Compare commits

..

6 Commits

Author SHA1 Message Date
Will Jones
4dc7cef280 fixes for action 2023-05-24 14:26:11 -07:00
Will Jones
47f5163768 cleanup 2023-05-23 18:43:24 -07:00
Will Jones
7ea809d8a0 match versions 2023-05-23 17:41:42 -07:00
Will Jones
8d7726b1ea fill out rest of release script 2023-05-23 17:40:34 -07:00
Will Jones
f5bb2a2096 more progress on release workflow 2023-05-23 17:14:58 -07:00
Will Jones
89aee07fa9 wip: see if we can build the lib in ci 2023-05-22 14:27:47 -07:00
566 changed files with 11832 additions and 91522 deletions

View File

@@ -1,57 +0,0 @@
[tool.bumpversion]
current_version = "0.10.0-beta.1"
parse = """(?x)
(?P<major>0|[1-9]\\d*)\\.
(?P<minor>0|[1-9]\\d*)\\.
(?P<patch>0|[1-9]\\d*)
(?:-(?P<pre_l>[a-zA-Z-]+)\\.(?P<pre_n>0|[1-9]\\d*))?
"""
serialize = [
"{major}.{minor}.{patch}-{pre_l}.{pre_n}",
"{major}.{minor}.{patch}",
]
search = "{current_version}"
replace = "{new_version}"
regex = false
ignore_missing_version = false
ignore_missing_files = false
tag = true
sign_tags = false
tag_name = "v{new_version}"
tag_message = "Bump version: {current_version} → {new_version}"
allow_dirty = true
commit = true
message = "Bump version: {current_version} → {new_version}"
commit_args = ""
[tool.bumpversion.parts.pre_l]
values = ["beta", "final"]
optional_value = "final"
[[tool.bumpversion.files]]
filename = "node/package.json"
search = "\"version\": \"{current_version}\","
replace = "\"version\": \"{new_version}\","
[[tool.bumpversion.files]]
filename = "nodejs/package.json"
search = "\"version\": \"{current_version}\","
replace = "\"version\": \"{new_version}\","
# nodejs binary packages
[[tool.bumpversion.files]]
glob = "nodejs/npm/*/package.json"
search = "\"version\": \"{current_version}\","
replace = "\"version\": \"{new_version}\","
# Cargo files
# ------------
[[tool.bumpversion.files]]
filename = "rust/ffi/node/Cargo.toml"
search = "\nversion = \"{current_version}\""
replace = "\nversion = \"{new_version}\""
[[tool.bumpversion.files]]
filename = "rust/lancedb/Cargo.toml"
search = "\nversion = \"{current_version}\""
replace = "\nversion = \"{new_version}\""

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

33
.github/labeler.yml vendored
View File

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

View File

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

View File

@@ -1,63 +0,0 @@
# We create a composite action to be re-used both for testing and for releasing
name: build-linux-wheel
description: "Build a manylinux wheel for lance"
inputs:
python-minor-version:
description: "8, 9, 10, 11, 12"
required: true
args:
description: "--release"
required: false
default: ""
arm-build:
description: "Build for arm64 instead of x86_64"
# Note: this does *not* mean the host is arm64, since we might be cross-compiling.
required: false
default: "false"
manylinux:
description: "The manylinux version to build for"
required: false
default: "2_17"
runs:
using: "composite"
steps:
- name: CONFIRM ARM BUILD
shell: bash
run: |
echo "ARM BUILD: ${{ inputs.arm-build }}"
- name: Build x86_64 Manylinux wheel
if: ${{ inputs.arm-build == 'false' }}
uses: PyO3/maturin-action@v1
with:
command: build
working-directory: python
target: x86_64-unknown-linux-gnu
manylinux: ${{ inputs.manylinux }}
args: ${{ inputs.args }}
before-script-linux: |
set -e
yum install -y openssl-devel \
&& curl -L https://github.com/protocolbuffers/protobuf/releases/download/v24.4/protoc-24.4-linux-$(uname -m).zip > /tmp/protoc.zip \
&& unzip /tmp/protoc.zip -d /usr/local \
&& rm /tmp/protoc.zip
- name: Build Arm Manylinux Wheel
if: ${{ inputs.arm-build == 'true' }}
uses: PyO3/maturin-action@v1
with:
command: build
working-directory: python
docker-options: "-e PIP_EXTRA_INDEX_URL=https://pypi.fury.io/lancedb/"
target: aarch64-unknown-linux-gnu
manylinux: ${{ inputs.manylinux }}
args: ${{ inputs.args }}
before-script-linux: |
set -e
apt install -y unzip
if [ $(uname -m) = "x86_64" ]; then
PROTOC_ARCH="x86_64"
else
PROTOC_ARCH="aarch_64"
fi
curl -L https://github.com/protocolbuffers/protobuf/releases/download/v24.4/protoc-24.4-linux-$PROTOC_ARCH.zip > /tmp/protoc.zip \
&& unzip /tmp/protoc.zip -d /usr/local \
&& rm /tmp/protoc.zip

View File

@@ -1,26 +0,0 @@
# We create a composite action to be re-used both for testing and for releasing
name: build_wheel
description: "Build a lance wheel"
inputs:
python-minor-version:
description: "8, 9, 10, 11"
required: true
args:
description: "--release"
required: false
default: ""
runs:
using: "composite"
steps:
- name: Install macos dependency
shell: bash
run: |
brew install protobuf
- name: Build wheel
uses: PyO3/maturin-action@v1
with:
command: build
args: ${{ inputs.args }}
docker-options: "-e PIP_EXTRA_INDEX_URL=https://pypi.fury.io/lancedb/"
working-directory: python
interpreter: 3.${{ inputs.python-minor-version }}

View File

@@ -1,34 +0,0 @@
# We create a composite action to be re-used both for testing and for releasing
name: build_wheel
description: "Build a lance wheel"
inputs:
python-minor-version:
description: "8, 9, 10, 11"
required: true
args:
description: "--release"
required: false
default: ""
runs:
using: "composite"
steps:
- name: Install Protoc v21.12
working-directory: C:\
run: |
New-Item -Path 'C:\protoc' -ItemType Directory
Set-Location C:\protoc
Invoke-WebRequest https://github.com/protocolbuffers/protobuf/releases/download/v21.12/protoc-21.12-win64.zip -OutFile C:\protoc\protoc.zip
7z x protoc.zip
Add-Content $env:GITHUB_PATH "C:\protoc\bin"
shell: powershell
- name: Build wheel
uses: PyO3/maturin-action@v1
with:
command: build
args: ${{ inputs.args }}
docker-options: "-e PIP_EXTRA_INDEX_URL=https://pypi.fury.io/lancedb/"
working-directory: python
- uses: actions/upload-artifact@v3
with:
name: windows-wheels
path: python\target\wheels

View File

@@ -1,36 +0,0 @@
name: Cargo Publish
on:
push:
tags-ignore:
# We don't publish pre-releases for Rust. Crates.io is just a source
# distribution, so we don't need to publish pre-releases.
- 'v*-beta*'
- '*-v*' # for example, python-vX.Y.Z
env:
# This env var is used by Swatinem/rust-cache@v2 for the cache
# key, so we set it to make sure it is always consistent.
CARGO_TERM_COLOR: always
# Up-to-date compilers needed for fp16kernels.
CC: gcc-12
CXX: g++-12
jobs:
build:
runs-on: ubuntu-22.04
timeout-minutes: 30
# Only runs on tags that matches the make-release action
if: startsWith(github.ref, 'refs/tags/v')
steps:
- uses: actions/checkout@v4
- uses: Swatinem/rust-cache@v2
with:
workspaces: rust
- name: Install dependencies
run: |
sudo apt update
sudo apt install -y protobuf-compiler libssl-dev
- name: Publish the package
run: |
cargo publish -p lancedb --all-features --token ${{ secrets.CARGO_REGISTRY_TOKEN }}

View File

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

View File

@@ -24,16 +24,12 @@ jobs:
environment:
name: github-pages
url: ${{ steps.deployment.outputs.page_url }}
runs-on: buildjet-8vcpu-ubuntu-2204
runs-on: ubuntu-22.04
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Install dependecies needed for ubuntu
run: |
sudo apt install -y protobuf-compiler libssl-dev
rustup update && rustup default
uses: actions/checkout@v3
- name: Set up Python
uses: actions/setup-python@v5
uses: actions/setup-python@v4
with:
python-version: "3.10"
cache: "pip"
@@ -43,32 +39,9 @@ jobs:
run: |
python -m pip install -e .
python -m pip install -r ../docs/requirements.txt
- name: Set up node
uses: actions/setup-node@v3
with:
node-version: 20
cache: 'npm'
cache-dependency-path: node/package-lock.json
- uses: Swatinem/rust-cache@v2
- name: Install node dependencies
working-directory: node
run: |
sudo apt update
sudo apt install -y protobuf-compiler libssl-dev
- name: Build node
working-directory: node
run: |
npm ci
npm run build
npm run tsc
- name: Create markdown files
working-directory: node
run: |
npx typedoc --plugin typedoc-plugin-markdown --out ../docs/src/javascript src/index.ts
- name: Build docs
working-directory: docs
run: |
PYTHONPATH=. mkdocs build
PYTHONPATH=. mkdocs build -f docs/mkdocs.yml
- name: Setup Pages
uses: actions/configure-pages@v2
- name: Upload artifact

View File

@@ -1,108 +0,0 @@
name: Documentation Code Testing
on:
push:
branches:
- main
paths:
- docs/**
- .github/workflows/docs_test.yml
pull_request:
paths:
- docs/**
- .github/workflows/docs_test.yml
# Allows you to run this workflow manually from the Actions tab
workflow_dispatch:
env:
# Disable full debug symbol generation to speed up CI build and keep memory down
# "1" means line tables only, which is useful for panic tracebacks.
RUSTFLAGS: "-C debuginfo=1 -C target-cpu=haswell -C target-feature=+f16c,+avx2,+fma"
RUST_BACKTRACE: "1"
jobs:
test-python:
name: Test doc python code
runs-on: "warp-ubuntu-latest-x64-4x"
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Print CPU capabilities
run: cat /proc/cpuinfo
- name: Install protobuf
run: |
sudo apt update
sudo apt install -y protobuf-compiler
- name: Install dependecies needed for ubuntu
run: |
sudo apt install -y libssl-dev
rustup update && rustup default
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: 3.11
cache: "pip"
cache-dependency-path: "docs/test/requirements.txt"
- name: Rust cache
uses: swatinem/rust-cache@v2
- name: Build Python
working-directory: docs/test
run:
python -m pip install -r requirements.txt
- name: Create test files
run: |
cd docs/test
python md_testing.py
- name: Test
run: |
cd docs/test/python
for d in *; do cd "$d"; echo "$d".py; python "$d".py; cd ..; done
test-node:
name: Test doc nodejs code
runs-on: "warp-ubuntu-latest-x64-4x"
timeout-minutes: 60
strategy:
fail-fast: false
steps:
- name: Checkout
uses: actions/checkout@v4
with:
fetch-depth: 0
lfs: true
- name: Print CPU capabilities
run: cat /proc/cpuinfo
- name: Set up Node
uses: actions/setup-node@v4
with:
node-version: 20
- name: Install protobuf
run: |
sudo apt update
sudo apt install -y protobuf-compiler
- name: Install dependecies needed for ubuntu
run: |
sudo apt install -y libssl-dev
rustup update && rustup default
- name: Rust cache
uses: swatinem/rust-cache@v2
- name: Install node dependencies
run: |
sudo swapoff -a
sudo fallocate -l 8G /swapfile
sudo chmod 600 /swapfile
sudo mkswap /swapfile
sudo swapon /swapfile
sudo swapon --show
cd node
npm ci
npm run build-release
cd ../docs
npm install
- name: Test
env:
LANCEDB_URI: ${{ secrets.LANCEDB_URI }}
LANCEDB_DEV_API_KEY: ${{ secrets.LANCEDB_DEV_API_KEY }}
run: |
cd docs
npm t

