Bump version: 0.12.0-beta.0 → 0.12.0

PR fixes #1514

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.4.20"
+current_version = "0.8.0"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

.github/workflows/build_linux_wheel/action.yml

@@ -46,6 +46,7 @@ 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 }}
         args: ${{ inputs.args }}

.github/workflows/build_mac_wheel/action.yml

@@ -21,5 +21,6 @@ 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

@@ -26,6 +26,7 @@ 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/docs_test.yml

@@ -24,7 +24,7 @@ env:
 jobs:
   test-python:
     name: Test doc python code
-    runs-on: "buildjet-8vcpu-ubuntu-2204"
+    runs-on: "warp-ubuntu-latest-x64-4x"
     steps:
     - name: Checkout
       uses: actions/checkout@v4
@@ -56,7 +56,7 @@ jobs:
         for d in *; do cd "$d"; echo "$d".py; python "$d".py; cd ..; done
   test-node:
     name: Test doc nodejs code
-    runs-on: "buildjet-8vcpu-ubuntu-2204"
+    runs-on: "warp-ubuntu-latest-x64-4x"
     timeout-minutes: 60
     strategy:
       fail-fast: false

.github/workflows/java.yml

@@ -0,0 +1,113 @@
+name: Build and Run Java JNI Tests
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - java/**
+  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-java-11:
+    runs-on: ubuntu-22.04
+    name: ubuntu-22.04 + Java 11
+    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 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
+  linux-build-java-17:
+    runs-on: ubuntu-22.04
+    name: ubuntu-22.04 + Java 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" >> $GITHUB_ENV
+      - name: Java Style Check
+        run: mvn checkstyle:check
+      # Disable because of issues in lancedb rust core code
+      # - name: Rust Clippy
+      #   working-directory: java/core/lancedb-jni
+      #   run: cargo clippy --all-targets -- -D warnings
+      - name: Running tests with Java 17
+        run: |
+          export JAVA_TOOL_OPTIONS="$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

@@ -94,6 +94,6 @@ jobs:
           branch: ${{ github.ref }}
           tags: true
       - uses: ./.github/workflows/update_package_lock
-        if: ${{ inputs.dry_run }} == "false"
+        if: ${{ !inputs.dry_run && inputs.other }}
         with:
           github_token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/npm-publish.yml

@@ -3,10 +3,11 @@ name: NPM Publish
 on:
   push:
     tags:
-      - 'v*'
+      - "v*"
 
 jobs:
   node:
+    name: vectordb Typescript
     runs-on: ubuntu-latest
     # Only runs on tags that matches the make-release action
     if: startsWith(github.ref, 'refs/tags/v')
@@ -39,6 +40,7 @@ jobs:
             node/vectordb-*.tgz
 
   node-macos:
+    name: vectordb ${{ matrix.config.arch }}
     strategy:
       matrix:
         config:
@@ -69,6 +71,7 @@ jobs:
             node/dist/lancedb-vectordb-darwin*.tgz
 
   nodejs-macos:
+    name: lancedb ${{ matrix.config.arch }}
     strategy:
       matrix:
         config:
@@ -99,7 +102,7 @@ jobs:
             nodejs/dist/*.node
 
   node-linux:
-    name: node-linux (${{ matrix.config.arch}}-unknown-linux-gnu
+    name: vectordb (${{ 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')
@@ -111,12 +114,11 @@ jobs:
             runner: ubuntu-latest
           - arch: aarch64
             # For successful fat LTO builds, we need a large runner to avoid OOM errors.
-            runner: buildjet-16vcpu-ubuntu-2204-arm
+            runner: warp-ubuntu-latest-arm64-4x
     steps:
       - name: Checkout
         uses: actions/checkout@v4
-      # Buildjet aarch64 runners have only 1.5 GB RAM per core, vs 3.5 GB per core for
+      # To avoid OOM errors on ARM, we create a swap file.
-      # x86_64 runners. To avoid OOM errors on ARM, we create a swap file.
       - name: Configure aarch64 build
         if: ${{ matrix.config.arch == 'aarch64' }}
         run: |
@@ -140,7 +142,7 @@ jobs:
             node/dist/lancedb-vectordb-linux*.tgz
 
   nodejs-linux:
-    name: nodejs-linux (${{ matrix.config.arch}}-unknown-linux-gnu
+    name: lancedb (${{ 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')
@@ -191,6 +193,7 @@ jobs:
             !nodejs/dist/*.node
 
   node-windows:
+    name: vectordb ${{ matrix.target }}
     runs-on: windows-2022
     # Only runs on tags that matches the make-release action
     if: startsWith(github.ref, 'refs/tags/v')
@@ -224,6 +227,7 @@ jobs:
             node/dist/lancedb-vectordb-win32*.tgz
 
   nodejs-windows:
+    name: lancedb ${{ matrix.target }}
     runs-on: windows-2022
     # Only runs on tags that matches the make-release action
     if: startsWith(github.ref, 'refs/tags/v')
@@ -257,6 +261,7 @@ jobs:
             nodejs/dist/*.node
 
   release:
+    name: vectordb NPM Publish
     needs: [node, node-macos, node-linux, node-windows]
     runs-on: ubuntu-latest
     # Only runs on tags that matches the make-release action
@@ -285,8 +290,18 @@ jobs:
           for filename in *.tgz; do
             npm publish $PUBLISH_ARGS $filename
           done
+      - name: Notify Slack Action
+        uses: ravsamhq/notify-slack-action@2.3.0
+        if: ${{ always() }}
+        with:
+          status: ${{ job.status }}
+          notify_when: "failure"
+          notification_title: "{workflow} is failing"
+        env:
+          SLACK_WEBHOOK_URL: ${{ secrets.ACTION_MONITORING_SLACK }}
 
   release-nodejs:
+    name: lancedb NPM Publish
     needs: [nodejs-macos, nodejs-linux, nodejs-windows]
     runs-on: ubuntu-latest
     # Only runs on tags that matches the make-release action
@@ -323,7 +338,7 @@ jobs:
       - 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 
+        # 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`.
@@ -334,6 +349,15 @@ jobs:
           else
             npm publish --access public
           fi
+      - name: Notify Slack Action
+        uses: ravsamhq/notify-slack-action@2.3.0
+        if: ${{ always() }}
+        with:
+          status: ${{ job.status }}
+          notify_when: "failure"
+          notification_title: "{workflow} is failing"
+        env:
+          SLACK_WEBHOOK_URL: ${{ secrets.ACTION_MONITORING_SLACK }}
 
   update-package-lock:
     needs: [release]
@@ -368,7 +392,7 @@ jobs:
       - uses: ./.github/workflows/update_package_lock_nodejs
         with:
           github_token: ${{ secrets.GITHUB_TOKEN }}
-  
+
   gh-release:
     runs-on: ubuntu-latest
     permissions:

.github/workflows/python.yml

@@ -33,11 +33,11 @@ jobs:
           python-version: "3.11"
       - name: Install ruff
         run: |
-          pip install ruff==0.2.2
+          pip install ruff==0.5.4
       - name: Format check
         run: ruff format --check .
       - name: Lint
-        run: ruff .
+        run: ruff check .
   doctest:
     name: "Doctest"
     timeout-minutes: 30
@@ -65,7 +65,7 @@ jobs:
           workspaces: python
       - name: Install
         run: |
-          pip install -e .[tests,dev,embeddings]
+          pip install --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests,dev,embeddings]
           pip install tantivy
           pip install mlx
       - name: Doctest
@@ -189,7 +189,7 @@ jobs:
       - name: Install lancedb
         run: |
           pip install "pydantic<2"
-          pip install -e .[tests]
+          pip install --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests]
           pip install tantivy
       - name: Run tests
         run: pytest -m "not slow and not s3_test" -x -v --durations=30 python/tests

.github/workflows/run_tests/action.yml

@@ -15,7 +15,7 @@ runs:
     - name: Install lancedb
       shell: bash
       run: |
-        pip3 install $(ls target/wheels/lancedb-*.whl)[tests,dev]
+        pip3 install --extra-index-url https://pypi.fury.io/lancedb/ $(ls target/wheels/lancedb-*.whl)[tests,dev]
     - name: Setup localstack for integration tests
       if: ${{ inputs.integration == 'true' }}
       shell: bash

.github/workflows/rust.yml

@@ -53,7 +53,10 @@ jobs:
       run: cargo clippy --all --all-features -- -D warnings
   linux:
     timeout-minutes: 30
-    runs-on: ubuntu-22.04
+    # To build all features, we need more disk space than is available
+    # on the GitHub-provided runner. This is mostly due to the the
+    # sentence-transformers feature.
+    runs-on: warp-ubuntu-latest-x64-4x
     defaults:
       run:
         shell: bash
@@ -131,4 +134,3 @@ jobs:
           $env:VCPKG_ROOT = $env:VCPKG_INSTALLATION_ROOT
           cargo build
           cargo test
-  

.github/workflows/upload_wheel/action.yml

@@ -27,7 +27,6 @@ runs:
         echo "repo=pypi" >> $GITHUB_OUTPUT
       fi
   - name: Publish to PyPI
-    working-directory: python
     shell: bash
     env:
       FURY_TOKEN: ${{ inputs.fury_token }}

.gitignore

@@ -4,6 +4,7 @@
 **/__pycache__
 .DS_Store
 venv
+.venv
 
 .vscode
 .zed

.pre-commit-config.yaml

@@ -14,8 +14,8 @@ repos:
   hooks:
     - id: local-biome-check
       name: biome check
-      entry: npx 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/.*
+      exclude: nodejs/lancedb/native.d.ts|nodejs/dist/.*|nodejs/examples/.*

Cargo.toml

@@ -1,5 +1,11 @@
 [workspace]
-members = ["rust/ffi/node", "rust/lancedb", "nodejs", "python"]
+members = [
+    "rust/ffi/node",
+    "rust/lancedb",
+    "nodejs",
+    "python",
+    "java/core/lancedb-jni",
+]
 # Python package needs to be built by maturin.
 exclude = ["python"]
 resolver = "2"
@@ -14,27 +20,30 @@ keywords = ["lancedb", "lance", "database", "vector", "search"]
 categories = ["database-implementations"]
 
 [workspace.dependencies]
-lance = { "version" = "=0.11.0", "features" = ["dynamodb"] }
+lance = { "version" = "=0.16.0", "features" = ["dynamodb"] }
-lance-index = { "version" = "=0.11.0" }
+lance-index = { "version" = "=0.16.0" }
-lance-linalg = { "version" = "=0.11.0" }
+lance-linalg = { "version" = "=0.16.0" }
-lance-testing = { "version" = "=0.11.0" }
+lance-testing = { "version" = "=0.16.0" }
+lance-datafusion = { "version" = "=0.16.0" }
+lance-encoding = { "version" = "=0.16.0" }
 # Note that this one does not include pyarrow
-arrow = { version = "51.0", optional = false }
+arrow = { version = "52.2", optional = false }
-arrow-array = "51.0"
+arrow-array = "52.2"
-arrow-data = "51.0"
+arrow-data = "52.2"
-arrow-ipc = "51.0"
+arrow-ipc = "52.2"
-arrow-ord = "51.0"
+arrow-ord = "52.2"
-arrow-schema = "51.0"
+arrow-schema = "52.2"
-arrow-arith = "51.0"
+arrow-arith = "52.2"
-arrow-cast = "51.0"
+arrow-cast = "52.2"
 async-trait = "0"
 chrono = "0.4.35"
+datafusion-physical-plan = "40.0"
 half = { "version" = "=2.4.1", default-features = false, features = [
     "num-traits",
 ] }
 futures = "0"
 log = "0.4"
-object_store = "0.9.0"
+object_store = "0.10.1"
 pin-project = "1.0.7"
 snafu = "0.7.4"
 url = "2"

README.md

@@ -7,8 +7,8 @@
 
 <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/) 
+[![Blog](https://img.shields.io/badge/Blog-12100E?style=for-the-badge&logoColor=white)](https://blog.lancedb.com/)
-[![Discord](https://img.shields.io/badge/Discord-%235865F2.svg?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/zMM32dvNtd) 
+[![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)
 
 </p>
@@ -44,26 +44,24 @@ LanceDB's core is written in Rust 🦀 and is built using <a href="https://githu
 
 **Javascript**
 ```shell
-npm install vectordb
+npm install @lancedb/lancedb
 ```
 
 ```javascript
-const lancedb = require('vectordb');
+import * as lancedb from "@lancedb/lancedb";
-const db = await lancedb.connect('data/sample-lancedb');
 
-const table = await db.createTable({
+const db = await lancedb.connect("data/sample-lancedb");
-  name: 'vectors',
+const table = await db.createTable("vectors", [
-  data:  [
+	{ id: 1, vector: [0.1, 0.2], item: "foo", price: 10 },
-    { id: 1, vector: [0.1, 0.2], item: "foo", price: 10 },
+	{ id: 2, vector: [1.1, 1.2], item: "bar", price: 50 },
-    { id: 2, vector: [1.1, 1.2], item: "bar", price: 50 }
+], {mode: 'overwrite'});
-  ]
-})
 
-const query = table.search([0.1, 0.3]).limit(2);
+
-const results = await query.execute();
+const query = table.vectorSearch([0.1, 0.3]).limit(2);
+const results = await query.toArray();
 
 // You can also search for rows by specific criteria without involving a vector search.
-const rowsByCriteria = await table.search(undefined).where("price >= 10").execute();
+const rowsByCriteria = await table.query().where("price >= 10").toArray();
 ```
 
 **Python**
@@ -83,5 +81,5 @@ result = table.search([100, 100]).limit(2).to_pandas()
 ```
 
 ## Blogs, Tutorials & Videos
-* 📈 <a href="https://blog.eto.ai/benchmarking-random-access-in-lance-ed690757a826">2000x better performance with Lance over Parquet</a>
+* 📈 <a href="https://blog.lancedb.com/benchmarking-random-access-in-lance/">2000x better performance with Lance over Parquet</a>
 * 🤖 <a href="https://github.com/lancedb/lancedb/blob/main/docs/src/notebooks/youtube_transcript_search.ipynb">Build a question and answer bot with LanceDB</a>

ci/build_linux_artifacts.sh

@@ -18,4 +18,4 @@ docker run \
     -v $(pwd):/io -w /io \
     --memory-swap=-1 \
     lancedb-node-manylinux \
-    bash ci/manylinux_node/build.sh $ARCH
+    bash ci/manylinux_node/build_vectordb.sh $ARCH

ci/build_linux_artifacts_nodejs.sh

@@ -4,9 +4,9 @@ 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
+pushd ci/manylinux_node
 docker build \
-    -t lancedb-nodejs-manylinux \
+    -t lancedb-node-manylinux-$ARCH \
     --build-arg="ARCH=$ARCH" \
     --build-arg="DOCKER_USER=$(id -u)" \
     --progress=plain \
@@ -17,5 +17,5 @@ popd
 docker run \
     -v $(pwd):/io -w /io \
     --memory-swap=-1 \
-    lancedb-nodejs-manylinux \
+    lancedb-node-manylinux-$ARCH \
-    bash ci/manylinux_nodejs/build.sh $ARCH
+    bash ci/manylinux_node/build_lancedb.sh $ARCH

ci/manylinux_node/Dockerfile

@@ -4,7 +4,7 @@
 # range of linux distributions.
 ARG ARCH=x86_64
 
-FROM quay.io/pypa/manylinux2014_${ARCH}
+FROM quay.io/pypa/manylinux_2_28_${ARCH}
 
 ARG ARCH=x86_64
 ARG DOCKER_USER=default_user
@@ -18,8 +18,8 @@ COPY install_protobuf.sh install_protobuf.sh
 RUN ./install_protobuf.sh ${ARCH}
 
 ENV DOCKER_USER=${DOCKER_USER}
-# Create a group and user
+# Create a group and user, but only if it doesn't exist
-RUN echo ${ARCH} && adduser --user-group --create-home --uid ${DOCKER_USER} build_user
+RUN echo ${ARCH} && id -u ${DOCKER_USER} >/dev/null 2>&1 || adduser --user-group --create-home --uid ${DOCKER_USER} build_user
 
 # We switch to the user to install Rust and Node, since those like to be 
 # installed at the user level.

ci/manylinux_node/install_openssl.sh

@@ -6,7 +6,7 @@
 # /usr/bin/ld: failed to set dynamic section sizes: Bad value
 set -e
 
-git clone -b OpenSSL_1_1_1u \
+git clone -b OpenSSL_1_1_1v \
     --single-branch \
     https://github.com/openssl/openssl.git
 

ci/manylinux_node/prepare_manylinux_node.sh

@@ -8,7 +8,7 @@ install_node() {
 
     source "$HOME"/.bashrc
 
-    nvm install --no-progress 16
+    nvm install --no-progress 18
 }
 
 install_rust() {

ci/manylinux_nodejs/Dockerfile

@@ -1,31 +0,0 @@
-# Many linux dockerfile with Rust, Node, and Lance dependencies installed.
-# This container allows building the node modules native libraries in an
-# environment with a very old glibc, so that we are compatible with a wide
-# range of linux distributions.
-ARG ARCH=x86_64
-
-FROM quay.io/pypa/manylinux2014_${ARCH}
-
-ARG ARCH=x86_64
-ARG DOCKER_USER=default_user
-
-# Install static openssl
-COPY install_openssl.sh install_openssl.sh
-RUN ./install_openssl.sh ${ARCH} > /dev/null
-
-# Protobuf is also installed as root.
-COPY install_protobuf.sh install_protobuf.sh
-RUN ./install_protobuf.sh ${ARCH}
-
-ENV DOCKER_USER=${DOCKER_USER}
-# Create a group and user
-RUN echo ${ARCH} && adduser --user-group --create-home --uid ${DOCKER_USER} build_user
-
-# We switch to the user to install Rust and Node, since those like to be
-# installed at the user level.
-USER ${DOCKER_USER}
-
-COPY prepare_manylinux_node.sh prepare_manylinux_node.sh
-RUN cp /prepare_manylinux_node.sh $HOME/ && \
-    cd $HOME && \
-    ./prepare_manylinux_node.sh ${ARCH}

ci/manylinux_nodejs/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

docs/mkdocs.yml

@@ -57,6 +57,8 @@ plugins:
             - https://arrow.apache.org/docs/objects.inv
             - https://pandas.pydata.org/docs/objects.inv
   - mkdocs-jupyter
+  - render_swagger:
+      allow_arbitrary_locations : true
 
 markdown_extensions:
   - admonition
@@ -98,14 +100,21 @@ nav:
               - Quickstart: reranking/index.md
               - Cohere Reranker: reranking/cohere.md
               - Linear Combination Reranker: reranking/linear_combination.md
+              - Reciprocal Rank Fusion Reranker: reranking/rrf.md
               - Cross Encoder Reranker: reranking/cross_encoder.md
               - ColBERT Reranker: reranking/colbert.md
+              - Jina Reranker: reranking/jina.md
               - OpenAI Reranker: reranking/openai.md
               - 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
+          - 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
@@ -120,8 +129,11 @@ nav:
           - 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 🦙: https://docs.llamaindex.ai/en/stable/examples/vector_stores/LanceDBIndexDemo/
+          - LlamaIndex 🦙:
+            - LlamaIndex docs: integrations/llamaIndex.md
+            - LlamaIndex demo: notebooks/llamaIndex_demo.ipynb
           - Pydantic: python/pydantic.md
           - Voxel51: integrations/voxel51.md
           - PromptTools: integrations/prompttools.md
@@ -129,12 +141,15 @@ nav:
           - Overview: examples/index.md
           - 🐍 Python:
               - Overview: examples/examples_python.md
-              - YouTube Transcript Search: notebooks/youtube_transcript_search.ipynb
+              - Build From Scratch: examples/python_examples/build_from_scratch.md
-              - Documentation QA Bot using LangChain: notebooks/code_qa_bot.ipynb
+              - Multimodal: examples/python_examples/multimodal.md
-              - Multimodal search using CLIP: notebooks/multimodal_search.ipynb
+              - Rag: examples/python_examples/rag.md
-              - Example - Calculate CLIP Embeddings with Roboflow Inference: examples/image_embeddings_roboflow.md
+              - Miscellaneous: 
-              - Serverless QA Bot with S3 and Lambda: examples/serverless_lancedb_with_s3_and_lambda.md
+                  - YouTube Transcript Search: notebooks/youtube_transcript_search.ipynb
-              - Serverless QA Bot with Modal: examples/serverless_qa_bot_with_modal_and_langchain.md
+                  - 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:
               - Overview: examples/examples_js.md
               - Serverless Website Chatbot: examples/serverless_website_chatbot.md
@@ -146,13 +161,14 @@ nav:
       - ⚙️ API reference:
           - 🐍 Python: python/python.md
           - 👾 JavaScript (vectordb): javascript/modules.md
-          - 👾 JavaScript (lancedb): javascript/modules.md
+          - 👾 JavaScript (lancedb): js/globals.md
           - 🦀 Rust: https://docs.rs/lancedb/latest/lancedb/
       - ☁️ LanceDB Cloud:
           - Overview: cloud/index.md
           - API reference:
               - 🐍 Python: python/saas-python.md
-              - 👾 JavaScript: javascript/saas-modules.md
+              - 👾 JavaScript: javascript/modules.md
+              - REST API: cloud/rest.md
 
   - Quick start: basic.md
   - Concepts:
@@ -173,14 +189,21 @@ nav:
           - Quickstart: reranking/index.md
           - Cohere Reranker: reranking/cohere.md
           - Linear Combination Reranker: reranking/linear_combination.md
+          - Reciprocal Rank Fusion Reranker: reranking/rrf.md
           - Cross Encoder Reranker: reranking/cross_encoder.md
           - ColBERT Reranker: reranking/colbert.md
+          - Jina Reranker: reranking/jina.md
           - OpenAI Reranker: reranking/openai.md
           - 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
+      - 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
@@ -193,33 +216,44 @@ nav:
       - Pandas and PyArrow: python/pandas_and_pyarrow.md
       - Polars: python/polars_arrow.md
       - DuckDB: python/duckdb.md
-      - LangChain 🦜️🔗↗: https://python.langchain.com/docs/integrations/vectorstores/lancedb
+      - LangChain 🦜️🔗↗: integrations/langchain.md
       - LangChain.js 🦜️🔗↗: https://js.langchain.com/docs/integrations/vectorstores/lancedb
-      - LlamaIndex 🦙↗: https://gpt-index.readthedocs.io/en/latest/examples/vector_stores/LanceDBIndexDemo.html
+      - 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
+      - 🐍 Python:
-      - Documentation QA Bot using LangChain: notebooks/code_qa_bot.ipynb
+          - Overview: examples/examples_python.md
-      - Multimodal search using CLIP: notebooks/multimodal_search.ipynb
+          - Build From Scratch: examples/python_examples/build_from_scratch.md
-      - Serverless QA Bot with S3 and Lambda: examples/serverless_lancedb_with_s3_and_lambda.md
+          - Multimodal: examples/python_examples/multimodal.md
-      - Serverless QA Bot with Modal: examples/serverless_qa_bot_with_modal_and_langchain.md
+          - Rag: examples/python_examples/rag.md
-      - YouTube Transcript Search (JS): examples/youtube_transcript_bot_with_nodejs.md
+          - Miscellaneous: 
-      - Serverless Chatbot from any website: examples/serverless_website_chatbot.md
+              - YouTube Transcript Search: notebooks/youtube_transcript_search.ipynb
-      - TransformersJS Embedding Search: examples/transformerjs_embedding_search_nodejs.md
+              - 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:
+          - 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
   - API reference:
       - Overview: api_reference.md
       - Python: python/python.md
       - Javascript (vectordb): javascript/modules.md
-      - Javascript (lancedb): js/modules.md
+      - Javascript (lancedb): js/globals.md
       - Rust: https://docs.rs/lancedb/latest/lancedb/index.html
   - LanceDB Cloud:
       - Overview: cloud/index.md
       - API reference:
           - 🐍 Python: python/saas-python.md
-          - 👾 JavaScript: javascript/saas-modules.md
+          - 👾 JavaScript: javascript/modules.md
+          - REST API: cloud/rest.md
 
 extra_css:
   - styles/global.css

docs/openapi.yml

@@ -0,0 +1,487 @@
+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

@@ -2,4 +2,5 @@ mkdocs==1.5.3
 mkdocs-jupyter==0.24.1
 mkdocs-material==9.5.3
 mkdocstrings[python]==0.20.0
-pydantic
+mkdocs-render-swagger-plugin
+pydantic

docs/src/ann_indexes.md

@@ -38,13 +38,27 @@ Lance supports `IVF_PQ` index type by default.
     tbl.create_index(num_partitions=256, num_sub_vectors=96)
     ```
 
-=== "Typescript"
+=== "TypeScript"
 
-    ```typescript
+    === "@lancedb/lancedb"
-    --8<--- "docs/src/ann_indexes.ts:import"
 
-    --8<-- "docs/src/ann_indexes.ts:ingest"
+        Creating indexes is done via the [lancedb.Table.createIndex](../js/classes/Table.md/#createIndex) method.
-    ```
+
+        ```typescript
+        --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"
 
@@ -91,27 +105,27 @@ 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"
 
-     <!-- 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:
 
@@ -150,11 +164,19 @@ There are a couple of parameters that can be used to fine-tune the search:
     1  [0.48587373, 0.269207, 0.15095535, 0.65531915,...  item 3953  108.393867
     ```
 
-=== "Typescript"
+=== "TypeScript"
 
-    ```typescript
+    === "@lancedb/lancedb"
-    --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"
 
@@ -172,15 +194,23 @@ 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"
 
-     ```javascript
+    === "@lancedb/lancedb"
-     --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)
 
