Compare commits

..

1 Commits

Author SHA1 Message Date
albertlockett
3228fb9cd9 test 2024-10-08 18:28:02 -04:00
273 changed files with 6507 additions and 19648 deletions

View File

@@ -1,5 +1,5 @@
[tool.bumpversion]
current_version = "0.14.1-beta.2"
current_version = "0.11.0-beta.1"
parse = """(?x)
(?P<major>0|[1-9]\\d*)\\.
(?P<minor>0|[1-9]\\d*)\\.
@@ -66,47 +66,6 @@ glob = "nodejs/npm/*/package.json"
replace = "\"version\": \"{new_version}\","
search = "\"version\": \"{current_version}\","
# vectodb node binary packages
[[tool.bumpversion.files]]
glob = "node/package.json"
replace = "\"@lancedb/vectordb-darwin-arm64\": \"{new_version}\""
search = "\"@lancedb/vectordb-darwin-arm64\": \"{current_version}\""
[[tool.bumpversion.files]]
glob = "node/package.json"
replace = "\"@lancedb/vectordb-darwin-x64\": \"{new_version}\""
search = "\"@lancedb/vectordb-darwin-x64\": \"{current_version}\""
[[tool.bumpversion.files]]
glob = "node/package.json"
replace = "\"@lancedb/vectordb-linux-arm64-gnu\": \"{new_version}\""
search = "\"@lancedb/vectordb-linux-arm64-gnu\": \"{current_version}\""
[[tool.bumpversion.files]]
glob = "node/package.json"
replace = "\"@lancedb/vectordb-linux-x64-gnu\": \"{new_version}\""
search = "\"@lancedb/vectordb-linux-x64-gnu\": \"{current_version}\""
[[tool.bumpversion.files]]
glob = "node/package.json"
replace = "\"@lancedb/vectordb-linux-arm64-musl\": \"{new_version}\""
search = "\"@lancedb/vectordb-linux-arm64-musl\": \"{current_version}\""
[[tool.bumpversion.files]]
glob = "node/package.json"
replace = "\"@lancedb/vectordb-linux-x64-musl\": \"{new_version}\""
search = "\"@lancedb/vectordb-linux-x64-musl\": \"{current_version}\""
[[tool.bumpversion.files]]
glob = "node/package.json"
replace = "\"@lancedb/vectordb-win32-x64-msvc\": \"{new_version}\""
search = "\"@lancedb/vectordb-win32-x64-msvc\": \"{current_version}\""
[[tool.bumpversion.files]]
glob = "node/package.json"
replace = "\"@lancedb/vectordb-win32-arm64-msvc\": \"{new_version}\""
search = "\"@lancedb/vectordb-win32-arm64-msvc\": \"{current_version}\""
# Cargo files
# ------------
[[tool.bumpversion.files]]
@@ -118,8 +77,3 @@ search = "\nversion = \"{current_version}\""
filename = "rust/lancedb/Cargo.toml"
replace = "\nversion = \"{new_version}\""
search = "\nversion = \"{current_version}\""
[[tool.bumpversion.files]]
filename = "nodejs/Cargo.toml"
replace = "\nversion = \"{new_version}\""
search = "\nversion = \"{current_version}\""

View File

@@ -31,9 +31,6 @@ rustflags = [
[target.x86_64-unknown-linux-gnu]
rustflags = ["-C", "target-cpu=haswell", "-C", "target-feature=+avx2,+fma,+f16c"]
[target.x86_64-unknown-linux-musl]
rustflags = ["-C", "target-cpu=haswell", "-C", "target-feature=-crt-static,+avx2,+fma,+f16c"]
[target.aarch64-apple-darwin]
rustflags = ["-C", "target-cpu=apple-m1", "-C", "target-feature=+neon,+fp16,+fhm,+dotprod"]
@@ -41,7 +38,3 @@ rustflags = ["-C", "target-cpu=apple-m1", "-C", "target-feature=+neon,+fp16,+fhm
# not found errors on systems that are missing it.
[target.x86_64-pc-windows-msvc]
rustflags = ["-Ctarget-feature=+crt-static"]
# Experimental target for Arm64 Windows
[target.aarch64-pc-windows-msvc]
rustflags = ["-Ctarget-feature=+crt-static"]

View File

@@ -31,7 +31,7 @@ jobs:
- name: Install dependecies needed for ubuntu
run: |
sudo apt install -y protobuf-compiler libssl-dev
rustup update && rustup default
rustup update && rustup default
- name: Set up Python
uses: actions/setup-python@v5
with:
@@ -41,8 +41,8 @@ jobs:
- name: Build Python
working-directory: python
run: |
python -m pip install --extra-index-url https://pypi.fury.io/lancedb/ -e .
python -m pip install --extra-index-url https://pypi.fury.io/lancedb/ -r ../docs/requirements.txt
python -m pip install -e .
python -m pip install -r ../docs/requirements.txt
- name: Set up node
uses: actions/setup-node@v3
with:
@@ -72,9 +72,9 @@ jobs:
- name: Setup Pages
uses: actions/configure-pages@v2
- name: Upload artifact
uses: actions/upload-pages-artifact@v3
uses: actions/upload-pages-artifact@v1
with:
path: "docs/site"
- name: Deploy to GitHub Pages
id: deployment
uses: actions/deploy-pages@v4
uses: actions/deploy-pages@v1

View File

@@ -49,7 +49,7 @@ jobs:
- name: Build Python
working-directory: docs/test
run:
python -m pip install --extra-index-url https://pypi.fury.io/lancedb/ -r requirements.txt
python -m pip install -r requirements.txt
- name: Create test files
run: |
cd docs/test

View File

@@ -53,9 +53,6 @@ jobs:
cargo clippy --all --all-features -- -D warnings
npm ci
npm run lint-ci
- name: Lint examples
working-directory: nodejs/examples
run: npm ci && npm run lint-ci
linux:
name: Linux (NodeJS ${{ matrix.node-version }})
timeout-minutes: 30
@@ -94,18 +91,6 @@ jobs:
env:
S3_TEST: "1"
run: npm run test
- name: Setup examples
working-directory: nodejs/examples
run: npm ci
- name: Test examples
working-directory: ./
env:
OPENAI_API_KEY: test
OPENAI_BASE_URL: http://0.0.0.0:8000
run: |
python ci/mock_openai.py &
cd nodejs/examples
npm test
macos:
timeout-minutes: 30
runs-on: "macos-14"

View File

@@ -101,7 +101,7 @@ jobs:
path: |
nodejs/dist/*.node
node-linux-gnu:
node-linux:
name: vectordb (${{ matrix.config.arch}}-unknown-linux-gnu)
runs-on: ${{ matrix.config.runner }}
# Only runs on tags that matches the make-release action
@@ -133,67 +133,15 @@ jobs:
free -h
- name: Build Linux Artifacts
run: |
bash ci/build_linux_artifacts.sh ${{ matrix.config.arch }} ${{ matrix.config.arch }}-unknown-linux-gnu
bash ci/build_linux_artifacts.sh ${{ matrix.config.arch }}
- name: Upload Linux Artifacts
uses: actions/upload-artifact@v4
with:
name: node-native-linux-${{ matrix.config.arch }}-gnu
name: node-native-linux-${{ matrix.config.arch }}
path: |
node/dist/lancedb-vectordb-linux*.tgz
node-linux-musl:
name: vectordb (${{ matrix.config.arch}}-unknown-linux-musl)
runs-on: ubuntu-latest
container: alpine:edge
# Only runs on tags that matches the make-release action
if: startsWith(github.ref, 'refs/tags/v')
strategy:
fail-fast: false
matrix:
config:
- arch: x86_64
- arch: aarch64
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Install common dependencies
run: |
apk add protobuf-dev curl clang mold grep npm bash
curl --proto '=https' --tlsv1.3 -sSf https://raw.githubusercontent.com/rust-lang/rustup/refs/heads/master/rustup-init.sh | sh -s -- -y --default-toolchain 1.80.0
echo "source $HOME/.cargo/env" >> saved_env
echo "export CC=clang" >> saved_env
echo "export RUSTFLAGS='-Ctarget-cpu=haswell -Ctarget-feature=-crt-static,+avx2,+fma,+f16c -Clinker=clang -Clink-arg=-fuse-ld=mold'" >> saved_env
- name: Configure aarch64 build
if: ${{ matrix.config.arch == 'aarch64' }}
run: |
source "$HOME/.cargo/env"
rustup target add aarch64-unknown-linux-musl --toolchain 1.80.0
crt=$(realpath $(dirname $(rustup which rustc))/../lib/rustlib/aarch64-unknown-linux-musl/lib/self-contained)
sysroot_lib=/usr/aarch64-unknown-linux-musl/usr/lib
apk_url=https://dl-cdn.alpinelinux.org/alpine/latest-stable/main/aarch64/
curl -sSf $apk_url > apk_list
for pkg in gcc libgcc musl; do curl -sSf $apk_url$(cat apk_list | grep -oP '(?<=")'$pkg'-\d.*?(?=")') | tar zxf -; done
mkdir -p $sysroot_lib
echo 'GROUP ( libgcc_s.so.1 -lgcc )' > $sysroot_lib/libgcc_s.so
cp usr/lib/libgcc_s.so.1 $sysroot_lib
cp usr/lib/gcc/aarch64-alpine-linux-musl/*/libgcc.a $sysroot_lib
cp lib/ld-musl-aarch64.so.1 $sysroot_lib/libc.so
echo '!<arch>' > $sysroot_lib/libdl.a
(cd $crt && cp crti.o crtbeginS.o crtendS.o crtn.o -t $sysroot_lib)
echo "export CARGO_BUILD_TARGET=aarch64-unknown-linux-musl" >> saved_env
echo "export RUSTFLAGS='-Ctarget-cpu=apple-m1 -Ctarget-feature=-crt-static,+neon,+fp16,+fhm,+dotprod -Clinker=clang -Clink-arg=-fuse-ld=mold -Clink-arg=--target=aarch64-unknown-linux-musl -Clink-arg=--sysroot=/usr/aarch64-unknown-linux-musl -Clink-arg=-lc'" >> saved_env
- name: Build Linux Artifacts
run: |
source ./saved_env
bash ci/manylinux_node/build_vectordb.sh ${{ matrix.config.arch }} ${{ matrix.config.arch }}-unknown-linux-musl
- name: Upload Linux Artifacts
uses: actions/upload-artifact@v4
with:
name: node-native-linux-${{ matrix.config.arch }}-musl
path: |
node/dist/lancedb-vectordb-linux*.tgz
nodejs-linux-gnu:
nodejs-linux:
name: lancedb (${{ matrix.config.arch}}-unknown-linux-gnu
runs-on: ${{ matrix.config.runner }}
# Only runs on tags that matches the make-release action
@@ -230,7 +178,7 @@ jobs:
- name: Upload Linux Artifacts
uses: actions/upload-artifact@v4
with:
name: nodejs-native-linux-${{ matrix.config.arch }}-gnu
name: nodejs-native-linux-${{ matrix.config.arch }}
path: |
nodejs/dist/*.node
# The generic files are the same in all distros so we just pick
@@ -244,62 +192,6 @@ jobs:
nodejs/dist/*
!nodejs/dist/*.node
nodejs-linux-musl:
name: lancedb (${{ matrix.config.arch}}-unknown-linux-musl
runs-on: ubuntu-latest
container: alpine:edge
# Only runs on tags that matches the make-release action
if: startsWith(github.ref, 'refs/tags/v')
strategy:
fail-fast: false
matrix:
config:
- arch: x86_64
- arch: aarch64
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Install common dependencies
run: |
apk add protobuf-dev curl clang mold grep npm bash openssl-dev openssl-libs-static
curl --proto '=https' --tlsv1.3 -sSf https://raw.githubusercontent.com/rust-lang/rustup/refs/heads/master/rustup-init.sh | sh -s -- -y --default-toolchain 1.80.0
echo "source $HOME/.cargo/env" >> saved_env
echo "export CC=clang" >> saved_env
echo "export RUSTFLAGS='-Ctarget-cpu=haswell -Ctarget-feature=-crt-static,+avx2,+fma,+f16c -Clinker=clang -Clink-arg=-fuse-ld=mold'" >> saved_env
echo "export X86_64_UNKNOWN_LINUX_MUSL_OPENSSL_INCLUDE_DIR=/usr/include" >> saved_env
echo "export X86_64_UNKNOWN_LINUX_MUSL_OPENSSL_LIB_DIR=/usr/lib" >> saved_env
- name: Configure aarch64 build
if: ${{ matrix.config.arch == 'aarch64' }}
run: |
source "$HOME/.cargo/env"
rustup target add aarch64-unknown-linux-musl --toolchain 1.80.0
crt=$(realpath $(dirname $(rustup which rustc))/../lib/rustlib/aarch64-unknown-linux-musl/lib/self-contained)
sysroot_lib=/usr/aarch64-unknown-linux-musl/usr/lib
apk_url=https://dl-cdn.alpinelinux.org/alpine/latest-stable/main/aarch64/
curl -sSf $apk_url > apk_list
for pkg in gcc libgcc musl openssl-dev openssl-libs-static; do curl -sSf $apk_url$(cat apk_list | grep -oP '(?<=")'$pkg'-\d.*?(?=")') | tar zxf -; done
mkdir -p $sysroot_lib
echo 'GROUP ( libgcc_s.so.1 -lgcc )' > $sysroot_lib/libgcc_s.so
cp usr/lib/libgcc_s.so.1 $sysroot_lib
cp usr/lib/gcc/aarch64-alpine-linux-musl/*/libgcc.a $sysroot_lib
cp lib/ld-musl-aarch64.so.1 $sysroot_lib/libc.so
echo '!<arch>' > $sysroot_lib/libdl.a
(cd $crt && cp crti.o crtbeginS.o crtendS.o crtn.o -t $sysroot_lib)
echo "export CARGO_BUILD_TARGET=aarch64-unknown-linux-musl" >> saved_env
echo "export RUSTFLAGS='-Ctarget-feature=-crt-static,+neon,+fp16,+fhm,+dotprod -Clinker=clang -Clink-arg=-fuse-ld=mold -Clink-arg=--target=aarch64-unknown-linux-musl -Clink-arg=--sysroot=/usr/aarch64-unknown-linux-musl -Clink-arg=-lc'" >> saved_env
echo "export AARCH64_UNKNOWN_LINUX_MUSL_OPENSSL_INCLUDE_DIR=$(realpath usr/include)" >> saved_env
echo "export AARCH64_UNKNOWN_LINUX_MUSL_OPENSSL_LIB_DIR=$(realpath usr/lib)" >> saved_env
- name: Build Linux Artifacts
run: |
source ./saved_env
bash ci/manylinux_node/build_lancedb.sh ${{ matrix.config.arch }}
- name: Upload Linux Artifacts
uses: actions/upload-artifact@v4
with:
name: nodejs-native-linux-${{ matrix.config.arch }}-musl
path: |
nodejs/dist/*.node
node-windows:
name: vectordb ${{ matrix.target }}
runs-on: windows-2022
@@ -334,51 +226,6 @@ jobs:
path: |
node/dist/lancedb-vectordb-win32*.tgz
node-windows-arm64:
name: vectordb ${{ matrix.config.arch }}-pc-windows-msvc
if: startsWith(github.ref, 'refs/tags/v')
runs-on: ubuntu-latest
container: alpine:edge
strategy:
fail-fast: false
matrix:
config:
# - arch: x86_64
- arch: aarch64
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Install dependencies
run: |
apk add protobuf-dev curl clang lld llvm19 grep npm bash msitools sed
curl --proto '=https' --tlsv1.3 -sSf https://raw.githubusercontent.com/rust-lang/rustup/refs/heads/master/rustup-init.sh | sh -s -- -y --default-toolchain 1.80.0
echo "source $HOME/.cargo/env" >> saved_env
echo "export CC=clang" >> saved_env
echo "export AR=llvm-ar" >> saved_env
source "$HOME/.cargo/env"
rustup target add ${{ matrix.config.arch }}-pc-windows-msvc --toolchain 1.80.0
(mkdir -p sysroot && cd sysroot && sh ../ci/sysroot-${{ matrix.config.arch }}-pc-windows-msvc.sh)
echo "export C_INCLUDE_PATH=/usr/${{ matrix.config.arch }}-pc-windows-msvc/usr/include" >> saved_env
echo "export CARGO_BUILD_TARGET=${{ matrix.config.arch }}-pc-windows-msvc" >> saved_env
- name: Configure x86_64 build
if: ${{ matrix.config.arch == 'x86_64' }}
run: |
echo "export RUSTFLAGS='-Ctarget-cpu=haswell -Ctarget-feature=+crt-static,+avx2,+fma,+f16c -Clinker=lld -Clink-arg=/LIBPATH:/usr/x86_64-pc-windows-msvc/usr/lib'" >> saved_env
- name: Configure aarch64 build
if: ${{ matrix.config.arch == 'aarch64' }}
run: |
echo "export RUSTFLAGS='-Ctarget-feature=+crt-static,+neon,+fp16,+fhm,+dotprod -Clinker=lld -Clink-arg=/LIBPATH:/usr/aarch64-pc-windows-msvc/usr/lib -Clink-arg=arm64rt.lib'" >> saved_env
- name: Build Windows Artifacts
run: |
source ./saved_env
bash ci/manylinux_node/build_vectordb.sh ${{ matrix.config.arch }} ${{ matrix.config.arch }}-pc-windows-msvc
- name: Upload Windows Artifacts
uses: actions/upload-artifact@v4
with:
name: node-native-windows-${{ matrix.config.arch }}
path: |
node/dist/lancedb-vectordb-win32*.tgz
nodejs-windows:
name: lancedb ${{ matrix.target }}
runs-on: windows-2022
@@ -413,57 +260,9 @@ jobs:
path: |
nodejs/dist/*.node
nodejs-windows-arm64:
name: lancedb ${{ matrix.config.arch }}-pc-windows-msvc
# Only runs on tags that matches the make-release action
if: startsWith(github.ref, 'refs/tags/v')
runs-on: ubuntu-latest
container: alpine:edge
strategy:
fail-fast: false
matrix:
config:
# - arch: x86_64
- arch: aarch64
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Install dependencies
run: |
apk add protobuf-dev curl clang lld llvm19 grep npm bash msitools sed
curl --proto '=https' --tlsv1.3 -sSf https://raw.githubusercontent.com/rust-lang/rustup/refs/heads/master/rustup-init.sh | sh -s -- -y --default-toolchain 1.80.0
echo "source $HOME/.cargo/env" >> saved_env
echo "export CC=clang" >> saved_env
echo "export AR=llvm-ar" >> saved_env
source "$HOME/.cargo/env"
rustup target add ${{ matrix.config.arch }}-pc-windows-msvc --toolchain 1.80.0
(mkdir -p sysroot && cd sysroot && sh ../ci/sysroot-${{ matrix.config.arch }}-pc-windows-msvc.sh)
echo "export C_INCLUDE_PATH=/usr/${{ matrix.config.arch }}-pc-windows-msvc/usr/include" >> saved_env
echo "export CARGO_BUILD_TARGET=${{ matrix.config.arch }}-pc-windows-msvc" >> saved_env
printf '#!/bin/sh\ncargo "$@"' > $HOME/.cargo/bin/cargo-xwin
chmod u+x $HOME/.cargo/bin/cargo-xwin
- name: Configure x86_64 build
if: ${{ matrix.config.arch == 'x86_64' }}
run: |
echo "export RUSTFLAGS='-Ctarget-cpu=haswell -Ctarget-feature=+crt-static,+avx2,+fma,+f16c -Clinker=lld -Clink-arg=/LIBPATH:/usr/x86_64-pc-windows-msvc/usr/lib'" >> saved_env
- name: Configure aarch64 build
if: ${{ matrix.config.arch == 'aarch64' }}
run: |
echo "export RUSTFLAGS='-Ctarget-feature=+crt-static,+neon,+fp16,+fhm,+dotprod -Clinker=lld -Clink-arg=/LIBPATH:/usr/aarch64-pc-windows-msvc/usr/lib -Clink-arg=arm64rt.lib'" >> saved_env
- name: Build Windows Artifacts
run: |
source ./saved_env
bash ci/manylinux_node/build_lancedb.sh ${{ matrix.config.arch }}
- name: Upload Windows Artifacts
uses: actions/upload-artifact@v4
with:
name: nodejs-native-windows-${{ matrix.config.arch }}
path: |
nodejs/dist/*.node
release:
name: vectordb NPM Publish
needs: [node, node-macos, node-linux-gnu, node-linux-musl, node-windows, node-windows-arm64]
needs: [node, node-macos, node-linux, node-windows]
runs-on: ubuntu-latest
# Only runs on tags that matches the make-release action
if: startsWith(github.ref, 'refs/tags/v')
@@ -481,7 +280,7 @@ jobs:
env:
NODE_AUTH_TOKEN: ${{ secrets.LANCEDB_NPM_REGISTRY_TOKEN }}
run: |
# Tag beta as "preview" instead of default "latest". See lancedb
# Tag beta as "preview" instead of default "latest". See lancedb
# npm publish step for more info.
if [[ $GITHUB_REF =~ refs/tags/v(.*)-beta.* ]]; then
PUBLISH_ARGS="--tag preview"
@@ -503,7 +302,7 @@ jobs:
release-nodejs:
name: lancedb NPM Publish
needs: [nodejs-macos, nodejs-linux-gnu, nodejs-linux-musl, nodejs-windows, nodejs-windows-arm64]
needs: [nodejs-macos, nodejs-linux, nodejs-windows]
runs-on: ubuntu-latest
# Only runs on tags that matches the make-release action
if: startsWith(github.ref, 'refs/tags/v')
@@ -561,7 +360,6 @@ jobs:
SLACK_WEBHOOK_URL: ${{ secrets.ACTION_MONITORING_SLACK }}
update-package-lock:
if: startsWith(github.ref, 'refs/tags/v')
needs: [release]
runs-on: ubuntu-latest
permissions:
@@ -579,7 +377,6 @@ jobs:
github_token: ${{ secrets.GITHUB_TOKEN }}
update-package-lock-nodejs:
if: startsWith(github.ref, 'refs/tags/v')
needs: [release-nodejs]
runs-on: ubuntu-latest
permissions:
@@ -597,7 +394,6 @@ jobs:
github_token: ${{ secrets.GITHUB_TOKEN }}
gh-release:
if: startsWith(github.ref, 'refs/tags/v')
runs-on: ubuntu-latest
permissions:
contents: write

View File

@@ -83,7 +83,7 @@ jobs:
- name: Set up Python
uses: actions/setup-python@v4
with:
python-version: 3.12
python-version: 3.8
- uses: ./.github/workflows/build_windows_wheel
with:
python-minor-version: 8

View File

@@ -138,7 +138,7 @@ jobs:
run: rm -rf target/wheels
windows:
name: "Windows: ${{ matrix.config.name }}"
timeout-minutes: 60
timeout-minutes: 30
strategy:
matrix:
config:

View File

@@ -35,22 +35,21 @@ jobs:
CC: clang-18
CXX: clang++-18
steps:
- uses: actions/checkout@v4
with:
- uses: actions/checkout@v4
with:
fetch-depth: 0
lfs: true
- uses: Swatinem/rust-cache@v2
with:
workspaces: rust
- name: Install dependencies
run: |
- uses: Swatinem/rust-cache@v2
with:
workspaces: rust
- name: Install dependencies
run: |
sudo apt update
sudo apt install -y protobuf-compiler libssl-dev
- name: Run format
run: cargo fmt --all -- --check
- name: Run clippy
run: cargo clippy --workspace --tests --all-features -- -D warnings
- name: Run format
run: cargo fmt --all -- --check
- name: Run clippy
run: cargo clippy --workspace --tests --all-features -- -D warnings
linux:
timeout-minutes: 30
# To build all features, we need more disk space than is available
@@ -66,38 +65,37 @@ jobs:
CC: clang-18
CXX: clang++-18
steps:
- uses: actions/checkout@v4
with:
- uses: actions/checkout@v4
with:
fetch-depth: 0
lfs: true
- uses: Swatinem/rust-cache@v2
with:
- uses: Swatinem/rust-cache@v2
with:
workspaces: rust
- name: Install dependencies
run: |
- name: Install dependencies
run: |
sudo apt update
sudo apt install -y protobuf-compiler libssl-dev
- name: Make Swap
run: |
sudo fallocate -l 16G /swapfile
sudo chmod 600 /swapfile
sudo mkswap /swapfile
sudo swapon /swapfile
- name: Start S3 integration test environment
working-directory: .
run: docker compose up --detach --wait
- name: Build
run: cargo build --all-features
- name: Run tests
run: cargo test --all-features
- name: Run examples
run: cargo run --example simple
- name: Make Swap
run: |
sudo fallocate -l 16G /swapfile
sudo chmod 600 /swapfile
sudo mkswap /swapfile
sudo swapon /swapfile
- name: Start S3 integration test environment
working-directory: .
run: docker compose up --detach --wait
- name: Build
run: cargo build --all-features
- name: Run tests
run: cargo test --all-features
- name: Run examples
run: cargo run --example simple
macos:
timeout-minutes: 30
strategy:
matrix:
mac-runner: ["macos-13", "macos-14"]
mac-runner: [ "macos-13", "macos-14" ]
runs-on: "${{ matrix.mac-runner }}"
defaults:
run:
@@ -106,8 +104,8 @@ jobs:
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
lfs: true
fetch-depth: 0
lfs: true
- name: CPU features
run: sysctl -a | grep cpu
- uses: Swatinem/rust-cache@v2
@@ -120,7 +118,6 @@ jobs:
- name: Run tests
# Run with everything except the integration tests.
run: cargo test --features remote,fp16kernels
windows:
runs-on: windows-2022
steps:
@@ -142,99 +139,3 @@ jobs:
$env:VCPKG_ROOT = $env:VCPKG_INSTALLATION_ROOT
cargo build
cargo test
windows-arm64:
runs-on: windows-4x-arm
steps:
- name: Install Git
run: |
Invoke-WebRequest -Uri "https://github.com/git-for-windows/git/releases/download/v2.44.0.windows.1/Git-2.44.0-64-bit.exe" -OutFile "git-installer.exe"
Start-Process -FilePath "git-installer.exe" -ArgumentList "/VERYSILENT", "/NORESTART" -Wait
shell: powershell
- name: Add Git to PATH
run: |
Add-Content $env:GITHUB_PATH "C:\Program Files\Git\bin"
$env:Path = [System.Environment]::GetEnvironmentVariable("Path","Machine") + ";" + [System.Environment]::GetEnvironmentVariable("Path","User")
shell: powershell
- name: Configure Git symlinks
run: git config --global core.symlinks true
- uses: actions/checkout@v4
- uses: actions/setup-python@v5
with:
python-version: "3.13"
- name: Install Visual Studio Build Tools
run: |
Invoke-WebRequest -Uri "https://aka.ms/vs/17/release/vs_buildtools.exe" -OutFile "vs_buildtools.exe"
Start-Process -FilePath "vs_buildtools.exe" -ArgumentList "--quiet", "--wait", "--norestart", "--nocache", `
"--installPath", "C:\BuildTools", `
"--add", "Microsoft.VisualStudio.Component.VC.Tools.ARM64", `
"--add", "Microsoft.VisualStudio.Component.VC.Tools.x86.x64", `
"--add", "Microsoft.VisualStudio.Component.Windows11SDK.22621", `
"--add", "Microsoft.VisualStudio.Component.VC.ATL", `
"--add", "Microsoft.VisualStudio.Component.VC.ATLMFC", `
"--add", "Microsoft.VisualStudio.Component.VC.Llvm.Clang" -Wait
shell: powershell
- name: Add Visual Studio Build Tools to PATH
run: |
$vsPath = "C:\BuildTools\VC\Tools\MSVC"
$latestVersion = (Get-ChildItem $vsPath | Sort-Object {[version]$_.Name} -Descending)[0].Name
Add-Content $env:GITHUB_PATH "C:\BuildTools\VC\Tools\MSVC\$latestVersion\bin\Hostx64\arm64"
Add-Content $env:GITHUB_PATH "C:\BuildTools\VC\Tools\MSVC\$latestVersion\bin\Hostx64\x64"
Add-Content $env:GITHUB_PATH "C:\Program Files (x86)\Windows Kits\10\bin\10.0.22621.0\arm64"
Add-Content $env:GITHUB_PATH "C:\Program Files (x86)\Windows Kits\10\bin\10.0.22621.0\x64"
Add-Content $env:GITHUB_PATH "C:\BuildTools\VC\Tools\Llvm\x64\bin"
# Add MSVC runtime libraries to LIB
$env:LIB = "C:\BuildTools\VC\Tools\MSVC\$latestVersion\lib\arm64;" +
"C:\Program Files (x86)\Windows Kits\10\Lib\10.0.22621.0\um\arm64;" +
"C:\Program Files (x86)\Windows Kits\10\Lib\10.0.22621.0\ucrt\arm64"
Add-Content $env:GITHUB_ENV "LIB=$env:LIB"
# Add INCLUDE paths
$env:INCLUDE = "C:\BuildTools\VC\Tools\MSVC\$latestVersion\include;" +
"C:\Program Files (x86)\Windows Kits\10\Include\10.0.22621.0\ucrt;" +
"C:\Program Files (x86)\Windows Kits\10\Include\10.0.22621.0\um;" +
"C:\Program Files (x86)\Windows Kits\10\Include\10.0.22621.0\shared"
Add-Content $env:GITHUB_ENV "INCLUDE=$env:INCLUDE"
shell: powershell
- name: Install Rust
run: |
Invoke-WebRequest https://win.rustup.rs/x86_64 -OutFile rustup-init.exe
.\rustup-init.exe -y --default-host aarch64-pc-windows-msvc
shell: powershell
- name: Add Rust to PATH
run: |
Add-Content $env:GITHUB_PATH "$env:USERPROFILE\.cargo\bin"
shell: powershell
- uses: Swatinem/rust-cache@v2
with:
workspaces: rust
- name: Install 7-Zip ARM
run: |
New-Item -Path 'C:\7zip' -ItemType Directory
Invoke-WebRequest https://7-zip.org/a/7z2408-arm64.exe -OutFile C:\7zip\7z-installer.exe
Start-Process -FilePath C:\7zip\7z-installer.exe -ArgumentList '/S' -Wait
shell: powershell
- name: Add 7-Zip to PATH
run: Add-Content $env:GITHUB_PATH "C:\Program Files\7-Zip"
shell: powershell
- name: Install Protoc v21.12
working-directory: C:\
run: |
if (Test-Path 'C:\protoc') {
Write-Host "Protoc directory exists, skipping installation"
return
}
New-Item -Path 'C:\protoc' -ItemType Directory
Set-Location C:\protoc
Invoke-WebRequest https://github.com/protocolbuffers/protobuf/releases/download/v21.12/protoc-21.12-win64.zip -OutFile C:\protoc\protoc.zip
& 'C:\Program Files\7-Zip\7z.exe' x protoc.zip
shell: powershell
- name: Add Protoc to PATH
run: Add-Content $env:GITHUB_PATH "C:\protoc\bin"
shell: powershell
- name: Run tests
run: |
$env:VCPKG_ROOT = $env:VCPKG_INSTALLATION_ROOT
cargo build --target aarch64-pc-windows-msvc
cargo test --target aarch64-pc-windows-msvc