View File

@@ -1,109 +0,0 @@
name: Build and publish Java packages
on:
release:
types: [released]
pull_request:
paths:
- .github/workflows/java-publish.yml
jobs:
macos-arm64:
name: Build on MacOS Arm64
runs-on: macos-14
timeout-minutes: 45
defaults:
run:
working-directory: ./java/core/lancedb-jni
steps:
- name: Checkout repository
uses: actions/checkout@v4
- uses: Swatinem/rust-cache@v2
- name: Install dependencies
run: |
brew install protobuf
- name: Build release
run: |
cargo build --release
- uses: actions/upload-artifact@v4
with:
name: liblancedb_jni_darwin_aarch64.zip
path: target/release/liblancedb_jni.dylib
retention-days: 1
if-no-files-found: error
linux-arm64:
name: Build on Linux Arm64
runs-on: warp-ubuntu-2204-arm64-8x
timeout-minutes: 45
defaults:
run:
working-directory: ./java/core/lancedb-jni
steps:
- name: Checkout repository
uses: actions/checkout@v4
- uses: Swatinem/rust-cache@v2
- uses: actions-rust-lang/setup-rust-toolchain@v1
with:
toolchain: "1.79.0"
cache-workspaces: "./java/core/lancedb-jni"
# Disable full debug symbol generation to speed up CI build and keep memory down
# "1" means line tables only, which is useful for panic tracebacks.
rustflags: "-C debuginfo=1"
- name: Install dependencies
run: |
sudo apt -y -qq update
sudo apt install -y protobuf-compiler libssl-dev pkg-config
- name: Build release
run: |
cargo build --release
- uses: actions/upload-artifact@v4
with:
name: liblancedb_jni_linux_aarch64.zip
path: target/release/liblancedb_jni.so
retention-days: 1
if-no-files-found: error
linux-x86:
runs-on: warp-ubuntu-2204-x64-8x
timeout-minutes: 30
needs: [macos-arm64, linux-arm64]
defaults:
run:
working-directory: ./java
steps:
- name: Checkout repository
uses: actions/checkout@v4
- uses: Swatinem/rust-cache@v2
- name: Set up Java 8
uses: actions/setup-java@v4
with:
distribution: temurin
java-version: 8
cache: "maven"
server-id: ossrh
server-username: SONATYPE_USER
server-password: SONATYPE_TOKEN
gpg-private-key: ${{ secrets.GPG_PRIVATE_KEY }}
gpg-passphrase: ${{ secrets.GPG_PASSPHRASE }}
- name: Install dependencies
run: |
sudo apt -y -qq update
sudo apt install -y protobuf-compiler libssl-dev pkg-config
- name: Download artifact
uses: actions/download-artifact@v4
- name: Copy native libs
run: |
mkdir -p ./core/target/classes/nativelib/darwin-aarch64 ./core/target/classes/nativelib/linux-aarch64
cp ../liblancedb_jni_darwin_aarch64.zip/liblancedb_jni.dylib ./core/target/classes/nativelib/darwin-aarch64/liblancedb_jni.dylib
cp ../liblancedb_jni_linux_aarch64.zip/liblancedb_jni.so ./core/target/classes/nativelib/linux-aarch64/liblancedb_jni.so
- name: Set github
run: |
git config --global user.email "LanceDB Github Runner"
git config --global user.name "dev+gha@lancedb.com"
- name: Publish with Java 8
run: |
echo "use-agent" >> ~/.gnupg/gpg.conf
echo "pinentry-mode loopback" >> ~/.gnupg/gpg.conf
export GPG_TTY=$(tty)
mvn --batch-mode -DskipTests -DpushChanges=false -Dgpg.passphrase=${{ secrets.GPG_PASSPHRASE }} deploy -P deploy-to-ossrh
env:
SONATYPE_USER: ${{ secrets.SONATYPE_USER }}
SONATYPE_TOKEN: ${{ secrets.SONATYPE_TOKEN }}

View File

@@ -1,113 +0,0 @@
name: Build and Run Java JNI Tests
on:
push:
branches:
- main
paths:
- java/**
pull_request:
paths:
- java/**
- rust/**
- .github/workflows/java.yml
env:
# This env var is used by Swatinem/rust-cache@v2 for the cache
# key, so we set it to make sure it is always consistent.
CARGO_TERM_COLOR: always
# Disable full debug symbol generation to speed up CI build and keep memory down
# "1" means line tables only, which is useful for panic tracebacks.
RUSTFLAGS: "-C debuginfo=1"
RUST_BACKTRACE: "1"
# according to: https://matklad.github.io/2021/09/04/fast-rust-builds.html
# CI builds are faster with incremental disabled.
CARGO_INCREMENTAL: "0"
CARGO_BUILD_JOBS: "1"
jobs:
linux-build-java-11:
runs-on: ubuntu-22.04
name: ubuntu-22.04 + Java 11
defaults:
run:
working-directory: ./java
steps:
- name: Checkout repository
uses: actions/checkout@v4
- uses: Swatinem/rust-cache@v2
with:
workspaces: java/core/lancedb-jni
- name: Run cargo fmt
run: cargo fmt --check
working-directory: ./java/core/lancedb-jni
- name: Install dependencies
run: |
sudo apt update
sudo apt install -y protobuf-compiler libssl-dev
- name: Install Java 11
uses: actions/setup-java@v4
with:
distribution: temurin
java-version: 11
cache: "maven"
- name: Java Style Check
run: mvn checkstyle:check
# Disable because of issues in lancedb rust core code
# - name: Rust Clippy
# working-directory: java/core/lancedb-jni
# run: cargo clippy --all-targets -- -D warnings
- name: Running tests with Java 11
run: mvn clean test
linux-build-java-17:
runs-on: ubuntu-22.04
name: ubuntu-22.04 + Java 17
defaults:
run:
working-directory: ./java
steps:
- name: Checkout repository
uses: actions/checkout@v4
- uses: Swatinem/rust-cache@v2
with:
workspaces: java/core/lancedb-jni
- name: Run cargo fmt
run: cargo fmt --check
working-directory: ./java/core/lancedb-jni
- name: Install dependencies
run: |
sudo apt update
sudo apt install -y protobuf-compiler libssl-dev
- name: Install Java 17
uses: actions/setup-java@v4
with:
distribution: temurin
java-version: 17
cache: "maven"
- run: echo "JAVA_17=$JAVA_HOME" >> $GITHUB_ENV
- name: Java Style Check
run: mvn checkstyle:check
# Disable because of issues in lancedb rust core code
# - name: Rust Clippy
# working-directory: java/core/lancedb-jni
# run: cargo clippy --all-targets -- -D warnings
- name: Running tests with Java 17
run: |
export JAVA_TOOL_OPTIONS="$JAVA_TOOL_OPTIONS \
-XX:+IgnoreUnrecognizedVMOptions \
--add-opens=java.base/java.lang=ALL-UNNAMED \
--add-opens=java.base/java.lang.invoke=ALL-UNNAMED \
--add-opens=java.base/java.lang.reflect=ALL-UNNAMED \
--add-opens=java.base/java.io=ALL-UNNAMED \
--add-opens=java.base/java.net=ALL-UNNAMED \
--add-opens=java.base/java.nio=ALL-UNNAMED \
--add-opens=java.base/java.util=ALL-UNNAMED \
--add-opens=java.base/java.util.concurrent=ALL-UNNAMED \
--add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED \
--add-opens=java.base/jdk.internal.ref=ALL-UNNAMED \
--add-opens=java.base/sun.nio.ch=ALL-UNNAMED \
--add-opens=java.base/sun.nio.cs=ALL-UNNAMED \
--add-opens=java.base/sun.security.action=ALL-UNNAMED \
--add-opens=java.base/sun.util.calendar=ALL-UNNAMED \
--add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED \
-Djdk.reflect.useDirectMethodHandle=false \
-Dio.netty.tryReflectionSetAccessible=true"
JAVA_HOME=$JAVA_17 mvn clean test

View File

@@ -1,99 +0,0 @@
name: Create release commit
# This workflow increments versions, tags the version, and pushes it.
# When a tag is pushed, another workflow is triggered that creates a GH release
# and uploads the binaries. This workflow is only for creating the tag.
# This script will enforce that a minor version is incremented if there are any
# breaking changes since the last minor increment. However, it isn't able to
# differentiate between breaking changes in Node versus Python. If you wish to
# bypass this check, you can manually increment the version and push the tag.
on:
workflow_dispatch:
inputs:
dry_run:
description: 'Dry run (create the local commit/tags but do not push it)'
required: true
default: false
type: boolean
type:
description: 'What kind of release is this?'
required: true
default: 'preview'
type: choice
options:
- preview
- stable
python:
description: 'Make a Python release'
required: true
default: true
type: boolean
other:
description: 'Make a Node/Rust release'
required: true
default: true
type: boolean
bump-minor:
description: 'Bump minor version'
required: true
default: false
type: boolean
jobs:
make-release:
# Creates tag and GH release. The GH release will trigger the build and release jobs.
runs-on: ubuntu-latest
permissions:
contents: write
steps:
- name: Output Inputs
run: echo "${{ toJSON(github.event.inputs) }}"
- uses: actions/checkout@v4
with:
fetch-depth: 0
lfs: true
# It's important we use our token here, as the default token will NOT
# trigger any workflows watching for new tags. See:
# https://docs.github.com/en/actions/using-workflows/triggering-a-workflow#triggering-a-workflow-from-a-workflow
token: ${{ secrets.LANCEDB_RELEASE_TOKEN }}
- name: Set git configs for bumpversion
shell: bash
run: |
git config user.name 'Lance Release'
git config user.email 'lance-dev@lancedb.com'
- name: Set up Python 3.11
uses: actions/setup-python@v5
with:
python-version: "3.11"
- name: Bump Python version
if: ${{ inputs.python }}
working-directory: python
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
# Need to get the commit before bumping the version, so we can
# determine if there are breaking changes in the next step as well.
echo "COMMIT_BEFORE_BUMP=$(git rev-parse HEAD)" >> $GITHUB_ENV
pip install bump-my-version PyGithub packaging
bash ../ci/bump_version.sh ${{ inputs.type }} ${{ inputs.bump-minor }} python-v
- name: Bump Node/Rust version
if: ${{ inputs.other }}
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
pip install bump-my-version PyGithub packaging
bash ci/bump_version.sh ${{ inputs.type }} ${{ inputs.bump-minor }} v $COMMIT_BEFORE_BUMP
- name: Push new version tag
if: ${{ !inputs.dry_run }}
uses: ad-m/github-push-action@master
with:
# Need to use PAT here too to trigger next workflow. See comment above.
github_token: ${{ secrets.LANCEDB_RELEASE_TOKEN }}
branch: ${{ github.ref }}
tags: true
- uses: ./.github/workflows/update_package_lock
if: ${{ !inputs.dry_run && inputs.other }}
with:
github_token: ${{ secrets.GITHUB_TOKEN }}

View File

@@ -9,35 +9,48 @@ on:
- node/**
- rust/ffi/node/**
- .github/workflows/node.yml
- docker-compose.yml
concurrency:
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: true
env:
# Disable full debug symbol generation to speed up CI build and keep memory down
# "1" means line tables only, which is useful for panic tracebacks.
#
# Use native CPU to accelerate tests if possible, especially for f16
# target-cpu=haswell fixes failing ci build
RUSTFLAGS: "-C debuginfo=1 -C target-cpu=haswell -C target-feature=+f16c,+avx2,+fma"
RUSTFLAGS: "-C debuginfo=1"
RUST_BACKTRACE: "1"
jobs:
lint:
name: Lint
runs-on: ubuntu-22.04
defaults:
run:
shell: bash
working-directory: node
steps:
- uses: actions/checkout@v3
with:
fetch-depth: 0
lfs: true
- uses: actions/setup-node@v3
with:
node-version: 18
cache: 'npm'
cache-dependency-path: node/package-lock.json
- name: Lint
run: |
npm ci
npm run lint
linux:
name: Linux (Node ${{ matrix.node-version }})
timeout-minutes: 30
strategy:
matrix:
node-version: [ "18", "20" ]
node-version: [ "16", "18" ]
runs-on: "ubuntu-22.04"
defaults:
run:
shell: bash
working-directory: node
steps:
- uses: actions/checkout@v4
- uses: actions/checkout@v3
with:
fetch-depth: 0
lfs: true
@@ -54,11 +67,10 @@ jobs:
- name: Build
run: |
npm ci
npm run tsc
npm run build
npm run pack-build
npm install --no-save ./dist/lancedb-vectordb-*.tgz
# Remove index.node to test with dependency installed
rm index.node
npm install --no-save ./dist/vectordb-*.tgz
- name: Test
run: npm run test
macos:
@@ -69,13 +81,13 @@ jobs:
shell: bash
working-directory: node
steps:
- uses: actions/checkout@v4
- uses: actions/checkout@v3
with:
fetch-depth: 0
lfs: true
- uses: actions/setup-node@v3
with:
node-version: 20
node-version: 18
cache: 'npm'
cache-dependency-path: node/package-lock.json
- uses: Swatinem/rust-cache@v2
@@ -84,64 +96,10 @@ jobs:
- name: Build
run: |
npm ci
npm run tsc
npm run build
npm run pack-build
npm install --no-save ./dist/lancedb-vectordb-*.tgz
# Remove index.node to test with dependency installed
rm index.node
npm install --no-save ./dist/vectordb-*.tgz
- name: Test
run: |
npm run test
aws-integtest:
timeout-minutes: 45
runs-on: "ubuntu-22.04"
defaults:
run:
shell: bash
working-directory: node
env:
AWS_ACCESS_KEY_ID: ACCESSKEY
AWS_SECRET_ACCESS_KEY: SECRETKEY
AWS_DEFAULT_REGION: us-west-2
# this one is for s3
AWS_ENDPOINT: http://localhost:4566
# this one is for dynamodb
DYNAMODB_ENDPOINT: http://localhost:4566
ALLOW_HTTP: true
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
lfs: true
- uses: actions/setup-node@v3
with:
node-version: 20
cache: 'npm'
cache-dependency-path: node/package-lock.json
- name: start local stack
run: docker compose -f ../docker-compose.yml up -d --wait
- name: create s3
run: aws s3 mb s3://lancedb-integtest --endpoint $AWS_ENDPOINT
- name: create ddb
run: |
aws dynamodb create-table \
--table-name lancedb-integtest \
--attribute-definitions '[{"AttributeName": "base_uri", "AttributeType": "S"}, {"AttributeName": "version", "AttributeType": "N"}]' \
--key-schema '[{"AttributeName": "base_uri", "KeyType": "HASH"}, {"AttributeName": "version", "KeyType": "RANGE"}]' \
--provisioned-throughput '{"ReadCapacityUnits": 10, "WriteCapacityUnits": 10}' \
--endpoint-url $DYNAMODB_ENDPOINT
- uses: Swatinem/rust-cache@v2
- name: Install dependencies
run: |
sudo apt update
sudo apt install -y protobuf-compiler libssl-dev
- name: Build
run: |
npm ci
npm run build
npm run pack-build
npm install --no-save ./dist/lancedb-vectordb-*.tgz
# Remove index.node to test with dependency installed
rm index.node
- name: Test
run: npm run integration-test