@@ -188,23 +218,31 @@ 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"
 
-     ```typescript
+    === "@lancedb/lancedb"
-     --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
 

docs/src/api_reference.md

@@ -4,5 +4,5 @@ The API reference for the LanceDB client SDKs are available at the following loc
 
 - [Python](python/python.md)
 - [JavaScript (legacy vectordb package)](javascript/modules.md)
-- [JavaScript (newer @lancedb/lancedb package)](js/modules.md)
+- [JavaScript (newer @lancedb/lancedb package)](js/globals.md)
 - [Rust](https://docs.rs/lancedb/latest/lancedb/index.html)

docs/src/assets/colab.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" width="117" height="20"><linearGradient id="b" x2="0" y2="100%"><stop offset="0" stop-color="#bbb" stop-opacity=".1"/><stop offset="1" stop-opacity=".1"/></linearGradient><clipPath id="a"><rect width="117" height="20" rx="3" fill="#fff"/></clipPath><g clip-path="url(#a)"><path fill="#555" d="M0 0h30v20H0z"/><path fill="#007ec6" d="M30 0h87v20H30z"/><path fill="url(#b)" d="M0 0h117v20H0z"/></g><g fill="#fff" text-anchor="middle" font-family="DejaVu Sans,Verdana,Geneva,sans-serif" font-size="110"><svg x="4px" y="0px" width="22px" height="20px" viewBox="-2 0 28 24" style="background-color: #fff;border-radius: 1px;"><path style="fill:#e8710a;" d="M1.977,16.77c-2.667-2.277-2.605-7.079,0-9.357C2.919,8.057,3.522,9.075,4.49,9.691c-1.152,1.6-1.146,3.201-0.004,4.803C3.522,15.111,2.918,16.126,1.977,16.77z"/><path style="fill:#f9ab00;" d="M12.257,17.114c-1.767-1.633-2.485-3.658-2.118-6.02c0.451-2.91,2.139-4.893,4.946-5.678c2.565-0.718,4.964-0.217,6.878,1.819c-0.884,0.743-1.707,1.547-2.434,2.446C18.488,8.827,17.319,8.435,16,8.856c-2.404,0.767-3.046,3.241-1.494,5.644c-0.241,0.275-0.493,0.541-0.721,0.826C13.295,15.939,12.511,16.3,12.257,17.114z"/><path style="fill:#e8710a;" d="M19.529,9.682c0.727-0.899,1.55-1.703,2.434-2.446c2.703,2.783,2.701,7.031-0.005,9.764c-2.648,2.674-6.936,2.725-9.701,0.115c0.254-0.814,1.038-1.175,1.528-1.788c0.228-0.285,0.48-0.552,0.721-0.826c1.053,0.916,2.254,1.268,3.6,0.83C20.502,14.551,21.151,11.927,19.529,9.682z"/><path style="fill:#f9ab00;" d="M4.49,9.691C3.522,9.075,2.919,8.057,1.977,7.413c2.209-2.398,5.721-2.942,8.476-1.355c0.555,0.32,0.719,0.606,0.285,1.128c-0.157,0.188-0.258,0.422-0.391,0.631c-0.299,0.47-0.509,1.067-0.929,1.371C8.933,9.539,8.523,8.847,8.021,8.746C6.673,8.475,5.509,8.787,4.49,9.691z"/><path style="fill:#f9ab00;" d="M1.977,16.77c0.941-0.644,1.545-1.659,2.509-2.277c1.373,1.152,2.85,1.433,4.45,0.499c0.332-0.194,0.503-0.088,0.673,0.19c0.386,0.635,0.753,1.285,1.181,1.89c0.34,0.48,0.222,0.715-0.253,1.006C7.84,19.73,4.205,19.188,1.977,16.77z"/></svg><text x="245" y="140" transform="scale(.1)" textLength="30"> </text><text x="725" y="150" fill="#010101" fill-opacity=".3" transform="scale(.1)" textLength="770">Open in Colab</text><text x="725" y="140" transform="scale(.1)" textLength="770">Open in Colab</text></g> </svg>

docs/src/assets/ghost.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" width="88.25" height="28" role="img" aria-label="GHOST"><title>GHOST</title><g shape-rendering="crispEdges"><rect width="88.25" height="28" fill="#000"/></g><g fill="#fff" text-anchor="middle" font-family="Verdana,Geneva,DejaVu Sans,sans-serif" text-rendering="geometricPrecision" font-size="100"><image x="9" y="7" width="14" height="14" xlink:href="data:image/svg+xml;base64,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"/><text transform="scale(.1)" x="541.25" y="175" textLength="442.5" fill="#fff" font-weight="bold">GHOST</text></g></svg>

docs/src/assets/github.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" width="95.5" height="28" role="img" aria-label="GITHUB"><title>GITHUB</title><g shape-rendering="crispEdges"><rect width="95.5" height="28" fill="#121011"/></g><g fill="#fff" text-anchor="middle" font-family="Verdana,Geneva,DejaVu Sans,sans-serif" text-rendering="geometricPrecision" font-size="100"><image x="9" y="7" width="14" height="14" xlink:href="data:image/svg+xml;base64,PHN2ZyBmaWxsPSJ3aGl0ZSIgcm9sZT0iaW1nIiB2aWV3Qm94PSIwIDAgMjQgMjQiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyI+PHRpdGxlPkdpdEh1YjwvdGl0bGU+PHBhdGggZD0iTTEyIC4yOTdjLTYuNjMgMC0xMiA1LjM3My0xMiAxMiAwIDUuMzAzIDMuNDM4IDkuOCA4LjIwNSAxMS4zODUuNi4xMTMuODItLjI1OC44Mi0uNTc3IDAtLjI4NS0uMDEtMS4wNC0uMDE1LTIuMDQtMy4zMzguNzI0LTQuMDQyLTEuNjEtNC4wNDItMS42MUM0LjQyMiAxOC4wNyAzLjYzMyAxNy43IDMuNjMzIDE3LjdjLTEuMDg3LS43NDQuMDg0LS43MjkuMDg0LS43MjkgMS4yMDUuMDg0IDEuODM4IDEuMjM2IDEuODM4IDEuMjM2IDEuMDcgMS44MzUgMi44MDkgMS4zMDUgMy40OTUuOTk4LjEwOC0uNzc2LjQxNy0xLjMwNS43Ni0xLjYwNS0yLjY2NS0uMy01LjQ2Ni0xLjMzMi01LjQ2Ni01LjkzIDAtMS4zMS40NjUtMi4zOCAxLjIzNS0zLjIyLS4xMzUtLjMwMy0uNTQtMS41MjMuMTA1LTMuMTc2IDAgMCAxLjAwNS0uMzIyIDMuMyAxLjIzLjk2LS4yNjcgMS45OC0uMzk5IDMtLjQwNSAxLjAyLjAwNiAyLjA0LjEzOCAzIC40MDUgMi4yOC0xLjU1MiAzLjI4NS0xLjIzIDMuMjg1LTEuMjMuNjQ1IDEuNjUzLjI0IDIuODczLjEyIDMuMTc2Ljc2NS44NCAxLjIzIDEuOTEgMS4yMyAzLjIyIDAgNC42MS0yLjgwNSA1LjYyNS01LjQ3NSA1LjkyLjQyLjM2LjgxIDEuMDk2LjgxIDIuMjIgMCAxLjYwNi0uMDE1IDIuODk2LS4wMTUgMy4yODYgMCAuMzE1LjIxLjY5LjgyNS41N0MyMC41NjUgMjIuMDkyIDI0IDE3LjU5MiAyNCAxMi4yOTdjMC02LjYyNy01LjM3My0xMi0xMi0xMiIvPjwvc3ZnPg=="/><text transform="scale(.1)" x="577.5" y="175" textLength="515" fill="#fff" font-weight="bold">GITHUB</text></g></svg>

docs/src/assets/python.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" width="97.5" height="28" role="img" aria-label="PYTHON"><title>PYTHON</title><g shape-rendering="crispEdges"><rect width="97.5" height="28" fill="#3670a0"/></g><g fill="#fff" text-anchor="middle" font-family="Verdana,Geneva,DejaVu Sans,sans-serif" text-rendering="geometricPrecision" font-size="100"><image x="9" y="7" width="14" height="14" xlink:href="data:image/svg+xml;base64,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"/><text transform="scale(.1)" x="587.5" y="175" textLength="535" fill="#fff" font-weight="bold">PYTHON</text></g></svg>

docs/src/basic.md

@@ -16,11 +16,60 @@
       pip install lancedb
       ```
 
-=== "Typescript"
+=== "Typescript[^1]"
+    === "@lancedb/lancedb"
 
-      ```shell
+        ```shell
-      npm install vectordb
+        npm install @lancedb/lancedb
-      ```
+        ```
+        !!! 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;
+            }
+            })
+            ```
+
+        !!! note "Yarn users"
+
+            Unlike other package managers, Yarn does not automatically resolve peer dependencies. If you are using Yarn, you will need to manually install 'apache-arrow':
+
+            ```shell
+            yarn add apache-arrow
+            ```
+
+    === "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;
+            }
+            })
+            ```
+
+        !!! note "Yarn users"
+
+            Unlike other package managers, Yarn does not automatically resolve peer dependencies. If you are using Yarn, you will need to manually install 'apache-arrow':
+
+            ```shell
+            yarn add apache-arrow
+            ```
 
 === "Rust"
 
@@ -58,14 +107,21 @@ recommend switching to stable releases.
       pip install --pre --extra-index-url https://pypi.fury.io/lancedb/ lancedb
       ```
 
-=== "Typescript"
+=== "Typescript[^1]"
 
-      ```shell
+    === "@lancedb/lancedb"
-      npm install vectordb@preview
+
-      ```
+        ```shell
+        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:
 
@@ -93,23 +149,22 @@ recommend switching to stable releases.
         use the same syntax as the asynchronous API.  To help with this migration we
         have created a [migration guide](migration.md) detailing the differences.
 
-=== "Typescript"
+=== "Typescript[^1]"
 
-    ```typescript
+    === "@lancedb/lancedb"
-    --8<-- "docs/src/basic_legacy.ts:import"
 
-    --8<-- "docs/src/basic_legacy.ts:open_db"
+        ```typescript
-    ```
+        import * as lancedb from "@lancedb/lancedb";
+        import * as arrow from "apache-arrow";
 
-    !!! note "`@lancedb/lancedb` vs. `vectordb`"
+        --8<-- "nodejs/examples/basic.ts:connect"
+        ```
 
-        The Javascript SDK was originally released as `vectordb`.  In an effort to
+    === "vectordb (deprecated)"
-        reduce maintenance we are aligning our SDKs.  The new, aligned, Javascript
+
-        API is being released as `lancedb`.  If you are starting new work we encourage
+        ```typescript
-        you to try out `lancedb`.  Once the new API is feature complete we will begin
+        --8<-- "docs/src/basic_legacy.ts:open_db"
-        slowly deprecating `vectordb` in favor of `lancedb`. There is a
+        ```
-        [migration guide](migration.md) detailing the differences which will assist
-        you in this process.
 
 === "Rust"
 
@@ -152,15 +207,23 @@ table.
     --8<-- "python/python/tests/docs/test_basic.py:create_table_async_pandas"
     ```
 
-=== "Typescript"
+=== "Typescript[^1]"
 
-    ```typescript
+    === "@lancedb/lancedb"
-    --8<-- "docs/src/basic_legacy.ts:create_table"
-    ```
 
-    If the table already exists, LanceDB will raise an error by default.
+        ```typescript
-    If you want to overwrite the table, you can pass in `mode="overwrite"`
+        --8<-- "nodejs/examples/basic.ts:create_table"
-    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"
 
@@ -180,6 +243,9 @@ table.
 
 !!! 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.
@@ -194,11 +260,22 @@ similar to a `CREATE TABLE` statement in SQL.
       --8<-- "python/python/tests/docs/test_basic.py:create_empty_table_async"
       ```
 
-=== "Typescript"
+    !!! note "You can define schema in Pydantic"
+        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
+=== "Typescript[^1]"
-    --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"
 
@@ -217,11 +294,19 @@ Once created, you can open a table as follows:
     --8<-- "python/python/tests/docs/test_basic.py:open_table_async"
     ```
 
-=== "Typescript"
+=== "Typescript[^1]"
+    === "@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"
 
@@ -238,11 +323,18 @@ If you forget the name of your table, you can always get a listing of all table
     --8<-- "python/python/tests/docs/test_basic.py:table_names_async"
     ```
 
-=== "Javascript"
+=== "Typescript[^1]"
+    === "@lancedb/lancedb"
 
-    ```javascript
+        ```typescript
-    console.log(await db.tableNames());
+        --8<-- "nodejs/examples/basic.ts:table_names"
-    ```
+        ```
+
+    === "vectordb (deprecated)"
+
+        ```typescript
+        console.log(await db.tableNames());
+        ```
 
 === "Rust"
 
@@ -261,11 +353,18 @@ After a table has been created, you can always add more data to it as follows:
     --8<-- "python/python/tests/docs/test_basic.py:add_data_async"
     ```
 
-=== "Typescript"
+=== "Typescript[^1]"
+    === "@lancedb/lancedb"
 
-    ```typescript
+        ```typescript
-    --8<-- "docs/src/basic_legacy.ts:add"
+        --8<-- "nodejs/examples/basic.ts:add_data"
-    ```
+        ```
+
+    === "vectordb (deprecated)"
+
+        ```typescript
+        --8<-- "docs/src/basic_legacy.ts:add"
+        ```
 
 === "Rust"
 
@@ -286,11 +385,18 @@ Once you've embedded the query, you can find its nearest neighbors as follows:
 
     This returns a pandas DataFrame with the results.
 
-=== "Typescript"
+=== "Typescript[^1]"
+    === "@lancedb/lancedb"
 
-    ```typescript
+        ```typescript
-    --8<-- "docs/src/basic_legacy.ts:search"
+        --8<-- "nodejs/examples/basic.ts:vector_search"
-    ```
+        ```
+
+    === "vectordb (deprecated)"
+
+        ```typescript
+        --8<-- "docs/src/basic_legacy.ts:search"
+        ```
 
 === "Rust"
 
@@ -319,11 +425,18 @@ LanceDB allows you to create an ANN index on a table as follows:
     --8<-- "python/python/tests/docs/test_basic.py:create_index_async"
     ```
 
-=== "Typescript"
+=== "Typescript[^1]"
+    === "@lancedb/lancedb"
 
-    ```{.typescript .ignore}
+        ```typescript
-    --8<-- "docs/src/basic_legacy.ts:create_index"
+        --8<-- "nodejs/examples/basic.ts:create_index"
-    ```
+        ```
+
+    === "vectordb (deprecated)"
+
+        ```{.typescript .ignore}
+        --8<-- "docs/src/basic_legacy.ts:create_index"
+        ```
 
 === "Rust"
 
@@ -351,11 +464,19 @@ This can delete any number of rows that match the filter.
     --8<-- "python/python/tests/docs/test_basic.py:delete_rows_async"
     ```
 
-=== "Typescript"
+=== "Typescript[^1]"
 
-    ```typescript
+    === "@lancedb/lancedb"
-    --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"
 
@@ -372,9 +493,15 @@ simple or complex as needed. To see what expressions are supported, see the
 
       Read more: [lancedb.table.Table.delete][]
 
-=== "Javascript"
+=== "Typescript[^1]"
 
-      Read more: [vectordb.Table.delete](javascript/interfaces/Table.md#delete)
+    === "@lancedb/lancedb"
+
+        Read more: [lancedb.Table.delete](javascript/interfaces/Table.md#delete)
+
+    === "vectordb (deprecated)"
+
+        Read more: [vectordb.Table.delete](javascript/interfaces/Table.md#delete)
 
 === "Rust"
 
@@ -386,23 +513,31 @@ 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"
+    --8<-- "python/python/tests/docs/test_basic.py:drop_table"
-      --8<-- "python/python/tests/docs/test_basic.py:drop_table_async"
+    --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"
+=== "Typescript[^1]"
 
-      ```typescript
+    === "@lancedb/lancedb"
-      --8<-- "docs/src/basic_legacy.ts:drop_table"
-      ```
 
-      This permanently removes the table and is not recoverable, unlike deleting rows.
+        ```typescript
-      If the table does not exist an exception is raised.
+        --8<-- "nodejs/examples/basic.ts:drop_table"
+        ```
+
+    === "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"
 
@@ -410,22 +545,40 @@ Use the `drop_table()` method on the database to remove a table.
     --8<-- "rust/lancedb/examples/simple.rs:drop_table"
     ```
 
-!!! note "Bundling `vectordb` apps with Webpack"
 
-    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.
+## Using the Embedding API
+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.
 
-    ```javascript
+=== "Python"
-    /** @type {import('next').NextConfig} */
+
-    module.exports = ({
+    ```python
-    webpack(config) {
+    --8<-- "python/python/tests/docs/test_embeddings_optional.py:imports"
-        config.externals.push({ vectordb: 'vectordb' })
+    --8<-- "python/python/tests/docs/test_embeddings_optional.py:openai_embeddings"
-        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

@@ -1,6 +1,14 @@
 // --8<-- [start:import]
 import * as lancedb from "vectordb";
-import { Schema, Field, Float32, FixedSizeList, Int32, Float16 } from "apache-arrow";
+import {
+  Schema,
+  Field,
+  Float32,
+  FixedSizeList,
+  Int32,
+  Float16,
+} from "apache-arrow";
+import * as arrow from "apache-arrow";
 // --8<-- [end:import]
 import * as fs from "fs";
 import { Table as ArrowTable, Utf8 } from "apache-arrow";
@@ -20,9 +28,33 @@ const example = async () => {
       { vector: [3.1, 4.1], item: "foo", price: 10.0 },
       { vector: [5.9, 26.5], item: "bar", price: 20.0 },
     ],
-    { writeMode: lancedb.WriteMode.Overwrite }
+    { writeMode: lancedb.WriteMode.Overwrite },
   );
   // --8<-- [end:create_table]
+  {
+    // --8<-- [start:create_table_with_schema]
+    const schema = new arrow.Schema([
+      new arrow.Field(
+        "vector",
+        new arrow.FixedSizeList(
+          2,
+          new arrow.Field("item", new arrow.Float32(), true),
+        ),
+      ),
+      new arrow.Field("item", new arrow.Utf8(), true),
+      new arrow.Field("price", new arrow.Float32(), true),
+    ]);
+    const data = [
+      { vector: [3.1, 4.1], item: "foo", price: 10.0 },
+      { vector: [5.9, 26.5], item: "bar", price: 20.0 },
+    ];
+    const tbl = await db.createTable({
+      name: "myTableWithSchema",
+      data,
+      schema,
+    });
+    // --8<-- [end:create_table_with_schema]
+  }
 
   // --8<-- [start:add]
   const newData = Array.from({ length: 500 }, (_, i) => ({
@@ -42,33 +74,35 @@ const example = async () => {
   // --8<-- [end:create_index]
 
   // --8<-- [start:create_empty_table]
-  const schema = new Schema([
+  const schema = new arrow.Schema([
-    new Field("id", new Int32()),
+    new arrow.Field("id", new arrow.Int32()),
-    new Field("name", new Utf8()),
+    new arrow.Field("name", new arrow.Utf8()),
   ]);
+
   const empty_tbl = await db.createTable({ name: "empty_table", schema });
   // --8<-- [end:create_empty_table]
-
+  {
-  // --8<-- [start:create_f16_table]
+    // --8<-- [start:create_f16_table]
-  const dim = 16
+    const dim = 16;
-  const total = 10
+    const total = 10;
-  const f16_schema = new Schema([
+    const schema = new Schema([
-      new Field('id', new Int32()),
+      new Field("id", new Int32()),
       new Field(
-        'vector',
+        "vector",
-        new FixedSizeList(dim, new Field('item', new Float16(), true)),
+        new FixedSizeList(dim, new Field("item", new Float16(), true)),
-        false
+        false,
-      )
+      ),
-    ])
+    ]);
-  const data = lancedb.makeArrowTable(
+    const data = lancedb.makeArrowTable(
       Array.from(Array(total), (_, i) => ({
         id: i,
-        vector: Array.from(Array(dim), Math.random)
+        vector: Array.from(Array(dim), Math.random),
       })),
-      { f16_schema }
+      { schema },
-    )
+    );
-  const table = await db.createTable('f16_tbl', data)
+    const table = await db.createTable("f16_tbl", data);
-  // --8<-- [end:create_f16_table]
+    // --8<-- [end:create_f16_table]
+  }
 
   // --8<-- [start:search]
   const query = await tbl.search([100, 100]).limit(2).execute();

docs/src/cloud/rest.md

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

docs/src/embeddings/custom_embedding_function.md

@@ -15,198 +15,226 @@ There is another optional layer of abstraction available: `TextEmbeddingFunction
 
 Let's implement `SentenceTransformerEmbeddings` class. All you need to do is implement the `generate_embeddings()` and `ndims` function to handle the input types you expect and register the class in the global `EmbeddingFunctionRegistry`
 
-```python
-from lancedb.embeddings import register
-from lancedb.util import attempt_import_or_raise
 
-@register("sentence-transformers")
+=== "Python"
-class SentenceTransformerEmbeddings(TextEmbeddingFunction):
-    name: str = "all-MiniLM-L6-v2"
-    # set more default instance vars like device, etc.
 
-    def __init__(self, **kwargs):
+    ```python
-        super().__init__(**kwargs)
+    from lancedb.embeddings import register
-        self._ndims = None
+    from lancedb.util import attempt_import_or_raise
-    
-    def generate_embeddings(self, texts):
-        return self._embedding_model().encode(list(texts), ...).tolist()
 
-    def ndims(self):
+    @register("sentence-transformers")
-        if self._ndims is None:
+    class SentenceTransformerEmbeddings(TextEmbeddingFunction):
-            self._ndims = len(self.generate_embeddings("foo")[0])
+        name: str = "all-MiniLM-L6-v2"
-        return self._ndims
+        # set more default instance vars like device, etc.
 
-    @cached(cache={}) 
+        def __init__(self, **kwargs):
-    def _embedding_model(self):
+            super().__init__(**kwargs)
-        return sentence_transformers.SentenceTransformer(name)
+            self._ndims = None
-```
 
-This is a stripped down version of our implementation of `SentenceTransformerEmbeddings` that removes certain optimizations and defaul settings.
+        def generate_embeddings(self, texts):
+            return self._embedding_model().encode(list(texts), ...).tolist()
+
+        def ndims(self):
+            if self._ndims is None:
+                self._ndims = len(self.generate_embeddings("foo")[0])
+            return self._ndims
+
+        @cached(cache={})
+        def _embedding_model(self):
+            return sentence_transformers.SentenceTransformer(name)
+    ```
+
+=== "TypeScript"
+
+    ```ts
+    --8<--- "nodejs/examples/custom_embedding_function.ts:imports"
+
+    --8<--- "nodejs/examples/custom_embedding_function.ts:embedding_impl"
+    ```
+
+
+This is a stripped down version of our implementation of `SentenceTransformerEmbeddings` that removes certain optimizations and default settings.
 
 Now you can use this embedding function to create your table schema and that's it! you can then ingest data and run queries without manually vectorizing the inputs.
 
-```python
+=== "Python"
-from lancedb.pydantic import LanceModel, Vector
 
-registry = EmbeddingFunctionRegistry.get_instance()
+    ```python
-stransformer = registry.get("sentence-transformers").create()
+    from lancedb.pydantic import LanceModel, Vector
 
-class TextModelSchema(LanceModel):
+    registry = EmbeddingFunctionRegistry.get_instance()
-    vector: Vector(stransformer.ndims) = stransformer.VectorField()
+    stransformer = registry.get("sentence-transformers").create()
-    text: str = stransformer.SourceField()
 
-tbl = db.create_table("table", schema=TextModelSchema)
+    class TextModelSchema(LanceModel):
+        vector: Vector(stransformer.ndims) = stransformer.VectorField()
+        text: str = stransformer.SourceField()
 
-tbl.add(pd.DataFrame({"text": ["halo", "world"]}))
+    tbl = db.create_table("table", schema=TextModelSchema)
-result = tbl.search("world").limit(5)
-```
 
-NOTE:
+    tbl.add(pd.DataFrame({"text": ["halo", "world"]}))
+    result = tbl.search("world").limit(5)
+    ```
 
-You can always implement the `EmbeddingFunction` interface directly if you want or need to, `TextEmbeddingFunction` just makes it much simpler and faster for you to do so, by setting up the boiler plat for text-specific use case
+=== "TypeScript"
+
+    ```ts
+    --8<--- "nodejs/examples/custom_embedding_function.ts:call_custom_function"
+    ```
+
+!!! note
+
+    You can always implement the `EmbeddingFunction` interface directly if you want or need to, `TextEmbeddingFunction` just makes it much simpler and faster for you to do so, by setting up the boiler plat for text-specific use case
 
 ## Multi-modal embedding function example
-You can also use the `EmbeddingFunction` interface to implement more complex workflows such as multi-modal embedding function support. LanceDB implements `OpenClipEmeddingFunction` class that suppports multi-modal seach. Here's the implementation that you can use as a reference to build your own multi-modal embedding functions.
+You can also use the `EmbeddingFunction` interface to implement more complex workflows such as multi-modal embedding function support.
 
-```python
+=== "Python"
-@register("open-clip")
-class OpenClipEmbeddings(EmbeddingFunction):
-    name: str = "ViT-B-32"
-    pretrained: str = "laion2b_s34b_b79k"
-    device: str = "cpu"
-    batch_size: int = 64
-    normalize: bool = True
-    _model = PrivateAttr()
-    _preprocess = PrivateAttr()
-    _tokenizer = PrivateAttr()
 
-    def __init__(self, *args, **kwargs):
+    LanceDB implements `OpenClipEmeddingFunction` class that suppports multi-modal seach. Here's the implementation that you can use as a reference to build your own multi-modal embedding functions.
-        super().__init__(*args, **kwargs)
-        open_clip = attempt_import_or_raise("open_clip", "open-clip") # EmbeddingFunction util to import external libs and raise if not found
-        model, _, preprocess = open_clip.create_model_and_transforms(
-            self.name, pretrained=self.pretrained
-        )
-        model.to(self.device)
-        self._model, self._preprocess = model, preprocess
-        self._tokenizer = open_clip.get_tokenizer(self.name)
-        self._ndims = None
 
-    def ndims(self):
+    ```python
-        if self._ndims is None:
+    @register("open-clip")
-            self._ndims = self.generate_text_embeddings("foo").shape[0]
+    class OpenClipEmbeddings(EmbeddingFunction):
-        return self._ndims
+        name: str = "ViT-B-32"
+        pretrained: str = "laion2b_s34b_b79k"
+        device: str = "cpu"
+        batch_size: int = 64
+        normalize: bool = True
+        _model = PrivateAttr()
+        _preprocess = PrivateAttr()
+        _tokenizer = PrivateAttr()
 
-    def compute_query_embeddings(
+        def __init__(self, *args, **kwargs):
-        self, query: Union[str, "PIL.Image.Image"], *args, **kwargs
+            super().__init__(*args, **kwargs)
-    ) -> List[np.ndarray]:
+            open_clip = attempt_import_or_raise("open_clip", "open-clip") # EmbeddingFunction util to import external libs and raise if not found
-        """
+            model, _, preprocess = open_clip.create_model_and_transforms(
-        Compute the embeddings for a given user query
+                self.name, pretrained=self.pretrained
+            )
+            model.to(self.device)
+            self._model, self._preprocess = model, preprocess
+            self._tokenizer = open_clip.get_tokenizer(self.name)
+            self._ndims = None
 
-        Parameters
+        def ndims(self):
-        ----------
+            if self._ndims is None:
-        query : Union[str, PIL.Image.Image]
+                self._ndims = self.generate_text_embeddings("foo").shape[0]
-            The query to embed. A query can be either text or an image.
+            return self._ndims
-        """
+
-        if isinstance(query, str):
+        def compute_query_embeddings(
-            return [self.generate_text_embeddings(query)]
+            self, query: Union[str, "PIL.Image.Image"], *args, **kwargs
-        else:
+        ) -> List[np.ndarray]:
+            """
+            Compute the embeddings for a given user query
+
+            Parameters
+            ----------
+            query : Union[str, PIL.Image.Image]
+                The query to embed. A query can be either text or an image.
+            """
+            if isinstance(query, str):
+                return [self.generate_text_embeddings(query)]
+            else:
+                PIL = attempt_import_or_raise("PIL", "pillow")
+                if isinstance(query, PIL.Image.Image):
+                    return [self.generate_image_embedding(query)]
+                else:
+                    raise TypeError("OpenClip supports str or PIL Image as query")
+
+        def generate_text_embeddings(self, text: str) -> np.ndarray:
+            torch = attempt_import_or_raise("torch")
+            text = self.sanitize_input(text)
+            text = self._tokenizer(text)
+            text.to(self.device)
+            with torch.no_grad():
+                text_features = self._model.encode_text(text.to(self.device))
+                if self.normalize:
+                    text_features /= text_features.norm(dim=-1, keepdim=True)
+                return text_features.cpu().numpy().squeeze()
+
+        def sanitize_input(self, images: IMAGES) -> Union[List[bytes], np.ndarray]:
+            """
+            Sanitize the input to the embedding function.
+            """
+            if isinstance(images, (str, bytes)):
+                images = [images]
+            elif isinstance(images, pa.Array):
+                images = images.to_pylist()
+            elif isinstance(images, pa.ChunkedArray):
+                images = images.combine_chunks().to_pylist()
+            return images
+
+        def compute_source_embeddings(
+            self, images: IMAGES, *args, **kwargs
+        ) -> List[np.array]:
+            """
+            Get the embeddings for the given images
+            """
+            images = self.sanitize_input(images)
+            embeddings = []
+            for i in range(0, len(images), self.batch_size):
+                j = min(i + self.batch_size, len(images))
+                batch = images[i:j]
+                embeddings.extend(self._parallel_get(batch))
+            return embeddings
+
+        def _parallel_get(self, images: Union[List[str], List[bytes]]) -> List[np.ndarray]:
+            """
+            Issue concurrent requests to retrieve the image data
+            """
+            with concurrent.futures.ThreadPoolExecutor() as executor:
+                futures = [
+                    executor.submit(self.generate_image_embedding, image)
+                    for image in images
+                ]
+                return [future.result() for future in futures]
+
+        def generate_image_embedding(
+            self, image: Union[str, bytes, "PIL.Image.Image"]
+        ) -> np.ndarray:
+            """
+            Generate the embedding for a single image
+
+            Parameters
+            ----------
+            image : Union[str, bytes, PIL.Image.Image]
+                The image to embed. If the image is a str, it is treated as a uri.
+                If the image is bytes, it is treated as the raw image bytes.
+            """
+            torch = attempt_import_or_raise("torch")
+            # TODO handle retry and errors for https
+            image = self._to_pil(image)
+            image = self._preprocess(image).unsqueeze(0)
+            with torch.no_grad():
+                return self._encode_and_normalize_image(image)
+
+        def _to_pil(self, image: Union[str, bytes]):
             PIL = attempt_import_or_raise("PIL", "pillow")
-            if isinstance(query, PIL.Image.Image):
+            if isinstance(image, bytes):
-                return [self.generate_image_embedding(query)]
+                return PIL.Image.open(io.BytesIO(image))
-            else:
+            if isinstance(image, PIL.Image.Image):
-                raise TypeError("OpenClip supports str or PIL Image as query")
+                return image
+            elif isinstance(image, str):
+                parsed = urlparse.urlparse(image)
+                # TODO handle drive letter on windows.
+                if parsed.scheme == "file":
+                    return PIL.Image.open(parsed.path)
+                elif parsed.scheme == "":
+                    return PIL.Image.open(image if os.name == "nt" else parsed.path)
+                elif parsed.scheme.startswith("http"):
+                    return PIL.Image.open(io.BytesIO(url_retrieve(image)))
+                else:
+                    raise NotImplementedError("Only local and http(s) urls are supported")
 
-    def generate_text_embeddings(self, text: str) -> np.ndarray:
+        def _encode_and_normalize_image(self, image_tensor: "torch.Tensor"):
-        torch = attempt_import_or_raise("torch")
+            """
-        text = self.sanitize_input(text)
+            encode a single image tensor and optionally normalize the output
-        text = self._tokenizer(text)
+            """
-        text.to(self.device)
+            image_features = self._model.encode_image(image_tensor)
-        with torch.no_grad():
-            text_features = self._model.encode_text(text.to(self.device))
             if self.normalize:
-                text_features /= text_features.norm(dim=-1, keepdim=True)
+                image_features /= image_features.norm(dim=-1, keepdim=True)
-            return text_features.cpu().numpy().squeeze()
+            return image_features.cpu().numpy().squeeze()
+    ```
 
