": notebooks/DisappearingEmbeddingFunction.ipynb
-          - Filtering: sql.md
+  - 🔌 Integrations:
-          - Versioning & Reproducibility: notebooks/reproducibility.ipynb
+    - Tools and data formats: integrations/index.md
-          - Configuring Storage: guides/storage.md
+    - Pandas and PyArrow: python/pandas_and_pyarrow.md
-          - Sync -> Async Migration Guide: migration.md
+    - Polars: python/polars_arrow.md
-          - Tuning retrieval performance:
+    - DuckDB: python/duckdb.md
-              - Choosing right query type: guides/tuning_retrievers/1_query_types.md
+    - LangChain 🔗: https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/lancedb.html
-              - Reranking: guides/tuning_retrievers/2_reranking.md
+    - LangChain JS/TS 🔗: https://js.langchain.com/docs/modules/data_connection/vectorstores/integrations/lancedb
-              - Embedding fine-tuning: guides/tuning_retrievers/3_embed_tuning.md
+    - LlamaIndex 🦙: https://gpt-index.readthedocs.io/en/latest/examples/vector_stores/LanceDBIndexDemo.html
-      - 🧬 Managing embeddings:
+    - Pydantic: python/pydantic.md
-          - Overview: embeddings/index.md
+    - Voxel51: integrations/voxel51.md
-          - Embedding functions: embeddings/embedding_functions.md
+    - PromptTools: integrations/prompttools.md
-          - Available models: embeddings/default_embedding_functions.md
+  - 🎯 Examples:
-          - User-defined embedding functions: embeddings/custom_embedding_function.md
+    - Overview: examples/index.md
-          - "Example: Multi-lingual semantic search": notebooks/multi_lingual_example.ipynb
+    - 🐍 Python:
-          - "Example: MultiModal CLIP Embeddings": notebooks/DisappearingEmbeddingFunction.ipynb
+      - Overview: examples/examples_python.md
-      - 🔌 Integrations:
-          - Tools and data formats: integrations/index.md
-          - Pandas and PyArrow: python/pandas_and_pyarrow.md
-          - Polars: python/polars_arrow.md
-          - DuckDB: python/duckdb.md
-          - LangChain:
-            - LangChain 🔗: integrations/langchain.md
-            - LangChain demo: notebooks/langchain_demo.ipynb
-            - LangChain JS/TS 🔗: https://js.langchain.com/docs/integrations/vectorstores/lancedb
-          - LlamaIndex 🦙:
-            - LlamaIndex docs: integrations/llamaIndex.md
-            - LlamaIndex demo: notebooks/llamaIndex_demo.ipynb
-          - Pydantic: python/pydantic.md
-          - Voxel51: integrations/voxel51.md
-          - PromptTools: integrations/prompttools.md
-      - 🎯 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/modules.md
-              - REST API: cloud/rest.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
-          - Jina Reranker: reranking/jina.md
-          - OpenAI Reranker: reranking/openai.md
-          - Building Custom Rerankers: reranking/custom_reranker.md
-          - Example: notebooks/lancedb_reranking.ipynb
-      - Filtering: sql.md
-      - Versioning & Reproducibility: notebooks/reproducibility.ipynb
-      - Configuring Storage: guides/storage.md
-      - Sync -> Async Migration Guide: migration.md
-      - Tuning retrieval performance:
-          - Choosing right query type: guides/tuning_retrievers/1_query_types.md
-          - Reranking: guides/tuning_retrievers/2_reranking.md
-          - Embedding fine-tuning: guides/tuning_retrievers/3_embed_tuning.md
-  - Managing Embeddings:
-      - 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 🦜️🔗↗: integrations/langchain.md
-      - LangChain.js 🦜️🔗↗: https://js.langchain.com/docs/integrations/vectorstores/lancedb
-      - LlamaIndex 🦙↗: integrations/llamaIndex.md
-      - Pydantic: python/pydantic.md
-      - Voxel51: integrations/voxel51.md
-      - PromptTools: integrations/prompttools.md
-  - Examples:
-      - examples/index.md
       - YouTube Transcript Search: notebooks/youtube_transcript_search.ipynb
       - Documentation QA Bot using LangChain: notebooks/code_qa_bot.ipynb
       - Multimodal search using CLIP: notebooks/multimodal_search.ipynb
+      - Example - Calculate CLIP Embeddings with Roboflow Inference: examples/image_embeddings_roboflow.md
       - Serverless QA Bot with S3 and Lambda: examples/serverless_lancedb_with_s3_and_lambda.md
       - Serverless QA Bot with Modal: examples/serverless_qa_bot_with_modal_and_langchain.md
-      - YouTube Transcript Search (JS): examples/youtube_transcript_bot_with_nodejs.md
+    - 👾 JavaScript:
-      - Serverless Chatbot from any website: examples/serverless_website_chatbot.md
+      - 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
-  - API reference:
+  - 🔧 CLI & Config: cli_config.md
-      - Overview: api_reference.md
+  - 💭 FAQs: faq.md
-      - Python: python/python.md
+  - ⚙️ API reference:
-      - Javascript (vectordb): javascript/modules.md
+    - 🐍 Python: python/python.md
-      - Javascript (lancedb): js/modules.md
+    - 👾 JavaScript: javascript/modules.md
-      - Rust: https://docs.rs/lancedb/latest/lancedb/index.html
+    - 🦀 Rust: https://docs.rs/vectordb/latest/vectordb/
-  - LanceDB Cloud:
+  - ☁️ LanceDB Cloud:
-      - Overview: cloud/index.md
+    - Overview: cloud/index.md
-      - API reference:
+    - API reference:
-          - 🐍 Python: python/saas-python.md
+      - 🐍 Python: python/saas-python.md
-          - 👾 JavaScript: javascript/modules.md
+      - 👾 JavaScript: javascript/saas-modules.md
-          - REST API: cloud/rest.md
+
+
+- Quick start: basic.md
+- Concepts:
+    - Vector search: concepts/vector_search.md
+    - Indexing: concepts/index_ivfpq.md
+    - Storage: concepts/storage.md
+    - Data management: concepts/data_management.md
+- Guides:
+    - Working with tables: guides/tables.md
+    - Building an ANN index: ann_indexes.md
+    - Vector Search: search.md
+    - Full-text search: fts.md
+    - Hybrid search:
+      - Overview: hybrid_search/hybrid_search.md
+      - Comparing Rerankers: hybrid_search/eval.md
+      - Airbnb financial data example: notebooks/hybrid_search.ipynb
+    - Filtering: sql.md
+    - Versioning & Reproducibility: notebooks/reproducibility.ipynb
+    - Configuring Storage: guides/storage.md
+- Managing Embeddings:
+  - Overview: embeddings/index.md
+  - Embedding functions: embeddings/embedding_functions.md
+  - Available models: embeddings/default_embedding_functions.md
+  - User-defined embedding functions: embeddings/custom_embedding_function.md
+  - "Example: Multi-lingual semantic search": notebooks/multi_lingual_example.ipynb
+  - "Example: MultiModal CLIP Embeddings": notebooks/DisappearingEmbeddingFunction.ipynb
+- Integrations:
+  - Overview: integrations/index.md
+  - Pandas and PyArrow: python/pandas_and_pyarrow.md
+  - Polars: python/polars_arrow.md
+  - DuckDB : python/duckdb.md
+  - LangChain 🦜️🔗↗: https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/lancedb.html
+  - LangChain.js 🦜️🔗↗: https://js.langchain.com/docs/modules/data_connection/vectorstores/integrations/lancedb
+  - LlamaIndex 🦙↗: https://gpt-index.readthedocs.io/en/latest/examples/vector_stores/LanceDBIndexDemo.html
+  - Pydantic: python/pydantic.md
+  - Voxel51: integrations/voxel51.md
+  - PromptTools: integrations/prompttools.md
+- Python 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
+- Javascript examples:
+  - Overview: examples/examples_js.md
+  - YouTube Transcript Search: 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:
+  - Python: python/python.md
+  - Javascript: javascript/modules.md
+- LanceDB Cloud:
+    - Overview: cloud/index.md
+    - API reference:
+      - 🐍 Python: python/saas-python.md
+      - 👾 JavaScript: javascript/saas-modules.md
 
 extra_css:
   - styles/global.css
@@ -251,10 +221,3 @@ 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/openapi.yml

@@ -1,487 +0,0 @@
-openapi: 3.1.0
-info:
-  version: 1.0.0
-  title: LanceDB Cloud API
-  description: |
-    LanceDB Cloud API is a RESTful API that allows users to access and modify data stored in LanceDB Cloud.
-    Table actions are considered temporary resource creations and all use POST method.
-  contact:
-    name: LanceDB support
-    url: https://lancedb.com
-    email: contact@lancedb.com
-
-servers:
-  - url: https://{db}.{region}.api.lancedb.com
-    description: LanceDB Cloud REST endpoint.
-    variables:
-      db:
-        default: ""
-        description: the name of DB
-      region:
-        default: "us-east-1"
-        description: the service region of the DB
-
-security:
-  - key_auth: []
-
-components:
-  securitySchemes:
-    key_auth:
-      name: x-api-key
-      type: apiKey
-      in: header
-  parameters:
-    table_name:
-      name: name
-      in: path
-      description: name of the table
-      required: true
-      schema:
-        type: string
-  responses:
-    invalid_request:
-      description: Invalid request
-      content:
-        text/plain:
-          schema:
-            type: string
-    not_found:
-      description: Not found
-      content:
-        text/plain:
-          schema:
-            type: string
-    unauthorized:
-      description: Unauthorized
-      content:
-        text/plain:
-          schema:
-            type: string
-  requestBodies:
-    arrow_stream_buffer:
-      description: Arrow IPC stream buffer
-      required: true
-      content:
-        application/vnd.apache.arrow.stream:
-          schema:
-            type: string
-            format: binary
-
-paths:
-  /v1/table/:
-    get:
-      description: List tables, optionally, with pagination.
-      tags:
-        - Tables
-      summary: List Tables
-      operationId: listTables
-      parameters:
-        - name: limit
-          in: query
-          description: Limits the number of items to return.
-          schema:
-            type: integer
-        - name: page_token
-          in: query
-          description: Specifies the starting position of the next query
-          schema:
-            type: string
-      responses:
-        "200":
-          description: Successfully returned a list of tables in the DB
-          content:
-            application/json:
-              schema:
-                type: object
-                properties:
-                  tables:
-                    type: array
-                    items:
-                      type: string
-                  page_token:
-                    type: string
-
-        "400":
-          $ref: "#/components/responses/invalid_request"
-        "401":
-          $ref: "#/components/responses/unauthorized"
-        "404":
-          $ref: "#/components/responses/not_found"
-
-  /v1/table/{name}/create/:
-    post:
-      description: Create a new table
-      summary: Create a new table
-      operationId: createTable
-      tags:
-        - Tables
-      parameters:
-        - $ref: "#/components/parameters/table_name"
-      requestBody:
-        $ref: "#/components/requestBodies/arrow_stream_buffer"
-      responses:
-        "200":
-          description: Table successfully created
-        "400":
-          $ref: "#/components/responses/invalid_request"
-        "401":
-          $ref: "#/components/responses/unauthorized"
-        "404":
-          $ref: "#/components/responses/not_found"
-
-  /v1/table/{name}/query/:
-    post:
-      description: Vector Query
-      url: https://{db-uri}.{aws-region}.api.lancedb.com/v1/table/{name}/query/
-      tags:
-        - Data
-      summary: Vector Query
-      parameters:
-        - $ref: "#/components/parameters/table_name"
-      requestBody:
-        required: true
-        content:
-          application/json:
-            schema:
-              type: object
-              properties:
-                vector:
-                  type: FixedSizeList
-                  description: |
-                    The targetted vector to search for. Required.
-                vector_column:
-                  type: string
-                  description: |
-                    The column to query, it can be inferred from the schema if there is only one vector column.
-                prefilter:
-                  type: boolean
-                  description: |
-                    Whether to prefilter the data. Optional.
-                k:
-                  type: integer
-                  description: |
-                    The number of search results to return. Default is 10.
-                distance_type:
-                  type: string
-                  description: |
-                    The distance metric to use for search. L2, Cosine, Dot and Hamming are supported. Default is L2.
-                bypass_vector_index:
-                  type: boolean
-                  description: |
-                    Whether to bypass vector index. Optional.
-                filter:
-                  type: string
-                  description: |
-                    A filter expression that specifies the rows to query. Optional.
-                columns:
-                  type: array
-                  items:
-                    type: string
-                  description: |
-                    The columns to return. Optional.
-                nprobe:
-                  type: integer
-                  description: |
-                    The number of probes to use for search. Optional.
-                refine_factor:
-                  type: integer
-                  description: |
-                    The refine factor to use for search. Optional.
-                  default: null
-                fast_search:
-                  type: boolean
-                  description: |
-                    Whether to use fast search. Optional.
-                  default: false
-              required:
-                - vector
-
-      responses:
-        "200":
-          description: top k results if query is successfully executed
-          content:
-            application/json:
-              schema:
-                type: object
-                properties:
-                  results:
-                    type: array
-                    items:
-                      type: object
-                      properties:
-                        id:
-                          type: integer
-                        selected_col_1_to_return:
-                          type: col_1_type
-                        selected_col_n_to_return:
-                          type: col_n_type
-                        _distance:
-                          type: float
-
-        "400":
-          $ref: "#/components/responses/invalid_request"
-        "401":
-          $ref: "#/components/responses/unauthorized"
-        "404":
-          $ref: "#/components/responses/not_found"
-
-  /v1/table/{name}/insert/:
-    post:
-      description: Insert new data to the Table.
-      tags:
-        - Data
-      operationId: insertData
-      summary: Insert new data.
-      parameters:
-        - $ref: "#/components/parameters/table_name"
-      requestBody:
-        $ref: "#/components/requestBodies/arrow_stream_buffer"
-      responses:
-        "200":
-          description: Insert successful
-        "400":
-          $ref: "#/components/responses/invalid_request"
-        "401":
-          $ref: "#/components/responses/unauthorized"
-        "404":
-          $ref: "#/components/responses/not_found"
-  /v1/table/{name}/merge_insert/:
-    post:
-      description: Create a "merge insert" operation
-        This operation can add rows, update rows, and remove rows all in a single
-        transaction. See python method `lancedb.table.Table.merge_insert` for examples.
-      tags:
-        - Data
-      summary: Merge Insert
-      operationId: mergeInsert
-      parameters:
-        - $ref: "#/components/parameters/table_name"
-        - name: on
-          in: query
-          description: |
-            The column to use as the primary key for the merge operation.
-          required: true
-          schema:
-            type: string
-        - name: when_matched_update_all
-          in: query
-          description: |
-            Rows that exist in both the source table (new data) and
-            the target table (old data) will be updated, replacing
-            the old row with the corresponding matching row.
-          required: false
-          schema:
-            type: boolean
-        - name: when_matched_update_all_filt
-          in: query
-          description: |
-            If present then only rows that satisfy the filter expression will
-            be updated
-          required: false
-          schema:
-            type: string
-        - name: when_not_matched_insert_all
-          in: query
-          description: |
-            Rows that exist only in the source table (new data) will be
-            inserted into the target table (old data).
-          required: false
-          schema:
-            type: boolean
-        - name: when_not_matched_by_source_delete
-          in: query
-          description: |
-            Rows that exist only in the target table (old data) will be
-            deleted. An optional condition (`when_not_matched_by_source_delete_filt`)
-            can be provided to limit what data is deleted.
-          required: false
-          schema:
-            type: boolean
-        - name: when_not_matched_by_source_delete_filt
-          in: query
-          description: |
-            The filter expression that specifies the rows to delete.
-          required: false
-          schema:
-            type: string
-      requestBody:
-        $ref: "#/components/requestBodies/arrow_stream_buffer"
-      responses:
-        "200":
-          description: Merge Insert successful
-        "400":
-          $ref: "#/components/responses/invalid_request"
-        "401":
-          $ref: "#/components/responses/unauthorized"
-        "404":
-          $ref: "#/components/responses/not_found"
-  /v1/table/{name}/delete/:
-    post:
-      description: Delete rows from a table.
-      tags:
-        - Data
-      summary: Delete rows from a table
-      operationId: deleteData
-      parameters:
-        - $ref: "#/components/parameters/table_name"
-      requestBody:
-        required: true
-        content:
-          application/json:
-            schema:
-              type: object
-              properties:
-                predicate:
-                  type: string
-                  description: |
-                    A filter expression that specifies the rows to delete.
-      responses:
-        "200":
-          description: Delete successful
-        "401":
-          $ref: "#/components/responses/unauthorized"
-  /v1/table/{name}/drop/:
-    post:
-      description: Drop a table
-      tags:
-        - Tables
-      summary: Drop a table
-      operationId: dropTable
-      parameters:
-        - $ref: "#/components/parameters/table_name"
-      requestBody:
-        $ref: "#/components/requestBodies/arrow_stream_buffer"
-      responses:
-        "200":
-          description: Drop successful
-        "401":
-          $ref: "#/components/responses/unauthorized"
-
-  /v1/table/{name}/describe/:
-    post:
-      description: Describe a table and return Table Information.
-      tags:
-        - Tables
-      summary: Describe a table
-      operationId: describeTable
-      parameters:
-        - $ref: "#/components/parameters/table_name"
-      responses:
-        "200":
-          description: Table information
-          content:
-            application/json:
-              schema:
-                type: object
-                properties:
-                  table:
-                    type: string
-                  version:
-                    type: integer
-                  schema:
-                    type: string
-                  stats:
-                    type: object
-        "401":
-          $ref: "#/components/responses/unauthorized"
-        "404":
-          $ref: "#/components/responses/not_found"
-
-  /v1/table/{name}/index/list/:
-    post:
-      description: List indexes of a table
-      tags:
-        - Tables
-      summary: List indexes of a table
-      operationId: listIndexes
-      parameters:
-        - $ref: "#/components/parameters/table_name"
-      responses:
-        "200":
-          description: Available list of indexes on the table.
-          content:
-            application/json:
-              schema:
-                type: object
-                properties:
-                  indexes:
-                    type: array
-                    items:
-                      type: object
-                      properties:
-                        columns:
-                          type: array
-                          items:
-                            type: string
-                        index_name:
-                          type: string
-                        index_uuid:
-                          type: string
-        "401":
-          $ref: "#/components/responses/unauthorized"
-        "404":
-          $ref: "#/components/responses/not_found"
-  /v1/table/{name}/create_index/:
-    post:
-      description: Create vector index on a Table
-      tags:
-        - Tables
-      summary: Create vector index on a Table
-      operationId: createIndex
-      parameters:
-        - $ref: "#/components/parameters/table_name"
-      requestBody:
-        required: true
-        content:
-          application/json:
-            schema:
-              type: object
-              properties:
-                column:
-                  type: string
-                metric_type:
-                  type: string
-                  nullable: false
-                  description: |
-                    The metric type to use for the index. L2, Cosine, Dot are supported.
-                index_type:
-                  type: string
-      responses:
-        "200":
-          description: Index successfully created
-        "400":
-          $ref: "#/components/responses/invalid_request"
-        "401":
-          $ref: "#/components/responses/unauthorized"
-        "404":
-          $ref: "#/components/responses/not_found"
-  /v1/table/{name}/create_scalar_index/:
-    post:
-      description: Create a scalar index on a table
-      tags:
-        - Tables
-      summary: Create a scalar index on a table
-      operationId: createScalarIndex
-      parameters:
-        - $ref: "#/components/parameters/table_name"
-      requestBody:
-        required: true
-        content:
-          application/json:
-            schema:
-              type: object
-              properties:
-                column:
-                  type: string
-                index_type:
-                  type: string
-                  required: false
-      responses:
-        "200":
-          description: Scalar Index successfully created
-        "400":
-          $ref: "#/components/responses/invalid_request"
-        "401":
-          $ref: "#/components/responses/unauthorized"
-        "404":
-          $ref: "#/components/responses/not_found"

docs/requirements.txt

@@ -2,5 +2,5 @@ mkdocs==1.5.3
 mkdocs-jupyter==0.24.1
 mkdocs-material==9.5.3
 mkdocstrings[python]==0.20.0
-mkdocs-render-swagger-plugin
 pydantic
+mkdocs-ultralytics-plugin==0.0.44

docs/src/ann_indexes.md

@@ -7,11 +7,20 @@ 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 as data comes in.
-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
 