View File

@@ -1,122 +0,0 @@
name: NodeJS (NAPI)
on:
push:
branches:
- main
pull_request:
paths:
- nodejs/**
- .github/workflows/nodejs.yml
- docker-compose.yml
concurrency:
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: true
env:
# Disable full debug symbol generation to speed up CI build and keep memory down
# "1" means line tables only, which is useful for panic tracebacks.
RUSTFLAGS: "-C debuginfo=1"
RUST_BACKTRACE: "1"
jobs:
lint:
name: Lint
runs-on: ubuntu-22.04
defaults:
run:
shell: bash
working-directory: nodejs
env:
# Need up-to-date compilers for kernels
CC: gcc-12
CXX: g++-12
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
lfs: true
- uses: actions/setup-node@v3
with:
node-version: 20
cache: 'npm'
cache-dependency-path: nodejs/package-lock.json
- uses: Swatinem/rust-cache@v2
- name: Install dependencies
run: |
sudo apt update
sudo apt install -y protobuf-compiler libssl-dev
- name: Lint
run: |
cargo fmt --all -- --check
cargo clippy --all --all-features -- -D warnings
npm ci
npm run lint-ci
linux:
name: Linux (NodeJS ${{ matrix.node-version }})
timeout-minutes: 30
strategy:
matrix:
node-version: [ "18", "20" ]
runs-on: "ubuntu-22.04"
defaults:
run:
shell: bash
working-directory: nodejs
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
lfs: true
- uses: actions/setup-node@v3
with:
node-version: ${{ matrix.node-version }}
cache: 'npm'
cache-dependency-path: node/package-lock.json
- uses: Swatinem/rust-cache@v2
- name: Install dependencies
run: |
sudo apt update
sudo apt install -y protobuf-compiler libssl-dev
npm install -g @napi-rs/cli
- name: Build
run: |
npm ci
npm run build
- name: Setup localstack
working-directory: .
run: docker compose up --detach --wait
- name: Test
env:
S3_TEST: "1"
run: npm run test
macos:
timeout-minutes: 30
runs-on: "macos-14"
defaults:
run:
shell: bash
working-directory: nodejs
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
lfs: true
- uses: actions/setup-node@v3
with:
node-version: 20
cache: 'npm'
cache-dependency-path: node/package-lock.json
- uses: Swatinem/rust-cache@v2
- name: Install dependencies
run: |
brew install protobuf
npm install -g @napi-rs/cli
- name: Build
run: |
npm ci
npm run build
- name: Test
run: |
npm run test

View File

@@ -1,460 +0,0 @@
name: NPM Publish
on:
push:
tags:
- "v*"
jobs:
node:
name: vectordb Typescript
runs-on: ubuntu-latest
# Only runs on tags that matches the make-release action
if: startsWith(github.ref, 'refs/tags/v')
defaults:
run:
shell: bash
working-directory: node
steps:
- name: Checkout
uses: actions/checkout@v4
- uses: actions/setup-node@v3
with:
node-version: 20
cache: "npm"
cache-dependency-path: node/package-lock.json
- name: Install dependencies
run: |
sudo apt update
sudo apt install -y protobuf-compiler libssl-dev
- name: Build
run: |
npm ci
npm run tsc
npm pack
- name: Upload Linux Artifacts
uses: actions/upload-artifact@v4
with:
name: node-package
path: |
node/vectordb-*.tgz
node-macos:
name: vectordb ${{ matrix.config.arch }}
strategy:
matrix:
config:
- arch: x86_64-apple-darwin
runner: macos-13
- arch: aarch64-apple-darwin
# xlarge is implicitly arm64.
runner: macos-14
runs-on: ${{ matrix.config.runner }}
# Only runs on tags that matches the make-release action
if: startsWith(github.ref, 'refs/tags/v')
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Install system dependencies
run: brew install protobuf
- name: Install npm dependencies
run: |
cd node
npm ci
- name: Build MacOS native node modules
run: bash ci/build_macos_artifacts.sh ${{ matrix.config.arch }}
- name: Upload Darwin Artifacts
uses: actions/upload-artifact@v4
with:
name: node-native-darwin-${{ matrix.config.arch }}
path: |
node/dist/lancedb-vectordb-darwin*.tgz
nodejs-macos:
name: lancedb ${{ matrix.config.arch }}
strategy:
matrix:
config:
- arch: x86_64-apple-darwin
runner: macos-13
- arch: aarch64-apple-darwin
# xlarge is implicitly arm64.
runner: macos-14
runs-on: ${{ matrix.config.runner }}
# Only runs on tags that matches the make-release action
if: startsWith(github.ref, 'refs/tags/v')
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Install system dependencies
run: brew install protobuf
- name: Install npm dependencies
run: |
cd nodejs
npm ci
- name: Build MacOS native nodejs modules
run: bash ci/build_macos_artifacts_nodejs.sh ${{ matrix.config.arch }}
- name: Upload Darwin Artifacts
uses: actions/upload-artifact@v4
with:
name: nodejs-native-darwin-${{ matrix.config.arch }}
path: |
nodejs/dist/*.node
node-linux:
name: vectordb (${{ matrix.config.arch}}-unknown-linux-gnu)
runs-on: ${{ matrix.config.runner }}
# Only runs on tags that matches the make-release action
if: startsWith(github.ref, 'refs/tags/v')
strategy:
fail-fast: false
matrix:
config:
- arch: x86_64
runner: ubuntu-latest
- arch: aarch64
# For successful fat LTO builds, we need a large runner to avoid OOM errors.
runner: warp-ubuntu-latest-arm64-4x
steps:
- name: Checkout
uses: actions/checkout@v4
# To avoid OOM errors on ARM, we create a swap file.
- name: Configure aarch64 build
if: ${{ matrix.config.arch == 'aarch64' }}
run: |
free -h
sudo fallocate -l 16G /swapfile
sudo chmod 600 /swapfile
sudo mkswap /swapfile
sudo swapon /swapfile
echo "/swapfile swap swap defaults 0 0" >> sudo /etc/fstab
# print info
swapon --show
free -h
- name: Build Linux Artifacts
run: |
bash ci/build_linux_artifacts.sh ${{ matrix.config.arch }}
- name: Upload Linux Artifacts
uses: actions/upload-artifact@v4
with:
name: node-native-linux-${{ matrix.config.arch }}
path: |
node/dist/lancedb-vectordb-linux*.tgz
nodejs-linux:
name: lancedb (${{ matrix.config.arch}}-unknown-linux-gnu
runs-on: ${{ matrix.config.runner }}
# Only runs on tags that matches the make-release action
if: startsWith(github.ref, 'refs/tags/v')
strategy:
fail-fast: false
matrix:
config:
- arch: x86_64
runner: ubuntu-latest
- arch: aarch64
# For successful fat LTO builds, we need a large runner to avoid OOM errors.
runner: buildjet-16vcpu-ubuntu-2204-arm
steps:
- name: Checkout
uses: actions/checkout@v4
# Buildjet aarch64 runners have only 1.5 GB RAM per core, vs 3.5 GB per core for
# x86_64 runners. To avoid OOM errors on ARM, we create a swap file.
- name: Configure aarch64 build
if: ${{ matrix.config.arch == 'aarch64' }}
run: |
free -h
sudo fallocate -l 16G /swapfile
sudo chmod 600 /swapfile
sudo mkswap /swapfile
sudo swapon /swapfile
echo "/swapfile swap swap defaults 0 0" >> sudo /etc/fstab
# print info
swapon --show
free -h
- name: Build Linux Artifacts
run: |
bash ci/build_linux_artifacts_nodejs.sh ${{ matrix.config.arch }}
- name: Upload Linux Artifacts
uses: actions/upload-artifact@v4
with:
name: nodejs-native-linux-${{ matrix.config.arch }}
path: |
nodejs/dist/*.node
# The generic files are the same in all distros so we just pick
# one to do the upload.
- name: Upload Generic Artifacts
if: ${{ matrix.config.arch == 'x86_64' }}
uses: actions/upload-artifact@v4
with:
name: nodejs-dist
path: |
nodejs/dist/*
!nodejs/dist/*.node
node-windows:
name: vectordb ${{ matrix.target }}
runs-on: windows-2022
# Only runs on tags that matches the make-release action
if: startsWith(github.ref, 'refs/tags/v')
strategy:
fail-fast: false
matrix:
target: [x86_64-pc-windows-msvc]
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Install Protoc v21.12
working-directory: C:\
run: |
New-Item -Path 'C:\protoc' -ItemType Directory
Set-Location C:\protoc
Invoke-WebRequest https://github.com/protocolbuffers/protobuf/releases/download/v21.12/protoc-21.12-win64.zip -OutFile C:\protoc\protoc.zip
7z x protoc.zip
Add-Content $env:GITHUB_PATH "C:\protoc\bin"
shell: powershell
- name: Install npm dependencies
run: |
cd node
npm ci
- name: Build Windows native node modules
run: .\ci\build_windows_artifacts.ps1 ${{ matrix.target }}
- name: Upload Windows Artifacts
uses: actions/upload-artifact@v4
with:
name: node-native-windows
path: |
node/dist/lancedb-vectordb-win32*.tgz
nodejs-windows:
name: lancedb ${{ matrix.target }}
runs-on: windows-2022
# Only runs on tags that matches the make-release action
if: startsWith(github.ref, 'refs/tags/v')
strategy:
fail-fast: false
matrix:
target: [x86_64-pc-windows-msvc]
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Install Protoc v21.12
working-directory: C:\
run: |
New-Item -Path 'C:\protoc' -ItemType Directory
Set-Location C:\protoc
Invoke-WebRequest https://github.com/protocolbuffers/protobuf/releases/download/v21.12/protoc-21.12-win64.zip -OutFile C:\protoc\protoc.zip
7z x protoc.zip
Add-Content $env:GITHUB_PATH "C:\protoc\bin"
shell: powershell
- name: Install npm dependencies
run: |
cd nodejs
npm ci
- name: Build Windows native node modules
run: .\ci\build_windows_artifacts_nodejs.ps1 ${{ matrix.target }}
- name: Upload Windows Artifacts
uses: actions/upload-artifact@v4
with:
name: nodejs-native-windows
path: |
nodejs/dist/*.node
release:
name: vectordb NPM Publish
needs: [node, node-macos, node-linux, node-windows]
runs-on: ubuntu-latest
# Only runs on tags that matches the make-release action
if: startsWith(github.ref, 'refs/tags/v')
steps:
- uses: actions/download-artifact@v4
with:
pattern: node-*
- name: Display structure of downloaded files
run: ls -R
- uses: actions/setup-node@v3
with:
node-version: 20
registry-url: "https://registry.npmjs.org"
- name: Publish to NPM
env:
NODE_AUTH_TOKEN: ${{ secrets.LANCEDB_NPM_REGISTRY_TOKEN }}
run: |
# Tag beta as "preview" instead of default "latest". See lancedb
# npm publish step for more info.
if [[ $GITHUB_REF =~ refs/tags/v(.*)-beta.* ]]; then
PUBLISH_ARGS="--tag preview"
fi
mv */*.tgz .
for filename in *.tgz; do
npm publish $PUBLISH_ARGS $filename
done
- name: Notify Slack Action
uses: ravsamhq/notify-slack-action@2.3.0
if: ${{ always() }}
with:
status: ${{ job.status }}
notify_when: "failure"
notification_title: "{workflow} is failing"
env:
SLACK_WEBHOOK_URL: ${{ secrets.ACTION_MONITORING_SLACK }}
release-nodejs:
name: lancedb NPM Publish
needs: [nodejs-macos, nodejs-linux, nodejs-windows]
runs-on: ubuntu-latest
# Only runs on tags that matches the make-release action
if: startsWith(github.ref, 'refs/tags/v')
defaults:
run:
shell: bash
working-directory: nodejs
steps:
- name: Checkout
uses: actions/checkout@v4
- uses: actions/download-artifact@v4
with:
name: nodejs-dist
path: nodejs/dist
- uses: actions/download-artifact@v4
name: Download arch-specific binaries
with:
pattern: nodejs-*
path: nodejs/nodejs-artifacts
merge-multiple: true
- name: Display structure of downloaded files
run: find .
- uses: actions/setup-node@v3
with:
node-version: 20
registry-url: "https://registry.npmjs.org"
- name: Install napi-rs
run: npm install -g @napi-rs/cli
- name: Prepare artifacts
run: npx napi artifacts -d nodejs-artifacts
- name: Display structure of staged files
run: find npm
- name: Publish to NPM
env:
NODE_AUTH_TOKEN: ${{ secrets.LANCEDB_NPM_REGISTRY_TOKEN }}
# By default, things are published to the latest tag. This is what is
# installed by default if the user does not specify a version. This is
# good for stable releases, but for pre-releases, we want to publish to
# the "preview" tag so they can install with `npm install lancedb@preview`.
# See: https://medium.com/@mbostock/prereleases-and-npm-e778fc5e2420
run: |
if [[ $GITHUB_REF =~ refs/tags/v(.*)-beta.* ]]; then
npm publish --access public --tag preview
else
npm publish --access public
fi
- name: Notify Slack Action
uses: ravsamhq/notify-slack-action@2.3.0
if: ${{ always() }}
with:
status: ${{ job.status }}
notify_when: "failure"
notification_title: "{workflow} is failing"
env:
SLACK_WEBHOOK_URL: ${{ secrets.ACTION_MONITORING_SLACK }}
update-package-lock:
needs: [release]
runs-on: ubuntu-latest
permissions:
contents: write
steps:
- name: Checkout
uses: actions/checkout@v4
with:
ref: main
persist-credentials: false
fetch-depth: 0
lfs: true
- uses: ./.github/workflows/update_package_lock
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
update-package-lock-nodejs:
needs: [release-nodejs]
runs-on: ubuntu-latest
permissions:
contents: write
steps:
- name: Checkout
uses: actions/checkout@v4
with:
ref: main
persist-credentials: false
fetch-depth: 0
lfs: true
- uses: ./.github/workflows/update_package_lock_nodejs
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
gh-release:
runs-on: ubuntu-latest
permissions:
contents: write
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
lfs: true
- name: Extract version
id: extract_version
env:
GITHUB_REF: ${{ github.ref }}
run: |
set -e
echo "Extracting tag and version from $GITHUB_REF"
if [[ $GITHUB_REF =~ refs/tags/v(.*) ]]; then
VERSION=${BASH_REMATCH[1]}
TAG=v$VERSION
echo "tag=$TAG" >> $GITHUB_OUTPUT
echo "version=$VERSION" >> $GITHUB_OUTPUT
else
echo "Failed to extract version from $GITHUB_REF"
exit 1
fi
echo "Extracted version $VERSION from $GITHUB_REF"
if [[ $VERSION =~ beta ]]; then
echo "This is a beta release"
# Get last release (that is not this one)
FROM_TAG=$(git tag --sort='version:refname' \
| grep ^v \
| grep -vF "$TAG" \
| python ci/semver_sort.py v \
| tail -n 1)
else
echo "This is a stable release"
# Get last stable tag (ignore betas)
FROM_TAG=$(git tag --sort='version:refname' \
| grep ^v \
| grep -vF "$TAG" \
| grep -v beta \
| python ci/semver_sort.py v \
| tail -n 1)
fi
echo "Found from tag $FROM_TAG"
echo "from_tag=$FROM_TAG" >> $GITHUB_OUTPUT
- name: Create Release Notes
id: release_notes
uses: mikepenz/release-changelog-builder-action@v4
with:
configuration: .github/release_notes.json
toTag: ${{ steps.extract_version.outputs.tag }}
fromTag: ${{ steps.extract_version.outputs.from_tag }}
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: Create GH release
uses: softprops/action-gh-release@v2
with:
prerelease: ${{ contains('beta', github.ref) }}
tag_name: ${{ steps.extract_version.outputs.tag }}
token: ${{ secrets.GITHUB_TOKEN }}
generate_release_notes: false
name: Node/Rust LanceDB v${{ steps.extract_version.outputs.version }}
body: ${{ steps.release_notes.outputs.changelog }}