View File

@@ -17,7 +17,6 @@ runs:
run: |
python -m pip install --upgrade pip
pip install twine
python3 -m pip install --upgrade pkginfo
- name: Choose repo
shell: bash
id: choose_repo

View File

@@ -18,33 +18,28 @@ repository = "https://github.com/lancedb/lancedb"
description = "Serverless, low-latency vector database for AI applications"
keywords = ["lancedb", "lance", "database", "vector", "search"]
categories = ["database-implementations"]
rust-version = "1.80.0" # TODO: lower this once we upgrade Lance again.
[workspace.dependencies]
lance = { "version" = "=0.21.0", "features" = [
"dynamodb",
], git = "https://github.com/lancedb/lance.git", tag = "v0.21.0-beta.2" }
lance-io = { version = "=0.21.0", git = "https://github.com/lancedb/lance.git", tag = "v0.21.0-beta.2" }
lance-index = { version = "=0.21.0", git = "https://github.com/lancedb/lance.git", tag = "v0.21.0-beta.2" }
lance-linalg = { version = "=0.21.0", git = "https://github.com/lancedb/lance.git", tag = "v0.21.0-beta.2" }
lance-table = { version = "=0.21.0", git = "https://github.com/lancedb/lance.git", tag = "v0.21.0-beta.2" }
lance-testing = { version = "=0.21.0", git = "https://github.com/lancedb/lance.git", tag = "v0.21.0-beta.2" }
lance-datafusion = { version = "=0.21.0", git = "https://github.com/lancedb/lance.git", tag = "v0.21.0-beta.2" }
lance-encoding = { version = "=0.21.0", git = "https://github.com/lancedb/lance.git", tag = "v0.21.0-beta.2" }
lance = { "version" = "=0.18.0", "features" = ["dynamodb"] }
lance-index = { "version" = "=0.18.0" }
lance-linalg = { "version" = "=0.18.0" }
lance-table = { "version" = "=0.18.0" }
lance-testing = { "version" = "=0.18.0" }
lance-datafusion = { "version" = "=0.18.0" }
lance-encoding = { "version" = "=0.18.0" }
# Note that this one does not include pyarrow
arrow = { version = "53.2", optional = false }
arrow-array = "53.2"
arrow-data = "53.2"
arrow-ipc = "53.2"
arrow-ord = "53.2"
arrow-schema = "53.2"
arrow-arith = "53.2"
arrow-cast = "53.2"
arrow = { version = "52.2", optional = false }
arrow-array = "52.2"
arrow-data = "52.2"
arrow-ipc = "52.2"
arrow-ord = "52.2"
arrow-schema = "52.2"
arrow-arith = "52.2"
arrow-cast = "52.2"
async-trait = "0"
chrono = "0.4.35"
datafusion-common = "42.0"
datafusion-physical-plan = "42.0"
env_logger = "0.10"
datafusion-common = "40.0"
datafusion-physical-plan = "40.0"
half = { "version" = "=2.4.1", default-features = false, features = [
"num-traits",
] }

View File

@@ -10,7 +10,6 @@
[![Blog](https://img.shields.io/badge/Blog-12100E?style=for-the-badge&logoColor=white)](https://blog.lancedb.com/)
[![Discord](https://img.shields.io/badge/Discord-%235865F2.svg?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/zMM32dvNtd)
[![Twitter](https://img.shields.io/badge/Twitter-%231DA1F2.svg?style=for-the-badge&logo=Twitter&logoColor=white)](https://twitter.com/lancedb)
[![Gurubase](https://img.shields.io/badge/Gurubase-Ask%20LanceDB%20Guru-006BFF?style=for-the-badge)](https://gurubase.io/g/lancedb)
</p>

View File

@@ -1,9 +1,8 @@
#!/bin/bash
set -e
ARCH=${1:-x86_64}
TARGET_TRIPLE=${2:-x86_64-unknown-linux-gnu}
# We pass down the current user so that when we later mount the local files
# We pass down the current user so that when we later mount the local files
# into the container, the files are accessible by the current user.
pushd ci/manylinux_node
docker build \
@@ -19,4 +18,4 @@ docker run \
-v $(pwd):/io -w /io \
--memory-swap=-1 \
lancedb-node-manylinux \
bash ci/manylinux_node/build_vectordb.sh $ARCH $TARGET_TRIPLE
bash ci/manylinux_node/build_vectordb.sh $ARCH

View File

@@ -3,7 +3,6 @@
# Targets supported:
# - x86_64-pc-windows-msvc
# - i686-pc-windows-msvc
# - aarch64-pc-windows-msvc
function Prebuild-Rust {
param (
@@ -32,7 +31,7 @@ function Build-NodeBinaries {
$targets = $args[0]
if (-not $targets) {
$targets = "x86_64-pc-windows-msvc", "aarch64-pc-windows-msvc"
$targets = "x86_64-pc-windows-msvc"
}
Write-Host "Building artifacts for targets: $targets"

View File

@@ -3,7 +3,6 @@
# Targets supported:
# - x86_64-pc-windows-msvc
# - i686-pc-windows-msvc
# - aarch64-pc-windows-msvc
function Prebuild-Rust {
param (
@@ -32,7 +31,7 @@ function Build-NodeBinaries {
$targets = $args[0]
if (-not $targets) {
$targets = "x86_64-pc-windows-msvc", "aarch64-pc-windows-msvc"
$targets = "x86_64-pc-windows-msvc"
}
Write-Host "Building artifacts for targets: $targets"

View File

@@ -11,8 +11,7 @@ fi
export OPENSSL_STATIC=1
export OPENSSL_INCLUDE_DIR=/usr/local/include/openssl
#Alpine doesn't have .bashrc
FILE=$HOME/.bashrc && test -f $FILE && source $FILE
source $HOME/.bashrc
cd nodejs
npm ci

View File

@@ -2,20 +2,18 @@
# Builds the node module for manylinux. Invoked by ci/build_linux_artifacts.sh.
set -e
ARCH=${1:-x86_64}
TARGET_TRIPLE=${2:-x86_64-unknown-linux-gnu}
if [ "$ARCH" = "x86_64" ]; then
export OPENSSL_LIB_DIR=/usr/local/lib64/
else
else
export OPENSSL_LIB_DIR=/usr/local/lib/
fi
export OPENSSL_STATIC=1
export OPENSSL_INCLUDE_DIR=/usr/local/include/openssl
#Alpine doesn't have .bashrc
FILE=$HOME/.bashrc && test -f $FILE && source $FILE
source $HOME/.bashrc
cd node
npm ci
npm run build-release
npm run pack-build -- -t $TARGET_TRIPLE
npm run pack-build

View File

@@ -1,57 +0,0 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright The LanceDB Authors
"""A zero-dependency mock OpenAI embeddings API endpoint for testing purposes."""
import argparse
import json
import http.server
class MockOpenAIRequestHandler(http.server.BaseHTTPRequestHandler):
def do_POST(self):
content_length = int(self.headers["Content-Length"])
post_data = self.rfile.read(content_length)
post_data = json.loads(post_data.decode("utf-8"))
# See: https://platform.openai.com/docs/api-reference/embeddings/create
if isinstance(post_data["input"], str):
num_inputs = 1
else:
num_inputs = len(post_data["input"])
model = post_data.get("model", "text-embedding-ada-002")
data = []
for i in range(num_inputs):
data.append({
"object": "embedding",
"embedding": [0.1] * 1536,
"index": i,
})
response = {
"object": "list",
"data": data,
"model": model,
"usage": {
"prompt_tokens": 0,
"total_tokens": 0,
}
}
self.send_response(200)
self.send_header("Content-type", "application/json")
self.end_headers()
self.wfile.write(json.dumps(response).encode("utf-8"))
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="Mock OpenAI embeddings API endpoint")
parser.add_argument("--port", type=int, default=8000, help="Port to listen on")
args = parser.parse_args()
port = args.port
print(f"server started on port {port}. Press Ctrl-C to stop.")
print(f"To use, set OPENAI_BASE_URL=http://localhost:{port} in your environment.")
with http.server.HTTPServer(("0.0.0.0", port), MockOpenAIRequestHandler) as server:
server.serve_forever()

View File

@@ -1,105 +0,0 @@
#!/bin/sh
# https://github.com/mstorsjo/msvc-wine/blob/master/vsdownload.py
# https://github.com/mozilla/gecko-dev/blob/6027d1d91f2d3204a3992633b3ef730ff005fc64/build/vs/vs2022-car.yaml
# function dl() {
# curl -O https://download.visualstudio.microsoft.com/download/pr/$1
# }
# [[.h]]
# "id": "Win11SDK_10.0.26100"
# "version": "10.0.26100.7"
# libucrt.lib
# example: <assert.h>
# dir: ucrt/
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/2ee3a5fc6e9fc832af7295b138e93839/universal%20crt%20headers%20libraries%20and%20sources-x86_en-us.msi
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/b1aa09b90fe314aceb090f6ec7626624/16ab2ea2187acffa6435e334796c8c89.cab
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/400609bb0ff5804e36dbe6dcd42a7f01/6ee7bbee8435130a869cf971694fd9e2.cab
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/2ac327317abb865a0e3f56b2faefa918/78fa3c824c2c48bd4a49ab5969adaaf7.cab
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/f034bc0b2680f67dccd4bfeea3d0f932/7afc7b670accd8e3cc94cfffd516f5cb.cab
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/7ed5e12f9d50f80825a8b27838cf4c7f/96076045170fe5db6d5dcf14b6f6688e.cab
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/764edc185a696bda9e07df8891dddbbb/a1e2a83aa8a71c48c742eeaff6e71928.cab
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/66854bedc6dbd5ccb5dd82c8e2412231/b2f03f34ff83ec013b9e45c7cd8e8a73.cab
# example: <windows.h>
# dir: um/
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/b286efac4d83a54fc49190bddef1edc9/windows%20sdk%20for%20windows%20store%20apps%20headers-x86_en-us.msi
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/e0dc3811d92ab96fcb72bf63d6c08d71/766c0ffd568bbb31bf7fb6793383e24a.cab
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/613503da4b5628768497822826aed39f/8125ee239710f33ea485965f76fae646.cab
# example: <winapifamily.h>
# dir: /shared
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/122979f0348d3a2a36b6aa1a111d5d0c/windows%20sdk%20for%20windows%20store%20apps%20headers%20onecoreuap-x86_en-us.msi
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/766e04beecdfccff39e91dd9eb32834a/e89e3dcbb016928c7e426238337d69eb.cab
# "id": "Microsoft.VisualC.14.16.CRT.Headers"
# "version": "14.16.27045"
# example: <vcruntime.h>
# dir: MSVC/
curl -O https://download.visualstudio.microsoft.com/download/pr/bac0afd7-cc9e-4182-8a83-9898fa20e092/87bbe41e09a2f83711e72696f49681429327eb7a4b90618c35667a6ba2e2880e/Microsoft.VisualC.14.16.CRT.Headers.vsix
# [[.lib]]
# advapi32.lib bcrypt.lib kernel32.lib ntdll.lib user32.lib uuid.lib ws2_32.lib userenv.lib cfgmgr32.lib runtimeobject.lib
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/944c4153b849a1f7d0c0404a4f1c05ea/windows%20sdk%20for%20windows%20store%20apps%20libs-x86_en-us.msi
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/5306aed3e1a38d1e8bef5934edeb2a9b/05047a45609f311645eebcac2739fc4c.cab
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/13c8a73a0f5a6474040b26d016a26fab/13d68b8a7b6678a368e2d13ff4027521.cab
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/149578fb3b621cdb61ee1813b9b3e791/463ad1b0783ebda908fd6c16a4abfe93.cab
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/5c986c4f393c6b09d5aec3b539e9fb4a/5a22e5cde814b041749fb271547f4dd5.cab
# fwpuclnt.lib arm64rt.lib
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/7a332420d812f7c1d41da865ae5a7c52/windows%20sdk%20desktop%20libs%20arm64-x86_en-us.msi
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/19de98ed4a79938d0045d19c047936b3/3e2f7be479e3679d700ce0782e4cc318.cab
# libcmt.lib libvcruntime.lib
curl -O https://download.visualstudio.microsoft.com/download/pr/bac0afd7-cc9e-4182-8a83-9898fa20e092/227f40682a88dc5fa0ccb9cadc9ad30af99ad1f1a75db63407587d079f60d035/Microsoft.VisualC.14.16.CRT.ARM64.Desktop.vsix
msiextract universal%20crt%20headers%20libraries%20and%20sources-x86_en-us.msi
msiextract windows%20sdk%20for%20windows%20store%20apps%20headers-x86_en-us.msi
msiextract windows%20sdk%20for%20windows%20store%20apps%20headers%20onecoreuap-x86_en-us.msi
msiextract windows%20sdk%20for%20windows%20store%20apps%20libs-x86_en-us.msi
msiextract windows%20sdk%20desktop%20libs%20arm64-x86_en-us.msi
unzip -o Microsoft.VisualC.14.16.CRT.Headers.vsix
unzip -o Microsoft.VisualC.14.16.CRT.ARM64.Desktop.vsix
mkdir -p /usr/aarch64-pc-windows-msvc/usr/include
mkdir -p /usr/aarch64-pc-windows-msvc/usr/lib
# lowercase folder/file names
echo "$(find . -regex ".*/[^/]*[A-Z][^/]*")" | xargs -I{} sh -c 'mv "$(echo "{}" | sed -E '"'"'s/(.*\/)/\L\1/'"'"')" "$(echo "{}" | tr [A-Z] [a-z])"'
# .h
(cd 'program files/windows kits/10/include/10.0.26100.0' && cp -r ucrt/* um/* shared/* -t /usr/aarch64-pc-windows-msvc/usr/include)
cp -r contents/vc/tools/msvc/14.16.27023/include/* /usr/aarch64-pc-windows-msvc/usr/include
# lowercase #include "" and #include <>
find /usr/aarch64-pc-windows-msvc/usr/include -type f -exec sed -i -E 's/(#include <[^<>]*?[A-Z][^<>]*?>)|(#include "[^"]*?[A-Z][^"]*?")/\L\1\2/' "{}" ';'
# ARM intrinsics
# original dir: MSVC/
# '__n128x4' redefined in arm_neon.h
# "arm64_neon.h" included from intrin.h
(cd /usr/lib/llvm19/lib/clang/19/include && cp arm_neon.h intrin.h -t /usr/aarch64-pc-windows-msvc/usr/include)
# .lib
# _Interlocked intrinsics
# must always link with arm64rt.lib
# reason: https://developercommunity.visualstudio.com/t/libucrtlibstreamobj-error-lnk2001-unresolved-exter/1544787#T-ND1599818
# I don't understand the 'correct' fix for this, arm64rt.lib is supposed to be the workaround
(cd 'program files/windows kits/10/lib/10.0.26100.0/um/arm64' && cp advapi32.lib bcrypt.lib kernel32.lib ntdll.lib user32.lib uuid.lib ws2_32.lib userenv.lib cfgmgr32.lib runtimeobject.lib fwpuclnt.lib arm64rt.lib -t /usr/aarch64-pc-windows-msvc/usr/lib)
(cd 'contents/vc/tools/msvc/14.16.27023/lib/arm64' && cp libcmt.lib libvcruntime.lib -t /usr/aarch64-pc-windows-msvc/usr/lib)
cp 'program files/windows kits/10/lib/10.0.26100.0/ucrt/arm64/libucrt.lib' /usr/aarch64-pc-windows-msvc/usr/lib

View File

@@ -1,105 +0,0 @@
#!/bin/sh
# https://github.com/mstorsjo/msvc-wine/blob/master/vsdownload.py
# https://github.com/mozilla/gecko-dev/blob/6027d1d91f2d3204a3992633b3ef730ff005fc64/build/vs/vs2022-car.yaml
# function dl() {
# curl -O https://download.visualstudio.microsoft.com/download/pr/$1
# }
# [[.h]]
# "id": "Win11SDK_10.0.26100"
# "version": "10.0.26100.7"
# libucrt.lib
# example: <assert.h>
# dir: ucrt/
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/2ee3a5fc6e9fc832af7295b138e93839/universal%20crt%20headers%20libraries%20and%20sources-x86_en-us.msi
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/b1aa09b90fe314aceb090f6ec7626624/16ab2ea2187acffa6435e334796c8c89.cab
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/400609bb0ff5804e36dbe6dcd42a7f01/6ee7bbee8435130a869cf971694fd9e2.cab
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/2ac327317abb865a0e3f56b2faefa918/78fa3c824c2c48bd4a49ab5969adaaf7.cab
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/f034bc0b2680f67dccd4bfeea3d0f932/7afc7b670accd8e3cc94cfffd516f5cb.cab
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/7ed5e12f9d50f80825a8b27838cf4c7f/96076045170fe5db6d5dcf14b6f6688e.cab
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/764edc185a696bda9e07df8891dddbbb/a1e2a83aa8a71c48c742eeaff6e71928.cab
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/66854bedc6dbd5ccb5dd82c8e2412231/b2f03f34ff83ec013b9e45c7cd8e8a73.cab
# example: <windows.h>
# dir: um/
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/b286efac4d83a54fc49190bddef1edc9/windows%20sdk%20for%20windows%20store%20apps%20headers-x86_en-us.msi
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/e0dc3811d92ab96fcb72bf63d6c08d71/766c0ffd568bbb31bf7fb6793383e24a.cab
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/613503da4b5628768497822826aed39f/8125ee239710f33ea485965f76fae646.cab
# example: <winapifamily.h>
# dir: /shared
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/122979f0348d3a2a36b6aa1a111d5d0c/windows%20sdk%20for%20windows%20store%20apps%20headers%20onecoreuap-x86_en-us.msi
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/766e04beecdfccff39e91dd9eb32834a/e89e3dcbb016928c7e426238337d69eb.cab
# "id": "Microsoft.VisualC.14.16.CRT.Headers"
# "version": "14.16.27045"
# example: <vcruntime.h>
# dir: MSVC/
curl -O https://download.visualstudio.microsoft.com/download/pr/bac0afd7-cc9e-4182-8a83-9898fa20e092/87bbe41e09a2f83711e72696f49681429327eb7a4b90618c35667a6ba2e2880e/Microsoft.VisualC.14.16.CRT.Headers.vsix
# [[.lib]]
# advapi32.lib bcrypt.lib kernel32.lib ntdll.lib user32.lib uuid.lib ws2_32.lib userenv.lib cfgmgr32.lib
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/944c4153b849a1f7d0c0404a4f1c05ea/windows%20sdk%20for%20windows%20store%20apps%20libs-x86_en-us.msi
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/5306aed3e1a38d1e8bef5934edeb2a9b/05047a45609f311645eebcac2739fc4c.cab
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/13c8a73a0f5a6474040b26d016a26fab/13d68b8a7b6678a368e2d13ff4027521.cab
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/149578fb3b621cdb61ee1813b9b3e791/463ad1b0783ebda908fd6c16a4abfe93.cab
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/5c986c4f393c6b09d5aec3b539e9fb4a/5a22e5cde814b041749fb271547f4dd5.cab
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/bfc3904a0195453419ae4dfea7abd6fb/e10768bb6e9d0ea730280336b697da66.cab
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/637f9f3be880c71f9e3ca07b4d67345c/f9b24c8280986c0683fbceca5326d806.cab
# dbghelp.lib fwpuclnt.lib
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/9f51690d5aa804b1340ce12d1ec80f89/windows%20sdk%20desktop%20libs%20x64-x86_en-us.msi
curl -O https://download.visualstudio.microsoft.com/download/pr/32863b8d-a46d-4231-8e84-0888519d20a9/d3a7df4ca3303a698640a29e558a5e5b/58314d0646d7e1a25e97c902166c3155.cab
# libcmt.lib libvcruntime.lib
curl -O https://download.visualstudio.microsoft.com/download/pr/bac0afd7-cc9e-4182-8a83-9898fa20e092/8728f21ae09940f1f4b4ee47b4a596be2509e2a47d2f0c83bbec0ea37d69644b/Microsoft.VisualC.14.16.CRT.x64.Desktop.vsix
msiextract universal%20crt%20headers%20libraries%20and%20sources-x86_en-us.msi
msiextract windows%20sdk%20for%20windows%20store%20apps%20headers-x86_en-us.msi
msiextract windows%20sdk%20for%20windows%20store%20apps%20headers%20onecoreuap-x86_en-us.msi
msiextract windows%20sdk%20for%20windows%20store%20apps%20libs-x86_en-us.msi
msiextract windows%20sdk%20desktop%20libs%20x64-x86_en-us.msi
unzip -o Microsoft.VisualC.14.16.CRT.Headers.vsix
unzip -o Microsoft.VisualC.14.16.CRT.x64.Desktop.vsix
mkdir -p /usr/x86_64-pc-windows-msvc/usr/include
mkdir -p /usr/x86_64-pc-windows-msvc/usr/lib
# lowercase folder/file names
echo "$(find . -regex ".*/[^/]*[A-Z][^/]*")" | xargs -I{} sh -c 'mv "$(echo "{}" | sed -E '"'"'s/(.*\/)/\L\1/'"'"')" "$(echo "{}" | tr [A-Z] [a-z])"'
# .h
(cd 'program files/windows kits/10/include/10.0.26100.0' && cp -r ucrt/* um/* shared/* -t /usr/x86_64-pc-windows-msvc/usr/include)
cp -r contents/vc/tools/msvc/14.16.27023/include/* /usr/x86_64-pc-windows-msvc/usr/include
# lowercase #include "" and #include <>
find /usr/x86_64-pc-windows-msvc/usr/include -type f -exec sed -i -E 's/(#include <[^<>]*?[A-Z][^<>]*?>)|(#include "[^"]*?[A-Z][^"]*?")/\L\1\2/' "{}" ';'
# x86 intrinsics
# original dir: MSVC/
# '_mm_movemask_epi8' defined in emmintrin.h
# '__v4sf' defined in xmmintrin.h
# '__v2si' defined in mmintrin.h
# '__m128d' redefined in immintrin.h
# '__m128i' redefined in intrin.h
# '_mm_comlt_epu8' defined in ammintrin.h
(cd /usr/lib/llvm19/lib/clang/19/include && cp emmintrin.h xmmintrin.h mmintrin.h immintrin.h intrin.h ammintrin.h -t /usr/x86_64-pc-windows-msvc/usr/include)
# .lib
(cd 'program files/windows kits/10/lib/10.0.26100.0/um/x64' && cp advapi32.lib bcrypt.lib kernel32.lib ntdll.lib user32.lib uuid.lib ws2_32.lib userenv.lib cfgmgr32.lib dbghelp.lib fwpuclnt.lib -t /usr/x86_64-pc-windows-msvc/usr/lib)
(cd 'contents/vc/tools/msvc/14.16.27023/lib/x64' && cp libcmt.lib libvcruntime.lib -t /usr/x86_64-pc-windows-msvc/usr/lib)
cp 'program files/windows kits/10/lib/10.0.26100.0/ucrt/x64/libucrt.lib' /usr/x86_64-pc-windows-msvc/usr/lib

View File

@@ -55,9 +55,6 @@ plugins:
show_signature_annotations: true
show_root_heading: true
members_order: source
docstring_section_style: list
signature_crossrefs: true
separate_signature: true
import:
# for cross references
- https://arrow.apache.org/docs/objects.inv
@@ -93,9 +90,6 @@ markdown_extensions:
- pymdownx.emoji:
emoji_index: !!python/name:material.extensions.emoji.twemoji
emoji_generator: !!python/name:material.extensions.emoji.to_svg
- markdown.extensions.toc:
baselevel: 1
permalink: ""
nav:
- Home:
@@ -103,7 +97,7 @@ nav:
- 🏃🏼‍♂️ Quick start: basic.md
- 📚 Concepts:
- Vector search: concepts/vector_search.md
- Indexing:
- Indexing:
- IVFPQ: concepts/index_ivfpq.md
- HNSW: concepts/index_hnsw.md
- Storage: concepts/storage.md
@@ -112,8 +106,7 @@ nav:
- Working with tables: guides/tables.md
- Building a vector index: ann_indexes.md
- Vector Search: search.md
- Full-text search (native): fts.md
- Full-text search (tantivy-based): fts_tantivy.md
- Full-text search: fts.md
- Building a scalar index: guides/scalar_index.md
- Hybrid search:
- Overview: hybrid_search/hybrid_search.md
@@ -141,7 +134,6 @@ nav:
- Jina Reranker: reranking/jina.md
- OpenAI Reranker: reranking/openai.md
- AnswerDotAi Rerankers: reranking/answerdotai.md
- Voyage AI Rerankers: reranking/voyageai.md
- Building Custom Rerankers: reranking/custom_reranker.md
- Example: notebooks/lancedb_reranking.ipynb
- Filtering: sql.md
@@ -153,10 +145,10 @@ nav:
- Reranking: guides/tuning_retrievers/2_reranking.md
- Embedding fine-tuning: guides/tuning_retrievers/3_embed_tuning.md
- 🧬 Managing embeddings:
- Understand Embeddings: embeddings/understanding_embeddings.md
- Understand Embeddings: embeddings/understanding_embeddings.md
- Get Started: embeddings/index.md
- Embedding functions: embeddings/embedding_functions.md
- Available models:
- Available models:
- Overview: embeddings/default_embedding_functions.md
- Text Embedding Functions:
- Sentence Transformers: embeddings/available_embedding_models/text_embedding_functions/sentence_transformers.md
@@ -169,7 +161,6 @@ nav:
- Jina Embeddings: embeddings/available_embedding_models/text_embedding_functions/jina_embedding.md
- AWS Bedrock Text Embedding Functions: embeddings/available_embedding_models/text_embedding_functions/aws_bedrock_embedding.md
- IBM watsonx.ai Embeddings: embeddings/available_embedding_models/text_embedding_functions/ibm_watsonx_ai_embedding.md
- Voyage AI Embeddings: embeddings/available_embedding_models/text_embedding_functions/voyageai_embedding.md
- Multimodal Embedding Functions:
- OpenClip embeddings: embeddings/available_embedding_models/multimodal_embedding_functions/openclip_embedding.md
- Imagebind embeddings: embeddings/available_embedding_models/multimodal_embedding_functions/imagebind_embedding.md
@@ -206,7 +197,7 @@ nav:
- Evaluation: examples/python_examples/evaluations.md
- AI Agent: examples/python_examples/aiagent.md
- Recommender System: examples/python_examples/recommendersystem.md
- Miscellaneous:
- Miscellaneous:
- Serverless QA Bot with S3 and Lambda: examples/serverless_lancedb_with_s3_and_lambda.md
- Serverless QA Bot with Modal: examples/serverless_qa_bot_with_modal_and_langchain.md
- 👾 JavaScript:
@@ -216,10 +207,9 @@ nav:
- TransformersJS Embedding Search: examples/transformerjs_embedding_search_nodejs.md
- 🦀 Rust:
- Overview: examples/examples_rust.md
- 📓 Studies:
- Studies:
- ↗Improve retrievers with hybrid search and reranking: https://blog.lancedb.com/hybrid-search-and-reranking-report/
- 💭 FAQs: faq.md
- 🔍 Troubleshooting: troubleshooting.md
- ⚙️ API reference:
- 🐍 Python: python/python.md
- 👾 JavaScript (vectordb): javascript/modules.md
@@ -235,7 +225,7 @@ nav:
- Quick start: basic.md
- Concepts:
- Vector search: concepts/vector_search.md
- Indexing:
- Indexing:
- IVFPQ: concepts/index_ivfpq.md
- HNSW: concepts/index_hnsw.md
- Storage: concepts/storage.md
@@ -244,8 +234,7 @@ nav:
- Working with tables: guides/tables.md
- Building an ANN index: ann_indexes.md
- Vector Search: search.md
- Full-text search (native): fts.md
- Full-text search (tantivy-based): fts_tantivy.md
- Full-text search: fts.md
- Building a scalar index: guides/scalar_index.md
- Hybrid search:
- Overview: hybrid_search/hybrid_search.md
@@ -284,10 +273,10 @@ nav:
- Reranking: guides/tuning_retrievers/2_reranking.md
- Embedding fine-tuning: guides/tuning_retrievers/3_embed_tuning.md
- Managing Embeddings:
- Understand Embeddings: embeddings/understanding_embeddings.md
- Understand Embeddings: embeddings/understanding_embeddings.md
- Get Started: embeddings/index.md
- Embedding functions: embeddings/embedding_functions.md
- Available models:
- Available models:
- Overview: embeddings/default_embedding_functions.md
- Text Embedding Functions:
- Sentence Transformers: embeddings/available_embedding_models/text_embedding_functions/sentence_transformers.md
@@ -332,7 +321,7 @@ nav:
- Evaluation: examples/python_examples/evaluations.md
- AI Agent: examples/python_examples/aiagent.md
- Recommender System: examples/python_examples/recommendersystem.md
- Miscellaneous:
- Miscellaneous:
- Serverless QA Bot with S3 and Lambda: examples/serverless_lancedb_with_s3_and_lambda.md
- Serverless QA Bot with Modal: examples/serverless_qa_bot_with_modal_and_langchain.md
- 👾 JavaScript:
@@ -375,4 +364,5 @@ extra:
- icon: fontawesome/brands/x-twitter
link: https://twitter.com/lancedb
- icon: fontawesome/brands/linkedin
link: https://www.linkedin.com/company/lancedb
link: https://www.linkedin.com/company/lancedb

21
docs/package-lock.json generated
View File

@@ -19,7 +19,7 @@
},
"../node": {
"name": "vectordb",
"version": "0.12.0",
"version": "0.4.6",
"cpu": [
"x64",
"arm64"
@@ -31,7 +31,9 @@
"win32"
],
"dependencies": {
"@apache-arrow/ts": "^14.0.2",
"@neon-rs/load": "^0.0.74",
"apache-arrow": "^14.0.2",
"axios": "^1.4.0"
},
"devDependencies": {
@@ -44,7 +46,6 @@
"@types/temp": "^0.9.1",
"@types/uuid": "^9.0.3",
"@typescript-eslint/eslint-plugin": "^5.59.1",
"apache-arrow-old": "npm:apache-arrow@13.0.0",
"cargo-cp-artifact": "^0.1",
"chai": "^4.3.7",
"chai-as-promised": "^7.1.1",
@@ -61,19 +62,15 @@
"ts-node-dev": "^2.0.0",
"typedoc": "^0.24.7",
"typedoc-plugin-markdown": "^3.15.3",
"typescript": "^5.1.0",
"typescript": "*",
"uuid": "^9.0.0"
},
"optionalDependencies": {
"@lancedb/vectordb-darwin-arm64": "0.12.0",
"@lancedb/vectordb-darwin-x64": "0.12.0",
"@lancedb/vectordb-linux-arm64-gnu": "0.12.0",
"@lancedb/vectordb-linux-x64-gnu": "0.12.0",
"@lancedb/vectordb-win32-x64-msvc": "0.12.0"
},
"peerDependencies": {
"@apache-arrow/ts": "^14.0.2",
"apache-arrow": "^14.0.2"
"@lancedb/vectordb-darwin-arm64": "0.4.6",
"@lancedb/vectordb-darwin-x64": "0.4.6",
"@lancedb/vectordb-linux-arm64-gnu": "0.4.6",
"@lancedb/vectordb-linux-x64-gnu": "0.4.6",
"@lancedb/vectordb-win32-x64-msvc": "0.4.6"
}
},
"../node/node_modules/apache-arrow": {