@@ -19,75 +28,39 @@ 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
+     ```python
-    import lancedb
+     import lancedb
-    import numpy as np
+     import numpy as np
-    uri = "data/sample-lancedb"
+     uri = "data/sample-lancedb"
-    db = lancedb.connect(uri)
+     db = lancedb.connect(uri)
 
-    # Create 10,000 sample vectors
+     # Create 10,000 sample vectors
-    data = [{"vector": row, "item": f"item {i}"}
+     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"
+=== "Typescript"
 
-    === "@lancedb/lancedb"
+     ```typescript
+     --8<--- "docs/src/ann_indexes.ts:import"
 
-        Creating indexes is done via the [lancedb.Table.createIndex](../js/classes/Table.md/#createIndex) method.
+     --8<-- "docs/src/ann_indexes.ts:ingest"
+     ```
 
-        ```typescript
+- **metric** (default: "L2"): The distance metric to use. By default it uses euclidean distance "`L2`".
-        --8<--- "nodejs/examples/ann_indexes.ts:import"
-
-        --8<-- "nodejs/examples/ann_indexes.ts:ingest"
-        ```
-
-    === "vectordb (deprecated)"
-
-        Creating indexes is done via the [lancedb.Table.createIndex](../javascript/interfaces/Table.md/#createIndex) method.
-
-        ```typescript
-        --8<--- "docs/src/ann_indexes.ts:import"
-
-        --8<-- "docs/src/ann_indexes.ts:ingest"
-        ```
-
-=== "Rust"
-
-    ```rust
-    --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
+- **num_partitions** (default: 256): The number of partitions of the index.
-  of the number of rows.
+- **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
-!!! note
+  a single PQ code.
-
-    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)
@@ -105,29 +78,29 @@ You can specify the GPU device to train IVF partitions via
 
 === "Linux"
 
-    <!-- skip-test -->
+     <!-- skip-test -->
-    ``` { .python .copy }
+     ``` { .python .copy }
-    # Create index using CUDA on Nvidia GPUs.
+     # Create index using CUDA on Nvidia GPUs.
-    tbl.create_index(
+     tbl.create_index(
-        num_partitions=256,
+          num_partitions=256,
-        num_sub_vectors=96,
+          num_sub_vectors=96,
-        accelerator="cuda"
+          accelerator="cuda"
-    )
+     )
-    ```
+     ```
 
-=== "MacOS"
+=== "Macos"
 
-    <!-- skip-test -->
+     <!-- skip-test -->
-    ```python
+     ```python
-    # Create index using MPS on Apple Silicon.
+     # Create index using MPS on Apple Silicon.
-    tbl.create_index(
+     tbl.create_index(
-        num_partitions=256,
+          num_partitions=256,
-        num_sub_vectors=96,
+          num_sub_vectors=96,
-        accelerator="mps"
+          accelerator="mps"
-    )
+     )
-    ```
+     ```
 
-Troubleshooting:
+Trouble shootings:
 
 If you see `AssertionError: Torch not compiled with CUDA enabled`, you need to [install
 PyTorch with CUDA support](https://pytorch.org/get-started/locally/).
@@ -150,41 +123,25 @@ There are a couple of parameters that can be used to fine-tune the search:
 
 === "Python"
 
-    ```python
+     ```python
-    tbl.search(np.random.random((1536))) \
+     tbl.search(np.random.random((1536))) \
-        .limit(2) \
+         .limit(2) \
-        .nprobes(20) \
+         .nprobes(20) \
-        .refine_factor(10) \
+         .refine_factor(10) \
-        .to_pandas()
+         .to_pandas()
-    ```
+     ```
 
-    ```text
+     ```text
                                               vector       item       _distance
-    0  [0.44949695, 0.8444449, 0.06281311, 0.23338133...  item 1141  103.575333
+     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
+     1  [0.48587373, 0.269207, 0.15095535, 0.65531915,...  item 3953  108.393867
-    ```
+     ```
 
-=== "TypeScript"
+=== "Typescript"
 
-    === "@lancedb/lancedb"
+     ```typescript
-
+     --8<-- "docs/src/ann_indexes.ts:search1"
-        ```typescript
+     ```
-        --8<-- "nodejs/examples/ann_indexes.ts:search1"
-        ```
-
-    === "vectordb (deprecated)"
-
-        ```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.
 
@@ -194,23 +151,15 @@ You can further filter the elements returned by a search using a where clause.
 
 === "Python"
 
-    ```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_pandas()
-    ```
+     ```
 
-=== "TypeScript"
+=== "Typescript"
 
-    === "@lancedb/lancedb"
+     ```javascript
-
+     --8<-- "docs/src/ann_indexes.ts:search2"
-        ```typescript
+     ```
-        --8<-- "nodejs/examples/ann_indexes.ts:search2"
-        ```
-
-    === "vectordb (deprecated)"
-
-        ```javascript
-        --8<-- "docs/src/ann_indexes.ts:search2"
-        ```
 
 ### Projections (select clause)
 
@@ -218,49 +167,33 @@ You can select the columns returned by the query using a select clause.
 
 === "Python"
 
-    ```python
+     ```python
-    tbl.search(np.random.random((1536))).select(["vector"]).to_pandas()
+     tbl.search(np.random.random((1536))).select(["vector"]).to_pandas()
-    ```
+     ```
 
 
-    ```text
+     ```text
-                                                vector _distance
+                                                   vector _distance
-    0  [0.30928212, 0.022668175, 0.1756372, 0.4911822...  93.971092
+     0  [0.30928212, 0.022668175, 0.1756372, 0.4911822...  93.971092
-    1  [0.2525465, 0.01723831, 0.261568, 0.002007689,...  95.173485
+     1  [0.2525465, 0.01723831, 0.261568, 0.002007689,...  95.173485
-    ...
+     ...
-    ```
+     ```
 
-=== "TypeScript"
+=== "Typescript"
 
-    === "@lancedb/lancedb"
+     ```typescript
-
+     --8<-- "docs/src/ann_indexes.ts:search3"
-        ```typescript
+     ```
-        --8<-- "nodejs/examples/ann_indexes.ts:search3"
-        ```
-
-    === "vectordb (deprecated)"
-
-        ```typescript
-        --8<-- "docs/src/ann_indexes.ts:search3"
-        ```
 
 ## FAQ
 
-### Why do I need to manually create an index?
-
-Currently, LanceDB does _not_ automatically create the ANN index.
-LanceDB is well-optimized for kNN (exhaustive search) via a disk-based index. For many use-cases,
-datasets of the order of ~100K vectors don't require index creation. If you can live with up to
-100ms latency, skipping index creation is a simpler workflow while guaranteeing 100% recall.
-
 ### When is it necessary to create an ANN vector index?
 
-`LanceDB` comes out-of-the-box with highly optimized SIMD code for computing vector similarity.
+`LanceDB` has manually-tuned SIMD code for computing vector distances.
-In our benchmarks, computing distances for 100K pairs of 1K dimension vectors takes **less than 20ms**.
+In our benchmarks, computing 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,
+For small datasets (< 100K rows) or applications that can accept 100ms latency, vector indices are usually not necessary.
-vector indices are usually not necessary.
 
-For large-scale or higher dimension vectors, it can beneficial to create vector index for performance.
+For large-scale or higher dimension vectors, it is beneficial to create vector index.
 
 ### How big is my index, and how many memory will it take?
 

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

@@ -3,7 +3,7 @@
 !!! info "LanceDB can be run in a number of ways:"
 
     * Embedded within an existing backend (like your Django, Flask, Node.js or FastAPI application)
-    * Directly from a client application like a Jupyter notebook for analytical workloads
+    * Connected to directly from a client application like a Jupyter notebook for analytical workloads
     * Deployed as a remote serverless database
 
 ![](assets/lancedb_embedded_explanation.png)
@@ -16,50 +16,21 @@
       pip install lancedb
       ```
 
-=== "Typescript[^1]"
+=== "Typescript"
-    === "@lancedb/lancedb"
 
-        ```shell
+      ```shell
-        npm install @lancedb/lancedb
+      npm install vectordb
-        ```
+      ```
-        !!! note "Bundling `@lancedb/lancedb` apps with Webpack"
 
-            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.
-
-            ```javascript
-            /** @type {import('next').NextConfig} */
-            module.exports = ({
-            webpack(config) {
-                config.externals.push({ '@lancedb/lancedb': '@lancedb/lancedb' })
-                return config;
-            }
-            })
-            ```
-    === "vectordb (deprecated)"
-
-        ```shell
-        npm install vectordb
-        ```
-        !!! note "Bundling `vectordb` apps with Webpack"
-
-            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.
-
-            ```javascript
-            /** @type {import('next').NextConfig} */
-            module.exports = ({
-            webpack(config) {
-                config.externals.push({ vectordb: 'vectordb' })
-                return config;
-            }
-            })
-            ```
 === "Rust"
 
+    !!! warning "Rust SDK is experimental, might introduce breaking changes in the near future"
+
     ```shell
-    cargo add lancedb
+    cargo add vectordb
     ```
 
-    !!! info "To use the lancedb create, you first need to install protobuf."
+    !!! info "To use the vectordb create, you first need to install protobuf."
 
     === "macOS"
 
@@ -73,109 +44,49 @@
         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)"
+    !!! info "Please also make sure you're using the same version of Arrow as in the [vectordb crate](https://github.com/lancedb/lancedb/blob/main/Cargo.toml)"
 
-### Preview releases
+## How to connect to a database
-
-Stable releases are created about every 2 weeks. For the latest features and bug
-fixes, you can install the preview release. These releases receive the same
-level of testing as stable releases, but are not guaranteed to be available for
-more than 6 months after they are released. Once your application is stable, we
-recommend switching to stable releases.
 
 === "Python"
 
-      ```shell
+      ```python
-      pip install --pre --extra-index-url https://pypi.fury.io/lancedb/ lancedb
+      import lancedb
+      uri = "data/sample-lancedb"
+      db = lancedb.connect(uri)
       ```
 
-=== "Typescript[^1]"
+=== "Typescript"
 
-    === "@lancedb/lancedb"
+    ```typescript
+    --8<-- "docs/src/basic_legacy.ts:import"
 
-        ```shell
+    --8<-- "docs/src/basic_legacy.ts:open_db"
-        npm install @lancedb/lancedb@preview
-        ```
-    === "vectordb (deprecated)"
-
-        ```shell
-        npm install vectordb@preview
-        ```
-
-=== "Rust"
-
-    We don't push preview releases to crates.io, but you can referent the tag
-    in GitHub within your Cargo dependencies:
-
-    ```toml
-    [dependencies]
-    lancedb = { git = "https://github.com/lancedb/lancedb.git", tag = "vX.Y.Z-beta.N" }
     ```
 
-## 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[^1]"
-
-    === "@lancedb/lancedb"
-
-        ```typescript
-        import * as lancedb from "@lancedb/lancedb";
-        import * as arrow from "apache-arrow";
-
-        --8<-- "nodejs/examples/basic.ts:connect"
-        ```
-
-    === "vectordb (deprecated)"
-
-        ```typescript
-        --8<-- "docs/src/basic_legacy.ts:open_db"
-        ```
-
 === "Rust"
 
     ```rust
     #[tokio::main]
     async fn main() -> Result<()> {
-        --8<-- "rust/lancedb/examples/simple.rs:connect"
+        --8<-- "rust/vectordb/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."
+    !!! info "See [examples/simple.rs](https://github.com/lancedb/lancedb/tree/main/rust/vectordb/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
+## How to 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"
+    tbl = db.create_table("my_table",
-    --8<-- "python/python/tests/docs/test_basic.py:create_table_async"
+                    data=[{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
+                          {"vector": [5.9, 26.5], "item": "bar", "price": 20.0}])
     ```
 
     If the table already exists, LanceDB will raise an error by default.
@@ -185,115 +96,80 @@ table.
     You can also pass in a pandas DataFrame directly:
 
     ```python
-    --8<-- "python/python/tests/docs/test_basic.py:create_table_pandas"
+    import pandas as pd
-    --8<-- "python/python/tests/docs/test_basic.py:create_table_async_pandas"
+    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)
     ```
 
-=== "Typescript[^1]"
+=== "Typescript"
 
-    === "@lancedb/lancedb"
+    ```typescript
+    --8<-- "docs/src/basic_legacy.ts:create_table"
+    ```
 
-        ```typescript
+    If the table already exists, LanceDB will raise an error by default.
-        --8<-- "nodejs/examples/basic.ts:create_table"
+    If you want to overwrite the table, you can pass in `mode="overwrite"`
-        ```
+    to the `createTable` function.
-
-    === "vectordb (deprecated)"
-
-        ```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"
+    use arrow_schema::{DataType, Schema, Field};
+    use arrow_array::{RecordBatch, RecordBatchIterator};
+
+    --8<-- "rust/vectordb/examples/simple.rs:create_table"
     ```
 
-    If the table already exists, LanceDB will raise an error by default.  See
+    If the table already exists, LanceDB will raise an error by default.
-    [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
+!!! 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)."
 
-        The Rust SDK currently expects data to be provided as an Arrow
+### Creating an empty table
-        [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)."
-
-!!! info "Automatic embedding generation with Embedding API"
-    When working with embedding models, it is recommended to use the LanceDB embedding API to automatically create vector representation of the data and queries in the background. See the [quickstart example](#using-the-embedding-api) or the embedding API [guide](./embeddings/)
-
-### 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
+In this case, you can create an empty table and specify the schema.
-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 pyarrow as pa
-      --8<-- "python/python/tests/docs/test_basic.py:create_empty_table_async"
+      schema = pa.schema([pa.field("vector", pa.list_(pa.float32(), list_size=2))])
+      tbl = db.create_table("empty_table", schema=schema)
       ```
 
-    !!! note "You can define schema in Pydantic"
+=== "Typescript"
-        LanceDB comes with Pydantic support, which allows you to define the schema of your data using Pydantic models. This makes it easy to work with LanceDB tables and data. Learn more about all supported types in [tables guide](./guides/tables.md).
 
-=== "Typescript[^1]"
+    ```typescript
-
+    --8<-- "docs/src/basic_legacy.ts:create_empty_table"
-    === "@lancedb/lancedb"
+    ```
-
-        ```typescript
-        --8<-- "nodejs/examples/basic.ts:create_empty_table"
-        ```
-
-    === "vectordb (deprecated)"
-
-        ```typescript
-        --8<-- "docs/src/basic_legacy.ts:create_empty_table"
-        ```
 
 === "Rust"
 
     ```rust
-    --8<-- "rust/lancedb/examples/simple.rs:create_empty_table"
+    --8<-- "rust/vectordb/examples/simple.rs:create_empty_table"
     ```
 
-## Open an existing table
+## How to open an existing table
 
-Once created, you can open a table as follows:
+Once created, you can open a table using the following code:
 
 === "Python"
 
     ```python
-    --8<-- "python/python/tests/docs/test_basic.py:open_table"
+    tbl = db.open_table("my_table")
-    --8<-- "python/python/tests/docs/test_basic.py:open_table_async"
     ```
 
-=== "Typescript[^1]"
+=== "Typescript"
-    === "@lancedb/lancedb"
-
-        ```typescript
-        --8<-- "nodejs/examples/basic.ts:open_table"
-        ```
-
-    === "vectordb (deprecated)"
-
-        ```typescript
-        const tbl = await db.openTable("myTable");
-        ```
 
+    ```typescript
+    const tbl = await db.openTable("myTable");
+    ```
 
 === "Rust"
 
     ```rust
-    --8<-- "rust/lancedb/examples/simple.rs:open_existing_tbl"
+    --8<-- "rust/vectordb/examples/simple.rs:open_with_existing_file"
     ```
 
 If you forget the name of your table, you can always get a listing of all table names:
@@ -301,139 +177,101 @@ If you forget the name of your table, you can always get a listing of all table
 === "Python"
 
     ```python
-    --8<-- "python/python/tests/docs/test_basic.py:table_names"
+    print(db.table_names())
-    --8<-- "python/python/tests/docs/test_basic.py:table_names_async"
     ```
 
-=== "Typescript[^1]"
+=== "Javascript"
-    === "@lancedb/lancedb"
 
-        ```typescript
+    ```javascript
-        --8<-- "nodejs/examples/basic.ts:table_names"
+    console.log(await db.tableNames());
-        ```
+    ```
-
-    === "vectordb (deprecated)"
-
-        ```typescript
-        console.log(await db.tableNames());
-        ```
 
 === "Rust"
 
     ```rust
-    --8<-- "rust/lancedb/examples/simple.rs:list_names"
+    --8<-- "rust/vectordb/examples/simple.rs:list_names"
     ```
 
-## Add data to a table
+## How to add data to a table
 
-After a table has been created, you can always add more data to it as follows:
+After a table has been created, you can always add more data to it using
 
 === "Python"
 
     ```python
-    --8<-- "python/python/tests/docs/test_basic.py:add_data"
+
-    --8<-- "python/python/tests/docs/test_basic.py:add_data_async"
+    # Option 1: Add a list of dicts to a table
+    data = [{"vector": [1.3, 1.4], "item": "fizz", "price": 100.0},
+            {"vector": [9.5, 56.2], "item": "buzz", "price": 200.0}]
+    tbl.add(data)
+
+    # Option 2: Add a pandas DataFrame to a table
+    df = pd.DataFrame(data)
+    tbl.add(data)
     ```
 
-=== "Typescript[^1]"
+=== "Typescript"
-    === "@lancedb/lancedb"
 
-        ```typescript
+    ```typescript
-        --8<-- "nodejs/examples/basic.ts:add_data"
+    --8<-- "docs/src/basic_legacy.ts:add"
-        ```
+    ```
-
-    === "vectordb (deprecated)"
-
-        ```typescript
-        --8<-- "docs/src/basic_legacy.ts:add"
-        ```
 
 === "Rust"
 
     ```rust
-    --8<-- "rust/lancedb/examples/simple.rs:add"
+    --8<-- "rust/vectordb/examples/simple.rs:add"
     ```
 
-## Search for nearest neighbors
+## How to search for (approximate) nearest neighbors
 
-Once you've embedded the query, you can find its nearest neighbors as follows:
+Once you've embedded the query, you can find its nearest neighbors using the following code:
 
 === "Python"
 
     ```python
-    --8<-- "python/python/tests/docs/test_basic.py:vector_search"
+    tbl.search([100, 100]).limit(2).to_pandas()
-    --8<-- "python/python/tests/docs/test_basic.py:vector_search_async"
     ```
 
     This returns a pandas DataFrame with the results.
 
-=== "Typescript[^1]"
+=== "Typescript"
-    === "@lancedb/lancedb"
 
-        ```typescript
+    ```typescript
-        --8<-- "nodejs/examples/basic.ts:vector_search"
+    --8<-- "docs/src/basic_legacy.ts:search"
-        ```
+    ```
-
-    === "vectordb (deprecated)"
-
-        ```typescript
-        --8<-- "docs/src/basic_legacy.ts:search"
-        ```
 
 === "Rust"
 
     ```rust
     use futures::TryStreamExt;
 
-    --8<-- "rust/lancedb/examples/simple.rs:search"
+    --8<-- "rust/vectordb/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"
+    tbl.create_index()
-    --8<-- "python/python/tests/docs/test_basic.py:create_index_async"
     ```
 
-=== "Typescript[^1]"
+=== "Typescript"
-    === "@lancedb/lancedb"
 
-        ```typescript
+    ```{.typescript .ignore}
-        --8<-- "nodejs/examples/basic.ts:create_index"
+    --8<-- "docs/src/basic_legacy.ts:create_index"
-        ```
+    ```
-
-    === "vectordb (deprecated)"
-
-        ```{.typescript .ignore}
-        --8<-- "docs/src/basic_legacy.ts:create_index"
-        ```
 
 === "Rust"
 
     ```rust
-    --8<-- "rust/lancedb/examples/simple.rs:create_index"
+     --8<-- "rust/vectordb/examples/simple.rs:create_index"
     ```
 
-!!! note "Why do I need to create an index manually?"
+Check [Approximate Nearest Neighbor (ANN) Indexes](/ann_indices.md) section for more details.
-LanceDB does not automatically create the ANN index for two reasons. The first is that it's optimized
-for really fast retrievals via a disk-based index, and the second is that data and query workloads can
-be very diverse, so there's no one-size-fits-all index configuration. LanceDB provides many parameters
-to fine-tune index size, query latency and accuracy. See the section on
-[ANN indexes](ann_indexes.md) for more details.
 