View File

@@ -1,160 +0,0 @@
name: PyPI Publish
on:
push:
tags:
- 'python-v*'
jobs:
linux:
name: Python ${{ matrix.config.platform }} manylinux${{ matrix.config.manylinux }}
timeout-minutes: 60
strategy:
matrix:
config:
- platform: x86_64
manylinux: "2_17"
extra_args: ""
- platform: x86_64
manylinux: "2_28"
extra_args: "--features fp16kernels"
- platform: aarch64
manylinux: "2_24"
extra_args: ""
# We don't build fp16 kernels for aarch64, because it uses
# cross compilation image, which doesn't have a new enough compiler.
runs-on: "ubuntu-22.04"
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
lfs: true
- name: Set up Python
uses: actions/setup-python@v4
with:
python-version: 3.8
- uses: ./.github/workflows/build_linux_wheel
with:
python-minor-version: 8
args: "--release --strip ${{ matrix.config.extra_args }}"
arm-build: ${{ matrix.config.platform == 'aarch64' }}
manylinux: ${{ matrix.config.manylinux }}
- uses: ./.github/workflows/upload_wheel
with:
pypi_token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
fury_token: ${{ secrets.FURY_TOKEN }}
mac:
timeout-minutes: 60
runs-on: ${{ matrix.config.runner }}
strategy:
matrix:
config:
- target: x86_64-apple-darwin
runner: macos-13
- target: aarch64-apple-darwin
runner: macos-14
env:
MACOSX_DEPLOYMENT_TARGET: 10.15
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
lfs: true
- name: Set up Python
uses: actions/setup-python@v4
with:
python-version: 3.12
- uses: ./.github/workflows/build_mac_wheel
with:
python-minor-version: 8
args: "--release --strip --target ${{ matrix.config.target }} --features fp16kernels"
- uses: ./.github/workflows/upload_wheel
with:
pypi_token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
fury_token: ${{ secrets.FURY_TOKEN }}
windows:
timeout-minutes: 60
runs-on: windows-latest
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
lfs: true
- name: Set up Python
uses: actions/setup-python@v4
with:
python-version: 3.8
- uses: ./.github/workflows/build_windows_wheel
with:
python-minor-version: 8
args: "--release --strip"
vcpkg_token: ${{ secrets.VCPKG_GITHUB_PACKAGES }}
- uses: ./.github/workflows/upload_wheel
with:
pypi_token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
fury_token: ${{ secrets.FURY_TOKEN }}
gh-release:
runs-on: ubuntu-latest
permissions:
contents: write
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
lfs: true
- name: Extract version
id: extract_version
env:
GITHUB_REF: ${{ github.ref }}
run: |
set -e
echo "Extracting tag and version from $GITHUB_REF"
if [[ $GITHUB_REF =~ refs/tags/python-v(.*) ]]; then
VERSION=${BASH_REMATCH[1]}
TAG=python-v$VERSION
echo "tag=$TAG" >> $GITHUB_OUTPUT
echo "version=$VERSION" >> $GITHUB_OUTPUT
else
echo "Failed to extract version from $GITHUB_REF"
exit 1
fi
echo "Extracted version $VERSION from $GITHUB_REF"
if [[ $VERSION =~ beta ]]; then
echo "This is a beta release"
# Get last release (that is not this one)
FROM_TAG=$(git tag --sort='version:refname' \
| grep ^python-v \
| grep -vF "$TAG" \
| python ci/semver_sort.py python-v \
| tail -n 1)
else
echo "This is a stable release"
# Get last stable tag (ignore betas)
FROM_TAG=$(git tag --sort='version:refname' \
| grep ^python-v \
| grep -vF "$TAG" \
| grep -v beta \
| python ci/semver_sort.py python-v \
| tail -n 1)
fi
echo "Found from tag $FROM_TAG"
echo "from_tag=$FROM_TAG" >> $GITHUB_OUTPUT
- name: Create Python Release Notes
id: python_release_notes
uses: mikepenz/release-changelog-builder-action@v4
with:
configuration: .github/release_notes.json
toTag: ${{ steps.extract_version.outputs.tag }}
fromTag: ${{ steps.extract_version.outputs.from_tag }}
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: Create Python GH release
uses: softprops/action-gh-release@v2
with:
prerelease: ${{ contains('beta', github.ref) }}
tag_name: ${{ steps.extract_version.outputs.tag }}
token: ${{ secrets.GITHUB_TOKEN }}
generate_release_notes: false
name: Python LanceDB v${{ steps.extract_version.outputs.version }}
body: ${{ steps.python_release_notes.outputs.changelog }}

View File

@@ -8,188 +8,51 @@ on:
paths:
- python/**
- .github/workflows/python.yml
concurrency:
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: true
jobs:
lint:
name: "Lint"
timeout-minutes: 30
runs-on: "ubuntu-22.04"
defaults:
run:
shell: bash
working-directory: python
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
lfs: true
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: "3.11"
- name: Install ruff
run: |
pip install ruff==0.5.4
- name: Format check
run: ruff format --check .
- name: Lint
run: ruff check .
doctest:
name: "Doctest"
timeout-minutes: 30
runs-on: "ubuntu-22.04"
defaults:
run:
shell: bash
working-directory: python
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
lfs: true
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: "3.11"
cache: "pip"
- name: Install protobuf
run: |
sudo apt update
sudo apt install -y protobuf-compiler
- uses: Swatinem/rust-cache@v2
with:
workspaces: python
- name: Install
run: |
pip install --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests,dev,embeddings]
pip install tantivy
pip install mlx
- name: Doctest
run: pytest --doctest-modules python/lancedb
linux:
name: "Linux: python-3.${{ matrix.python-minor-version }}"
timeout-minutes: 30
strategy:
matrix:
python-minor-version: ["9", "11"]
python-minor-version: [ "8", "9", "10", "11" ]
runs-on: "ubuntu-22.04"
defaults:
run:
shell: bash
working-directory: python
steps:
- uses: actions/checkout@v4
- uses: actions/checkout@v3
with:
fetch-depth: 0
lfs: true
- name: Install protobuf
run: |
sudo apt update
sudo apt install -y protobuf-compiler
- name: Set up Python
uses: actions/setup-python@v5
uses: actions/setup-python@v4
with:
python-version: 3.${{ matrix.python-minor-version }}
- uses: Swatinem/rust-cache@v2
with:
workspaces: python
- uses: ./.github/workflows/build_linux_wheel
- uses: ./.github/workflows/run_tests
with:
integration: true
# Make sure wheels are not included in the Rust cache
- name: Delete wheels
run: rm -rf target/wheels
platform:
name: "Mac: ${{ matrix.config.name }}"
timeout-minutes: 30
strategy:
matrix:
config:
- name: x86
runner: macos-13
- name: Arm
runner: macos-14
runs-on: "${{ matrix.config.runner }}"
defaults:
run:
shell: bash
working-directory: python
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
lfs: true
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: "3.11"
- uses: Swatinem/rust-cache@v2
with:
workspaces: python
- uses: ./.github/workflows/build_mac_wheel
- uses: ./.github/workflows/run_tests
# Make sure wheels are not included in the Rust cache
- name: Delete wheels
run: rm -rf target/wheels
windows:
name: "Windows: ${{ matrix.config.name }}"
timeout-minutes: 30
strategy:
matrix:
config:
- name: x86
runner: windows-latest
runs-on: "${{ matrix.config.runner }}"
defaults:
run:
shell: bash
working-directory: python
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
lfs: true
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: "3.11"
- uses: Swatinem/rust-cache@v2
with:
workspaces: python
- uses: ./.github/workflows/build_windows_wheel
- uses: ./.github/workflows/run_tests
# Make sure wheels are not included in the Rust cache
- name: Delete wheels
run: rm -rf target/wheels
pydantic1x:
timeout-minutes: 30
runs-on: "ubuntu-22.04"
defaults:
run:
shell: bash
working-directory: python
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
lfs: true
- name: Install dependencies
run: |
sudo apt update
sudo apt install -y protobuf-compiler
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: 3.9
- name: Install lancedb
run: |
pip install "pydantic<2"
pip install --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests]
pip install tantivy
pip install -e .
pip install pytest
- name: Run tests
run: pytest -m "not slow and not s3_test" -x -v --durations=30 python/tests
run: pytest -x -v --durations=30 tests
mac:
timeout-minutes: 30
runs-on: "macos-12"
defaults:
run:
shell: bash
working-directory: python
steps:
- uses: actions/checkout@v3
with:
fetch-depth: 0
lfs: true
- name: Set up Python
uses: actions/setup-python@v4
with:
python-version: "3.10"
- name: Install lancedb
run: |
pip install -e .
pip install pytest
- name: Run tests
run: pytest -x -v --durations=30 tests