View File

@@ -45,9 +45,9 @@ Lance supports `IVF_PQ` index type by default.
Creating indexes is done via the [lancedb.Table.createIndex](../js/classes/Table.md/#createIndex) method.
```typescript
--8<--- "nodejs/examples/ann_indexes.test.ts:import"
--8<--- "nodejs/examples/ann_indexes.ts:import"
--8<-- "nodejs/examples/ann_indexes.test.ts:ingest"
--8<-- "nodejs/examples/ann_indexes.ts:ingest"
```
=== "vectordb (deprecated)"
@@ -83,7 +83,6 @@ The following IVF_PQ paramters can be specified:
- **num_sub_vectors**: The number of sub-vectors (M) that will be created during Product Quantization (PQ).
For D dimensional vector, it will be divided into `M` subvectors with dimension `D/M`, each of which is replaced by
a single PQ code. The default is the dimension of the vector divided by 16.
- **num_bits**: The number of bits used to encode each sub-vector. Only 4 and 8 are supported. The higher the number of bits, the higher the accuracy of the index, also the slower search. The default is 8.
!!! note
@@ -141,15 +140,13 @@ There are a couple of parameters that can be used to fine-tune the search:
- **limit** (default: 10): The amount of results that will be returned
- **nprobes** (default: 20): The number of probes used. A higher number makes search more accurate but also slower.<br/>
Most of the time, setting nprobes to cover 5-15% of the dataset should achieve high recall with low latency.<br/>
- _For example_, For a dataset of 1 million vectors divided into 256 partitions, `nprobes` should be set to ~20-40. This value can be adjusted to achieve the optimal balance between search latency and search quality. <br/>
Most of the time, setting nprobes to cover 5-10% of the dataset should achieve high recall with low latency.<br/>
e.g., for 1M vectors divided up into 256 partitions, nprobes should be set to ~20-40.<br/>
Note: nprobes is only applicable if an ANN index is present. If specified on a table without an ANN index, it is ignored.
- **refine_factor** (default: None): Refine the results by reading extra elements and re-ranking them in memory.<br/>
A higher number makes search more accurate but also slower. If you find the recall is less than ideal, try refine_factor=10 to start.<br/>
- _For example_, For a dataset of 1 million vectors divided into 256 partitions, setting the `refine_factor` to 200 will initially retrieve the top 4,000 candidates (top k * refine_factor) from all searched partitions. These candidates are then reranked to determine the final top 20 results.<br/>
!!! note
Both `nprobes` and `refine_factor` are only applicable if an ANN index is present. If specified on a table without an ANN index, those parameters are ignored.
e.g., for 1M vectors divided into 256 partitions, if you're looking for top 20, then refine_factor=200 reranks the whole partition.<br/>
Note: refine_factor is only applicable if an ANN index is present. If specified on a table without an ANN index, it is ignored.
=== "Python"
@@ -172,7 +169,7 @@ There are a couple of parameters that can be used to fine-tune the search:
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/ann_indexes.test.ts:search1"
--8<-- "nodejs/examples/ann_indexes.ts:search1"
```
=== "vectordb (deprecated)"
@@ -206,7 +203,7 @@ You can further filter the elements returned by a search using a where clause.
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/ann_indexes.test.ts:search2"
--8<-- "nodejs/examples/ann_indexes.ts:search2"
```
=== "vectordb (deprecated)"
@@ -238,7 +235,7 @@ You can select the columns returned by the query using a select clause.
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/ann_indexes.test.ts:search3"
--8<-- "nodejs/examples/ann_indexes.ts:search3"
```
=== "vectordb (deprecated)"
@@ -278,15 +275,7 @@ Product quantization can lead to approximately `16 * sizeof(float32) / 1 = 64` t
Higher number of partitions could lead to more efficient I/O during queries and better accuracy, but it takes much more time to train.
On `SIFT-1M` dataset, our benchmark shows that keeping each partition 1K-4K rows lead to a good latency / recall.
`num_sub_vectors` specifies how many Product Quantization (PQ) short codes to generate on each vector. The number should be a factor of the vector dimension. Because
`num_sub_vectors` specifies how many Product Quantization (PQ) short codes to generate on each vector. Because
PQ is a lossy compression of the original vector, a higher `num_sub_vectors` usually results in
less space distortion, and thus yields better accuracy. However, a higher `num_sub_vectors` also causes heavier I/O and more PQ computation, and thus, higher latency. `dimension / num_sub_vectors` should be a multiple of 8 for optimum SIMD efficiency.
!!! note
if `num_sub_vectors` is set to be greater than the vector dimension, you will see errors like `attempt to divide by zero`
### How to choose `m` and `ef_construction` for `IVF_HNSW_*` index?
`m` determines the number of connections a new node establishes with its closest neighbors upon entering the graph. Typically, `m` falls within the range of 5 to 48. Lower `m` values are suitable for low-dimensional data or scenarios where recall is less critical. Conversely, higher `m` values are beneficial for high-dimensional data or when high recall is required. In essence, a larger `m` results in a denser graph with increased connectivity, but at the expense of higher memory consumption.
`ef_construction` balances build speed and accuracy. Higher values increase accuracy but slow down the build process. A typical range is 150 to 300. For good search results, a minimum value of 100 is recommended. In most cases, setting this value above 500 offers no additional benefit. Ensure that `ef_construction` is always set to a value equal to or greater than `ef` in the search phase
less space distortion, and thus yields better accuracy. However, a higher `num_sub_vectors` also causes heavier I/O and
more PQ computation, and thus, higher latency. `dimension / num_sub_vectors` should be a multiple of 8 for optimum SIMD efficiency.

View File

@@ -157,7 +157,7 @@ recommend switching to stable releases.
import * as lancedb from "@lancedb/lancedb";
import * as arrow from "apache-arrow";
--8<-- "nodejs/examples/basic.test.ts:connect"
--8<-- "nodejs/examples/basic.ts:connect"
```
=== "vectordb (deprecated)"
@@ -212,7 +212,7 @@ table.
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/basic.test.ts:create_table"
--8<-- "nodejs/examples/basic.ts:create_table"
```
=== "vectordb (deprecated)"
@@ -268,7 +268,7 @@ similar to a `CREATE TABLE` statement in SQL.
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/basic.test.ts:create_empty_table"
--8<-- "nodejs/examples/basic.ts:create_empty_table"
```
=== "vectordb (deprecated)"
@@ -298,7 +298,7 @@ Once created, you can open a table as follows:
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/basic.test.ts:open_table"
--8<-- "nodejs/examples/basic.ts:open_table"
```
=== "vectordb (deprecated)"
@@ -327,7 +327,7 @@ If you forget the name of your table, you can always get a listing of all table
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/basic.test.ts:table_names"
--8<-- "nodejs/examples/basic.ts:table_names"
```
=== "vectordb (deprecated)"
@@ -357,7 +357,7 @@ After a table has been created, you can always add more data to it as follows:
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/basic.test.ts:add_data"
--8<-- "nodejs/examples/basic.ts:add_data"
```
=== "vectordb (deprecated)"
@@ -389,7 +389,7 @@ Once you've embedded the query, you can find its nearest neighbors as follows:
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/basic.test.ts:vector_search"
--8<-- "nodejs/examples/basic.ts:vector_search"
```
=== "vectordb (deprecated)"
@@ -429,7 +429,7 @@ LanceDB allows you to create an ANN index on a table as follows:
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/basic.test.ts:create_index"
--8<-- "nodejs/examples/basic.ts:create_index"
```
=== "vectordb (deprecated)"
@@ -469,7 +469,7 @@ This can delete any number of rows that match the filter.
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/basic.test.ts:delete_rows"
--8<-- "nodejs/examples/basic.ts:delete_rows"
```
=== "vectordb (deprecated)"
@@ -527,7 +527,7 @@ Use the `drop_table()` method on the database to remove a table.
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/basic.test.ts:drop_table"
--8<-- "nodejs/examples/basic.ts:drop_table"
```
=== "vectordb (deprecated)"
@@ -561,8 +561,8 @@ You can use the embedding API when working with embedding models. It automatical
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/embedding.test.ts:imports"
--8<-- "nodejs/examples/embedding.test.ts:openai_embeddings"
--8<-- "nodejs/examples/embedding.ts:imports"
--8<-- "nodejs/examples/embedding.ts:openai_embeddings"
```
=== "Rust"

View File

@@ -57,13 +57,6 @@ Then the greedy search routine operates as follows:
## Usage
There are three key parameters to set when constructing an HNSW index:
* `metric`: Use an `L2` euclidean distance metric. We also support `dot` and `cosine` distance.
* `m`: The number of neighbors to select for each vector in the HNSW graph.
* `ef_construction`: The number of candidates to evaluate during the construction of the HNSW graph.
We can combine the above concepts to understand how to build and query an HNSW index in LanceDB.
### Construct index

View File

@@ -58,10 +58,8 @@ In Python, the index can be created as follows:
# Make sure you have enough data in the table for an effective training step
tbl.create_index(metric="L2", num_partitions=256, num_sub_vectors=96)
```
!!! note
`num_partitions`=256 and `num_sub_vectors`=96 does not work for every dataset. Those values needs to be adjusted for your particular dataset.
The `num_partitions` is usually chosen to target a particular number of vectors per partition. `num_sub_vectors` is typically chosen based on the desired recall and the dimensionality of the vector. See [here](../ann_indexes.md/#how-to-choose-num_partitions-and-num_sub_vectors-for-ivf_pq-index) for best practices on choosing these parameters.
The `num_partitions` is usually chosen to target a particular number of vectors per partition. `num_sub_vectors` is typically chosen based on the desired recall and the dimensionality of the vector. See the [FAQs](#faq) below for best practices on choosing these parameters.
### Query the index

View File

@@ -6,7 +6,6 @@ LanceDB registers the OpenAI embeddings function in the registry by default, as
|---|---|---|---|
| `name` | `str` | `"text-embedding-ada-002"` | The name of the model. |
| `dim` | `int` | Model default | For OpenAI's newer text-embedding-3 model, we can specify a dimensionality that is smaller than the 1536 size. This feature supports it |
| `use_azure` | bool | `False` | Set true to use Azure OpenAPI SDK |
```python

View File

@@ -1,51 +0,0 @@
# VoyageAI Embeddings
Voyage AI provides cutting-edge embedding and rerankers.
Using voyageai API requires voyageai package, which can be installed using `pip install voyageai`. Voyage AI 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 `VOYAGE_API_KEY` environment variable to use the VoyageAI API.
Supported models are:
- voyage-3
- voyage-3-lite
- voyage-finance-2
- voyage-multilingual-2
- voyage-law-2
- voyage-code-2
Supported parameters (to be passed in `create` method) are:
| Parameter | Type | Default Value | Description |
|---|---|--------|---------|
| `name` | `str` | `None` | The model ID of the model to use. Supported base models for Text Embeddings: voyage-3, voyage-3-lite, voyage-finance-2, voyage-multilingual-2, voyage-law-2, voyage-code-2 |
| `input_type` | `str` | `None` | Type of the input text. Default to None. Other options: query, document. |
| `truncation` | `bool` | `True` | Whether to truncate the input texts to fit within the context length. |
Usage Example:
```python
import lancedb
from lancedb.pydantic import LanceModel, Vector
from lancedb.embeddings import EmbeddingFunctionRegistry
voyageai = EmbeddingFunctionRegistry
.get_instance()
.get("voyageai")
.create(name="voyage-3")
class TextModel(LanceModel):
text: str = voyageai.SourceField()
vector: Vector(voyageai.ndims()) = voyageai.VectorField()
data = [ { "text": "hello world" },
{ "text": "goodbye world" }]
db = lancedb.connect("~/.lancedb")
tbl = db.create_table("test", schema=TextModel, mode="overwrite")
tbl.add(data)
```

View File

@@ -47,9 +47,9 @@ Let's implement `SentenceTransformerEmbeddings` class. All you need to do is imp
=== "TypeScript"
```ts
--8<--- "nodejs/examples/custom_embedding_function.test.ts:imports"
--8<--- "nodejs/examples/custom_embedding_function.ts:imports"
--8<--- "nodejs/examples/custom_embedding_function.test.ts:embedding_impl"
--8<--- "nodejs/examples/custom_embedding_function.ts:embedding_impl"
```
@@ -78,7 +78,7 @@ Now you can use this embedding function to create your table schema and that's i
=== "TypeScript"
```ts
--8<--- "nodejs/examples/custom_embedding_function.test.ts:call_custom_function"
--8<--- "nodejs/examples/custom_embedding_function.ts:call_custom_function"
```
!!! note

View File

@@ -53,7 +53,6 @@ These functions are registered by default to handle text embeddings.
| [**Jina Embeddings**](available_embedding_models/text_embedding_functions/jina_embedding.md "jina") | 🔗 World-class embedding models to improve your search and RAG systems. You will need **jina api key**. | [<img src="https://raw.githubusercontent.com/lancedb/assets/main/docs/assets/logos/jina.png" alt="Jina Icon" width="90" height="35">](available_embedding_models/text_embedding_functions/jina_embedding.md) |
| [ **AWS Bedrock Functions**](available_embedding_models/text_embedding_functions/aws_bedrock_embedding.md "bedrock-text") | ☁️ AWS Bedrock supports multiple base models for generating text embeddings. You need to setup the AWS credentials to use this embedding function. | [<img src="https://raw.githubusercontent.com/lancedb/assets/main/docs/assets/logos/aws_bedrock.png" alt="AWS Bedrock Icon" width="120" height="35">](available_embedding_models/text_embedding_functions/aws_bedrock_embedding.md) |
| [**IBM Watsonx.ai**](available_embedding_models/text_embedding_functions/ibm_watsonx_ai_embedding.md "watsonx") | 💡 Generate text embeddings using IBM's watsonx.ai platform. **Note**: watsonx.ai library is an optional dependency. | [<img src="https://raw.githubusercontent.com/lancedb/assets/main/docs/assets/logos/watsonx.png" alt="Watsonx Icon" width="140" height="35">](available_embedding_models/text_embedding_functions/ibm_watsonx_ai_embedding.md) |
| [**VoyageAI Embeddings**](available_embedding_models/text_embedding_functions/voyageai_embedding.md "voyageai") | 🌕 Voyage AI provides cutting-edge embedding and rerankers. This will help you get started with **VoyageAI** embedding models using LanceDB. Using voyageai API requires voyageai package. Install it via `pip`. | [<img src="https://www.voyageai.com/logo.svg" alt="VoyageAI Icon" width="140" height="35">](available_embedding_models/text_embedding_functions/voyageai_embedding.md) |
@@ -67,7 +66,6 @@ These functions are registered by default to handle text embeddings.
[jina-key]: "jina"
[aws-key]: "bedrock-text"
[watsonx-key]: "watsonx"
[voyageai-key]: "voyageai"
## Multi-modal Embedding Functions🖼

View File

@@ -94,8 +94,8 @@ the embeddings at all:
=== "@lancedb/lancedb"
```ts
--8<-- "nodejs/examples/embedding.test.ts:imports"
--8<-- "nodejs/examples/embedding.test.ts:embedding_function"
--8<-- "nodejs/examples/embedding.ts:imports"
--8<-- "nodejs/examples/embedding.ts:embedding_function"
```
=== "vectordb (deprecated)"
@@ -150,7 +150,7 @@ need to worry about it when you query the table:
.toArray()
```
=== "vectordb (deprecated)"
=== "vectordb (deprecated)
```ts
const results = await table

View File

@@ -51,8 +51,8 @@ LanceDB registers the OpenAI embeddings function in the registry as `openai`. Yo
=== "TypeScript"
```typescript
--8<--- "nodejs/examples/embedding.test.ts:imports"
--8<--- "nodejs/examples/embedding.test.ts:openai_embeddings"
--8<--- "nodejs/examples/embedding.ts:imports"
--8<--- "nodejs/examples/embedding.ts:openai_embeddings"
```
=== "Rust"
@@ -121,10 +121,12 @@ class Words(LanceModel):
vector: Vector(func.ndims()) = func.VectorField()
table = db.create_table("words", schema=Words)
table.add([
{"text": "hello world"},
{"text": "goodbye world"}
])
table.add(
[
{"text": "hello world"},
{"text": "goodbye world"}
]
)
query = "greetings"
actual = table.search(query).limit(1).to_pydantic(Words)[0]

View File

@@ -36,6 +36,6 @@
[aware_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/tutorials/chatbot_using_Llama2_&_lanceDB/main.ipynb
[aware_ghost]: https://blog.lancedb.com/context-aware-chatbot-using-llama-2-lancedb-as-vector-database-4d771d95c755
[csv_github]: https://github.com/lancedb/vectordb-recipes/tree/main/examples/archived_examples/Chat_with_csv_file
[csv_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/archived_examples/Chat_with_csv_file/main.ipynb
[csv_github]: https://github.com/lancedb/vectordb-recipes/blob/main/tutorials/Chat_with_csv_file
[csv_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/tutorials/Chat_with_csv_file/main.ipynb
[csv_ghost]: https://blog.lancedb.com/p/d8c71df4-e55f-479a-819e-cde13354a6a3/

View File

@@ -12,7 +12,7 @@ LanceDB supports multimodal search by indexing and querying vector representatio
|:----------------|:-----------------|:-----------|
| **Multimodal CLIP: DiffusionDB 🌐💥** | Multi-Modal Search with **CLIP** and **LanceDB** Using **DiffusionDB** Data for Combined Text and Image Understanding ! 🔓 | [![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 📸🔍** | Find **relevant documents** and **images** with a single query using **LanceDB's** multimodal search capabilities, to seamlessly integrate text and visuals ! 🌉 | [![GitHub](../../assets/github.svg)](https://github.com/lancedb/vectordb-recipes/tree/main/examples/archived_examples/multimodal_search) <br>[![Open In Collab](../../assets/colab.svg)](https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/archived_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/) |
| **Multimodal Image + Text Search 📸🔍** | Find **relevant documents** and **images** with a single query using **LanceDB's** multimodal search capabilities, to seamlessly integrate 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 🔍👀** | Learn how **Cambrian-1** works, using an example of **Vision-Centric** exploration on images found through vector search ! Work on **Flickr-8k** dataset 🔎 | [![Kaggle](https://img.shields.io/badge/Kaggle-035a7d?style=for-the-badge&logo=kaggle&logoColor=white)](https://www.kaggle.com/code/prasantdixit/cambrian-1-vision-centric-exploration-of-images/)<br> [![Ghost](../../assets/ghost.svg)](https://blog.lancedb.com/cambrian-1-vision-centric-exploration/) |

View File

@@ -70,12 +70,12 @@ Build RAG (Retrieval-Augmented Generation) with LanceDB, a powerful solution fo
[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/tree/main/examples/archived_examples/QueryExpansion%26Reranker
[query_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/archived_examples/QueryExpansion&Reranker/main.ipynb
[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/tree/main/examples/archived_examples/RAG_Fusion
[fusion_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/archived_examples/RAG_Fusion/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

View File

@@ -19,8 +19,8 @@ Deliver personalized experiences with Recommender Systems. 🎁
[movie_python]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/movie-recommender/main.py
[genre_github]: https://github.com/lancedb/vectordb-recipes/tree/main/examples/archived_examples/movie-recommendation-with-genres
[genre_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/archived_examples/movie-recommendation-with-genres/movie_recommendation_with_doc2vec_and_lancedb.ipynb
[genre_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/movie-recommendation-with-genres
[genre_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/movie-recommendation-with-genres/movie_recommendation_with_doc2vec_and_lancedb.ipynb
[genre_ghost]: https://blog.lancedb.com/movie-recommendation-system-using-lancedb-and-doc2vec/
[product_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/product-recommender
@@ -33,5 +33,5 @@ Deliver personalized experiences with Recommender Systems. 🎁
[arxiv_python]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/arxiv-recommender/main.py
[food_github]: https://github.com/lancedb/vectordb-recipes/tree/main/examples/archived_examples/Food_recommendation
[food_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/archived_examples/Food_recommendation/main.ipynb
[food_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/Food_recommendation
[food_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/Food_recommendation/main.ipynb

View File

@@ -37,16 +37,16 @@ LanceDB implements vector search algorithms for efficient document retrieval and
[NER_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/tutorials/NER-powered-Semantic-Search/NER_powered_Semantic_Search_with_LanceDB.ipynb
[NER_ghost]: https://blog.lancedb.com/ner-powered-semantic-search-using-lancedb-51051dc3e493
[audio_search_github]: https://github.com/lancedb/vectordb-recipes/tree/main/examples/archived_examples/audio_search
[audio_search_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/archived_examples/audio_search/main.ipynb
[audio_search_python]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/archived_examples/audio_search/main.py
[audio_search_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/audio_search
[audio_search_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/audio_search/main.ipynb
[audio_search_python]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/audio_search/main.py
[mls_github]: https://github.com/lancedb/vectordb-recipes/tree/main/examples/archived_examples/multi-lingual-wiki-qa
[mls_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/archived_examples/multi-lingual-wiki-qa/main.ipynb
[mls_python]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/archived_examples/multi-lingual-wiki-qa/main.py
[mls_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/multi-lingual-wiki-qa
[mls_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/multi-lingual-wiki-qa/main.ipynb
[mls_python]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/multi-lingual-wiki-qa/main.py
[fr_github]: https://github.com/lancedb/vectordb-recipes/tree/main/examples/archived_examples/facial_recognition
[fr_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/archived_examples/facial_recognition/main.ipynb
[fr_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/facial_recognition
[fr_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/facial_recognition/main.ipynb
[sentiment_analysis_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/Sentiment-Analysis-Analyse-Hotel-Reviews
[sentiment_analysis_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/Sentiment-Analysis-Analyse-Hotel-Reviews/Sentiment_Analysis_using_LanceDB.ipynb
@@ -70,8 +70,8 @@ LanceDB implements vector search algorithms for efficient document retrieval and
[openvino_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/Accelerate-Vector-Search-Applications-Using-OpenVINO/clip_text_image_search.ipynb
[openvino_ghost]: https://blog.lancedb.com/accelerate-vector-search-applications-using-openvino-lancedb/
[zsic_github]: https://github.com/lancedb/vectordb-recipes/tree/main/examples/archived_examples/zero-shot-image-classification
[zsic_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/archived_examples/zero-shot-image-classification/main.ipynb
[zsic_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/zero-shot-image-classification
[zsic_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/zero-shot-image-classification/main.ipynb
[zsic_ghost]: https://blog.lancedb.com/zero-shot-image-classification-with-vector-search/

View File

@@ -1,9 +1,21 @@
# Full-text search (Native FTS)
# Full-text search
LanceDB provides support for full-text search via Lance, allowing you to incorporate keyword-based search (based on BM25) in your retrieval solutions.
LanceDB provides support for full-text search via Lance (before via [Tantivy](https://github.com/quickwit-oss/tantivy) (Python only)), allowing you to incorporate keyword-based search (based on BM25) in your retrieval solutions.
Currently, the Lance full text search is missing some features that are in the Tantivy full text search. This includes query parser and customizing the tokenizer. Thus, in Python, Tantivy is still the default way to do full text search and many of the instructions below apply just to Tantivy-based indices.
## Installation (Only for Tantivy-based FTS)
!!! note
The Python SDK uses tantivy-based FTS by default, need to pass `use_tantivy=False` to use native FTS.
No need to install the tantivy dependency if using native FTS
To use full-text search, install the dependency [`tantivy-py`](https://github.com/quickwit-oss/tantivy-py):
```sh
# Say you want to use tantivy==0.20.1
pip install tantivy==0.20.1
```
## Example
@@ -27,7 +39,7 @@ Consider that we have a LanceDB table named `my_table`, whose string column `tex
# passing `use_tantivy=False` to use lance FTS index
# `use_tantivy=True` by default
table.create_fts_index("text", use_tantivy=False)
table.create_fts_index("text")
table.search("puppy").limit(10).select(["text"]).to_list()
# [{'text': 'Frodo was a happy puppy', '_score': 0.6931471824645996}]
# ...
@@ -81,78 +93,56 @@ Consider that we have a LanceDB table named `my_table`, whose string column `tex
```
It would search on all indexed columns by default, so it's useful when there are multiple indexed columns.
For now, this is supported in tantivy way only.
Passing `fts_columns="text"` if you want to specify the columns to search.
Passing `fts_columns="text"` if you want to specify the columns to search, but it's not available for Tantivy-based full text search.
!!! 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 would filter out words that are with length greater than 40, and lowercase all words.
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".
Stemming is useful for improving search results by reducing words to their root form, e.g. "running" to "run". LanceDB supports stemming for multiple languages, you can specify the tokenizer name to enable stemming by the pattern `tokenizer_name="{language_code}_stem"`, e.g. `en_stem` for English.
For now, only the Tantivy-based FTS index supports to specify the tokenizer, so it's only available in Python with `use_tantivy=True`.
For example, to enable stemming for English:
```python
table.create_fts_index("text", use_tantivy=True, tokenizer_name="en_stem")
```
=== "use_tantivy=True"
```python
table.create_fts_index("text", use_tantivy=True, tokenizer_name="en_stem")
```
=== "use_tantivy=False"
[**Not supported yet**](https://github.com/lancedb/lance/issues/1195)
the following [languages](https://docs.rs/tantivy/latest/tantivy/tokenizer/enum.Language.html) are currently supported.
The tokenizer is customizable, you can specify how the tokenizer splits the text, and how it filters out words, etc.
## Index multiple columns
For example, for language with accents, you can specify the tokenizer to use `ascii_folding` to remove accents, e.g. 'é' to 'e':
```python
table.create_fts_index("text",
use_tantivy=False,
language="French",
stem=True,
ascii_folding=True)
```
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`:
=== "use_tantivy=True"
```python
table.create_fts_index(["text1", "text2"])
```
=== "use_tantivy=False"
[**Not supported yet**](https://github.com/lancedb/lance/issues/1195)
Note that the search API call does not change - you can search over all indexed columns at once.
## Filtering
LanceDB full text search supports to filter the search results by a condition, both pre-filtering and post-filtering are supported.
Currently the LanceDB full text search feature supports *post-filtering*, meaning filters are
applied on top of the full text search results. This can be invoked via the familiar
`where` syntax:
This can be invoked via the familiar `where` syntax.
With pre-filtering:
=== "Python"
```python
table.search("puppy").limit(10).where("meta='foo'", prefilte=True).to_list()
```
=== "TypeScript"
```typescript
await tbl
.search("puppy")
.select(["id", "doc"])
.limit(10)
.where("meta='foo'")
.prefilter(true)
.toArray();
```
=== "Rust"
```rust
table
.query()
.full_text_search(FullTextSearchQuery::new("puppy".to_owned()))
.select(lancedb::query::Select::Columns(vec!["doc".to_owned()]))
.limit(10)
.only_if("meta='foo'")
.execute()
.await?;
```
With post-filtering:
=== "Python"
```python
table.search("puppy").limit(10).where("meta='foo'", prefilte=False).to_list()
table.search("puppy").limit(10).where("meta='foo'").to_list()
```
=== "TypeScript"
@@ -163,7 +153,6 @@ With post-filtering:
.select(["id", "doc"])
.limit(10)
.where("meta='foo'")
.prefilter(false)
.toArray();
```
@@ -174,56 +163,104 @@ With post-filtering:
.query()
.full_text_search(FullTextSearchQuery::new(words[0].to_owned()))
.select(lancedb::query::Select::Columns(vec!["doc".to_owned()]))
.postfilter()
.limit(10)
.only_if("meta='foo'")
.execute()
.await?;
```
## Sorting
!!! warning "Warn"
Sorting is available for only Tantivy-based FTS
You can pre-sort the documents by specifying `ordering_field_names` when
creating the full-text search index. Once pre-sorted, you can then specify
`ordering_field_name` while searching to return results sorted by the given
field. For example,
```python
table.create_fts_index(["text_field"], use_tantivy=True, ordering_field_names=["sort_by_field"])
(table.search("terms", ordering_field_name="sort_by_field")
.limit(20)
.to_list())
```
!!! note
If you wish to specify an ordering field at query time, you must also
have specified it during indexing time. Otherwise at query time, an
error will be raised that looks like `ValueError: The field does not exist: xxx`
!!! note
The fields to sort on must be of typed unsigned integer, or else you will see
an error during indexing that looks like
`TypeError: argument 'value': 'float' object cannot be interpreted as an integer`.
!!! note
You can specify multiple fields for ordering at indexing time.
But at query time only one ordering field is supported.
## Phrase queries vs. terms queries
!!! warning "Warn"
Lance-based FTS doesn't support queries using boolean operators `OR`, `AND`.
For full-text search you can specify either a **phrase** query like `"the old man and the sea"`,
or a **terms** search query like `old man sea`. For more details on the terms
or a **terms** search query like `"(Old AND Man) AND Sea"`. For more details on the terms
query syntax, see Tantivy's [query parser rules](https://docs.rs/tantivy/latest/tantivy/query/struct.QueryParser.html).
To search for a phrase, the index must be created with `with_position=True`:
!!! tip "Note"
The query parser will raise an exception on queries that are ambiguous. For example, in the query `they could have been dogs OR cats`, `OR` is capitalized so it's considered a keyword query operator. But it's ambiguous how the left part should be treated. So if you submit this search query as is, you'll get `Syntax Error: they could have been dogs OR cats`.
```py
# This raises a syntax error
table.search("they could have been dogs OR cats")
```
On the other hand, lowercasing `OR` to `or` will work, because there are no capitalized logical operators and
the query is treated as a phrase query.
```py
# This works!
table.search("they could have been dogs or cats")
```
It can be cumbersome to have to remember what will cause a syntax error depending on the type of
query you want to perform. To make this simpler, when you want to perform a phrase query, you can
enforce it in one of two ways:
1. Place the double-quoted query inside single quotes. For example, `table.search('"they could have been dogs OR cats"')` is treated as
a phrase query.
1. Explicitly declare the `phrase_query()` method. This is useful when you have a phrase query that
itself contains double quotes. For example, `table.search('the cats OR dogs were not really "pets" at all').phrase_query()`
is treated as a phrase query.
In general, a query that's declared as a phrase query will be wrapped in double quotes during parsing, with nested
double quotes replaced by single quotes.
## Configurations (Only for Tantivy-based FTS)
By default, LanceDB configures a 1GB heap size limit for creating the index. You can
reduce this if running on a smaller node, or increase this for faster performance while
indexing a larger corpus.
```python
table.create_fts_index("text", use_tantivy=False, with_position=True)
# configure a 512MB heap size
heap = 1024 * 1024 * 512
table.create_fts_index(["text1", "text2"], writer_heap_size=heap, replace=True)
```
This will allow you to search for phrases, but it will also significantly increase the index size and indexing time.
## Current limitations
## Incremental indexing
For that Tantivy-based FTS:
LanceDB supports incremental indexing, which means you can add new records to the table without reindexing the entire table.
1. Currently we do not yet support incremental writes.
If you add data after FTS index creation, it won't be reflected
in search results until you do a full reindex.
This can make the query more efficient, especially when the table is large and the new records are relatively small.
=== "Python"
```python
table.add([{"vector": [3.1, 4.1], "text": "Frodo was a happy puppy"}])
table.optimize()
```
=== "TypeScript"
```typescript
await tbl.add([{ vector: [3.1, 4.1], text: "Frodo was a happy puppy" }]);
await tbl.optimize();
```
=== "Rust"
```rust
let more_data: Box<dyn RecordBatchReader + Send> = create_some_records()?;
tbl.add(more_data).execute().await?;
tbl.optimize(OptimizeAction::All).execute().await?;
```
!!! note
New data added after creating the FTS index will appear in search results while incremental index is still progress, but with increased latency due to a flat search on the unindexed portion. LanceDB Cloud automates this merging process, minimizing the impact on search speed.
2. We currently only support local filesystem paths for the FTS index.
This is a tantivy limitation. We've implemented an object store plugin
but there's no way in tantivy-py to specify to use it.

View File

@@ -1,160 +0,0 @@
# Full-text search (Tantivy-based FTS)
LanceDB also provides support for full-text search via [Tantivy](https://github.com/quickwit-oss/tantivy), allowing you to incorporate keyword-based search (based on BM25) in your retrieval solutions.
The tantivy-based FTS is only available in Python and does not support building indexes on object storage or incremental indexing. If you need these features, try native FTS [native FTS](fts.md).
## Installation
To use full-text search, install the dependency [`tantivy-py`](https://github.com/quickwit-oss/tantivy-py):
```sh
# Say you want to use tantivy==0.20.1
pip install tantivy==0.20.1
```
## Example
Consider that we have a LanceDB table named `my_table`, whose string column `content` we want to index and query via keyword search, the FTS index must be created before you can search via keywords.
```python
import lancedb
uri = "data/sample-lancedb"
db = lancedb.connect(uri)
table = db.create_table(
"my_table",
data=[
{"id": 1, "vector": [3.1, 4.1], "title": "happy puppy", "content": "Frodo was a happy puppy", "meta": "foo"},
{"id": 2, "vector": [5.9, 26.5], "title": "playing kittens", "content": "There are several kittens playing around the puppy", "meta": "bar"},
],
)
# passing `use_tantivy=False` to use lance FTS index
# `use_tantivy=True` by default
table.create_fts_index("content", use_tantivy=True)
table.search("puppy").limit(10).select(["content"]).to_list()
# [{'text': 'Frodo was a happy puppy', '_score': 0.6931471824645996}]
# ...
```
It would search on all indexed columns by default, so it's useful when there are multiple indexed columns.
!!! 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("content", use_tantivy=True, tokenizer_name="en_stem", replace=True)
```
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`:
```python
table.create_fts_index(["title", "content"], use_tantivy=True, replace=True)
```
Note that the search API call does not change - you can search over all indexed columns at once.
## Filtering
Currently the LanceDB full text search feature supports *post-filtering*, meaning filters are
applied on top of the full text search results (see [native FTS](fts.md) if you need pre-filtering). This can be invoked via the familiar
`where` syntax:
```python
table.search("puppy").limit(10).where("meta='foo'").to_list()
```
## Sorting
You can pre-sort the documents by specifying `ordering_field_names` when
creating the full-text search index. Once pre-sorted, you can then specify
`ordering_field_name` while searching to return results sorted by the given
field. For example,
```python
table.create_fts_index(["content"], use_tantivy=True, ordering_field_names=["id"], replace=True)
(table.search("puppy", ordering_field_name="id")
.limit(20)
.to_list())
```
!!! note
If you wish to specify an ordering field at query time, you must also
have specified it during indexing time. Otherwise at query time, an
error will be raised that looks like `ValueError: The field does not exist: xxx`
!!! note
The fields to sort on must be of typed unsigned integer, or else you will see
an error during indexing that looks like
`TypeError: argument 'value': 'float' object cannot be interpreted as an integer`.
!!! note
You can specify multiple fields for ordering at indexing time.
But at query time only one ordering field is supported.
## Phrase queries vs. terms queries
For full-text search you can specify either a **phrase** query like `"the old man and the sea"`,
or a **terms** search query like `"(Old AND Man) AND Sea"`. For more details on the terms
query syntax, see Tantivy's [query parser rules](https://docs.rs/tantivy/latest/tantivy/query/struct.QueryParser.html).
!!! tip "Note"
The query parser will raise an exception on queries that are ambiguous. For example, in the query `they could have been dogs OR cats`, `OR` is capitalized so it's considered a keyword query operator. But it's ambiguous how the left part should be treated. So if you submit this search query as is, you'll get `Syntax Error: they could have been dogs OR cats`.
```py
# This raises a syntax error
table.search("they could have been dogs OR cats")
```
On the other hand, lowercasing `OR` to `or` will work, because there are no capitalized logical operators and
the query is treated as a phrase query.
```py
# This works!
table.search("they could have been dogs or cats")
```
It can be cumbersome to have to remember what will cause a syntax error depending on the type of
query you want to perform. To make this simpler, when you want to perform a phrase query, you can
enforce it in one of two ways:
1. Place the double-quoted query inside single quotes. For example, `table.search('"they could have been dogs OR cats"')` is treated as
a phrase query.
1. Explicitly declare the `phrase_query()` method. This is useful when you have a phrase query that
itself contains double quotes. For example, `table.search('the cats OR dogs were not really "pets" at all').phrase_query()`
is treated as a phrase query.
In general, a query that's declared as a phrase query will be wrapped in double quotes during parsing, with nested
double quotes replaced by single quotes.
## Configurations
By default, LanceDB configures a 1GB heap size limit for creating the index. You can
reduce this if running on a smaller node, or increase this for faster performance while
indexing a larger corpus.
```python
# configure a 512MB heap size
heap = 1024 * 1024 * 512
table.create_fts_index(["title", "content"], use_tantivy=True, writer_heap_size=heap, replace=True)
```
## Current limitations
1. New data added after creating the FTS index will appear in search results, but with increased latency due to a flat search on the unindexed portion. Re-indexing with `create_fts_index` will reduce latency. LanceDB Cloud automates this merging process, minimizing the impact on search speed.
2. We currently only support local filesystem paths for the FTS index.
This is a tantivy limitation. We've implemented an object store plugin
but there's no way in tantivy-py to specify to use it.