-    def sanitize_input(self, images: IMAGES) -> Union[List[bytes], np.ndarray]:
+=== "TypeScript"
-        """
-        Sanitize the input to the embedding function.
-        """
-        if isinstance(images, (str, bytes)):
-            images = [images]
-        elif isinstance(images, pa.Array):
-            images = images.to_pylist()
-        elif isinstance(images, pa.ChunkedArray):
-            images = images.combine_chunks().to_pylist()
-        return images
 
-    def compute_source_embeddings(
+    Coming Soon! See this [issue](https://github.com/lancedb/lancedb/issues/1482) to track the status!
-        self, images: IMAGES, *args, **kwargs
-    ) -> List[np.array]:
-        """
-        Get the embeddings for the given images
-        """
-        images = self.sanitize_input(images)
-        embeddings = []
-        for i in range(0, len(images), self.batch_size):
-            j = min(i + self.batch_size, len(images))
-            batch = images[i:j]
-            embeddings.extend(self._parallel_get(batch))
-        return embeddings
-
-    def _parallel_get(self, images: Union[List[str], List[bytes]]) -> List[np.ndarray]:
-        """
-        Issue concurrent requests to retrieve the image data
-        """
-        with concurrent.futures.ThreadPoolExecutor() as executor:
-            futures = [
-                executor.submit(self.generate_image_embedding, image)
-                for image in images
-            ]
-            return [future.result() for future in futures]
-
-    def generate_image_embedding(
-        self, image: Union[str, bytes, "PIL.Image.Image"]
-    ) -> np.ndarray:
-        """
-        Generate the embedding for a single image
-
-        Parameters
-        ----------
-        image : Union[str, bytes, PIL.Image.Image]
-            The image to embed. If the image is a str, it is treated as a uri.
-            If the image is bytes, it is treated as the raw image bytes.
-        """
-        torch = attempt_import_or_raise("torch")
-        # TODO handle retry and errors for https
-        image = self._to_pil(image)
-        image = self._preprocess(image).unsqueeze(0)
-        with torch.no_grad():
-            return self._encode_and_normalize_image(image)
-
-    def _to_pil(self, image: Union[str, bytes]):
-        PIL = attempt_import_or_raise("PIL", "pillow")
-        if isinstance(image, bytes):
-            return PIL.Image.open(io.BytesIO(image))
-        if isinstance(image, PIL.Image.Image):
-            return image
-        elif isinstance(image, str):
-            parsed = urlparse.urlparse(image)
-            # TODO handle drive letter on windows.
-            if parsed.scheme == "file":
-                return PIL.Image.open(parsed.path)
-            elif parsed.scheme == "":
-                return PIL.Image.open(image if os.name == "nt" else parsed.path)
-            elif parsed.scheme.startswith("http"):
-                return PIL.Image.open(io.BytesIO(url_retrieve(image)))
-            else:
-                raise NotImplementedError("Only local and http(s) urls are supported")
-
-    def _encode_and_normalize_image(self, image_tensor: "torch.Tensor"):
-        """
-        encode a single image tensor and optionally normalize the output
-        """
-        image_features = self._model.encode_image(image_tensor)
-        if self.normalize:
-            image_features /= image_features.norm(dim=-1, keepdim=True)
-        return image_features.cpu().numpy().squeeze()
-```

docs/src/embeddings/default_embedding_functions.md

@@ -17,6 +17,7 @@ Allows you to set parameters when registering a `sentence-transformers` object.
 | `name` | `str` | `all-MiniLM-L6-v2` | The name of the model |
 | `device` | `str` | `cpu` | The device to run the model on (can be `cpu` or `gpu`) |
 | `normalize` | `bool` | `True` | Whether to normalize the input text before feeding it to the model |
+| `trust_remote_code` | `bool` | `False` | Whether to trust and execute remote code from the model's Huggingface repository |
 
 
 ??? "Check out available sentence-transformer models here!"
@@ -193,13 +194,13 @@ from lancedb.pydantic import LanceModel, Vector
 
 model = get_registry().get("huggingface").create(name='facebook/bart-base')
 
-class TextModel(LanceModel):
+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()
+table.add(df)
 query = "old greeting"
 actual = table.search(query).limit(1).to_pydantic(Words)[0]
 print(actual.text)
@@ -216,7 +217,7 @@ Generate embeddings via the [ollama](https://github.com/ollama/ollama-python) py
 |------------------------|----------------------------|--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------|
 | `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](./modelfile.md#valid-parameters-and-values) such as `temperature`. |
+| `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`.                                                                                                |
 
@@ -365,6 +366,108 @@ 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:
@@ -415,6 +518,82 @@ tbl.add(df)
 rs = tbl.search("hello").limit(1).to_pandas()
 ```
 
+# IBM watsonx.ai Embeddings
+
+Generate text embeddings using IBM's watsonx.ai platform.
+
+## Supported Models
+
+You can find a list of supported models at [IBM watsonx.ai Documentation](https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models-embed.html?context=wx). The currently supported model names are:
+
+- `ibm/slate-125m-english-rtrvr`
+- `ibm/slate-30m-english-rtrvr`
+- `sentence-transformers/all-minilm-l12-v2`
+- `intfloat/multilingual-e5-large`
+
+## Parameters
+
+The following parameters can be passed to the `create` method:
+
+| Parameter  | Type     | Default Value                    | Description                                               |
+|------------|----------|----------------------------------|-----------------------------------------------------------|
+| name       | str      | "ibm/slate-125m-english-rtrvr"   | The model ID of the watsonx.ai model to use               |
+| api_key    | str      | None                             | Optional IBM Cloud API key (or set `WATSONX_API_KEY`)     |
+| project_id | str      | None                             | Optional watsonx project ID (or set `WATSONX_PROJECT_ID`) |
+| url        | str      | None                             | Optional custom URL for the watsonx.ai instance           |
+| params     | dict     | None                             | Optional additional parameters for the embedding model    |
+
+## Usage Example
+
+First, the watsonx.ai library is an optional dependency, so must be installed seperately:
+
+```
+pip install ibm-watsonx-ai
+```
+
+Optionally set environment variables (if not passing credentials to `create` directly):
+
+```sh
+export WATSONX_API_KEY="YOUR_WATSONX_API_KEY"
+export WATSONX_PROJECT_ID="YOUR_WATSONX_PROJECT_ID"
+```
+
+```python
+import os
+import lancedb
+from lancedb.pydantic import LanceModel, Vector
+from lancedb.embeddings import EmbeddingFunctionRegistry
+
+watsonx_embed = EmbeddingFunctionRegistry
+  .get_instance()
+  .get("watsonx")
+  .create(
+    name="ibm/slate-125m-english-rtrvr",
+    # Uncomment and set these if not using environment variables
+    # api_key="your_api_key_here",
+    # project_id="your_project_id_here",
+    # url="your_watsonx_url_here",
+    # params={...},
+  )
+
+class TextModel(LanceModel):
+    text: str = watsonx_embed.SourceField()
+    vector: Vector(watsonx_embed.ndims()) = watsonx_embed.VectorField()
+
+data = [
+    {"text": "hello world"},
+    {"text": "goodbye world"},
+]
+
+db = lancedb.connect("~/.lancedb")
+tbl = db.create_table("watsonx_test", schema=TextModel, mode="overwrite")
+
+tbl.add(data)
+
+rs = tbl.search("hello").limit(1).to_pandas()
+print(rs)
+```
+
 ## Multi-modal embedding functions
 Multi-modal embedding functions allow you to query your table using both images and text.
 
@@ -462,7 +641,7 @@ uris = [
 # get each uri as bytes
 image_bytes = [requests.get(uri).content for uri in uris]
 table.add(
-    [{"label": labels, "image_uri": uris, "image_bytes": image_bytes}]
+    pd.DataFrame({"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
@@ -568,3 +747,54 @@ 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 +2,12 @@ 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. 
+    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 
+    However, if your embedding function changes, you'll have to re-configure your table with the new embedding function
     and regenerate the embeddings. In the future, we plan to support the ability to change the embedding function via
     table metadata and have LanceDB automatically take care of regenerating the embeddings.
 
@@ -13,7 +16,7 @@ For this purpose, LanceDB introduces an **embedding functions API**, that allow
 
 === "Python"
     In the LanceDB python SDK, we define a global embedding function registry with
-    many different embedding models and even more coming soon. 
+    many different embedding models and even more coming soon.
     Here's let's an implementation of CLIP as example.
 
     ```python
@@ -23,20 +26,35 @@ For this purpose, LanceDB introduces an **embedding functions API**, that allow
     clip = registry.get("open-clip").create()
     ```
 
-    You can also define your own embedding function by implementing the `EmbeddingFunction` 
+    You can also define your own embedding function by implementing the `EmbeddingFunction`
     abstract base interface. It subclasses Pydantic Model which can be utilized to write complex schemas simply as we'll see next!
 
-=== "JavaScript""
+=== "TypeScript"
     In the TypeScript SDK, the choices are more limited. For now, only the OpenAI
     embedding function is available.
 
     ```javascript
-    const lancedb = require("vectordb");
+    import * as lancedb from '@lancedb/lancedb'
+    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 embedding = new lancedb.OpenAIEmbeddingFunction('text', apiKey)
+    const func = getRegistry().get("openai").create({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
@@ -52,14 +70,14 @@ For this purpose, LanceDB introduces an **embedding functions API**, that allow
 
     `VectorField` tells LanceDB to use the clip embedding function to generate query embeddings for the `vector` column and `SourceField` ensures that when adding data, we automatically use the specified embedding function to encode `image_uri`.
 
-=== "JavaScript"
+=== "TypeScript"
 
     For the TypeScript SDK, a schema can be inferred from input data, or an explicit
     Arrow schema can be provided.
 
 ## 3. Create table and add data
 
-Now that we have chosen/defined our embedding function and the schema, 
+Now that we have chosen/defined our embedding function and the schema,
 we can create the table and ingest data without needing to explicitly generate
 the embeddings at all:
 
@@ -71,17 +89,26 @@ the embeddings at all:
     table.add([{"image_uri": u} for u in uris])
     ```
 
-=== "JavaScript"
+=== "TypeScript"
 
-    ```javascript
+    === "@lancedb/lancedb"
-    const db = await lancedb.connect("data/sample-lancedb");
-    const data = [
-    { text: "pepperoni"},
-    { text: "pineapple"}
-    ]
 
-    const table = await db.createTable("vectors", data, embedding)
+        ```ts
-    ```
+        --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
@@ -94,8 +121,8 @@ need to worry about it when you query the table:
     ```python
     results = (
         table.search("dog")
-        .limit(10)
+            .limit(10)
-        .to_pandas()
+            .to_pandas()
     )
     ```
 
@@ -106,22 +133,32 @@ 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.
 
-=== "JavaScript"
+=== "TypeScript"
+
+    === "@lancedb/lancedb"
+
+        ```ts
+        const results = await table.search("What's the best pizza topping?")
+            .limit(10)
+            .toArray()
+        ```
+
+    === "vectordb (deprecated)
+
+        ```ts
+        const results = await table
+            .search("What's the best pizza topping?")
+            .limit(10)
+            .execute()
+        ```
 
-    ```javascript
-    const results = await table
-    .search("What's the best pizza topping?")
-    .limit(10)
-    .execute()
-    ```    
-    
     The above snippet returns an array of records with the top 10 nearest neighbors to the query.
 
 ---

docs/src/embeddings/index.md

@@ -1,13 +1,13 @@
-Due to the nature of vector embeddings, they can be used to represent any kind of data, from text to images to audio. 
+Due to the nature of vector embeddings, they can be used to represent any kind of data, from text to images to audio.
-This makes them a very powerful tool for machine learning practitioners. 
+This makes them a very powerful tool for machine learning practitioners.
-However, there's no one-size-fits-all solution for generating embeddings - there are many different libraries and APIs 
+However, there's no one-size-fits-all solution for generating embeddings - there are many different libraries and APIs
 (both commercial and open source) that can be used to generate embeddings from structured/unstructured data.
 
 LanceDB supports 3 methods of working with embeddings.
 
 1. You can manually generate embeddings for the data and queries. This is done outside of LanceDB.
 2. You can use the built-in [embedding functions](./embedding_functions.md) to embed the data and queries in the background.
-3. For python users, you can define your own [custom embedding function](./custom_embedding_function.md)
+3. 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).
@@ -18,15 +18,103 @@ It is retained for compatibility and will be removed in a future version.
 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("openai").create(name="text-embedding-ada-002")
+func = get_registry().get("jina").create(name="jina-clip-v1")
 
 class Words(LanceModel):
     text: str = func.SourceField()
@@ -44,31 +132,3 @@ query = "greetings"
 actual = table.search(query).limit(1).to_pydantic(Words)[0]
 print(actual.text)
 ```
-
-### Sentence Transformers Embedding function
-LanceDB registers the Sentence Transformers embeddings function in the registry as `sentence-transformers`. You can pass any supported model name to the `create`. By default it uses `"sentence-transformers/paraphrase-MiniLM-L6-v2"`.
-
-```python
-import lancedb
-from lancedb.pydantic import LanceModel, Vector
-from lancedb.embeddings import get_registry
-
-db = lancedb.connect("/tmp/db")
-model = get_registry().get("sentence-transformers").create(name="BAAI/bge-small-en-v1.5", device="cpu")
-
-class Words(LanceModel):
-    text: str = model.SourceField()
-    vector: Vector(model.ndims()) = model.VectorField()
-
-table = db.create_table("words", schema=Words)
-table.add(
-    [
-        {"text": "hello world"},
-        {"text": "goodbye world"}
-    ]
-)
-
-query = "greetings"
-actual = table.search(query).limit(1).to_pydantic(Words)[0]
-print(actual.text)
-```

docs/src/examples/index.md

@@ -10,7 +10,7 @@ LanceDB provides language APIs, allowing you to embed a database in your languag
 
 ## Applications powered by LanceDB
 
-| Project Name                                        | Description                                                                                                          | Screenshot                                |
+| Project Name | Description |
-|-----------------------------------------------------|----------------------------------------------------------------------------------------------------------------------|-------------------------------------------|
+| --- | --- |
-| [YOLOExplorer](https://github.com/lancedb/yoloexplorer) | Iterate on your YOLO / CV datasets using SQL, Vector semantic search, and more within seconds                  | ![YOLOExplorer](https://github.com/lancedb/vectordb-recipes/assets/15766192/ae513a29-8f15-4e0b-99a1-ccd8272b6131) |
+| **Ultralytics Explorer 🚀**<br>[![Ultralytics](https://img.shields.io/badge/Ultralytics-Docs-green?labelColor=0f3bc4&style=flat-square&logo=https://cdn.prod.website-files.com/646dd1f1a3703e451ba81ecc/64994922cf2a6385a4bf4489_UltralyticsYOLO_mark_blue.svg&link=https://docs.ultralytics.com/datasets/explorer/)](https://docs.ultralytics.com/datasets/explorer/)<br>[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ultralytics/ultralytics/blob/main/docs/en/datasets/explorer/explorer.ipynb) |  - 🔍 **Explore CV Datasets**: Semantic search, SQL queries, vector similarity, natural language.<br>- 🖥️ **GUI & Python API**: Seamless dataset interaction.<br>- ⚡ **Efficient & Scalable**: Leverages LanceDB for large datasets.<br>- 📊 **Detailed Analysis**: Easily analyze data patterns.<br>- 🌐 **Browser GUI Demo**: Create embeddings, search images, run queries. |
-| [Website Chatbot (Deployable Vercel Template)](https://github.com/lancedb/lancedb-vercel-chatbot) | Create a chatbot from the sitemap of any website/docs of your choice. Built using vectorDB serverless native javascript package. | ![Chatbot](../assets/vercel-template.gif)    |
+| **Website Chatbot🤖**<br>[![GitHub](https://img.shields.io/badge/github-%23121011.svg?style=for-the-badge&logo=github&logoColor=white)](https://github.com/lancedb/lancedb-vercel-chatbot)<br>[![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2Flancedb%2Flancedb-vercel-chatbot&amp;env=OPENAI_API_KEY&amp;envDescription=OpenAI%20API%20Key%20for%20chat%20completion.&amp;project-name=lancedb-vercel-chatbot&amp;repository-name=lancedb-vercel-chatbot&amp;demo-title=LanceDB%20Chatbot%20Demo&amp;demo-description=Demo%20website%20chatbot%20with%20LanceDB.&amp;demo-url=https%3A%2F%2Flancedb.vercel.app&amp;demo-image=https%3A%2F%2Fi.imgur.com%2FazVJtvr.png) | - 🌐 **Chatbot from Sitemap/Docs**: Create a chatbot using site or document context.<br>- 🚀 **Embed LanceDB in Next.js**: Lightweight, on-prem storage.<br>- 🧠 **AI-Powered Context Retrieval**: Efficiently access relevant data.<br>- 🔧 **Serverless & Native JS**: Seamless integration with Next.js.<br>- ⚡ **One-Click Deploy on Vercel**: Quick and easy setup.. |

docs/src/examples/python_examples/build_from_scratch.md

@@ -0,0 +1,13 @@
+# Build from Scratch with LanceDB 🚀
+
+Start building your GenAI applications from the ground up using LanceDB's efficient vector-based document retrieval capabilities! 📄
+
+#### Get Started in Minutes ⏱️
+
+These examples provide a solid foundation for building your own GenAI applications using LanceDB. Jump from idea to proof of concept quickly with applied examples. Get started and see what you can create! 💻
+
+| **Build From Scratch**                     | **Description**                                                                                              | **Links**                                                                                                                                                                                                                                                                                                                                                                                                                |
+|:-------------------------------------------|:-------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| **Build RAG from Scratch🚀💻**             | 📝 Create a **Retrieval-Augmented Generation** (RAG) model from scratch using LanceDB.                       | [![GitHub](https://img.shields.io/badge/github-%23121011.svg?style=for-the-badge&logo=github&logoColor=white)](https://github.com/lancedb/vectordb-recipes/tree/main/tutorials/RAG-from-Scratch)<br>[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)]()                                                                                                                                  |
+| **Local RAG from Scratch with Llama3🔥💡** | 🐫 Build a local RAG model using **Llama3** and **LanceDB** for fast and efficient text generation.          | [![GitHub](https://img.shields.io/badge/github-%23121011.svg?style=for-the-badge&logo=github&logoColor=white)](https://github.com/lancedb/vectordb-recipes/tree/main/tutorials/Local-RAG-from-Scratch)<br>[![Python](https://img.shields.io/badge/python-3670A0?style=for-the-badge&logo=python&logoColor=ffdd54)](https://github.com/lancedb/vectordb-recipes/blob/main/tutorials/Local-RAG-from-Scratch/rag.py)    |
+| **Multi-Head RAG from Scratch📚💻**        | 🤯 Develop a **Multi-Head RAG model** from scratch, enabling generation of text based on multiple documents. | [![GitHub](https://img.shields.io/badge/github-%23121011.svg?style=for-the-badge&logo=github&logoColor=white)](https://github.com/lancedb/vectordb-recipes/tree/main/tutorials/Multi-Head-RAG-from-Scratch)<br>[![Python](https://img.shields.io/badge/python-3670A0?style=for-the-badge&logo=python&logoColor=ffdd54)](https://github.com/lancedb/vectordb-recipes/tree/main/tutorials/Multi-Head-RAG-from-Scratch) |

docs/src/examples/python_examples/multimodal.md

@@ -0,0 +1,28 @@
+# Multimodal Search with LanceDB 🔍💡
+
+Experience the future of search with LanceDB's multimodal capabilities. Combine text and image queries to find the most relevant results in your corpus and unlock new possibilities! 🔓💡
+
+#### Explore the Future of Search 🚀
+
+Unlock the power of multimodal search with LanceDB, enabling efficient vector-based retrieval of text and image data! 📊💻
+
+
+
+| **Multimodal**  | **Description**  | **Links**  |
+|:----------------|:-----------------|:-----------|
+| **Multimodal CLIP: DiffusionDB 🌐💥**    | Revolutionize search with Multimodal CLIP and DiffusionDB, combining text and image understanding for a new dimension of discovery! 🔓 | [![GitHub](../../assets/github.svg)][Clip_diffusionDB_github] <br>[![Open In Collab](../../assets/colab.svg)][Clip_diffusionDB_colab] <br>[![Python](../../assets/python.svg)][Clip_diffusionDB_python] <br>[![Ghost](../../assets/ghost.svg)][Clip_diffusionDB_ghost] |
+| **Multimodal CLIP: Youtube Videos 📹👀** | Search Youtube videos using Multimodal CLIP, finding relevant content with ease and accuracy! 🎯                                                                                                                                                                | [![Github](../../assets/github.svg)][Clip_youtube_github]                                                                                                    <br>[![Open In Collab](../../assets/colab.svg)][Clip_youtube_colab]                                                                                           <br> [![Python](../../assets/python.svg)][Clip_youtube_python]         <br>[![Ghost](../../assets/ghost.svg)][Clip_youtube_python] |
+| **Multimodal Image + Text Search 📸🔍**               | Discover relevant documents and images with a single query, using LanceDB's multimodal search capabilities to bridge the gap between text and visuals! 🌉 | [![GitHub](../../assets/github.svg)](https://github.com/lancedb/vectordb-recipes/blob/main/examples/multimodal_search) <br>[![Open In Collab](../../assets/colab.svg)](https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/multimodal_search/main.ipynb) <br> [![Python](../../assets/python.svg)](https://github.com/lancedb/vectordb-recipes/blob/main/examples/multimodal_search/main.py)<br> [![Ghost](../../assets/ghost.svg)](https://blog.lancedb.com/multi-modal-ai-made-easy-with-lancedb-clip-5aaf8801c939/) |
+| **Cambrian-1: Vision-Centric Image Exploration 🔍👀** | Dive into vision-centric exploration of images with Cambrian-1, powered by LanceDB's multimodal search to uncover new insights! 🔎                        | [![GitHub](../../assets/github.svg)](https://www.kaggle.com/code/prasantdixit/cambrian-1-vision-centric-exploration-of-images/)<br>[![Open In Collab](../../assets/colab.svg)]() <br> [![Python](../../assets/python.svg)]() <br> [![Ghost](../../assets/ghost.svg)](https://blog.lancedb.com/cambrian-1-vision-centric-exploration/)                                                                                                                                                                                                                   |
+
+
+[Clip_diffusionDB_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/multimodal_clip_diffusiondb
+[Clip_diffusionDB_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/multimodal_clip_diffusiondb/main.ipynb
+[Clip_diffusionDB_python]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/multimodal_clip_diffusiondb/main.py
+[Clip_diffusionDB_ghost]: https://blog.lancedb.com/multi-modal-ai-made-easy-with-lancedb-clip-5aaf8801c939/
+
+
+[Clip_youtube_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/multimodal_video_search
+[Clip_youtube_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/multimodal_video_search/main.ipynb
+[Clip_youtube_python]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/multimodal_video_search/main.py
+[Clip_youtube_ghost]: https://blog.lancedb.com/multi-modal-ai-made-easy-with-lancedb-clip-5aaf8801c939/

docs/src/examples/python_examples/rag.md

@@ -0,0 +1,85 @@
+
+**🔍💡 RAG: Revolutionize Information Retrieval with LanceDB 🔓**
+====================================================================
+
+Unlock the full potential of Retrieval-Augmented Generation (RAG) with LanceDB, the ultimate solution for efficient vector-based information retrieval 📊. Input text queries and retrieve relevant documents with lightning-fast speed ⚡️ and accuracy ✅. Generate comprehensive answers by combining retrieved information, uncovering new insights 🔍 and connections.
+
+### Experience the Future of Search 🔄
+
+Experience the future of search with RAG, transforming information retrieval and answer generation. Apply RAG to various industries, streamlining processes 📈, saving time ⏰, and resources 💰. Stay ahead of the curve with innovative technology 🔝, powered by LanceDB. Discover the power of RAG with LanceDB and transform your industry with innovative solutions 💡.
+
+
+| **RAG**                                      | **Description**                                                                                                                                                  | **Links**                  |
+|----------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------|                                                                                                                                                     
+| **RAG with Matryoshka Embeddings and LlamaIndex** 🪆🔗  | Utilize **Matryoshka embeddings** and **LlamaIndex** to improve the efficiency and accuracy of your RAG models. 📈✨ | [![Github](../../assets/github.svg)][matryoshka_github] <br>[![Open In Collab](../../assets/colab.svg)][matryoshka_colab]  |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        
+| **Improve RAG with Re-ranking** 📈🔄 | Enhance your RAG applications by implementing **re-ranking strategies** for more relevant document retrieval. 📚🔍 | [![Github](../../assets/github.svg)][rag_reranking_github] <br>[![Open In Collab](../../assets/colab.svg)][rag_reranking_colab] <br>[![Ghost](../../assets/ghost.svg)][rag_reranking_ghost] |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        
+| **Instruct-Multitask** 🧠🎯 |  Integrate the **Instruct Embedding Model** with LanceDB to streamline your embedding API, reducing redundant code and overhead. 🌐📊 | [![Github](../../assets/github.svg)][instruct_multitask_github] <br>[![Open In Collab](../../assets/colab.svg)][instruct_multitask_colab] <br>[![Python](../../assets/python.svg)][instruct_multitask_python] <br>[![Ghost](../../assets/ghost.svg)][instruct_multitask_ghost] |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        
+| **Improve RAG with HyDE** 🌌🔍 | Use **Hypothetical Document Embeddings** for efficient, accurate, and unsupervised dense retrieval. 📄🔍 | [![Github](../../assets/github.svg)][hyde_github] <br>[![Open In Collab](../../assets/colab.svg)][hyde_colab]<br>[![Ghost](../../assets/ghost.svg)][hyde_ghost]                 |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        
+| **Improve RAG with LOTR** 🧙‍♂️📜 | Enhance RAG with **Lord of the Retriever (LOTR)** to address 'Lost in the Middle' challenges, especially in medical data. 🌟📜 | [![Github](../../assets/github.svg)][lotr_github] <br>[![Open In Collab](../../assets/colab.svg)][lotr_colab] <br>[![Ghost](../../assets/ghost.svg)][lotr_ghost] |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        
+| **Advanced RAG: Parent Document Retriever** 📑🔗 | Use **Parent Document & Bigger Chunk Retriever** to maintain context and relevance when generating related content. 🎵📄 | [![Github](../../assets/github.svg)][parent_doc_retriever_github] <br>[![Open In Collab](../../assets/colab.svg)][parent_doc_retriever_colab] <br>[![Ghost](../../assets/ghost.svg)][parent_doc_retriever_ghost] |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        
+| **Corrective RAG with Langgraph** 🔧📊 | Enhance RAG reliability with **Corrective RAG (CRAG)** by self-reflecting and fact-checking for accurate and trustworthy results. ✅🔍 |[![Github](../../assets/github.svg)][corrective_rag_github] <br>[![Open In Collab](../../assets/colab.svg)][corrective_rag_colab] <br>[![Ghost](../../assets/ghost.svg)][corrective_rag_ghost] |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        
+| **Contextual Compression with RAG** 🗜️🧠 | Apply **contextual compression techniques** to condense large documents while retaining essential information. 📄🗜️                                               | [![Github](../../assets/github.svg)][compression_rag_github] <br>[![Open In Collab](../../assets/colab.svg)][compression_rag_colab] <br>[![Ghost](../../assets/ghost.svg)][compression_rag_ghost] |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        
+| **Improve RAG with FLARE** 🔥|  Enable users to ask questions directly to academic papers, focusing on ArXiv papers, with Forward-Looking Active REtrieval augmented generation.🚀🌟                                                                       | [![Github](../../assets/github.svg)][flare_github] <br>[![Open In Collab](../../assets/colab.svg)][flare_colab] <br>[![Ghost](../../assets/ghost.svg)][flare_ghost] |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        
+| **Query Expansion and Reranker** 🔍🔄 | Enhance RAG with query expansion using Large Language Models and advanced **reranking methods** like Cross Encoders, ColBERT v2, and FlashRank for improved document retrieval precision and recall 🔍📈                                                         | [![Github](../../assets/github.svg)][query_github] <br>[![Open In Collab](../../assets/colab.svg)][query_colab] |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        
+| **RAG Fusion** ⚡🌐 | Revolutionize search with RAG Fusion, utilizing the **RRF algorithm** to rerank documents based on user queries, and leveraging LanceDB and OPENAI Embeddings for efficient information retrieval ⚡🌐                                                                          | [![Github](../../assets/github.svg)][fusion_github] <br>[![Open In Collab](../../assets/colab.svg)][fusion_colab] |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        
+| **Agentic RAG** 🤖📚 | Unlock autonomous information retrieval with **Agentic RAG**, a framework of **intelligent agents** that collaborate to synthesize, summarize, and compare data across sources, enabling proactive and informed decision-making 🤖📚                                                              | [![Github](../../assets/github.svg)][agentic_github] <br>[![Open In Collab](../../assets/colab.svg)][agentic_colab] |
+
+
+
+
+
+
+
+
+
+
+
+
+[matryoshka_github]: https://github.com/lancedb/vectordb-recipes/blob/main/tutorials/RAG-with_MatryoshkaEmbed-Llamaindex
+[matryoshka_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/tutorials/RAG-with_MatryoshkaEmbed-Llamaindex/RAG_with_MatryoshkaEmbedding_and_Llamaindex.ipynb
+
+[rag_reranking_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/RAG_Reranking
+[rag_reranking_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/RAG_Reranking/main.ipynb
+[rag_reranking_ghost]: https://blog.lancedb.com/simplest-method-to-improve-rag-pipeline-re-ranking-cf6eaec6d544
+
+
+[instruct_multitask_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/instruct-multitask
+[instruct_multitask_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/instruct-multitask/main.ipynb
+[instruct_multitask_python]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/instruct-multitask/main.py
+[instruct_multitask_ghost]: https://blog.lancedb.com/multitask-embedding-with-lancedb-be18ec397543
+
+[hyde_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/Advance-RAG-with-HyDE
+[hyde_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/Advance-RAG-with-HyDE/main.ipynb
+[hyde_ghost]: https://blog.lancedb.com/advanced-rag-precise-zero-shot-dense-retrieval-with-hyde-0946c54dfdcb
+
+[lotr_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/Advance_RAG_LOTR
+[lotr_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/Advance_RAG_LOTR/main.ipynb
+[lotr_ghost]: https://blog.lancedb.com/better-rag-with-lotr-lord-of-retriever-23c8336b9a35
+
+[parent_doc_retriever_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/parent_document_retriever
+[parent_doc_retriever_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/parent_document_retriever/main.ipynb
+[parent_doc_retriever_ghost]: https://blog.lancedb.com/modified-rag-parent-document-bigger-chunk-retriever-62b3d1e79bc6
+
+[corrective_rag_github]: https://github.com/lancedb/vectordb-recipes/blob/main/tutorials/Corrective-RAG-with_Langgraph
+[corrective_rag_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/tutorials/Corrective-RAG-with_Langgraph/CRAG_with_Langgraph.ipynb
+[corrective_rag_ghost]: https://blog.lancedb.com/implementing-corrective-rag-in-the-easiest-way-2/
+
+[compression_rag_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/Contextual-Compression-with-RAG
+[compression_rag_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/Contextual-Compression-with-RAG/main.ipynb
+[compression_rag_ghost]: https://blog.lancedb.com/enhance-rag-integrate-contextual-compression-and-filtering-for-precision-a29d4a810301/
+
+[flare_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/better-rag-FLAIR
+[flare_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/better-rag-FLAIR/main.ipynb
+[flare_ghost]: https://blog.lancedb.com/better-rag-with-active-retrieval-augmented-generation-flare-3b66646e2a9f/
+
+[query_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/QueryExpansion&Reranker
+[query_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/QueryExpansion&Reranker/main.ipynb
+
+
+[fusion_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/RAG_Fusion
+[fusion_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/RAG_Fusion/main.ipynb
+
+[agentic_github]: https://github.com/lancedb/vectordb-recipes/blob/main/tutorials/Agentic_RAG
+[agentic_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/tutorials/Agentic_RAG/main.ipynb
+
+

docs/src/fts.md

@@ -2,7 +2,6 @@
 
 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)
 
-A hybrid search solution combining vector and full-text search is also on the way.
 
 ## Installation
 
@@ -55,6 +54,16 @@ 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`:
@@ -140,6 +149,7 @@ 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
 
 By default, LanceDB configures a 1GB heap size limit for creating the index. You can

docs/src/guides/storage.md

@@ -32,28 +32,54 @@ LanceDB OSS supports object stores such as AWS S3 (and compatible stores), Azure
     db = lancedb.connect("az://bucket/path")
     ```
 
-=== "JavaScript"
+=== "TypeScript"
 
-    AWS S3:
+    === "@lancedb/lancedb"
 