181
.github/workflows/release.yml vendored Normal file
View File

@@ -0,0 +1,181 @@
name: Prepare Release
# Based on https://github.com/dherman/neon-prebuild-example/blob/eaa4d33d682e5eb7abbc3da7aed153a1b1acb1b3/.github/workflows/publish.yml
on:
push:
tags:
- v*
jobs:
draft-release:
runs-on: ubuntu-latest
steps:
- uses: softprops/action-gh-release@v1
with:
draft: true
prerelease: true # hardcoded on for now
generate_release_notes: true
rust:
runs-on: ubuntu-latest
needs: draft-release
defaults:
run:
shell: bash
working-directory: rust/vectordb
steps:
- uses: actions/checkout@v3
with:
fetch-depth: 0
lfs: true
- name: Install dependencies
run: |
sudo apt update
sudo apt install -y protobuf-compiler libssl-dev
- name: Package Rust
run: cargo package --all-features
- uses: softprops/action-gh-release@v1
with:
draft: true
files: target/vectordb-*.crate
python:
runs-on: ubuntu-latest
needs: draft-release
defaults:
run:
shell: bash
working-directory: python
steps:
- uses: actions/checkout@v3
with:
fetch-depth: 0
lfs: true
- name: Set up Python
uses: actions/setup-python@v4
with:
python-version: "3.10"
- name: Build wheel
run: |
pip install wheel
python setup.py sdist bdist_wheel
- uses: softprops/action-gh-release@v1
with:
draft: true
files: |
python/dist/lancedb-*.tar.gz
python/dist/lancedb-*.whl
node:
runs-on: ubuntu-latest
needs: draft-release
defaults:
run:
shell: bash
working-directory: node
steps:
- name: Checkout
uses: actions/checkout@v2
- uses: actions/setup-node@v3
with:
node-version: 20
cache: 'npm'
cache-dependency-path: node/package-lock.json
- name: Install dependencies
run: |
sudo apt update
sudo apt install -y protobuf-compiler libssl-dev
- name: Build
run: |
npm ci
npm run tsc
npm pack
- uses: softprops/action-gh-release@v1
with:
draft: true
files: node/vectordb-*.tgz
node-macos:
runs-on: macos-12
needs: draft-release
strategy:
fail-fast: false
matrix:
target: [x86_64-apple-darwin, aarch64-apple-darwin]
steps:
- name: Checkout
uses: actions/checkout@v2
- name: Install system dependencies
run: brew install protobuf
- name: Install npm dependencies
run: |
cd node
npm ci
- name: Build MacOS native node modules
run: bash ci/build_macos_artifacts.sh ${{ matrix.target }}
- uses: softprops/action-gh-release@v1
with:
draft: true
files: node/dist/vectordb-darwin*.tgz
node-linux:
runs-on: ubuntu-latest
needs: draft-release
strategy:
fail-fast: false
matrix:
target:
- x86_64-unknown-linux-gnu
- aarch64-unknown-linux-gnu
- aarch64-unknown-linux-musl
- x86_64-unknown-linux-musl
steps:
- name: Checkout
uses: actions/checkout@v2
- name: Setup Rust
uses: ATiltedTree/setup-rust@v1
with:
rust-version: stable
- name: Install system dependencies
run: |
sudo apt update
sudo apt install -y protobuf-compiler libssl-dev
cargo install cross
- name: Install npm dependencies
run: |
cd node
npm ci
- name: Build Linux native node modules
run: bash ci/build_linux_artifacts.sh ${{ matrix.target }}
- uses: softprops/action-gh-release@v1
with:
draft: true
files: node/dist/vectordb-linux*.tgz
release:
needs: [python, node, node-macos, node-linux, rust]
runs-on: ubuntu-latest
steps:
- uses: actions/download-artifact@v3
- name: Publish to PyPI
env:
TWINE_USERNAME: __token__
TWINE_PASSWORD: ${{ secrets.PYPI_TOKEN }}
run: |
python -m twine upload --non-interactive \
--skip-existing \
--repository testpypi python/dist/*
- name: Publish to NPM
run: |
for filename in node/dist/*.tgz; do
npm publish --dry-run $filename
done
- name: Publish to crates.io
env:
CARGO_REGISTRY_TOKEN: ${{ secrets.CARGO_REGISTRY_TOKEN }}
run: |
cargo publish --dry-run --no-verify rust/target/vectordb-*.crate
# - uses: softprops/action-gh-release@v1
# with:
# draft: false

View File

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

View File

@@ -1,136 +0,0 @@
name: Rust
on:
push:
branches:
- main
pull_request:
paths:
- Cargo.toml
- rust/**
- .github/workflows/rust.yml
concurrency:
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: true
env:
# This env var is used by Swatinem/rust-cache@v2 for the cache
# key, so we set it to make sure it is always consistent.
CARGO_TERM_COLOR: always
# Disable full debug symbol generation to speed up CI build and keep memory down
# "1" means line tables only, which is useful for panic tracebacks.
RUSTFLAGS: "-C debuginfo=1"
RUST_BACKTRACE: "1"
jobs:
lint:
timeout-minutes: 30
runs-on: ubuntu-22.04
defaults:
run:
shell: bash
working-directory: rust
env:
# Need up-to-date compilers for kernels
CC: gcc-12
CXX: g++-12
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
lfs: true
- uses: Swatinem/rust-cache@v2
with:
workspaces: rust
- name: Install dependencies
run: |
sudo apt update
sudo apt install -y protobuf-compiler libssl-dev
- name: Run format
run: cargo fmt --all -- --check
- name: Run clippy
run: cargo clippy --all --all-features -- -D warnings
linux:
timeout-minutes: 30
# To build all features, we need more disk space than is available
# on the GitHub-provided runner. This is mostly due to the the
# sentence-transformers feature.
runs-on: warp-ubuntu-latest-x64-4x
defaults:
run:
shell: bash
working-directory: rust
env:
# Need up-to-date compilers for kernels
CC: gcc-12
CXX: g++-12
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
lfs: true
- uses: Swatinem/rust-cache@v2
with:
workspaces: rust
- name: Install dependencies
run: |
sudo apt update
sudo apt install -y protobuf-compiler libssl-dev
- name: 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" ]
runs-on: "${{ matrix.mac-runner }}"
defaults:
run:
shell: bash
working-directory: rust
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
lfs: true
- name: CPU features
run: sysctl -a | grep cpu
- uses: Swatinem/rust-cache@v2
with:
workspaces: rust
- name: Install dependencies
run: brew install protobuf
- name: Build
run: cargo build --all-features
- name: Run tests
# Run with everything except the integration tests.
run: cargo test --features remote,fp16kernels
windows:
runs-on: windows-2022
steps:
- uses: actions/checkout@v4
- uses: Swatinem/rust-cache@v2
with:
workspaces: rust
- name: Install Protoc v21.12
working-directory: C:\
run: |
New-Item -Path 'C:\protoc' -ItemType Directory
Set-Location C:\protoc
Invoke-WebRequest https://github.com/protocolbuffers/protobuf/releases/download/v21.12/protoc-21.12-win64.zip -OutFile C:\protoc\protoc.zip
7z x protoc.zip
Add-Content $env:GITHUB_PATH "C:\protoc\bin"
shell: powershell
- name: Run tests
run: |
$env:VCPKG_ROOT = $env:VCPKG_INSTALLATION_ROOT
cargo build
cargo test

View File

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

View File

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

View File

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

View File

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

View File

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

View File

@@ -1,44 +0,0 @@
name: upload-wheel
description: "Upload wheels to Pypi"
inputs:
pypi_token:
required: true
description: "release token for the repo"
fury_token:
required: true
description: "release token for the fury repo"
runs:
using: "composite"
steps:
- name: Install dependencies
shell: bash
run: |
python -m pip install --upgrade pip
pip install twine
- name: Choose repo
shell: bash
id: choose_repo
run: |
if [ ${{ github.ref }} == "*beta*" ]; then
echo "repo=fury" >> $GITHUB_OUTPUT
else
echo "repo=pypi" >> $GITHUB_OUTPUT
fi
- name: Publish to PyPI
shell: bash
env:
FURY_TOKEN: ${{ inputs.fury_token }}
PYPI_TOKEN: ${{ inputs.pypi_token }}
run: |
if [ ${{ steps.choose_repo.outputs.repo }} == "fury" ]; then
WHEEL=$(ls target/wheels/lancedb-*.whl 2> /dev/null | head -n 1)
echo "Uploading $WHEEL to Fury"
curl -f -F package=@$WHEEL https://$FURY_TOKEN@push.fury.io/lancedb/
else
twine upload --repository ${{ steps.choose_repo.outputs.repo }} \
--username __token__ \
--password $PYPI_TOKEN \
target/wheels/lancedb-*.whl
fi

16
.gitignore vendored
View File

@@ -3,11 +3,9 @@
*.egg-info
**/__pycache__
.DS_Store
venv
.venv
.vscode
.zed
rust/target
rust/Cargo.lock
@@ -19,15 +17,10 @@ site
python/build
python/dist
**/.ipynb_checkpoints
notebooks/.ipynb_checkpoints
**/.hypothesis
# Compiled Dynamic libraries
*.so
*.dylib
*.dll
## Javascript
*.node
**/node_modules
@@ -35,12 +28,7 @@ python/dist
node/dist
node/examples/**/package-lock.json
node/examples/**/dist
nodejs/lancedb/native*
dist
## Rust
target
**/sccache.log
Cargo.lock

View File

@@ -5,17 +5,7 @@ repos:
- id: check-yaml
- id: end-of-file-fixer
- id: trailing-whitespace
- repo: https://github.com/astral-sh/ruff-pre-commit
# Ruff version.
rev: v0.2.2
- repo: https://github.com/psf/black
rev: 22.12.0
hooks:
- id: ruff
- repo: local
hooks:
- id: local-biome-check
name: biome check
entry: npx @biomejs/biome@1.8.3 check --config-path nodejs/biome.json nodejs/
language: system
types: [text]
files: "nodejs/.*"
exclude: nodejs/lancedb/native.d.ts|nodejs/dist/.*|nodejs/examples/.*
- id: black

3791
Cargo.lock generated Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -1,53 +1,6 @@
[workspace]
members = [
"rust/ffi/node",
"rust/lancedb",
"nodejs",
"python",
"java/core/lancedb-jni",
"rust/vectordb",
"rust/ffi/node"
]
# Python package needs to be built by maturin.
exclude = ["python"]
resolver = "2"
[workspace.package]
edition = "2021"
authors = ["LanceDB Devs <dev@lancedb.com>"]
license = "Apache-2.0"
repository = "https://github.com/lancedb/lancedb"
description = "Serverless, low-latency vector database for AI applications"
keywords = ["lancedb", "lance", "database", "vector", "search"]
categories = ["database-implementations"]
[workspace.dependencies]
lance = { "version" = "=0.17.0", "features" = ["dynamodb"] }
lance-index = { "version" = "=0.17.0" }
lance-linalg = { "version" = "=0.17.0" }
lance-table = { "version" = "=0.17.0" }
lance-testing = { "version" = "=0.17.0" }
lance-datafusion = { "version" = "=0.17.0" }
lance-encoding = { "version" = "=0.17.0" }
# Note that this one does not include pyarrow
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-physical-plan = "40.0"
half = { "version" = "=2.4.1", default-features = false, features = [
"num-traits",
] }
futures = "0"
log = "0.4"
object_store = "0.10.2"
pin-project = "1.0.7"
snafu = "0.7.4"
url = "2"
num-traits = "0.2"
regex = "1.10"
lazy_static = "1"