View File

@@ -1,35 +1,23 @@
# Building a Scalar Index
# Building Scalar Index
Scalar indices organize data by scalar attributes (e.g. numbers, categorical values), enabling fast filtering of vector data. In vector databases, scalar indices accelerate the retrieval of scalar data associated with vectors, thus enhancing the query performance when searching for vectors that meet certain scalar criteria.
Similar to many SQL databases, LanceDB supports several types of scalar indices to accelerate search
Similar to many SQL databases, LanceDB supports several types of Scalar indices to accelerate search
over scalar columns.
- `BTREE`: The most common type is BTREE. The index stores a copy of the
column in sorted order. This sorted copy allows a binary search to be used to
satisfy queries.
- `BITMAP`: this index stores a bitmap for each unique value in the column. It
uses a series of bits to indicate whether a value is present in a row of a table
- `LABEL_LIST`: a special index that can be used on `List<T>` columns to
support queries with `array_contains_all` and `array_contains_any`
using an underlying bitmap index.
- `BTREE`: The most common type is BTREE. This index is inspired by the btree data structure
although only the first few layers of the btree are cached in memory.
It will perform well on columns with a large number of unique values and few rows per value.
- `BITMAP`: this index stores a bitmap for each unique value in the column.
This index is useful for columns with a finite number of unique values and many rows per value.
For example, columns that represent "categories", "labels", or "tags"
- `LABEL_LIST`: a special index that is used to index list columns whose values have a finite set of possibilities.
For example, a column that contains lists of tags (e.g. `["tag1", "tag2", "tag3"]`) can be indexed with a `LABEL_LIST` index.
!!! tips "How to choose the right scalar index type"
`BTREE`: This index is good for scalar columns with mostly distinct values and does best when the query is highly selective.
`BITMAP`: This index works best for low-cardinality numeric or string columns, where the number of unique values is small (i.e., less than a few thousands).
`LABEL_LIST`: This index should be used for columns containing list-type data.
| Data Type | Filter | Index Type |
| --------------------------------------------------------------- | ----------------------------------------- | ------------ |
| Numeric, String, Temporal | `<`, `=`, `>`, `in`, `between`, `is null` | `BTREE` |
| Boolean, numbers or strings with fewer than 1,000 unique values | `<`, `=`, `>`, `in`, `between`, `is null` | `BITMAP` |
| List of low cardinality of numbers or strings | `array_has_any`, `array_has_all` | `LABEL_LIST` |
### Create a scalar index
=== "Python"
```python
@@ -58,7 +46,7 @@ over scalar columns.
await tlb.create_index("publisher", { config: lancedb.Index.bitmap() })
```
The following scan will be faster if the column `book_id` has a scalar index:
For example, the following scan will be faster if the column `my_col` has a scalar index:
=== "Python"
@@ -118,30 +106,3 @@ Scalar indices can also speed up scans containing a vector search or full text s
.limit(10)
.toArray();
```
### Update a scalar index
Updating the table data (adding, deleting, or modifying records) requires that you also update the scalar index. This can be done by calling `optimize`, which will trigger an update to the existing scalar index.
=== "Python"
```python
table.add([{"vector": [7, 8], "book_id": 4}])
table.optimize()
```
=== "TypeScript"
```typescript
await tbl.add([{ vector: [7, 8], book_id: 4 }]);
await tbl.optimize();
```
=== "Rust"
```rust
let more_data: Box<dyn RecordBatchReader + Send> = create_some_records()?;
tbl.add(more_data).execute().await?;
tbl.optimize(OptimizeAction::All).execute().await?;
```
!!! note
New data added after creating the scalar index will still appear in search results if optimize is not used, but with increased latency due to a flat search on the unindexed portion. LanceDB Cloud automates the optimize process, minimizing the impact on search speed.

View File

@@ -27,13 +27,10 @@ LanceDB OSS supports object stores such as AWS S3 (and compatible stores), Azure
Azure Blob Storage:
<!-- skip-test -->
```python
import lancedb
db = lancedb.connect("az://bucket/path")
```
Note that for Azure, storage credentials must be configured. See [below](#azure-blob-storage) for more details.
=== "TypeScript"
@@ -90,6 +87,11 @@ In most cases, when running in the respective cloud and permissions are set up c
export TIMEOUT=60s
```
!!! note "`storage_options` availability"
The `storage_options` parameter is only available in Python *async* API and JavaScript API.
It is not yet supported in the Python synchronous API.
If you only want this to apply to one particular connection, you can pass the `storage_options` argument when opening the connection:
=== "Python"
@@ -496,7 +498,7 @@ This can also be done with the ``AWS_ENDPOINT`` and ``AWS_DEFAULT_REGION`` envir
#### S3 Express
LanceDB supports [S3 Express One Zone](https://aws.amazon.com/s3/storage-classes/express-one-zone/) endpoints, but requires additional infrastructure configuration for the compute service, such as EC2 or Lambda. Please refer to [Networking requirements for S3 Express One Zone](https://docs.aws.amazon.com/AmazonS3/latest/userguide/s3-express-networking.html).
LanceDB supports [S3 Express One Zone](https://aws.amazon.com/s3/storage-classes/express-one-zone/) endpoints, but requires additional configuration. Also, S3 Express endpoints only support connecting from an EC2 instance within the same region.
To configure LanceDB to use an S3 Express endpoint, you must set the storage option `s3_express`. The bucket name in your table URI should **include the suffix**.

View File

@@ -85,13 +85,13 @@ Initialize a LanceDB connection and create a table
```ts
--8<-- "nodejs/examples/basic.test.ts:create_table"
--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.test.ts:create_table_with_schema"
--8<-- "nodejs/examples/basic.ts:create_table_with_schema"
```
!!! info "Note"
@@ -100,14 +100,14 @@ Initialize a LanceDB connection and create a table
passed in will NOT be appended to the table in that case.
```ts
--8<-- "nodejs/examples/basic.test.ts:create_table_exists_ok"
--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.test.ts:create_table_overwrite"
--8<-- "nodejs/examples/basic.ts:create_table_overwrite"
```
=== "vectordb (deprecated)"
@@ -227,7 +227,7 @@ LanceDB supports float16 data type!
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/basic.test.ts:create_f16_table"
--8<-- "nodejs/examples/basic.ts:create_f16_table"
```
=== "vectordb (deprecated)"
@@ -274,7 +274,7 @@ table = db.create_table(table_name, schema=Content)
Sometimes your data model may contain nested objects.
For example, you may want to store the document string
and the document source name as a nested Document object:
and the document soure name as a nested Document object:
```python
class Document(BaseModel):
@@ -455,7 +455,7 @@ You can create an empty table for scenarios where you want to add data to the ta
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/basic.test.ts:create_empty_table"
--8<-- "nodejs/examples/basic.ts:create_empty_table"
```
=== "vectordb (deprecated)"
@@ -466,7 +466,7 @@ You can create an empty table for scenarios where you want to add data to the ta
## Adding to a table
After a table has been created, you can always add more data to it using the `add` method
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.
@@ -535,7 +535,7 @@ After a table has been created, you can always add more data to it using the `ad
```
??? "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` field as None to allow LanceDB to automatically vectorize the data.
When using LanceDB's embedding API, you can add Pydantic models directly to the table. LanceDB will automatically convert the `vector` field to a vector before adding it to the table. You need to specify the default value of `vector` feild as None to allow LanceDB to automatically vectorize the data.
```python
import lancedb
@@ -790,122 +790,6 @@ Use the `drop_table()` method on the database to remove a table.
This permanently removes the table and is not recoverable, unlike deleting rows.
If the table does not exist an exception is raised.
## Changing schemas
While tables must have a schema specified when they are created, you can
change the schema over time. There's three methods to alter the schema of
a table:
* `add_columns`: Add new columns to the table
* `alter_columns`: Alter the name, nullability, or data type of a column
* `drop_columns`: Drop columns from the table
### Adding new columns
You can add new columns to the table with the `add_columns` method. New columns
are filled with values based on a SQL expression. For example, you can add a new
column `y` to the table and fill it with the value of `x + 1`.
=== "Python"
```python
table.add_columns({"double_price": "price * 2"})
```
**API Reference:** [lancedb.table.Table.add_columns][]
=== "Typescript"
```typescript
--8<-- "nodejs/examples/basic.test.ts:add_columns"
```
**API Reference:** [lancedb.Table.addColumns](../js/classes/Table.md/#addcolumns)
If you want to fill it with null, you can use `cast(NULL as <data_type>)` as
the SQL expression to fill the column with nulls, while controlling the data
type of the column. Available data types are base on the
[DataFusion data types](https://datafusion.apache.org/user-guide/sql/data_types.html).
You can use any of the SQL types, such as `BIGINT`:
```sql
cast(NULL as BIGINT)
```
Using Arrow data types and the `arrow_typeof` function is not yet supported.
<!-- TODO: we could provide a better formula for filling with nulls:
https://github.com/lancedb/lance/issues/3175
-->
### Altering existing columns
You can alter the name, nullability, or data type of a column with the `alter_columns`
method.
Changing the name or nullability of a column just updates the metadata. Because
of this, it's a fast operation. Changing the data type of a column requires
rewriting the column, which can be a heavy operation.
=== "Python"
```python
import pyarrow as pa
table.alter_column({"path": "double_price", "rename": "dbl_price",
"data_type": pa.float32(), "nullable": False})
```
**API Reference:** [lancedb.table.Table.alter_columns][]
=== "Typescript"
```typescript
--8<-- "nodejs/examples/basic.test.ts:alter_columns"
```
**API Reference:** [lancedb.Table.alterColumns](../js/classes/Table.md/#altercolumns)
### Dropping columns
You can drop columns from the table with the `drop_columns` method. This will
will remove the column from the schema.
<!-- TODO: Provide guidance on how to reduce disk usage once optimize helps here
waiting on: https://github.com/lancedb/lance/issues/3177
-->
=== "Python"
```python
table.drop_columns(["dbl_price"])
```
**API Reference:** [lancedb.table.Table.drop_columns][]
=== "Typescript"
```typescript
--8<-- "nodejs/examples/basic.test.ts:drop_columns"
```
**API Reference:** [lancedb.Table.dropColumns](../js/classes/Table.md/#altercolumns)
## Handling bad vectors
In LanceDB Python, you can use the `on_bad_vectors` parameter to choose how
invalid vector values are handled. Invalid vectors are vectors that are not valid
because:
1. They are the wrong dimension
2. They contain NaN values
3. They are null but are on a non-nullable field
By default, LanceDB will raise an error if it encounters a bad vector. You can
also choose one of the following options:
* `drop`: Ignore rows with bad vectors
* `fill`: Replace bad values (NaNs) or missing values (too few dimensions) with
the fill value specified in the `fill_value` parameter. An input like
`[1.0, NaN, 3.0]` will be replaced with `[1.0, 0.0, 3.0]` if `fill_value=0.0`.
* `null`: Replace bad vectors with null (only works if the column is nullable).
A bad vector `[1.0, NaN, 3.0]` will be replaced with `null` if the column is
nullable. If the vector column is non-nullable, then bad vectors will cause an
error
## Consistency
@@ -975,4 +859,4 @@ There are three possible settings for `read_consistency_interval`:
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.
[^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.

View File

@@ -49,8 +49,7 @@ The following pages go deeper into the internal of LanceDB and how to use it.
* [Working with tables](guides/tables.md): Learn how to work with tables and their associated functions
* [Indexing](ann_indexes.md): Understand how to create indexes
* [Vector search](search.md): Learn how to perform vector similarity search
* [Full-text search (native)](fts.md): Learn how to perform full-text search
* [Full-text search (tantivy-based)](fts_tantivy.md): Learn how to perform full-text search using Tantivy
* [Full-text search](fts.md): Learn how to perform full-text search
* [Managing embeddings](embeddings/index.md): Managing embeddings and the embedding functions API in LanceDB
* [Ecosystem Integrations](integrations/index.md): Integrate LanceDB with other tools in the data ecosystem
* [Python API Reference](python/python.md): Python OSS and Cloud API references

View File

@@ -1,10 +1,5 @@
**LangChain** is a framework designed for building applications with large language models (LLMs) by chaining together various components. It supports a range of functionalities including memory, agents, and chat models, enabling developers to create context-aware applications.
![Illustration](https://raw.githubusercontent.com/lancedb/assets/refs/heads/main/docs/assets/integration/langchain_rag.png)
LangChain streamlines these stages (in figure above) by providing pre-built components and tools for integration, memory management, and deployment, allowing developers to focus on application logic rather than underlying complexities.
Integration of **Langchain** with **LanceDB** enables applications to retrieve the most relevant data by comparing query vectors against stored vectors, facilitating effective information retrieval. It results in better and context aware replies and actions by the LLMs.
# Langchain
![Illustration](../assets/langchain.png)
## Quick Start
You can load your document data using langchain's loaders, for this example we are using `TextLoader` and `OpenAIEmbeddings` as the embedding model. Checkout Complete example here - [LangChain demo](../notebooks/langchain_example.ipynb)
@@ -31,28 +26,20 @@ print(docs[0].page_content)
## Documentation
In the above example `LanceDB` vector store class object is created using `from_documents()` method which is a `classmethod` and returns the initialized class object.
You can also use `LanceDB.from_texts(texts: List[str],embedding: Embeddings)` class method.
The exhaustive list of parameters for `LanceDB` vector store are :
|Name|type|Purpose|default|
|:----|:----|:----|:----|
|`connection`| (Optional) `Any` |`lancedb.db.LanceDBConnection` connection object to use. If not provided, a new connection will be created.|`None`|
|`embedding`| (Optional) `Embeddings` | Langchain embedding model.|Provided by user.|
|`uri`| (Optional) `str` |It specifies the directory location of **LanceDB database** and establishes a connection that can be used to interact with the database. |`/tmp/lancedb`|
|`vector_key` |(Optional) `str`| Column name to use for vector's in the table.|`'vector'`|
|`id_key` |(Optional) `str`| Column name to use for id's in the table.|`'id'`|
|`text_key` |(Optional) `str` |Column name to use for text in the table.|`'text'`|
|`table_name` |(Optional) `str`| Name of your table in the database.|`'vectorstore'`|
|`api_key` |(Optional `str`) |API key to use for LanceDB cloud database.|`None`|
|`region` |(Optional) `str`| Region to use for LanceDB cloud database.|Only for LanceDB Cloud : `None`.|
|`mode` |(Optional) `str` |Mode to use for adding data to the table. Valid values are "append" and "overwrite".|`'overwrite'`|
|`table`| (Optional) `Any`|You can connect to an existing table of LanceDB, created outside of langchain, and utilize it.|`None`|
|`distance`|(Optional) `str`|The choice of distance metric used to calculate the similarity between vectors.|`'l2'`|
|`reranker` |(Optional) `Any`|The reranker to use for LanceDB.|`None`|
|`relevance_score_fn` |(Optional) `Callable[[float], float]` | Langchain relevance score function to be used.|`None`|
|`limit`|`int`|Set the maximum number of results to return.|`DEFAULT_K` (it is 4)|
The exhaustive list of parameters for `LanceDB` vector store are :
- `connection`: (Optional) `lancedb.db.LanceDBConnection` connection object to use. If not provided, a new connection will be created.
- `embedding`: Langchain embedding model.
- `vector_key`: (Optional) Column name to use for vector's in the table. Defaults to `'vector'`.
- `id_key`: (Optional) Column name to use for id's in the table. Defaults to `'id'`.
- `text_key`: (Optional) Column name to use for text in the table. Defaults to `'text'`.
- `table_name`: (Optional) Name of your table in the database. Defaults to `'vectorstore'`.
- `api_key`: (Optional) API key to use for LanceDB cloud database. Defaults to `None`.
- `region`: (Optional) Region to use for LanceDB cloud database. Only for LanceDB Cloud, defaults to `None`.
- `mode`: (Optional) Mode to use for adding data to the table. Defaults to `'overwrite'`.
- `reranker`: (Optional) The reranker to use for LanceDB.
- `relevance_score_fn`: (Optional[Callable[[float], float]]) Langchain relevance score function to be used. Defaults to `None`.
```python
db_url = "db://lang_test" # url of db you created
@@ -64,24 +51,19 @@ vector_store = LanceDB(
api_key=api_key, #(dont include for local API)
region=region, #(dont include for local API)
embedding=embeddings,
table_name='langchain_test' # Optional
table_name='langchain_test' #Optional
)
```
### Methods
##### add_texts()
- `texts`: `Iterable` of strings to add to the vectorstore.
- `metadatas`: Optional `list[dict()]` of metadatas associated with the texts.
- `ids`: Optional `list` of ids to associate with the texts.
- `kwargs`: `Any`
This method turn texts into embedding and add it to the database.
|Name|Purpose|defaults|
|:---|:---|:---|
|`texts`|`Iterable` of strings to add to the vectorstore.|Provided by user|
|`metadatas`|Optional `list[dict()]` of metadatas associated with the texts.|`None`|
|`ids`|Optional `list` of ids to associate with the texts.|`None`|
|`kwargs`| Other keyworded arguments provided by the user. |-|
It returns list of ids of the added texts.
This method adds texts and stores respective embeddings automatically.
```python
vector_store.add_texts(texts = ['test_123'], metadatas =[{'source' :'wiki'}])
@@ -96,25 +78,14 @@ pd_df.to_csv("docsearch.csv", index=False)
# you can also create a new vector store object using an older connection object:
vector_store = LanceDB(connection=tbl, embedding=embeddings)
```
------
##### create_index()
- `col_name`: `Optional[str] = None`
- `vector_col`: `Optional[str] = None`
- `num_partitions`: `Optional[int] = 256`
- `num_sub_vectors`: `Optional[int] = 96`
- `index_cache_size`: `Optional[int] = None`
This method creates a scalar(for non-vector cols) or a vector index on a table.
|Name|type|Purpose|defaults|
|:---|:---|:---|:---|
|`vector_col`|`Optional[str]`| Provide if you want to create index on a vector column. |`None`|
|`col_name`|`Optional[str]`| Provide if you want to create index on a non-vector column. |`None`|
|`metric`|`Optional[str]` |Provide the metric to use for vector index. choice of metrics: 'L2', 'dot', 'cosine'. |`L2`|
|`num_partitions`|`Optional[int]`|Number of partitions to use for the index.|`256`|
|`num_sub_vectors`|`Optional[int]` |Number of sub-vectors to use for the index.|`96`|
|`index_cache_size`|`Optional[int]` |Size of the index cache.|`None`|
|`name`|`Optional[str]` |Name of the table to create index on.|`None`|
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.
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
@@ -125,63 +96,42 @@ 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`
This method performs similarity search based on **text query**.
| Name | Type | Purpose | Default |
|---------|----------------------|---------|---------|
| `query` | `str` | A `str` representing the text query that you want to search for in the vector store. | N/A |
| `k` | `Optional[int]` | It specifies the number of documents to return. | `None` |
| `filter` | `Optional[Dict[str, str]]`| It is used to filter the search results by specific metadata criteria. | `None` |
| `fts` | `Optional[bool]` | It indicates whether to perform a full-text search (FTS). | `False` |
| `name` | `Optional[str]` | It is used for specifying the name of the table to query. If not provided, it uses the default table set during the initialization of the LanceDB instance. | `None` |
| `kwargs` | `Any` | Other keyworded arguments provided by the user. | N/A |
Return documents most similar to the query **without relevance scores**.
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`
The method returns documents that are most similar to the specified **embedding (query) vector**.
| Name | Type | Purpose | Default |
|-------------|---------------------------|---------|---------|
| `embedding` | `List[float]` | The embedding vector you want to use to search for similar documents in the vector store. | N/A |
| `k` | `Optional[int]` | It specifies the number of documents to return. | `None` |
| `filter` | `Optional[Dict[str, str]]`| It is used to filter the search results by specific metadata criteria. | `None` |
| `name` | `Optional[str]` | It is used for specifying the name of the table to query. If not provided, it uses the default table set during the initialization of the LanceDB instance. | `None` |
| `kwargs` | `Any` | Other keyworded arguments provided by the user. | N/A |
**It does not provide relevance scores.**
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** along with their relevance scores.
| Name | Type | Purpose | Default |
|----------|---------------------------|---------|---------|
| `query` | `str` |A `str` representing the text query you want to search for in the vector store. This query will be converted into an embedding using the specified embedding function. | N/A |
| `k` | `Optional[int]` | It specifies the number of documents to return. | `None` |
| `filter` | `Optional[Dict[str, str]]`| It is used to filter the search results by specific metadata criteria. This allows you to narrow down the search results based on certain metadata attributes associated with the documents. | `None` |
| `kwargs` | `Any` | Other keyworded arguments provided by the user. | N/A |
It gets called by base class's `similarity_search_with_relevance_scores` which selects relevance score based on our `_select_relevance_score_fn`.
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)
@@ -189,21 +139,15 @@ 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`
Similarity search using **query vector**.
| Name | Type | Purpose | Default |
|-------------|---------------------------|---------|---------|
| `embedding` | `List[float]` | The embedding vector you want to use to search for similar documents in the vector store. | N/A |
| `k` | `Optional[int]` | It specifies the number of documents to return. | `None` |
| `filter` | `Optional[Dict[str, str]]`| It is used to filter the search results by specific metadata criteria. | `None` |
| `name` | `Optional[str]` | It is used for specifying the name of the table to query. | `None` |
| `kwargs` | `Any` | Other keyworded arguments provided by the user. | N/A |
The method returns documents most similar to the specified embedding (query) vector, along with their relevance scores.
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)
@@ -211,22 +155,20 @@ 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`
This method returns docs selected using the maximal marginal relevance(MMR).
Returns docs selected using the maximal marginal relevance(MMR).
Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents.
| Name | Type | Purpose | Default |
|---------------|-----------------|-----------|---------|
| `query` | `str` | Text to look up documents similar to. | N/A |
| `k` | `Optional[int]` | Number of Documents to return.| `4` |
| `fetch_k`| `Optional[int]`| Number of Documents to fetch to pass to MMR algorithm.| `None` |
| `lambda_mult` | `float` | 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. | `0.5` |
| `filter`| `Optional[Dict[str, str]]`| Filter by metadata. | `None` |
|`kwargs`| Other keyworded arguments provided by the user. |-|
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
@@ -244,19 +186,12 @@ 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)`
This method ddds images by automatically creating their embeddings and adds them to the vectorstore.
| Name | Type | Purpose | Default |
|------------|-------------------------------|--------------------------------|---------|
| `uris` | `List[str]` | File path to the image | N/A |
| `metadatas`| `Optional[List[dict]]` | Optional list of metadatas | `None` |
| `ids` | `Optional[List[str]]` | Optional list of IDs | `None` |
It returns list of IDs of the added images.
Adds images by automatically creating their embeddings and adds them to the vectorstore.
```python
vec_store.add_images(uris=image_uris)

View File

@@ -45,7 +45,7 @@ Let's see how using LanceDB inside phidata helps in making LLM more useful:
**Install the following packages in the virtual environment**
```python
pip install lancedb phidata youtube_transcript_api openai ollama numpy pandas
pip install lancedb phidata youtube_transcript_api openai ollama pandas numpy
```
**Create python files and import necessary libraries**