-    ```javascript
+        AWS S3:
-    const lancedb = require("lancedb");
-    const db = await lancedb.connect("s3://bucket/path");
-    ```
 
-    Google Cloud Storage:
+        ```ts
+        import * as lancedb from "@lancedb/lancedb";
+        const db = await lancedb.connect("s3://bucket/path");
+        ```
 
-    ```javascript
+        Google Cloud Storage:
-    const lancedb = require("lancedb");
-    const db = await lancedb.connect("gs://bucket/path");
-    ```
 
-    Azure Blob Storage:
+        ```ts
+        import * as lancedb from "@lancedb/lancedb";
+        const db = await lancedb.connect("gs://bucket/path");
+        ```
 
-    ```javascript
+        Azure Blob Storage:
-    const lancedb = require("lancedb");
+
-    const db = await lancedb.connect("az://bucket/path");
+        ```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`:
 
@@ -78,13 +104,26 @@ If you only want this to apply to one particular connection, you can pass the `s
     )
     ```
 
-=== "JavaScript"
+=== "TypeScript"
 
-    ```javascript
+    === "@lancedb/lancedb"
-    const lancedb = require("lancedb");
+
-    const db = await lancedb.connect("s3://bucket/path",
+        ```ts
-                                     {storageOptions: {timeout: "60s"}});
+        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:
 
@@ -101,18 +140,33 @@ Getting even more specific, you can set the `timeout` for only a particular tabl
     )
     ```
 
-=== "JavaScript"
+=== "TypeScript"
 
-    <!-- skip-test -->
+    === "@lancedb/lancedb"
-    ```javascript
+
-    const lancedb = require("lancedb");
+        <!-- skip-test -->
-    const db = await lancedb.connect("s3://bucket/path");
+        ```ts
-    const table = db.createTable(
+        import * as lancedb from "@lancedb/lancedb";
-        "table",
+        const db = await lancedb.connect("s3://bucket/path");
-        [{ a: 1, b: 2}],
+        const table = db.createTable(
-        {storageOptions: {timeout: "60s"}}
+            "table",
-    );
+            [{ a: 1, b: 2}],
-    ```
+            {storageOptions: {timeout: "60s"}}
+        );
+        ```
+
+    === "vectordb (deprecated)"
+
+        <!-- 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"
 
@@ -135,7 +189,6 @@ There are several options that can be set for all object stores, mostly related
 | `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.
@@ -155,21 +208,39 @@ These can be set as environment variables or passed in the `storage_options` par
     )
     ```
 
-=== "JavaScript"
+=== "TypeScript"
 
-    ```javascript
+    === "@lancedb/lancedb"
-    const lancedb = require("lancedb");
+
-    const db = await lancedb.connect(
+        ```ts
-        "s3://bucket/path",
+        import * as lancedb from "@lancedb/lancedb";
-        {
+        const db = await lancedb.connect(
-            storageOptions: {
+            "s3://bucket/path",
-                awsAccessKeyId: "my-access-key",
+            {
-                awsSecretAccessKey: "my-secret-key",
+                storageOptions: {
-                awsSessionToken: "my-session-token",
+                    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.
 
@@ -188,7 +259,6 @@ The following keys can be used as both environment variables or keys in the `sto
 | `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"
 
     LanceDB uses [multi-part uploads](https://docs.aws.amazon.com/AmazonS3/latest/userguide/mpuoverview.html) when writing data to S3 in order to maximize write speed. LanceDB will abort these uploads when it shuts down gracefully, such as when cancelled by keyboard interrupt. However, in the rare case that LanceDB crashes, it is possible that some data will be left lingering in your account. To cleanup this data, we recommend (as AWS themselves do) that you setup a lifecycle rule to delete in-progress uploads after 7 days. See the AWS guide:
@@ -265,6 +335,108 @@ 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:
@@ -282,20 +454,37 @@ LanceDB can also connect to S3-compatible stores, such as MinIO. To do so, you m
     )
     ```
 
-=== "JavaScript"
+=== "TypeScript"
 
-    ```javascript
+    === "@lancedb/lancedb"
-    const lancedb = require("lancedb");
+
-    const db = await lancedb.connect(
+        ```ts
-        "s3://bucket/path",
+        import * as lancedb from "@lancedb/lancedb";
-        {
+        const db = await lancedb.connect(
-            storageOptions: {
+            "s3://bucket/path",
-                region: "us-east-1",
+            {
-                endpoint: "http://minio:9000",
+                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.
 
@@ -326,21 +515,37 @@ To configure LanceDB to use an S3 Express endpoint, you must set the storage opt
     )
     ```
 
-=== "JavaScript"
+=== "TypeScript"
 
-    ```javascript
+    === "@lancedb/lancedb"
-    const lancedb = require("lancedb");
+
-    const db = await lancedb.connect(
+        ```ts
-        "s3://my-bucket--use1-az4--x-s3/path",
+        import * as lancedb from "@lancedb/lancedb";
-        {
+        const db = await lancedb.connect(
-            storageOptions: {
+            "s3://my-bucket--use1-az4--x-s3/path",
-                region: "us-east-1",
+            {
-                s3Express: "true",
+                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
 
@@ -359,26 +564,40 @@ GCS credentials are configured by setting the `GOOGLE_SERVICE_ACCOUNT` environme
     )
     ```
 
-=== "JavaScript"
+=== "TypeScript"
 
-    ```javascript
+    === "@lancedb/lancedb"
-    const lancedb = require("lancedb");
+
-    const db = await lancedb.connect(
+        ```ts
-        "gs://my-bucket/my-database",
+        import * as lancedb from "@lancedb/lancedb";
-        {
+        const db = await lancedb.connect(
-            storageOptions: {
+            "gs://my-bucket/my-database",
-                serviceAccount: "path/to/service-account.json",
+            {
+                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 -->
 
@@ -388,7 +607,6 @@ The following keys can be used as both environment variables or keys in the `sto
 | ``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:
@@ -407,20 +625,37 @@ Azure Blob Storage credentials can be configured by setting the `AZURE_STORAGE_A
     )
     ```
 
-=== "JavaScript"
+=== "TypeScript"
 
-    ```javascript
+    === "@lancedb/lancedb"
-    const lancedb = require("lancedb");
+
-    const db = await lancedb.connect(
+        ```ts
-        "az://my-container/my-database",
+        import * as lancedb from "@lancedb/lancedb";
-        {
+        const db = await lancedb.connect(
-            storageOptions: {
+            "az://my-container/my-database",
-                accountName: "some-account",
+            {
-                accountKey: "some-key",
+                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:
 
@@ -445,4 +680,4 @@ These keys can be used as both environment variables or keys in the `storage_opt
 | ``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 -->
+<!-- TODO: demonstrate how to configure networked file systems for optimal performance -->

docs/src/guides/tables.md

@@ -3,32 +3,46 @@
 
 A Table is a collection of Records in a LanceDB Database. Tables in Lance have a schema that defines the columns and their types. These schemas can include nested columns and can evolve over time.
 
-This guide will show how to create tables, insert data into them, and update the data.  
+This guide will show how to create tables, insert data into them, and update the data.
 
 
 ## 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 arrow = require("apache-arrow");
+
+        const uri = "data/sample-lancedb";
+        const db = await lancedb.connect(uri);
+        ```
+
+
+
 ### From list of tuples or dictionaries
 
 === "Python"
@@ -45,102 +59,150 @@ This guide will show how to create tables, insert data into them, and update the
 
     db["my_table"].head()
     ```
+
     !!! info "Note"
-        If the table already exists, LanceDB will raise an error by default. 
+        If the table already exists, LanceDB will raise an error by default.
 
         `create_table` supports an optional `exist_ok` 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.
 
-        ```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")
-        ```
-
-=== "Javascript"
-    You can create a LanceDB table in JavaScript using an array of JSON records as follows.
-
-    ```javascript
-    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.
-
-    ```javascript
-    const table = await con.createTable(tableName, data, { writeMode: WriteMode.Overwrite })
     ```
 
-    ### From a Pandas DataFrame
+    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
-    import pandas as pd
+    db.create_table("name", data, mode="overwrite")
-
-    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]
-    })
-
-    db.create_table("my_table", data)
-
-    db["my_table"].head()
     ```
-    !!! info "Note"
+
+=== "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.
+
+        ```ts
+        --8<-- "nodejs/examples/basic.ts:create_table_overwrite"
+        ```
+
+    === "vectordb (deprecated)"
+
+        ```ts
+        --8<-- "docs/src/basic_legacy.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<-- "docs/src/basic_legacy.ts:create_table_with_schema"
+        ```
+
+        !!! warning
+            `existsOk` is not available in `vectordb`
+
+
+
+            If the table already exists, vectordb will raise an error by default.
+            You can use `writeMode: WriteMode.Overwrite` to overwrite the table.
+            But this will delete the existing table and create a new one with the same name.
+
+
+        Sometimes you want to make sure that you start fresh.
+
+        If you want to overwrite the table, you can pass in `writeMode: lancedb.WriteMode.Overwrite` to the createTable function.
+
+        ```ts
+        const table = await con.createTable(tableName, data, {
+            writeMode: WriteMode.Overwrite
+        })
+        ```
+
+### From a Pandas DataFrame
+
+```python
+import pandas as pd
+
+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]
+})
+
+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
     import numpy as np
-    
+
     dim = 16
     total = 2
     schema = pa.schema(
@@ -160,13 +222,19 @@ This guide will show how to create tables, insert data into them, and update the
     tbl = db.create_table("f16_tbl", data, schema=schema)
     ```
 
-=== "Javascript"
+=== "Typescript[^1]"
-    You can also create LanceDB tables directly from Arrow tables. 
-    LanceDB supports Float16 data type!
 
-    ```javascript
+    === "@lancedb/lancedb"
-    --8<-- "docs/src/basic_legacy.ts:create_f16_table"
+
-    ```
+        ```typescript
+        --8<-- "nodejs/examples/basic.ts:create_f16_table"
+        ```
+
+    === "vectordb (deprecated)"
+
+        ```typescript
+        --8<-- "docs/src/basic_legacy.ts:create_f16_table"
+        ```
 
 ### From Pydantic Models
 
@@ -225,7 +293,7 @@ class NestedSchema(LanceModel):
 tbl = db.create_table("nested_table", schema=NestedSchema, mode="overwrite")
 ```
 
-This creates a struct column called "document" that has two subfields 
+This creates a struct column called "document" that has two subfields
 called "content" and "source":
 
 ```
@@ -236,7 +304,7 @@ 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    
+    child 1, source: string not null
 ```
 
 #### Validators
@@ -261,7 +329,7 @@ class TestModel(LanceModel):
     @classmethod
     def tz_must_match(cls, dt: datetime) -> datetime:
         assert dt.tzinfo == tz
-        return dt        
+        return dt
 
 ok = TestModel(dt_with_tz=datetime.now(tz))
 
@@ -329,23 +397,24 @@ You can also use iterators of other types like Pandas DataFrame or Pylists direc
     tbl = db.open_table("my_table")
     ```
 
-=== "JavaScript"
+=== "Typescript[^1]"
+
     If you forget the name of your table, you can always get a listing of all table names.
 
-    ```javascript
+    ```typescript
     console.log(await db.tableNames());
     ```
 
     Then, you can open any existing tables.
 
-    ```javascript
+    ```typescript
     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
 
@@ -364,8 +433,8 @@ You can also use iterators of other types like Pandas DataFrame or Pylists direc
     tbl = db.create_table("empty_table_add", schema=schema)
     ```
 
-    Alternatively, you can also use Pydantic to specify the schema for the empty table. Note that we do not 
+    Alternatively, you can also use Pydantic to specify the schema for the empty table. Note that we do not
-    directly import `pydantic` but instead use `lancedb.pydantic` which is a subclass of `pydantic.BaseModel` 
+    directly import `pydantic` but instead use `lancedb.pydantic` which is a subclass of `pydantic.BaseModel`
     that has been extended to support LanceDB specific types like `Vector`.
 
     ```python
@@ -382,9 +451,23 @@ You can also use iterators of other types like Pandas DataFrame or Pylists direc
 
     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 using the various methods available.
+After a table has been created, you can always add more data to it usind the `add` method
 
 === "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.
@@ -452,8 +535,27 @@ After a table has been created, you can always add more data to it using the var
     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.
 
-=== "JavaScript"
+        ```python
+        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(
@@ -509,15 +611,15 @@ Use the `delete()` method on tables to delete rows from a table. To choose which
     # 0  3  [5.0, 6.0]
     ```
 
-=== "JavaScript"
+=== "Typescript[^1]"
 
-    ```javascript
+    ```ts
     await tbl.delete('item = "fizz"')
     ```
 
     ### Deleting row with specific column value
 
-    ```javascript
+    ```ts
     const con = await lancedb.connect("./.lancedb")
     const data = [
       {id: 1, vector: [1, 2]},
@@ -531,7 +633,7 @@ Use the `delete()` method on tables to delete rows from a table. To choose which
 
     ### Delete from a list of values
 
-    ```javascript
+    ```ts
     const to_remove = [1, 5];
     await tbl.delete(`id IN (${to_remove.join(",")})`)
     await tbl.countRows() // Returns 1
@@ -588,26 +690,49 @@ This can be used to update zero to all rows depending on how many rows match the
     2  2  [10.0, 10.0]
     ```
 
-=== "JavaScript/Typescript"
+=== "Typescript[^1]"
 
-    API Reference: [vectordb.Table.update](../javascript/interfaces/Table.md/#update)
+    === "@lancedb/lancedb"
 
-    ```javascript
+        API Reference: [lancedb.Table.update](../js/classes/Table.md/#update)
-    const lancedb = require("vectordb");
 
-    const db = await lancedb.connect("./.lancedb");
+        ```ts
+        import * as lancedb from "@lancedb/lancedb";
 
-    const data = [
+        const db = await lancedb.connect("./.lancedb");
-      {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]} })
+        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)
 
-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.
+        await tbl.update({vector: [10, 10]}, { where: "x = 2"})
+        ```
+
+    === "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"
 
@@ -626,16 +751,47 @@ The `values` parameter is used to provide the new values for the columns as lite
     2  3  [10.0, 10.0]
     ```
 
-=== "JavaScript/Typescript"
+=== "Typescript[^1]"
 
-    ```javascript
+    === "@lancedb/lancedb"
-    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.
@@ -651,7 +807,7 @@ There are three possible settings for `read_consistency_interval`:
     This is only tune-able in LanceDB OSS. In LanceDB Cloud, readers are always eventually consistent.
 
 === "Python"
-    
+
     To set strong consistency, use `timedelta(0)`:
 
     ```python
@@ -673,33 +829,35 @@ There are three possible settings for `read_consistency_interval`:
     ```python
     db = lancedb.connect("./.lancedb")
     table = db.open_table("my_table")
-    
+
     # (Other writes happen to my_table from another process)
 
     # Check for updates
     table.checkout_latest()
     ```
 
-=== "JavaScript/Typescript"
+=== "Typescript[^1]"
 
     To set strong consistency, use `0`:
 
-    ```javascript
+    ```ts
     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:
 
-    ```javascript
+    ```ts
     const db = await lancedb.connect({ uri: "./.lancedb", readConsistencyInterval: 5 });
     const table = await db.openTable("my_table");
     ```
 
-<!-- Node doesn't yet support the version time travel: https://github.com/lancedb/lancedb/issues/1007 
+<!-- Node doesn't yet support the version time travel: https://github.com/lancedb/lancedb/issues/1007
     Once it does, we can show manual consistency check for Node as well.
 -->
 
 ## What's next?
 
-Learn the best practices on creating an ANN index and getting the most out of it.
+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

@@ -0,0 +1,131 @@
+## 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

@@ -0,0 +1,80 @@
+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

@@ -0,0 +1,82 @@
+## 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

@@ -5,7 +5,9 @@ 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/integrations/langchain.md

@@ -2,7 +2,7 @@
 ![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.
+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
@@ -38,6 +38,8 @@ The exhaustive list of parameters for `LanceDB` vector store are :
 - `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
@@ -54,12 +56,14 @@ vector_store = LanceDB(
 ```
 
 ### Methods 
-To add texts and store respective embeddings automatically:   
+
 ##### 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'}]) 
@@ -74,7 +78,6 @@ 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)
 ```
-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.
 ##### create_index() 
 - `col_name`: `Optional[str] = None`
 - `vector_col`: `Optional[str] = None`
@@ -82,6 +85,8 @@ For index creation make sure your table has enough data in it. An ANN index is u
 - `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')
@@ -89,4 +94,108 @@ 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

@@ -0,0 +1,142 @@
+# 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/README.md

@@ -1,4 +1,6 @@
-@lancedb/lancedb / [Exports](modules.md)
+**@lancedb/lancedb** • [**Docs**](globals.md)
+
+***
 