34
Cross.toml Normal file
View File

@@ -0,0 +1,34 @@
# These make sure our builds are compatible with old glibc versions.
[target.x86_64-unknown-linux-gnu]
pre-build = [
"yum install -y openssl-devel unzip",
# protobuf is too old, so we directly download binaries
"PB_REL=https://github.com/protocolbuffers/protobuf/releases",
"PB_VERSION=23.1",
"curl -LO $PB_REL/download/v$PB_VERSION/protoc-$PB_VERSION-linux-x86_64.zip",
"unzip protoc-$PB_VERSION-linux-x86_64.zip -d /usr/local",
]
image = "ghcr.io/cross-rs/x86_64-unknown-linux-gnu:main-centos"
[target.aarch64-unknown-linux-gnu]
pre-build = [
"yum install -y openssl-devel unzip",
# protobuf is too old, so we directly download binaries
"PB_REL=https://github.com/protocolbuffers/protobuf/releases",
"PB_VERSION=23.1",
"curl -LO $PB_REL/download/v$PB_VERSION/protoc-$PB_VERSION-linux-x86_64.zip",
"unzip protoc-$PB_VERSION-linux-x86_64.zip -d /usr/local",
]
image = "ghcr.io/cross-rs/aarch64-unknown-linux-gnu:main-centos"
[target.x86_64-unknown-linux-musl]
pre-build = [
"dpkg --add-architecture $CROSS_DEB_ARCH",
"apt-get update && apt-get install --assume-yes libssl-dev:$CROSS_DEB_ARCH",
]
[target.aarch64-unknown-linux-musl]
pre-build = [
"dpkg --add-architecture $CROSS_DEB_ARCH",
"apt-get update && apt-get install --assume-yes libssl-dev:$CROSS_DEB_ARCH",
]

View File

@@ -1,26 +1,21 @@
<div align="center">
<p align="center">
<img width="275" alt="LanceDB Logo" src="https://github.com/lancedb/lancedb/assets/5846846/37d7c7ad-c2fd-4f56-9f16-fffb0d17c73a">
<img width="275" alt="LanceDB Logo" src="https://user-images.githubusercontent.com/917119/226205734-6063d87a-1ecc-45fe-85be-1dea6383a3d8.png">
**Developer-friendly, database for multimodal AI**
**Developer-friendly, serverless vector database for AI applications**
<a href='https://github.com/lancedb/vectordb-recipes/tree/main' target="_blank"><img alt='LanceDB' src='https://img.shields.io/badge/VectorDB_Recipes-100000?style=for-the-badge&logo=LanceDB&logoColor=white&labelColor=645cfb&color=645cfb'/></a>
<a href='https://lancedb.github.io/lancedb/' target="_blank"><img alt='lancdb' src='https://img.shields.io/badge/DOCS-100000?style=for-the-badge&logo=lancdb&logoColor=white&labelColor=645cfb&color=645cfb'/></a>
[![Blog](https://img.shields.io/badge/Blog-12100E?style=for-the-badge&logoColor=white)](https://blog.lancedb.com/)
[![Discord](https://img.shields.io/badge/Discord-%235865F2.svg?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/zMM32dvNtd)
[![Twitter](https://img.shields.io/badge/Twitter-%231DA1F2.svg?style=for-the-badge&logo=Twitter&logoColor=white)](https://twitter.com/lancedb)
</p>
<img max-width="750px" alt="LanceDB Multimodal Search" src="https://github.com/lancedb/lancedb/assets/917119/09c5afc5-7816-4687-bae4-f2ca194426ec">
<a href="https://lancedb.github.io/lancedb/">Documentation</a>
<a href="https://blog.lancedb.com/">Blog</a>
<a href="https://discord.gg/zMM32dvNtd">Discord</a>
<a href="https://twitter.com/lancedb">Twitter</a>
</p>
</div>
<hr />
LanceDB is an open-source database for vector-search built with persistent storage, which greatly simplifies retrieval, filtering and management of embeddings.
LanceDB is an open-source database for vector-search built with persistent storage, which greatly simplifies retrevial, filtering and management of embeddings.
The key features of LanceDB include:
@@ -28,40 +23,32 @@ The key features of LanceDB include:
* Store, query and filter vectors, metadata and multi-modal data (text, images, videos, point clouds, and more).
* Support for vector similarity search, full-text search and SQL.
* Native Python and Javascript/Typescript support.
* Zero-copy, automatic versioning, manage versions of your data without needing extra infrastructure.
* GPU support in building vector index(*).
* Ecosystem integrations with [LangChain 🦜️🔗](https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/lanecdb.html), [LlamaIndex 🦙](https://gpt-index.readthedocs.io/en/latest/examples/vector_stores/LanceDBIndexDemo.html), Apache-Arrow, Pandas, Polars, DuckDB and more on the way.
* Ecosystem integrations with [LangChain 🦜️🔗](https://python.langchain.com/docs/integrations/vectorstores/lancedb/), [LlamaIndex 🦙](https://gpt-index.readthedocs.io/en/latest/examples/vector_stores/LanceDBIndexDemo.html), Apache-Arrow, Pandas, Polars, DuckDB and more on the way.
LanceDB's core is written in Rust 🦀 and is built using <a href="https://github.com/lancedb/lance">Lance</a>, an open-source columnar format designed for performant ML workloads.
LanceDB's core is written in Rust 🦀 and is built using <a href="https://github.com/eto-ai/lance">Lance</a>, an open-source columnar format designed for performant ML workloads.
## Quick Start
**Javascript**
```shell
npm install @lancedb/lancedb
npm install vectordb
```
```javascript
import * as lancedb from "@lancedb/lancedb";
const lancedb = require('vectordb');
const db = await lancedb.connect('data/sample-lancedb');
const db = await lancedb.connect("data/sample-lancedb");
const table = await db.createTable("vectors", [
{ id: 1, vector: [0.1, 0.2], item: "foo", price: 10 },
{ id: 2, vector: [1.1, 1.2], item: "bar", price: 50 },
], {mode: 'overwrite'});
const table = await db.createTable('vectors',
[{ id: 1, vector: [0.1, 0.2], item: "foo", price: 10 },
{ id: 2, vector: [1.1, 1.2], item: "bar", price: 50 }])
const query = table.vectorSearch([0.1, 0.3]).limit(2);
const results = await query.toArray();
// You can also search for rows by specific criteria without involving a vector search.
const rowsByCriteria = await table.query().where("price >= 10").toArray();
const query = table.search([0.1, 0.3]);
query.limit = 20;
const results = await query.execute();
```
**Python**
@@ -72,14 +59,14 @@ pip install lancedb
```python
import lancedb
uri = "data/sample-lancedb"
uri = "/tmp/lancedb"
db = lancedb.connect(uri)
table = db.create_table("my_table",
data=[{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
{"vector": [5.9, 26.5], "item": "bar", "price": 20.0}])
result = table.search([100, 100]).limit(2).to_pandas()
result = table.search([100, 100]).limit(2).to_df()
```
## Blogs, Tutorials & Videos
* 📈 <a href="https://blog.lancedb.com/benchmarking-random-access-in-lance/">2000x better performance with Lance over Parquet</a>
* 🤖 <a href="https://github.com/lancedb/lancedb/blob/main/docs/src/notebooks/youtube_transcript_search.ipynb">Build a question and answer bot with LanceDB</a>
* 📈 <a href="https://blog.eto.ai/benchmarking-random-access-in-lance-ed690757a826">2000x better performance with Lance over Parquet</a>
* 🤖 <a href="https://github.com/lancedb/lancedb/blob/main/notebooks/youtube_transcript_search.ipynb">Build a question and answer bot with LanceDB</a>

53
ci/build_linux_artifacts.sh Executable file → Normal file
View File

@@ -1,21 +1,40 @@
#!/bin/bash
# Builds the Linux artifacts (node binaries).
# Usage: ./build_linux_artifacts.sh [target]
# Targets supported:
# - x86_64-unknown-linux-gnu:centos
# - aarch64-unknown-linux-gnu:centos
# - aarch64-unknown-linux-musl
# - x86_64-unknown-linux-musl
# On MacOS, need to run in a linux container:
# docker run -v $(pwd):/io -w /io
# Must run rustup toolchain install stable-x86_64-unknown-linux-gnu --force-non-host
set -e
ARCH=${1:-x86_64}
# We pass down the current user so that when we later mount the local files
# into the container, the files are accessible by the current user.
pushd ci/manylinux_node
docker build \
-t lancedb-node-manylinux \
--build-arg="ARCH=$ARCH" \
--build-arg="DOCKER_USER=$(id -u)" \
--progress=plain \
.
build_node_binaries() {
pushd node
for target in $1
do
echo "Building node library for $target"
# cross doesn't yet pass this down to Docker, so we do it ourselves.
export CROSS_CONTAINER_OPTS="--platform linux/amd64"
if [[ $target == *musl ]]; then
# This is needed for cargo to allow build cdylibs with musl
RUSTFLAGS="-C target-feature=-crt-static"
fi
npm run cross-release -- --target $target
npm run pack-build -- --target $target
done
popd
}
# We turn on memory swap to avoid OOM killer
docker run \
-v $(pwd):/io -w /io \
--memory-swap=-1 \
lancedb-node-manylinux \
bash ci/manylinux_node/build_vectordb.sh $ARCH
if [ -n "$1" ]; then
targets=$1
else
# targets="x86_64-unknown-linux-gnu aarch64-unknown-linux-gnu aarch64-unknown-linux-musl x86_64-unknown-linux-musl"
targets="aarch64-unknown-linux-gnu"
fi
build_node_binaries $targets

View File

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

View File

@@ -1,22 +1,16 @@
# Builds the macOS artifacts (node binaries).
# Usage: ./ci/build_macos_artifacts.sh [target]
# Usage: ./build_macos_artifacts.sh [target]
# Targets supported: x86_64-apple-darwin aarch64-apple-darwin
set -e
prebuild_rust() {
# Building here for the sake of easier debugging.
pushd rust/ffi/node
echo "Building rust library for $1"
export RUST_BACKTRACE=1
cargo build --release --target $1
popd
}
build_node_binaries() {
pushd node
echo "Building node library for $1"
npm run build-release -- --target $1
npm run pack-build -- --target $1
for target in $1
do
echo "Building node library for $target"
npm run build-release -- --target $target
npm run pack-build -- --target $target
done
popd
}
@@ -25,10 +19,4 @@ if [ -n "$1" ]; then
else
targets="x86_64-apple-darwin aarch64-apple-darwin"
fi
echo "Building artifacts for targets: $targets"
for target in $targets
do
prebuild_rust $target
build_node_binaries $target
done
build_node_binaries $targets

View File

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

View File

@@ -1,41 +0,0 @@
# Builds the Windows artifacts (node binaries).
# Usage: .\ci\build_windows_artifacts.ps1 [target]
# Targets supported:
# - x86_64-pc-windows-msvc
# - i686-pc-windows-msvc
function Prebuild-Rust {
param (
[string]$target
)
# Building here for the sake of easier debugging.
Push-Location -Path "rust/ffi/node"
Write-Host "Building rust library for $target"
$env:RUST_BACKTRACE=1
cargo build --release --target $target
Pop-Location
}
function Build-NodeBinaries {
param (
[string]$target
)
Push-Location -Path "node"
Write-Host "Building node library for $target"
npm run build-release -- --target $target
npm run pack-build -- --target $target
Pop-Location
}
$targets = $args[0]
if (-not $targets) {
$targets = "x86_64-pc-windows-msvc"
}
Write-Host "Building artifacts for targets: $targets"
foreach ($target in $targets) {
Prebuild-Rust $target
Build-NodeBinaries $target
}

View File

@@ -1,41 +0,0 @@
# Builds the Windows artifacts (nodejs binaries).
# Usage: .\ci\build_windows_artifacts_nodejs.ps1 [target]
# Targets supported:
# - x86_64-pc-windows-msvc
# - i686-pc-windows-msvc
function Prebuild-Rust {
param (
[string]$target
)
# Building here for the sake of easier debugging.
Push-Location -Path "rust/lancedb"
Write-Host "Building rust library for $target"
$env:RUST_BACKTRACE=1
cargo build --release --target $target
Pop-Location
}
function Build-NodeBinaries {
param (
[string]$target
)
Push-Location -Path "nodejs"
Write-Host "Building nodejs library for $target"
$env:RUST_TARGET=$target
npm run build-release
Pop-Location
}
$targets = $args[0]
if (-not $targets) {
$targets = "x86_64-pc-windows-msvc"
}
Write-Host "Building artifacts for targets: $targets"
foreach ($target in $targets) {
Prebuild-Rust $target
Build-NodeBinaries $target
}