View File

@@ -41,6 +41,7 @@ To build everything fresh:
```bash
npm install
npm run tsc
npm run build
```
@@ -50,6 +51,18 @@ Then you should be able to run the tests with:
npm test
```
### Rebuilding Rust library
```bash
npm run build
```
### Rebuilding Typescript
```bash
npm run tsc
```
### Fix lints
To run the linter and have it automatically fix all errors

View File

@@ -38,4 +38,4 @@ A [WriteMode](../enums/WriteMode.md) to use on this operation
#### Defined in
[index.ts:1359](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1359)
[index.ts:1019](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L1019)

View File

@@ -30,7 +30,6 @@ A connection to a LanceDB database.
- [dropTable](LocalConnection.md#droptable)
- [openTable](LocalConnection.md#opentable)
- [tableNames](LocalConnection.md#tablenames)
- [withMiddleware](LocalConnection.md#withmiddleware)
## Constructors
@@ -47,7 +46,7 @@ A connection to a LanceDB database.
#### Defined in
[index.ts:739](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L739)
[index.ts:489](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L489)
## Properties
@@ -57,7 +56,7 @@ A connection to a LanceDB database.
#### Defined in
[index.ts:737](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L737)
[index.ts:487](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L487)
___
@@ -75,7 +74,7 @@ ___
#### Defined in
[index.ts:736](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L736)
[index.ts:486](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L486)
## Accessors
@@ -93,7 +92,7 @@ ___
#### Defined in
[index.ts:744](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L744)
[index.ts:494](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L494)
## Methods
@@ -114,7 +113,7 @@ Creates a new Table, optionally initializing it with new data.
| Name | Type |
| :------ | :------ |
| `name` | `string` \| [`CreateTableOptions`](../interfaces/CreateTableOptions.md)\<`T`\> |
| `data?` | `Table`\<`any`\> \| `Record`\<`string`, `unknown`\>[] |
| `data?` | `Record`\<`string`, `unknown`\>[] |
| `optsOrEmbedding?` | [`WriteOptions`](../interfaces/WriteOptions.md) \| [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)\<`T`\> |
| `opt?` | [`WriteOptions`](../interfaces/WriteOptions.md) |
@@ -128,7 +127,7 @@ Creates a new Table, optionally initializing it with new data.
#### Defined in
[index.ts:788](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L788)
[index.ts:542](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L542)
___
@@ -159,7 +158,7 @@ ___
#### Defined in
[index.ts:822](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L822)
[index.ts:576](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L576)
___
@@ -185,7 +184,7 @@ Drop an existing table.
#### Defined in
[index.ts:876](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L876)
[index.ts:630](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L630)
___
@@ -211,7 +210,7 @@ Open a table in the database.
#### Defined in
[index.ts:760](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L760)
[index.ts:510](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L510)
**openTable**\<`T`\>(`name`, `embeddings`): `Promise`\<[`Table`](../interfaces/Table.md)\<`T`\>\>
@@ -240,7 +239,7 @@ Connection.openTable
#### Defined in
[index.ts:768](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L768)
[index.ts:518](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L518)
**openTable**\<`T`\>(`name`, `embeddings?`): `Promise`\<[`Table`](../interfaces/Table.md)\<`T`\>\>
@@ -267,7 +266,7 @@ Connection.openTable
#### Defined in
[index.ts:772](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L772)
[index.ts:522](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L522)
___
@@ -287,36 +286,4 @@ Get the names of all tables in the database.
#### Defined in
[index.ts:751](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L751)
___
### withMiddleware
**withMiddleware**(`middleware`): [`Connection`](../interfaces/Connection.md)
Instrument the behavior of this Connection with middleware.
The middleware will be called in the order they are added.
Currently this functionality is only supported for remote Connections.
#### Parameters
| Name | Type |
| :------ | :------ |
| `middleware` | `HttpMiddleware` |
#### Returns
[`Connection`](../interfaces/Connection.md)
- this Connection instrumented by the passed middleware
#### Implementation of
[Connection](../interfaces/Connection.md).[withMiddleware](../interfaces/Connection.md#withmiddleware)
#### Defined in
[index.ts:880](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L880)
[index.ts:501](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L501)

View File

@@ -37,8 +37,6 @@ A LanceDB Table is the collection of Records. Each Record has one or more vector
### Methods
- [add](LocalTable.md#add)
- [addColumns](LocalTable.md#addcolumns)
- [alterColumns](LocalTable.md#altercolumns)
- [checkElectron](LocalTable.md#checkelectron)
- [cleanupOldVersions](LocalTable.md#cleanupoldversions)
- [compactFiles](LocalTable.md#compactfiles)
@@ -46,16 +44,13 @@ A LanceDB Table is the collection of Records. Each Record has one or more vector
- [createIndex](LocalTable.md#createindex)
- [createScalarIndex](LocalTable.md#createscalarindex)
- [delete](LocalTable.md#delete)
- [dropColumns](LocalTable.md#dropcolumns)
- [filter](LocalTable.md#filter)
- [getSchema](LocalTable.md#getschema)
- [indexStats](LocalTable.md#indexstats)
- [listIndices](LocalTable.md#listindices)
- [mergeInsert](LocalTable.md#mergeinsert)
- [overwrite](LocalTable.md#overwrite)
- [search](LocalTable.md#search)
- [update](LocalTable.md#update)
- [withMiddleware](LocalTable.md#withmiddleware)
## Constructors
@@ -79,7 +74,7 @@ A LanceDB Table is the collection of Records. Each Record has one or more vector
#### Defined in
[index.ts:892](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L892)
[index.ts:642](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L642)
**new LocalTable**\<`T`\>(`tbl`, `name`, `options`, `embeddings`)
@@ -100,7 +95,7 @@ A LanceDB Table is the collection of Records. Each Record has one or more vector
#### Defined in
[index.ts:899](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L899)
[index.ts:649](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L649)
## Properties
@@ -110,7 +105,7 @@ A LanceDB Table is the collection of Records. Each Record has one or more vector
#### Defined in
[index.ts:889](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L889)
[index.ts:639](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L639)
___
@@ -120,7 +115,7 @@ ___
#### Defined in
[index.ts:888](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L888)
[index.ts:638](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L638)
___
@@ -130,7 +125,7 @@ ___
#### Defined in
[index.ts:887](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L887)
[index.ts:637](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L637)
___
@@ -148,7 +143,7 @@ ___
#### Defined in
[index.ts:890](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L890)
[index.ts:640](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L640)
___
@@ -158,7 +153,7 @@ ___
#### Defined in
[index.ts:886](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L886)
[index.ts:636](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L636)
___
@@ -184,7 +179,7 @@ Creates a filter query to find all rows matching the specified criteria
#### Defined in
[index.ts:938](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L938)
[index.ts:688](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L688)
## Accessors
@@ -202,7 +197,7 @@ Creates a filter query to find all rows matching the specified criteria
#### Defined in
[index.ts:918](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L918)
[index.ts:668](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L668)
___
@@ -220,7 +215,7 @@ ___
#### Defined in
[index.ts:1171](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1171)
[index.ts:849](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L849)
## Methods
@@ -234,7 +229,7 @@ Insert records into this Table.
| Name | Type | Description |
| :------ | :------ | :------ |
| `data` | `Table`\<`any`\> \| `Record`\<`string`, `unknown`\>[] | Records to be inserted into the Table |
| `data` | `Record`\<`string`, `unknown`\>[] | Records to be inserted into the Table |
#### Returns
@@ -248,59 +243,7 @@ The number of rows added to the table
#### Defined in
[index.ts:946](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L946)
___
### addColumns
**addColumns**(`newColumnTransforms`): `Promise`\<`void`\>
Add new columns with defined values.
#### Parameters
| Name | Type | Description |
| :------ | :------ | :------ |
| `newColumnTransforms` | \{ `name`: `string` ; `valueSql`: `string` }[] | 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`\>
#### Implementation of
[Table](../interfaces/Table.md).[addColumns](../interfaces/Table.md#addcolumns)
#### Defined in
[index.ts:1195](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1195)
___
### alterColumns
**alterColumns**(`columnAlterations`): `Promise`\<`void`\>
Alter the name or nullability of columns.
#### Parameters
| Name | Type | Description |
| :------ | :------ | :------ |
| `columnAlterations` | [`ColumnAlteration`](../interfaces/ColumnAlteration.md)[] | One or more alterations to apply to columns. |
#### Returns
`Promise`\<`void`\>
#### Implementation of
[Table](../interfaces/Table.md).[alterColumns](../interfaces/Table.md#altercolumns)
#### Defined in
[index.ts:1201](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1201)
[index.ts:696](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L696)
___
@@ -314,7 +257,7 @@ ___
#### Defined in
[index.ts:1183](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1183)
[index.ts:861](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L861)
___
@@ -337,7 +280,7 @@ Clean up old versions of the table, freeing disk space.
#### Defined in
[index.ts:1130](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1130)
[index.ts:808](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L808)
___
@@ -364,22 +307,16 @@ Metrics about the compaction operation.
#### Defined in
[index.ts:1153](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1153)
[index.ts:831](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L831)
___
### countRows
**countRows**(`filter?`): `Promise`\<`number`\>
**countRows**(): `Promise`\<`number`\>
Returns the number of rows in this table.
#### Parameters
| Name | Type |
| :------ | :------ |
| `filter?` | `string` |
#### Returns
`Promise`\<`number`\>
@@ -390,7 +327,7 @@ Returns the number of rows in this table.
#### Defined in
[index.ts:1021](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1021)
[index.ts:749](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L749)
___
@@ -420,13 +357,13 @@ VectorIndexParams.
#### Defined in
[index.ts:1003](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1003)
[index.ts:734](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L734)
___
### createScalarIndex
**createScalarIndex**(`column`, `replace?`): `Promise`\<`void`\>
**createScalarIndex**(`column`, `replace`): `Promise`\<`void`\>
Create a scalar index on this Table for the given column
@@ -435,7 +372,7 @@ Create a scalar index on this Table for the given column
| Name | Type | Description |
| :------ | :------ | :------ |
| `column` | `string` | The column to index |
| `replace?` | `boolean` | If false, fail if an index already exists on the column it is always set to true for remote connections Scalar indices, like vector indices, can be used to speed up scans. A scalar index can speed up scans that contain filter expressions on the indexed column. For example, the following scan will be faster if the column `my_col` has a scalar index: ```ts const con = await lancedb.connect('./.lancedb'); const table = await con.openTable('images'); const results = await table.where('my_col = 7').execute(); ``` Scalar indices can also speed up scans containing a vector search and a prefilter: ```ts const con = await lancedb.connect('././lancedb'); const table = await con.openTable('images'); const results = await table.search([1.0, 2.0]).where('my_col != 7').prefilter(true); ``` Scalar indices can only speed up scans for basic filters using equality, comparison, range (e.g. `my_col BETWEEN 0 AND 100`), and set membership (e.g. `my_col IN (0, 1, 2)`) Scalar indices can be used if the filter contains multiple indexed columns and the filter criteria are AND'd or OR'd together (e.g. `my_col < 0 AND other_col> 100`) Scalar indices may be used if the filter contains non-indexed columns but, depending on the structure of the filter, they may not be usable. For example, if the column `not_indexed` does not have a scalar index then the filter `my_col = 0 OR not_indexed = 1` will not be able to use any scalar index on `my_col`. |
| `replace` | `boolean` | If false, fail if an index already exists on the column Scalar indices, like vector indices, can be used to speed up scans. A scalar index can speed up scans that contain filter expressions on the indexed column. For example, the following scan will be faster if the column `my_col` has a scalar index: ```ts const con = await lancedb.connect('./.lancedb'); const table = await con.openTable('images'); const results = await table.where('my_col = 7').execute(); ``` Scalar indices can also speed up scans containing a vector search and a prefilter: ```ts const con = await lancedb.connect('././lancedb'); const table = await con.openTable('images'); const results = await table.search([1.0, 2.0]).where('my_col != 7').prefilter(true); ``` Scalar indices can only speed up scans for basic filters using equality, comparison, range (e.g. `my_col BETWEEN 0 AND 100`), and set membership (e.g. `my_col IN (0, 1, 2)`) Scalar indices can be used if the filter contains multiple indexed columns and the filter criteria are AND'd or OR'd together (e.g. `my_col < 0 AND other_col> 100`) Scalar indices may be used if the filter contains non-indexed columns but, depending on the structure of the filter, they may not be usable. For example, if the column `not_indexed` does not have a scalar index then the filter `my_col = 0 OR not_indexed = 1` will not be able to use any scalar index on `my_col`. |
#### Returns
@@ -455,7 +392,7 @@ await table.createScalarIndex('my_col')
#### Defined in
[index.ts:1011](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1011)
[index.ts:742](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L742)
___
@@ -481,38 +418,7 @@ Delete rows from this table.
#### Defined in
[index.ts:1030](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1030)
___
### dropColumns
▸ **dropColumns**(`columnNames`): `Promise`\<`void`\>
Drop one or more columns from the dataset
This is a metadata-only operation and does not remove the data from the
underlying storage. In order to remove the data, you must subsequently
call ``compact_files`` to rewrite the data without the removed columns and
then call ``cleanup_files`` to remove the old files.
#### Parameters
| Name | Type | Description |
| :------ | :------ | :------ |
| `columnNames` | `string`[] | The names of the columns to drop. These can be nested column references (e.g. "a.b.c") or top-level column names (e.g. "a"). |
#### Returns
`Promise`\<`void`\>
#### Implementation of
[Table](../interfaces/Table.md).[dropColumns](../interfaces/Table.md#dropcolumns)
#### Defined in
[index.ts:1205](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1205)
[index.ts:758](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L758)
___
@@ -532,13 +438,9 @@ Creates a filter query to find all rows matching the specified criteria
[`Query`](Query.md)\<`T`\>
#### Implementation of
[Table](../interfaces/Table.md).[filter](../interfaces/Table.md#filter)
#### Defined in
[index.ts:934](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L934)
[index.ts:684](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L684)
___
@@ -552,13 +454,13 @@ ___
#### Defined in
[index.ts:1176](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1176)
[index.ts:854](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L854)
___
### indexStats
▸ **indexStats**(`indexName`): `Promise`\<[`IndexStats`](../interfaces/IndexStats.md)\>
▸ **indexStats**(`indexUuid`): `Promise`\<[`IndexStats`](../interfaces/IndexStats.md)\>
Get statistics about an index.
@@ -566,7 +468,7 @@ Get statistics about an index.
| Name | Type |
| :------ | :------ |
| `indexName` | `string` |
| `indexUuid` | `string` |
#### Returns
@@ -578,7 +480,7 @@ Get statistics about an index.
#### Defined in
[index.ts:1167](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1167)
[index.ts:845](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L845)
___
@@ -598,57 +500,7 @@ List the indicies on this table.
#### Defined in
[index.ts:1163](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1163)
___
### mergeInsert
▸ **mergeInsert**(`on`, `data`, `args`): `Promise`\<`void`\>
Runs a "merge insert" operation on the table
This operation can add rows, update rows, and remove rows all in a single
transaction. It is a very generic tool that can be used to create
behaviors like "insert if not exists", "update or insert (i.e. upsert)",
or even replace a portion of existing data with new data (e.g. replace
all data where month="january")
The merge insert operation works by combining new data from a
**source table** with existing data in a **target table** by using a
join. There are three categories of records.
"Matched" records are records that exist in both the source table and
the target table. "Not matched" records exist only in the source table
(e.g. these are new data) "Not matched by source" records exist only
in the target table (this is old data)
The MergeInsertArgs can be used to customize what should happen for
each category of data.
Please note that the data may appear to be reordered as part of this
operation. This is because updated rows will be deleted from the
dataset and then reinserted at the end with the new values.
#### Parameters
| Name | Type | Description |
| :------ | :------ | :------ |
| `on` | `string` | a column to join on. This is how records from the source table and target table are matched. |
| `data` | `Table`\<`any`\> \| `Record`\<`string`, `unknown`\>[] | the new data to insert |
| `args` | [`MergeInsertArgs`](../interfaces/MergeInsertArgs.md) | parameters controlling how the operation should behave |
#### Returns
`Promise`\<`void`\>
#### Implementation of
[Table](../interfaces/Table.md).[mergeInsert](../interfaces/Table.md#mergeinsert)
#### Defined in
[index.ts:1065](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1065)
[index.ts:841](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L841)
___
@@ -662,7 +514,7 @@ Insert records into this Table, replacing its contents.
| Name | Type | Description |
| :------ | :------ | :------ |
| `data` | `Table`\<`any`\> \| `Record`\<`string`, `unknown`\>[] | Records to be inserted into the Table |
| `data` | `Record`\<`string`, `unknown`\>[] | Records to be inserted into the Table |
#### Returns
@@ -676,7 +528,7 @@ The number of rows added to the table
#### Defined in
[index.ts:977](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L977)
[index.ts:716](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L716)
___
@@ -702,7 +554,7 @@ Creates a search query to find the nearest neighbors of the given search term
#### Defined in
[index.ts:926](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L926)
[index.ts:676](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L676)
___
@@ -728,36 +580,4 @@ Update rows in this table.
#### Defined in
[index.ts:1043](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1043)
___
### withMiddleware
▸ **withMiddleware**(`middleware`): [`Table`](../interfaces/Table.md)\<`T`\>
Instrument the behavior of this Table with middleware.
The middleware will be called in the order they are added.
Currently this functionality is only supported for remote tables.
#### Parameters
| Name | Type |
| :------ | :------ |
| `middleware` | `HttpMiddleware` |
#### Returns
[`Table`](../interfaces/Table.md)\<`T`\>
- this Table instrumented by the passed middleware
#### Implementation of
[Table](../interfaces/Table.md).[withMiddleware](../interfaces/Table.md#withmiddleware)
#### Defined in
[index.ts:1209](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1209)
[index.ts:771](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L771)

View File

@@ -1,82 +0,0 @@
[vectordb](../README.md) / [Exports](../modules.md) / MakeArrowTableOptions
# Class: MakeArrowTableOptions
Options to control the makeArrowTable call.
## Table of contents
### Constructors
- [constructor](MakeArrowTableOptions.md#constructor)
### Properties
- [dictionaryEncodeStrings](MakeArrowTableOptions.md#dictionaryencodestrings)
- [embeddings](MakeArrowTableOptions.md#embeddings)
- [schema](MakeArrowTableOptions.md#schema)
- [vectorColumns](MakeArrowTableOptions.md#vectorcolumns)
## Constructors
### constructor
**new MakeArrowTableOptions**(`values?`)
#### Parameters
| Name | Type |
| :------ | :------ |
| `values?` | `Partial`\<[`MakeArrowTableOptions`](MakeArrowTableOptions.md)\> |
#### Defined in
[arrow.ts:98](https://github.com/lancedb/lancedb/blob/92179835/node/src/arrow.ts#L98)
## Properties
### dictionaryEncodeStrings
**dictionaryEncodeStrings**: `boolean` = `false`
If true then string columns will be encoded with dictionary encoding
Set this to true if your string columns tend to repeat the same values
often. For more precise control use the `schema` property to specify the
data type for individual columns.
If `schema` is provided then this property is ignored.
#### Defined in
[arrow.ts:96](https://github.com/lancedb/lancedb/blob/92179835/node/src/arrow.ts#L96)
___
### embeddings
`Optional` **embeddings**: [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)\<`any`\>
#### Defined in
[arrow.ts:85](https://github.com/lancedb/lancedb/blob/92179835/node/src/arrow.ts#L85)
___
### schema
`Optional` **schema**: `Schema`\<`any`\>
#### Defined in
[arrow.ts:63](https://github.com/lancedb/lancedb/blob/92179835/node/src/arrow.ts#L63)
___
### vectorColumns
**vectorColumns**: `Record`\<`string`, `VectorColumnOptions`\>
#### Defined in
[arrow.ts:81](https://github.com/lancedb/lancedb/blob/92179835/node/src/arrow.ts#L81)

View File

@@ -40,7 +40,7 @@ An embedding function that automatically creates vector representation for a giv
#### Defined in
[embedding/openai.ts:22](https://github.com/lancedb/lancedb/blob/92179835/node/src/embedding/openai.ts#L22)
[embedding/openai.ts:21](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/embedding/openai.ts#L21)
## Properties
@@ -50,17 +50,17 @@ An embedding function that automatically creates vector representation for a giv
#### Defined in
[embedding/openai.ts:20](https://github.com/lancedb/lancedb/blob/92179835/node/src/embedding/openai.ts#L20)
[embedding/openai.ts:19](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/embedding/openai.ts#L19)
___
### \_openai
`Private` `Readonly` **\_openai**: `OpenAI`
`Private` `Readonly` **\_openai**: `any`
#### Defined in
[embedding/openai.ts:19](https://github.com/lancedb/lancedb/blob/92179835/node/src/embedding/openai.ts#L19)
[embedding/openai.ts:18](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/embedding/openai.ts#L18)
___
@@ -76,7 +76,7 @@ The name of the column that will be used as input for the Embedding Function.
#### Defined in
[embedding/openai.ts:56](https://github.com/lancedb/lancedb/blob/92179835/node/src/embedding/openai.ts#L56)
[embedding/openai.ts:50](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/embedding/openai.ts#L50)
## Methods
@@ -102,4 +102,4 @@ Creates a vector representation for the given values.
#### Defined in
[embedding/openai.ts:43](https://github.com/lancedb/lancedb/blob/92179835/node/src/embedding/openai.ts#L43)
[embedding/openai.ts:38](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/embedding/openai.ts#L38)

View File

@@ -19,7 +19,6 @@ A builder for nearest neighbor queries for LanceDB.
### Properties
- [\_embeddings](Query.md#_embeddings)
- [\_fastSearch](Query.md#_fastsearch)
- [\_filter](Query.md#_filter)
- [\_limit](Query.md#_limit)
- [\_metricType](Query.md#_metrictype)
@@ -35,7 +34,6 @@ A builder for nearest neighbor queries for LanceDB.
### Methods
- [execute](Query.md#execute)
- [fastSearch](Query.md#fastsearch)
- [filter](Query.md#filter)
- [isElectron](Query.md#iselectron)
- [limit](Query.md#limit)
@@ -67,7 +65,7 @@ A builder for nearest neighbor queries for LanceDB.
#### Defined in
[query.ts:39](https://github.com/lancedb/lancedb/blob/92179835/node/src/query.ts#L39)
[query.ts:38](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/query.ts#L38)
## Properties
@@ -77,17 +75,7 @@ A builder for nearest neighbor queries for LanceDB.
#### Defined in
[query.ts:37](https://github.com/lancedb/lancedb/blob/92179835/node/src/query.ts#L37)
___
### \_fastSearch
`Private` **\_fastSearch**: `boolean`
#### Defined in
[query.ts:36](https://github.com/lancedb/lancedb/blob/92179835/node/src/query.ts#L36)
[query.ts:36](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/query.ts#L36)
___
@@ -97,7 +85,7 @@ ___
#### Defined in
[query.ts:33](https://github.com/lancedb/lancedb/blob/92179835/node/src/query.ts#L33)
[query.ts:33](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/query.ts#L33)
___
@@ -107,7 +95,7 @@ ___
#### Defined in
[query.ts:29](https://github.com/lancedb/lancedb/blob/92179835/node/src/query.ts#L29)
[query.ts:29](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/query.ts#L29)
___
@@ -117,7 +105,7 @@ ___
#### Defined in
[query.ts:34](https://github.com/lancedb/lancedb/blob/92179835/node/src/query.ts#L34)
[query.ts:34](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/query.ts#L34)
___
@@ -127,7 +115,7 @@ ___
#### Defined in
[query.ts:31](https://github.com/lancedb/lancedb/blob/92179835/node/src/query.ts#L31)
[query.ts:31](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/query.ts#L31)
___
@@ -137,7 +125,7 @@ ___
#### Defined in
[query.ts:35](https://github.com/lancedb/lancedb/blob/92179835/node/src/query.ts#L35)
[query.ts:35](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/query.ts#L35)
___
@@ -147,7 +135,7 @@ ___
#### Defined in
[query.ts:26](https://github.com/lancedb/lancedb/blob/92179835/node/src/query.ts#L26)
[query.ts:26](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/query.ts#L26)
___
@@ -157,7 +145,7 @@ ___
#### Defined in
[query.ts:28](https://github.com/lancedb/lancedb/blob/92179835/node/src/query.ts#L28)
[query.ts:28](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/query.ts#L28)
___
@@ -167,7 +155,7 @@ ___
#### Defined in
[query.ts:30](https://github.com/lancedb/lancedb/blob/92179835/node/src/query.ts#L30)
[query.ts:30](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/query.ts#L30)
___
@@ -177,7 +165,7 @@ ___
#### Defined in
[query.ts:32](https://github.com/lancedb/lancedb/blob/92179835/node/src/query.ts#L32)
[query.ts:32](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/query.ts#L32)
___
@@ -187,7 +175,7 @@ ___
#### Defined in
[query.ts:27](https://github.com/lancedb/lancedb/blob/92179835/node/src/query.ts#L27)
[query.ts:27](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/query.ts#L27)
___
@@ -213,7 +201,7 @@ A filter statement to be applied to this query.
#### Defined in
[query.ts:90](https://github.com/lancedb/lancedb/blob/92179835/node/src/query.ts#L90)
[query.ts:87](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/query.ts#L87)
## Methods
@@ -235,30 +223,7 @@ Execute the query and return the results as an Array of Objects
#### Defined in
[query.ts:127](https://github.com/lancedb/lancedb/blob/92179835/node/src/query.ts#L127)
___
### fastSearch
**fastSearch**(`value`): [`Query`](Query.md)\<`T`\>
Skip searching un-indexed data. This can make search faster, but will miss
any data that is not yet indexed.
#### Parameters
| Name | Type |
| :------ | :------ |
| `value` | `boolean` |
#### Returns
[`Query`](Query.md)\<`T`\>
#### Defined in
[query.ts:119](https://github.com/lancedb/lancedb/blob/92179835/node/src/query.ts#L119)
[query.ts:115](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/query.ts#L115)
___
@@ -280,7 +245,7 @@ A filter statement to be applied to this query.
#### Defined in
[query.ts:85](https://github.com/lancedb/lancedb/blob/92179835/node/src/query.ts#L85)
[query.ts:82](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/query.ts#L82)
___
@@ -294,7 +259,7 @@ ___
#### Defined in
[query.ts:155](https://github.com/lancedb/lancedb/blob/92179835/node/src/query.ts#L155)
[query.ts:142](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/query.ts#L142)
___
@@ -303,7 +268,6 @@ ___
**limit**(`value`): [`Query`](Query.md)\<`T`\>
Sets the number of results that will be returned
default value is 10
#### Parameters
@@ -317,7 +281,7 @@ default value is 10
#### Defined in
[query.ts:58](https://github.com/lancedb/lancedb/blob/92179835/node/src/query.ts#L58)
[query.ts:55](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/query.ts#L55)
___
@@ -343,7 +307,7 @@ MetricType for the different options
#### Defined in
[query.ts:105](https://github.com/lancedb/lancedb/blob/92179835/node/src/query.ts#L105)
[query.ts:102](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/query.ts#L102)
___
@@ -365,7 +329,7 @@ The number of probes used. A higher number makes search more accurate but also s
#### Defined in
[query.ts:76](https://github.com/lancedb/lancedb/blob/92179835/node/src/query.ts#L76)
[query.ts:73](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/query.ts#L73)
___
@@ -385,7 +349,7 @@ ___
#### Defined in
[query.ts:110](https://github.com/lancedb/lancedb/blob/92179835/node/src/query.ts#L110)
[query.ts:107](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/query.ts#L107)
___
@@ -407,7 +371,7 @@ Refine the results by reading extra elements and re-ranking them in memory.
#### Defined in
[query.ts:67](https://github.com/lancedb/lancedb/blob/92179835/node/src/query.ts#L67)
[query.ts:64](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/query.ts#L64)
___
@@ -429,4 +393,4 @@ Return only the specified columns.
#### Defined in
[query.ts:96](https://github.com/lancedb/lancedb/blob/92179835/node/src/query.ts#L96)
[query.ts:93](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/query.ts#L93)

View File

@@ -1,52 +0,0 @@
[vectordb](../README.md) / [Exports](../modules.md) / IndexStatus
# Enumeration: IndexStatus
## Table of contents
### Enumeration Members
- [Done](IndexStatus.md#done)
- [Failed](IndexStatus.md#failed)
- [Indexing](IndexStatus.md#indexing)
- [Pending](IndexStatus.md#pending)
## Enumeration Members
### Done
**Done** = ``"done"``
#### Defined in
[index.ts:713](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L713)
___
### Failed
• **Failed** = ``"failed"``
#### Defined in
[index.ts:714](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L714)
___
### Indexing
• **Indexing** = ``"indexing"``
#### Defined in
[index.ts:712](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L712)
___
### Pending
• **Pending** = ``"pending"``
#### Defined in
[index.ts:711](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L711)

View File

@@ -22,7 +22,7 @@ Cosine distance
#### Defined in
[index.ts:1381](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1381)
[index.ts:1041](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L1041)
___
@@ -34,7 +34,7 @@ Dot product
#### Defined in
[index.ts:1386](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1386)
[index.ts:1046](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L1046)
___
@@ -46,4 +46,4 @@ Euclidean distance
#### Defined in
[index.ts:1376](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1376)
[index.ts:1036](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L1036)

View File

@@ -22,7 +22,7 @@ Append new data to the table.
#### Defined in
[index.ts:1347](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1347)
[index.ts:1007](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L1007)