 # LanceDB JavaScript SDK
 
@@ -45,29 +47,20 @@ npm run test
 
 ### Running lint / format
 
-LanceDb uses eslint for linting. VSCode does not need any plugins to use eslint. However, it
+LanceDb uses [biome](https://biomejs.dev/) for linting and formatting. if you are using VSCode you will need to install the official [Biome](https://marketplace.visualstudio.com/items?itemName=biomejs.biome) extension.
-may need some additional configuration. Make sure that eslint.experimental.useFlatConfig is
+To manually lint your code you can run:
-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
+to automatically fix all fixable issues:
-"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
+npm run lint-fix
 ```
 
-If you need to manually format your code you can run:
+If you do not have your workspace root set to the `nodejs` directory, unfortunately the extension will not work. You can still run the linting and formatting commands manually.
-
-```sh
-npx prettier --write .
-```
 
 ### Generating docs
 

docs/src/js/classes/Connection.md

@@ -1,6 +1,10 @@
-[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / Connection
+[**@lancedb/lancedb**](../README.md) • **Docs**
 
-# Class: Connection
+***
+
+[@lancedb/lancedb](../globals.md) / Connection
+
+# Class: `abstract` Connection
 
 A LanceDB Connection that allows you to open tables and create new ones.
 
@@ -19,62 +23,21 @@ 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()
 
-• **new Connection**(`inner`): [`Connection`](Connection.md)
+> **new Connection**(): [`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()
 
-▸ **close**(): `void`
+> `abstract` **close**(): `void`
 
 Close the connection, releasing any underlying resources.
 
@@ -86,63 +49,78 @@ Any attempt to use the connection after it is closed will result in an error.
 
 `void`
 
-#### Defined in
+***
 
-[connection.ts:88](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/connection.ts#L88)
+### createEmptyTable()
 
-___
+> `abstract` **createEmptyTable**(`name`, `schema`, `options`?): `Promise`<[`Table`](Table.md)>
-
-### createEmptyTable
-
-▸ **createEmptyTable**(`name`, `schema`, `options?`): `Promise`\<[`Table`](Table.md)\>
 
 Creates a new empty Table
 
 #### Parameters
 
-| Name | Type | Description |
+• **name**: `string`
-| :------ | :------ | :------ |
+
-| `name` | `string` | The name of the table. |
+The name of the table.
-| `schema` | `Schema`\<`any`\> | The schema of the table |
+
-| `options?` | `Partial`\<[`CreateTableOptions`](../interfaces/CreateTableOptions.md)\> | - |
+• **schema**: `SchemaLike`
+
+The schema of the table
+
+• **options?**: `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
 
 #### Returns
 
-`Promise`\<[`Table`](Table.md)\>
+`Promise`&lt;[`Table`](Table.md)&gt;
 
-#### Defined in
+***
 
-[connection.ts:151](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/connection.ts#L151)
+### createTable()
 
-___
+#### createTable(options)
 
-### createTable
+> `abstract` **createTable**(`options`): `Promise`&lt;[`Table`](Table.md)&gt;
-
-▸ **createTable**(`name`, `data`, `options?`): `Promise`\<[`Table`](Table.md)\>
 
 Creates a new Table and initialize it with new data.
 
-#### Parameters
+##### Parameters
 
-| Name | Type | Description |
+• **options**: `object` & `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
-| :------ | :------ | :------ |
-| `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
+The options object.
 
-`Promise`\<[`Table`](Table.md)\>
+##### Returns
 
-#### Defined in
+`Promise`&lt;[`Table`](Table.md)&gt;
 
-[connection.ts:123](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/connection.ts#L123)
+#### createTable(name, data, options)
 
-___
+> `abstract` **createTable**(`name`, `data`, `options`?): `Promise`&lt;[`Table`](Table.md)&gt;
 
-### display
+Creates a new Table and initialize it with new data.
 
-▸ **display**(): `string`
+##### Parameters
+
+• **name**: `string`
+
+The name of the table.
+
+• **data**: `TableLike` \| `Record`&lt;`string`, `unknown`&gt;[]
+
+Non-empty Array of Records
+to be inserted into the table
+
+• **options?**: `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
+
+##### Returns
+
+`Promise`&lt;[`Table`](Table.md)&gt;
+
+***
+
+### display()
+
+> `abstract` **display**(): `string`
 
 Return a brief description of the connection
 
@@ -150,37 +128,29 @@ Return a brief description of the connection
 
 `string`
 
-#### Defined in
+***
 
-[connection.ts:93](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/connection.ts#L93)
+### dropTable()
 
-___
+> `abstract` **dropTable**(`name`): `Promise`&lt;`void`&gt;
-
-### dropTable
-
-▸ **dropTable**(`name`): `Promise`\<`void`\>
 
 Drop an existing table.
 
 #### Parameters
 
-| Name | Type | Description |
+• **name**: `string`
-| :------ | :------ | :------ |
+
-| `name` | `string` | The name of the table to drop. |
+The name of the table to drop.
 
 #### Returns
 
-`Promise`\<`void`\>
+`Promise`&lt;`void`&gt;
 
-#### Defined in
+***
 
-[connection.ts:173](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/connection.ts#L173)
+### isOpen()
 
-___
+> `abstract` **isOpen**(): `boolean`
-
-### isOpen
-
-▸ **isOpen**(): `boolean`
 
 Return true if the connection has not been closed
 
@@ -188,37 +158,31 @@ Return true if the connection has not been closed
 
 `boolean`
 
-#### Defined in
+***
 
-[connection.ts:77](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/connection.ts#L77)
+### openTable()
 
-___
+> `abstract` **openTable**(`name`, `options`?): `Promise`&lt;[`Table`](Table.md)&gt;
-
-### openTable
-
-▸ **openTable**(`name`): `Promise`\<[`Table`](Table.md)\>
 
 Open a table in the database.
 
 #### Parameters
 
-| Name | Type | Description |
+• **name**: `string`
-| :------ | :------ | :------ |
+
-| `name` | `string` | The name of the table |
+The name of the table
+
+• **options?**: `Partial`&lt;`OpenTableOptions`&gt;
 
 #### Returns
 
-`Promise`\<[`Table`](Table.md)\>
+`Promise`&lt;[`Table`](Table.md)&gt;
 
-#### Defined in
+***
 
-[connection.ts:112](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/connection.ts#L112)
+### tableNames()
 
-___
+> `abstract` **tableNames**(`options`?): `Promise`&lt;`string`[]&gt;
-
-### tableNames
-
-▸ **tableNames**(`options?`): `Promise`\<`string`[]\>
 
 List all the table names in this database.
 
@@ -226,14 +190,11 @@ Tables will be returned in lexicographical order.
 
 #### Parameters
 
-| Name | Type | Description |
+• **options?**: `Partial`&lt;[`TableNamesOptions`](../interfaces/TableNamesOptions.md)&gt;
-| :------ | :------ | :------ |
+
-| `options?` | `Partial`\<[`TableNamesOptions`](../interfaces/TableNamesOptions.md)\> | options to control the paging / start point |
+options to control the
+paging / start point
 
 #### Returns
 
-`Promise`\<`string`[]\>
+`Promise`&lt;`string`[]&gt;
-
-#### Defined in
-
-[connection.ts:104](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/connection.ts#L104)

docs/src/js/classes/Index.md

@@ -1,57 +1,16 @@
-[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / Index
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.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()
 
-▸ **btree**(): [`Index`](Index.md)
+> `static` **btree**(): [`Index`](Index.md)
 
 Create a btree index
 
@@ -75,15 +34,11 @@ block size may be added in the future.
 
 [`Index`](Index.md)
 
-#### Defined in
+***
 
-[indices.ts:175](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/indices.ts#L175)
+### ivfPq()
 
-___
+> `static` **ivfPq**(`options`?): [`Index`](Index.md)
-
-### ivfPq
-
-▸ **ivfPq**(`options?`): [`Index`](Index.md)
 
 Create an IvfPq index
 
@@ -108,14 +63,8 @@ currently is also a memory intensive operation.
 
 #### Parameters
 
-| Name | Type |
+• **options?**: `Partial`<[`IvfPqOptions`](../interfaces/IvfPqOptions.md)>
-| :------ | :------ |
-| `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

@@ -1,46 +1,32 @@
-[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / MakeArrowTableOptions
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.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()
 
-• **new MakeArrowTableOptions**(`values?`): [`MakeArrowTableOptions`](MakeArrowTableOptions.md)
+> **new MakeArrowTableOptions**(`values`?): [`MakeArrowTableOptions`](MakeArrowTableOptions.md)
 
 #### Parameters
 
-| Name | Type |
+• **values?**: `Partial`<[`MakeArrowTableOptions`](MakeArrowTableOptions.md)>
-| :------ | :------ |
-| `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`
+> **dictionaryEncodeStrings**: `boolean` = `false`
 
 If true then string columns will be encoded with dictionary encoding
 
@@ -50,26 +36,26 @@ 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)
+### embeddingFunction?
 
-___
+> `optional` **embeddingFunction**: [`EmbeddingFunctionConfig`](../namespaces/embedding/interfaces/EmbeddingFunctionConfig.md)
 
-### schema
+***
 
-• `Optional` **schema**: `Schema`\<`any`\>
+### embeddings?
 
-#### Defined in
+> `optional` **embeddings**: [`EmbeddingFunction`](../namespaces/embedding/classes/EmbeddingFunction.md)&lt;`unknown`, `FunctionOptions`&gt;
 
-[arrow.ts:67](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/arrow.ts#L67)
+***
 
-___
+### schema?
+
+> `optional` **schema**: `SchemaLike`
+
+***
 
 ### vectorColumns
 
-• **vectorColumns**: `Record`\<`string`, [`VectorColumnOptions`](VectorColumnOptions.md)\>
+> **vectorColumns**: `Record`&lt;`string`, [`VectorColumnOptions`](VectorColumnOptions.md)&gt;
-
-#### Defined in
-
-[arrow.ts:85](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/arrow.ts#L85)

docs/src/js/classes/Query.md

@@ -1,48 +1,26 @@
-[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / Query
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / Query
 
 # Class: Query
 
 A builder for LanceDB queries.
 
-## Hierarchy
+## Extends
 
-- [`QueryBase`](QueryBase.md)\<`NativeQuery`, [`Query`](Query.md)\>
+- [`QueryBase`](QueryBase.md)&lt;`NativeQuery`&gt;
-
-  ↳ **`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()
 
-• **new Query**(`tbl`): [`Query`](Query.md)
+> **new Query**(`tbl`): [`Query`](Query.md)
 
 #### Parameters
 
-| Name | Type |
+• **tbl**: `Table`
-| :------ | :------ |
-| `tbl` | `Table` |
 
 #### Returns
 
@@ -50,57 +28,67 @@ A builder for LanceDB queries.
 
 #### Overrides
 
-[QueryBase](QueryBase.md).[constructor](QueryBase.md#constructor)
+[`QueryBase`](QueryBase.md).[`constructor`](QueryBase.md#constructors)
-
-#### Defined in
-
-[query.ts:329](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L329)
 
 ## Properties
 
 ### inner
 
-• `Protected` **inner**: `Query`
+> `protected` **inner**: `Query` \| `Promise`&lt;`Query`&gt;
 
 #### Inherited from
 
-[QueryBase](QueryBase.md).[inner](QueryBase.md#inner)
+[`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]**(): `AsyncIterator`\<`RecordBatch`\<`any`\>, `any`, `undefined`\>
+> **\[asyncIterator\]**(): `AsyncIterator`&lt;`RecordBatch`&lt;`any`&gt;, `any`, `undefined`&gt;
 
 #### Returns
 
-`AsyncIterator`\<`RecordBatch`\<`any`\>, `any`, `undefined`\>
+`AsyncIterator`&lt;`RecordBatch`&lt;`any`&gt;, `any`, `undefined`&gt;
 
 #### Inherited from
 
-[QueryBase](QueryBase.md).[[asyncIterator]](QueryBase.md#[asynciterator])
+[`QueryBase`](QueryBase.md).[`[asyncIterator]`](QueryBase.md#%5Basynciterator%5D)
 
-#### Defined in
+***
 
-[query.ts:154](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L154)
+### doCall()
 
-___
+> `protected` **doCall**(`fn`): `void`
 
-### execute
+#### Parameters
 
-▸ **execute**(): [`RecordBatchIterator`](RecordBatchIterator.md)
+• **fn**
+
+#### Returns
+
+`void`
+
+#### Inherited from
+
+[`QueryBase`](QueryBase.md).[`doCall`](QueryBase.md#docall)
+
+***
+
+### execute()
+
+> `protected` **execute**(`options`?): [`RecordBatchIterator`](RecordBatchIterator.md)
 
 Execute the query and return the results as an
 
+#### Parameters
+
+• **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
+
 #### Returns
 
 [`RecordBatchIterator`](RecordBatchIterator.md)
 
-**`See`**
+#### See
 
  - AsyncIterator
 of
@@ -114,17 +102,76 @@ single query)
 
 #### Inherited from
 
-[QueryBase](QueryBase.md).[execute](QueryBase.md#execute)
+[`QueryBase`](QueryBase.md).[`execute`](QueryBase.md#execute)
 
-#### Defined in
+***
 
-[query.ts:149](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L149)
+### explainPlan()
 
-___
+> **explainPlan**(`verbose`): `Promise`&lt;`string`&gt;
 
-### limit
+Generates an explanation of the query execution plan.
 
-▸ **limit**(`limit`): [`Query`](Query.md)
+#### Parameters
+
+• **verbose**: `boolean` = `false`
+
+If true, provides a more detailed explanation. Defaults to false.
+
+#### Returns
+
+`Promise`&lt;`string`&gt;
+
+A Promise that resolves to a string containing the query execution plan explanation.
+
+#### Example
+
+```ts
+import * as lancedb from "@lancedb/lancedb"
+const db = await lancedb.connect("./.lancedb");
+const table = await db.createTable("my_table", [
+  { vector: [1.1, 0.9], id: "1" },
+]);
+const plan = await table.query().nearestTo([0.5, 0.2]).explainPlan();
+```
+
+#### Inherited from
+
+[`QueryBase`](QueryBase.md).[`explainPlan`](QueryBase.md#explainplan)
+
+***
+
+### ~~filter()~~
+
+> **filter**(`predicate`): `this`
+
+A filter statement to be applied to this query.
+
+#### Parameters
+
+• **predicate**: `string`
+
+#### Returns
+
+`this`
+
+#### Alias
+
+where
+
+#### Deprecated
+
+Use `where` instead
+
+#### Inherited from
+
+[`QueryBase`](QueryBase.md).[`filter`](QueryBase.md#filter)
+
+***
+
+### limit()
+
+> **limit**(`limit`): `this`
 
 Set the maximum number of results to return.
 
@@ -133,45 +180,39 @@ called then every valid row from the table will be returned.
 
 #### Parameters
 
-| Name | Type |
+• **limit**: `number`
-| :------ | :------ |
-| `limit` | `number` |
 
 #### Returns
 
-[`Query`](Query.md)
+`this`
 
 #### Inherited from
 
-[QueryBase](QueryBase.md).[limit](QueryBase.md#limit)
+[`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()
 
-___
+> `protected` **nativeExecute**(`options`?): `Promise`&lt;`RecordBatchIterator`&gt;
 
-### nativeExecute
+#### Parameters
 
-▸ **nativeExecute**(): `Promise`\<`RecordBatchIterator`\>
+• **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
 
 #### Returns
 
-`Promise`\<`RecordBatchIterator`\>
+`Promise`&lt;`RecordBatchIterator`&gt;
 
 #### Inherited from
 
-[QueryBase](QueryBase.md).[nativeExecute](QueryBase.md#nativeexecute)
+[`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)
-
-### nearestTo
-
-▸ **nearestTo**(`vector`): [`VectorQuery`](VectorQuery.md)
 
 Find the nearest vectors to the given query vector.
 
@@ -191,15 +232,13 @@ If there is more than one vector column you must use
 
 #### Parameters
 
-| Name | Type |
+• **vector**: `IntoVector`
-| :------ | :------ |
-| `vector` | `unknown` |
 
 #### Returns
 
 [`VectorQuery`](VectorQuery.md)
 
-**`See`**
+#### See
 
  - [VectorQuery#column](VectorQuery.md#column)  to specify which column you would like
 to compare with.
@@ -223,15 +262,11 @@ 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`): `this`
-
-### select
-
-▸ **select**(`columns`): [`Query`](Query.md)
 
 Return only the specified columns.
 
@@ -255,15 +290,13 @@ input to this method would be:
 
 #### Parameters
 
-| Name | Type |
+• **columns**: `string` \| `string`[] \| `Record`&lt;`string`, `string`&gt; \| `Map`&lt;`string`, `string`&gt;
-| :------ | :------ |
-| `columns` | `string`[] \| `Record`\<`string`, `string`\> \| `Map`\<`string`, `string`\> |
 
 #### Returns
 
-[`Query`](Query.md)
+`this`
 
-**`Example`**
+#### Example
 
 ```ts
 new Map([["combined", "a + b"], ["c", "c"]])
@@ -278,61 +311,57 @@ object insertion order is easy to get wrong and `Map` is more foolproof.
 
 #### Inherited from
 
-[QueryBase](QueryBase.md).[select](QueryBase.md#select)
+[`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**(`options`?): `Promise`&lt;`any`[]&gt;
-
-### toArray
-
-▸ **toArray**(): `Promise`\<`unknown`[]\>
 
 Collect the results as an array of objects.
 
+#### Parameters
+
+• **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
+
 #### Returns
 
-`Promise`\<`unknown`[]\>
+`Promise`&lt;`any`[]&gt;
 
 #### Inherited from
 
-[QueryBase](QueryBase.md).[toArray](QueryBase.md#toarray)
+[`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**(`options`?): `Promise`&lt;`Table`&lt;`any`&gt;&gt;
-
-### toArrow
-
-▸ **toArrow**(): `Promise`\<`Table`\<`any`\>\>
 
 Collect the results as an Arrow
 
+#### Parameters
+
+• **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
+
 #### Returns
 
-`Promise`\<`Table`\<`any`\>\>
+`Promise`&lt;`Table`&lt;`any`&gt;&gt;
 
-**`See`**
+#### See
 
 ArrowTable.
 
 #### Inherited from
 
-[QueryBase](QueryBase.md).[toArrow](QueryBase.md#toarrow)
+[`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`): `this`
-
-### where
-
-▸ **where**(`predicate`): [`Query`](Query.md)
 
 A filter statement to be applied to this query.
 
@@ -340,15 +369,13 @@ The filter should be supplied as an SQL query string.  For example:
 
 #### Parameters
 
-| Name | Type |
+• **predicate**: `string`
-| :------ | :------ |
-| `predicate` | `string` |
 
 #### Returns
 
-[`Query`](Query.md)
+`this`
 
-**`Example`**
+#### Example
 
 ```ts
 x > 10
@@ -361,8 +388,4 @@ on the filter column(s).
 
 #### Inherited from
 
-[QueryBase](QueryBase.md).[where](QueryBase.md#where)
+[`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

@@ -1,117 +1,91 @@
-[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / QueryBase
+[**@lancedb/lancedb**](../README.md) • **Docs**
 
-# Class: QueryBase\<NativeQueryType, QueryType\>
+***
+
+[@lancedb/lancedb](../globals.md) / QueryBase
+
+# Class: QueryBase&lt;NativeQueryType&gt;
 
 Common methods supported by all query types
 
-## Type parameters
+## Extended by
 
-| Name | Type |
+- [`Query`](Query.md)
-| :------ | :------ |
+- [`VectorQuery`](VectorQuery.md)
-| `NativeQueryType` | extends `NativeQuery` \| `NativeVectorQuery` |
-| `QueryType` | `QueryType` |
 
-## Hierarchy
+## Type Parameters
 
-- **`QueryBase`**
+• **NativeQueryType** *extends* `NativeQuery` \| `NativeVectorQuery`
-
-  ↳ [`Query`](Query.md)
-
-  ↳ [`VectorQuery`](VectorQuery.md)
 
 ## Implements
 
-- `AsyncIterable`\<`RecordBatch`\>
+- `AsyncIterable`&lt;`RecordBatch`&gt;
-
-## 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()
 
-• **new QueryBase**\<`NativeQueryType`, `QueryType`\>(`inner`): [`QueryBase`](QueryBase.md)\<`NativeQueryType`, `QueryType`\>
+> `protected` **new QueryBase**&lt;`NativeQueryType`&gt;(`inner`): [`QueryBase`](QueryBase.md)&lt;`NativeQueryType`&gt;
-
-#### Type parameters
-
-| Name | Type |
-| :------ | :------ |
-| `NativeQueryType` | extends `Query` \| `VectorQuery` |
-| `QueryType` | `QueryType` |
 
 #### Parameters
 
-| Name | Type |
+• **inner**: `NativeQueryType` \| `Promise`&lt;`NativeQueryType`&gt;
-| :------ | :------ |
-| `inner` | `NativeQueryType` |
 
 #### Returns
 
-[`QueryBase`](QueryBase.md)\<`NativeQueryType`, `QueryType`\>
+[`QueryBase`](QueryBase.md)&lt;`NativeQueryType`&gt;
-
-#### Defined in
-
-[query.ts:59](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L59)
 
 ## Properties
 
 ### inner
 
-• `Protected` **inner**: `NativeQueryType`
+> `protected` **inner**: `NativeQueryType` \| `Promise`&lt;`NativeQueryType`&gt;
-
-#### Defined in
-
-[query.ts:59](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L59)
 
 ## Methods
 
-### [asyncIterator]
+### \[asyncIterator\]()
 
-▸ **[asyncIterator]**(): `AsyncIterator`\<`RecordBatch`\<`any`\>, `any`, `undefined`\>
+> **\[asyncIterator\]**(): `AsyncIterator`&lt;`RecordBatch`&lt;`any`&gt;, `any`, `undefined`&gt;
 
 #### Returns
 
-`AsyncIterator`\<`RecordBatch`\<`any`\>, `any`, `undefined`\>
+`AsyncIterator`&lt;`RecordBatch`&lt;`any`&gt;, `any`, `undefined`&gt;
 
 #### Implementation of
 
-AsyncIterable.[asyncIterator]
+`AsyncIterable.[asyncIterator]`
 
-#### Defined in
+***
 
-[query.ts:154](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L154)
+### doCall()
 
-___
+> `protected` **doCall**(`fn`): `void`
 
-### execute
+#### Parameters
 
-▸ **execute**(): [`RecordBatchIterator`](RecordBatchIterator.md)
+• **fn**
+
+#### Returns
+
+`void`
+
+***
+
+### execute()
+
+> `protected` **execute**(`options`?): [`RecordBatchIterator`](RecordBatchIterator.md)
 
 Execute the query and return the results as an
 
+#### Parameters
+
+• **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
+
 #### Returns
 
 [`RecordBatchIterator`](RecordBatchIterator.md)
 
-**`See`**
+#### See
 
  - AsyncIterator
 of
@@ -123,15 +97,66 @@ 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)
+### explainPlan()
 
-___
+> **explainPlan**(`verbose`): `Promise`&lt;`string`&gt;
 
-### limit
+Generates an explanation of the query execution plan.
 
-▸ **limit**(`limit`): `QueryType`
+#### Parameters
+
+• **verbose**: `boolean` = `false`
+
+If true, provides a more detailed explanation. Defaults to false.
+
+#### Returns
+
+`Promise`&lt;`string`&gt;
+
+A Promise that resolves to a string containing the query execution plan explanation.
+
+#### Example
+
+```ts
+import * as lancedb from "@lancedb/lancedb"
+const db = await lancedb.connect("./.lancedb");
+const table = await db.createTable("my_table", [
+  { vector: [1.1, 0.9], id: "1" },
+]);
+const plan = await table.query().nearestTo([0.5, 0.2]).explainPlan();
+```
+
+***
+
+### ~~filter()~~
+
+> **filter**(`predicate`): `this`
+
+A filter statement to be applied to this query.
+
+#### Parameters
+
+• **predicate**: `string`
+
+#### Returns
+
+`this`
+
+#### Alias
+
+where
+
+#### Deprecated
+
+Use `where` instead
+
+***
+
+### limit()
+
+> **limit**(`limit`): `this`
 
 Set the maximum number of results to return.
 
@@ -140,37 +165,31 @@ called then every valid row from the table will be returned.
 
 #### Parameters
 
-| Name | Type |
+• **limit**: `number`
-| :------ | :------ |
-| `limit` | `number` |
 
 #### Returns
 
-`QueryType`
+`this`
 
-#### Defined in
+***
 
-[query.ts:129](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L129)
+### nativeExecute()
 
-___
+> `protected` **nativeExecute**(`options`?): `Promise`&lt;`RecordBatchIterator`&gt;
 
-### nativeExecute
+#### Parameters
 
-▸ **nativeExecute**(): `Promise`\<`RecordBatchIterator`\>
+• **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
 
 #### Returns
 
-`Promise`\<`RecordBatchIterator`\>
+`Promise`&lt;`RecordBatchIterator`&gt;
 
-#### Defined in
+***
 
-[query.ts:134](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L134)
+### select()
 
-___
+> **select**(`columns`): `this`
-
-### select
-
-▸ **select**(`columns`): `QueryType`
 
 Return only the specified columns.
 
@@ -194,15 +213,13 @@ input to this method would be:
 
 #### Parameters
 
-| Name | Type |
+• **columns**: `string` \| `string`[] \| `Record`&lt;`string`, `string`&gt; \| `Map`&lt;`string`, `string`&gt;
-| :------ | :------ |
-| `columns` | `string`[] \| `Record`\<`string`, `string`\> \| `Map`\<`string`, `string`\> |
 
 #### Returns
 
-`QueryType`
+`this`
 
-**`Example`**
+#### Example
 
 ```ts
 new Map([["combined", "a + b"], ["c", "c"]])
@@ -215,51 +232,47 @@ uses `Object.entries` which should preserve the insertion order of the object.
 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**(`options`?): `Promise`&lt;`any`[]&gt;
-
-### toArray
-
-▸ **toArray**(): `Promise`\<`unknown`[]\>
 
 Collect the results as an array of objects.
 
+#### Parameters
+
+• **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
+
 #### Returns
 
-`Promise`\<`unknown`[]\>
+`Promise`&lt;`any`[]&gt;
 
-#### Defined in
+***
 
-[query.ts:169](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L169)
+### toArrow()
 
-___
+> **toArrow**(`options`?): `Promise`&lt;`Table`&lt;`any`&gt;&gt;
-
-### toArrow
-
-▸ **toArrow**(): `Promise`\<`Table`\<`any`\>\>
 
 Collect the results as an Arrow
 
+#### Parameters
+
+• **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
+
 #### Returns
 
-`Promise`\<`Table`\<`any`\>\>
+`Promise`&lt;`Table`&lt;`any`&gt;&gt;
 
-**`See`**
+#### See
 
 ArrowTable.
 
-#### Defined in
+***
 
-[query.ts:160](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L160)
+### where()
 
-___
+> **where**(`predicate`): `this`
-
-### where
-
-▸ **where**(`predicate`): `QueryType`
 
 A filter statement to be applied to this query.
 
@@ -267,15 +280,13 @@ The filter should be supplied as an SQL query string.  For example:
 
 #### Parameters
 
-| Name | Type |
+• **predicate**: `string`
-| :------ | :------ |
-| `predicate` | `string` |
 
 #### Returns
 
-`QueryType`
+`this`
 
-**`Example`**
+#### Example
 
 ```ts
 x > 10
@@ -285,7 +296,3 @@ 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 +1,39 @@
-[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / RecordBatchIterator
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / RecordBatchIterator
 
 # Class: RecordBatchIterator
 
 ## Implements
 
-- `AsyncIterator`\<`RecordBatch`\>
+- `AsyncIterator`&lt;`RecordBatch`&gt;
-
-## 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()
 
-• **new RecordBatchIterator**(`promise?`): [`RecordBatchIterator`](RecordBatchIterator.md)
+> **new RecordBatchIterator**(`promise`?): [`RecordBatchIterator`](RecordBatchIterator.md)
 
 #### Parameters
 
-| Name | Type |
+• **promise?**: `Promise`&lt;`RecordBatchIterator`&gt;
-| :------ | :------ |
-| `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()
 
-▸ **next**(): `Promise`\<`IteratorResult`\<`RecordBatch`\<`any`\>, `any`\>\>
+> **next**(): `Promise`&lt;`IteratorResult`&lt;`RecordBatch`&lt;`any`&gt;, `any`&gt;&gt;
 
 #### Returns
 
-`Promise`\<`IteratorResult`\<`RecordBatch`\<`any`\>, `any`\>\>
+`Promise`&lt;`IteratorResult`&lt;`RecordBatch`&lt;`any`&gt;, `any`&gt;&gt;
 
 #### Implementation of
 
-AsyncIterator.next
+`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

@@ -1,6 +1,10 @@
-[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / Table
+[**@lancedb/lancedb**](../README.md) • **Docs**
 
-# Class: Table
+***
+
+[@lancedb/lancedb](../globals.md) / Table
+
+# Class: `abstract` Table
 
 A Table is a collection of Records in a LanceDB Database.
 
@@ -13,196 +17,149 @@ 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()
 
-• **new Table**(`inner`): [`Table`](Table.md)
+> **new Table**(): [`Table`](Table.md)
-
-Construct a Table. Internal use only.
-
-#### Parameters
-
-| Name | Type |
-| :------ | :------ |
-| `inner` | `Table` |
 
 #### Returns
 
 [`Table`](Table.md)
 
-#### Defined in
+## Accessors
 
-[table.ts:69](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L69)
+### name
 
-## Properties
+> `get` `abstract` **name**(): `string`
 
-### inner
+Returns the name of the table
 
-• `Private` `Readonly` **inner**: `Table`
+#### Returns
 
-#### Defined in
+`string`
-
-[table.ts:66](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L66)
 
 ## Methods
 
-### add
+### add()
 
-▸ **add**(`data`, `options?`): `Promise`\<`void`\>
+> `abstract` **add**(`data`, `options`?): `Promise`&lt;`void`&gt;
 
 Insert records into this Table.
 
 #### Parameters
 
-| Name | Type | Description |
+• **data**: [`Data`](../type-aliases/Data.md)
-| :------ | :------ | :------ |
+
-| `data` | [`Data`](../modules.md#data) | Records to be inserted into the Table |
+Records to be inserted into the Table
-| `options?` | `Partial`\<[`AddDataOptions`](../interfaces/AddDataOptions.md)\> | - |
+
+• **options?**: `Partial`&lt;[`AddDataOptions`](../interfaces/AddDataOptions.md)&gt;
 
 #### Returns
 
-`Promise`\<`void`\>
+`Promise`&lt;`void`&gt;
 
-#### Defined in
+***
 
-[table.ts:105](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L105)
+### addColumns()
 
-___
+> `abstract` **addColumns**(`newColumnTransforms`): `Promise`&lt;`void`&gt;
-
-### addColumns
-
-▸ **addColumns**(`newColumnTransforms`): `Promise`\<`void`\>
 
 Add new columns with defined values.
 
 #### Parameters
 
-| Name | Type | Description |
+• **newColumnTransforms**: [`AddColumnsSql`](../interfaces/AddColumnsSql.md)[]
-| :------ | :------ | :------ |
+
-| `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. |
+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`\>
+`Promise`&lt;`void`&gt;
 
-#### Defined in
+***
 
-[table.ts:261](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L261)
+### alterColumns()
 
-___
+> `abstract` **alterColumns**(`columnAlterations`): `Promise`&lt;`void`&gt;
-
-### alterColumns
-
-▸ **alterColumns**(`columnAlterations`): `Promise`\<`void`\>
 
 Alter the name or nullability of columns.
 
 #### Parameters
 
-| Name | Type | Description |
+• **columnAlterations**: [`ColumnAlteration`](../interfaces/ColumnAlteration.md)[]
-| :------ | :------ | :------ |
+
-| `columnAlterations` | [`ColumnAlteration`](../interfaces/ColumnAlteration.md)[] | One or more alterations to apply to columns. |
+One or more alterations to
+apply to columns.
 
 #### Returns
 
-`Promise`\<`void`\>
+`Promise`&lt;`void`&gt;
 
-#### Defined in
+***
 
-[table.ts:270](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L270)
+### checkout()
 
-___
+> `abstract` **checkout**(`version`): `Promise`&lt;`void`&gt;
 
-### checkout
+Checks out a specific version of the table _This is an in-place operation._
 
-▸ **checkout**(`version`): `Promise`\<`void`\>
+This allows viewing previous versions of the table. If you wish to
+keep writing to the dataset starting from an old version, then use
+the `restore` function.
 
-Checks out a specific version of the Table
+Calling this method will set the table into time-travel mode. If you
-
+wish to return to standard mode, call `checkoutLatest`.
-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`
-| :------ | :------ |
+
-| `version` | `number` |
+The version to checkout
 
 #### Returns
 
-`Promise`\<`void`\>
+`Promise`&lt;`void`&gt;
 
-#### Defined in
+#### Example
 
-[table.ts:317](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L317)
+```typescript
+import * as lancedb from "@lancedb/lancedb"
+const db = await lancedb.connect("./.lancedb");
+const table = await db.createTable("my_table", [
+  { vector: [1.1, 0.9], type: "vector" },
+]);
 
-___
+console.log(await table.version()); // 1
+console.log(table.display());
+await table.add([{ vector: [0.5, 0.2], type: "vector" }]);
+await table.checkout(1);
+console.log(await table.version()); // 2
+```
 
-### checkoutLatest
+***
 
-▸ **checkoutLatest**(): `Promise`\<`void`\>
+### checkoutLatest()
 
-Ensures the table is pointing at the latest version
+> `abstract` **checkoutLatest**(): `Promise`&lt;`void`&gt;
 
-This can be used to manually update a table when the read_consistency_interval is None
+Checkout the latest version of the table. _This is an in-place operation._
-It can also be used to undo a `[Self::checkout]` operation
+
+The table will be set back into standard mode, and will track the latest
+version of the table.
 
 #### Returns
 
-`Promise`\<`void`\>
+`Promise`&lt;`void`&gt;
 
-#### Defined in
+***
 
-[table.ts:327](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L327)
+### close()
 
-___
+> `abstract` **close**(): `void`
-
-### close
-
-▸ **close**(): `void`
 
 Close the table, releasing any underlying resources.
 
@@ -214,37 +171,27 @@ Any attempt to use the table after it is closed will result in an error.
 
 `void`
 
-#### Defined in
+***
 
-[table.ts:85](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L85)
+### countRows()
 
-___
+> `abstract` **countRows**(`filter`?): `Promise`&lt;`number`&gt;
-
-### countRows
-
-▸ **countRows**(`filter?`): `Promise`\<`number`\>
 
 Count the total number of rows in the dataset.
 
 #### Parameters
 
-| Name | Type |
+• **filter?**: `string`
-| :------ | :------ |
-| `filter?` | `string` |
 
 #### Returns
 
-`Promise`\<`number`\>
+`Promise`&lt;`number`&gt;
 
-#### Defined in
+***
 
-[table.ts:152](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L152)
+### createIndex()
 
-___
+> `abstract` **createIndex**(`column`, `options`?): `Promise`&lt;`void`&gt;
-
-### createIndex
-
-▸ **createIndex**(`column`, `options?`): `Promise`\<`void`\>
 
 Create an index to speed up queries.
 
@@ -255,73 +202,66 @@ vector and non-vector searches)
 
 #### Parameters
 
-| Name | Type |
+• **column**: `string`
-| :------ | :------ |
+
-| `column` | `string` |
+• **options?**: `Partial`&lt;[`IndexOptions`](../interfaces/IndexOptions.md)&gt;
-| `options?` | `Partial`\<[`IndexOptions`](../interfaces/IndexOptions.md)\> |
 
 #### Returns
 
-`Promise`\<`void`\>
+`Promise`&lt;`void`&gt;
 
-**`Example`**
+#### Note
+
+We currently don't support custom named indexes,
+The index name will always be `${column}_idx`
+
+#### Examples
 