-## Delete rows from a table
+## How to 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.
@@ -442,125 +280,78 @@ This can delete any number of rows that match the filter.
 === "Python"
 
     ```python
-    --8<-- "python/python/tests/docs/test_basic.py:delete_rows"
+    tbl.delete('item = "fizz"')
-    --8<-- "python/python/tests/docs/test_basic.py:delete_rows_async"
     ```
 
-=== "Typescript[^1]"
+=== "Typescript"
 
-    === "@lancedb/lancedb"
+    ```typescript
-
+    --8<-- "docs/src/basic_legacy.ts:delete"
-        ```typescript
+    ```
-        --8<-- "nodejs/examples/basic.ts:delete_rows"
-        ```
-
-    === "vectordb (deprecated)"
-
-        ```typescript
-        --8<-- "docs/src/basic_legacy.ts:delete"
-        ```
 
 === "Rust"
 
     ```rust
-    --8<-- "rust/lancedb/examples/simple.rs:delete"
+    --8<-- "rust/vectordb/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
+as the `where()` clause on a search. They can be as simple or complex as needed.
-simple or complex as needed. To see what expressions are supported, see the
+To see what expressions are supported, see the [SQL filters](sql.md) section.
-[SQL filters](sql.md) section.
 
 === "Python"
 
       Read more: [lancedb.table.Table.delete][]
 
-=== "Typescript[^1]"
+=== "Javascript"
 
-    === "@lancedb/lancedb"
+      Read more: [vectordb.Table.delete](javascript/interfaces/Table.md#delete)
 
-        Read more: [lancedb.Table.delete](javascript/interfaces/Table.md#delete)
+## How to remove a table
-
-    === "vectordb (deprecated)"
-
-        Read more: [vectordb.Table.delete](javascript/interfaces/Table.md#delete)
-
-=== "Rust"
-
-      Read more: [lancedb::Table::delete](https://docs.rs/lancedb/latest/lancedb/table/struct.Table.html#method.delete)
-
-## Drop a table
 
 Use the `drop_table()` method on the database to remove a table.
 
 === "Python"
 
-    ```python
+      ```python
-    --8<-- "python/python/tests/docs/test_basic.py:drop_table"
+      db.drop_table("my_table")
-    --8<-- "python/python/tests/docs/test_basic.py:drop_table_async"
+      ```
-    ```
 
-    This permanently removes the table and is not recoverable, unlike deleting rows.
+      This permanently removes the table and is not recoverable, unlike deleting rows.
-    By default, if the table does not exist an exception is raised. To suppress this,
+      By default, if the table does not exist an exception is raised. To suppress this,
-    you can pass in `ignore_missing=True`.
+      you can pass in `ignore_missing=True`.
 
-=== "Typescript[^1]"
+=== "Typescript"
 
-    === "@lancedb/lancedb"
+      ```typescript
+      --8<-- "docs/src/basic_legacy.ts:drop_table"
+      ```
 
-        ```typescript
+      This permanently removes the table and is not recoverable, unlike deleting rows.
-        --8<-- "nodejs/examples/basic.ts:drop_table"
+      If the table does not exist an exception is raised.
-        ```
-
-    === "vectordb (deprecated)"
-
-        ```typescript
-        --8<-- "docs/src/basic_legacy.ts:drop_table"
-        ```
-
-        This permanently removes the table and is not recoverable, unlike deleting rows.
-        If the table does not exist an exception is raised.
 
 === "Rust"
 
     ```rust
-    --8<-- "rust/lancedb/examples/simple.rs:drop_table"
+    --8<-- "rust/vectordb/examples/simple.rs:drop_table"
     ```
 
+!!! note "Bundling `vectordb` apps with Webpack"
 
-## Using the Embedding API
+    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.
-You can use the embedding API when working with embedding models. It automatically vectorizes the data at ingestion and query time and comes with built-in integrations with popular embedding models like Openai, Hugging Face, Sentence Transformers, CLIP and more.
 
-=== "Python"
+    ```javascript
-
+    /** @type {import('next').NextConfig} */
-    ```python
+    module.exports = ({
-    --8<-- "python/python/tests/docs/test_embeddings_optional.py:imports"
+    webpack(config) {
-    --8<-- "python/python/tests/docs/test_embeddings_optional.py:openai_embeddings"
+        config.externals.push({ vectordb: 'vectordb' })
+        return config;
+    }
+    })
     ```
 
-=== "Typescript[^1]"
-
-    === "@lancedb/lancedb"
-
-        ```typescript
-        --8<-- "nodejs/examples/embedding.ts:imports"
-        --8<-- "nodejs/examples/embedding.ts:openai_embeddings"
-        ```
-
-=== "Rust"
-
-    ```rust
-    --8<-- "rust/lancedb/examples/openai.rs:imports"
-    --8<-- "rust/lancedb/examples/openai.rs:openai_embeddings"
-    ```
-
-Learn about using the existing integrations and creating custom embedding functions in the [embedding API guide](./embeddings/).
-
-
 ## 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.
 
 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.
-
-[^1]: The `vectordb` package is a legacy package that is  deprecated in favor of `@lancedb/lancedb`.  The `vectordb` package will continue to receive bug fixes and security updates until September 2024.  We recommend all new projects use `@lancedb/lancedb`.  See the [migration guide](migration.md) for more information.

docs/src/basic_legacy.ts

@@ -24,7 +24,6 @@ const example = async () => {
   );
   // --8<-- [end:create_table]
 
-
   // --8<-- [start:add]
   const newData = Array.from({ length: 500 }, (_, i) => ({
     vector: [i, i + 1],

docs/src/cli_config.md

@@ -0,0 +1,51 @@
+
+# CLI & Config
+
+## LanceDB CLI
+Once lanceDB is installed, you can access the CLI using `lancedb` command on the console.
+
+```
+lancedb
+```
+
+This lists out all the various command-line options available. You can get the usage or help for a particular command.
+
+```
+lancedb {command} --help
+```
+
+## LanceDB config
+LanceDB uses a global config file to store certain settings. These settings are configurable using the lanceDB cli.
+To view your config settings, you can use:
+
+```
+lancedb config
+```
+
+These config parameters can be tuned using the cli.
+
+```
+lancedb {config_name} --{argument}
+```
+
+## LanceDB Opt-in Diagnostics
+When enabled, LanceDB will send anonymous events to help us improve LanceDB. These diagnostics are used only for error reporting and no data is collected. Error & stats allow us to automate certain aspects of bug reporting, prioritization of fixes and feature requests.
+These diagnostics are opt-in and can be enabled or disabled using the `lancedb diagnostics` command. These are enabled by default.
+
+### Get usage help
+
+```
+lancedb diagnostics --help
+```
+
+### Disable diagnostics
+
+```
+lancedb diagnostics --disabled
+```
+
+### Enable diagnostics
+
+```
+lancedb diagnostics --enabled
+```

docs/src/cloud/rest.md

@@ -1 +0,0 @@
-!!swagger ../../openapi.yml!!

docs/src/concepts/index_ivfpq.md

@@ -31,7 +31,7 @@ As an example, consider starting with 128-dimensional vector consisting of 32-bi
 
 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.
+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 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)
 
@@ -81,4 +81,24 @@ The above query will perform a search on the table `tbl` using the given query v
 * `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.
+
+
+## FAQ
+
+### When is it necessary to create a vector index?
+
+LanceDB has manually-tuned SIMD code for computing vector distances. In our benchmarks, computing 100K pairs of 1K dimension vectors takes **<20ms**. For small datasets (<100K rows) or applications that can accept up to 100ms latency, vector indices are usually not necessary.
+
+For large-scale or higher dimension vectors, it is beneficial to create vector index.
+
+### How big is my index, and how much 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 1024-dimension vectors, 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?
+
+`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 PQ short codes to generate on each vector. Because PQ is a lossy compression of the original vector, a higher `num_sub_vectors` usually results in less space distortion, and thus yields better accuracy. However, a higher `num_sub_vectors` also 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.

docs/src/embeddings/default_embedding_functions.md

@@ -19,256 +19,49 @@ Allows you to set parameters when registering a `sentence-transformers` object.
 | `normalize` | `bool` | `True` | Whether to normalize the input text before feeding it to the model |
 
 
-??? "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 Words(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(df)
-query = "old greeting"
-actual = table.search(query).limit(1).to_pydantic(Words)[0]
-print(actual.text)
-```
-
-
-### Ollama embeddings
-Generate embeddings via the [ollama](https://github.com/ollama/ollama-python) python library. More details:
-
-- [Ollama docs on embeddings](https://github.com/ollama/ollama/blob/main/docs/api.md#generate-embeddings)
-- [Ollama blog on embeddings](https://ollama.com/blog/embedding-models)
-
-| Parameter              | Type                       | Default Value            | Description                                                                                                                                    |
-|------------------------|----------------------------|--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------|
-| `name`                 | `str`                      | `nomic-embed-text`       | The name of the model.                                                                                                                         |
-| `host`                 | `str`                      | `http://localhost:11434` | The Ollama host to connect to.                                                                                                                 |
-| `options`              | `ollama.Options` or `dict` | `None`                   | Additional model parameters listed in the documentation for the Modelfile such as `temperature`. |
-| `keep_alive`           | `float` or `str`           | `"5m"`                   | Controls how long the model will stay loaded into memory following the request.                                                                |
-| `ollama_client_kwargs` | `dict`                     | `{}`                     | kwargs that can be past to the `ollama.Client`.                                                                                                |
-
-```python
-import lancedb
-from lancedb.pydantic import LanceModel, Vector
-from lancedb.embeddings import get_registry
-
 db = lancedb.connect("/tmp/db")
-func = get_registry().get("ollama").create(name="nomic-embed-text")
+registry = EmbeddingFunctionRegistry.get_instance()
+func = registry.get("sentence-transformers").create(device="cpu")
 
 class Words(LanceModel):
     text: str = func.SourceField()
     vector: Vector(func.ndims()) = func.VectorField()
 
-table = db.create_table("words", schema=Words, mode="overwrite")
+table = db.create_table("words", schema=Words)
-table.add([
+table.add(
-    {"text": "hello world"},
+    [
-    {"text": "goodbye world"}
+        {"text": "hello world"}
-])
+        {"text": "goodbye world"}
+    ]
+)
 
 query = "greetings"
 actual = table.search(query).limit(1).to_pydantic(Words)[0]
 print(actual.text)
 ```
 
-
 ### OpenAI embeddings
 LanceDB registers the OpenAI embeddings function in the registry by default, as `openai`. Below are the parameters that you can customize when creating the instances:
 
 | 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")
+registry = EmbeddingFunctionRegistry.get_instance()
+func = registry.get("openai").create()
 
 class Words(LanceModel):
     text: str = func.SourceField()
     vector: Vector(func.ndims()) = func.VectorField()
 
-table = db.create_table("words", schema=Words, mode="overwrite")
+table = db.create_table("words", schema=Words)
 table.add(
     [
-        {"text": "hello world"},
+        {"text": "hello world"}
         {"text": "goodbye world"}
     ]
     )
@@ -365,107 +158,6 @@ tbl.add(df)
 rs = tbl.search("hello").limit(1).to_pandas()
 ```
 
-### Cohere Embeddings
-Using cohere API requires cohere package, which can be installed using `pip install cohere`. Cohere embeddings are used to generate embeddings for text data. The embeddings can be used for various tasks like semantic search, clustering, and classification.
-You also need to set the `COHERE_API_KEY` environment variable to use the Cohere API.
-
-Supported models are:
-```
-    * embed-english-v3.0
-    * embed-multilingual-v3.0
-    * embed-english-light-v3.0
-    * embed-multilingual-light-v3.0
-    * embed-english-v2.0
-    * embed-english-light-v2.0
-    * embed-multilingual-v2.0
-```
-
-Supported parameters (to be passed in `create` method) are:
-
-| Parameter | Type | Default Value | Description |
-|---|---|---|---|
-| `name` | `str` | `"embed-english-v2.0"` | The model ID of the cohere model to use. Supported base models for Text Embeddings: embed-english-v3.0, embed-multilingual-v3.0, embed-english-light-v3.0, embed-multilingual-light-v3.0, embed-english-v2.0, embed-english-light-v2.0, embed-multilingual-v2.0 |
-| `source_input_type` | `str` | `"search_document"` | The type of input data to be used for the source column. |
-| `query_input_type` | `str` | `"search_query"` | The type of input data to be used for the query. |
-
-Cohere supports following input types:
-| Input Type               | Description                          |
-|-------------------------|---------------------------------------|
-| "`search_document`"     | Used for embeddings stored in a vector|
-|                         | database for search use-cases.        |
-| "`search_query`"        | Used for embeddings of search queries |
-|                         | run against a vector DB               |
-| "`semantic_similarity`" | Specifies the given text will be used |
-|                         | for Semantic Textual Similarity (STS) |
-| "`classification`"      | Used for embeddings passed through a  |
-|                         | text classifier.                      |
-| "`clustering`"          | Used for the embeddings run through a |
-|                         | clustering algorithm                  |
-
-Usage Example:
-    
-    ```python
-        import lancedb
-        from lancedb.pydantic import LanceModel, Vector
-        from lancedb.embeddings import EmbeddingFunctionRegistry
-
-        cohere = EmbeddingFunctionRegistry
-            .get_instance()
-            .get("cohere")
-            .create(name="embed-multilingual-v2.0")
-
-        class TextModel(LanceModel):
-            text: str = cohere.SourceField()
-            vector: Vector(cohere.ndims()) =  cohere.VectorField()
-
-        data = [ { "text": "hello world" },
-                { "text": "goodbye world" }]
-
-        db = lancedb.connect("~/.lancedb")
-        tbl = db.create_table("test", schema=TextModel, mode="overwrite")
-
-        tbl.add(data)
-    ```
-
-### Jina Embeddings
-Jina embeddings are used to generate embeddings for text and image data.
-You also need to set the `JINA_API_KEY` environment variable to use the Jina API.
-
-You can find a list of supported models under [https://jina.ai/embeddings/](https://jina.ai/embeddings/)
-
-Supported parameters (to be passed in `create` method) are:
-
-| Parameter | Type | Default Value | Description |
-|---|---|---|---|
-| `name` | `str` | `"jina-clip-v1"` | The model ID of the jina model to use |
-
-Usage Example:
-
-```python
-    import os
-    import lancedb
-    from lancedb.pydantic import LanceModel, Vector
-    from lancedb.embeddings import EmbeddingFunctionRegistry
-
-    os.environ['JINA_API_KEY'] = 'jina_*'
-
-    jina_embed = EmbeddingFunctionRegistry.get_instance().get("jina").create(name="jina-embeddings-v2-base-en")
-
-
-    class TextModel(LanceModel):
-        text: str = jina_embed.SourceField()
-        vector: Vector(jina_embed.ndims()) = jina_embed.VectorField()
-
-
-    data = [{"text": "hello world"},
-            {"text": "goodbye world"}]
-
-    db = lancedb.connect("~/.lancedb-2")
-    tbl = db.create_table("test", schema=TextModel, mode="overwrite")
-
-    tbl.add(data)
-```
-
 ### 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:
@@ -483,8 +175,7 @@ Supported Embedding modelIDs are:
 * `cohere.embed-english-v3`
 * `cohere.embed-multilingual-v3`
 
-Supported parameters (to be passed in `create` method) are:
+Supported paramters (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 |
@@ -498,10 +189,6 @@ Supported parameters (to be passed in `create` method) are:
 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):
@@ -535,13 +222,12 @@ This embedding function supports ingesting images as both bytes and urls. You ca
 !!! 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()
+registry = EmbeddingFunctionRegistry.get_instance()
+func = registry.get("open-clip").create()
 
 class Images(LanceModel):
     label: str
@@ -563,7 +249,7 @@ uris = [
 # get each uri as bytes
 image_bytes = [requests.get(uri).content for uri in uris]
 table.add(
-    pd.DataFrame({"label": labels, "image_uri": uris, "image_bytes": image_bytes})
+    [{"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
@@ -602,121 +288,4 @@ 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).
-
-### Jina Embeddings
-Jina embeddings can also be used to embed both text and image data, only some of the models support image data and you can check the list
-under [https://jina.ai/embeddings/](https://jina.ai/embeddings/)
-
-Supported parameters (to be passed in `create` method) are:
-
-| Parameter | Type | Default Value | Description |
-|---|---|---|---|
-| `name` | `str` | `"jina-clip-v1"` | The model ID of the jina model to use |
-
-Usage Example:
-
-```python
-    import os
-    import requests
-    import lancedb
-    from lancedb.pydantic import LanceModel, Vector
-    from lancedb.embeddings import get_registry
-    import pandas as pd
-
-    os.environ['JINA_API_KEY'] = 'jina_*'
-
-    db = lancedb.connect("~/.lancedb")
-    func = get_registry().get("jina").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(
-      pd.DataFrame({"label": labels, "image_uri": uris, "image_bytes": image_bytes})
-    )
-```

docs/src/embeddings/embedding_functions.md

@@ -2,9 +2,6 @@ Representing multi-modal data as vector embeddings is becoming a standard practi
 
 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.
 
-!!! Note "LanceDB cloud doesn't support embedding functions yet"
-    LanceDB Cloud does not support embedding functions yet. You need to generate embeddings before ingesting into the table or querying.
-
 !!! 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 
@@ -29,32 +26,17 @@ For this purpose, LanceDB introduces an **embedding functions API**, that allow
     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!
 
-=== "TypeScript"
+=== "JavaScript""
     In the TypeScript SDK, the choices are more limited. For now, only the OpenAI
     embedding function is available.
 
     ```javascript
-    import * as lancedb from '@lancedb/lancedb'
+    const lancedb = require("vectordb");
-    import { getRegistry } from '@lancedb/lancedb/embeddings'
 
     // You need to provide an OpenAI API key
     const apiKey = "sk-..."
     // The embedding function will create embeddings for the 'text' column
-    const func = getRegistry().get("openai").create({apiKey})
+    const embedding = new lancedb.OpenAIEmbeddingFunction('text', apiKey)
-    ```
-=== "Rust"
-    In the Rust SDK, the choices are more limited. For now, only the OpenAI
-    embedding function is available. But unlike the Python and TypeScript SDKs, you need manually register the OpenAI embedding function.
-
-    ```toml
-    // Make sure to include the `openai` feature
-    [dependencies]
-    lancedb = {version = "*", features = ["openai"]}
-    ```
-
-    ```rust
-    --8<-- "rust/lancedb/examples/openai.rs:imports"
-    --8<-- "rust/lancedb/examples/openai.rs:openai_embeddings"
     ```
 
 ## 2. Define the data model or schema
@@ -64,13 +46,13 @@ For this purpose, LanceDB introduces an **embedding functions API**, that allow
 
     ```python
     class Pets(LanceModel):
-        vector: Vector(clip.ndims()) = clip.VectorField()
+        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`.
 
-=== "TypeScript"
+=== "JavaScript"
 
     For the TypeScript SDK, a schema can be inferred from input data, or an explicit
     Arrow schema can be provided.
@@ -89,26 +71,17 @@ the embeddings at all:
     table.add([{"image_uri": u} for u in uris])
     ```
 
-=== "TypeScript"
+=== "JavaScript"
 
-    === "@lancedb/lancedb"
+    ```javascript
+    const db = await lancedb.connect("data/sample-lancedb");
+    const data = [
+    { text: "pepperoni"},
+    { text: "pineapple"}
+    ]
 
-        ```ts
+    const table = await db.createTable("vectors", data, embedding)
-        --8<-- "nodejs/examples/embedding.ts:imports"
+    ```
-        --8<-- "nodejs/examples/embedding.ts:embedding_function"
-        ```
-
-    === "vectordb (deprecated)"
-
-        ```ts
-        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
@@ -121,8 +94,8 @@ need to worry about it when you query the table:
     ```python
     results = (
         table.search("dog")
-            .limit(10)
+        .limit(10)
-            .to_pandas()
+        .to_pandas()
     )
     ```
 
@@ -133,31 +106,21 @@ need to worry about it when you query the table:
     query_image = Image.open(p)
     results = (
         table.search(query_image)
-            .limit(10)
+        .limit(10)
-            .to_pandas()
+        .to_pandas()
     )
     ```
 
     Both of the above snippet returns a pandas DataFrame with the 10 closest vectors to the query.
 
-=== "TypeScript"
+=== "JavaScript"
 
-    === "@lancedb/lancedb"
+    ```javascript
-
+    const results = await table
-        ```ts
+    .search("What's the best pizza topping?")
-        const results = await table.search("What's the best pizza topping?")
+    .limit(10)
-            .limit(10)
+    .execute()
-            .toArray()
+    ```    
-        ```
-
-    === "vectordb (deprecated)
-
-        ```ts
-        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.
 