___
@@ -34,7 +34,7 @@ Create a new [Table](../interfaces/Table.md).
#### Defined in
[index.ts:1343](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1343)
[index.ts:1003](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L1003)
___
@@ -46,4 +46,4 @@ Overwrite the existing [Table](../interfaces/Table.md) if presented.
#### Defined in
[index.ts:1345](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1345)
[index.ts:1005](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L1005)

View File

@@ -18,7 +18,7 @@
#### Defined in
[index.ts:68](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L68)
[index.ts:54](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L54)
___
@@ -28,7 +28,7 @@ ___
#### Defined in
[index.ts:70](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L70)
[index.ts:56](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L56)
___
@@ -38,4 +38,4 @@ ___
#### Defined in
[index.ts:72](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L72)
[index.ts:58](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L58)

View File

@@ -19,7 +19,7 @@ The number of bytes removed from disk.
#### Defined in
[index.ts:1218](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1218)
[index.ts:878](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L878)
___
@@ -31,4 +31,4 @@ The number of old table versions removed.
#### Defined in
[index.ts:1222](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1222)
[index.ts:882](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L882)

View File

@@ -1,53 +0,0 @@
[vectordb](../README.md) / [Exports](../modules.md) / ColumnAlteration
# Interface: ColumnAlteration
A definition of a column alteration. The alteration changes the column at
`path` to have the new name `name`, to be nullable if `nullable` is true,
and to have the data type `data_type`. At least one of `rename` or `nullable`
must be provided.
## Table of contents
### Properties
- [nullable](ColumnAlteration.md#nullable)
- [path](ColumnAlteration.md#path)
- [rename](ColumnAlteration.md#rename)
## Properties
### nullable
`Optional` **nullable**: `boolean`
Set the new nullability. Note that a nullable column cannot be made non-nullable.
#### Defined in
[index.ts:638](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L638)
___
### path
**path**: `string`
The path to the column to alter. This is a dot-separated path to the column.
If it is a top-level column then it is just the name of the column. If it is
a nested column then it is the path to the column, e.g. "a.b.c" for a column
`c` nested inside a column `b` nested inside a column `a`.
#### Defined in
[index.ts:633](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L633)
___
### rename
`Optional` **rename**: `string`
#### Defined in
[index.ts:634](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L634)

View File

@@ -22,7 +22,7 @@ fragments added.
#### Defined in
[index.ts:1273](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1273)
[index.ts:933](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L933)
___
@@ -35,7 +35,7 @@ file.
#### Defined in
[index.ts:1268](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1268)
[index.ts:928](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L928)
___
@@ -47,7 +47,7 @@ The number of new fragments that were created.
#### Defined in
[index.ts:1263](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1263)
[index.ts:923](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L923)
___
@@ -59,4 +59,4 @@ The number of fragments that were removed.
#### Defined in
[index.ts:1259](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1259)
[index.ts:919](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L919)

View File

@@ -24,7 +24,7 @@ Default is true.
#### Defined in
[index.ts:1241](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1241)
[index.ts:901](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L901)
___
@@ -38,7 +38,7 @@ the deleted rows. Default is 10%.
#### Defined in
[index.ts:1247](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1247)
[index.ts:907](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L907)
___
@@ -46,11 +46,11 @@ ___
`Optional` **maxRowsPerGroup**: `number`
The maximum number of T per group. Defaults to 1024.
The maximum number of rows per group. Defaults to 1024.
#### Defined in
[index.ts:1235](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1235)
[index.ts:895](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L895)
___
@@ -63,7 +63,7 @@ the number of cores on the machine.
#### Defined in
[index.ts:1252](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1252)
[index.ts:912](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L912)
___
@@ -77,4 +77,4 @@ Defaults to 1024 * 1024.
#### Defined in
[index.ts:1231](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1231)
[index.ts:891](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L891)

View File

@@ -22,7 +22,6 @@ Connection could be local against filesystem or remote against a server.
- [dropTable](Connection.md#droptable)
- [openTable](Connection.md#opentable)
- [tableNames](Connection.md#tablenames)
- [withMiddleware](Connection.md#withmiddleware)
## Properties
@@ -32,7 +31,7 @@ Connection could be local against filesystem or remote against a server.
#### Defined in
[index.ts:261](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L261)
[index.ts:183](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L183)
## Methods
@@ -60,7 +59,7 @@ Creates a new Table, optionally initializing it with new data.
#### Defined in
[index.ts:285](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L285)
[index.ts:207](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L207)
**createTable**(`name`, `data`): `Promise`\<[`Table`](Table.md)\<`number`[]\>\>
@@ -71,7 +70,7 @@ Creates a new Table and initialize it with new data.
| Name | Type | Description |
| :------ | :------ | :------ |
| `name` | `string` | The name of the table. |
| `data` | `Table`\<`any`\> \| `Record`\<`string`, `unknown`\>[] | Non-empty Array of Records to be inserted into the table |
| `data` | `Record`\<`string`, `unknown`\>[] | Non-empty Array of Records to be inserted into the table |
#### Returns
@@ -79,7 +78,7 @@ Creates a new Table and initialize it with new data.
#### Defined in
[index.ts:299](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L299)
[index.ts:221](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L221)
**createTable**(`name`, `data`, `options`): `Promise`\<[`Table`](Table.md)\<`number`[]\>\>
@@ -90,7 +89,7 @@ Creates a new Table and initialize it with new data.
| Name | Type | Description |
| :------ | :------ | :------ |
| `name` | `string` | The name of the table. |
| `data` | `Table`\<`any`\> \| `Record`\<`string`, `unknown`\>[] | Non-empty Array of Records to be inserted into the table |
| `data` | `Record`\<`string`, `unknown`\>[] | Non-empty Array of Records to be inserted into the table |
| `options` | [`WriteOptions`](WriteOptions.md) | The write options to use when creating the table. |
#### Returns
@@ -99,7 +98,7 @@ Creates a new Table and initialize it with new data.
#### Defined in
[index.ts:311](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L311)
[index.ts:233](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L233)
**createTable**\<`T`\>(`name`, `data`, `embeddings`): `Promise`\<[`Table`](Table.md)\<`T`\>\>
@@ -116,7 +115,7 @@ Creates a new Table and initialize it with new data.
| Name | Type | Description |
| :------ | :------ | :------ |
| `name` | `string` | The name of the table. |
| `data` | `Table`\<`any`\> \| `Record`\<`string`, `unknown`\>[] | Non-empty Array of Records to be inserted into the table |
| `data` | `Record`\<`string`, `unknown`\>[] | Non-empty Array of Records to be inserted into the table |
| `embeddings` | [`EmbeddingFunction`](EmbeddingFunction.md)\<`T`\> | An embedding function to use on this table |
#### Returns
@@ -125,7 +124,7 @@ Creates a new Table and initialize it with new data.
#### Defined in
[index.ts:324](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L324)
[index.ts:246](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L246)
**createTable**\<`T`\>(`name`, `data`, `embeddings`, `options`): `Promise`\<[`Table`](Table.md)\<`T`\>\>
@@ -142,7 +141,7 @@ Creates a new Table and initialize it with new data.
| Name | Type | Description |
| :------ | :------ | :------ |
| `name` | `string` | The name of the table. |
| `data` | `Table`\<`any`\> \| `Record`\<`string`, `unknown`\>[] | Non-empty Array of Records to be inserted into the table |
| `data` | `Record`\<`string`, `unknown`\>[] | Non-empty Array of Records to be inserted into the table |
| `embeddings` | [`EmbeddingFunction`](EmbeddingFunction.md)\<`T`\> | An embedding function to use on this table |
| `options` | [`WriteOptions`](WriteOptions.md) | The write options to use when creating the table. |
@@ -152,7 +151,7 @@ Creates a new Table and initialize it with new data.
#### Defined in
[index.ts:337](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L337)
[index.ts:259](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L259)
___
@@ -174,7 +173,7 @@ Drop an existing table.
#### Defined in
[index.ts:348](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L348)
[index.ts:270](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L270)
___
@@ -203,7 +202,7 @@ Open a table in the database.
#### Defined in
[index.ts:271](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L271)
[index.ts:193](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L193)
___
@@ -217,32 +216,4 @@ ___
#### Defined in
[index.ts:263](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L263)
___
### withMiddleware
**withMiddleware**(`middleware`): [`Connection`](Connection.md)
Instrument the behavior of this Connection with middleware.
The middleware will be called in the order they are added.
Currently this functionality is only supported for remote Connections.
#### Parameters
| Name | Type |
| :------ | :------ |
| `middleware` | `HttpMiddleware` |
#### Returns
[`Connection`](Connection.md)
- this Connection instrumented by the passed middleware
#### Defined in
[index.ts:360](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L360)
[index.ts:185](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L185)

View File

@@ -10,10 +10,7 @@
- [awsCredentials](ConnectionOptions.md#awscredentials)
- [awsRegion](ConnectionOptions.md#awsregion)
- [hostOverride](ConnectionOptions.md#hostoverride)
- [readConsistencyInterval](ConnectionOptions.md#readconsistencyinterval)
- [region](ConnectionOptions.md#region)
- [storageOptions](ConnectionOptions.md#storageoptions)
- [timeout](ConnectionOptions.md#timeout)
- [uri](ConnectionOptions.md#uri)
## Properties
@@ -22,13 +19,9 @@
`Optional` **apiKey**: `string`
API key for the remote connections
Can also be passed by setting environment variable `LANCEDB_API_KEY`
#### Defined in
[index.ts:112](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L112)
[index.ts:81](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L81)
___
@@ -40,14 +33,9 @@ User provided AWS crednetials.
If not provided, LanceDB will use the default credentials provider chain.
**`Deprecated`**
Pass `aws_access_key_id`, `aws_secret_access_key`, and `aws_session_token`
through `storageOptions` instead.
#### Defined in
[index.ts:92](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L92)
[index.ts:75](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L75)
___
@@ -55,15 +43,11 @@ ___
`Optional` **awsRegion**: `string`
AWS region to connect to. Default is defaultAwsRegion
**`Deprecated`**
Pass `region` through `storageOptions` instead.
AWS region to connect to. Default is defaultAwsRegion.
#### Defined in
[index.ts:98](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L98)
[index.ts:78](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L78)
___
@@ -71,33 +55,13 @@ ___
`Optional` **hostOverride**: `string`
Override the host URL for the remote connection.
Override the host URL for the remote connections.
This is useful for local testing.
#### Defined in
[index.ts:122](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L122)
___
### readConsistencyInterval
`Optional` **readConsistencyInterval**: `number`
(For LanceDB OSS only): The interval, in seconds, at which to check for
updates to the table from other processes. If None, then consistency is not
checked. For performance reasons, this is the default. For strong
consistency, set this to zero seconds. Then every read will check for
updates from other processes. As a compromise, you can set this to a
non-zero value for eventual consistency. If more than that interval
has passed since the last check, then the table will be checked for updates.
Note: this consistency only applies to read operations. Write operations are
always consistent.
#### Defined in
[index.ts:140](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L140)
[index.ts:91](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L91)
___
@@ -105,37 +69,11 @@ ___
`Optional` **region**: `string`
Region to connect. Default is 'us-east-1'
Region to connect
#### Defined in
[index.ts:115](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L115)
___
### storageOptions
`Optional` **storageOptions**: `Record`\<`string`, `string`\>
User provided options for object storage. For example, S3 credentials or request timeouts.
The various options are described at https://lancedb.github.io/lancedb/guides/storage/
#### Defined in
[index.ts:105](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L105)
___
### timeout
`Optional` **timeout**: `number`
Duration in milliseconds for request timeout. Default = 10,000 (10 seconds)
#### Defined in
[index.ts:127](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L127)
[index.ts:84](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L84)
___
@@ -147,8 +85,8 @@ LanceDB database URI.
- `/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)
- `db://host:port` - remote database (SaaS)
#### Defined in
[index.ts:83](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L83)
[index.ts:69](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L69)

View File

@@ -26,7 +26,7 @@
#### Defined in
[index.ts:163](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L163)
[index.ts:116](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L116)
___
@@ -36,7 +36,7 @@ ___
#### Defined in
[index.ts:169](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L169)
[index.ts:122](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L122)
___
@@ -46,7 +46,7 @@ ___
#### Defined in
[index.ts:160](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L160)
[index.ts:113](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L113)
___
@@ -56,7 +56,7 @@ ___
#### Defined in
[index.ts:166](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L166)
[index.ts:119](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L119)
___
@@ -66,4 +66,4 @@ ___
#### Defined in
[index.ts:172](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L172)
[index.ts:125](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L125)

View File

@@ -18,29 +18,11 @@ An embedding function that automatically creates vector representation for a giv
### Properties
- [destColumn](EmbeddingFunction.md#destcolumn)
- [embed](EmbeddingFunction.md#embed)
- [embeddingDataType](EmbeddingFunction.md#embeddingdatatype)
- [embeddingDimension](EmbeddingFunction.md#embeddingdimension)
- [excludeSource](EmbeddingFunction.md#excludesource)
- [sourceColumn](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/92179835/node/src/embedding/embedding_function.ts#L49)
___
### embed
**embed**: (`data`: `T`[]) => `Promise`\<`number`[][]\>
@@ -63,54 +45,7 @@ Creates a vector representation for the given values.
#### Defined in
[embedding/embedding_function.ts:62](https://github.com/lancedb/lancedb/blob/92179835/node/src/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/92179835/node/src/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/92179835/node/src/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/92179835/node/src/embedding/embedding_function.ts#L57)
[embedding/embedding_function.ts:27](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/embedding/embedding_function.ts#L27)
___
@@ -122,4 +57,4 @@ 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/92179835/node/src/embedding/embedding_function.ts#L24)
[embedding/embedding_function.ts:22](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/embedding/embedding_function.ts#L22)

View File

@@ -6,51 +6,18 @@
### Properties
- [distanceType](IndexStats.md#distancetype)
- [indexType](IndexStats.md#indextype)
- [numIndexedRows](IndexStats.md#numindexedrows)
- [numIndices](IndexStats.md#numindices)
- [numUnindexedRows](IndexStats.md#numunindexedrows)
## Properties
### distanceType
`Optional` **distanceType**: `string`
#### Defined in
[index.ts:728](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L728)
___
### indexType
**indexType**: `string`
#### Defined in
[index.ts:727](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L727)
___
### numIndexedRows
**numIndexedRows**: ``null`` \| `number`
#### Defined in
[index.ts:725](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L725)
___
### numIndices
• `Optional` **numIndices**: `number`
#### Defined in
[index.ts:729](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L729)
[index.ts:478](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L478)
___
@@ -60,4 +27,4 @@ ___
#### Defined in
[index.ts:726](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L726)
[index.ts:479](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L479)

View File

@@ -29,7 +29,7 @@ The column to be indexed
#### Defined in
[index.ts:1282](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1282)
[index.ts:942](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L942)
___
@@ -41,7 +41,7 @@ Cache size of the index
#### Defined in
[index.ts:1331](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1331)
[index.ts:991](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L991)
___
@@ -53,7 +53,7 @@ A unique name for the index
#### Defined in
[index.ts:1287](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1287)
[index.ts:947](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L947)
___
@@ -65,7 +65,7 @@ The max number of iterations for kmeans training.
#### Defined in
[index.ts:1302](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1302)
[index.ts:962](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L962)
___
@@ -77,7 +77,7 @@ Max number of iterations to train OPQ, if `use_opq` is true.
#### Defined in
[index.ts:1321](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1321)
[index.ts:981](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L981)
___
@@ -89,7 +89,7 @@ Metric type, L2 or Cosine
#### Defined in
[index.ts:1292](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1292)
[index.ts:952](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L952)
___
@@ -101,7 +101,7 @@ The number of bits to present one PQ centroid.
#### Defined in
[index.ts:1316](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1316)
[index.ts:976](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L976)
___
@@ -113,7 +113,7 @@ The number of partitions this index
#### Defined in
[index.ts:1297](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1297)
[index.ts:957](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L957)
___
@@ -125,7 +125,7 @@ Number of subvectors to build PQ code
#### Defined in
[index.ts:1312](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1312)
[index.ts:972](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L972)
___
@@ -137,7 +137,7 @@ Replace an existing index with the same name if it exists.
#### Defined in
[index.ts:1326](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1326)
[index.ts:986](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L986)
___
@@ -147,7 +147,7 @@ ___
#### Defined in
[index.ts:1333](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1333)
[index.ts:993](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L993)
___
@@ -159,4 +159,4 @@ Train as optimized product quantization.
#### Defined in
[index.ts:1307](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1307)
[index.ts:967](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L967)

View File

@@ -1,73 +0,0 @@
[vectordb](../README.md) / [Exports](../modules.md) / MergeInsertArgs
# Interface: MergeInsertArgs
## Table of contents
### Properties
- [whenMatchedUpdateAll](MergeInsertArgs.md#whenmatchedupdateall)
- [whenNotMatchedBySourceDelete](MergeInsertArgs.md#whennotmatchedbysourcedelete)
- [whenNotMatchedInsertAll](MergeInsertArgs.md#whennotmatchedinsertall)
## Properties
### whenMatchedUpdateAll
`Optional` **whenMatchedUpdateAll**: `string` \| `boolean`
If true then 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.
If there are multiple matches then the behavior is undefined.
Currently this causes multiple copies of the row to be created
but that behavior is subject to change.
Optionally, a filter can be specified. This should be an SQL
filter where fields with the prefix "target." refer to fields
in the target table (old data) and fields with the prefix
"source." refer to fields in the source table (new data). For
example, the filter "target.lastUpdated < source.lastUpdated" will
only update matched rows when the incoming `lastUpdated` value is
newer.
Rows that do not match the filter will not be updated. Rows that
do not match the filter do become "not matched" rows.
#### Defined in
[index.ts:690](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L690)
___
### whenNotMatchedBySourceDelete
`Optional` **whenNotMatchedBySourceDelete**: `string` \| `boolean`
If true then rows that exist only in the target table (old data)
will be deleted.
If this is a string then it will be treated as an SQL filter and
only rows that both do not match any row in the source table and
match the given filter will be deleted.
This can be used to replace a selection of existing data with
new data.
#### Defined in
[index.ts:707](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L707)
___
### whenNotMatchedInsertAll
`Optional` **whenNotMatchedInsertAll**: `boolean`
If true then rows that exist only in the source table (new data)
will be inserted into the target table.
#### Defined in
[index.ts:695](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L695)

View File

@@ -25,26 +25,17 @@ A LanceDB Table is the collection of Records. Each Record has one or more vector
- [delete](Table.md#delete)
- [indexStats](Table.md#indexstats)
- [listIndices](Table.md#listindices)
- [mergeInsert](Table.md#mergeinsert)
- [name](Table.md#name)
- [overwrite](Table.md#overwrite)
- [schema](Table.md#schema)
- [search](Table.md#search)
- [update](Table.md#update)
### Methods
- [addColumns](Table.md#addcolumns)
- [alterColumns](Table.md#altercolumns)
- [dropColumns](Table.md#dropcolumns)
- [filter](Table.md#filter)
- [withMiddleware](Table.md#withmiddleware)
## Properties
### add
**add**: (`data`: `Table`\<`any`\> \| `Record`\<`string`, `unknown`\>[]) => `Promise`\<`number`\>
**add**: (`data`: `Record`\<`string`, `unknown`\>[]) => `Promise`\<`number`\>
#### Type declaration
@@ -56,7 +47,7 @@ Insert records into this Table.
| Name | Type | Description |
| :------ | :------ | :------ |
| `data` | `Table`\<`any`\> \| `Record`\<`string`, `unknown`\>[] | Records to be inserted into the Table |
| `data` | `Record`\<`string`, `unknown`\>[] | Records to be inserted into the Table |
##### Returns
@@ -66,33 +57,27 @@ The number of rows added to the table
#### Defined in
[index.ts:381](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L381)
[index.ts:291](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L291)
___
### countRows
**countRows**: (`filter?`: `string`) => `Promise`\<`number`\>
**countRows**: () => `Promise`\<`number`\>
#### Type declaration
▸ (`filter?`): `Promise`\<`number`\>
▸ (): `Promise`\<`number`\>
Returns the number of rows in this table.
##### Parameters
| Name | Type |
| :------ | :------ |
| `filter?` | `string` |
##### Returns
`Promise`\<`number`\>
#### Defined in
[index.ts:454](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L454)
[index.ts:361](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L361)
___
@@ -122,17 +107,17 @@ VectorIndexParams.
#### Defined in
[index.ts:398](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L398)
[index.ts:306](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L306)
___
### createScalarIndex
**createScalarIndex**: (`column`: `string`, `replace?`: `boolean`) => `Promise`\<`void`\>
**createScalarIndex**: (`column`: `string`, `replace`: `boolean`) => `Promise`\<`void`\>
#### Type declaration
▸ (`column`, `replace?`): `Promise`\<`void`\>
▸ (`column`, `replace`): `Promise`\<`void`\>
Create a scalar index on this Table for the given column
@@ -141,7 +126,7 @@ Create a scalar index on this Table for the given column
| Name | Type | Description |
| :------ | :------ | :------ |
| `column` | `string` | The column to index |
| `replace?` | `boolean` | If false, fail if an index already exists on the column it is always set to true for remote connections Scalar indices, like vector indices, can be used to speed up scans. A scalar index can speed up scans that contain filter expressions on the indexed column. For example, the following scan will be faster if the column `my_col` has a scalar index: ```ts const con = await lancedb.connect('./.lancedb'); const table = await con.openTable('images'); const results = await table.where('my_col = 7').execute(); ``` Scalar indices can also speed up scans containing a vector search and a prefilter: ```ts const con = await lancedb.connect('././lancedb'); const table = await con.openTable('images'); const results = await table.search([1.0, 2.0]).where('my_col != 7').prefilter(true); ``` Scalar indices can only speed up scans for basic filters using equality, comparison, range (e.g. `my_col BETWEEN 0 AND 100`), and set membership (e.g. `my_col IN (0, 1, 2)`) Scalar indices can be used if the filter contains multiple indexed columns and the filter criteria are AND'd or OR'd together (e.g. `my_col < 0 AND other_col> 100`) Scalar indices may be used if the filter contains non-indexed columns but, depending on the structure of the filter, they may not be usable. For example, if the column `not_indexed` does not have a scalar index then the filter `my_col = 0 OR not_indexed = 1` will not be able to use any scalar index on `my_col`. |
| `replace` | `boolean` | If false, fail if an index already exists on the column Scalar indices, like vector indices, can be used to speed up scans. A scalar index can speed up scans that contain filter expressions on the indexed column. For example, the following scan will be faster if the column `my_col` has a scalar index: ```ts const con = await lancedb.connect('./.lancedb'); const table = await con.openTable('images'); const results = await table.where('my_col = 7').execute(); ``` Scalar indices can also speed up scans containing a vector search and a prefilter: ```ts const con = await lancedb.connect('././lancedb'); const table = await con.openTable('images'); const results = await table.search([1.0, 2.0]).where('my_col != 7').prefilter(true); ``` Scalar indices can only speed up scans for basic filters using equality, comparison, range (e.g. `my_col BETWEEN 0 AND 100`), and set membership (e.g. `my_col IN (0, 1, 2)`) Scalar indices can be used if the filter contains multiple indexed columns and the filter criteria are AND'd or OR'd together (e.g. `my_col < 0 AND other_col> 100`) Scalar indices may be used if the filter contains non-indexed columns but, depending on the structure of the filter, they may not be usable. For example, if the column `not_indexed` does not have a scalar index then the filter `my_col = 0 OR not_indexed = 1` will not be able to use any scalar index on `my_col`. |
##### Returns
@@ -157,7 +142,7 @@ await table.createScalarIndex('my_col')
#### Defined in
[index.ts:449](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L449)
[index.ts:356](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L356)
___
@@ -209,17 +194,17 @@ await tbl.countRows() // Returns 1
#### Defined in
[index.ts:488](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L488)
[index.ts:395](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L395)
___
### indexStats
• **indexStats**: (`indexName`: `string`) => `Promise`\<[`IndexStats`](IndexStats.md)\>
• **indexStats**: (`indexUuid`: `string`) => `Promise`\<[`IndexStats`](IndexStats.md)\>
#### Type declaration
▸ (`indexName`): `Promise`\<[`IndexStats`](IndexStats.md)\>
▸ (`indexUuid`): `Promise`\<[`IndexStats`](IndexStats.md)\>
Get statistics about an index.
@@ -227,7 +212,7 @@ Get statistics about an index.
| Name | Type |
| :------ | :------ |
| `indexName` | `string` |
| `indexUuid` | `string` |
##### Returns
@@ -235,7 +220,7 @@ Get statistics about an index.
#### Defined in
[index.ts:567](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L567)
[index.ts:438](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L438)
___
@@ -255,57 +240,7 @@ List the indicies on this table.
#### Defined in
[index.ts:562](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L562)
___
### mergeInsert
• **mergeInsert**: (`on`: `string`, `data`: `Table`\<`any`\> \| `Record`\<`string`, `unknown`\>[], `args`: [`MergeInsertArgs`](MergeInsertArgs.md)) => `Promise`\<`void`\>
#### Type declaration
▸ (`on`, `data`, `args`): `Promise`\<`void`\>
Runs a "merge insert" operation on the table
This operation can add rows, update rows, and remove rows all in a single
transaction. It is a very generic tool that can be used to create
behaviors like "insert if not exists", "update or insert (i.e. upsert)",
or even replace a portion of existing data with new data (e.g. replace
all data where month="january")
The merge insert operation works by combining new data from a
**source table** with existing data in a **target table** by using a
join. There are three categories of records.
"Matched" records are records that exist in both the source table and
the target table. "Not matched" records exist only in the source table
(e.g. these are new data) "Not matched by source" records exist only
in the target table (this is old data)
The MergeInsertArgs can be used to customize what should happen for
each category of data.
Please note that the data may appear to be reordered as part of this
operation. This is because updated rows will be deleted from the
dataset and then reinserted at the end with the new values.
##### Parameters
| Name | Type | Description |
| :------ | :------ | :------ |
| `on` | `string` | a column to join on. This is how records from the source table and target table are matched. |
| `data` | `Table`\<`any`\> \| `Record`\<`string`, `unknown`\>[] | the new data to insert |
| `args` | [`MergeInsertArgs`](MergeInsertArgs.md) | parameters controlling how the operation should behave |
##### Returns
`Promise`\<`void`\>
#### Defined in
[index.ts:553](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L553)
[index.ts:433](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L433)
___
@@ -315,13 +250,13 @@ ___
#### Defined in
[index.ts:367](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L367)
[index.ts:277](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L277)
___
### overwrite
• **overwrite**: (`data`: `Table`\<`any`\> \| `Record`\<`string`, `unknown`\>[]) => `Promise`\<`number`\>
• **overwrite**: (`data`: `Record`\<`string`, `unknown`\>[]) => `Promise`\<`number`\>
#### Type declaration
@@ -333,7 +268,7 @@ Insert records into this Table, replacing its contents.
| Name | Type | Description |
| :------ | :------ | :------ |
| `data` | `Table`\<`any`\> \| `Record`\<`string`, `unknown`\>[] | Records to be inserted into the Table |
| `data` | `Record`\<`string`, `unknown`\>[] | Records to be inserted into the Table |
##### Returns
@@ -343,7 +278,7 @@ The number of rows added to the table