 ```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"]);
+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)
+await table.createIndex("vector", {
-  .ivf_pq({ num_partitions: 128, num_sub_vectors: 16 })
+  config: lancedb.Index.ivfPq({
-  .build();
+    numPartitions: 128,
+    numSubVectors: 16,
+  }),
+});
 ```
 
-**`Example`**
-
 ```ts
 // Or create a Scalar index
-await table.createIndex("my_float_col").build();
+await table.createIndex("my_float_col");
 ```
 
-#### Defined in
+***
 
-[table.ts:184](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L184)
+### delete()
 
-___
+> `abstract` **delete**(`predicate`): `Promise`&lt;`void`&gt;
-
-### delete
-
-▸ **delete**(`predicate`): `Promise`\<`void`\>
 
 Delete the rows that satisfy the predicate.
 
 #### Parameters
 
-| Name | Type |
+• **predicate**: `string`
-| :------ | :------ |
-| `predicate` | `string` |
 
 #### Returns
 
-`Promise`\<`void`\>
+`Promise`&lt;`void`&gt;
 
-#### Defined in
+***
 
-[table.ts:157](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L157)
+### display()
 
-___
+> `abstract` **display**(): `string`
-
-### display
-
-▸ **display**(): `string`
 
 Return a brief description of the table
 
@@ -329,15 +269,11 @@ Return a brief description of the table
 
 `string`
 
-#### Defined in
+***
 
-[table.ts:90](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L90)
+### dropColumns()
 
-___
+> `abstract` **dropColumns**(`columnNames`): `Promise`&lt;`void`&gt;
-
-### dropColumns
-
-▸ **dropColumns**(`columnNames`): `Promise`\<`void`\>
 
 Drop one or more columns from the dataset
 
@@ -348,23 +284,41 @@ then call ``cleanup_files`` to remove the old files.
 
 #### Parameters
 
-| Name | Type | Description |
+• **columnNames**: `string`[]
-| :------ | :------ | :------ |
+
-| `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"). |
+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`\>
+`Promise`&lt;`void`&gt;
 
-#### Defined in
+***
 
-[table.ts:285](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L285)
+### indexStats()
 
-___
+> `abstract` **indexStats**(`name`): `Promise`&lt;`undefined` \| [`IndexStatistics`](../interfaces/IndexStatistics.md)&gt;
 
-### isOpen
+List all the stats of a specified index
 
-▸ **isOpen**(): `boolean`
+#### Parameters
+
+• **name**: `string`
+
+The name of the index.
+
+#### Returns
+
+`Promise`&lt;`undefined` \| [`IndexStatistics`](../interfaces/IndexStatistics.md)&gt;
+
+The stats of the index. If the index does not exist, it will return undefined
+
+***
+
+### isOpen()
+
+> `abstract` **isOpen**(): `boolean`
 
 Return true if the table has not been closed
 
@@ -372,31 +326,79 @@ Return true if the table has not been closed
 
 `boolean`
 
-#### Defined in
+***
 
-[table.ts:74](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L74)
+### listIndices()
 
-___
+> `abstract` **listIndices**(): `Promise`&lt;[`IndexConfig`](../interfaces/IndexConfig.md)[]&gt;
 
-### listIndices
+List all indices that have been created with [Table.createIndex](Table.md#createindex)
-
-▸ **listIndices**(): `Promise`\<[`IndexConfig`](../interfaces/IndexConfig.md)[]\>
-
-List all indices that have been created with Self::create_index
 
 #### Returns
 
-`Promise`\<[`IndexConfig`](../interfaces/IndexConfig.md)[]\>
+`Promise`&lt;[`IndexConfig`](../interfaces/IndexConfig.md)[]&gt;
 
-#### Defined in
+***
 
-[table.ts:350](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L350)
+### mergeInsert()
 
-___
+> `abstract` **mergeInsert**(`on`): `MergeInsertBuilder`
 
-### query
+#### Parameters
 
-▸ **query**(): [`Query`](Query.md)
+• **on**: `string` \| `string`[]
+
+#### Returns
+
+`MergeInsertBuilder`
+
+***
+
+### optimize()
+
+> `abstract` **optimize**(`options`?): `Promise`&lt;`OptimizeStats`&gt;
+
+Optimize the on-disk data and indices for better performance.
+
+Modeled after ``VACUUM`` in PostgreSQL.
+
+ Optimization covers three operations:
+
+ - Compaction: Merges small files into larger ones
+ - Prune: Removes old versions of the dataset
+ - Index: Optimizes the indices, adding new data to existing indices
+
+ Experimental API
+ ----------------
+
+ The optimization process is undergoing active development and may change.
+ Our goal with these changes is to improve the performance of optimization and
+ reduce the complexity.
+
+ That being said, it is essential today to run optimize if you want the best
+ performance.  It should be stable and safe to use in production, but it our
+ hope that the API may be simplified (or not even need to be called) in the
+ future.
+
+ The frequency an application shoudl call optimize is based on the frequency of
+ data modifications.  If data is frequently added, deleted, or updated then
+ optimize should be run frequently.  A good rule of thumb is to run optimize if
+ you have added or modified 100,000 or more records or run more than 20 data
+ modification operations.
+
+#### Parameters
+
+• **options?**: `Partial`&lt;`OptimizeOptions`&gt;
+
+#### Returns
+
+`Promise`&lt;`OptimizeStats`&gt;
+
+***
+
+### query()
+
+> `abstract` **query**(): [`Query`](Query.md)
 
 Create a [Query](Query.md) Builder.
 
@@ -406,8 +408,7 @@ 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
+only fetch the columns you need.
-more details.
 
 When appropriate, various indices and statistics based pruning will be used to
 accelerate the query.
@@ -418,21 +419,22 @@ accelerate the query.
 
 A builder that can be used to parameterize the query
 
-**`Example`**
+#### Examples
 
 ```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.
+// is greater than 5. LanceDb supports a broad set of filtering functions.
-for await (const batch of table.query()
+for await (const batch of table
-                         .filter("id > 1").select(["id"]).limit(20)) {
+  .query()
- console.log(batch);
+  .where("id > 1")
+  .select(["id"])
+  .limit(20)) {
+  console.log(batch);
 }
 ```
 
-**`Example`**
-
 ```ts
 // Vector Similarity Search
 //
@@ -440,18 +442,17 @@ for await (const batch of table.query()
 // 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 /
+// The `refineFactor` and `nprobes` methods are used to control the recall /
 // latency tradeoff of the search.
-for await (const batch of table.query()
+for await (const batch of table
-                   .nearestTo([1, 2, 3])
+  .query()
-                   .refineFactor(5).nprobe(10)
+  .where("id > 1")
-                   .limit(10)) {
+  .select(["id"])
- console.log(batch);
+  .limit(20)) {
+  console.log(batch);
 }
 ```
 
-**`Example`**
-
 ```ts
 // Scan the full dataset
 //
@@ -461,15 +462,11 @@ for await (const batch of table.query()) {
 }
 ```
 
-#### Defined in
+***
 
-[table.ts:238](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L238)
+### restore()
 
-___
+> `abstract` **restore**(): `Promise`&lt;`void`&gt;
-
-### restore
-
-▸ **restore**(): `Promise`\<`void`\>
 
 Restore the table to the currently checked out version
 
@@ -484,33 +481,121 @@ out state and the read_consistency_interval, if any, will apply.
 
 #### Returns
 
-`Promise`\<`void`\>
+`Promise`&lt;`void`&gt;
 
-#### Defined in
+***
 
-[table.ts:343](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L343)
+### schema()
 
-___
+> `abstract` **schema**(): `Promise`&lt;`Schema`&lt;`any`&gt;&gt;
-
-### schema
-
-▸ **schema**(): `Promise`\<`Schema`\<`any`\>\>
 
 Get the schema of the table.
 
 #### Returns
 
-`Promise`\<`Schema`\<`any`\>\>
+`Promise`&lt;`Schema`&lt;`any`&gt;&gt;
 
-#### Defined in
+***
 
-[table.ts:95](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L95)
+### search()
 
-___
+#### search(query)
 
-### update
+> `abstract` **search**(`query`): [`VectorQuery`](VectorQuery.md)
 
-▸ **update**(`updates`, `options?`): `Promise`\<`void`\>
+Create a search query to find the nearest neighbors
+of the given query vector
+
+##### Parameters
+
+• **query**: `string`
+
+the query. This will be converted to a vector using the table's provided embedding function
+
+##### Returns
+
+[`VectorQuery`](VectorQuery.md)
+
+##### Note
+
+If no embedding functions are defined in the table, this will error when collecting the results.
+
+#### search(query)
+
+> `abstract` **search**(`query`): [`VectorQuery`](VectorQuery.md)
+
+Create a search query to find the nearest neighbors
+of the given query vector
+
+##### Parameters
+
+• **query**: `IntoVector`
+
+the query vector
+
+##### Returns
+
+[`VectorQuery`](VectorQuery.md)
+
+***
+
+### toArrow()
+
+> `abstract` **toArrow**(): `Promise`&lt;`Table`&lt;`any`&gt;&gt;
+
+Return the table as an arrow table
+
+#### Returns
+
+`Promise`&lt;`Table`&lt;`any`&gt;&gt;
+
+***
+
+### update()
+
+#### update(opts)
+
+> `abstract` **update**(`opts`): `Promise`&lt;`void`&gt;
+
+Update existing records in the Table
+
+##### Parameters
+
+• **opts**: `object` & `Partial`&lt;[`UpdateOptions`](../interfaces/UpdateOptions.md)&gt;
+
+##### Returns
+
+`Promise`&lt;`void`&gt;
+
+##### Example
+
+```ts
+table.update({where:"x = 2", values:{"vector": [10, 10]}})
+```
+
+#### update(opts)
+
+> `abstract` **update**(`opts`): `Promise`&lt;`void`&gt;
+
+Update existing records in the Table
+
+##### Parameters
+
+• **opts**: `object` & `Partial`&lt;[`UpdateOptions`](../interfaces/UpdateOptions.md)&gt;
+
+##### Returns
+
+`Promise`&lt;`void`&gt;
+
+##### Example
+
+```ts
+table.update({where:"x = 2", valuesSql:{"x": "x + 1"}})
+```
+
+#### update(updates, options)
+
+> `abstract` **update**(`updates`, `options`?): `Promise`&lt;`void`&gt;
 
 Update existing records in the Table
 
@@ -527,26 +612,32 @@ 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
+##### Parameters
 
-| Name | Type | Description |
+• **updates**: `Record`&lt;`string`, `string`&gt; \| `Map`&lt;`string`, `string`&gt;
-| :------ | :------ | :------ |
-| `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
+the
+columns to update
 
-`Promise`\<`void`\>
+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")
 
-#### Defined in
+• **options?**: `Partial`&lt;[`UpdateOptions`](../interfaces/UpdateOptions.md)&gt;
 
-[table.ts:137](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L137)
+additional options to control
+the update behavior
 
-___
+##### Returns
 
-### vectorSearch
+`Promise`&lt;`void`&gt;
 
-▸ **vectorSearch**(`vector`): [`VectorQuery`](VectorQuery.md)
+***
+
+### vectorSearch()
+
+> `abstract` **vectorSearch**(`vector`): [`VectorQuery`](VectorQuery.md)
 
 Search the table with a given query vector.
 
@@ -556,39 +647,50 @@ by `query`.
 
 #### Parameters
 
-| Name | Type |
+• **vector**: `IntoVector`
-| :------ | :------ |
-| `vector` | `unknown` |
 
 #### Returns
 
 [`VectorQuery`](VectorQuery.md)
 
-**`See`**
+#### 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()
 
-___
+> `abstract` **version**(): `Promise`&lt;`number`&gt;
-
-### version
-
-▸ **version**(): `Promise`\<`number`\>
 
 Retrieve the version of the table
 
-LanceDb supports versioning.  Every operation that modifies the table increases
+#### Returns
-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
+`Promise`&lt;`number`&gt;
-version to replace the current table with a previous version.
+
+***
+
+### parseTableData()
+
+> `static` **parseTableData**(`data`, `options`?, `streaming`?): `Promise`&lt;`object`&gt;
+
+#### Parameters
+
+• **data**: `TableLike` \| `Record`&lt;`string`, `unknown`&gt;[]
+
+• **options?**: `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
+
+• **streaming?**: `boolean` = `false`
 
 #### Returns
 
-`Promise`\<`number`\>
+`Promise`&lt;`object`&gt;
 
-#### Defined in
+##### buf
 
-[table.ts:297](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L297)
+> **buf**: `Buffer`
+
+##### mode
+
+> **mode**: `string`

docs/src/js/classes/VectorColumnOptions.md

@@ -1,45 +1,29 @@
-[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / VectorColumnOptions
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / VectorColumnOptions
 
 # Class: VectorColumnOptions
 
-## Table of contents
-
-### Constructors
-
-- [constructor](VectorColumnOptions.md#constructor)
-
-### Properties
-
-- [type](VectorColumnOptions.md#type)
-
 ## Constructors
 
-### constructor
+### new VectorColumnOptions()
 
-• **new VectorColumnOptions**(`values?`): [`VectorColumnOptions`](VectorColumnOptions.md)
+> **new VectorColumnOptions**(`values`?): [`VectorColumnOptions`](VectorColumnOptions.md)
 
 #### Parameters
 
-| Name | Type |
+• **values?**: `Partial`<[`VectorColumnOptions`](VectorColumnOptions.md)>
-| :------ | :------ |
-| `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`\>
+> **type**: `Float`&lt;`Floats`&gt;
 
 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

@@ -1,4 +1,8 @@
-[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / VectorQuery
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / VectorQuery
 
 # Class: VectorQuery
 
@@ -6,50 +10,19 @@ A builder used to construct a vector search
 
 This builder can be reused to execute the query many times.
 
-## Hierarchy
+## Extends
 
-- [`QueryBase`](QueryBase.md)\<`NativeVectorQuery`, [`VectorQuery`](VectorQuery.md)\>
+- [`QueryBase`](QueryBase.md)&lt;`NativeVectorQuery`&gt;
-
-  ↳ **`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()
 
-• **new VectorQuery**(`inner`): [`VectorQuery`](VectorQuery.md)
+> **new VectorQuery**(`inner`): [`VectorQuery`](VectorQuery.md)
 
 #### Parameters
 
-| Name | Type |
+• **inner**: `VectorQuery` \| `Promise`&lt;`VectorQuery`&gt;
-| :------ | :------ |
-| `inner` | `VectorQuery` |
 
 #### Returns
 
@@ -57,49 +30,37 @@ This builder can be reused to execute the query many times.
 
 #### Overrides
 
-[QueryBase](QueryBase.md).[constructor](QueryBase.md#constructor)
+[`QueryBase`](QueryBase.md).[`constructor`](QueryBase.md#constructors)
-
-#### Defined in
-
-[query.ts:189](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L189)
 
 ## Properties
 
 ### inner
 
-• `Protected` **inner**: `VectorQuery`
+> `protected` **inner**: `VectorQuery` \| `Promise`&lt;`VectorQuery`&gt;
 
 #### Inherited from
 
-[QueryBase](QueryBase.md).[inner](QueryBase.md#inner)
+[`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]**(): `AsyncIterator`\<`RecordBatch`\<`any`\>, `any`, `undefined`\>
+> **\[asyncIterator\]**(): `AsyncIterator`&lt;`RecordBatch`&lt;`any`&gt;, `any`, `undefined`&gt;
 
 #### Returns
 
-`AsyncIterator`\<`RecordBatch`\<`any`\>, `any`, `undefined`\>
+`AsyncIterator`&lt;`RecordBatch`&lt;`any`&gt;, `any`, `undefined`&gt;
 
 #### Inherited from
 
-[QueryBase](QueryBase.md).[[asyncIterator]](QueryBase.md#[asynciterator])
+[`QueryBase`](QueryBase.md).[`[asyncIterator]`](QueryBase.md#%5Basynciterator%5D)
 
-#### Defined in
+***
 
-[query.ts:154](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L154)
+### bypassVectorIndex()
 
-___
+> **bypassVectorIndex**(): [`VectorQuery`](VectorQuery.md)
-
-### bypassVectorIndex
-
-▸ **bypassVectorIndex**(): [`VectorQuery`](VectorQuery.md)
 
 If this is called then any vector index is skipped
 
@@ -113,15 +74,11 @@ calculate your recall to select an appropriate value for nprobes.
 
 [`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)
-
-### column
-
-▸ **column**(`column`): [`VectorQuery`](VectorQuery.md)
 
 Set the vector column to query
 
@@ -130,30 +87,24 @@ the call to
 
 #### Parameters
 
-| Name | Type |
+• **column**: `string`
-| :------ | :------ |
-| `column` | `string` |
 
 #### Returns
 
 [`VectorQuery`](VectorQuery.md)
 
-**`See`**
+#### 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)
-
-### distanceType
-
-▸ **distanceType**(`distanceType`): [`VectorQuery`](VectorQuery.md)
 
 Set the distance metric to use
 
@@ -163,15 +114,13 @@ use.  See
 
 #### Parameters
 
-| Name | Type |
+• **distanceType**: `"l2"` \| `"cosine"` \| `"dot"`
-| :------ | :------ |
-| `distanceType` | `string` |
 
 #### Returns
 
 [`VectorQuery`](VectorQuery.md)
 
-**`See`**
+#### See
 
 [IvfPqOptions.distanceType](../interfaces/IvfPqOptions.md#distancetype) for more details on the different
 distance metrics available.
@@ -182,23 +131,41 @@ invalid.
 
 By default "l2" is used.
 
-#### Defined in
+***
 
-[query.ts:248](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L248)
+### doCall()
 
-___
+> `protected` **doCall**(`fn`): `void`
 
-### execute
+#### Parameters
 
-▸ **execute**(): [`RecordBatchIterator`](RecordBatchIterator.md)
+• **fn**
+
+#### Returns
+
+`void`
+
+#### Inherited from
+
+[`QueryBase`](QueryBase.md).[`doCall`](QueryBase.md#docall)
+
+***
+
+### execute()
+
+> `protected` **execute**(`options`?): [`RecordBatchIterator`](RecordBatchIterator.md)
 
 Execute the query and return the results as an
 
+#### Parameters
+
+• **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
+
 #### Returns
 
 [`RecordBatchIterator`](RecordBatchIterator.md)
 
-**`See`**
+#### See
 
  - AsyncIterator
 of
@@ -212,17 +179,76 @@ single query)
 
 #### Inherited from
 
-[QueryBase](QueryBase.md).[execute](QueryBase.md#execute)
+[`QueryBase`](QueryBase.md).[`execute`](QueryBase.md#execute)
 
-#### Defined in
+***
 
-[query.ts:149](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/query.ts#L149)
+### explainPlan()
 
-___
+> **explainPlan**(`verbose`): `Promise`&lt;`string`&gt;
 
-### limit
+Generates an explanation of the query execution plan.
 
-▸ **limit**(`limit`): [`VectorQuery`](VectorQuery.md)
+#### Parameters
+
+• **verbose**: `boolean` = `false`
+
+If true, provides a more detailed explanation. Defaults to false.
+
+#### Returns
+
+`Promise`&lt;`string`&gt;
+
+A Promise that resolves to a string containing the query execution plan explanation.
+
+#### Example
+
+```ts
+import * as lancedb from "@lancedb/lancedb"
+const db = await lancedb.connect("./.lancedb");
+const table = await db.createTable("my_table", [
+  { vector: [1.1, 0.9], id: "1" },
+]);
+const plan = await table.query().nearestTo([0.5, 0.2]).explainPlan();
+```
+
+#### Inherited from
+
+[`QueryBase`](QueryBase.md).[`explainPlan`](QueryBase.md#explainplan)
+
+***
+
+### ~~filter()~~
+
+> **filter**(`predicate`): `this`
+
+A filter statement to be applied to this query.
+
+#### Parameters
+
+• **predicate**: `string`
+
+#### Returns
+
+`this`
+
+#### Alias
+
+where
+
+#### Deprecated
+
+Use `where` instead
+
+#### Inherited from
+
+[`QueryBase`](QueryBase.md).[`filter`](QueryBase.md#filter)
+
+***
+
+### limit()
+
+> **limit**(`limit`): `this`
 
 Set the maximum number of results to return.
 
@@ -231,45 +257,39 @@ called then every valid row from the table will be returned.
 
 #### Parameters
 
-| Name | Type |
+• **limit**: `number`
-| :------ | :------ |
-| `limit` | `number` |
 
 #### Returns
 
-[`VectorQuery`](VectorQuery.md)
+`this`
 
 #### Inherited from
 
-[QueryBase](QueryBase.md).[limit](QueryBase.md#limit)
+[`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()
 
-___
+> `protected` **nativeExecute**(`options`?): `Promise`&lt;`RecordBatchIterator`&gt;
 
-### nativeExecute
+#### Parameters
 
-▸ **nativeExecute**(): `Promise`\<`RecordBatchIterator`\>
+• **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
 
 #### Returns
 
-`Promise`\<`RecordBatchIterator`\>
+`Promise`&lt;`RecordBatchIterator`&gt;
 
 #### Inherited from
 
-[QueryBase](QueryBase.md).[nativeExecute](QueryBase.md#nativeexecute)
+[`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)
-
-### nprobes
-
-▸ **nprobes**(`nprobes`): [`VectorQuery`](VectorQuery.md)
 
 Set the number of partitions to search (probe)
 
@@ -294,23 +314,17 @@ you the desired recall.
 
 #### Parameters
 
-| Name | Type |
+• **nprobes**: `number`
-| :------ | :------ |
-| `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)
-
-### postfilter
-
-▸ **postfilter**(): [`VectorQuery`](VectorQuery.md)
 
 If this is called then filtering will happen after the vector search instead of
 before.
@@ -333,20 +347,16 @@ Post filtering happens during the "refine stage" (described in more detail in
 
 [`VectorQuery`](VectorQuery.md)
 
-**`See`**
+#### 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)
-
-### refineFactor
-
-▸ **refineFactor**(`refineFactor`): [`VectorQuery`](VectorQuery.md)
 
 A multiplier to control how many additional rows are taken during the refine step
 
@@ -378,23 +388,17 @@ distance between the query vector and the actual uncompressed vector.
 
 #### Parameters
 
-| Name | Type |
+• **refineFactor**: `number`
-| :------ | :------ |
-| `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`): `this`
-
-### select
-
-▸ **select**(`columns`): [`VectorQuery`](VectorQuery.md)
 
 Return only the specified columns.
 
@@ -418,15 +422,13 @@ input to this method would be:
 
 #### Parameters
 
-| Name | Type |
+• **columns**: `string` \| `string`[] \| `Record`&lt;`string`, `string`&gt; \| `Map`&lt;`string`, `string`&gt;
-| :------ | :------ |
-| `columns` | `string`[] \| `Record`\<`string`, `string`\> \| `Map`\<`string`, `string`\> |
 
 #### Returns
 
-[`VectorQuery`](VectorQuery.md)
+`this`
 
-**`Example`**
+#### Example
 
 ```ts
 new Map([["combined", "a + b"], ["c", "c"]])
@@ -441,61 +443,57 @@ object insertion order is easy to get wrong and `Map` is more foolproof.
 
 #### Inherited from
 
-[QueryBase](QueryBase.md).[select](QueryBase.md#select)
+[`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**(`options`?): `Promise`&lt;`any`[]&gt;
-
-### toArray
-
-▸ **toArray**(): `Promise`\<`unknown`[]\>
 
 Collect the results as an array of objects.
 
+#### Parameters
+
+• **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
+
 #### Returns
 
-`Promise`\<`unknown`[]\>
+`Promise`&lt;`any`[]&gt;
 
 #### Inherited from
 
-[QueryBase](QueryBase.md).[toArray](QueryBase.md#toarray)
+[`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**(`options`?): `Promise`&lt;`Table`&lt;`any`&gt;&gt;
-
-### toArrow
-
-▸ **toArrow**(): `Promise`\<`Table`\<`any`\>\>
 
 Collect the results as an Arrow
 
+#### Parameters
+
+• **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
+
 #### Returns
 
-`Promise`\<`Table`\<`any`\>\>
+`Promise`&lt;`Table`&lt;`any`&gt;&gt;
 
-**`See`**
+#### See
 
 ArrowTable.
 
 #### Inherited from
 
-[QueryBase](QueryBase.md).[toArrow](QueryBase.md#toarrow)
+[`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`): `this`
-
-### where
-
-▸ **where**(`predicate`): [`VectorQuery`](VectorQuery.md)
 
 A filter statement to be applied to this query.
 