@@ -186,7 +149,7 @@ You can also use the integration for adding utility operations in the schema. Fo
 
 ```python
 class Pets(LanceModel):
-    vector: Vector(clip.ndims()) = clip.VectorField()
+    vector: Vector(clip.ndims) = clip.VectorField()
     image_uri: str = clip.SourceField()
 
     @property

docs/src/embeddings/index.md

@@ -7,128 +7,8 @@ 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. You can define your own [custom embedding function](./custom_embedding_function.md)
+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"
-
-    ```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)
-    ```
-
-=== "TypeScript"
-
-    ```typescript
-    --8<--- "nodejs/examples/embedding.ts:imports"
-    --8<--- "nodejs/examples/embedding.ts:openai_embeddings"
-    ```
-
-=== "Rust"
-
-    ```rust
-    --8<--- "rust/lancedb/examples/openai.rs:imports"
-    --8<--- "rust/lancedb/examples/openai.rs:openai_embeddings"
-    ```
-
-### 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"
-    ```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)
-    ```
-
-=== "TypeScript"
-
-    Coming Soon!
-
-=== "Rust"
-
-    Coming Soon!
-
-### Jina Embeddings
-
-LanceDB registers the JinaAI embeddings function in the registry as `jina`. You can pass any supported model name to the `create`. By default it uses `"jina-clip-v1"`.
-`jina-clip-v1` can handle both text and images and other models only support `text`.
-
-You need to pass `JINA_API_KEY` in the environment variable or pass it as `api_key` to `create` method.
-
-```python
-import os
-import lancedb
-from lancedb.pydantic import LanceModel, Vector
-from lancedb.embeddings import get_registry
-os.environ['JINA_API_KEY'] = "jina_*"
-
-db = lancedb.connect("/tmp/db")
-func = get_registry().get("jina").create(name="jina-clip-v1")
-
-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)
-```

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

@@ -43,7 +43,7 @@ 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
+pip install tantivy@git+https://github.com/quickwit-oss/tantivy-py#164adc87e1a033117001cf70e38c82a53014d985
 ```
 
 Create a new Python file and add the following code:

docs/src/examples/index.md

@@ -2,11 +2,10 @@
 
 ## Recipes and example code
 
-LanceDB provides language APIs, allowing you to embed a database in your language of choice.
+LanceDB provides language APIs, allowing you to embed a database in your language of choice. We currently provide Python and Javascript APIs, with the Rust API and examples actively being worked on and will be available soon.
 
 * 🐍 [Python](examples_python.md) examples
-* 👾 [JavaScript](examples_js.md) examples
+* 👾 [JavaScript](exampled_js.md) examples
-* 🦀 Rust examples (coming soon)
 
 ## Applications powered by LanceDB
 

docs/src/extra_js/init_ask_ai_widget.js

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

docs/src/faq.md

@@ -16,7 +16,7 @@ As we mention in our talk titled “[Lance, a modern columnar data format](https
 
 ### Why build in Rust? 🦀
 
-We believe that the Rust ecosystem has attained mainstream maturity and that Rust will form the underpinnings of large parts of the data and ML landscape in a few years. Performance, latency and reliability are paramount to a vector DB, and building in Rust allows us to iterate and release updates more rapidly due to Rust’s safety guarantees. Both Lance (the data format) and LanceDB (the database) are written entirely in Rust. We also provide Python, JavaScript, and Rust client libraries to interact with the database.
+We believe that the Rust ecosystem has attained mainstream maturity and that Rust will form the underpinnings of large parts of the data and ML landscape in a few years. Performance, latency and reliability are paramount to a vector DB, and building in Rust allows us to iterate and release updates more rapidly due to Rust’s safety guarantees. Both Lance (the data format) and LanceDB (the database) are written entirely in Rust. We also provide Python and JavaScript client libraries to interact with the database. Our Rust API is a little rough around the edges right now, but is fast becoming on par with the Python and JS APIs.
 
 ### What is the difference between LanceDB OSS and LanceDB Cloud?
 
@@ -40,11 +40,11 @@ LanceDB and its underlying data format, Lance, are built to scale to really larg
 
 No. LanceDB is blazing fast (due to its disk-based index) for even brute force kNN search, within reason. In our benchmarks, computing 100K pairs of 1000-dimension vectors takes less than 20ms. For small datasets of ~100K records or applications that can accept ~100ms latency, an ANN index is usually not necessary.
 
-For large-scale (>1M) or higher dimension vectors, it is beneficial to create an ANN index. See the [ANN indexes](ann_indexes.md) section for more details.
+For large-scale (>1M) or higher dimension vectors, it is beneficial to create an ANN index.
 
 ### Does LanceDB support full-text search?
 
-Yes, LanceDB supports full-text search (FTS) via [Tantivy](https://github.com/quickwit-oss/tantivy). Our current FTS integration is Python-only, and our goal is to push it down to the Rust level in future versions to enable much more powerful search capabilities available to our Python, JavaScript and Rust clients.  Follow along in the [Github issue](https://github.com/lancedb/lance/issues/1195)
+Yes, LanceDB supports full-text search (FTS) via [Tantivy](https://github.com/quickwit-oss/tantivy). Our current FTS integration is Python-only, and our goal is to push it down to the Rust level in future versions to enable much more powerful search capabilities available to our Python, JavaScript and Rust clients.
 
 ### How can I speed up data inserts?
 

docs/src/fts.md

@@ -1,7 +1,8 @@
 # Full-text search
 
-LanceDB provides support for full-text search via [Tantivy](https://github.com/quickwit-oss/tantivy) (currently Python only), allowing you to incorporate keyword-based search (based on BM25) in your retrieval solutions. Our goal is to push the FTS integration down to the Rust level in the future, so that it's available for Rust and JavaScript users as well.  Follow along at [this Github issue](https://github.com/lancedb/lance/issues/1195)
+LanceDB provides support for full-text search via [Tantivy](https://github.com/quickwit-oss/tantivy) (currently Python only), allowing you to incorporate keyword-based search (based on BM25) in your retrieval solutions. Our goal is to push the FTS integration down to the Rust level in the future, so that it's available for JavaScript users as well.
 
+A hybrid search solution combining vector and full-text search is also on the way.
 
 ## Installation
 
@@ -54,16 +55,6 @@ This returns the result as a list of dictionaries as follows.
 !!! note
     LanceDB automatically searches on the existing FTS index if the input to the search is of type `str`. If you provide a vector as input, LanceDB will search the ANN index instead.
 
-## Tokenization
-By default the text is tokenized by splitting on punctuation and whitespaces and then removing tokens that are longer than 40 chars. For more language specific tokenization then provide the argument tokenizer_name with the 2 letter language code followed by "_stem". So for english it would be "en_stem".
-
-```python
-table.create_fts_index("text", tokenizer_name="en_stem")
-```
-
-The following [languages](https://docs.rs/tantivy/latest/tantivy/tokenizer/enum.Language.html) are currently supported.
-
-
 ## Index multiple columns
 
 If you have multiple string columns to index, there's no need to combine them manually -- simply pass them all as a list to `create_fts_index`:
@@ -84,70 +75,20 @@ applied on top of the full text search results. This can be invoked via the fami
 table.search("puppy").limit(10).where("meta='foo'").to_list()
 ```
 
-## Sorting
+## Syntax
 
-You can pre-sort the documents by specifying `ordering_field_names` when
+For full-text search you can perform either a phrase query like "the old man and the sea", 
-creating the full-text search index. Once pre-sorted, you can then specify
+or a structured search query like "(Old AND Man) AND Sea".
-`ordering_field_name` while searching to return results sorted by the given
+Double quotes are used to disambiguate.
-field. For example, 
 
-```
+For example: 
-table.create_fts_index(["text_field"], ordering_field_names=["sort_by_field"])
 
-(table.search("terms", ordering_field_name="sort_by_field")
+If you intended "they could have been dogs OR cats" as a phrase query, this actually
- .limit(20)
+raises a syntax error since `OR` is a recognized operator. If you make `or` lower case,
- .to_list())
+this avoids the syntax error. However, it is cumbersome to have to remember what will
-```
+conflict with the query syntax. Instead, if you search using 
-
+`table.search('"they could have been dogs OR cats"')`, then the syntax checker avoids
-!!! note
+checking inside the quotes.
-    If you wish to specify an ordering field at query time, you must also
-    have specified it during indexing time. Otherwise at query time, an
-    error will be raised that looks like `ValueError: The field does not exist: xxx`
-
-!!! note
-    The fields to sort on must be of typed unsigned integer, or else you will see 
-    an error during indexing that looks like 
-    `TypeError: argument 'value': 'float' object cannot be interpreted as an integer`.
-
-!!! note
-    You can specify multiple fields for ordering at indexing time.
-    But at query time only one ordering field is supported.
-
-
-## Phrase queries vs. terms queries
-
-For full-text search you can specify either a **phrase** query like `"the old man and the sea"`,
-or a **terms** search query like `"(Old AND Man) AND Sea"`. For more details on the terms
-query syntax, see Tantivy's [query parser rules](https://docs.rs/tantivy/latest/tantivy/query/struct.QueryParser.html).
-
-!!! tip "Note"
-    The query parser will raise an exception on queries that are ambiguous. For example, in the query `they could have been dogs OR cats`, `OR` is capitalized so it's considered a keyword query operator. But it's ambiguous how the left part should be treated. So if you submit this search query as is, you'll get `Syntax Error: they could have been dogs OR cats`.
-
-    ```py
-    # This raises a syntax error
-    table.search("they could have been dogs OR cats")
-    ```
-
-    On the other hand, lowercasing `OR` to `or` will work, because there are no capitalized logical operators and
-    the query is treated as a phrase query.
-
-    ```py
-    # This works!
-    table.search("they could have been dogs or cats")
-    ```
-
-It can be cumbersome to have to remember what will cause a syntax error depending on the type of
-query you want to perform. To make this simpler, when you want to perform a phrase query, you can
-enforce it in one of two ways:
-
-1. Place the double-quoted query inside single quotes. For example, `table.search('"they could have been dogs OR cats"')` is treated as
-a phrase query.
-2. Explicitly declare the `phrase_query()` method. This is useful when you have a phrase query that
-itself contains double quotes. For example, `table.search('the cats OR dogs were not really "pets" at all').phrase_query()`
-is treated as a phrase query.
-
-In general, a query that's declared as a phrase query will be wrapped in double quotes during parsing, with nested
-double quotes replaced by single quotes.
 
 
 ## Configurations
@@ -171,3 +112,4 @@ table.create_fts_index(["text1", "text2"], writer_heap_size=heap, replace=True)
 2. We currently only support local filesystem paths for the FTS index. 
    This is a tantivy limitation. We've implemented an object store plugin
    but there's no way in tantivy-py to specify to use it.
+

docs/src/guides/storage.md

@@ -32,232 +32,41 @@ LanceDB OSS supports object stores such as AWS S3 (and compatible stores), Azure
     db = lancedb.connect("az://bucket/path")
     ```
 
-=== "TypeScript"
+=== "JavaScript"
 
-    === "@lancedb/lancedb"
+    AWS S3:
 
-        AWS S3:
+    ```javascript
-
+    const lancedb = require("lancedb");
-        ```ts
+    const db = await lancedb.connect("s3://bucket/path");
-        import * as lancedb from "@lancedb/lancedb";
-        const db = await lancedb.connect("s3://bucket/path");
-        ```
-
-        Google Cloud Storage:
-
-        ```ts
-        import * as lancedb from "@lancedb/lancedb";
-        const db = await lancedb.connect("gs://bucket/path");
-        ```
-
-        Azure Blob Storage:
-
-        ```ts
-        import * as lancedb from "@lancedb/lancedb";
-        const db = await lancedb.connect("az://bucket/path");
-        ```
-
-
-    === "vectordb (deprecated)"
-
-        AWS S3:
-
-        ```ts
-        const lancedb = require("lancedb");
-        const db = await lancedb.connect("s3://bucket/path");
-        ```
-
-        Google Cloud Storage:
-
-        ```ts
-        const lancedb = require("lancedb");
-        const db = await lancedb.connect("gs://bucket/path");
-        ```
-
-        Azure Blob Storage:
-
-        ```ts
-        const lancedb = require("lancedb");
-        const db = await lancedb.connect("az://bucket/path");
-        ```
-
-In most cases, when running in the respective cloud and permissions are set up correctly, no additional configuration is required. When running outside of the respective cloud, authentication credentials must be provided. Credentials and other configuration options can be set in two ways: first, by setting environment variables. And second, by passing a `storage_options` object to the `connect` function. For example, to increase the request timeout to 60 seconds, you can set the `TIMEOUT` environment variable to `60s`:
-
-```bash
-export TIMEOUT=60s
-```
-
-!!! note "`storage_options` availability"
-
-    The `storage_options` parameter is only available in Python *async* API and JavaScript API.
-    It is not yet supported in the Python synchronous API.
-
-If you only want this to apply to one particular connection, you can pass the `storage_options` argument when opening the connection:
-
-=== "Python"
-
-    ```python
-    import lancedb
-    db = await lancedb.connect_async(
-        "s3://bucket/path",
-        storage_options={"timeout": "60s"}
-    )
     ```
 
-=== "TypeScript"
+    Google Cloud Storage:
 
-    === "@lancedb/lancedb"
+    ```javascript
-
+    const lancedb = require("lancedb");
-        ```ts
+    const db = await lancedb.connect("gs://bucket/path");
-        import * as lancedb from "@lancedb/lancedb";
-
-        const db = await lancedb.connect("s3://bucket/path", {
-            storageOptions: {timeout: "60s"}
-        });
-        ```
-
-    === "vectordb (deprecated)"
-
-        ```ts
-        const lancedb = require("lancedb");
-        const db = await lancedb.connect("s3://bucket/path", {
-            storageOptions: {timeout: "60s"}
-        });
-        ```
-
-Getting even more specific, you can set the `timeout` for only a particular table:
-
-=== "Python"
-
-    <!-- skip-test -->
-    ```python
-    import lancedb
-    db = await lancedb.connect_async("s3://bucket/path")
-    table = await db.create_table(
-        "table",
-        [{"a": 1, "b": 2}],
-        storage_options={"timeout": "60s"}
-    )
     ```
 
-=== "TypeScript"
+    Azure Blob Storage:
 
-    === "@lancedb/lancedb"
+    ```javascript
+    const lancedb = require("lancedb");
+    const db = await lancedb.connect("az://bucket/path");
+    ```
 
-        <!-- skip-test -->
+In most cases, when running in the respective cloud and permissions are set up correctly, no additional configuration is required. When running outside of the respective cloud, authentication credentials must be provided using environment variables. In general, these environment variables are the same as those used by the respective cloud SDKs. The sections below describe the environment variables that can be used to configure each object store.
-        ```ts
-        import * as lancedb from "@lancedb/lancedb";
-        const db = await lancedb.connect("s3://bucket/path");
-        const table = db.createTable(
-            "table",
-            [{ a: 1, b: 2}],
-            {storageOptions: {timeout: "60s"}}
-        );
-        ```
 
-    === "vectordb (deprecated)"
+LanceDB OSS uses the [object-store](https://docs.rs/object_store/latest/object_store/) Rust crate for object store access. There are general environment variables that can be used to configure the object store, such as the request timeout and proxy configuration. See the [object_store ClientConfigKey](https://docs.rs/object_store/latest/object_store/enum.ClientConfigKey.html) doc for available configuration options. The environment variables that can be set are the snake-cased versions of these variable names. For example, to set `ProxyUrl` use the environment variable `PROXY_URL`. (Don't let the Rust docs intimidate you! We link to them so you can see an up-to-date list of the available options.)
 
-        <!-- skip-test -->
-        ```ts
-        const lancedb = require("lancedb");
-        const db = await lancedb.connect("s3://bucket/path");
-        const table = db.createTable(
-            "table",
-            [{ a: 1, b: 2}],
-            {storageOptions: {timeout: "60s"}}
-        );
-        ```
-
-!!! info "Storage option casing"
-
-    The storage option keys are case-insensitive. So `connect_timeout` and `CONNECT_TIMEOUT` are the same setting. Usually lowercase is used in the `storage_options` argument and uppercase is used for environment variables. In the `lancedb` Node package, the keys can also be provided in `camelCase` capitalization. For example, `connectTimeout` is equivalent to `connect_timeout`.
-
-### General configuration
-
-There are several options that can be set for all object stores, mostly related to network client configuration.
-
-<!-- from here: https://docs.rs/object_store/latest/object_store/enum.ClientConfigKey.html -->
-
-| Key                        | Description                                                                                      |
-|----------------------------|--------------------------------------------------------------------------------------------------|
-| `allow_http`               | Allow non-TLS, i.e. non-HTTPS connections. Default: `False`.                                      |
-| `allow_invalid_certificates`| Skip certificate validation on HTTPS connections. Default: `False`.                               |
-| `connect_timeout`          | Timeout for only the connect phase of a Client. Default: `5s`.                                    |
-| `timeout`                  | Timeout for the entire request, from connection until the response body has finished. Default: `30s`. |
-| `user_agent`               | User agent string to use in requests.                                                             |
-| `proxy_url`                | URL of a proxy server to use for requests. Default: `None`.                                       |
-| `proxy_ca_certificate`     | PEM-formatted CA certificate for proxy connections.                                                |
-| `proxy_excludes`           | List of hosts that bypass the proxy. This is a comma-separated list of domains and IP masks. Any subdomain of the provided domain will be bypassed. For example, `example.com, 192.168.1.0/24` would bypass `https://api.example.com`, `https://www.example.com`, and any IP in the range `192.168.1.0/24`. |
 
 ### AWS S3
 
-To configure credentials for AWS S3, you can use the `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, and `AWS_SESSION_TOKEN` keys. Region can also be set, but it is not mandatory when using AWS.
+To configure credentials for AWS S3, you can use the `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, and `AWS_SESSION_TOKEN` environment variables.
-These can be set as environment variables or passed in the `storage_options` parameter:
-
-=== "Python"
-
-    ```python
-    import lancedb
-    db = await lancedb.connect_async(
-        "s3://bucket/path",
-        storage_options={
-            "aws_access_key_id": "my-access-key",
-            "aws_secret_access_key": "my-secret-key",
-            "aws_session_token": "my-session-token",
-        }
-    )
-    ```
-
-=== "TypeScript"
-
-    === "@lancedb/lancedb"
-
-        ```ts
-        import * as lancedb from "@lancedb/lancedb";
-        const db = await lancedb.connect(
-            "s3://bucket/path",
-            {
-                storageOptions: {
-                    awsAccessKeyId: "my-access-key",
-                    awsSecretAccessKey: "my-secret-key",
-                    awsSessionToken: "my-session-token",
-                }
-            }
-        );
-        ```
-
-    === "vectordb (deprecated)"
-
-        ```ts
-        const lancedb = require("lancedb");
-        const db = await lancedb.connect(
-            "s3://bucket/path",
-            {
-                storageOptions: {
-                    awsAccessKeyId: "my-access-key",
-                    awsSecretAccessKey: "my-secret-key",
-                    awsSessionToken: "my-session-token",
-                }
-            }
-        );
-        ```
 
 Alternatively, if you are using AWS SSO, you can use the `AWS_PROFILE` and `AWS_DEFAULT_REGION` environment variables.
 
-The following keys can be used as both environment variables or keys in the `storage_options` parameter:
+You can see a full list of environment variables [here](https://docs.rs/object_store/latest/object_store/aws/struct.AmazonS3Builder.html#method.from_env).
-
-| Key                                | Description                                                                                          |
-|------------------------------------|------------------------------------------------------------------------------------------------------|
-| `aws_region` / `region`             | The AWS region the bucket is in. This can be automatically detected when using AWS S3, but must be specified for S3-compatible stores. |
-| `aws_access_key_id` / `access_key_id` | The AWS access key ID to use.                                                                       |
-| `aws_secret_access_key` / `secret_access_key` | The AWS secret access key to use.                                                               |
-| `aws_session_token` / `session_token` | The AWS session token to use.                                                                     |
-| `aws_endpoint` / `endpoint`         | The endpoint to use for S3-compatible stores.                                                       |
-| `aws_virtual_hosted_style_request` / `virtual_hosted_style_request` | Whether to use virtual hosted-style requests, where the bucket name is part of the endpoint. Meant to be used with `aws_endpoint`. Default: `False`. |
-| `aws_s3_express` / `s3_express`     | Whether to use S3 Express One Zone endpoints. Default: `False`. See more details below.             |
-| `aws_server_side_encryption`        | The server-side encryption algorithm to use. Must be one of `"AES256"`, `"aws:kms"`, or `"aws:kms:dsse"`. Default: `None`. |
-| `aws_sse_kms_key_id`                | The KMS key ID to use for server-side encryption. If set, `aws_server_side_encryption` must be `"aws:kms"` or `"aws:kms:dsse"`. |
-| `aws_sse_bucket_key_enabled`        | Whether to use bucket keys for server-side encryption.                                               |
 
 !!! tip "Automatic cleanup for failed writes"
 
@@ -335,349 +144,24 @@ For **read-only access**, LanceDB will need a policy such as:
 }
 ```
 