#### Defined in
[index.ts:389](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L389)
[index.ts:299](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L299)
___
@@ -353,7 +288,7 @@ ___
#### Defined in
[index.ts:571](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L571)
[index.ts:440](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L440)
___
@@ -379,7 +314,7 @@ Creates a search query to find the nearest neighbors of the given search term
#### Defined in
[index.ts:373](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L373)
[index.ts:283](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L283)
___
@@ -430,123 +365,4 @@ let results = await tbl.search([1, 1]).execute();
#### Defined in
[index.ts:521](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L521)
## Methods
### addColumns
▸ **addColumns**(`newColumnTransforms`): `Promise`\<`void`\>
Add new columns with defined values.
#### Parameters
| Name | Type | Description |
| :------ | :------ | :------ |
| `newColumnTransforms` | \{ `name`: `string` ; `valueSql`: `string` }[] | pairs of column names and the SQL expression to use to calculate the value of the new column. These expressions will be evaluated for each row in the table, and can reference existing columns in the table. |
#### Returns
`Promise`\<`void`\>
#### Defined in
[index.ts:582](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L582)
___
### alterColumns
▸ **alterColumns**(`columnAlterations`): `Promise`\<`void`\>
Alter the name or nullability of columns.
#### Parameters
| Name | Type | Description |
| :------ | :------ | :------ |
| `columnAlterations` | [`ColumnAlteration`](ColumnAlteration.md)[] | One or more alterations to apply to columns. |
#### Returns
`Promise`\<`void`\>
#### Defined in
[index.ts:591](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L591)
___
### dropColumns
▸ **dropColumns**(`columnNames`): `Promise`\<`void`\>
Drop one or more columns from the dataset
This is a metadata-only operation and does not remove the data from the
underlying storage. In order to remove the data, you must subsequently
call ``compact_files`` to rewrite the data without the removed columns and
then call ``cleanup_files`` to remove the old files.
#### Parameters
| Name | Type | Description |
| :------ | :------ | :------ |
| `columnNames` | `string`[] | The names of the columns to drop. These can be nested column references (e.g. "a.b.c") or top-level column names (e.g. "a"). |
#### Returns
`Promise`\<`void`\>
#### Defined in
[index.ts:605](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L605)
___
### filter
▸ **filter**(`value`): [`Query`](../classes/Query.md)\<`T`\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `value` | `string` |
#### Returns
[`Query`](../classes/Query.md)\<`T`\>
#### Defined in
[index.ts:569](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L569)
___
### withMiddleware
▸ **withMiddleware**(`middleware`): [`Table`](Table.md)\<`T`\>
Instrument the behavior of this Table with middleware.
The middleware will be called in the order they are added.
Currently this functionality is only supported for remote tables.
#### Parameters
| Name | Type |
| :------ | :------ |
| `middleware` | `HttpMiddleware` |
#### Returns
[`Table`](Table.md)\<`T`\>
- this Table instrumented by the passed middleware
#### Defined in
[index.ts:617](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L617)
[index.ts:428](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L428)

View File

@@ -20,7 +20,7 @@ new values to set
#### Defined in
[index.ts:652](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L652)
[index.ts:454](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L454)
___
@@ -33,4 +33,4 @@ in which case all rows will be updated.
#### Defined in
[index.ts:646](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L646)
[index.ts:448](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L448)

View File

@@ -20,7 +20,7 @@ new values to set as SQL expressions.
#### Defined in
[index.ts:666](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L666)
[index.ts:468](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L468)
___
@@ -33,4 +33,4 @@ in which case all rows will be updated.
#### Defined in
[index.ts:660](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L660)
[index.ts:462](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L462)

View File

@@ -8,7 +8,6 @@
- [columns](VectorIndex.md#columns)
- [name](VectorIndex.md#name)
- [status](VectorIndex.md#status)
- [uuid](VectorIndex.md#uuid)
## Properties
@@ -19,7 +18,7 @@
#### Defined in
[index.ts:718](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L718)
[index.ts:472](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L472)
___
@@ -29,17 +28,7 @@ ___
#### Defined in
[index.ts:719](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L719)
___
### status
**status**: [`IndexStatus`](../enums/IndexStatus.md)
#### Defined in
[index.ts:721](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L721)
[index.ts:473](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L473)
___
@@ -49,4 +38,4 @@ ___
#### Defined in
[index.ts:720](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L720)
[index.ts:474](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L474)

View File

@@ -24,4 +24,4 @@ A [WriteMode](../enums/WriteMode.md) to use on this operation
#### Defined in
[index.ts:1355](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1355)
[index.ts:1015](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L1015)

View File

@@ -6,7 +6,6 @@
### Enumerations
- [IndexStatus](enums/IndexStatus.md)
- [MetricType](enums/MetricType.md)
- [WriteMode](enums/WriteMode.md)
@@ -15,7 +14,6 @@
- [DefaultWriteOptions](classes/DefaultWriteOptions.md)
- [LocalConnection](classes/LocalConnection.md)
- [LocalTable](classes/LocalTable.md)
- [MakeArrowTableOptions](classes/MakeArrowTableOptions.md)
- [OpenAIEmbeddingFunction](classes/OpenAIEmbeddingFunction.md)
- [Query](classes/Query.md)
@@ -23,7 +21,6 @@
- [AwsCredentials](interfaces/AwsCredentials.md)
- [CleanupStats](interfaces/CleanupStats.md)
- [ColumnAlteration](interfaces/ColumnAlteration.md)
- [CompactionMetrics](interfaces/CompactionMetrics.md)
- [CompactionOptions](interfaces/CompactionOptions.md)
- [Connection](interfaces/Connection.md)
@@ -32,7 +29,6 @@
- [EmbeddingFunction](interfaces/EmbeddingFunction.md)
- [IndexStats](interfaces/IndexStats.md)
- [IvfPQIndexConfig](interfaces/IvfPQIndexConfig.md)
- [MergeInsertArgs](interfaces/MergeInsertArgs.md)
- [Table](interfaces/Table.md)
- [UpdateArgs](interfaces/UpdateArgs.md)
- [UpdateSqlArgs](interfaces/UpdateSqlArgs.md)
@@ -46,9 +42,7 @@
### Functions
- [connect](modules.md#connect)
- [convertToTable](modules.md#converttotable)
- [isWriteOptions](modules.md#iswriteoptions)
- [makeArrowTable](modules.md#makearrowtable)
## Type Aliases
@@ -58,7 +52,7 @@
#### Defined in
[index.ts:1336](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1336)
[index.ts:996](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L996)
## Functions
@@ -68,11 +62,11 @@
Connect to a LanceDB instance at the given URI.
Accepted formats:
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)
- `db://host:port` - remote database (SaaS)
#### Parameters
@@ -90,7 +84,7 @@ Accepted formats:
#### Defined in
[index.ts:188](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L188)
[index.ts:141](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L141)
**connect**(`opts`): `Promise`\<[`Connection`](interfaces/Connection.md)\>
@@ -108,35 +102,7 @@ Connect to a LanceDB instance with connection options.
#### Defined in
[index.ts:194](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L194)
___
### convertToTable
**convertToTable**\<`T`\>(`data`, `embeddings?`, `makeTableOptions?`): `Promise`\<`ArrowTable`\>
#### Type parameters
| Name |
| :------ |
| `T` |
#### Parameters
| Name | Type |
| :------ | :------ |
| `data` | `Record`\<`string`, `unknown`\>[] |
| `embeddings?` | [`EmbeddingFunction`](interfaces/EmbeddingFunction.md)\<`T`\> |
| `makeTableOptions?` | `Partial`\<[`MakeArrowTableOptions`](classes/MakeArrowTableOptions.md)\> |
#### Returns
`Promise`\<`ArrowTable`\>
#### Defined in
[arrow.ts:465](https://github.com/lancedb/lancedb/blob/92179835/node/src/arrow.ts#L465)
[index.ts:147](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L147)
___
@@ -156,116 +122,4 @@ value is WriteOptions
#### Defined in
[index.ts:1362](https://github.com/lancedb/lancedb/blob/92179835/node/src/index.ts#L1362)
___
### makeArrowTable
**makeArrowTable**(`data`, `options?`): `ArrowTable`
An enhanced version of the makeTable function from Apache Arrow
that supports nested fields and embeddings columns.
This function converts an array of Record<String, any> (row-major JS objects)
to an Arrow Table (a columnar structure)
Note that it currently does not support nulls.
If a schema is provided then it will be used to determine the resulting array
types. Fields will also be reordered to fit the order defined by the schema.
If a schema is not provided then the types will be inferred and the field order
will be controlled by the order of properties in the first record.
If the input is empty then a schema must be provided to create an empty table.
When a schema is not specified then data types will be inferred. The inference
rules are as follows:
- boolean => Bool
- number => Float64
- String => Utf8
- Buffer => Binary
- Record<String, any> => Struct
- Array<any> => List
#### Parameters
| Name | Type | Description |
| :------ | :------ | :------ |
| `data` | `Record`\<`string`, `any`\>[] | input data |
| `options?` | `Partial`\<[`MakeArrowTableOptions`](classes/MakeArrowTableOptions.md)\> | options to control the makeArrowTable call. |
#### Returns
`ArrowTable`
**`Example`**
```ts
import { fromTableToBuffer, makeArrowTable } from "../arrow";
import { Field, FixedSizeList, Float16, Float32, Int32, Schema } from "apache-arrow";
const schema = new Schema([
new Field("a", new Int32()),
new Field("b", new Float32()),
new Field("c", new FixedSizeList(3, new Field("item", new Float16()))),
]);
const table = makeArrowTable([
{ a: 1, b: 2, c: [1, 2, 3] },
{ a: 4, b: 5, c: [4, 5, 6] },
{ a: 7, b: 8, c: [7, 8, 9] },
], { schema });
```
By default it assumes that the column named `vector` is a vector column
and it will be converted into a fixed size list array of type float32.
The `vectorColumns` option can be used to support other vector column
names and data types.
```ts
const schema = new Schema([
new Field("a", new Float64()),
new Field("b", new Float64()),
new Field(
"vector",
new FixedSizeList(3, new Field("item", new Float32()))
),
]);
const table = makeArrowTable([
{ a: 1, b: 2, vector: [1, 2, 3] },
{ a: 4, b: 5, vector: [4, 5, 6] },
{ a: 7, b: 8, vector: [7, 8, 9] },
]);
assert.deepEqual(table.schema, schema);
```
You can specify the vector column types and names using the options as well
```typescript
const schema = new Schema([
new Field('a', new Float64()),
new Field('b', new Float64()),
new Field('vec1', new FixedSizeList(3, new Field('item', new Float16()))),
new Field('vec2', new FixedSizeList(3, new Field('item', new Float16())))
]);
const table = makeArrowTable([
{ a: 1, b: 2, vec1: [1, 2, 3], vec2: [2, 4, 6] },
{ a: 4, b: 5, vec1: [4, 5, 6], vec2: [8, 10, 12] },
{ a: 7, b: 8, vec1: [7, 8, 9], vec2: [14, 16, 18] }
], {
vectorColumns: {
vec1: { type: new Float16() },
vec2: { type: new Float16() }
}
}
assert.deepEqual(table.schema, schema)
```
#### Defined in
[arrow.ts:198](https://github.com/lancedb/lancedb/blob/92179835/node/src/arrow.ts#L198)
[index.ts:1022](https://github.com/lancedb/lancedb/blob/c89d5e6/node/src/index.ts#L1022)

1
docs/src/js/.nojekyll Normal file
View File

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

View File

@@ -27,9 +27,7 @@ the underlying connection has been closed.
### new Connection()
```ts
new Connection(): Connection
```
> **new Connection**(): [`Connection`](Connection.md)
#### Returns
@@ -39,9 +37,7 @@ new Connection(): Connection
### close()
```ts
abstract close(): void
```
> `abstract` **close**(): `void`
Close the connection, releasing any underlying resources.
@@ -57,24 +53,21 @@ Any attempt to use the connection after it is closed will result in an error.
### createEmptyTable()
```ts
abstract createEmptyTable(
name,
schema,
options?): Promise<Table>
```
> `abstract` **createEmptyTable**(`name`, `schema`, `options`?): `Promise`&lt;[`Table`](Table.md)&gt;
Creates a new empty Table
#### Parameters
* **name**: `string`
The name of the table.
**name**: `string`
* **schema**: `SchemaLike`
The schema of the table
The name of the table.
* **options?**: `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
**schema**: `SchemaLike`
The schema of the table
**options?**: `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
#### Returns
@@ -86,16 +79,15 @@ Creates a new empty Table
#### createTable(options)
```ts
abstract createTable(options): Promise<Table>
```
> `abstract` **createTable**(`options`): `Promise`&lt;[`Table`](Table.md)&gt;
Creates a new Table and initialize it with new data.
##### Parameters
* **options**: `object` & `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
The options object.
**options**: `object` & `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
The options object.
##### Returns
@@ -103,25 +95,22 @@ Creates a new Table and initialize it with new data.
#### createTable(name, data, options)
```ts
abstract createTable(
name,
data,
options?): Promise<Table>
```
> `abstract` **createTable**(`name`, `data`, `options`?): `Promise`&lt;[`Table`](Table.md)&gt;
Creates a new Table and initialize it with new data.
##### Parameters
* **name**: `string`
The name of the table.
**name**: `string`
* **data**: `TableLike` \| `Record`&lt;`string`, `unknown`&gt;[]
Non-empty Array of Records
to be inserted into the table
The name of the table.
* **options?**: `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
**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
@@ -131,9 +120,7 @@ Creates a new Table and initialize it with new data.
### display()
```ts
abstract display(): string
```
> `abstract` **display**(): `string`
Return a brief description of the connection
@@ -145,16 +132,15 @@ Return a brief description of the connection
### dropTable()
```ts
abstract dropTable(name): Promise<void>
```
> `abstract` **dropTable**(`name`): `Promise`&lt;`void`&gt;
Drop an existing table.
#### Parameters
* **name**: `string`
The name of the table to drop.
**name**: `string`
The name of the table to drop.
#### Returns
@@ -164,9 +150,7 @@ Drop an existing table.
### isOpen()
```ts
abstract isOpen(): boolean
```
> `abstract` **isOpen**(): `boolean`
Return true if the connection has not been closed
@@ -178,18 +162,17 @@ Return true if the connection has not been closed
### openTable()
```ts
abstract openTable(name, options?): Promise<Table>
```
> `abstract` **openTable**(`name`, `options`?): `Promise`&lt;[`Table`](Table.md)&gt;
Open a table in the database.
#### Parameters
* **name**: `string`
The name of the table
**name**: `string`
* **options?**: `Partial`&lt;`OpenTableOptions`&gt;
The name of the table
**options?**: `Partial`&lt;`OpenTableOptions`&gt;
#### Returns
@@ -199,9 +182,7 @@ Open a table in the database.
### tableNames()
```ts
abstract tableNames(options?): Promise<string[]>
```
> `abstract` **tableNames**(`options`?): `Promise`&lt;`string`[]&gt;
List all the table names in this database.
@@ -209,9 +190,10 @@ Tables will be returned in lexicographical order.
#### Parameters
* **options?**: `Partial`&lt;[`TableNamesOptions`](../interfaces/TableNamesOptions.md)&gt;
options to control the
paging / start point
**options?**: `Partial`&lt;[`TableNamesOptions`](../interfaces/TableNamesOptions.md)&gt;
options to control the
paging / start point
#### Returns

View File

@@ -8,30 +8,9 @@
## Methods
### bitmap()
```ts
static bitmap(): Index
```
Create a bitmap index.
A `Bitmap` index stores a bitmap for each distinct value in the column for every row.
This index works best for low-cardinality columns, where the number of unique values
is small (i.e., less than a few hundreds).
#### Returns
[`Index`](Index.md)
***
### btree()
```ts
static btree(): Index
```
> `static` **btree**(): [`Index`](Index.md)
Create a btree index
@@ -57,82 +36,9 @@ block size may be added in the future.
***
### fts()
```ts
static fts(options?): Index
```
Create a full text search index
A full text search index is an index on a string column, so that you can conduct full
text searches on the column.
The results of a full text search are ordered by relevance measured by BM25.
You can combine filters with full text search.
For now, the full text search index only supports English, and doesn't support phrase search.
#### Parameters
* **options?**: `Partial`&lt;`FtsOptions`&gt;
#### Returns
[`Index`](Index.md)
***
### hnswPq()
```ts
static hnswPq(options?): Index
```
Create a hnswPq index
HNSW-PQ stands for Hierarchical Navigable Small World - Product Quantization.
It is a variant of the HNSW algorithm that uses product quantization to compress
the vectors.
#### Parameters
* **options?**: `Partial`&lt;`HnswPqOptions`&gt;
#### Returns
[`Index`](Index.md)
***
### hnswSq()
```ts
static hnswSq(options?): Index
```
Create a hnswSq index
HNSW-SQ stands for Hierarchical Navigable Small World - Scalar Quantization.
It is a variant of the HNSW algorithm that uses scalar quantization to compress
the vectors.
#### Parameters
* **options?**: `Partial`&lt;`HnswSqOptions`&gt;
#### Returns
[`Index`](Index.md)
***
### ivfPq()
```ts
static ivfPq(options?): Index
```
> `static` **ivfPq**(`options`?): [`Index`](Index.md)
Create an IvfPq index
@@ -157,25 +63,29 @@ currently is also a memory intensive operation.
#### Parameters
* **options?**: `Partial`&lt;[`IvfPqOptions`](../interfaces/IvfPqOptions.md)&gt;
**options?**: `Partial`&lt;[`IvfPqOptions`](../interfaces/IvfPqOptions.md)&gt;
#### Returns
[`Index`](Index.md)
***
### fts()
### labelList()
> `static` **fts**(`options`?): [`Index`](Index.md)
```ts
static labelList(): Index
```
Create a full text search index
Create a label list index.
This index is used to search for text data. The index is created by tokenizing the text
into words and then storing occurrences of these words in a data structure called inverted index
that allows for fast search.
LabelList index is a scalar index that can be used on `List<T>` columns to
support queries with `array_contains_all` and `array_contains_any`
using an underlying bitmap index.
During a search the query is tokenized and the inverted index is used to find the rows that
contain the query words. The rows are then scored based on BM25 and the top scoring rows are
sorted and returned.
#### Parameters
**options?**: `Partial`&lt;[`FtsOptions`](../interfaces/FtsOptions.md)&gt;
#### Returns

View File

@@ -12,13 +12,11 @@ Options to control the makeArrowTable call.
### new MakeArrowTableOptions()
```ts
new MakeArrowTableOptions(values?): MakeArrowTableOptions
```
> **new MakeArrowTableOptions**(`values`?): [`MakeArrowTableOptions`](MakeArrowTableOptions.md)
#### Parameters
* **values?**: `Partial`&lt;[`MakeArrowTableOptions`](MakeArrowTableOptions.md)&gt;
**values?**: `Partial`&lt;[`MakeArrowTableOptions`](MakeArrowTableOptions.md)&gt;
#### Returns
@@ -28,9 +26,7 @@ new MakeArrowTableOptions(values?): MakeArrowTableOptions
### dictionaryEncodeStrings
```ts
dictionaryEncodeStrings: boolean = false;
```
> **dictionaryEncodeStrings**: `boolean` = `false`
If true then string columns will be encoded with dictionary encoding
@@ -44,30 +40,22 @@ If `schema` is provided then this property is ignored.
### embeddingFunction?
```ts
optional embeddingFunction: EmbeddingFunctionConfig;
```
> `optional` **embeddingFunction**: [`EmbeddingFunctionConfig`](../namespaces/embedding/interfaces/EmbeddingFunctionConfig.md)
***
### embeddings?
```ts
optional embeddings: EmbeddingFunction<unknown, FunctionOptions>;
```
> `optional` **embeddings**: [`EmbeddingFunction`](../namespaces/embedding/classes/EmbeddingFunction.md)&lt;`unknown`, `FunctionOptions`&gt;
***
### schema?
```ts
optional schema: SchemaLike;
```
> `optional` **schema**: `SchemaLike`
***
### vectorColumns
```ts
vectorColumns: Record<string, VectorColumnOptions>;
```
> **vectorColumns**: `Record`&lt;`string`, [`VectorColumnOptions`](VectorColumnOptions.md)&gt;

View File

@@ -16,13 +16,11 @@ A builder for LanceDB queries.
### new Query()
```ts
new Query(tbl): Query
```
> **new Query**(`tbl`): [`Query`](Query.md)
#### Parameters
* **tbl**: `Table`
**tbl**: `Table`
#### Returns
@@ -36,9 +34,7 @@ new Query(tbl): Query
### inner
```ts
protected inner: Query | Promise<Query>;
```
> `protected` **inner**: `Query` \| `Promise`&lt;`Query`&gt;
#### Inherited from
@@ -48,9 +44,7 @@ protected inner: Query | Promise<Query>;
### \[asyncIterator\]()
```ts
asyncIterator: AsyncIterator<RecordBatch<any>, any, undefined>
```
> **\[asyncIterator\]**(): `AsyncIterator`&lt;`RecordBatch`&lt;`any`&gt;, `any`, `undefined`&gt;
#### Returns
@@ -64,13 +58,11 @@ asyncIterator: AsyncIterator<RecordBatch<any>, any, undefined>
### doCall()
```ts
protected doCall(fn): void
```
> `protected` **doCall**(`fn`): `void`
#### Parameters
* **fn**
**fn**
#### Returns
@@ -84,15 +76,13 @@ protected doCall(fn): void
### execute()
```ts
protected execute(options?): RecordBatchIterator
```
> `protected` **execute**(`options`?): [`RecordBatchIterator`](RecordBatchIterator.md)
Execute the query and return the results as an
#### Parameters
* **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
**options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
#### Returns
@@ -118,16 +108,15 @@ single query)
### explainPlan()
```ts
explainPlan(verbose): Promise<string>
```
> **explainPlan**(`verbose`): `Promise`&lt;`string`&gt;
Generates an explanation of the query execution plan.
#### Parameters
* **verbose**: `boolean` = `false`
If true, provides a more detailed explanation. Defaults to false.
**verbose**: `boolean` = `false`
If true, provides a more detailed explanation. Defaults to false.
#### Returns
@@ -152,38 +141,15 @@ const plan = await table.query().nearestTo([0.5, 0.2]).explainPlan();
***
### fastSearch()
```ts
fastSearch(): this
```
Skip searching un-indexed data. This can make search faster, but will miss
any data that is not yet indexed.
Use lancedb.Table#optimize to index all un-indexed data.
#### Returns
`this`
#### Inherited from
[`QueryBase`](QueryBase.md).[`fastSearch`](QueryBase.md#fastsearch)
***
### ~~filter()~~
```ts
filter(predicate): this
```
> **filter**(`predicate`): `this`
A filter statement to be applied to this query.
#### Parameters
* **predicate**: `string`
**predicate**: `string`
#### Returns
@@ -203,33 +169,9 @@ Use `where` instead
***
### fullTextSearch()
```ts
fullTextSearch(query, options?): this
```
#### Parameters
* **query**: `string`
* **options?**: `Partial`&lt;`FullTextSearchOptions`&gt;
#### Returns
`this`
#### Inherited from
[`QueryBase`](QueryBase.md).[`fullTextSearch`](QueryBase.md#fulltextsearch)
***
### limit()
```ts
limit(limit): this
```
> **limit**(`limit`): `this`
Set the maximum number of results to return.
@@ -238,7 +180,7 @@ called then every valid row from the table will be returned.
#### Parameters
* **limit**: `number`
**limit**: `number`
#### Returns
@@ -252,13 +194,11 @@ called then every valid row from the table will be returned.
### nativeExecute()
```ts
protected nativeExecute(options?): Promise<RecordBatchIterator>
```
> `protected` **nativeExecute**(`options`?): `Promise`&lt;`RecordBatchIterator`&gt;
#### Parameters
* **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
**options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
#### Returns
@@ -272,9 +212,7 @@ protected nativeExecute(options?): Promise<RecordBatchIterator>
### nearestTo()
```ts
nearestTo(vector): VectorQuery
```
> **nearestTo**(`vector`): [`VectorQuery`](VectorQuery.md)
Find the nearest vectors to the given query vector.
@@ -294,7 +232,7 @@ If there is more than one vector column you must use
#### Parameters
* **vector**: `IntoVector`
**vector**: `IntoVector`
#### Returns
@@ -326,49 +264,9 @@ a default `limit` of 10 will be used.
***
### nearestToText()
```ts
nearestToText(query, columns?): Query
```
#### Parameters
* **query**: `string`
* **columns?**: `string`[]
#### Returns
[`Query`](Query.md)
***
### offset()
```ts
offset(offset): this
```
#### Parameters
* **offset**: `number`
#### Returns
`this`
#### Inherited from
[`QueryBase`](QueryBase.md).[`offset`](QueryBase.md#offset)
***
### select()
```ts
select(columns): this
```
> **select**(`columns`): `this`
Return only the specified columns.
@@ -392,7 +290,7 @@ input to this method would be:
#### Parameters
* **columns**: `string` \| `string`[] \| `Record`&lt;`string`, `string`&gt; \| `Map`&lt;`string`, `string`&gt;
**columns**: `string` \| `string`[] \| `Record`&lt;`string`, `string`&gt; \| `Map`&lt;`string`, `string`&gt;
#### Returns
@@ -419,15 +317,13 @@ object insertion order is easy to get wrong and `Map` is more foolproof.
### toArray()
```ts
toArray(options?): Promise<any[]>
```
> **toArray**(`options`?): `Promise`&lt;`any`[]&gt;
Collect the results as an array of objects.
#### Parameters
* **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
**options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
#### Returns
@@ -441,15 +337,13 @@ Collect the results as an array of objects.
### toArrow()
```ts
toArrow(options?): Promise<Table<any>>
```
> **toArrow**(`options`?): `Promise`&lt;`Table`&lt;`any`&gt;&gt;
Collect the results as an Arrow
#### Parameters
* **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
**options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
#### Returns
@@ -467,9 +361,7 @@ ArrowTable.
### where()
```ts
where(predicate): this
```
> **where**(`predicate`): `this`
A filter statement to be applied to this query.
@@ -477,7 +369,7 @@ The filter should be supplied as an SQL query string. For example:
#### Parameters
* **predicate**: `string`
**predicate**: `string`
#### Returns
@@ -497,25 +389,3 @@ on the filter column(s).
#### Inherited from
[`QueryBase`](QueryBase.md).[`where`](QueryBase.md#where)
***
### withRowId()
```ts
withRowId(): this
```
Whether to return the row id in the results.
This column can be used to match results between different queries. For
example, to match results from a full text search and a vector search in
order to perform hybrid search.
#### Returns
`this`
#### Inherited from
[`QueryBase`](QueryBase.md).[`withRowId`](QueryBase.md#withrowid)

View File

@@ -25,13 +25,11 @@ Common methods supported by all query types
### new QueryBase()
```ts
protected new QueryBase<NativeQueryType>(inner): QueryBase<NativeQueryType>
```
> `protected` **new QueryBase**&lt;`NativeQueryType`&gt;(`inner`): [`QueryBase`](QueryBase.md)&lt;`NativeQueryType`&gt;
#### Parameters
* **inner**: `NativeQueryType` \| `Promise`&lt;`NativeQueryType`&gt;
**inner**: `NativeQueryType` \| `Promise`&lt;`NativeQueryType`&gt;
#### Returns
@@ -41,17 +39,13 @@ protected new QueryBase<NativeQueryType>(inner): QueryBase<NativeQueryType>
### inner
```ts
protected inner: NativeQueryType | Promise<NativeQueryType>;
```
> `protected` **inner**: `NativeQueryType` \| `Promise`&lt;`NativeQueryType`&gt;
## Methods
### \[asyncIterator\]()
```ts
asyncIterator: AsyncIterator<RecordBatch<any>, any, undefined>
```
> **\[asyncIterator\]**(): `AsyncIterator`&lt;`RecordBatch`&lt;`any`&gt;, `any`, `undefined`&gt;
#### Returns
@@ -65,13 +59,11 @@ asyncIterator: AsyncIterator<RecordBatch<any>, any, undefined>
### doCall()
```ts
protected doCall(fn): void
```
> `protected` **doCall**(`fn`): `void`
#### Parameters
* **fn**
**fn**
#### Returns
@@ -81,15 +73,13 @@ protected doCall(fn): void
### execute()
```ts
protected execute(options?): RecordBatchIterator
```
> `protected` **execute**(`options`?): [`RecordBatchIterator`](RecordBatchIterator.md)
Execute the query and return the results as an
#### Parameters
* **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
**options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
#### Returns
@@ -111,16 +101,15 @@ single query)
### explainPlan()
```ts
explainPlan(verbose): Promise<string>
```
> **explainPlan**(`verbose`): `Promise`&lt;`string`&gt;
Generates an explanation of the query execution plan.
#### Parameters
* **verbose**: `boolean` = `false`
If true, provides a more detailed explanation. Defaults to false.
**verbose**: `boolean` = `false`
If true, provides a more detailed explanation. Defaults to false.
#### Returns
@@ -141,34 +130,15 @@ const plan = await table.query().nearestTo([0.5, 0.2]).explainPlan();
***
### fastSearch()
```ts
fastSearch(): this
```
Skip searching un-indexed data. This can make search faster, but will miss
any data that is not yet indexed.
Use lancedb.Table#optimize to index all un-indexed data.
#### Returns
`this`
***
### ~~filter()~~
```ts
filter(predicate): this
```
> **filter**(`predicate`): `this`
A filter statement to be applied to this query.
#### Parameters
* **predicate**: `string`
**predicate**: `string`
#### Returns
@@ -184,29 +154,9 @@ Use `where` instead
***
### fullTextSearch()
```ts
fullTextSearch(query, options?): this
```
#### Parameters
* **query**: `string`
* **options?**: `Partial`&lt;`FullTextSearchOptions`&gt;
#### Returns
`this`
***
### limit()
```ts
limit(limit): this
```
> **limit**(`limit`): `this`
Set the maximum number of results to return.
@@ -215,7 +165,7 @@ called then every valid row from the table will be returned.
#### Parameters
* **limit**: `number`
**limit**: `number`
#### Returns
@@ -225,13 +175,11 @@ called then every valid row from the table will be returned.
### nativeExecute()
```ts
protected nativeExecute(options?): Promise<RecordBatchIterator>
```
> `protected` **nativeExecute**(`options`?): `Promise`&lt;`RecordBatchIterator`&gt;
#### Parameters
* **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
**options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
#### Returns
@@ -239,27 +187,9 @@ protected nativeExecute(options?): Promise<RecordBatchIterator>
***
### offset()
```ts
offset(offset): this
```
#### Parameters
* **offset**: `number`
#### Returns
`this`
***
### select()
```ts
select(columns): this
```
> **select**(`columns`): `this`
Return only the specified columns.
@@ -283,7 +213,7 @@ input to this method would be:
#### Parameters
* **columns**: `string` \| `string`[] \| `Record`&lt;`string`, `string`&gt; \| `Map`&lt;`string`, `string`&gt;
**columns**: `string` \| `string`[] \| `Record`&lt;`string`, `string`&gt; \| `Map`&lt;`string`, `string`&gt;
#### Returns
@@ -306,15 +236,13 @@ object insertion order is easy to get wrong and `Map` is more foolproof.
### toArray()
```ts
toArray(options?): Promise<any[]>
```
> **toArray**(`options`?): `Promise`&lt;`any`[]&gt;
Collect the results as an array of objects.
#### Parameters
* **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
**options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
#### Returns
@@ -324,15 +252,13 @@ Collect the results as an array of objects.
### toArrow()
```ts
toArrow(options?): Promise<Table<any>>
```
> **toArrow**(`options`?): `Promise`&lt;`Table`&lt;`any`&gt;&gt;
Collect the results as an Arrow
#### Parameters
* **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
**options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
#### Returns
@@ -346,9 +272,7 @@ ArrowTable.
### where()
```ts
where(predicate): this
```
> **where**(`predicate`): `this`
A filter statement to be applied to this query.
@@ -356,7 +280,7 @@ The filter should be supplied as an SQL query string. For example:
#### Parameters
* **predicate**: `string`
**predicate**: `string`
#### Returns
@@ -372,21 +296,3 @@ x > 5 OR y = 'test'
Filtering performance can often be improved by creating a scalar index
on the filter column(s).
```
***
### withRowId()
```ts
withRowId(): this
```
Whether to return the row id in the results.
This column can be used to match results between different queries. For
example, to match results from a full text search and a vector search in
order to perform hybrid search.
#### Returns
`this`