@@ -503,15 +501,13 @@ The filter should be supplied as an SQL query string.  For example:
 
 #### Parameters
 
-| Name | Type |
+• **predicate**: `string`
-| :------ | :------ |
-| `predicate` | `string` |
 
 #### Returns
 
-[`VectorQuery`](VectorQuery.md)
+`this`
 
-**`Example`**
+#### Example
 
 ```ts
 x > 10
@@ -524,8 +520,4 @@ on the filter column(s).
 
 #### Inherited from
 
-[QueryBase](QueryBase.md).[where](QueryBase.md#where)
+[`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/enumerations/WriteMode.md

@@ -0,0 +1,27 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / WriteMode
+
+# Enumeration: WriteMode
+
+Write mode for writing a table.
+
+## Enumeration Members
+
+### Append
+
+> **Append**: `"Append"`
+
+***
+
+### Create
+
+> **Create**: `"Create"`
+
+***
+
+### Overwrite
+
+> **Overwrite**: `"Overwrite"`

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/functions/connect.md

@@ -0,0 +1,82 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / connect
+
+# Function: connect()
+
+## connect(uri, opts)
+
+> **connect**(`uri`, `opts`?): `Promise`<[`Connection`](../classes/Connection.md)>
+
+Connect to a LanceDB instance at the given URI.
+
+Accepted formats:
+
+- `/path/to/database` - local database
+- `s3://bucket/path/to/database` or `gs://bucket/path/to/database` - database on cloud storage
+- `db://host:port` - remote database (LanceDB cloud)
+
+### Parameters
+
+• **uri**: `string`
+
+The uri of the database. If the database uri starts
+with `db://` then it connects to a remote database.
+
+• **opts?**: `Partial`<[`ConnectionOptions`](../interfaces/ConnectionOptions.md) \| `RemoteConnectionOptions`>
+
+### Returns
+
+`Promise`<[`Connection`](../classes/Connection.md)>
+
+### See
+
+[ConnectionOptions](../interfaces/ConnectionOptions.md) for more details on the URI format.
+
+### Examples
+
+```ts
+const conn = await connect("/path/to/database");
+```
+
+```ts
+const conn = await connect(
+  "s3://bucket/path/to/database",
+  {storageOptions: {timeout: "60s"}
+});
+```
+
+## connect(opts)
+
+> **connect**(`opts`): `Promise`<[`Connection`](../classes/Connection.md)>
+
+Connect to a LanceDB instance at the given URI.
+
+Accepted formats:
+
+- `/path/to/database` - local database
+- `s3://bucket/path/to/database` or `gs://bucket/path/to/database` - database on cloud storage
+- `db://host:port` - remote database (LanceDB cloud)
+
+### Parameters
+
+• **opts**: `Partial`<[`ConnectionOptions`](../interfaces/ConnectionOptions.md) \| `RemoteConnectionOptions`> & `object`
+
+### Returns
+
+`Promise`<[`Connection`](../classes/Connection.md)>
+
+### See
+
+[ConnectionOptions](../interfaces/ConnectionOptions.md) for more details on the URI format.
+
+### Example
+
+```ts
+const conn = await connect({
+  uri: "/path/to/database",
+  storageOptions: {timeout: "60s"}
+});
+```

docs/src/js/functions/makeArrowTable.md

@@ -1,103 +1,12 @@
-[@lancedb/lancedb](README.md) / Exports
+[**@lancedb/lancedb**](../README.md) • **Docs**
 
-# @lancedb/lancedb
+***
 
-## Table of contents
+[@lancedb/lancedb](../globals.md) / makeArrowTable
 
-### Namespaces
+# Function: makeArrowTable()
 
-- [embedding](modules/embedding.md)
+> **makeArrowTable**(`data`, `options`?, `metadata`?): `ArrowTable`
-
-### Enumerations
-
-- [WriteMode](enums/WriteMode.md)
-
-### Classes
-
-- [Connection](classes/Connection.md)
-- [Index](classes/Index.md)
-- [MakeArrowTableOptions](classes/MakeArrowTableOptions.md)
-- [Query](classes/Query.md)
-- [QueryBase](classes/QueryBase.md)
-- [RecordBatchIterator](classes/RecordBatchIterator.md)
-- [Table](classes/Table.md)
-- [VectorColumnOptions](classes/VectorColumnOptions.md)
-- [VectorQuery](classes/VectorQuery.md)
-
-### Interfaces
-
-- [AddColumnsSql](interfaces/AddColumnsSql.md)
-- [AddDataOptions](interfaces/AddDataOptions.md)
-- [ColumnAlteration](interfaces/ColumnAlteration.md)
-- [ConnectionOptions](interfaces/ConnectionOptions.md)
-- [CreateTableOptions](interfaces/CreateTableOptions.md)
-- [ExecutableQuery](interfaces/ExecutableQuery.md)
-- [IndexConfig](interfaces/IndexConfig.md)
-- [IndexOptions](interfaces/IndexOptions.md)
-- [IvfPqOptions](interfaces/IvfPqOptions.md)
-- [TableNamesOptions](interfaces/TableNamesOptions.md)
-- [UpdateOptions](interfaces/UpdateOptions.md)
-- [WriteOptions](interfaces/WriteOptions.md)
-
-### Type Aliases
-
-- [Data](modules.md#data)
-
-### Functions
-
-- [connect](modules.md#connect)
-- [makeArrowTable](modules.md#makearrowtable)
-
-## Type Aliases
-
-### Data
-
-Ƭ **Data**: `Record`\<`string`, `unknown`\>[] \| `ArrowTable`
-
-Data type accepted by NodeJS SDK
-
-#### Defined in
-
-[arrow.ts:40](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/arrow.ts#L40)
-
-## Functions
-
-### connect
-
-▸ **connect**(`uri`, `opts?`): `Promise`\<[`Connection`](classes/Connection.md)\>
-
-Connect to a LanceDB instance at the given URI.
-
-Accpeted formats:
-
-- `/path/to/database` - local database
-- `s3://bucket/path/to/database` or `gs://bucket/path/to/database` - database on cloud storage
-- `db://host:port` - remote database (LanceDB cloud)
-
-#### Parameters
-
-| Name | Type | Description |
-| :------ | :------ | :------ |
-| `uri` | `string` | The uri of the database. If the database uri starts with `db://` then it connects to a remote database. |
-| `opts?` | `Partial`\<[`ConnectionOptions`](interfaces/ConnectionOptions.md)\> | - |
-
-#### Returns
-
-`Promise`\<[`Connection`](classes/Connection.md)\>
-
-**`See`**
-
-[ConnectionOptions](interfaces/ConnectionOptions.md) for more details on the URI format.
-
-#### Defined in
-
-[index.ts:62](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/index.ts#L62)
-
-___
-
-### makeArrowTable
-
-▸ **makeArrowTable**(`data`, `options?`): `ArrowTable`
 
 An enhanced version of the makeTable function from Apache Arrow
 that supports nested fields and embeddings columns.
@@ -129,20 +38,20 @@ rules are as follows:
  - Record<String, any> => Struct
  - Array<any> => List
 
-#### Parameters
+## Parameters
 
-| Name | Type |
+• **data**: `Record`&lt;`string`, `unknown`&gt;[]
-| :------ | :------ |
-| `data` | `Record`\<`string`, `unknown`\>[] |
-| `options?` | `Partial`\<[`MakeArrowTableOptions`](classes/MakeArrowTableOptions.md)\> |
 
-#### Returns
+• **options?**: `Partial`&lt;[`MakeArrowTableOptions`](../classes/MakeArrowTableOptions.md)&gt;
+
+• **metadata?**: `Map`&lt;`string`, `string`&gt;
+
+## Returns
 
 `ArrowTable`
 
-**`Example`**
+## Example
 
-```ts
 import { fromTableToBuffer, makeArrowTable } from "../arrow";
 import { Field, FixedSizeList, Float16, Float32, Int32, Schema } from "apache-arrow";
 
@@ -203,7 +112,3 @@ const table = makeArrowTable([
  }
 assert.deepEqual(table.schema, schema)
 ```
-
-#### Defined in
-
-[arrow.ts:197](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/arrow.ts#L197)

docs/src/js/globals.md

@@ -0,0 +1,51 @@
+[**@lancedb/lancedb**](README.md) • **Docs**
+
+***
+
+# @lancedb/lancedb
+
+## Namespaces
+
+- [embedding](namespaces/embedding/README.md)
+
+## Enumerations
+
+- [WriteMode](enumerations/WriteMode.md)
+
+## Classes
+
+- [Connection](classes/Connection.md)
+- [Index](classes/Index.md)
+- [MakeArrowTableOptions](classes/MakeArrowTableOptions.md)
+- [Query](classes/Query.md)
+- [QueryBase](classes/QueryBase.md)
+- [RecordBatchIterator](classes/RecordBatchIterator.md)
+- [Table](classes/Table.md)
+- [VectorColumnOptions](classes/VectorColumnOptions.md)
+- [VectorQuery](classes/VectorQuery.md)
+
+## Interfaces
+
+- [AddColumnsSql](interfaces/AddColumnsSql.md)
+- [AddDataOptions](interfaces/AddDataOptions.md)
+- [ColumnAlteration](interfaces/ColumnAlteration.md)
+- [ConnectionOptions](interfaces/ConnectionOptions.md)
+- [CreateTableOptions](interfaces/CreateTableOptions.md)
+- [ExecutableQuery](interfaces/ExecutableQuery.md)
+- [IndexConfig](interfaces/IndexConfig.md)
+- [IndexMetadata](interfaces/IndexMetadata.md)
+- [IndexOptions](interfaces/IndexOptions.md)
+- [IndexStatistics](interfaces/IndexStatistics.md)
+- [IvfPqOptions](interfaces/IvfPqOptions.md)
+- [TableNamesOptions](interfaces/TableNamesOptions.md)
+- [UpdateOptions](interfaces/UpdateOptions.md)
+- [WriteOptions](interfaces/WriteOptions.md)
+
+## Type Aliases
+
+- [Data](type-aliases/Data.md)
+
+## Functions
+
+- [connect](functions/connect.md)
+- [makeArrowTable](functions/makeArrowTable.md)

docs/src/js/interfaces/AddColumnsSql.md

@@ -1,37 +1,26 @@
-[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / AddColumnsSql
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.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`
+> **name**: `string`
 
 The name of the new column.
 
-#### Defined in
+***
-
-native.d.ts:43
-
-___
 
 ### valueSql
 
-• **valueSql**: `string`
+> **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 +1,19 @@
-[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / AddDataOptions
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / AddDataOptions
 
 # Interface: AddDataOptions
 
 Options for adding data to a table.
 
-## Table of contents
-
-### Properties
-
-- [mode](AddDataOptions.md#mode)
-
 ## Properties
 
 ### mode
 
-• **mode**: ``"append"`` \| ``"overwrite"``
+> **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

@@ -1,4 +1,8 @@
-[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / ColumnAlteration
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / ColumnAlteration
 
 # Interface: ColumnAlteration
 
@@ -7,50 +11,30 @@ A definition of a column alteration. The alteration changes the column at
 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
+### nullable?
 
-• `Optional` **nullable**: `boolean`
+> `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`
+> **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`
-
-### 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

@@ -1,40 +1,16 @@
-[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / ConnectionOptions
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / ConnectionOptions
 
 # Interface: ConnectionOptions
 
-## Table of contents
-
-### Properties
-
-- [apiKey](ConnectionOptions.md#apikey)
-- [hostOverride](ConnectionOptions.md#hostoverride)
-- [readConsistencyInterval](ConnectionOptions.md#readconsistencyinterval)
-
 ## Properties
 
-### apiKey
+### readConsistencyInterval?
 
-• `Optional` **apiKey**: `string`
+> `optional` **readConsistencyInterval**: `number`
-
-#### 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
@@ -46,6 +22,12 @@ 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
+### storageOptions?
+
+> `optional` **storageOptions**: `Record`<`string`, `string`>
+
+(For LanceDB OSS only): configuration for object storage.
+
+The available options are described at https://lancedb.github.io/lancedb/guides/storage/

docs/src/js/interfaces/CreateTableOptions.md

@@ -1,32 +1,31 @@
-[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / CreateTableOptions
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / CreateTableOptions
 
 # Interface: CreateTableOptions
 
-## Table of contents
-
-### Properties
-
-- [existOk](CreateTableOptions.md#existok)
-- [mode](CreateTableOptions.md#mode)
-
 ## Properties
 
+### embeddingFunction?
+
+> `optional` **embeddingFunction**: [`EmbeddingFunctionConfig`](../namespaces/embedding/interfaces/EmbeddingFunctionConfig.md)
+
+***
+
 ### existOk
 
-• **existOk**: `boolean`
+> **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"``
+> **mode**: `"overwrite"` \| `"create"`
 
 The mode to use when creating the table.
 
@@ -36,6 +35,31 @@ 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)
+### schema?
+
+> `optional` **schema**: `SchemaLike`
+
+***
+
+### storageOptions?
+
+> `optional` **storageOptions**: `Record`<`string`, `string`>
+
+Configuration for object storage.
+
+Options already set on the connection will be inherited by the table,
+but can be overridden here.
+
+The available options are described at https://lancedb.github.io/lancedb/guides/storage/
+
+***
+
+### useLegacyFormat?
+
+> `optional` **useLegacyFormat**: `boolean`
+
+If true then data files will be written with the legacy format
+
+The default is true while the new format is in beta

docs/src/js/interfaces/ExecutableQuery.md

@@ -1,4 +1,8 @@
-[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / ExecutableQuery
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / ExecutableQuery
 
 # Interface: ExecutableQuery
 

docs/src/js/interfaces/IndexConfig.md

@@ -1,39 +1,36 @@
-[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / IndexConfig
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.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`[]
+> **columns**: `string`[]
 
 The columns in the index
 
-Currently this is always an array of size 1.  In the future there may
+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`
+> **indexType**: `string`
 
 The type of the index
 
-#### Defined in
+***
 
-native.d.ts:9
+### name
+
+> **name**: `string`
+
+The name of the index

docs/src/js/interfaces/IndexMetadata.md

@@ -0,0 +1,19 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / IndexMetadata
+
+# Interface: IndexMetadata
+
+## Properties
+
+### indexType?
+
+> `optional` **indexType**: `string`
+
+***
+
+### metricType?
+
+> `optional` **metricType**: `string`

docs/src/js/interfaces/IndexOptions.md

@@ -1,19 +1,16 @@
-[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / IndexOptions
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / IndexOptions
 
 # Interface: IndexOptions
 
-## Table of contents
-
-### Properties
-
-- [config](IndexOptions.md#config)
-- [replace](IndexOptions.md#replace)
-
 ## Properties
 
-### config
+### config?
 
-• `Optional` **config**: [`Index`](../classes/Index.md)
+> `optional` **config**: [`Index`](../classes/Index.md)
 
 Advanced index configuration
 
@@ -25,15 +22,11 @@ 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`
-
-### replace
-
-• `Optional` **replace**: `boolean`
 
 Whether to replace the existing index
 
@@ -42,7 +35,3 @@ 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/IndexStatistics.md

@@ -0,0 +1,39 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / IndexStatistics
+
+# Interface: IndexStatistics
+
+## Properties
+
+### indexType?
+
+> `optional` **indexType**: `string`
+
+The type of the index
+
+***
+
+### indices
+
+> **indices**: [`IndexMetadata`](IndexMetadata.md)[]
+
+The metadata for each index
+
+***
+
+### numIndexedRows
+
+> **numIndexedRows**: `number`
+
+The number of rows indexed by the index
+
+***
+
+### numUnindexedRows
+
+> **numUnindexedRows**: `number`
+
+The number of rows not indexed

docs/src/js/interfaces/IvfPqOptions.md

@@ -1,24 +1,18 @@
-[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / IvfPqOptions
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.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
+### distanceType?
 
-• `Optional` **distanceType**: ``"l2"`` \| ``"cosine"`` \| ``"dot"``
+> `optional` **distanceType**: `"l2"` \| `"cosine"` \| `"dot"`
 
 Distance type to use to build the index.
 
@@ -52,15 +46,11 @@ never be returned from a vector search.
 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`
-
-### maxIterations
-
-• `Optional` **maxIterations**: `number`
 
 Max iteration to train IVF kmeans.
 
@@ -72,15 +62,11 @@ 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`
-
-### numPartitions
-
-• `Optional` **numPartitions**: `number`
 
 The number of IVF partitions to create.
 
@@ -92,15 +78,11 @@ 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`
-
-### numSubVectors
-
-• `Optional` **numSubVectors**: `number`
 
 Number of sub-vectors of PQ.
 
@@ -115,15 +97,11 @@ 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`
-
-### sampleRate
-
-• `Optional` **sampleRate**: `number`
 
 The number of vectors, per partition, to sample when training IVF kmeans.
 
@@ -138,7 +116,3 @@ Increasing this value might improve the quality of the index but in most cases t
 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)

docs/src/js/interfaces/TableNamesOptions.md

@@ -1,38 +1,27 @@
-[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / TableNamesOptions
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / TableNamesOptions
 
 # Interface: TableNamesOptions
 
-## Table of contents
-
-### Properties
-
-- [limit](TableNamesOptions.md#limit)
-- [startAfter](TableNamesOptions.md#startafter)
-
 ## Properties
 
-### limit
+### limit?
 
-• `Optional` **limit**: `number`
+> `optional` **limit**: `number`
 
 An optional limit to the number of results to return.
 
-#### Defined in
+***
 
-[connection.ts:48](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/connection.ts#L48)
+### startAfter?
 
-___
+> `optional` **startAfter**: `string`
-
-### startAfter
-
-• `Optional` **startAfter**: `string`
 
 If present, only return names that come lexicographically after the
 supplied value.
 
 This can be combined with limit to implement pagination by setting this to
 the last table name from the previous page.
-
-#### Defined in
-
-[connection.ts:46](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/connection.ts#L46)

docs/src/js/interfaces/UpdateOptions.md

@@ -1,18 +1,16 @@
-[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / UpdateOptions
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / UpdateOptions
 
 # Interface: UpdateOptions
 
-## Table of contents
-
-### Properties
-
-- [where](UpdateOptions.md#where)
-
 ## Properties
 
 ### where
 
-• **where**: `string`
+> **where**: `string`
 
 A filter that limits the scope of the update.
 
@@ -22,7 +20,3 @@ Only rows that satisfy the expression will be updated.
 
 For example, this could be 'my_col == 0' to replace all instances
 of 0 in a column with some other default value.
-
-#### Defined in
-
-[table.ts:50](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/table.ts#L50)

docs/src/js/interfaces/WriteOptions.md

@@ -1,21 +1,17 @@
-[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / WriteOptions
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / WriteOptions
 
 # Interface: WriteOptions
 
 Write options when creating a Table.
 
-## Table of contents
-
-### Properties
-
-- [mode](WriteOptions.md#mode)
-
 ## Properties
 
-### mode
+### mode?
 
-• `Optional` **mode**: [`WriteMode`](../enums/WriteMode.md)
+> `optional` **mode**: [`WriteMode`](../enumerations/WriteMode.md)
 
-#### Defined in
+Write mode for writing to a table.
-
-native.d.ts:74

docs/src/js/interfaces/embedding.EmbeddingFunction.md

@@ -1,129 +0,0 @@
-[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / [embedding](../modules/embedding.md) / EmbeddingFunction
-
-# Interface: EmbeddingFunction\<T\>
-
-[embedding](../modules/embedding.md).EmbeddingFunction
-
-An embedding function that automatically creates vector representation for a given column.
-
-## Type parameters
-
-| Name |
-| :------ |
-| `T` |
-
-## Implemented by
-
-- [`OpenAIEmbeddingFunction`](../classes/embedding.OpenAIEmbeddingFunction.md)
-
-## Table of contents
-
-### Properties
-
-- [destColumn](embedding.EmbeddingFunction.md#destcolumn)
-- [embed](embedding.EmbeddingFunction.md#embed)
-- [embeddingDataType](embedding.EmbeddingFunction.md#embeddingdatatype)
-- [embeddingDimension](embedding.EmbeddingFunction.md#embeddingdimension)
-- [excludeSource](embedding.EmbeddingFunction.md#excludesource)
-- [sourceColumn](embedding.EmbeddingFunction.md#sourcecolumn)
-
-## Properties
-
-### destColumn
-
-• `Optional` **destColumn**: `string`
-
-The name of the column that will contain the embedding
-
-By default this is "vector"
-
-#### Defined in
-
-[embedding/embedding_function.ts:49](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/embedding/embedding_function.ts#L49)
-
-___
-
-### embed
-
-• **embed**: (`data`: `T`[]) => `Promise`\<`number`[][]\>
-
-Creates a vector representation for the given values.
-
-#### Type declaration
-
-▸ (`data`): `Promise`\<`number`[][]\>
-
-Creates a vector representation for the given values.
-
-##### Parameters
-
-| Name | Type |
-| :------ | :------ |
-| `data` | `T`[] |
-
-##### Returns
-
-`Promise`\<`number`[][]\>
-
-#### Defined in
-
-[embedding/embedding_function.ts:62](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/embedding/embedding_function.ts#L62)
-
-___
-
-### embeddingDataType
-
-• `Optional` **embeddingDataType**: `Float`\<`Floats`\>
-
-The data type of the embedding
-
-The embedding function should return `number`.  This will be converted into
-an Arrow float array.  By default this will be Float32 but this property can
-be used to control the conversion.
-
-#### Defined in
-
-[embedding/embedding_function.ts:33](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/embedding/embedding_function.ts#L33)
-
-___
-
-### embeddingDimension
-
-• `Optional` **embeddingDimension**: `number`
-
-The dimension of the embedding
-
-This is optional, normally this can be determined by looking at the results of
-`embed`.  If this is not specified, and there is an attempt to apply the embedding
-to an empty table, then that process will fail.
-
-#### Defined in
-
-[embedding/embedding_function.ts:42](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/embedding/embedding_function.ts#L42)
-
-___
-
-### excludeSource
-
-• `Optional` **excludeSource**: `boolean`
-
-Should the source column be excluded from the resulting table
-
-By default the source column is included.  Set this to true and
-only the embedding will be stored.
-
-#### Defined in
-
-[embedding/embedding_function.ts:57](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/embedding/embedding_function.ts#L57)
-
-___
-
-### sourceColumn
-
-• **sourceColumn**: `string`
-
-The name of the column that will be used as input for the Embedding Function.
-
-#### Defined in
-
-[embedding/embedding_function.ts:24](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/embedding/embedding_function.ts#L24)

docs/src/js/modules/embedding.md

@@ -1,45 +0,0 @@
-[@lancedb/lancedb](../README.md) / [Exports](../modules.md) / embedding
-
-# Namespace: embedding
-
-## Table of contents
-
-### Classes
-
-- [OpenAIEmbeddingFunction](../classes/embedding.OpenAIEmbeddingFunction.md)
-
-### Interfaces
-
-- [EmbeddingFunction](../interfaces/embedding.EmbeddingFunction.md)
-
-### Functions
-
-- [isEmbeddingFunction](embedding.md#isembeddingfunction)
-
-## Functions
-
-### isEmbeddingFunction
-
-▸ **isEmbeddingFunction**\<`T`\>(`value`): value is EmbeddingFunction\<T\>
-
-Test if the input seems to be an embedding function
-
-#### Type parameters
-
-| Name |
-| :------ |
-| `T` |
-
-#### Parameters
-
-| Name | Type |
-| :------ | :------ |
-| `value` | `unknown` |
-
-#### Returns
-
-value is EmbeddingFunction\<T\>
-
-#### Defined in
-
-[embedding/embedding_function.ts:66](https://github.com/lancedb/lancedb/blob/9d178c7/nodejs/lancedb/embedding/embedding_function.ts#L66)

docs/src/js/namespaces/embedding/README.md

@@ -0,0 +1,29 @@
+[**@lancedb/lancedb**](../../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../../globals.md) / embedding
+
+# embedding
+
+## Index
+
+### Classes
+
+- [EmbeddingFunction](classes/EmbeddingFunction.md)
+- [EmbeddingFunctionRegistry](classes/EmbeddingFunctionRegistry.md)
+- [OpenAIEmbeddingFunction](classes/OpenAIEmbeddingFunction.md)
+
+### Interfaces
+
+- [EmbeddingFunctionConfig](interfaces/EmbeddingFunctionConfig.md)
+
+### Type Aliases
+
+- [OpenAIOptions](type-aliases/OpenAIOptions.md)
+
+### Functions
+
+- [LanceSchema](functions/LanceSchema.md)
+- [getRegistry](functions/getRegistry.md)
+- [register](functions/register.md)

docs/src/js/namespaces/embedding/classes/EmbeddingFunction.md

@@ -0,0 +1,162 @@
+[**@lancedb/lancedb**](../../../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../../../globals.md) / [embedding](../README.md) / EmbeddingFunction
+
+# Class: `abstract` EmbeddingFunction<T, M>
+
+An embedding function that automatically creates vector representation for a given column.
+
+## Extended by
+
+- [`OpenAIEmbeddingFunction`](OpenAIEmbeddingFunction.md)
+
+## Type Parameters
+
+• **T** = `any`
+
+• **M** *extends* `FunctionOptions` = `FunctionOptions`
+
+## Constructors
+
+### new EmbeddingFunction()
+
+> **new EmbeddingFunction**<`T`, `M`>(): [`EmbeddingFunction`](EmbeddingFunction.md)<`T`, `M`>
+
+#### Returns
+
+[`EmbeddingFunction`](EmbeddingFunction.md)<`T`, `M`>
+
+## Methods
+
+### computeQueryEmbeddings()
+
+> **computeQueryEmbeddings**(`data`): `Promise`<`number`[] \| `Float32Array` \| `Float64Array`>
+
+Compute the embeddings for a single query
+
+#### Parameters
+
+• **data**: `T`
+
+#### Returns
+
+`Promise`<`number`[] \| `Float32Array` \| `Float64Array`>
+
+***
+
+### computeSourceEmbeddings()
+
+> `abstract` **computeSourceEmbeddings**(`data`): `Promise`<`number`[][] \| `Float32Array`[] \| `Float64Array`[]>
+
+Creates a vector representation for the given values.
+
+#### Parameters
+
+• **data**: `T`[]
+
+#### Returns
+
+`Promise`<`number`[][] \| `Float32Array`[] \| `Float64Array`[]>
+
+***
+
+### embeddingDataType()
+
+> `abstract` **embeddingDataType**(): `Float`<`Floats`>
+
+The datatype of the embeddings
+
+#### Returns
+
+`Float`<`Floats`>
+
+***
+
+### ndims()
+
+> **ndims**(): `undefined` \| `number`
+
+The number of dimensions of the embeddings
+
+#### Returns
+
+`undefined` \| `number`
+
+***
+
+### sourceField()
+
+> **sourceField**(`optionsOrDatatype`): [`DataType`<`Type`, `any`>, `Map`<`string`, [`EmbeddingFunction`](EmbeddingFunction.md)<`any`, `FunctionOptions`>>]
+
+sourceField is used in combination with `LanceSchema` to provide a declarative data model
+
+#### Parameters
+
+• **optionsOrDatatype**: `DataType`<`Type`, `any`> \| `Partial`<`FieldOptions`<`DataType`<`Type`, `any`>>>
+
+The options for the field or the datatype
+
+#### Returns
+
+[`DataType`<`Type`, `any`>, `Map`<`string`, [`EmbeddingFunction`](EmbeddingFunction.md)<`any`, `FunctionOptions`>>]
+
+#### See
+
+lancedb.LanceSchema
+
+***
+
+### toJSON()
+
+> `abstract` **toJSON**(): `Partial`<`M`>
+
+Convert the embedding function to a JSON object
+It is used to serialize the embedding function to the schema
+It's important that any object returned by this method contains all the necessary
+information to recreate the embedding function
+
+It should return the same object that was passed to the constructor
+If it does not, the embedding function will not be able to be recreated, or could be recreated incorrectly
+
+#### Returns
+
+`Partial`<`M`>
+
+#### Example
+
+```ts
+class MyEmbeddingFunction extends EmbeddingFunction {
+  constructor(options: {model: string, timeout: number}) {
+    super();
+    this.model = options.model;
+    this.timeout = options.timeout;
+  }
+  toJSON() {
+    return {
+      model: this.model,
+      timeout: this.timeout,
+    };
+}
+```
+
+***
+
+### vectorField()
+
+> **vectorField**(`optionsOrDatatype`?): [`DataType`<`Type`, `any`>, `Map`<`string`, [`EmbeddingFunction`](EmbeddingFunction.md)<`any`, `FunctionOptions`>>]
+
+vectorField is used in combination with `LanceSchema` to provide a declarative data model
+
+#### Parameters
+
+• **optionsOrDatatype?**: `DataType`<`Type`, `any`> \| `Partial`<`FieldOptions`<`DataType`<`Type`, `any`>>>
+
+#### Returns
+
+[`DataType`<`Type`, `any`>, `Map`<`string`, [`EmbeddingFunction`](EmbeddingFunction.md)<`any`, `FunctionOptions`>>]
+
+#### See
+
+lancedb.LanceSchema

docs/src/js/namespaces/embedding/classes/EmbeddingFunctionRegistry.md

@@ -0,0 +1,124 @@
+[**@lancedb/lancedb**](../../../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../../../globals.md) / [embedding](../README.md) / EmbeddingFunctionRegistry
+
+# Class: EmbeddingFunctionRegistry
+
+This is a singleton class used to register embedding functions
+and fetch them by name. It also handles serializing and deserializing.
+You can implement your own embedding function by subclassing EmbeddingFunction
+or TextEmbeddingFunction and registering it with the registry
+
+## Constructors
+
+### new EmbeddingFunctionRegistry()
+
+> **new EmbeddingFunctionRegistry**(): [`EmbeddingFunctionRegistry`](EmbeddingFunctionRegistry.md)
+
+#### Returns
+
+[`EmbeddingFunctionRegistry`](EmbeddingFunctionRegistry.md)
+
+## Methods
+
+### functionToMetadata()
+
+> **functionToMetadata**(`conf`): `Record`<`string`, `any`>
+
+#### Parameters
+
+• **conf**: [`EmbeddingFunctionConfig`](../interfaces/EmbeddingFunctionConfig.md)
+
+#### Returns
+
+`Record`<`string`, `any`>
+
+***
+
+### get()
+
+> **get**<`T`, `Name`>(`name`): `Name` *extends* `"openai"` ? `EmbeddingFunctionCreate`<[`OpenAIEmbeddingFunction`](OpenAIEmbeddingFunction.md)> : `undefined` \| `EmbeddingFunctionCreate`<`T`>
+
+Fetch an embedding function by name
+
+#### Type Parameters
+
+• **T** *extends* [`EmbeddingFunction`](EmbeddingFunction.md)<`unknown`, `FunctionOptions`>
+
+• **Name** *extends* `string` = `""`
+
+#### Parameters
+
+• **name**: `Name` *extends* `"openai"` ? `"openai"` : `string`
+
+The name of the function
+
+#### Returns
+
+`Name` *extends* `"openai"` ? `EmbeddingFunctionCreate`<[`OpenAIEmbeddingFunction`](OpenAIEmbeddingFunction.md)> : `undefined` \| `EmbeddingFunctionCreate`<`T`>
+
+***
+
+### getTableMetadata()
+
+> **getTableMetadata**(`functions`): `Map`<`string`, `string`>
+
+#### Parameters
+
+• **functions**: [`EmbeddingFunctionConfig`](../interfaces/EmbeddingFunctionConfig.md)[]
+
+#### Returns
+
+`Map`<`string`, `string`>
+
+***
+
+### register()
+
+> **register**<`T`>(`this`, `alias`?): (`ctor`) => `any`
+
+Register an embedding function
+
+#### Type Parameters
+
+• **T** *extends* `EmbeddingFunctionConstructor`<[`EmbeddingFunction`](EmbeddingFunction.md)<`any`, `FunctionOptions`>> = `EmbeddingFunctionConstructor`<[`EmbeddingFunction`](EmbeddingFunction.md)<`any`, `FunctionOptions`>>
+
+#### Parameters
+
+• **this**: [`EmbeddingFunctionRegistry`](EmbeddingFunctionRegistry.md)
+
+• **alias?**: `string`
+
+#### Returns
+
+`Function`
+
+##### Parameters
+
+• **ctor**: `T`
+
+##### Returns
+
+`any`
+
+#### Throws
+
+Error if the function is already registered
+
+***
+
+### reset()
+
+> **reset**(`this`): `void`
+
+reset the registry to the initial state
+
+#### Parameters
+
+• **this**: [`EmbeddingFunctionRegistry`](EmbeddingFunctionRegistry.md)
+
+#### Returns
+
+`void`