-#### DynamoDB Commit Store for concurrent writes
-
-By default, S3 does not support concurrent writes. Having two or more processes
-writing to the same table at the same time can lead to data corruption. This is
-because S3, unlike other object stores, does not have any atomic put or copy
-operation.
-
-To enable concurrent writes, you can configure LanceDB to use a DynamoDB table
-as a commit store. This table will be used to coordinate writes between
-different processes. To enable this feature, you must modify your connection
-URI to use the `s3+ddb` scheme and add a query parameter `ddbTableName` with the
-name of the table to use.
-
-=== "Python"
-
-    ```python
-    import lancedb
-    db = await lancedb.connect_async(
-        "s3+ddb://bucket/path?ddbTableName=my-dynamodb-table",
-    )
-    ```
-
-=== "JavaScript"
-
-    ```javascript
-    const lancedb = require("lancedb");
-
-    const db = await lancedb.connect(
-        "s3+ddb://bucket/path?ddbTableName=my-dynamodb-table",
-    );
-    ```
-
-The DynamoDB table must be created with the following schema:
-
-- Hash key: `base_uri` (string)
-- Range key: `version` (number)
-
-You can create this programmatically with:
-
-=== "Python"
-
-    <!-- skip-test -->
-    ```python
-    import boto3
-
-    dynamodb = boto3.client("dynamodb")
-    table = dynamodb.create_table(
-        TableName=table_name,
-        KeySchema=[
-            {"AttributeName": "base_uri", "KeyType": "HASH"},
-            {"AttributeName": "version", "KeyType": "RANGE"},
-        ],
-        AttributeDefinitions=[
-            {"AttributeName": "base_uri", "AttributeType": "S"},
-            {"AttributeName": "version", "AttributeType": "N"},
-        ],
-        ProvisionedThroughput={"ReadCapacityUnits": 1, "WriteCapacityUnits": 1},
-    )
-    ```
-
-=== "JavaScript"
-
-    <!-- skip-test -->
-    ```javascript
-    import {
-      CreateTableCommand,
-      DynamoDBClient,
-    } from "@aws-sdk/client-dynamodb";
-
-    const dynamodb = new DynamoDBClient({
-      region: CONFIG.awsRegion,
-      credentials: {
-        accessKeyId: CONFIG.awsAccessKeyId,
-        secretAccessKey: CONFIG.awsSecretAccessKey,
-      },
-      endpoint: CONFIG.awsEndpoint,
-    });
-    const command = new CreateTableCommand({
-      TableName: table_name,
-      AttributeDefinitions: [
-        {
-          AttributeName: "base_uri",
-          AttributeType: "S",
-        },
-        {
-          AttributeName: "version",
-          AttributeType: "N",
-        },
-      ],
-      KeySchema: [
-        { AttributeName: "base_uri", KeyType: "HASH" },
-        { AttributeName: "version", KeyType: "RANGE" },
-      ],
-      ProvisionedThroughput: {
-        ReadCapacityUnits: 1,
-        WriteCapacityUnits: 1,
-      },
-    });
-    await client.send(command);
-    ```
-
-
 #### S3-compatible stores
 
-LanceDB can also connect to S3-compatible stores, such as MinIO. To do so, you must specify both region and endpoint:
+LanceDB can also connect to S3-compatible stores, such as MinIO. To do so, you must specify two environment variables: `AWS_ENDPOINT` and `AWS_DEFAULT_REGION`. `AWS_ENDPOINT` should be the URL of the S3-compatible store, and `AWS_DEFAULT_REGION` should be the region to use.
 
-=== "Python"
+<!-- TODO: we should also document the use of S3 Express once we fully support it -->
-
-    ```python
-    import lancedb
-    db = await lancedb.connect_async(
-        "s3://bucket/path",
-        storage_options={
-            "region": "us-east-1",
-            "endpoint": "http://minio:9000",
-        }
-    )
-    ```
-
-=== "TypeScript"
-
-    === "@lancedb/lancedb"
-
-        ```ts
-        import * as lancedb from "@lancedb/lancedb";
-        const db = await lancedb.connect(
-            "s3://bucket/path",
-            {
-                storageOptions: {
-                    region: "us-east-1",
-                    endpoint: "http://minio:9000",
-                }
-            }
-        );
-        ```
-
-    === "vectordb (deprecated)"
-
-        ```ts
-        const lancedb = require("lancedb");
-        const db = await lancedb.connect(
-            "s3://bucket/path",
-            {
-                storageOptions: {
-                    region: "us-east-1",
-                    endpoint: "http://minio:9000",
-                }
-            }
-        );
-        ```
-
-This can also be done with the ``AWS_ENDPOINT`` and ``AWS_DEFAULT_REGION`` environment variables.
-
-!!! tip "Local servers"
-
-    For local development, the server often has a `http` endpoint rather than a
-    secure `https` endpoint. In this case, you must also set the `ALLOW_HTTP`
-    environment variable to `true` to allow non-TLS connections, or pass the
-    storage option `allow_http` as `true`. If you do not do this, you will get
-    an error like `URL scheme is not allowed`.
-
-#### S3 Express
-
-LanceDB supports [S3 Express One Zone](https://aws.amazon.com/s3/storage-classes/express-one-zone/) endpoints, but requires additional configuration. Also, S3 Express endpoints only support connecting from an EC2 instance within the same region.
-
-To configure LanceDB to use an S3 Express endpoint, you must set the storage option `s3_express`. The bucket name in your table URI should **include the suffix**.
-
-=== "Python"
-
-    ```python
-    import lancedb
-    db = await lancedb.connect_async(
-        "s3://my-bucket--use1-az4--x-s3/path",
-        storage_options={
-            "region": "us-east-1",
-            "s3_express": "true",
-        }
-    )
-    ```
-
-=== "TypeScript"
-
-    === "@lancedb/lancedb"
-
-        ```ts
-        import * as lancedb from "@lancedb/lancedb";
-        const db = await lancedb.connect(
-            "s3://my-bucket--use1-az4--x-s3/path",
-            {
-                storageOptions: {
-                    region: "us-east-1",
-                    s3Express: "true",
-                }
-            }
-        );
-        ```
-
-    === "vectordb (deprecated)"
-
-        ```ts
-        const lancedb = require("lancedb");
-        const db = await lancedb.connect(
-            "s3://my-bucket--use1-az4--x-s3/path",
-            {
-                storageOptions: {
-                    region: "us-east-1",
-                    s3Express: "true",
-                }
-            }
-        );
-        ```
 
 ### Google Cloud Storage
 
-GCS credentials are configured by setting the `GOOGLE_SERVICE_ACCOUNT` environment variable to the path of a JSON file containing the service account credentials. Alternatively, you can pass the path to the JSON file in the `storage_options`:
+GCS credentials are configured by setting the `GOOGLE_SERVICE_ACCOUNT` environment variable to the path of a JSON file containing the service account credentials. There are several aliases for this environment variable, documented [here](https://docs.rs/object_store/latest/object_store/gcp/struct.GoogleCloudStorageBuilder.html#method.from_env).
 
-=== "Python"
-
-    <!-- skip-test -->
-    ```python
-    import lancedb
-    db = await lancedb.connect_async(
-        "gs://my-bucket/my-database",
-        storage_options={
-            "service_account": "path/to/service-account.json",
-        }
-    )
-    ```
-
-=== "TypeScript"
-
-    === "@lancedb/lancedb"
-
-        ```ts
-        import * as lancedb from "@lancedb/lancedb";
-        const db = await lancedb.connect(
-            "gs://my-bucket/my-database",
-            {
-                storageOptions: {
-                    serviceAccount: "path/to/service-account.json",
-                }
-            }
-        );
-        ```
-
-    === "vectordb (deprecated)"
-
-        ```ts
-        const lancedb = require("lancedb");
-        const db = await lancedb.connect(
-            "gs://my-bucket/my-database",
-            {
-                storageOptions: {
-                    serviceAccount: "path/to/service-account.json",
-                }
-            }
-        );
-        ```
 
 !!! info "HTTP/2 support"
 
     By default, GCS uses HTTP/1 for communication, as opposed to HTTP/2. This improves maximum throughput significantly. However, if you wish to use HTTP/2 for some reason, you can set the environment variable `HTTP1_ONLY` to `false`.
 
-The following keys can be used as both environment variables or keys in the `storage_options` parameter:
-<!-- source: https://docs.rs/object_store/latest/object_store/gcp/enum.GoogleConfigKey.html -->
-
-| Key                                   | Description                                  |
-|---------------------------------------|----------------------------------------------|
-| ``google_service_account`` / `service_account` | Path to the service account JSON file.       |
-| ``google_service_account_key``        | The serialized service account key.          |
-| ``google_application_credentials``    | Path to the application credentials.         |
-
 ### Azure Blob Storage
 
-Azure Blob Storage credentials can be configured by setting the `AZURE_STORAGE_ACCOUNT_NAME`and `AZURE_STORAGE_ACCOUNT_KEY` environment variables. Alternatively, you can pass the account name and key in the `storage_options` parameter:
+Azure Blob Storage credentials can be configured by setting the `AZURE_STORAGE_ACCOUNT_NAME` and ``AZURE_STORAGE_ACCOUNT_KEY`` environment variables. The full list of environment variables that can be set are documented [here](https://docs.rs/object_store/latest/object_store/azure/struct.MicrosoftAzureBuilder.html#method.from_env).
 
-=== "Python"
-
-    <!-- skip-test -->
-    ```python
-    import lancedb
-    db = await lancedb.connect_async(
-        "az://my-container/my-database",
-        storage_options={
-            account_name: "some-account",
-            account_key: "some-key",
-        }
-    )
-    ```
-
-=== "TypeScript"
-
-    === "@lancedb/lancedb"
-
-        ```ts
-        import * as lancedb from "@lancedb/lancedb";
-        const db = await lancedb.connect(
-            "az://my-container/my-database",
-            {
-                storageOptions: {
-                    accountName: "some-account",
-                    accountKey: "some-key",
-                }
-            }
-        );
-        ```
-
-    === "vectordb (deprecated)"
-
-        ```ts
-        const lancedb = require("lancedb");
-        const db = await lancedb.connect(
-            "az://my-container/my-database",
-            {
-                storageOptions: {
-                    accountName: "some-account",
-                    accountKey: "some-key",
-                }
-            }
-        );
-        ```
-
-These keys can be used as both environment variables or keys in the `storage_options` parameter:
-
-<!-- source: https://docs.rs/object_store/latest/object_store/azure/enum.AzureConfigKey.html -->
-
-| Key                                   | Description                                                                                      |
-|---------------------------------------|--------------------------------------------------------------------------------------------------|
-| ``azure_storage_account_name``        | The name of the azure storage account.                                                           |
-| ``azure_storage_account_key``         | The serialized service account key.                                                              |
-| ``azure_client_id``                   | Service principal client id for authorizing requests.                                            |
-| ``azure_client_secret``               | Service principal client secret for authorizing requests.                                        |
-| ``azure_tenant_id``                   | Tenant id used in oauth flows.                                                                   |
-| ``azure_storage_sas_key``             | Shared access signature. The signature is expected to be percent-encoded, much like they are provided in the azure storage explorer or azure portal. |
-| ``azure_storage_token``               | Bearer token.                                                                                    |
-| ``azure_storage_use_emulator``        | Use object store with azurite storage emulator.                                                  |
-| ``azure_endpoint``                    | Override the endpoint used to communicate with blob storage.                                      |
-| ``azure_use_fabric_endpoint``         | Use object store with url scheme account.dfs.fabric.microsoft.com.                               |
-| ``azure_msi_endpoint``                | Endpoint to request a imds managed identity token.                                               |
-| ``azure_object_id``                   | Object id for use with managed identity authentication.                                          |
-| ``azure_msi_resource_id``             | Msi resource id for use with managed identity authentication.                                    |
-| ``azure_federated_token_file``        | File containing token for Azure AD workload identity federation.                                 |
-| ``azure_use_azure_cli``               | Use azure cli for acquiring access token.                                                        |
-| ``azure_disable_tagging``             | Disables tagging objects. This can be desirable if not supported by the backing store.           |
 
 <!-- TODO: demonstrate how to configure networked file systems for optimal performance -->

docs/src/guides/tables.md

@@ -8,40 +8,27 @@ This guide will show how to create tables, insert data into them, and update the
 
 ## Creating a LanceDB Table
 
-Initialize a LanceDB connection and create a table
-
 === "Python"
+    Initialize a LanceDB connection and create a table using one of the many methods listed below.
 
     ```python
     import lancedb
     db = lancedb.connect("./.lancedb")
     ```
 
+=== "Javascript"
+
+    Initialize a VectorDB connection and create a table using one of the many methods listed below.
+
+    ```javascript
+    const lancedb = require("vectordb");
+
+    const uri = "data/sample-lancedb";
+    const db = await lancedb.connect(uri);
+    ```
+
     LanceDB allows ingesting data from various sources - `dict`, `list[dict]`, `pd.DataFrame`, `pa.Table` or a `Iterator[pa.RecordBatch]`. Let's take a look at some of the these.
 
-=== "Typescript[^1]"
-
-    === "@lancedb/lancedb"
-
-        ```typescript
-        import * as lancedb from "@lancedb/lancedb";
-        import * as arrow from "apache-arrow";
-
-        const uri = "data/sample-lancedb";
-        const db = await lancedb.connect(uri);
-        ```
-
-    === "vectordb (deprecated)"
-
-        ```typescript
-        const lancedb = require("vectordb");
-
-        const uri = "data/sample-lancedb";
-        const db = await lancedb.connect(uri);
-        ```
-
-
-
 ### From list of tuples or dictionaries
 
 === "Python"
@@ -58,7 +45,6 @@ Initialize a LanceDB connection and create a table
 
     db["my_table"].head()
     ```
-
     !!! info "Note"
         If the table already exists, LanceDB will raise an error by default. 
 
@@ -66,120 +52,90 @@ Initialize a LanceDB connection and create a table
         and the table exists, then it simply opens the existing table. The data you
         passed in will NOT be appended to the table in that case.
 
-    ```python
+        ```python
-    db.create_table("name", data, exist_ok=True)
+        db.create_table("name", data, exist_ok=True)
-    ```
-
-    Sometimes you want to make sure that you start fresh. If you want to
-    overwrite the table, you can pass in mode="overwrite" to the createTable function.
-
-    ```python
-    db.create_table("name", data, mode="overwrite")
-    ```
-
-=== "Typescript[^1]"
-    You can create a LanceDB table in JavaScript using an array of records as follows.
-
-    === "@lancedb/lancedb"
-
-
-        ```ts
-        --8<-- "nodejs/examples/basic.ts:create_table"
-        ```
-
-        This will infer the schema from the provided data. If you want to explicitly provide a schema, you can use `apache-arrow` to declare a schema
-
-        ```ts
-        --8<-- "nodejs/examples/basic.ts:create_table_with_schema"
-        ```
-
-        !!! info "Note"
-            `createTable` supports an optional `existsOk` parameter. When set to true
-            and the table exists, then it simply opens the existing table. The data you
-            passed in will NOT be appended to the table in that case.
-
-
-        ```ts
-        --8<-- "nodejs/examples/basic.ts:create_table_exists_ok"
         ```
         
         Sometimes you want to make sure that you start fresh. If you want to 
-        overwrite the table, you can pass in mode: "overwrite" to the createTable function.
+        overwrite the table, you can pass in mode="overwrite" to the createTable function.
 
-        ```ts
+        ```python
-        --8<-- "nodejs/examples/basic.ts:create_table_overwrite"
+        db.create_table("name", data, mode="overwrite")
         ```
 
-    === "vectordb (deprecated)"
+=== "Javascript"
+    You can create a LanceDB table in JavaScript using an array of JSON records as follows.
 
-        ```ts
+    ```javascript
-        --8<-- "docs/src/basic_legacy.ts:create_table"
+    const tb = await db.createTable("my_table", [{
-        ```
+        "vector": [3.1, 4.1],
+        "item": "foo",
+        "price": 10.0
+    }, {
+        "vector": [5.9, 26.5],
+        "item": "bar",
+        "price": 20.0
+    }]);
+    ```
+    !!! info "Note"
+    If the table already exists, LanceDB will raise an error by default. If you want to overwrite the table, you need to specify the `WriteMode` in the createTable function.
 
-        !!! warning
+    ```javascript
-            `existsOk` option is not supported in `vectordb`
+    const table = await con.createTable(tableName, data, { writeMode: WriteMode.Overwrite })
+    ```
 
-        Sometimes you want to make sure that you start fresh. If you want to
+    ### From a Pandas DataFrame
-        overwrite the table, you can pass in mode: "overwrite" to the createTable function.
 
-        ```ts
+    ```python
-        const table = await con.createTable(tableName, data, { writeMode: WriteMode.Overwrite })
+    import pandas as pd
-        ```
 
-### From a Pandas DataFrame
+    data = pd.DataFrame({
+        "vector": [[1.1, 1.2, 1.3, 1.4], [0.2, 1.8, 0.4, 3.6]],
+        "lat": [45.5, 40.1],
+        "long": [-122.7, -74.1]
+    })
 
-```python
+    db.create_table("my_table", data)
-import pandas as pd
 
-data = pd.DataFrame({
+    db["my_table"].head()
-    "vector": [[1.1, 1.2, 1.3, 1.4], [0.2, 1.8, 0.4, 3.6]],
+    ```
-    "lat": [45.5, 40.1],
+    !!! info "Note"
-    "long": [-122.7, -74.1]
-})
-
-db.create_table("my_table", data)
-
-db["my_table"].head()
-```
-
-!!! info "Note"
     Data is converted to Arrow before being written to disk. For maximum control over how data is saved, either provide the PyArrow schema to convert to or else provide a PyArrow Table directly.
 
-The **`vector`** column needs to be a [Vector](../python/pydantic.md#vector-field) (defined as [pyarrow.FixedSizeList](https://arrow.apache.org/docs/python/generated/pyarrow.list_.html)) type.
+    The **`vector`** column needs to be a [Vector](../python/pydantic.md#vector-field) (defined as [pyarrow.FixedSizeList](https://arrow.apache.org/docs/python/generated/pyarrow.list_.html)) type. 
 