View File

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

View File

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

View File

@@ -1,31 +0,0 @@
# Many linux dockerfile with Rust, Node, and Lance dependencies installed.
# This container allows building the node modules native libraries in an
# environment with a very old glibc, so that we are compatible with a wide
# range of linux distributions.
ARG ARCH=x86_64
FROM quay.io/pypa/manylinux_2_28_${ARCH}
ARG ARCH=x86_64
ARG DOCKER_USER=default_user
# Install static openssl
COPY install_openssl.sh install_openssl.sh
RUN ./install_openssl.sh ${ARCH} > /dev/null
# Protobuf is also installed as root.
COPY install_protobuf.sh install_protobuf.sh
RUN ./install_protobuf.sh ${ARCH}
ENV DOCKER_USER=${DOCKER_USER}
# Create a group and user, but only if it doesn't exist
RUN echo ${ARCH} && id -u ${DOCKER_USER} >/dev/null 2>&1 || adduser --user-group --create-home --uid ${DOCKER_USER} build_user
# We switch to the user to install Rust and Node, since those like to be
# installed at the user level.
USER ${DOCKER_USER}
COPY prepare_manylinux_node.sh prepare_manylinux_node.sh
RUN cp /prepare_manylinux_node.sh $HOME/ && \
cd $HOME && \
./prepare_manylinux_node.sh ${ARCH}

View File

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

View File

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

View File

@@ -1,26 +0,0 @@
#!/bin/bash
# Builds openssl from source so we can statically link to it
# this is to avoid the error we get with the system installation:
# /usr/bin/ld: <library>: version node not found for symbol SSLeay@@OPENSSL_1.0.1
# /usr/bin/ld: failed to set dynamic section sizes: Bad value
set -e
git clone -b OpenSSL_1_1_1v \
--single-branch \
https://github.com/openssl/openssl.git
pushd openssl
if [[ $1 == x86_64* ]]; then
ARCH=linux-x86_64
else
# gnu target
ARCH=linux-aarch64
fi
./Configure no-shared $ARCH
make
make install

View File

@@ -1,15 +0,0 @@
#!/bin/bash
# Installs protobuf compiler. Should be run as root.
set -e
if [[ $1 == x86_64* ]]; then
ARCH=x86_64
else
# gnu target
ARCH=aarch_64
fi
PB_REL=https://github.com/protocolbuffers/protobuf/releases
PB_VERSION=23.1
curl -LO $PB_REL/download/v$PB_VERSION/protoc-$PB_VERSION-linux-$ARCH.zip
unzip protoc-$PB_VERSION-linux-$ARCH.zip -d /usr/local

View File

@@ -1,21 +0,0 @@
#!/bin/bash
set -e
install_node() {
echo "Installing node..."
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.34.0/install.sh | bash
source "$HOME"/.bashrc
nvm install --no-progress 18
}
install_rust() {
echo "Installing rust..."
curl https://sh.rustup.rs -sSf | bash -s -- -y
export PATH="$PATH:/root/.cargo/bin"
}
install_node
install_rust

View File

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

View File

@@ -0,0 +1,31 @@
# On MacOS, need to run in a linux container:
# cat ci/ubuntu_build.dockerfile | docker build -t lancedb-node-build -
# docker run -v /var/run/docker.sock:/var/run/docker.sock -v $(pwd):/io -w /io lancedb-node-build bash ci/build_linux_artifacts.sh
FROM ubuntu:20.04
ARG DEBIAN_FRONTEND=noninteractive
ENV TZ=Europe/Moscow
RUN apt update && apt install -y protobuf-compiler libssl-dev build-essential curl \
software-properties-common npm docker.io
# Install rust
RUN curl https://sh.rustup.rs -sSf | bash -s -- -y
ENV PATH="/root/.cargo/bin:${PATH}"
# Install cross
# https://github.com/cross-rs/cross/issues/1257#issuecomment-1544553706
RUN cargo install cross --git https://github.com/cross-rs/cross
# Install additional build targets
RUN rustup target add x86_64-unknown-linux-gnu aarch64-unknown-linux-gnu aarch64-unknown-linux-musl x86_64-unknown-linux-musl
# Install node
RUN npm install npm@latest -g && \
npm install n -g && \
n latest
# set CROSS_CONTAINER_IN_CONTAINER to inform `cross` that it is executed from within a container
ENV CROSS_CONTAINER_IN_CONTAINER=true
ENV CROSS_CONTAINER_ENGINE_NO_BUILDKIT=1

View File

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

View File

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

View File

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

View File

@@ -1,333 +1,32 @@
site_name: LanceDB
site_url: https://lancedb.github.io/lancedb/
repo_url: https://github.com/lancedb/lancedb
edit_uri: https://github.com/lancedb/lancedb/tree/main/docs/src
repo_name: lancedb/lancedb
site_name: LanceDB Documentation
docs_dir: src
theme:
name: "material"
logo: assets/logo.png
favicon: assets/logo.png
palette:
# Palette toggle for light mode
- scheme: lancedb
primary: custom
toggle:
icon: material/weather-night
name: Switch to dark mode
# Palette toggle for dark mode
- scheme: slate
primary: custom
toggle:
icon: material/weather-sunny
name: Switch to light mode
features:
- content.code.copy
- content.tabs.link
- content.action.edit
- content.tooltips
- toc.follow
- navigation.top
- navigation.tabs
- navigation.tabs.sticky
- navigation.footer
- navigation.tracking
- navigation.instant
icon:
repo: fontawesome/brands/github
annotation: material/arrow-right-circle
custom_dir: overrides
plugins:
- search
- autorefs
- mkdocstrings:
handlers:
python:
paths: [../python]
options:
docstring_style: numpy
heading_level: 3
show_source: true
show_symbol_type_in_heading: true
show_signature_annotations: true
show_root_heading: true
members_order: source
import:
# for cross references
- https://arrow.apache.org/docs/objects.inv
- https://pandas.pydata.org/docs/objects.inv
- mkdocs-jupyter
- render_swagger:
allow_arbitrary_locations: true
nav:
- Home: index.md
- Basics: basic.md
- Embeddings: embedding.md
- Indexing: ann_indexes.md
- Integrations: integrations.md
- Python API: python.md
markdown_extensions:
- admonition
- footnotes
- pymdownx.details
- pymdownx.highlight:
anchor_linenums: true
line_spans: __span
pygments_lang_class: true
- pymdownx.inlinehilite
- pymdownx.snippets:
base_path: ..
dedent_subsections: true
- pymdownx.superfences
- pymdownx.tabbed:
alternate_style: true
- md_in_html
- abbr
- attr_list
- pymdownx.snippets
- pymdownx.emoji:
emoji_index: !!python/name:material.extensions.emoji.twemoji
emoji_generator: !!python/name:material.extensions.emoji.to_svg
nav:
- Home:
- LanceDB: index.md
- 🏃🏼‍♂️ Quick start: basic.md
- 📚 Concepts:
- Vector search: concepts/vector_search.md
- Indexing:
- IVFPQ: concepts/index_ivfpq.md
- HNSW: concepts/index_hnsw.md
- Storage: concepts/storage.md
- Data management: concepts/data_management.md
- 🔨 Guides:
- Working with tables: guides/tables.md
- Building a vector index: ann_indexes.md
- Vector Search: search.md
- Full-text search: fts.md
- Building a scalar index: guides/scalar_index.md
- Hybrid search:
- Overview: hybrid_search/hybrid_search.md
- Comparing Rerankers: hybrid_search/eval.md
- Airbnb financial data example: notebooks/hybrid_search.ipynb
- Reranking:
- Quickstart: reranking/index.md
- Cohere Reranker: reranking/cohere.md
- Linear Combination Reranker: reranking/linear_combination.md
- Reciprocal Rank Fusion Reranker: reranking/rrf.md
- Cross Encoder Reranker: reranking/cross_encoder.md
- ColBERT Reranker: reranking/colbert.md
- Jina Reranker: reranking/jina.md
- OpenAI Reranker: reranking/openai.md
- AnswerDotAi Rerankers: reranking/answerdotai.md
- Building Custom Rerankers: reranking/custom_reranker.md
- Example: notebooks/lancedb_reranking.ipynb
- Filtering: sql.md
- Versioning & Reproducibility: notebooks/reproducibility.ipynb
- Configuring Storage: guides/storage.md
- Migration Guide: migration.md
- Tuning retrieval performance:
- Choosing right query type: guides/tuning_retrievers/1_query_types.md
- Reranking: guides/tuning_retrievers/2_reranking.md
- Embedding fine-tuning: guides/tuning_retrievers/3_embed_tuning.md
- 🧬 Managing embeddings:
- Overview: embeddings/index.md
- Embedding functions: embeddings/embedding_functions.md
- Available models:
- Overview: embeddings/default_embedding_functions.md
- Text Embedding Functions:
- Sentence Transformers: embeddings/available_embedding_models/text_embedding_functions/sentence_transformers.md
- Huggingface Embedding Models: embeddings/available_embedding_models/text_embedding_functions/huggingface_embedding.md
- Ollama Embeddings: embeddings/available_embedding_models/text_embedding_functions/ollama_embedding.md
- OpenAI Embeddings: embeddings/available_embedding_models/text_embedding_functions/openai_embedding.md
- Instructor Embeddings: embeddings/available_embedding_models/text_embedding_functions/instructor_embedding.md
- Gemini Embeddings: embeddings/available_embedding_models/text_embedding_functions/gemini_embedding.md
- Cohere Embeddings: embeddings/available_embedding_models/text_embedding_functions/cohere_embedding.md
- 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
- 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
- Jina Embeddings: embeddings/available_embedding_models/multimodal_embedding_functions/jina_multimodal_embedding.md
- User-defined embedding functions: embeddings/custom_embedding_function.md
- "Example: Multi-lingual semantic search": notebooks/multi_lingual_example.ipynb
- "Example: MultiModal CLIP Embeddings": notebooks/DisappearingEmbeddingFunction.ipynb
- 🔌 Integrations:
- Tools and data formats: integrations/index.md
- Pandas and PyArrow: python/pandas_and_pyarrow.md
- Polars: python/polars_arrow.md
- DuckDB: python/duckdb.md
- LangChain:
- LangChain 🔗: integrations/langchain.md
- LangChain demo: notebooks/langchain_demo.ipynb
- LangChain JS/TS 🔗: https://js.langchain.com/docs/integrations/vectorstores/lancedb
- LlamaIndex 🦙:
- LlamaIndex docs: integrations/llamaIndex.md
- LlamaIndex demo: notebooks/llamaIndex_demo.ipynb
- Pydantic: python/pydantic.md
- Voxel51: integrations/voxel51.md
- PromptTools: integrations/prompttools.md
- dlt: integrations/dlt.md
- 🎯 Examples:
- Overview: examples/index.md
- 🐍 Python:
- Overview: examples/examples_python.md
- Build From Scratch: examples/python_examples/build_from_scratch.md
- Multimodal: examples/python_examples/multimodal.md
- Rag: examples/python_examples/rag.md
- Vector Search: examples/python_examples/vector_search.md
- Chatbot: examples/python_examples/chatbot.md
- Evaluation: examples/python_examples/evaluations.md
- AI Agent: examples/python_examples/aiagent.md
- Recommender System: examples/python_examples/recommendersystem.md
- 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:
- Overview: examples/examples_js.md
- Serverless Website Chatbot: examples/serverless_website_chatbot.md
- YouTube Transcript Search: examples/youtube_transcript_bot_with_nodejs.md
- TransformersJS Embedding Search: examples/transformerjs_embedding_search_nodejs.md
- 🦀 Rust:
- Overview: examples/examples_rust.md
- Studies:
- ↗Improve retrievers with hybrid search and reranking: https://blog.lancedb.com/hybrid-search-and-reranking-report/
- 💭 FAQs: faq.md
- ⚙️ API reference:
- 🐍 Python: python/python.md
- 👾 JavaScript (vectordb): javascript/modules.md
- 👾 JavaScript (lancedb): js/globals.md
- 🦀 Rust: https://docs.rs/lancedb/latest/lancedb/
- ☁️ LanceDB Cloud:
- Overview: cloud/index.md
- API reference:
- 🐍 Python: python/saas-python.md
- 👾 JavaScript: javascript/modules.md
- REST API: cloud/rest.md
- Quick start: basic.md
- Concepts:
- Vector search: concepts/vector_search.md
- Indexing:
- IVFPQ: concepts/index_ivfpq.md
- HNSW: concepts/index_hnsw.md
- Storage: concepts/storage.md
- Data management: concepts/data_management.md
- Guides:
- Working with tables: guides/tables.md
- Building an ANN index: ann_indexes.md
- Vector Search: search.md
- Full-text search: fts.md
- Building a scalar index: guides/scalar_index.md
- Hybrid search:
- Overview: hybrid_search/hybrid_search.md
- Comparing Rerankers: hybrid_search/eval.md
- Airbnb financial data example: notebooks/hybrid_search.ipynb
- Reranking:
- Quickstart: reranking/index.md
- Cohere Reranker: reranking/cohere.md
- Linear Combination Reranker: reranking/linear_combination.md
- Reciprocal Rank Fusion Reranker: reranking/rrf.md
- Cross Encoder Reranker: reranking/cross_encoder.md
- ColBERT Reranker: reranking/colbert.md
- Jina Reranker: reranking/jina.md
- OpenAI Reranker: reranking/openai.md
- AnswerDotAi Rerankers: reranking/answerdotai.md
- Building Custom Rerankers: reranking/custom_reranker.md
- Example: notebooks/lancedb_reranking.ipynb
- Filtering: sql.md
- Versioning & Reproducibility: notebooks/reproducibility.ipynb
- Configuring Storage: guides/storage.md
- Migration Guide: migration.md
- Tuning retrieval performance:
- Choosing right query type: guides/tuning_retrievers/1_query_types.md
- Reranking: guides/tuning_retrievers/2_reranking.md
- Embedding fine-tuning: guides/tuning_retrievers/3_embed_tuning.md
- Managing Embeddings:
- Overview: embeddings/index.md
- Embedding functions: embeddings/embedding_functions.md
- Available models:
- Overview: embeddings/default_embedding_functions.md
- Text Embedding Functions:
- Sentence Transformers: embeddings/available_embedding_models/text_embedding_functions/sentence_transformers.md
- Huggingface Embedding Models: embeddings/available_embedding_models/text_embedding_functions/huggingface_embedding.md
- Ollama Embeddings: embeddings/available_embedding_models/text_embedding_functions/ollama_embedding.md
- OpenAI Embeddings: embeddings/available_embedding_models/text_embedding_functions/openai_embedding.md
- Instructor Embeddings: embeddings/available_embedding_models/text_embedding_functions/instructor_embedding.md
- Gemini Embeddings: embeddings/available_embedding_models/text_embedding_functions/gemini_embedding.md
- Cohere Embeddings: embeddings/available_embedding_models/text_embedding_functions/cohere_embedding.md
- 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
- 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
- Jina Embeddings: embeddings/available_embedding_models/multimodal_embedding_functions/jina_multimodal_embedding.md
- User-defined embedding functions: embeddings/custom_embedding_function.md
- "Example: Multi-lingual semantic search": notebooks/multi_lingual_example.ipynb
- "Example: MultiModal CLIP Embeddings": notebooks/DisappearingEmbeddingFunction.ipynb
- Integrations:
- Overview: integrations/index.md
- Pandas and PyArrow: python/pandas_and_pyarrow.md
- Polars: python/polars_arrow.md
- DuckDB: python/duckdb.md
- LangChain 🦜️🔗↗: integrations/langchain.md
- LangChain.js 🦜️🔗↗: https://js.langchain.com/docs/integrations/vectorstores/lancedb
- LlamaIndex 🦙↗: integrations/llamaIndex.md
- Pydantic: python/pydantic.md
- Voxel51: integrations/voxel51.md
- PromptTools: integrations/prompttools.md
- dlt: integrations/dlt.md
- Examples:
- examples/index.md
- 🐍 Python:
- Overview: examples/examples_python.md
- Build From Scratch: examples/python_examples/build_from_scratch.md
- Multimodal: examples/python_examples/multimodal.md
- Rag: examples/python_examples/rag.md
- Vector Search: examples/python_examples/vector_search.md
- Chatbot: examples/python_examples/chatbot.md
- Evaluation: examples/python_examples/evaluations.md
- AI Agent: examples/python_examples/aiagent.md
- Recommender System: examples/python_examples/recommendersystem.md
- 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:
- Overview: examples/examples_js.md
- Serverless Website Chatbot: examples/serverless_website_chatbot.md
- YouTube Transcript Search: examples/youtube_transcript_bot_with_nodejs.md
- TransformersJS Embedding Search: examples/transformerjs_embedding_search_nodejs.md
- 🦀 Rust:
- Overview: examples/examples_rust.md
- Studies:
- studies/overview.md
- ↗Improve retrievers with hybrid search and reranking: https://blog.lancedb.com/hybrid-search-and-reranking-report/
- API reference:
- Overview: api_reference.md
- Python: python/python.md
- Javascript (vectordb): javascript/modules.md
- Javascript (lancedb): js/globals.md
- Rust: https://docs.rs/lancedb/latest/lancedb/index.html
- LanceDB Cloud:
- Overview: cloud/index.md
- API reference:
- 🐍 Python: python/saas-python.md
- 👾 JavaScript: javascript/modules.md
- REST API: cloud/rest.md
extra_css:
- styles/global.css
- styles/extra.css
extra_javascript:
- "extra_js/init_ask_ai_widget.js"
extra:
analytics:
provider: google
property: G-B7NFM40W74
social:
- icon: fontawesome/brands/github
link: https://github.com/lancedb/lancedb
- icon: fontawesome/brands/x-twitter
link: https://twitter.com/lancedb
- icon: fontawesome/brands/linkedin
link: https://www.linkedin.com/company/lancedb
- pymdownx.superfences