View File

@@ -14,13 +14,11 @@
### new RecordBatchIterator()
```ts
new RecordBatchIterator(promise?): RecordBatchIterator
```
> **new RecordBatchIterator**(`promise`?): [`RecordBatchIterator`](RecordBatchIterator.md)
#### Parameters
* **promise?**: `Promise`&lt;`RecordBatchIterator`&gt;
**promise?**: `Promise`&lt;`RecordBatchIterator`&gt;
#### Returns
@@ -30,9 +28,7 @@ new RecordBatchIterator(promise?): RecordBatchIterator
### next()
```ts
next(): Promise<IteratorResult<RecordBatch<any>, any>>
```
> **next**(): `Promise`&lt;`IteratorResult`&lt;`RecordBatch`&lt;`any`&gt;, `any`&gt;&gt;
#### Returns

View File

@@ -21,9 +21,7 @@ collected.
### new Table()
```ts
new Table(): Table
```
> **new Table**(): [`Table`](Table.md)
#### Returns
@@ -33,9 +31,7 @@ new Table(): Table
### name
```ts
get abstract name(): string
```
> `get` `abstract` **name**(): `string`
Returns the name of the table
@@ -47,18 +43,17 @@ Returns the name of the table
### add()
```ts
abstract add(data, options?): Promise<void>
```
> `abstract` **add**(`data`, `options`?): `Promise`&lt;`void`&gt;
Insert records into this Table.
#### Parameters
* **data**: [`Data`](../type-aliases/Data.md)
Records to be inserted into the Table
**data**: [`Data`](../type-aliases/Data.md)
* **options?**: `Partial`&lt;[`AddDataOptions`](../interfaces/AddDataOptions.md)&gt;
Records to be inserted into the Table
**options?**: `Partial`&lt;[`AddDataOptions`](../interfaces/AddDataOptions.md)&gt;
#### Returns
@@ -68,19 +63,18 @@ Insert records into this Table.
### addColumns()
```ts
abstract addColumns(newColumnTransforms): Promise<void>
```
> `abstract` **addColumns**(`newColumnTransforms`): `Promise`&lt;`void`&gt;
Add new columns with defined values.
#### Parameters
* **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.
**newColumnTransforms**: [`AddColumnsSql`](../interfaces/AddColumnsSql.md)[]
pairs of column names and
the SQL expression to use to calculate the value of the new column. These
expressions will be evaluated for each row in the table, and can
reference existing columns in the table.
#### Returns
@@ -90,17 +84,16 @@ Add new columns with defined values.
### alterColumns()
```ts
abstract alterColumns(columnAlterations): Promise<void>
```
> `abstract` **alterColumns**(`columnAlterations`): `Promise`&lt;`void`&gt;
Alter the name or nullability of columns.
#### Parameters
* **columnAlterations**: [`ColumnAlteration`](../interfaces/ColumnAlteration.md)[]
One or more alterations to
apply to columns.
**columnAlterations**: [`ColumnAlteration`](../interfaces/ColumnAlteration.md)[]
One or more alterations to
apply to columns.
#### Returns
@@ -110,9 +103,7 @@ Alter the name or nullability of columns.
### checkout()
```ts
abstract checkout(version): Promise<void>
```
> `abstract` **checkout**(`version`): `Promise`&lt;`void`&gt;
Checks out a specific version of the table _This is an in-place operation._
@@ -125,8 +116,9 @@ wish to return to standard mode, call `checkoutLatest`.
#### Parameters
* **version**: `number`
The version to checkout
**version**: `number`
The version to checkout
#### Returns
@@ -152,9 +144,7 @@ console.log(await table.version()); // 2
### checkoutLatest()
```ts
abstract checkoutLatest(): Promise<void>
```
> `abstract` **checkoutLatest**(): `Promise`&lt;`void`&gt;
Checkout the latest version of the table. _This is an in-place operation._
@@ -169,9 +159,7 @@ version of the table.
### close()
```ts
abstract close(): void
```
> `abstract` **close**(): `void`
Close the table, releasing any underlying resources.
@@ -187,15 +175,13 @@ Any attempt to use the table after it is closed will result in an error.
### countRows()
```ts
abstract countRows(filter?): Promise<number>
```
> `abstract` **countRows**(`filter`?): `Promise`&lt;`number`&gt;
Count the total number of rows in the dataset.
#### Parameters
* **filter?**: `string`
**filter?**: `string`
#### Returns
@@ -205,9 +191,7 @@ Count the total number of rows in the dataset.
### createIndex()
```ts
abstract createIndex(column, options?): Promise<void>
```
> `abstract` **createIndex**(`column`, `options`?): `Promise`&lt;`void`&gt;
Create an index to speed up queries.
@@ -218,9 +202,9 @@ vector and non-vector searches)
#### Parameters
* **column**: `string`
**column**: `string`
* **options?**: `Partial`&lt;[`IndexOptions`](../interfaces/IndexOptions.md)&gt;
**options?**: `Partial`&lt;[`IndexOptions`](../interfaces/IndexOptions.md)&gt;
#### Returns
@@ -261,15 +245,13 @@ await table.createIndex("my_float_col");
### delete()
```ts
abstract delete(predicate): Promise<void>
```
> `abstract` **delete**(`predicate`): `Promise`&lt;`void`&gt;
Delete the rows that satisfy the predicate.
#### Parameters
* **predicate**: `string`
**predicate**: `string`
#### Returns
@@ -279,9 +261,7 @@ Delete the rows that satisfy the predicate.
### display()
```ts
abstract display(): string
```
> `abstract` **display**(): `string`
Return a brief description of the table
@@ -293,9 +273,7 @@ Return a brief description of the table
### dropColumns()
```ts
abstract dropColumns(columnNames): Promise<void>
```
> `abstract` **dropColumns**(`columnNames`): `Promise`&lt;`void`&gt;
Drop one or more columns from the dataset
@@ -306,10 +284,11 @@ then call ``cleanup_files`` to remove the old files.
#### Parameters
* **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").
**columnNames**: `string`[]
The names of the columns to drop. These can
be nested column references (e.g. "a.b.c") or top-level column names
(e.g. "a").
#### Returns
@@ -319,16 +298,15 @@ then call ``cleanup_files`` to remove the old files.
### indexStats()
```ts
abstract indexStats(name): Promise<undefined | IndexStatistics>
```
> `abstract` **indexStats**(`name`): `Promise`&lt;`undefined` \| [`IndexStatistics`](../interfaces/IndexStatistics.md)&gt;
List all the stats of a specified index
#### Parameters
* **name**: `string`
The name of the index.
**name**: `string`
The name of the index.
#### Returns
@@ -340,9 +318,7 @@ The stats of the index. If the index does not exist, it will return undefined
### isOpen()
```ts
abstract isOpen(): boolean
```
> `abstract` **isOpen**(): `boolean`
Return true if the table has not been closed
@@ -354,9 +330,7 @@ Return true if the table has not been closed
### listIndices()
```ts
abstract listIndices(): Promise<IndexConfig[]>
```
> `abstract` **listIndices**(): `Promise`&lt;[`IndexConfig`](../interfaces/IndexConfig.md)[]&gt;
List all indices that have been created with [Table.createIndex](Table.md#createindex)
@@ -366,29 +340,13 @@ List all indices that have been created with [Table.createIndex](Table.md#create
***
### listVersions()
```ts
abstract listVersions(): Promise<Version[]>
```
List all the versions of the table
#### Returns
`Promise`&lt;`Version`[]&gt;
***
### mergeInsert()
```ts
abstract mergeInsert(on): MergeInsertBuilder
```
> `abstract` **mergeInsert**(`on`): `MergeInsertBuilder`
#### Parameters
* **on**: `string` \| `string`[]
**on**: `string` \| `string`[]
#### Returns
@@ -398,9 +356,7 @@ abstract mergeInsert(on): MergeInsertBuilder
### optimize()
```ts
abstract optimize(options?): Promise<OptimizeStats>
```
> `abstract` **optimize**(`options`?): `Promise`&lt;`OptimizeStats`&gt;
Optimize the on-disk data and indices for better performance.
@@ -432,7 +388,7 @@ Modeled after ``VACUUM`` in PostgreSQL.
#### Parameters
* **options?**: `Partial`&lt;[`OptimizeOptions`](../interfaces/OptimizeOptions.md)&gt;
**options?**: `Partial`&lt;`OptimizeOptions`&gt;
#### Returns
@@ -442,9 +398,7 @@ Modeled after ``VACUUM`` in PostgreSQL.
### query()
```ts
abstract query(): Query
```
> `abstract` **query**(): [`Query`](Query.md)
Create a [Query](Query.md) Builder.
@@ -512,9 +466,7 @@ for await (const batch of table.query()) {
### restore()
```ts
abstract restore(): Promise<void>
```
> `abstract` **restore**(): `Promise`&lt;`void`&gt;
Restore the table to the currently checked out version
@@ -535,9 +487,7 @@ out state and the read_consistency_interval, if any, will apply.
### schema()
```ts
abstract schema(): Promise<Schema<any>>
```
> `abstract` **schema**(): `Promise`&lt;`Schema`&lt;`any`&gt;&gt;
Get the schema of the table.
@@ -549,41 +499,61 @@ Get the schema of the table.
### search()
```ts
abstract search(
query,
queryType?,
ftsColumns?): VectorQuery | Query
```
#### search(query)
> `abstract` **search**(`query`, `queryType`, `ftsColumns`): [`VectorQuery`](VectorQuery.md)
Create a search query to find the nearest neighbors
of the given query
of the given query vector, or the documents
with the highest relevance to the query string.
#### Parameters
##### Parameters
* **query**: `string` \| `IntoVector`
the query, a vector or string
**query**: `string`
* **queryType?**: `string`
the type of the query, "vector", "fts", or "auto"
the query. This will be converted to a vector using the table's provided embedding function,
or the query string for full-text search if `queryType` is "fts".
* **ftsColumns?**: `string` \| `string`[]
the columns to search in for full text search
for now, only one column can be searched at a time.
when "auto" is used, if the query is a string and an embedding function is defined, it will be treated as a vector query
if the query is a string and no embedding function is defined, it will be treated as a full text search query
**queryType**: `string` = `"auto"` \| `"fts"`
#### Returns
the type of query to run. If "auto", the query type will be determined based on the query.
[`VectorQuery`](VectorQuery.md) \| [`Query`](Query.md)
• **ftsColumns**: `string[] | str` = undefined
the columns to search in. If not provided, all indexed columns will be searched.
For now, this can support to search only one column.
##### 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()
```ts
abstract toArrow(): Promise<Table<any>>
```
> `abstract` **toArrow**(): `Promise`&lt;`Table`&lt;`any`&gt;&gt;
Return the table as an arrow table
@@ -597,15 +567,13 @@ Return the table as an arrow table
#### update(opts)
```ts
abstract update(opts): Promise<void>
```
> `abstract` **update**(`opts`): `Promise`&lt;`void`&gt;
Update existing records in the Table
##### Parameters
* **opts**: `object` & `Partial`&lt;[`UpdateOptions`](../interfaces/UpdateOptions.md)&gt;
**opts**: `object` & `Partial`&lt;[`UpdateOptions`](../interfaces/UpdateOptions.md)&gt;
##### Returns
@@ -619,15 +587,13 @@ table.update({where:"x = 2", values:{"vector": [10, 10]}})
#### update(opts)
```ts
abstract update(opts): Promise<void>
```
> `abstract` **update**(`opts`): `Promise`&lt;`void`&gt;
Update existing records in the Table
##### Parameters
* **opts**: `object` & `Partial`&lt;[`UpdateOptions`](../interfaces/UpdateOptions.md)&gt;
**opts**: `object` & `Partial`&lt;[`UpdateOptions`](../interfaces/UpdateOptions.md)&gt;
##### Returns
@@ -641,9 +607,7 @@ table.update({where:"x = 2", valuesSql:{"x": "x + 1"}})
#### update(updates, options)
```ts
abstract update(updates, options?): Promise<void>
```
> `abstract` **update**(`updates`, `options`?): `Promise`&lt;`void`&gt;
Update existing records in the Table
@@ -662,17 +626,20 @@ repeatedly calilng this method.
##### Parameters
* **updates**: `Record`&lt;`string`, `string`&gt; \| `Map`&lt;`string`, `string`&gt;
the
columns to update
Keys in the map should specify the name of the column to update.
Values in the map provide the new value of the column. These can
be SQL literal strings (e.g. "7" or "'foo'") or they can be expressions
based on the row being updated (e.g. "my_col + 1")
**updates**: `Record`&lt;`string`, `string`&gt; \| `Map`&lt;`string`, `string`&gt;
* **options?**: `Partial`&lt;[`UpdateOptions`](../interfaces/UpdateOptions.md)&gt;
additional options to control
the update behavior
the
columns to update
Keys in the map should specify the name of the column to update.
Values in the map provide the new value of the column. These can
be SQL literal strings (e.g. "7" or "'foo'") or they can be expressions
based on the row being updated (e.g. "my_col + 1")
• **options?**: `Partial`&lt;[`UpdateOptions`](../interfaces/UpdateOptions.md)&gt;
additional options to control
the update behavior
##### Returns
@@ -682,9 +649,7 @@ repeatedly calilng this method.
### vectorSearch()
```ts
abstract vectorSearch(vector): VectorQuery
```
> `abstract` **vectorSearch**(`vector`): [`VectorQuery`](VectorQuery.md)
Search the table with a given query vector.
@@ -694,7 +659,7 @@ by `query`.
#### Parameters
* **vector**: `IntoVector`
**vector**: `IntoVector`
#### Returns
@@ -708,9 +673,7 @@ by `query`.
### version()
```ts
abstract version(): Promise<number>
```
> `abstract` **version**(): `Promise`&lt;`number`&gt;
Retrieve the version of the table
@@ -722,20 +685,15 @@ Retrieve the version of the table
### parseTableData()
```ts
static parseTableData(
data,
options?,
streaming?): Promise<object>
```
> `static` **parseTableData**(`data`, `options`?, `streaming`?): `Promise`&lt;`object`&gt;
#### Parameters
* **data**: `TableLike` \| `Record`&lt;`string`, `unknown`&gt;[]
**data**: `TableLike` \| `Record`&lt;`string`, `unknown`&gt;[]
* **options?**: `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
**options?**: `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
* **streaming?**: `boolean` = `false`
**streaming?**: `boolean` = `false`
#### Returns
@@ -743,12 +701,8 @@ static parseTableData(
##### buf
```ts
buf: Buffer;
```
> **buf**: `Buffer`
##### mode
```ts
mode: string;
```
> **mode**: `string`

View File

@@ -10,13 +10,11 @@
### new VectorColumnOptions()
```ts
new VectorColumnOptions(values?): VectorColumnOptions
```
> **new VectorColumnOptions**(`values`?): [`VectorColumnOptions`](VectorColumnOptions.md)
#### Parameters
* **values?**: `Partial`&lt;[`VectorColumnOptions`](VectorColumnOptions.md)&gt;
**values?**: `Partial`&lt;[`VectorColumnOptions`](VectorColumnOptions.md)&gt;
#### Returns
@@ -26,8 +24,6 @@ new VectorColumnOptions(values?): VectorColumnOptions
### type
```ts
type: Float<Floats>;
```
> **type**: `Float`&lt;`Floats`&gt;
Vector column type.

View File

@@ -18,13 +18,11 @@ This builder can be reused to execute the query many times.
### new VectorQuery()
```ts
new VectorQuery(inner): VectorQuery
```
> **new VectorQuery**(`inner`): [`VectorQuery`](VectorQuery.md)
#### Parameters
* **inner**: `VectorQuery` \| `Promise`&lt;`VectorQuery`&gt;
**inner**: `VectorQuery` \| `Promise`&lt;`VectorQuery`&gt;
#### Returns
@@ -38,9 +36,7 @@ new VectorQuery(inner): VectorQuery
### inner
```ts
protected inner: VectorQuery | Promise<VectorQuery>;
```
> `protected` **inner**: `VectorQuery` \| `Promise`&lt;`VectorQuery`&gt;
#### Inherited from
@@ -50,9 +46,7 @@ protected inner: VectorQuery | Promise<VectorQuery>;
### \[asyncIterator\]()
```ts
asyncIterator: AsyncIterator<RecordBatch<any>, any, undefined>
```
> **\[asyncIterator\]**(): `AsyncIterator`&lt;`RecordBatch`&lt;`any`&gt;, `any`, `undefined`&gt;
#### Returns
@@ -64,27 +58,9 @@ asyncIterator: AsyncIterator<RecordBatch<any>, any, undefined>
***
### addQueryVector()
```ts
addQueryVector(vector): VectorQuery
```
#### Parameters
* **vector**: `IntoVector`
#### Returns
[`VectorQuery`](VectorQuery.md)
***
### bypassVectorIndex()
```ts
bypassVectorIndex(): VectorQuery
```
> **bypassVectorIndex**(): [`VectorQuery`](VectorQuery.md)
If this is called then any vector index is skipped
@@ -102,9 +78,7 @@ calculate your recall to select an appropriate value for nprobes.
### column()
```ts
column(column): VectorQuery
```
> **column**(`column`): [`VectorQuery`](VectorQuery.md)
Set the vector column to query
@@ -113,7 +87,7 @@ the call to
#### Parameters
* **column**: `string`
**column**: `string`
#### Returns
@@ -130,9 +104,7 @@ whose data type is a fixed-size-list of floats.
### distanceType()
```ts
distanceType(distanceType): VectorQuery
```
> **distanceType**(`distanceType`): [`VectorQuery`](VectorQuery.md)
Set the distance metric to use
@@ -142,7 +114,7 @@ use. See
#### Parameters
* **distanceType**: `"l2"` \| `"cosine"` \| `"dot"`
**distanceType**: `"l2"` \| `"cosine"` \| `"dot"`
#### Returns
@@ -163,13 +135,11 @@ By default "l2" is used.
### doCall()
```ts
protected doCall(fn): void
```
> `protected` **doCall**(`fn`): `void`
#### Parameters
* **fn**
**fn**
#### Returns
@@ -181,41 +151,15 @@ protected doCall(fn): void
***
### ef()
```ts
ef(ef): VectorQuery
```
Set the number of candidates to consider during the search
This argument is only used when the vector column has an HNSW index.
If there is no index then this value is ignored.
Increasing this value will increase the recall of your query but will
also increase the latency of your query. The default value is 1.5*limit.
#### Parameters
* **ef**: `number`
#### Returns
[`VectorQuery`](VectorQuery.md)
***
### execute()
```ts
protected execute(options?): RecordBatchIterator
```
> `protected` **execute**(`options`?): [`RecordBatchIterator`](RecordBatchIterator.md)
Execute the query and return the results as an
#### Parameters
* **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
**options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
#### Returns
@@ -241,16 +185,15 @@ single query)
### explainPlan()
```ts
explainPlan(verbose): Promise<string>
```
> **explainPlan**(`verbose`): `Promise`&lt;`string`&gt;
Generates an explanation of the query execution plan.
#### Parameters
* **verbose**: `boolean` = `false`
If true, provides a more detailed explanation. Defaults to false.
**verbose**: `boolean` = `false`
If true, provides a more detailed explanation. Defaults to false.
#### Returns
@@ -275,38 +218,15 @@ const plan = await table.query().nearestTo([0.5, 0.2]).explainPlan();
***
### fastSearch()
```ts
fastSearch(): this
```
Skip searching un-indexed data. This can make search faster, but will miss
any data that is not yet indexed.
Use lancedb.Table#optimize to index all un-indexed data.
#### Returns
`this`
#### Inherited from
[`QueryBase`](QueryBase.md).[`fastSearch`](QueryBase.md#fastsearch)
***
### ~~filter()~~
```ts
filter(predicate): this
```
> **filter**(`predicate`): `this`
A filter statement to be applied to this query.
#### Parameters
* **predicate**: `string`
**predicate**: `string`
#### Returns
@@ -326,33 +246,9 @@ Use `where` instead
***
### fullTextSearch()
```ts
fullTextSearch(query, options?): this
```
#### Parameters
* **query**: `string`
* **options?**: `Partial`&lt;`FullTextSearchOptions`&gt;
#### Returns
`this`
#### Inherited from
[`QueryBase`](QueryBase.md).[`fullTextSearch`](QueryBase.md#fulltextsearch)
***
### limit()
```ts
limit(limit): this
```
> **limit**(`limit`): `this`
Set the maximum number of results to return.
@@ -361,7 +257,7 @@ called then every valid row from the table will be returned.
#### Parameters
* **limit**: `number`
**limit**: `number`
#### Returns
@@ -375,13 +271,11 @@ called then every valid row from the table will be returned.
### nativeExecute()
```ts
protected nativeExecute(options?): Promise<RecordBatchIterator>
```
> `protected` **nativeExecute**(`options`?): `Promise`&lt;`RecordBatchIterator`&gt;
#### Parameters
* **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
**options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
#### Returns
@@ -395,9 +289,7 @@ protected nativeExecute(options?): Promise<RecordBatchIterator>
### nprobes()
```ts
nprobes(nprobes): VectorQuery
```
> **nprobes**(`nprobes`): [`VectorQuery`](VectorQuery.md)
Set the number of partitions to search (probe)
@@ -422,7 +314,7 @@ you the desired recall.
#### Parameters
* **nprobes**: `number`
**nprobes**: `number`
#### Returns
@@ -430,31 +322,9 @@ you the desired recall.
***
### offset()
```ts
offset(offset): this
```
#### Parameters
* **offset**: `number`
#### Returns
`this`
#### Inherited from
[`QueryBase`](QueryBase.md).[`offset`](QueryBase.md#offset)
***
### postfilter()
```ts
postfilter(): VectorQuery
```
> **postfilter**(): [`VectorQuery`](VectorQuery.md)
If this is called then filtering will happen after the vector search instead of
before.
@@ -486,9 +356,7 @@ factor can often help restore some of the results lost by post filtering.
### refineFactor()
```ts
refineFactor(refineFactor): VectorQuery
```
> **refineFactor**(`refineFactor`): [`VectorQuery`](VectorQuery.md)
A multiplier to control how many additional rows are taken during the refine step
@@ -520,7 +388,7 @@ distance between the query vector and the actual uncompressed vector.
#### Parameters
* **refineFactor**: `number`
**refineFactor**: `number`
#### Returns
@@ -530,9 +398,7 @@ distance between the query vector and the actual uncompressed vector.
### select()
```ts
select(columns): this
```
> **select**(`columns`): `this`
Return only the specified columns.
@@ -556,7 +422,7 @@ input to this method would be:
#### Parameters
* **columns**: `string` \| `string`[] \| `Record`&lt;`string`, `string`&gt; \| `Map`&lt;`string`, `string`&gt;
**columns**: `string` \| `string`[] \| `Record`&lt;`string`, `string`&gt; \| `Map`&lt;`string`, `string`&gt;
#### Returns
@@ -583,15 +449,13 @@ object insertion order is easy to get wrong and `Map` is more foolproof.
### toArray()
```ts
toArray(options?): Promise<any[]>
```
> **toArray**(`options`?): `Promise`&lt;`any`[]&gt;
Collect the results as an array of objects.
#### Parameters
* **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
**options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
#### Returns
@@ -605,15 +469,13 @@ Collect the results as an array of objects.
### toArrow()
```ts
toArrow(options?): Promise<Table<any>>
```
> **toArrow**(`options`?): `Promise`&lt;`Table`&lt;`any`&gt;&gt;
Collect the results as an Arrow
#### Parameters
* **options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
**options?**: `Partial`&lt;`QueryExecutionOptions`&gt;
#### Returns
@@ -631,9 +493,7 @@ ArrowTable.
### where()
```ts
where(predicate): this
```
> **where**(`predicate`): `this`
A filter statement to be applied to this query.
@@ -641,7 +501,7 @@ The filter should be supplied as an SQL query string. For example:
#### Parameters
* **predicate**: `string`
**predicate**: `string`
#### Returns
@@ -661,25 +521,3 @@ on the filter column(s).
#### Inherited from
[`QueryBase`](QueryBase.md).[`where`](QueryBase.md#where)
***
### withRowId()
```ts
withRowId(): this
```
Whether to return the row id in the results.
This column can be used to match results between different queries. For
example, to match results from a full text search and a vector search in
order to perform hybrid search.
#### Returns
`this`
#### Inherited from
[`QueryBase`](QueryBase.md).[`withRowId`](QueryBase.md#withrowid)

View File

@@ -12,22 +12,16 @@ Write mode for writing a table.
### Append
```ts
Append: "Append";
```
> **Append**: `"Append"`
***
### Create
```ts
Create: "Create";
```
> **Create**: `"Create"`
***
### Overwrite
```ts
Overwrite: "Overwrite";
```
> **Overwrite**: `"Overwrite"`

View File

@@ -8,9 +8,7 @@
## connect(uri, opts)
```ts
function connect(uri, opts?): Promise<Connection>
```
> **connect**(`uri`, `opts`?): `Promise`&lt;[`Connection`](../classes/Connection.md)&gt;
Connect to a LanceDB instance at the given URI.
@@ -22,11 +20,12 @@ Accepted formats:
### Parameters
* **uri**: `string`
The uri of the database. If the database uri starts
with `db://` then it connects to a remote database.
**uri**: `string`
* **opts?**: `Partial`&lt;[`ConnectionOptions`](../interfaces/ConnectionOptions.md)&gt;
The uri of the database. If the database uri starts
with `db://` then it connects to a remote database.
**opts?**: `Partial`&lt;[`ConnectionOptions`](../interfaces/ConnectionOptions.md) \| `RemoteConnectionOptions`&gt;
### Returns
@@ -51,9 +50,7 @@ const conn = await connect(
## connect(opts)
```ts
function connect(opts): Promise<Connection>
```
> **connect**(`opts`): `Promise`&lt;[`Connection`](../classes/Connection.md)&gt;
Connect to a LanceDB instance at the given URI.
@@ -65,7 +62,7 @@ Accepted formats:
### Parameters
* **opts**: `Partial`&lt;[`ConnectionOptions`](../interfaces/ConnectionOptions.md)&gt; & `object`
**opts**: `Partial`&lt;[`ConnectionOptions`](../interfaces/ConnectionOptions.md) \| `RemoteConnectionOptions`&gt; & `object`
### Returns

View File

@@ -6,12 +6,7 @@
# Function: makeArrowTable()
```ts
function makeArrowTable(
data,
options?,
metadata?): ArrowTable
```
> **makeArrowTable**(`data`, `options`?, `metadata`?): `ArrowTable`
An enhanced version of the makeTable function from Apache Arrow
that supports nested fields and embeddings columns.
@@ -45,11 +40,11 @@ rules are as follows:
## Parameters
* **data**: `Record`&lt;`string`, `unknown`&gt;[]
**data**: `Record`&lt;`string`, `unknown`&gt;[]
* **options?**: `Partial`&lt;[`MakeArrowTableOptions`](../classes/MakeArrowTableOptions.md)&gt;
**options?**: `Partial`&lt;[`MakeArrowTableOptions`](../classes/MakeArrowTableOptions.md)&gt;
* **metadata?**: `Map`&lt;`string`, `string`&gt;
**metadata?**: `Map`&lt;`string`, `string`&gt;
## Returns

View File

@@ -28,19 +28,17 @@
- [AddColumnsSql](interfaces/AddColumnsSql.md)
- [AddDataOptions](interfaces/AddDataOptions.md)
- [ClientConfig](interfaces/ClientConfig.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)
- [OptimizeOptions](interfaces/OptimizeOptions.md)
- [RetryConfig](interfaces/RetryConfig.md)
- [FtsOptions](interfaces/FtsOptions.md)
- [TableNamesOptions](interfaces/TableNamesOptions.md)
- [TimeoutConfig](interfaces/TimeoutConfig.md)
- [UpdateOptions](interfaces/UpdateOptions.md)
- [WriteOptions](interfaces/WriteOptions.md)

View File

@@ -12,9 +12,7 @@ A definition of a new column to add to a table.
### name
```ts
name: string;
```
> **name**: `string`
The name of the new column.
@@ -22,9 +20,7 @@ The name of the new column.
### valueSql
```ts
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.

View File

@@ -12,9 +12,7 @@ Options for adding data to a table.
### mode
```ts
mode: "append" | "overwrite";
```
> **mode**: `"append"` \| `"overwrite"`
If "append" (the default) then the new data will be added to the table

View File

@@ -1,31 +0,0 @@
[**@lancedb/lancedb**](../README.md) • **Docs**
***
[@lancedb/lancedb](../globals.md) / ClientConfig
# Interface: ClientConfig
## Properties
### retryConfig?
```ts
optional retryConfig: RetryConfig;
```
***
### timeoutConfig?
```ts
optional timeoutConfig: TimeoutConfig;
```
***
### userAgent?
```ts
optional userAgent: string;
```

View File

@@ -13,29 +13,9 @@ must be provided.
## Properties
### dataType?
```ts
optional dataType: string;
```
A new data type for the column. If not provided then the data type will not be changed.
Changing data types is limited to casting to the same general type. For example, these
changes are valid:
* `int32` -> `int64` (integers)
* `double` -> `float` (floats)
* `string` -> `large_string` (strings)
But these changes are not:
* `int32` -> `double` (mix integers and floats)
* `string` -> `int32` (mix strings and integers)
***
### nullable?
```ts
optional nullable: boolean;
```
> `optional` **nullable**: `boolean`
Set the new nullability. Note that a nullable column cannot be made non-nullable.
@@ -43,9 +23,7 @@ Set the new nullability. Note that a nullable column cannot be made non-nullable
### path
```ts
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
@@ -56,9 +34,7 @@ a nested column then it is the path to the column, e.g. "a.b.c" for a column
### rename?
```ts
optional rename: string;
```
> `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.

View File

@@ -8,44 +8,9 @@
## Properties
### apiKey?
```ts
optional apiKey: string;
```
(For LanceDB cloud only): the API key to use with LanceDB Cloud.
Can also be set via the environment variable `LANCEDB_API_KEY`.
***
### clientConfig?
```ts
optional clientConfig: ClientConfig;
```
(For LanceDB cloud only): configuration for the remote HTTP client.
***
### hostOverride?
```ts
optional hostOverride: string;
```
(For LanceDB cloud only): the host to use for LanceDB cloud. Used
for testing purposes.
***
### readConsistencyInterval?
```ts
optional readConsistencyInterval: number;
```
> `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
@@ -59,22 +24,9 @@ always consistent.
***
### region?
```ts
optional region: string;
```
(For LanceDB cloud only): the region to use for LanceDB cloud.
Defaults to 'us-east-1'.
***
### storageOptions?
```ts
optional storageOptions: Record<string, string>;
```
> `optional` **storageOptions**: `Record`&lt;`string`, `string`&gt;
(For LanceDB OSS only): configuration for object storage.

View File

@@ -8,46 +8,15 @@
## Properties
### dataStorageVersion?
```ts
optional dataStorageVersion: string;
```
The version of the data storage format to use.
The default is `stable`.
Set to "legacy" to use the old format.
***
### embeddingFunction?
```ts
optional embeddingFunction: EmbeddingFunctionConfig;
```
***
### enableV2ManifestPaths?
```ts
optional enableV2ManifestPaths: boolean;
```
Use the new V2 manifest paths. These paths provide more efficient
opening of datasets with many versions on object stores. WARNING:
turning this on will make the dataset unreadable for older versions
of LanceDB (prior to 0.10.0). To migrate an existing dataset, instead
use the LocalTable#migrateManifestPathsV2 method.
> `optional` **embeddingFunction**: [`EmbeddingFunctionConfig`](../namespaces/embedding/interfaces/EmbeddingFunctionConfig.md)
***
### existOk
```ts
existOk: boolean;
```
> **existOk**: `boolean`
If this is true and the table already exists and the mode is "create"
then no error will be raised.
@@ -56,9 +25,7 @@ then no error will be raised.
### mode
```ts
mode: "overwrite" | "create";
```
> **mode**: `"overwrite"` \| `"create"`
The mode to use when creating the table.
@@ -72,17 +39,13 @@ If this is set to "overwrite" then any existing table will be replaced.
### schema?
```ts
optional schema: SchemaLike;
```
> `optional` **schema**: `SchemaLike`
***
### storageOptions?
```ts
optional storageOptions: Record<string, string>;
```
> `optional` **storageOptions**: `Record`&lt;`string`, `string`&gt;
Configuration for object storage.
@@ -95,12 +58,8 @@ The available options are described at https://lancedb.github.io/lancedb/guides/
### useLegacyFormat?
```ts
optional useLegacyFormat: boolean;
```
> `optional` **useLegacyFormat**: `boolean`
If true then data files will be written with the legacy format
The default is false.
Deprecated. Use data storage version instead.
The default is true while the new format is in beta

View File

@@ -12,9 +12,7 @@ A description of an index currently configured on a column
### columns
```ts
columns: string[];
```
> **columns**: `string`[]
The columns in the index
@@ -25,9 +23,7 @@ be more columns to represent composite indices.
### indexType
```ts
indexType: string;
```
> **indexType**: `string`
The type of the index
@@ -35,8 +31,6 @@ The type of the index
### name
```ts
name: string;
```
> **name**: `string`
The name of the index

View File

@@ -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`

View File

@@ -10,9 +10,7 @@
### config?
```ts
optional config: Index;
```
> `optional` **config**: [`Index`](../classes/Index.md)
Advanced index configuration
@@ -28,9 +26,7 @@ will be used to determine the most useful kind of index to create.
### replace?
```ts
optional replace: boolean;
```
> `optional` **replace**: `boolean`
Whether to replace the existing index

View File

@@ -8,52 +8,32 @@
## Properties
### distanceType?
### indexType?
```ts
optional distanceType: string;
```
The type of the distance function used by the index. This is only
present for vector indices. Scalar and full text search indices do
not have a distance function.
***
### indexType
```ts
indexType: string;
```
> `optional` **indexType**: `string`
The type of the index
***
### indices
> **indices**: [`IndexMetadata`](IndexMetadata.md)[]
The metadata for each index
***
### numIndexedRows
```ts
numIndexedRows: number;
```
> **numIndexedRows**: `number`
The number of rows indexed by the index
***
### numIndices?
```ts
optional numIndices: number;
```
The number of parts this index is split into.
***
### numUnindexedRows
```ts
numUnindexedRows: number;
```
> **numUnindexedRows**: `number`
The number of rows not indexed

View File

@@ -12,9 +12,7 @@ Options to create an `IVF_PQ` index
### distanceType?
```ts
optional distanceType: "l2" | "cosine" | "dot";
```
> `optional` **distanceType**: `"l2"` \| `"cosine"` \| `"dot"`
Distance type to use to build the index.
@@ -52,9 +50,7 @@ L2 norm is 1), then dot distance is equivalent to the cosine distance.
### maxIterations?
```ts
optional maxIterations: number;
```
> `optional` **maxIterations**: `number`
Max iteration to train IVF kmeans.
@@ -70,9 +66,7 @@ The default value is 50.
### numPartitions?
```ts
optional numPartitions: number;
```
> `optional` **numPartitions**: `number`
The number of IVF partitions to create.
@@ -88,9 +82,7 @@ part of the search (searching within a partition) will be slow.
### numSubVectors?
```ts
optional numSubVectors: number;
```
> `optional` **numSubVectors**: `number`
Number of sub-vectors of PQ.
@@ -109,9 +101,7 @@ will likely result in poor performance.
### sampleRate?
```ts
optional sampleRate: number;
```
> `optional` **sampleRate**: `number`
The number of vectors, per partition, to sample when training IVF kmeans.

View File

@@ -1,39 +0,0 @@
[**@lancedb/lancedb**](../README.md) • **Docs**
***
[@lancedb/lancedb](../globals.md) / OptimizeOptions
# Interface: OptimizeOptions
## Properties
### cleanupOlderThan
```ts
cleanupOlderThan: Date;
```
If set then all versions older than the given date
be removed. The current version will never be removed.
The default is 7 days
#### Example
```ts
// Delete all versions older than 1 day
const olderThan = new Date();
olderThan.setDate(olderThan.getDate() - 1));
tbl.cleanupOlderVersions(olderThan);
// Delete all versions except the current version
tbl.cleanupOlderVersions(new Date());
```
***
### deleteUnverified
```ts
deleteUnverified: boolean;
```

View File

@@ -1,90 +0,0 @@
[**@lancedb/lancedb**](../README.md) • **Docs**
***
[@lancedb/lancedb](../globals.md) / RetryConfig
# Interface: RetryConfig
Retry configuration for the remote HTTP client.
## Properties
### backoffFactor?
```ts
optional backoffFactor: number;
```
The backoff factor to apply between retries. Default is 0.25. Between each retry
the client will wait for the amount of seconds:
`{backoff factor} * (2 ** ({number of previous retries}))`. So for the default
of 0.25, the first retry will wait 0.25 seconds, the second retry will wait 0.5
seconds, the third retry will wait 1 second, etc.
You can also set this via the environment variable
`LANCE_CLIENT_RETRY_BACKOFF_FACTOR`.
***
### backoffJitter?
```ts
optional backoffJitter: number;
```
The jitter to apply to the backoff factor, in seconds. Default is 0.25.
A random value between 0 and `backoff_jitter` will be added to the backoff
factor in seconds. So for the default of 0.25 seconds, between 0 and 250
milliseconds will be added to the sleep between each retry.
You can also set this via the environment variable
`LANCE_CLIENT_RETRY_BACKOFF_JITTER`.
***
### connectRetries?
```ts
optional connectRetries: number;
```
The maximum number of retries for connection errors. Default is 3. You
can also set this via the environment variable `LANCE_CLIENT_CONNECT_RETRIES`.
***
### readRetries?
```ts
optional readRetries: number;
```
The maximum number of retries for read errors. Default is 3. You can also
set this via the environment variable `LANCE_CLIENT_READ_RETRIES`.
***
### retries?
```ts
optional retries: number;
```
The maximum number of retries for a request. Default is 3. You can also
set this via the environment variable `LANCE_CLIENT_MAX_RETRIES`.
***
### statuses?
```ts
optional statuses: number[];
```
The HTTP status codes for which to retry the request. Default is
[429, 500, 502, 503].
You can also set this via the environment variable
`LANCE_CLIENT_RETRY_STATUSES`. Use a comma-separated list of integers.

Some files were not shown because too many files have changed in this diff Show More