-```python
+    ```python
-custom_schema = pa.schema([
+    custom_schema = pa.schema([
-pa.field("vector", pa.list_(pa.float32(), 4)),
+    pa.field("vector", pa.list_(pa.float32(), 4)),
-pa.field("lat", pa.float32()),
+    pa.field("lat", pa.float32()),
-pa.field("long", pa.float32())
+    pa.field("long", pa.float32())
-])
+    ])
 
-table = db.create_table("my_table", data, schema=custom_schema)
+    table = db.create_table("my_table", data, schema=custom_schema)
-```
+    ```
 
 ### From a Polars DataFrame
 
-LanceDB supports [Polars](https://pola.rs/), a modern, fast DataFrame library
+    LanceDB supports [Polars](https://pola.rs/), a modern, fast DataFrame library
-written in Rust. Just like in Pandas, the Polars integration is enabled by PyArrow
+    written in Rust. Just like in Pandas, the Polars integration is enabled by PyArrow
-under the hood. A deeper integration between LanceDB Tables and Polars DataFrames
+    under the hood. A deeper integration between LanceDB Tables and Polars DataFrames
-is on the way.
+    is on the way.
 
-```python
+    ```python
-import polars as pl
+    import polars as pl
 
-data = pl.DataFrame({
+    data = pl.DataFrame({
-    "vector": [[3.1, 4.1], [5.9, 26.5]],
+        "vector": [[3.1, 4.1], [5.9, 26.5]],
-    "item": ["foo", "bar"],
+        "item": ["foo", "bar"],
-    "price": [10.0, 20.0]
+        "price": [10.0, 20.0]
-})
+    })
-table = db.create_table("pl_table", data=data)
+    table = db.create_table("pl_table", data=data)
-```
+    ```
 
 ### From an Arrow Table
-You can also create LanceDB tables directly from Arrow tables.
-LanceDB supports float16 data type!
-
 === "Python"
+    You can also create LanceDB tables directly from Arrow tables. 
+    LanceDB supports float16 data type!
 
     ```python
     import pyarrows as pa
@@ -204,165 +160,159 @@ LanceDB supports float16 data type!
     tbl = db.create_table("f16_tbl", data, schema=schema)
     ```
 
-=== "Typescript[^1]"
+=== "Javascript"
+    You can also create LanceDB tables directly from Arrow tables. 
+    LanceDB supports Float16 data type!
 
-    === "@lancedb/lancedb"
+    ```javascript
+    --8<-- "docs/src/basic_legacy.ts:create_f16_table"
+    ```
 
-        ```typescript
+    ### From Pydantic Models
-        --8<-- "nodejs/examples/basic.ts:create_f16_table"
-        ```
 
-    === "vectordb (deprecated)"
+    When you create an empty table without data, you must specify the table schema.
+    LanceDB supports creating tables by specifying a PyArrow schema or a specialized
+    Pydantic model called `LanceModel`.
 
-        ```typescript
+    For example, the following Content model specifies a table with 5 columns:
-        --8<-- "docs/src/basic_legacy.ts:create_f16_table"
+    `movie_id`, `vector`, `genres`, `title`, and `imdb_id`. When you create a table, you can
-        ```
+    pass the class as the value of the `schema` parameter to `create_table`.
+    The `vector` column is a `Vector` type, which is a specialized Pydantic type that
+    can be configured with the vector dimensions. It is also important to note that
+    LanceDB only understands subclasses of `lancedb.pydantic.LanceModel`
+    (which itself derives from `pydantic.BaseModel`).
 
-### From Pydantic Models
+    ```python
+    from lancedb.pydantic import Vector, LanceModel
 
-When you create an empty table without data, you must specify the table schema.
+    class Content(LanceModel):
-LanceDB supports creating tables by specifying a PyArrow schema or a specialized
+        movie_id: int
-Pydantic model called `LanceModel`.
+        vector: Vector(128)
+        genres: str
+        title: str
+        imdb_id: int
 
-For example, the following Content model specifies a table with 5 columns:
+        @property
-`movie_id`, `vector`, `genres`, `title`, and `imdb_id`. When you create a table, you can
+        def imdb_url(self) -> str:
-pass the class as the value of the `schema` parameter to `create_table`.
+            return f"https://www.imdb.com/title/tt{self.imdb_id}"
-The `vector` column is a `Vector` type, which is a specialized Pydantic type that
-can be configured with the vector dimensions. It is also important to note that
-LanceDB only understands subclasses of `lancedb.pydantic.LanceModel`
-(which itself derives from `pydantic.BaseModel`).
 
-```python
+    import pyarrow as pa
-from lancedb.pydantic import Vector, LanceModel
+    db = lancedb.connect("~/.lancedb")
+    table_name = "movielens_small"
+    table = db.create_table(table_name, schema=Content)
+    ```
 
-class Content(LanceModel):
+    #### Nested schemas
-    movie_id: int
-    vector: Vector(128)
-    genres: str
-    title: str
-    imdb_id: int
 
-    @property
+    Sometimes your data model may contain nested objects.
-    def imdb_url(self) -> str:
+    For example, you may want to store the document string
-        return f"https://www.imdb.com/title/tt{self.imdb_id}"
+    and the document soure name as a nested Document object:
 
-import pyarrow as pa
+    ```python
-db = lancedb.connect("~/.lancedb")
+    class Document(BaseModel):
-table_name = "movielens_small"
+        content: str
-table = db.create_table(table_name, schema=Content)
+        source: str
-```
+    ```
 
-#### Nested schemas
+    This can be used as the type of a LanceDB table column:
 
-Sometimes your data model may contain nested objects.
+    ```python
-For example, you may want to store the document string
+    class NestedSchema(LanceModel):
-and the document soure name as a nested Document object:
+        id: str
+        vector: Vector(1536)
+        document: Document
 
-```python
+    tbl = db.create_table("nested_table", schema=NestedSchema, mode="overwrite")
-class Document(BaseModel):
+    ```
-    content: str
-    source: str
-```
 
-This can be used as the type of a LanceDB table column:
+    This creates a struct column called "document" that has two subfields 
+    called "content" and "source":
 
-```python
+    ```
-class NestedSchema(LanceModel):
+    In [28]: tbl.schema
-    id: str
+    Out[28]:
-    vector: Vector(1536)
+    id: string not null
-    document: Document
+    vector: fixed_size_list<item: float>[1536] not null
+        child 0, item: float
+    document: struct<content: string not null, source: string not null> not null
+        child 0, content: string not null
+        child 1, source: string not null    
+    ```
 
-tbl = db.create_table("nested_table", schema=NestedSchema, mode="overwrite")
+    #### Validators
-```
 
-This creates a struct column called "document" that has two subfields
+    Note that neither Pydantic nor PyArrow automatically validates that input data
-called "content" and "source":
+    is of the correct timezone, but this is easy to add as a custom field validator:
 
-```
+    ```python
-In [28]: tbl.schema
+    from datetime import datetime
-Out[28]:
+    from zoneinfo import ZoneInfo
-id: string not null
-vector: fixed_size_list<item: float>[1536] not null
-    child 0, item: float
-document: struct<content: string not null, source: string not null> not null
-    child 0, content: string not null
-    child 1, source: string not null
-```
 
-#### Validators
+    from lancedb.pydantic import LanceModel
+    from pydantic import Field, field_validator, ValidationError, ValidationInfo
 
-Note that neither Pydantic nor PyArrow automatically validates that input data
+    tzname = "America/New_York"
-is of the correct timezone, but this is easy to add as a custom field validator:
+    tz = ZoneInfo(tzname)
 
-```python
+    class TestModel(LanceModel):
-from datetime import datetime
+        dt_with_tz: datetime = Field(json_schema_extra={"tz": tzname})
-from zoneinfo import ZoneInfo
 
-from lancedb.pydantic import LanceModel
+        @field_validator('dt_with_tz')
-from pydantic import Field, field_validator, ValidationError, ValidationInfo
+        @classmethod
+        def tz_must_match(cls, dt: datetime) -> datetime:
+            assert dt.tzinfo == tz
+            return dt        
 
-tzname = "America/New_York"
+    ok = TestModel(dt_with_tz=datetime.now(tz))
-tz = ZoneInfo(tzname)
 
-class TestModel(LanceModel):
+    try:
-    dt_with_tz: datetime = Field(json_schema_extra={"tz": tzname})
+        TestModel(dt_with_tz=datetime.now(ZoneInfo("Asia/Shanghai")))
+        assert 0 == 1, "this should raise ValidationError"
+    except ValidationError:
+        print("A ValidationError was raised.")
+        pass
+    ```
 
-    @field_validator('dt_with_tz')
+    When you run this code it should print "A ValidationError was raised."
-    @classmethod
-    def tz_must_match(cls, dt: datetime) -> datetime:
-        assert dt.tzinfo == tz
-        return dt
 
-ok = TestModel(dt_with_tz=datetime.now(tz))
+    #### Pydantic custom types
 
-try:
+    LanceDB does NOT yet support converting pydantic custom types. If this is something you need,
-    TestModel(dt_with_tz=datetime.now(ZoneInfo("Asia/Shanghai")))
+    please file a feature request on the [LanceDB Github repo](https://github.com/lancedb/lancedb/issues/new).
-    assert 0 == 1, "this should raise ValidationError"
-except ValidationError:
-    print("A ValidationError was raised.")
-    pass
-```
 
-When you run this code it should print "A ValidationError was raised."
+    ### Using Iterators / Writing Large Datasets
 
-#### Pydantic custom types
+    It is recommended to use iterators to add large datasets in batches when creating your table in one go. This does not create multiple versions of your dataset unlike manually adding batches using `table.add()`
 
-LanceDB does NOT yet support converting pydantic custom types. If this is something you need,
+    LanceDB additionally supports PyArrow's `RecordBatch` Iterators or other generators producing supported data types.
-please file a feature request on the [LanceDB Github repo](https://github.com/lancedb/lancedb/issues/new).
 
-### Using Iterators / Writing Large Datasets
+    Here's an example using using `RecordBatch` iterator for creating tables.
 
-It is recommended to use iterators to add large datasets in batches when creating your table in one go. This does not create multiple versions of your dataset unlike manually adding batches using `table.add()`
+    ```python
+    import pyarrow as pa
 
-LanceDB additionally supports PyArrow's `RecordBatch` Iterators or other generators producing supported data types.
+    def make_batches():
+        for i in range(5):
+            yield pa.RecordBatch.from_arrays(
+                [
+                    pa.array([[3.1, 4.1, 5.1, 6.1], [5.9, 26.5, 4.7, 32.8]],
+                            pa.list_(pa.float32(), 4)),
+                    pa.array(["foo", "bar"]),
+                    pa.array([10.0, 20.0]),
+                ],
+                ["vector", "item", "price"],
+            )
 
-Here's an example using using `RecordBatch` iterator for creating tables.
+    schema = pa.schema([
+        pa.field("vector", pa.list_(pa.float32(), 4)),
+        pa.field("item", pa.utf8()),
+        pa.field("price", pa.float32()),
+    ])
 
-```python
+    db.create_table("batched_tale", make_batches(), schema=schema)
-import pyarrow as pa
+    ```
 
-def make_batches():
+    You can also use iterators of other types like Pandas DataFrame or Pylists directly in the above example.
-    for i in range(5):
-        yield pa.RecordBatch.from_arrays(
-            [
-                pa.array([[3.1, 4.1, 5.1, 6.1], [5.9, 26.5, 4.7, 32.8]],
-                        pa.list_(pa.float32(), 4)),
-                pa.array(["foo", "bar"]),
-                pa.array([10.0, 20.0]),
-            ],
-            ["vector", "item", "price"],
-        )
-
-schema = pa.schema([
-    pa.field("vector", pa.list_(pa.float32(), 4)),
-    pa.field("item", pa.utf8()),
-    pa.field("price", pa.float32()),
-])
-
-db.create_table("batched_tale", make_batches(), schema=schema)
-```
-
-You can also use iterators of other types like Pandas DataFrame or Pylists directly in the above example.
 
 ## Open existing tables
 
@@ -379,24 +329,23 @@ You can also use iterators of other types like Pandas DataFrame or Pylists direc
     tbl = db.open_table("my_table")
     ```
 
-=== "Typescript[^1]"
+=== "JavaScript"
-
     If you forget the name of your table, you can always get a listing of all table names.
 
-    ```typescript
+    ```javascript
     console.log(await db.tableNames());
     ```
 
     Then, you can open any existing tables.
 
-    ```typescript
+    ```javascript
     const tbl = await db.openTable("my_table");
     ```
 
 ## Creating empty table
-You can create an empty table for scenarios where you want to add data to the table later. An example would be when you want to collect data from a stream/external file and then add it to a table in batches.
 
 === "Python"
+    In Python, you can create an empty table for scenarios where you want to add data to the table later. An example would be when you want to collect data from a stream/external file and then add it to a table in batches.
 
     ```python
 
@@ -433,23 +382,9 @@ You can create an empty table for scenarios where you want to add data to the ta
 
     Once the empty table has been created, you can add data to it via the various methods listed in the [Adding to a table](#adding-to-a-table) section.
 
-=== "Typescript[^1]"
-
-    === "@lancedb/lancedb"
-
-        ```typescript
-        --8<-- "nodejs/examples/basic.ts:create_empty_table"
-        ```
-
-    === "vectordb (deprecated)"
-
-        ```typescript
-        --8<-- "docs/src/basic_legacy.ts:create_empty_table"
-        ```
-
 ## Adding to a table
 
-After a table has been created, you can always add more data to it usind the `add` method
+After a table has been created, you can always add more data to it using the various methods available.
 
 === "Python"
     You can add any of the valid data structures accepted by LanceDB table, i.e, `dict`, `list[dict]`, `pd.DataFrame`, or `Iterator[pa.RecordBatch]`. Below are some examples.
@@ -517,27 +452,8 @@ After a table has been created, you can always add more data to it usind the `ad
     tbl.add(pydantic_model_items)
     ```
 
-    ??? "Ingesting Pydantic models with LanceDB embedding API"
-        When using LanceDB's embedding API, you can add Pydantic models directly to the table. LanceDB will automatically convert the `vector` field to a vector before adding it to the table. You need to specify the default value of `vector` feild as None to allow LanceDB to automatically vectorize the data.
 
-        ```python
+=== "JavaScript"
-        import lancedb
-        from lancedb.pydantic import LanceModel, Vector
-        from lancedb.embeddings import get_registry
-
-        db = lancedb.connect("~/tmp")
-        embed_fcn = get_registry().get("huggingface").create(name="BAAI/bge-small-en-v1.5")
-
-        class Schema(LanceModel):
-            text: str = embed_fcn.SourceField()
-            vector: Vector(embed_fcn.ndims()) = embed_fcn.VectorField(default=None)
-
-        tbl = db.create_table("my_table", schema=Schema, mode="overwrite")
-        models = [Schema(text="hello"), Schema(text="world")]
-        tbl.add(models)
-        ```
-
-=== "Typescript[^1]"
 
     ```javascript
     await tbl.add(
@@ -593,15 +509,15 @@ Use the `delete()` method on tables to delete rows from a table. To choose which
     # 0  3  [5.0, 6.0]
     ```
 
-=== "Typescript[^1]"
+=== "JavaScript"
 
-    ```ts
+    ```javascript
     await tbl.delete('item = "fizz"')
     ```
 
     ### Deleting row with specific column value
 
-    ```ts
+    ```javascript
     const con = await lancedb.connect("./.lancedb")
     const data = [
       {id: 1, vector: [1, 2]},
@@ -615,7 +531,7 @@ Use the `delete()` method on tables to delete rows from a table. To choose which
 
     ### Delete from a list of values
 
-    ```ts
+    ```javascript
     const to_remove = [1, 5];
     await tbl.delete(`id IN (${to_remove.join(",")})`)
     await tbl.countRows() // Returns 1
@@ -672,49 +588,26 @@ This can be used to update zero to all rows depending on how many rows match the
     2  2  [10.0, 10.0]
     ```
 
-=== "Typescript[^1]"
+=== "JavaScript/Typescript"
 
-    === "@lancedb/lancedb"
+    API Reference: [vectordb.Table.update](../javascript/interfaces/Table.md/#update)
 
-        API Reference: [lancedb.Table.update](../js/classes/Table.md/#update)
+    ```javascript
+    const lancedb = require("vectordb");
 
-        ```ts
+    const db = await lancedb.connect("./.lancedb");
-        import * as lancedb from "@lancedb/lancedb";
 
-        const db = await lancedb.connect("./.lancedb");
+    const data = [
+      {x: 1, vector: [1, 2]},
+      {x: 2, vector: [3, 4]},
+      {x: 3, vector: [5, 6]},
+    ];
+    const tbl = await db.createTable("my_table", data)
 
-        const data = [
+    await tbl.update({ where: "x = 2", values: {vector: [10, 10]} })
-            {x: 1, vector: [1, 2]},
+    ```
-            {x: 2, vector: [3, 4]},
-            {x: 3, vector: [5, 6]},
-        ];
-        const tbl = await db.createTable("my_table", data)
 
-        await tbl.update({vector: [10, 10]}, { where: "x = 2"})
+The `values` parameter is used to provide the new values for the columns as literal values. You can also use the `values_sql` / `valuesSql` parameter to provide SQL expressions for the new values. For example, you can use `values_sql="x + 1"` to increment the value of the `x` column by 1.
-        ```
-
-    === "vectordb (deprecated)"
-
-        API Reference: [vectordb.Table.update](../javascript/interfaces/Table.md/#update)
-
-        ```ts
-        const lancedb = require("vectordb");
-
-        const db = await lancedb.connect("./.lancedb");
-
-        const data = [
-            {x: 1, vector: [1, 2]},
-            {x: 2, vector: [3, 4]},
-            {x: 3, vector: [5, 6]},
-        ];
-        const tbl = await db.createTable("my_table", data)
-
-        await tbl.update({ where: "x = 2", values: {vector: [10, 10]} })
-        ```
-
-#### Updating using a sql query
-
-  The `values` parameter is used to provide the new values for the columns as literal values. You can also use the `values_sql` / `valuesSql` parameter to provide SQL expressions for the new values. For example, you can use `values_sql="x + 1"` to increment the value of the `x` column by 1.
 
 === "Python"
 
@@ -733,47 +626,16 @@ This can be used to update zero to all rows depending on how many rows match the
     2  3  [10.0, 10.0]
     ```
 
-=== "Typescript[^1]"
+=== "JavaScript/Typescript"
 
-    === "@lancedb/lancedb"
+    ```javascript
-
+    await tbl.update({ valuesSql: { x: "x + 1" } })
-        Coming Soon!
+    ```
-
-    === "vectordb (deprecated)"
-
-        ```ts
-        await tbl.update({ valuesSql: { x: "x + 1" } })
-        ```
 
 !!! info "Note"
 
     When rows are updated, they are moved out of the index. The row will still show up in ANN queries, but the query will not be as fast as it would be if the row was in the index. If you update a large proportion of rows, consider rebuilding the index afterwards.
 
-## Drop a table
-
-Use the `drop_table()` method on the database to remove a table.
-
-=== "Python"
-
-      ```python
-      --8<-- "python/python/tests/docs/test_basic.py:drop_table"
-      --8<-- "python/python/tests/docs/test_basic.py:drop_table_async"
-      ```
-
-      This permanently removes the table and is not recoverable, unlike deleting rows.
-      By default, if the table does not exist an exception is raised. To suppress this,
-      you can pass in `ignore_missing=True`.
-
-=== "TypeScript"
-
-      ```typescript
-      --8<-- "docs/src/basic_legacy.ts:drop_table"
-      ```
-
-      This permanently removes the table and is not recoverable, unlike deleting rows.
-      If the table does not exist an exception is raised.
-
-
 ## Consistency
 
 In LanceDB OSS, users can set the `read_consistency_interval` parameter on connections to achieve different levels of read consistency. This parameter determines how frequently the database synchronizes with the underlying storage system to check for updates made by other processes. If another process updates a table, the database will not see the changes until the next synchronization.
@@ -818,18 +680,18 @@ There are three possible settings for `read_consistency_interval`:
     table.checkout_latest()
     ```
 
-=== "Typescript[^1]"
+=== "JavaScript/Typescript"
 
     To set strong consistency, use `0`:
 
-    ```ts
+    ```javascript
     const db = await lancedb.connect({ uri: "./.lancedb", readConsistencyInterval: 0 });
     const table = await db.openTable("my_table");
     ```
 
     For eventual consistency, specify the update interval as seconds:
 
-    ```ts
+    ```javascript
     const db = await lancedb.connect({ uri: "./.lancedb", readConsistencyInterval: 5 });
     const table = await db.openTable("my_table");
     ```
@@ -841,5 +703,3 @@ There are three possible settings for `read_consistency_interval`:
 ## What's next?
 