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

@@ -0,0 +1,196 @@
+[**@lancedb/lancedb**](../../../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../../../globals.md) / [embedding](../README.md) / OpenAIEmbeddingFunction
+
+# Class: OpenAIEmbeddingFunction
+
+An embedding function that automatically creates vector representation for a given column.
+
+## Extends
+
+- [`EmbeddingFunction`](EmbeddingFunction.md)<`string`, `Partial`<[`OpenAIOptions`](../type-aliases/OpenAIOptions.md)>>
+
+## Constructors
+
+### new OpenAIEmbeddingFunction()
+
+> **new OpenAIEmbeddingFunction**(`options`): [`OpenAIEmbeddingFunction`](OpenAIEmbeddingFunction.md)
+
+#### Parameters
+
+• **options**: `Partial`<[`OpenAIOptions`](../type-aliases/OpenAIOptions.md)> = `...`
+
+#### Returns
+
+[`OpenAIEmbeddingFunction`](OpenAIEmbeddingFunction.md)
+
+#### Overrides
+
+[`EmbeddingFunction`](EmbeddingFunction.md).[`constructor`](EmbeddingFunction.md#constructors)
+
+## Methods
+
+### computeQueryEmbeddings()
+
+> **computeQueryEmbeddings**(`data`): `Promise`<`number`[]>
+
+Compute the embeddings for a single query
+
+#### Parameters
+
+• **data**: `string`
+
+#### Returns
+
+`Promise`<`number`[]>
+
+#### Overrides
+
+[`EmbeddingFunction`](EmbeddingFunction.md).[`computeQueryEmbeddings`](EmbeddingFunction.md#computequeryembeddings)
+
+***
+
+### computeSourceEmbeddings()
+
+> **computeSourceEmbeddings**(`data`): `Promise`<`number`[][]>
+
+Creates a vector representation for the given values.
+
+#### Parameters
+
+• **data**: `string`[]
+
+#### Returns
+
+`Promise`<`number`[][]>
+
+#### Overrides
+
+[`EmbeddingFunction`](EmbeddingFunction.md).[`computeSourceEmbeddings`](EmbeddingFunction.md#computesourceembeddings)
+
+***
+
+### embeddingDataType()
+
+> **embeddingDataType**(): `Float`<`Floats`>
+
+The datatype of the embeddings
+
+#### Returns
+
+`Float`<`Floats`>
+
+#### Overrides
+
+[`EmbeddingFunction`](EmbeddingFunction.md).[`embeddingDataType`](EmbeddingFunction.md#embeddingdatatype)
+
+***
+
+### ndims()
+
+> **ndims**(): `number`
+
+The number of dimensions of the embeddings
+
+#### Returns
+
+`number`
+
+#### Overrides
+
+[`EmbeddingFunction`](EmbeddingFunction.md).[`ndims`](EmbeddingFunction.md#ndims)
+
+***
+
+### sourceField()
+
+> **sourceField**(`optionsOrDatatype`): [`DataType`<`Type`, `any`>, `Map`<`string`, [`EmbeddingFunction`](EmbeddingFunction.md)<`any`, `FunctionOptions`>>]
+
+sourceField is used in combination with `LanceSchema` to provide a declarative data model
+
+#### Parameters
+
+• **optionsOrDatatype**: `DataType`<`Type`, `any`> \| `Partial`<`FieldOptions`<`DataType`<`Type`, `any`>>>
+
+The options for the field or the datatype
+
+#### Returns
+
+[`DataType`<`Type`, `any`>, `Map`<`string`, [`EmbeddingFunction`](EmbeddingFunction.md)<`any`, `FunctionOptions`>>]
+
+#### See
+
+lancedb.LanceSchema
+
+#### Inherited from
+
+[`EmbeddingFunction`](EmbeddingFunction.md).[`sourceField`](EmbeddingFunction.md#sourcefield)
+
+***
+
+### toJSON()
+
+> **toJSON**(): `object`
+
+Convert the embedding function to a JSON object
+It is used to serialize the embedding function to the schema
+It's important that any object returned by this method contains all the necessary
+information to recreate the embedding function
+
+It should return the same object that was passed to the constructor
+If it does not, the embedding function will not be able to be recreated, or could be recreated incorrectly
+
+#### Returns
+
+`object`
+
+##### model
+
+> **model**: `string` & `object` \| `"text-embedding-ada-002"` \| `"text-embedding-3-small"` \| `"text-embedding-3-large"`
+
+#### Example
+
+```ts
+class MyEmbeddingFunction extends EmbeddingFunction {
+  constructor(options: {model: string, timeout: number}) {
+    super();
+    this.model = options.model;
+    this.timeout = options.timeout;
+  }
+  toJSON() {
+    return {
+      model: this.model,
+      timeout: this.timeout,
+    };
+}
+```
+
+#### Overrides
+
+[`EmbeddingFunction`](EmbeddingFunction.md).[`toJSON`](EmbeddingFunction.md#tojson)
+
+***
+
+### vectorField()
+
+> **vectorField**(`optionsOrDatatype`?): [`DataType`<`Type`, `any`>, `Map`<`string`, [`EmbeddingFunction`](EmbeddingFunction.md)<`any`, `FunctionOptions`>>]
+
+vectorField is used in combination with `LanceSchema` to provide a declarative data model
+
+#### Parameters
+
+• **optionsOrDatatype?**: `DataType`<`Type`, `any`> \| `Partial`<`FieldOptions`<`DataType`<`Type`, `any`>>>
+
+#### Returns
+
+[`DataType`<`Type`, `any`>, `Map`<`string`, [`EmbeddingFunction`](EmbeddingFunction.md)<`any`, `FunctionOptions`>>]
+
+#### See
+
+lancedb.LanceSchema
+
+#### Inherited from
+
+[`EmbeddingFunction`](EmbeddingFunction.md).[`vectorField`](EmbeddingFunction.md#vectorfield)

docs/src/js/namespaces/embedding/functions/LanceSchema.md

@@ -0,0 +1,39 @@
+[**@lancedb/lancedb**](../../../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../../../globals.md) / [embedding](../README.md) / LanceSchema
+
+# Function: LanceSchema()
+
+> **LanceSchema**(`fields`): `Schema`
+
+Create a schema with embedding functions.
+
+## Parameters
+
+• **fields**: `Record`<`string`, `object` \| [`object`, `Map`<`string`, [`EmbeddingFunction`](../classes/EmbeddingFunction.md)<`any`, `FunctionOptions`>>]>
+
+## Returns
+
+`Schema`
+
+Schema
+
+## Example
+
+```ts
+class MyEmbeddingFunction extends EmbeddingFunction {
+// ...
+}
+const func = new MyEmbeddingFunction();
+const schema = LanceSchema({
+  id: new Int32(),
+  text: func.sourceField(new Utf8()),
+  vector: func.vectorField(),
+  // optional: specify the datatype and/or dimensions
+  vector2: func.vectorField({ datatype: new Float32(), dims: 3}),
+});
+
+const table = await db.createTable("my_table", data, { schema });
+```

docs/src/js/namespaces/embedding/functions/getRegistry.md

@@ -0,0 +1,23 @@
+[**@lancedb/lancedb**](../../../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../../../globals.md) / [embedding](../README.md) / getRegistry
+
+# Function: getRegistry()
+
+> **getRegistry**(): [`EmbeddingFunctionRegistry`](../classes/EmbeddingFunctionRegistry.md)
+
+Utility function to get the global instance of the registry
+
+## Returns
+
+[`EmbeddingFunctionRegistry`](../classes/EmbeddingFunctionRegistry.md)
+
+`EmbeddingFunctionRegistry` The global instance of the registry
+
+## Example
+
+```ts
+const registry = getRegistry();
+const openai = registry.get("openai").create();

docs/src/js/namespaces/embedding/functions/register.md

@@ -0,0 +1,25 @@
+[**@lancedb/lancedb**](../../../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../../../globals.md) / [embedding](../README.md) / register
+
+# Function: register()
+
+> **register**(`name`?): (`ctor`) => `any`
+
+## Parameters
+
+• **name?**: `string`
+
+## Returns
+
+`Function`
+
+### Parameters
+
+• **ctor**: `EmbeddingFunctionConstructor`<[`EmbeddingFunction`](../classes/EmbeddingFunction.md)<`any`, `FunctionOptions`>>
+
+### Returns
+
+`any`

docs/src/js/namespaces/embedding/interfaces/EmbeddingFunctionConfig.md

@@ -0,0 +1,25 @@
+[**@lancedb/lancedb**](../../../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../../../globals.md) / [embedding](../README.md) / EmbeddingFunctionConfig
+
+# Interface: EmbeddingFunctionConfig
+
+## Properties
+
+### function
+
+> **function**: [`EmbeddingFunction`](../classes/EmbeddingFunction.md)<`any`, `FunctionOptions`>
+
+***
+
+### sourceColumn
+
+> **sourceColumn**: `string`
+
+***
+
+### vectorColumn?
+
+> `optional` **vectorColumn**: `string`

docs/src/js/namespaces/embedding/type-aliases/OpenAIOptions.md

@@ -0,0 +1,19 @@
+[**@lancedb/lancedb**](../../../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../../../globals.md) / [embedding](../README.md) / OpenAIOptions
+
+# Type Alias: OpenAIOptions
+
+> **OpenAIOptions**: `object`
+
+## Type declaration
+
+### apiKey
+
+> **apiKey**: `string`
+
+### model
+
+> **model**: `EmbeddingCreateParams`\[`"model"`\]

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

@@ -0,0 +1,11 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / Data
+
+# Type Alias: Data
+
+> **Data**: `Record`<`string`, `unknown`>[] \| `TableLike`
+
+Data type accepted by NodeJS SDK

docs/src/migration.md

@@ -9,7 +9,8 @@ around the asynchronous client.
 This guide describes the differences between the two APIs and will hopefully assist users
 that would like to migrate to the new API.
 
-## Closeable Connections
+## Python
+### Closeable Connections
 
 The Connection now has a `close` method. You can call this when
 you are done with the connection to eagerly free resources. Currently
@@ -32,20 +33,20 @@ async def my_async_fn():
 It is not mandatory to call the `close` method. If you do not call it
 then the connection will be closed when the object is garbage collected.
 
-## Closeable Table
+### Closeable Table
 
 The Table now also has a `close` method, similar to the connection. This
 can be used to eagerly free the cache used by a Table object. Similar to
 the connection, it can be used as a context manager and it is not mandatory
 to call the `close` method.
 
-### Changes to Table APIs
+#### Changes to Table APIs
 
 - Previously `Table.schema` was a property. Now it is an async method.
 - The method `Table.__len__` was removed and `len(table)` will no longer
   work. Use `Table.count_rows` instead.
 
-### Creating Indices
+#### Creating Indices
 
 The `Table.create_index` method is now used for creating both vector indices
 and scalar indices. It currently requires a column name to be specified (the
@@ -55,12 +56,12 @@ the size of the data.
 To specify index configuration details you will need to specify which kind of
 index you are using.
 
-### Querying
+#### Querying
 
 The `Table.search` method has been renamed to `AsyncTable.vector_search` for
 clarity.
 
-## Features not yet supported
+### Features not yet supported
 
 The following features are not yet supported by the asynchronous API. However,
 we plan to support them soon.
@@ -74,3 +75,117 @@ we plan to support them soon.
   search
 - Remote connections to LanceDb Cloud are not yet supported.
 - The method Table.head is not yet supported.
+
+## TypeScript/JavaScript
+
+For JS/TS users, we offer a brand new SDK [@lancedb/lancedb](https://www.npmjs.com/package/@lancedb/lancedb)
+
+We tried to keep the API as similar as possible to the previous version, but there are a few small changes. Here are the most important ones:
+
+### Creating Tables
+
+[CreateTableOptions.writeOptions.writeMode](./javascript/interfaces/WriteOptions.md#writemode) has been replaced with [CreateTableOptions.mode](./js/interfaces/CreateTableOptions.md#mode)
+
+=== "vectordb (deprecated)"
+
+    ```ts
+    db.createTable(tableName, data, { writeMode: lancedb.WriteMode.Overwrite });
+    ```
+
+=== "@lancedb/lancedb"
+
+    ```ts
+    db.createTable(tableName, data, { mode: "overwrite" })
+    ```
+
+### Changes to Table APIs
+
+Previously `Table.schema` was a property. Now it is an async method.
+
+#### Creating Indices
+
+The `Table.createIndex` method is now used for creating both vector indices
+and scalar indices. It currently requires a column name to be specified (the
+column to index). Vector index defaults are now smarter and scale better with
+the size of the data.
+
+=== "vectordb (deprecated)"
+
+    ```ts
+    await tbl.createIndex({
+      column: "vector", // default
+      type: "ivf_pq",
+      num_partitions: 2,
+      num_sub_vectors: 2,
+    });
+    ```
+
+=== "@lancedb/lancedb"
+
+    ```ts
+    await table.createIndex("vector", {
+      config: lancedb.Index.ivfPq({
+        numPartitions: 2,
+        numSubVectors: 2,
+      }),
+    });
+    ```
+
+### Embedding Functions
+
+The embedding API has been completely reworked, and it now more closely resembles the Python API, including the new [embedding registry](./js/classes/embedding.EmbeddingFunctionRegistry.md)
+
+=== "vectordb (deprecated)"
+
+    ```ts
+
+    const embeddingFunction = new lancedb.OpenAIEmbeddingFunction('text', API_KEY)
+    const data = [
+        { id: 1, text: 'Black T-Shirt', price: 10 },
+        { id: 2, text: 'Leather Jacket', price: 50 }
+    ]
+    const table = await db.createTable('vectors', data, embeddingFunction)
+    ```
+
+=== "@lancedb/lancedb"
+
+    ```ts
+    import * as lancedb from "@lancedb/lancedb";
+    import * as arrow from "apache-arrow";
+    import { LanceSchema, getRegistry } from "@lancedb/lancedb/embedding";
+
+    const func = getRegistry().get("openai").create({apiKey: API_KEY});
+
+    const data = [
+        { id: 1, text: 'Black T-Shirt', price: 10 },
+        { id: 2, text: 'Leather Jacket', price: 50 }
+    ]
+
+    const table = await db.createTable('vectors', data, {
+        embeddingFunction: {
+            sourceColumn: "text",
+            function: func,
+        }
+    })
+
+    ```
+
+You can also use a schema driven approach, which parallels the Pydantic integration in our Python SDK:
+
+```ts
+const func = getRegistry().get("openai").create({apiKey: API_KEY});
+
+const data = [
+    { id: 1, text: 'Black T-Shirt', price: 10 },
+    { id: 2, text: 'Leather Jacket', price: 50 }
+]
+const schema = LanceSchema({
+    id: new arrow.Int32(),
+    text: func.sourceField(new arrow.Utf8()),
+    price: new arrow.Float64(),
+    vector: func.vectorField()
+})
+
+const table = await db.createTable('vectors', data, {schema})
+
+```

docs/src/notebooks/LlamaIndex_example.ipynb

@@ -0,0 +1,538 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "2db56c9b",
+   "metadata": {},
+   "source": [
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_index/blob/main/docs/docs/examples/vector_stores/LanceDBIndexDemo.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "db0855d0",
+   "metadata": {},
+   "source": [
+    "# LanceDB Vector Store\n",
+    "In this notebook we are going to show how to use [LanceDB](https://www.lancedb.com) to perform vector searches in LlamaIndex"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "f44170b2",
+   "metadata": {},
+   "source": [
+    "If you're opening this Notebook on colab, you will probably need to install LlamaIndex 🦙."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6c84199c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install llama-index llama-index-vector-stores-lancedb"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1a90ce34",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install lancedb==0.6.13 #Only required if the above cell installs an older version of lancedb (pypi package may not be released yet)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "39c62671",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Refresh vector store URI if restarting or re-using the same notebook\n",
+    "! rm -rf ./lancedb"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "59b54276",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import logging\n",
+    "import sys\n",
+    "\n",
+    "# Uncomment to see debug logs\n",
+    "# logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)\n",
+    "# logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))\n",
+    "\n",
+    "\n",
+    "from llama_index.core import SimpleDirectoryReader, Document, StorageContext\n",
+    "from llama_index.core import VectorStoreIndex\n",
+    "from llama_index.vector_stores.lancedb import LanceDBVectorStore\n",
+    "import textwrap"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "26c71b6d",
+   "metadata": {},
+   "source": [
+    "### Setup OpenAI\n",
+    "The first step is to configure the openai key. It will be used to created embeddings for the documents loaded into the index"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "67b86621",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import openai\n",
+    "\n",
+    "openai.api_key = \"sk-\""
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "073f0a68",
+   "metadata": {},
+   "source": [
+    "Download Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "eef1b911",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "--2024-06-11 16:42:37--  https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/paul_graham/paul_graham_essay.txt\n",
+      "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.109.133, 185.199.110.133, 185.199.108.133, ...\n",
+      "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.109.133|:443... connected.\n",
+      "HTTP request sent, awaiting response... 200 OK\n",
+      "Length: 75042 (73K) [text/plain]\n",
+      "Saving to: ‘data/paul_graham/paul_graham_essay.txt’\n",
+      "\n",
+      "data/paul_graham/pa 100%[===================>]  73.28K  --.-KB/s    in 0.02s   \n",
+      "\n",
+      "2024-06-11 16:42:37 (3.97 MB/s) - ‘data/paul_graham/paul_graham_essay.txt’ saved [75042/75042]\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "!mkdir -p 'data/paul_graham/'\n",
+    "!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "f7010b1d-d1bb-4f08-9309-a328bb4ea396",
+   "metadata": {},
+   "source": [
+    "### Loading documents\n",
+    "Load the documents stored in the `data/paul_graham/` using the SimpleDirectoryReader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c154dd4b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Document ID: cac1ba78-5007-4cf8-89ba-280264790115 Document Hash: fe2d4d3ef3a860780f6c2599808caa587c8be6516fe0ba4ca53cf117044ba953\n"
+     ]
+    }
+   ],
+   "source": [
+    "documents = SimpleDirectoryReader(\"./data/paul_graham/\").load_data()\n",
+    "print(\"Document ID:\", documents[0].doc_id, \"Document Hash:\", documents[0].hash)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "c0232fd1",
+   "metadata": {},
+   "source": [
+    "### Create the index\n",
+    "Here we create an index backed by LanceDB using the documents loaded previously. LanceDBVectorStore takes a few arguments.\n",
+    "- uri (str, required): Location where LanceDB will store its files.\n",
+    "- table_name (str, optional): The table name where the embeddings will be stored. Defaults to \"vectors\".\n",
+    "- nprobes (int, optional): The number of probes used. A higher number makes search more accurate but also slower. Defaults to 20.\n",
+    "- refine_factor: (int, optional): Refine the results by reading extra elements and re-ranking them in memory. Defaults to None\n",
+    "\n",
+    "- More details can be found at [LanceDB docs](https://lancedb.github.io/lancedb/ann_indexes)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1f2e20ef",
+   "metadata": {},
+   "source": [
+    "##### For LanceDB cloud :\n",
+    "```python\n",
+    "vector_store = LanceDBVectorStore( \n",
+    "    uri=\"db://db_name\", # your remote DB URI\n",
+    "    api_key=\"sk_..\", # lancedb cloud api key\n",
+    "    region=\"your-region\" # the region you configured\n",
+    "    ...\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8731da62",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "vector_store = LanceDBVectorStore(\n",
+    "    uri=\"./lancedb\", mode=\"overwrite\", query_type=\"hybrid\"\n",
+    ")\n",
+    "storage_context = StorageContext.from_defaults(vector_store=vector_store)\n",
+    "\n",
+    "index = VectorStoreIndex.from_documents(\n",
+    "    documents, storage_context=storage_context\n",
+    ")"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "8ee4473a-094f-4d0a-a825-e1213db07240",
+   "metadata": {},
+   "source": [
+    "### Query the index\n",
+    "We can now ask questions using our index. We can use filtering via `MetadataFilters` or use native lance `where` clause."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5eb6419b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core.vector_stores import (\n",
+    "    MetadataFilters,\n",
+    "    FilterOperator,\n",
+    "    FilterCondition,\n",
+    "    MetadataFilter,\n",
+    ")\n",
+    "\n",
+    "from datetime import datetime\n",
+    "\n",
+    "\n",
+    "query_filters = MetadataFilters(\n",
+    "    filters=[\n",
+    "        MetadataFilter(\n",
+    "            key=\"creation_date\",\n",
+    "            operator=FilterOperator.EQ,\n",
+    "            value=datetime.now().strftime(\"%Y-%m-%d\"),\n",
+    "        ),\n",
+    "        MetadataFilter(\n",
+    "            key=\"file_size\", value=75040, operator=FilterOperator.GT\n",
+    "        ),\n",
+    "    ],\n",
+    "    condition=FilterCondition.AND,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ee201930",
+   "metadata": {},
+   "source": [
+    "### Hybrid Search\n",
+    "\n",
+    "LanceDB offers hybrid search with reranking capabilities. For complete documentation, refer [here](https://lancedb.github.io/lancedb/hybrid_search/hybrid_search/).\n",
+    "\n",
+    "This example uses the `colbert` reranker. The following cell installs the necessary dependencies for `colbert`. If you choose a different reranker, make sure to adjust the dependencies accordingly."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e12d1454",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "! pip install -U torch transformers tantivy@git+https://github.com/quickwit-oss/tantivy-py#164adc87e1a033117001cf70e38c82a53014d985"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c742cb07",
+   "metadata": {},
+   "source": [
+    "if you want to add a reranker at vector store initialization, you can pass it in the arguments like below :\n",
+    "```\n",
+    "from lancedb.rerankers import ColbertReranker\n",
+    "reranker = ColbertReranker()\n",
+    "vector_store = LanceDBVectorStore(uri=\"./lancedb\", reranker=reranker, mode=\"overwrite\")\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "27ea047b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import lancedb"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8414517f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from lancedb.rerankers import ColbertReranker\n",
+    "\n",
+    "reranker = ColbertReranker()\n",
+    "vector_store._add_reranker(reranker)\n",
+    "\n",
+    "query_engine = index.as_query_engine(\n",
+    "    filters=query_filters,\n",
+    "    # vector_store_kwargs={\n",
+    "    #     \"query_type\": \"fts\",\n",
+    "    # },\n",
+    ")\n",
+    "\n",
+    "response = query_engine.query(\"How much did Viaweb charge per month?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dc6ccb7a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Viaweb charged $100 a month for a small store and $300 a month for a big one.\n",
+      "metadata - {'65ed5f07-5b8a-4143-a939-e8764884828e': {'file_path': '/Users/raghavdixit/Desktop/open_source/llama_index_lance/docs/docs/examples/vector_stores/data/paul_graham/paul_graham_essay.txt', 'file_name': 'paul_graham_essay.txt', 'file_type': 'text/plain', 'file_size': 75042, 'creation_date': '2024-06-11', 'last_modified_date': '2024-06-11'}, 'be231827-20b8-4988-ac75-94fa79b3c22e': {'file_path': '/Users/raghavdixit/Desktop/open_source/llama_index_lance/docs/docs/examples/vector_stores/data/paul_graham/paul_graham_essay.txt', 'file_name': 'paul_graham_essay.txt', 'file_type': 'text/plain', 'file_size': 75042, 'creation_date': '2024-06-11', 'last_modified_date': '2024-06-11'}}\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(response)\n",
+    "print(\"metadata -\", response.metadata)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0c1c6c73",
+   "metadata": {},
+   "source": [
+    "##### lance filters(SQL like) directly via the `where` clause :"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0a2bcc07",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lance_filter = \"metadata.file_name = 'paul_graham_essay.txt' \"\n",
+    "retriever = index.as_retriever(vector_store_kwargs={\"where\": lance_filter})\n",
+    "response = retriever.retrieve(\"What did the author do growing up?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7ac47cf9",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "What I Worked On\n",
+      "\n",
+      "February 2021\n",
+      "\n",
+      "Before college the two main things I worked on, outside of school, were writing and programming. I didn't write essays. I wrote what beginning writers were supposed to write then, and probably still are: short stories. My stories were awful. They had hardly any plot, just characters with strong feelings, which I imagined made them deep.\n",
+      "\n",
+      "The first programs I tried writing were on the IBM 1401 that our school district used for what was then called \"data processing.\" This was in 9th grade, so I was 13 or 14. The school district's 1401 happened to be in the basement of our junior high school, and my friend Rich Draves and I got permission to use it. It was like a mini Bond villain's lair down there, with all these alien-looking machines — CPU, disk drives, printer, card reader — sitting up on a raised floor under bright fluorescent lights.\n",
+      "\n",
+      "The language we used was an early version of Fortran. You had to type programs on punch cards, then stack them in the card reader and press a button to load the program into memory and run it. The result would ordinarily be to print something on the spectacularly loud printer.\n",
+      "\n",
+      "I was puzzled by the 1401. I couldn't figure out what to do with it. And in retrospect there's not much I could have done with it. The only form of input to programs was data stored on punched cards, and I didn't have any data stored on punched cards. The only other option was to do things that didn't rely on any input, like calculate approximations of pi, but I didn't know enough math to do anything interesting of that type. So I'm not surprised I can't remember any programs I wrote, because they can't have done much. My clearest memory is of the moment I learned it was possible for programs not to terminate, when one of mine didn't. On a machine without time-sharing, this was a social as well as a technical error, as the data center manager's expression made clear.\n",
+      "\n",
+      "With microcomputers, everything changed. Now you could have a computer sitting right in front of you, on a desk, that could respond to your keystrokes as it was running instead of just churning through a stack of punch cards and then stopping. [1]\n",
+      "\n",
+      "The first of my friends to get a microcomputer built it himself. It was sold as a kit by Heathkit. I remember vividly how impressed and envious I felt watching him sitting in front of it, typing programs right into the computer.\n",
+      "\n",
+      "Computers were expensive in those days and it took me years of nagging before I convinced my father to buy one, a TRS-80, in about 1980. The gold standard then was the Apple II, but a TRS-80 was good enough. This was when I really started programming. I wrote simple games, a program to predict how high my model rockets would fly, and a word processor that my father used to write at least one book. There was only room in memory for about 2 pages of text, so he'd write 2 pages at a time and then print them out, but it was a lot better than a typewriter.\n",
+      "\n",
+      "Though I liked programming, I didn't plan to study it in college. In college I was going to study philosophy, which sounded much more powerful. It seemed, to my naive high school self, to be the study of the ultimate truths, compared to which the things studied in other fields would be mere domain knowledge. What I discovered when I got to college was that the other fields took up so much of the space of ideas that there wasn't much left for these supposed ultimate truths. All that seemed left for philosophy were edge cases that people in other fields felt could safely be ignored.\n",
+      "\n",
+      "I couldn't have put this into words when I was 18. All I knew at the time was that I kept taking philosophy courses and they kept being boring. So I decided to switch to AI.\n",
+      "\n",
+      "AI was in the air in the mid 1980s, but there were two things especially that made me want to work on it: a novel by Heinlein called The Moon is a Harsh Mistress, which featured an intelligent computer called Mike, and a PBS documentary that showed Terry Winograd using SHRDLU. I haven't tried rereading The Moon is a Harsh Mistress, so I don't know how well it has aged, but when I read it I was drawn entirely into its world.\n",
+      "metadata - {'file_path': '/Users/raghavdixit/Desktop/open_source/llama_index_lance/docs/docs/examples/vector_stores/data/paul_graham/paul_graham_essay.txt', 'file_name': 'paul_graham_essay.txt', 'file_type': 'text/plain', 'file_size': 75042, 'creation_date': '2024-06-11', 'last_modified_date': '2024-06-11'}\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(response[0].get_content())\n",
+    "print(\"metadata -\", response[0].metadata)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "6afc84ac",
+   "metadata": {},
+   "source": [
+    "### Appending data\n",
+    "You can also add data to an existing index"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "759a532e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "nodes = [node.node for node in response]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "069fc099",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "del index\n",
+    "\n",
+    "index = VectorStoreIndex.from_documents(\n",
+    "    [Document(text=\"The sky is purple in Portland, Maine\")],\n",
+    "    uri=\"/tmp/new_dataset\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a64ed441",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "index.insert_nodes(nodes)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b5cffcfe",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Portland, Maine\n"
+     ]
+    }
+   ],
+   "source": [
+    "query_engine = index.as_query_engine()\n",
+    "response = query_engine.query(\"Where is the sky purple?\")\n",
+    "print(textwrap.fill(str(response), 100))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ec548a02",
+   "metadata": {},
+   "source": [
+    "You can also create an index from an existing table"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dc99404d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "del index\n",
+    "\n",
+    "vec_store = LanceDBVectorStore.from_table(vector_store._table)\n",
+    "index = VectorStoreIndex.from_vector_store(vec_store)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7b2e8cca",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The author started Viaweb and Aspra.\n"
+     ]
+    }
+   ],
+   "source": [
+    "query_engine = index.as_query_engine()\n",
+    "response = query_engine.query(\"What companies did the author start?\")\n",
+    "print(textwrap.fill(str(response), 100))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}