 Learn the best practices on creating an ANN index and getting the most out of it.
-
-[^1]: The `vectordb` package is a legacy package that is  deprecated in favor of `@lancedb/lancedb`.  The `vectordb` package will continue to receive bug fixes and security updates until September 2024.  We recommend all new projects use `@lancedb/lancedb`.  See the [migration guide](migration.md) for more information.

docs/src/guides/tuning_retrievers/1_query_types.md

@@ -1,131 +0,0 @@
-## Improving retriever performance
-
-Try it yourself - <a href="https://colab.research.google.com/github/lancedb/lancedb/blob/main/docs/src/notebooks/lancedb_reranking.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a><br/>
-
-VectorDBs are used as retreivers in recommender or chatbot-based systems for retrieving relevant data based on user queries. For example, retriever is a critical component of Retrieval Augmented Generation (RAG) acrhitectures. In this section, we will discuss how to improve the performance of retrievers.
-
-There are serveral ways to improve the performance of retrievers. Some of the common techniques are:
-
-* Using different query types
-* Using hybrid search
-* Fine-tuning the embedding models
-* Using different embedding models
-
-Using different embedding models is something that's very specific to the use case and the data. So we will not discuss it here. In this section, we will discuss the first three techniques.
-
-
-!!! note "Note"
-    We'll be using a simple metric called "hit-rate" for evaluating the performance of the retriever across this guide. Hit-rate is the percentage of queries for which the retriever returned the correct answer in the top-k results. For example, if the retriever returned the correct answer in the top-3 results for 70% of the queries, then the hit-rate@3 is 0.7.
-
-
-## The dataset
-We'll be using a QA dataset generated using a LLama2 review paper. The dataset contains 221 query, context and answer triplets. The queries and answers are generated using GPT-4 based on a given query. Full script used to generate the dataset can be found on this [repo](https://github.com/lancedb/ragged). It can be downloaded from [here](https://github.com/AyushExel/assets/blob/main/data_qa.csv)
-
-### Using different query types
-Let's setup the embeddings and the dataset first. We'll use the LanceDB's `huggingface` embeddings integration for this guide. 
-
-```python
-import lancedb
-import pandas as pd
-from lancedb.embeddings import get_registry
-from lancedb.pydantic import Vector, LanceModel
-
-db = lancedb.connect("~/lancedb/query_types")
-df = pd.read_csv("data_qa.csv")
-
-embed_fcn = get_registry().get("huggingface").create(name="BAAI/bge-small-en-v1.")
-
-class Schema(LanceModel):
-    context: str = embed_fcn.SourceField()
-    vector: Vector(embed_fcn.ndims()) = embed_fcn.VectorField()
-
-table = db.create_table("qa", schema=Schema)
-table.add(df[["context"]].to_dict(orient="records"))
-
-queries = df["query"].tolist()
-```
-
-Now that we have the dataset and embeddings table set up, here's how you can run different query types on the dataset.
-
-* <b> Vector Search: </b>
-
-    ```python
-    table.search(quries[0], query_type="vector").limit(5).to_pandas()
-    ```
-    By default, LanceDB uses vector search query type for searching and it automatically converts the input query to a vector before searching when using embedding API. So, the following statement is equivalent to the above statement.
-
-    ```python
-    table.search(quries[0]).limit(5).to_pandas()
-    ```
-
-    Vector or semantic search is useful when you want to find documents that are similar to the query in terms of meaning.
-
----
-
-* <b> Full-text Search: </b>
-    
-    FTS requires creating an index on the column you want to search on. `replace=True` will replace the existing index if it exists.
-    Once the index is created, you can search using the `fts` query type.
-    ```python
-    table.create_fts_index("context", replace=True)
-    table.search(quries[0], query_type="fts").limit(5).to_pandas()
-    ```
-
-    Full-text search is useful when you want to find documents that contain the query terms.
-
----
-
-* <b> Hybrid Search: </b>
-
-    Hybrid search is a combination of vector and full-text search. Here's how you can run a hybrid search query on the dataset.
-    ```python
-    table.search(quries[0], query_type="hybrid").limit(5).to_pandas()
-    ```
-    Hybrid search requires a reranker to combine and rank the results from vector and full-text search. We'll cover reranking as a concept in the next section.
-
-    Hybrid search is useful when you want to combine the benefits of both vector and full-text search.
-
-    !!! note "Note"
-        By default, it uses `LinearCombinationReranker` that combines the scores from vector and full-text search using a weighted linear combination. It is the simplest reranker implementation available in LanceDB. You can also use other rerankers like `CrossEncoderReranker` or `CohereReranker` for reranking the results.
-        Learn more about rerankers [here](https://lancedb.github.io/lancedb/reranking/)
-
-    
-
-### Hit rate evaluation results
-
-Now that we have seen how to run different query types on the dataset, let's evaluate the hit-rate of each query type on the dataset.
-For brevity, the entire evaluation script is not shown here. You can find the complete evaluation and benchmarking utility scripts [here](https://github.com/lancedb/ragged).
-
-Here are the hit-rate results for the dataset:
-
-| Query Type | Hit-rate@5 |
-| --- | --- |
-| Vector Search | 0.640 |
-| Full-text Search | 0.595 |
-| Hybrid Search (w/ LinearCombinationReranker) | 0.645 |
-
-**Choosing query type** is very specific to the use case and the data. This synthetic dataset has been generated to be semantically challenging, i.e, the queries don't have a lot of keywords in common with the context. So, vector search performs better than full-text search. However, in real-world scenarios, full-text search might perform better than vector search. Hybrid search is a good choice when you want to combine the benefits of both vector and full-text search.
-
-### Evaluation results on other datasets
-
-The hit-rate results can vary based on the dataset and the query type. Here are the hit-rate results for the other datasets using the same embedding function.
-
-* <b> SQuAD Dataset: </b>
-
-    | Query Type | Hit-rate@5 |
-    | --- | --- |
-    | Vector Search | 0.822 |
-    | Full-text Search | 0.835 |
-    | Hybrid Search (w/ LinearCombinationReranker) | 0.8874 |
-
-* <b> Uber10K sec filing Dataset: </b>
-
-    | Query Type | Hit-rate@5 |
-    | --- | --- |
-    | Vector Search | 0.608 |
-    | Full-text Search | 0.82 |
-    | Hybrid Search (w/ LinearCombinationReranker) | 0.80 |
-
-In these standard datasets, FTS seems to perform much better than vector search because the queries have a lot of keywords in common with the context. So, in general choosing the query type is very specific to the use case and the data.
-
-

docs/src/guides/tuning_retrievers/2_reranking.md

@@ -1,80 +0,0 @@
-Continuing from the previous section, we can now rerank the results using more complex rerankers.
-
-Try it yourself - <a href="https://colab.research.google.com/github/lancedb/lancedb/blob/main/docs/src/notebooks/lancedb_reranking.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a><br/>
-
-## Reranking search results
-You can rerank any search results using a reranker. The syntax for reranking is as follows:
-
-```python
-from lancedb.rerankers import LinearCombinationReranker
-
-reranker = LinearCombinationReranker()
-table.search(quries[0], query_type="hybrid").rerank(reranker=reranker).limit(5).to_pandas()
-```
-Based on the `query_type`, the `rerank()` function can accept other arguments as well. For example, hybrid search accepts a `normalize` param to determine the score normalization method.
-
-!!! note "Note"
-    LanceDB provides a `Reranker` base class that can be extended to implement custom rerankers. Each reranker must implement the `rerank_hybrid` method. `rerank_vector` and `rerank_fts` methods are optional. For example, the `LinearCombinationReranker` only implements the `rerank_hybrid` method and so it can only be used for reranking hybrid search results.
-
-## Choosing a Reranker
-There are many rerankers available in LanceDB like `CrossEncoderReranker`, `CohereReranker`, and `ColBERT`. The choice of reranker depends on the dataset and the application. You can even implement you own custom reranker by extending the `Reranker` class. For more details about each available reranker and performance comparison, refer to the [rerankers](https://lancedb.github.io/lancedb/reranking/) documentation.
-
-In this example, we'll use the `CohereReranker` to rerank the search results. It requires  `cohere` to be installed and `COHERE_API_KEY` to be set in the environment. To get your API key, sign up on [Cohere](https://cohere.ai/).
-
-```python
-from lancedb.rerankers import CohereReranker
-
-# use Cohere reranker v3
-reranker = CohereReranker(model_name="rerank-english-v3.0") # default model is "rerank-english-v2.0"
-```
-
-### Reranking search results
-Now we can rerank all query type results using the `CohereReranker`:
-
-```python
-
-# rerank hybrid search results
-table.search(quries[0], query_type="hybrid").rerank(reranker=reranker).limit(5).to_pandas()
-
-# rerank vector search results
-table.search(quries[0], query_type="vector").rerank(reranker=reranker).limit(5).to_pandas()
-
-# rerank fts search results
-table.search(quries[0], query_type="fts").rerank(reranker=reranker).limit(5).to_pandas()
-```
-
-Each reranker can accept additional arguments. For example, `CohereReranker` accepts `top_k` and `batch_size` params to control the number of documents to rerank and the batch size for reranking respectively. Similarly, a custom reranker can accept any number of arguments based on the implementation. For example, a reranker can accept a `filter` that implements some custom logic to filter out documents before reranking.
-
-## Results
-
-Let us take a look at the same datasets from the previous sections, using the same embedding table but with Cohere reranker applied to all query types.
-
-!!! note "Note"
-    When reranking fts or vector search results, the search results are over-fetched by a factor of 2 and then reranked. From the reranked set, `top_k` (5 in this case) results are taken. This is done because reranking will have no effect on the hit-rate if we only fetch the `top_k` results.
-
-### Synthetic LLama2 paper dataset
-
-| Query Type | Hit-rate@5 |
-| --- | --- |
-| Vector |  0.640 |
-| FTS   |  0.595  |
-| Reranked vector | 0.677    |
-| Reranked fts  | 0.672    |
-| Hybrid | 0.759 |
-
-### SQuAD Dataset
-
-
-### Uber10K sec filing Dataset
-
-| Query Type | Hit-rate@5 |
-| --- | --- |
-| Vector |  0.608 |
-| FTS   |  0.824  |
-| Reranked vector | 0.671    |
-| Reranked fts  | 0.843    |
-| Hybrid | 0.849 |
-
-
-
-

docs/src/guides/tuning_retrievers/3_embed_tuning.md

@@ -1,82 +0,0 @@
-## Finetuning the Embedding Model
-Try it yourself - <a href="https://colab.research.google.com/github/lancedb/lancedb/blob/main/docs/src/notebooks/embedding_tuner.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a><br/>
-
-Another way to improve retriever performance is to fine-tune the embedding model itself. Fine-tuning the embedding model can help in learning better representations for the documents and queries in the dataset. This can be particularly useful when the dataset is very different from the pre-trained data used to train the embedding model.
-
-We'll use the same dataset as in the previous sections. Start off by splitting the dataset into training and validation sets:
-```python
-from sklearn.model_selection import train_test_split
-
-train_df, validation_df = train_test_split("data_qa.csv", test_size=0.2, random_state=42)
-
-train_df.to_csv("data_train.csv", index=False)
-validation_df.to_csv("data_val.csv", index=False)
-```
-
-You can use any tuning API to fine-tune embedding models. In this example, we'll utilise Llama-index as it also comes with utilities for synthetic data generation and training the model. 
-
-
-Then parse the dataset as llama-index text nodes and generate synthetic QA pairs from each node.
-```python
-from llama_index.core.node_parser import SentenceSplitter
-from llama_index.readers.file import PagedCSVReader
-from llama_index.finetuning import generate_qa_embedding_pairs
-from llama_index.core.evaluation import EmbeddingQAFinetuneDataset
-
-def load_corpus(file):
-    loader = PagedCSVReader(encoding="utf-8")
-    docs = loader.load_data(file=Path(file))
-
-    parser = SentenceSplitter()
-    nodes = parser.get_nodes_from_documents(docs)
-
-    return nodes
-
-from llama_index.llms.openai import OpenAI
-
-
-train_dataset = generate_qa_embedding_pairs(
-    llm=OpenAI(model="gpt-3.5-turbo"), nodes=train_nodes, verbose=False
-)
-val_dataset = generate_qa_embedding_pairs(
-    llm=OpenAI(model="gpt-3.5-turbo"), nodes=val_nodes, verbose=False
-)
-```
-
-Now we'll use `SentenceTransformersFinetuneEngine` engine to fine-tune the model. You can also use `sentence-transformers` or `transformers` library to fine-tune the model. 
-
-```python
-from llama_index.finetuning import SentenceTransformersFinetuneEngine
-
-finetune_engine = SentenceTransformersFinetuneEngine(
-    train_dataset,
-    model_id="BAAI/bge-small-en-v1.5",
-    model_output_path="tuned_model",
-    val_dataset=val_dataset,
-)
-finetune_engine.finetune()
-embed_model = finetune_engine.get_finetuned_model()
-```
-This saves the fine tuned embedding model in `tuned_model` folder. This al
-
-# Evaluation results
-In order to eval the retriever, you can either use this model to ingest the data into LanceDB directly or llama-index's LanceDB integration to create a `VectorStoreIndex` and use it as a retriever. 
-On performing the same hit-rate evaluation as before, we see a significant improvement in the hit-rate across all query types.
-
-### Baseline
-| Query Type | Hit-rate@5 |
-| --- | --- |
-| Vector Search | 0.640 |
-| Full-text Search | 0.595 |
-| Reranked Vector Search | 0.677 |
-| Reranked Full-text Search | 0.672 |
-| Hybrid Search (w/ CohereReranker) | 0.759|
-
-### Fine-tuned model ( 2 iterations )
-| Query Type | Hit-rate@5 |
-| --- | --- |
-| Vector Search | 0.672 |
-| Full-text Search | 0.595 |
-| Reranked Vector Search | 0.754 |
-| Reranked Full-text Search | 0.672|
-| Hybrid Search (w/ CohereReranker) | 0.768 |

docs/src/hybrid_search/eval.md

@@ -5,9 +5,7 @@ Hybrid Search is a broad (often misused) term. It can mean anything from combini
 ## The challenge of (re)ranking search results
 Once you have a group of the most relevant search results from multiple search sources, you'd likely standardize the score and rank them accordingly. This process can also be seen as another independent step - reranking.
 There are two approaches for reranking search results from multiple sources.
-
 * <b>Score-based</b>: Calculate final relevance scores based on a weighted linear combination of individual search algorithm scores. Example - Weighted linear combination of semantic search & keyword-based search results.
-
 * <b>Relevance-based</b>: Discards the existing scores and calculates the relevance of each search result - query pair. Example - Cross Encoder models
 
 Even though there are many strategies for reranking search results, none works for all cases. Moreover, evaluating them itself is a challenge. Also, reranking can be dataset, application specific so it's hard to generalize.

docs/src/index.md

@@ -28,7 +28,7 @@ LanceDB **Cloud** is a SaaS (software-as-a-service) solution that runs serverles
 
 * Fast production-scale vector similarity, full-text & hybrid search and a SQL query interface (via [DataFusion](https://github.com/apache/arrow-datafusion))
 
-* Python, Javascript/Typescript, and Rust support
+* Native Python and Javascript/Typescript support
 
 * Store, query & manage multi-modal data (text, images, videos, point clouds, etc.), not just the embeddings and metadata
 
@@ -54,4 +54,3 @@ The following pages go deeper into the internal of LanceDB and how to use it.
 * [Ecosystem Integrations](integrations/index.md): Integrate LanceDB with other tools in the data ecosystem
 * [Python API Reference](python/python.md): Python OSS and Cloud API references
 * [JavaScript API Reference](javascript/modules.md): JavaScript OSS and Cloud API references
-* [Rust API Reference](https://docs.rs/lancedb/latest/lancedb/index.html): Rust API reference

docs/src/integrations/index.md

@@ -13,7 +13,7 @@ Get started using these examples and quick links.
 | Integrations | |
 |---|---:|
 | <h3> LlamaIndex </h3>LlamaIndex is a simple, flexible data framework for connecting custom data sources to large language models. Llama index integrates with LanceDB as the serverless VectorDB. <h3>[Lean More](https://gpt-index.readthedocs.io/en/latest/examples/vector_stores/LanceDBIndexDemo.html) </h3> |<img src="../assets/llama-index.jpg" alt="image" width="150" height="auto">|
-| <h3>Langchain</h3>Langchain allows building applications with LLMs through composability <h3>[Lean More](https://lancedb.github.io/lancedb/integrations/langchain/) | <img src="../assets/langchain.png" alt="image" width="150" height="auto">|
+| <h3>Langchain</h3>Langchain allows building applications with LLMs through composability <h3>[Lean More](https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/lancedb.html) | <img src="../assets/langchain.png" alt="image" width="150" height="auto">|
 | <h3>Langchain TS</h3> Javascript bindings for Langchain. It integrates with LanceDB's serverless vectordb allowing you to build powerful AI applications through composibility using only serverless functions. <h3>[Learn More]( https://js.langchain.com/docs/modules/data_connection/vectorstores/integrations/lancedb) | <img src="../assets/langchain.png" alt="image" width="150" height="auto">|
 | <h3>Voxel51</h3>  It is an open source toolkit that enables you to build better computer vision workflows by improving the quality of your datasets and delivering insights about your models.<h3>[Learn More](./voxel51.md) | <img src="../assets/voxel.gif" alt="image" width="150" height="auto">|
 | <h3>PromptTools</h3>  Offers a set of free, open-source tools for testing and experimenting with models, prompts, and configurations. The core idea is to enable developers to evaluate prompts using familiar interfaces like code and notebooks. You can use it to experiment with different configurations of LanceDB, and test how LanceDB integrates with the LLM of your choice.<h3>[Learn More](./prompttools.md) | <img src="../assets/prompttools.jpeg" alt="image" width="150" height="auto">|

docs/src/integrations/langchain.md

@@ -1,201 +0,0 @@
-# Langchain
-![Illustration](../assets/langchain.png)
-
-## Quick Start
-You can load your document data using langchain's loaders, for this example we are using `TextLoader` and `OpenAIEmbeddings` as the embedding model. Checkout Complete example here - [LangChain demo](../notebooks/langchain_example.ipynb)
-```python
-import os
-from langchain.document_loaders import TextLoader
-from langchain.vectorstores import LanceDB
-from langchain_openai import OpenAIEmbeddings
-from langchain_text_splitters import CharacterTextSplitter
-
-os.environ["OPENAI_API_KEY"] = "sk-..."
-
-loader = TextLoader("../../modules/state_of_the_union.txt") # Replace with your data path
-documents = loader.load()
-
-documents = CharacterTextSplitter().split_documents(documents)
-embeddings = OpenAIEmbeddings()
-
-docsearch = LanceDB.from_documents(documents, embeddings)
-query = "What did the president say about Ketanji Brown Jackson"
-docs = docsearch.similarity_search(query)
-print(docs[0].page_content)
-```
-
-## Documentation
-In the above example `LanceDB` vector store class object is created using `from_documents()` method  which is a `classmethod` and returns the initialized class object. 
-You can also use `LanceDB.from_texts(texts: List[str],embedding: Embeddings)` class method.  
-
-The exhaustive list of parameters for `LanceDB` vector store are :  
-- `connection`: (Optional) `lancedb.db.LanceDBConnection` connection object to use.  If not provided, a new connection will be created.  
-- `embedding`: Langchain embedding model.  
-- `vector_key`: (Optional) Column name to use for vector's in the table. Defaults to `'vector'`.   
-- `id_key`: (Optional) Column name to use for id's in the table. Defaults to `'id'`.  
-- `text_key`: (Optional) Column name to use for text in the table. Defaults to `'text'`.  
-- `table_name`: (Optional) Name of your table in the database. Defaults to `'vectorstore'`.  
-- `api_key`: (Optional) API key to use for LanceDB cloud database. Defaults to `None`.  
-- `region`: (Optional) Region to use for LanceDB cloud database. Only for LanceDB Cloud, defaults to `None`.  
-- `mode`: (Optional) Mode to use for adding data to the table. Defaults to `'overwrite'`.  
-- `reranker`: (Optional) The reranker to use for LanceDB.
-- `relevance_score_fn`: (Optional[Callable[[float], float]]) Langchain relevance score function to be used. Defaults to `None`. 
-
-```python
-db_url = "db://lang_test" # url of db you created
-api_key = "xxxxx" # your API key
-region="us-east-1-dev"  # your selected region
-
-vector_store = LanceDB(
-    uri=db_url,
-    api_key=api_key, #(dont include for local API)
-    region=region, #(dont include for local API)
-    embedding=embeddings,
-    table_name='langchain_test' #Optional
-    )
-```
-
-### Methods 
-
-##### add_texts()
-- `texts`: `Iterable` of strings to add to the vectorstore.
-- `metadatas`: Optional `list[dict()]` of metadatas associated with the texts.
-- `ids`: Optional `list` of ids to associate with the texts. 
-- `kwargs`: `Any`
-
-This method adds texts and stores respective embeddings automatically.
-
-```python
-vector_store.add_texts(texts = ['test_123'], metadatas =[{'source' :'wiki'}]) 
-
-#Additionaly, to explore the table you can load it into a df or save it in a csv file:
-
-tbl = vector_store.get_table()
-print("tbl:", tbl)
-pd_df = tbl.to_pandas()
-pd_df.to_csv("docsearch.csv", index=False)
-
-# you can also create a new vector store object using an older connection object:
-vector_store = LanceDB(connection=tbl, embedding=embeddings)
-```
-##### create_index() 
-- `col_name`: `Optional[str] = None`
-- `vector_col`: `Optional[str] = None`
-- `num_partitions`: `Optional[int] = 256`
-- `num_sub_vectors`: `Optional[int] = 96`
-- `index_cache_size`: `Optional[int] = None`
-
-This method creates an index for the vector store. For index creation make sure your table has enough data in it. An ANN index is ususally not needed for datasets ~100K vectors. For large-scale (>1M) or higher dimension vectors, it is beneficial to create an ANN index.
-
-```python
-# for creating vector index
-vector_store.create_index(vector_col='vector', metric = 'cosine')
-
-# for creating scalar index(for non-vector columns)
-vector_store.create_index(col_name='text')
-
-```
-
-##### similarity_search()
-- `query`: `str`
-- `k`: `Optional[int] = None`
-- `filter`: `Optional[Dict[str, str]] = None`
-- `fts`: `Optional[bool] = False`
-- `name`: `Optional[str] = None`
-- `kwargs`: `Any`
-
-Return documents most similar to the query without relevance scores
-
-```python
-docs = docsearch.similarity_search(query)
-print(docs[0].page_content)
-```
-
-##### similarity_search_by_vector()
-- `embedding`: `List[float]`
-- `k`: `Optional[int] = None`
-- `filter`: `Optional[Dict[str, str]] = None`
-- `name`: `Optional[str] = None`
-- `kwargs`: `Any`
-
-Returns documents most similar to the query vector.
-
-```python
-docs = docsearch.similarity_search_by_vector(query)
-print(docs[0].page_content)
-```
-
-##### similarity_search_with_score()
-- `query`: `str`
-- `k`: `Optional[int] = None`
-- `filter`: `Optional[Dict[str, str]] = None`
-- `kwargs`: `Any`
-
-Returns documents most similar to the query string with relevance scores, gets called by base class's `similarity_search_with_relevance_scores` which selects relevance score based on our `_select_relevance_score_fn`.
-
-```python
-docs = docsearch.similarity_search_with_relevance_scores(query)
-print("relevance score - ", docs[0][1])
-print("text- ", docs[0][0].page_content[:1000])
-```
-
-##### similarity_search_by_vector_with_relevance_scores()
-- `embedding`: `List[float]`
-- `k`: `Optional[int] = None`
-- `filter`: `Optional[Dict[str, str]] = None`
-- `name`: `Optional[str] = None`
-- `kwargs`: `Any`
-
-Return documents most similar to the query vector with relevance scores.
-Relevance score 
-
-```python
-docs = docsearch.similarity_search_by_vector_with_relevance_scores(query_embedding)
-print("relevance score - ", docs[0][1])
-print("text- ", docs[0][0].page_content[:1000])
-```
-
-##### max_marginal_relevance_search()
-- `query`: `str`
-- `k`: `Optional[int] = None`
-- `fetch_k` : Number of Documents to fetch to pass to MMR algorithm, `Optional[int] = None`
-- `lambda_mult`: Number between 0 and 1 that determines the degree
-                        of diversity among the results with 0 corresponding
-                        to maximum diversity and 1 to minimum diversity.
-                        Defaults to 0.5. `float = 0.5`
-- `filter`: `Optional[Dict[str, str]] = None`
-- `kwargs`: `Any`
-
-Returns docs selected using the maximal marginal relevance(MMR).
-Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents.
-
-Similarly, `max_marginal_relevance_search_by_vector()` function returns docs most similar to the embedding passed to the function using MMR. instead of a string query you need to pass the embedding to be searched for. 
-
-```python
-result = docsearch.max_marginal_relevance_search(
-        query="text"
-    )
-result_texts = [doc.page_content for doc in result]
-print(result_texts)
-
-## search by vector :
-result = docsearch.max_marginal_relevance_search_by_vector(
-        embeddings.embed_query("text")
-    )
-result_texts = [doc.page_content for doc in result]
-print(result_texts)
-```
-
-##### add_images()
-- `uris` : File path to the image. `List[str]`.
-- `metadatas` : Optional list of metadatas. `(Optional[List[dict]], optional)`
-- `ids` : Optional list of IDs. `(Optional[List[str]], optional)`
-
-Adds images by automatically creating their embeddings and adds them to the vectorstore.
-
-```python
-vec_store.add_images(uris=image_uris) 
-# here image_uris are local fs paths to the images.
-```
-
-

docs/src/integrations/llamaIndex.md

@@ -1,142 +0,0 @@
-# Llama-Index
-![Illustration](../assets/llama-index.jpg)
-
-## Quick start
-You would need to install the integration via `pip install llama-index-vector-stores-lancedb` in order to use it. 
-You can run the below script to try it out :
-```python
-import logging
-import sys
-
-# Uncomment to see debug logs
-# logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
-# logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))
-
-from llama_index.core import SimpleDirectoryReader, Document, StorageContext
-from llama_index.core import VectorStoreIndex
-from llama_index.vector_stores.lancedb import LanceDBVectorStore
-import textwrap
-import openai
-
-openai.api_key = "sk-..."
-
-documents = SimpleDirectoryReader("./data/your-data-dir/").load_data()
-print("Document ID:", documents[0].doc_id, "Document Hash:", documents[0].hash)
-
-## For LanceDB cloud :
-# vector_store = LanceDBVectorStore( 
-#     uri="db://db_name", # your remote DB URI
-#     api_key="sk_..", # lancedb cloud api key
-#     region="your-region" # the region you configured
-#     ...
-# )
-
-vector_store = LanceDBVectorStore(
-    uri="./lancedb", mode="overwrite", query_type="vector"
-)
-storage_context = StorageContext.from_defaults(vector_store=vector_store)
-
-index = VectorStoreIndex.from_documents(
-    documents, storage_context=storage_context
-)
-lance_filter = "metadata.file_name = 'paul_graham_essay.txt' "
-retriever = index.as_retriever(vector_store_kwargs={"where": lance_filter})
-response = retriever.retrieve("What did the author do growing up?")
-```
-
-Checkout Complete example here - [LlamaIndex demo](../notebooks/LlamaIndex_example.ipynb)
-
-### Filtering
-For metadata filtering, you can use a Lance SQL-like string filter as demonstrated in the example above. Additionally, you can also filter using the `MetadataFilters` class from LlamaIndex:
-```python
-from llama_index.core.vector_stores import (
-    MetadataFilters,
-    FilterOperator,
-    FilterCondition,
-    MetadataFilter,
-)
-
-query_filters = MetadataFilters(
-    filters=[
-        MetadataFilter(
-            key="creation_date", operator=FilterOperator.EQ, value="2024-05-23"
-        ),
-        MetadataFilter(
-            key="file_size", value=75040, operator=FilterOperator.GT
-        ),
-    ],
-    condition=FilterCondition.AND,
-)
-```
-
-### Hybrid Search
-For complete documentation, refer [here](https://lancedb.github.io/lancedb/hybrid_search/hybrid_search/). This example uses the `colbert` reranker. Make sure to install necessary dependencies for the reranker you choose.
-```python
-from lancedb.rerankers import ColbertReranker
-
-reranker = ColbertReranker()
-vector_store._add_reranker(reranker)
-
-query_engine = index.as_query_engine(
-    filters=query_filters,
-    vector_store_kwargs={
-        "query_type": "hybrid",
-    }
-)
-
-response = query_engine.query("How much did Viaweb charge per month?")
-```
-
-In the above snippet, you can change/specify query_type again when creating the engine/retriever.
-
-## API reference
-The exhaustive list of parameters for `LanceDBVectorStore` vector store are :  
-- `connection`: Optional, `lancedb.db.LanceDBConnection` connection object to use. If not provided, a new connection will be created.
-- `uri`: Optional[str], the uri of your database. Defaults to `"/tmp/lancedb"`.
-- `table_name` : Optional[str], Name of your table in the database. Defaults to `"vectors"`.
-- `table`: Optional[Any], `lancedb.db.LanceTable` object to be passed. Defaults to `None`. 
-- `vector_column_name`: Optional[Any], Column name to use for vector's in the table. Defaults to `'vector'`.   
-- `doc_id_key`: Optional[str], Column name to use for document id's in the table. Defaults to `'doc_id'`.  
-- `text_key`: Optional[str], Column name to use for text in the table. Defaults to `'text'`.  
-- `api_key`: Optional[str], API key to use for LanceDB cloud database. Defaults to `None`.  
-- `region`: Optional[str], Region to use for LanceDB cloud database. Only for LanceDB Cloud, defaults to `None`.  
-- `nprobes` : Optional[int], Set the number of probes to use. Only applicable if ANN index is created on the table else its ignored. Defaults to `20`.
-- `refine_factor` : Optional[int], Refine the results by reading extra elements and re-ranking them in memory. Defaults to `None`.
-- `reranker`: Optional[Any], The reranker to use for LanceDB.
-        Defaults to `None`.
-- `overfetch_factor`: Optional[int], The factor by which to fetch more results.
-        Defaults to `1`.
-- `mode`: Optional[str], The mode to use for LanceDB.
-            Defaults to `"overwrite"`.
-- `query_type`:Optional[str], The type of query to use for LanceDB.
-            Defaults to `"vector"`.
-
-
-### Methods 
-
-- __from_table(cls, table: lancedb.db.LanceTable) -> `LanceDBVectorStore`__ : (class method) Creates instance from lancedb table. 
-
-- **_add_reranker(self, reranker: lancedb.rerankers.Reranker) -> `None`** : Add a reranker to an existing vector store. 
-    - Usage :
-        ```python
-        from lancedb.rerankers import ColbertReranker
-        reranker = ColbertReranker()
-        vector_store._add_reranker(reranker)
-        ```               
-- **_table_exists(self, tbl_name: `Optional[str]` = `None`) -> `bool`** : Returns `True` if `tbl_name` exists in database.
-- __create_index(  
-  self, scalar: `Optional[bool]` = False, col_name: `Optional[str]` = None, num_partitions: `Optional[int]` = 256, num_sub_vectors: `Optional[int]` = 96, index_cache_size: `Optional[int]` = None, metric: `Optional[str]` = "L2",  
-) -> `None`__ : Creates a scalar(for non-vector cols) or a vector index on a table.
-        Make sure your vector column has enough data before creating an index on it.
-
-- __add(self, nodes: `List[BaseNode]`, **add_kwargs: `Any`, ) -> `List[str]`__ :
-adds Nodes to the table
-
-- **delete(self, ref_doc_id: `str`) -> `None`**: Delete nodes using with node_ids.
-- **delete_nodes(self, node_ids: `List[str]`) -> `None`** : Delete nodes using with node_ids.
-- __query(
-        self,
-        query: `VectorStoreQuery`,
-        **kwargs: `Any`,
-    ) -> `VectorStoreQueryResult`__:
-        Query index(`VectorStoreIndex`) for top k most similar nodes. Accepts llamaIndex `VectorStoreQuery` object.

docs/src/js/.nojekyll

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

docs/src/js/README.md

@@ -1,83 +0,0 @@
-@lancedb/lancedb / [Exports](modules.md)
-
-# LanceDB JavaScript SDK
-
-A JavaScript library for [LanceDB](https://github.com/lancedb/lancedb).
-
-## Installation
-
-```bash
-npm install @lancedb/lancedb
-```
-
-This will download the appropriate native library for your platform. We currently
-support:
-
-- Linux (x86_64 and aarch64)
-- MacOS (Intel and ARM/M1/M2)
-- Windows (x86_64 only)
-
-We do not yet support musl-based Linux (such as Alpine Linux) or aarch64 Windows.
-
-## Usage
-
-### Basic Example
-
-```javascript
-import * as lancedb from "@lancedb/lancedb";
-const db = await lancedb.connect("data/sample-lancedb");
-const table = await db.createTable("my_table", [
-  { id: 1, vector: [0.1, 1.0], item: "foo", price: 10.0 },
-  { id: 2, vector: [3.9, 0.5], item: "bar", price: 20.0 },
-]);
-const results = await table.vectorSearch([0.1, 0.3]).limit(20).toArray();
-console.log(results);
-```
-
-The [quickstart](../basic.md) contains a more complete example.
-
-## Development
-
-```sh
-npm run build
-npm run test
-```
-
-### Running lint / format
-
-LanceDb uses eslint for linting. VSCode does not need any plugins to use eslint. However, it
-may need some additional configuration. Make sure that eslint.experimental.useFlatConfig is
-set to true. Also, if your vscode root folder is the repo root then you will need to set
-the eslint.workingDirectories to ["nodejs"]. To manually lint your code you can run:
-
-```sh
-npm run lint
-```
-
-LanceDb uses prettier for formatting. If you are using VSCode you will need to install the
-"Prettier - Code formatter" extension. You should then configure it to be the default formatter
-for typescript and you should enable format on save. To manually check your code's format you
-can run:
-
-```sh
-npm run chkformat
-```
-
-If you need to manually format your code you can run:
-
-```sh
-npx prettier --write .
-```
-
-### Generating docs
-
-```sh
-npm run docs
-
-cd ../docs
-# Asssume the virtual environment was created
-# python3 -m venv venv
-# pip install -r requirements.txt
-. ./venv/bin/activate
-mkdocs build
-```

docs/src/js/classes/Connection.md

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

docs/src/js/classes/Index.md

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

docs/src/js/classes/MakeArrowTableOptions.md

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

docs/src/js/classes/Query.md

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

docs/src/js/classes/QueryBase.md

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

docs/src/js/classes/RecordBatchIterator.md

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

docs/src/js/classes/Table.md

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

docs/src/js/classes/VectorColumnOptions.md

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

docs/src/js/classes/VectorQuery.md

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

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

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

docs/src/js/enums/WriteMode.md

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

docs/src/js/interfaces/AddColumnsSql.md

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

docs/src/js/interfaces/AddDataOptions.md

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

docs/src/js/interfaces/ColumnAlteration.md

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

docs/src/js/interfaces/ConnectionOptions.md

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

docs/src/js/interfaces/CreateTableOptions.md

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

docs/src/js/interfaces/ExecutableQuery.md

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

docs/src/js/interfaces/IndexConfig.md

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

docs/src/js/interfaces/IndexOptions.md

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

docs/src/js/interfaces/IvfPqOptions.md

@@ -1,144 +0,0 @@
-[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / IvfPqOptions
-
-# Interface: IvfPqOptions
-
-Options to create an `IVF_PQ` index
-
-## Table of contents
-
-### Properties
-
-- [distanceType](IvfPqOptions.md#distancetype)
-- [maxIterations](IvfPqOptions.md#maxiterations)
-- [numPartitions](IvfPqOptions.md#numpartitions)
-- [numSubVectors](IvfPqOptions.md#numsubvectors)
-- [sampleRate](IvfPqOptions.md#samplerate)
-
-## Properties
-
-### distanceType
-
-• `Optional` **distanceType**: ``"l2"`` \| ``"cosine"`` \| ``"dot"``
-
-Distance type to use to build the index.
-
-Default value is "l2".
-
-This is used when training the index to calculate the IVF partitions
-(vectors are grouped in partitions with similar vectors according to this
-distance type) and to calculate a subvector's code during quantization.
-
-The distance type used to train an index MUST match the distance type used
-to search the index.  Failure to do so will yield inaccurate results.
-
-The following distance types are available:
-
-"l2" - Euclidean distance. This is a very common distance metric that
-accounts for both magnitude and direction when determining the distance
-between vectors. L2 distance has a range of [0, ∞).
-
-"cosine" - Cosine distance.  Cosine distance is a distance metric
-calculated from the cosine similarity between two vectors. Cosine
-similarity is a measure of similarity between two non-zero vectors of an
-inner product space. It is defined to equal the cosine of the angle
-between them.  Unlike L2, the cosine distance is not affected by the
-magnitude of the vectors.  Cosine distance has a range of [0, 2].
-
-Note: the cosine distance is undefined when one (or both) of the vectors
-are all zeros (there is no direction).  These vectors are invalid and may
-never be returned from a vector search.
-
-"dot" - Dot product. Dot distance is the dot product of two vectors. Dot
-distance has a range of (-∞, ∞). If the vectors are normalized (i.e. their
-L2 norm is 1), then dot distance is equivalent to the cosine distance.
-
-#### Defined in
-
-[indices.ts:83](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/indices.ts#L83)
-
-___
-
-### maxIterations
-
-• `Optional` **maxIterations**: `number`
-
-Max iteration to train IVF kmeans.
-
-When training an IVF PQ index we use kmeans to calculate the partitions.  This parameter
-controls how many iterations of kmeans to run.
-
-Increasing this might improve the quality of the index but in most cases these extra
-iterations have diminishing returns.
-
-The default value is 50.
-
-#### Defined in
-
-[indices.ts:96](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/indices.ts#L96)
-
-___
-
-### numPartitions
-
-• `Optional` **numPartitions**: `number`
-
-The number of IVF partitions to create.
-
-This value should generally scale with the number of rows in the dataset.
-By default the number of partitions is the square root of the number of
-rows.
-
-If this value is too large then the first part of the search (picking the
-right partition) will be slow.  If this value is too small then the second
-part of the search (searching within a partition) will be slow.
-
-#### Defined in
-
-[indices.ts:32](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/indices.ts#L32)
-
-___
-
-### numSubVectors
-
-• `Optional` **numSubVectors**: `number`
-
-Number of sub-vectors of PQ.
-
-This value controls how much the vector is compressed during the quantization step.
-The more sub vectors there are the less the vector is compressed.  The default is
-the dimension of the vector divided by 16.  If the dimension is not evenly divisible
-by 16 we use the dimension divded by 8.
-
-The above two cases are highly preferred.  Having 8 or 16 values per subvector allows
-us to use efficient SIMD instructions.
-
-If the dimension is not visible by 8 then we use 1 subvector.  This is not ideal and
-will likely result in poor performance.
-
-#### Defined in
-
-[indices.ts:48](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/indices.ts#L48)
-
-___
-
-### sampleRate
-
-• `Optional` **sampleRate**: `number`
-
-The number of vectors, per partition, to sample when training IVF kmeans.
-
-When an IVF PQ index is trained, we need to calculate partitions.  These are groups
-of vectors that are similar to each other.  To do this we use an algorithm called kmeans.
-
-Running kmeans on a large dataset can be slow.  To speed this up we run kmeans on a
-random sample of the data.  This parameter controls the size of the sample.  The total
-number of vectors used to train the index is `sample_rate * num_partitions`.
-
-Increasing this value might improve the quality of the index but in most cases the
-default should be sufficient.
-
-The default value is 256.
-
-#### Defined in
-
-[indices.ts:113](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/indices.ts#L113)