View File

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

View File

@@ -1,176 +0,0 @@
<!--
Copyright (c) 2016-2023 Martin Donath <martin.donath@squidfunk.com>
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to
deal in the Software without restriction, including without limitation the
rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
sell copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in
all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
IN THE SOFTWARE.
-->
{% set class = "md-header" %}
{% if "navigation.tabs.sticky" in features %}
{% set class = class ~ " md-header--shadow md-header--lifted" %}
{% elif "navigation.tabs" not in features %}
{% set class = class ~ " md-header--shadow" %}
{% endif %}
<!-- Header -->
<header class="{{ class }}" data-md-component="header">
<nav
class="md-header__inner md-grid"
aria-label="{{ lang.t('header') }}"
>
<!-- Link to home -->
<a
href="{{ config.extra.homepage | d(nav.homepage.url, true) | url }}"
title="{{ config.site_name | e }}"
class="md-header__button md-logo"
aria-label="{{ config.site_name }}"
data-md-component="logo"
>
{% include "partials/logo.html" %}
</a>
<!-- Button to open drawer -->
<label class="md-header__button md-icon" for="__drawer">
{% include ".icons/material/menu" ~ ".svg" %}
</label>
<!-- Header title -->
<div class="md-header__title" style="width: auto !important;" data-md-component="header-title">
<div class="md-header__ellipsis">
<div class="md-header__topic">
<span class="md-ellipsis">
{{ config.site_name }}
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
{% if page.meta and page.meta.title %}
{{ page.meta.title }}
{% else %}
{{ page.title }}
{% endif %}
</span>
</div>
</div>
</div>
<!-- Color palette -->
{% if config.theme.palette %}
{% if not config.theme.palette is mapping %}
<form class="md-header__option" data-md-component="palette">
{% for option in config.theme.palette %}
{% set scheme = option.scheme | d("default", true) %}
{% set primary = option.primary | d("indigo", true) %}
{% set accent = option.accent | d("indigo", true) %}
<input
class="md-option"
data-md-color-media="{{ option.media }}"
data-md-color-scheme="{{ scheme | replace(' ', '-') }}"
data-md-color-primary="{{ primary | replace(' ', '-') }}"
data-md-color-accent="{{ accent | replace(' ', '-') }}"
{% if option.toggle %}
aria-label="{{ option.toggle.name }}"
{% else %}
aria-hidden="true"
{% endif %}
type="radio"
name="__palette"
id="__palette_{{ loop.index }}"
/>
{% if option.toggle %}
<label
class="md-header__button md-icon"
title="{{ option.toggle.name }}"
for="__palette_{{ loop.index0 or loop.length }}"
hidden
>
{% include ".icons/" ~ option.toggle.icon ~ ".svg" %}
</label>
{% endif %}
{% endfor %}
</form>
{% endif %}
{% endif %}
<!-- Site language selector -->
{% if config.extra.alternate %}
<div class="md-header__option">
<div class="md-select">
{% set icon = config.theme.icon.alternate or "material/translate" %}
<button
class="md-header__button md-icon"
aria-label="{{ lang.t('select.language') }}"
>
{% include ".icons/" ~ icon ~ ".svg" %}
</button>
<div class="md-select__inner">
<ul class="md-select__list">
{% for alt in config.extra.alternate %}
<li class="md-select__item">
<a
href="{{ alt.link | url }}"
hreflang="{{ alt.lang }}"
class="md-select__link"
>
{{ alt.name }}
</a>
</li>
{% endfor %}
</ul>
</div>
</div>
</div>
{% endif %}
<!-- Button to open search modal -->
{% if "material/search" in config.plugins %}
<label class="md-header__button md-icon" for="__search">
{% include ".icons/material/magnify.svg" %}
</label>
<!-- Search interface -->
{% include "partials/search.html" %}
{% endif %}
<div style="margin-left: 10px; margin-right: 5px;">
<a href="https://discord.com/invite/zMM32dvNtd" target="_blank" rel="noopener noreferrer">
<svg fill="#FFFFFF" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 50 50" width="25px" height="25px"><path d="M 41.625 10.769531 C 37.644531 7.566406 31.347656 7.023438 31.078125 7.003906 C 30.660156 6.96875 30.261719 7.203125 30.089844 7.589844 C 30.074219 7.613281 29.9375 7.929688 29.785156 8.421875 C 32.417969 8.867188 35.652344 9.761719 38.578125 11.578125 C 39.046875 11.867188 39.191406 12.484375 38.902344 12.953125 C 38.710938 13.261719 38.386719 13.429688 38.050781 13.429688 C 37.871094 13.429688 37.6875 13.378906 37.523438 13.277344 C 32.492188 10.15625 26.210938 10 25 10 C 23.789063 10 17.503906 10.15625 12.476563 13.277344 C 12.007813 13.570313 11.390625 13.425781 11.101563 12.957031 C 10.808594 12.484375 10.953125 11.871094 11.421875 11.578125 C 14.347656 9.765625 17.582031 8.867188 20.214844 8.425781 C 20.0625 7.929688 19.925781 7.617188 19.914063 7.589844 C 19.738281 7.203125 19.34375 6.960938 18.921875 7.003906 C 18.652344 7.023438 12.355469 7.566406 8.320313 10.8125 C 6.214844 12.761719 2 24.152344 2 34 C 2 34.175781 2.046875 34.34375 2.132813 34.496094 C 5.039063 39.605469 12.972656 40.941406 14.78125 41 C 14.789063 41 14.800781 41 14.8125 41 C 15.132813 41 15.433594 40.847656 15.621094 40.589844 L 17.449219 38.074219 C 12.515625 36.800781 9.996094 34.636719 9.851563 34.507813 C 9.4375 34.144531 9.398438 33.511719 9.765625 33.097656 C 10.128906 32.683594 10.761719 32.644531 11.175781 33.007813 C 11.234375 33.0625 15.875 37 25 37 C 34.140625 37 38.78125 33.046875 38.828125 33.007813 C 39.242188 32.648438 39.871094 32.683594 40.238281 33.101563 C 40.601563 33.515625 40.5625 34.144531 40.148438 34.507813 C 40.003906 34.636719 37.484375 36.800781 32.550781 38.074219 L 34.378906 40.589844 C 34.566406 40.847656 34.867188 41 35.1875 41 C 35.199219 41 35.210938 41 35.21875 41 C 37.027344 40.941406 44.960938 39.605469 47.867188 34.496094 C 47.953125 34.34375 48 34.175781 48 34 C 48 24.152344 43.785156 12.761719 41.625 10.769531 Z M 18.5 30 C 16.566406 30 15 28.210938 15 26 C 15 23.789063 16.566406 22 18.5 22 C 20.433594 22 22 23.789063 22 26 C 22 28.210938 20.433594 30 18.5 30 Z M 31.5 30 C 29.566406 30 28 28.210938 28 26 C 28 23.789063 29.566406 22 31.5 22 C 33.433594 22 35 23.789063 35 26 C 35 28.210938 33.433594 30 31.5 30 Z"/></svg>
</a>
</div>
<div style="margin-left: 5px; margin-right: 5px;">
<a href="https://twitter.com/lancedb" target="_blank" rel="noopener noreferrer">
<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" viewBox="0,0,256,256" width="25px" height="25px" fill-rule="nonzero"><g fill-opacity="0" fill="#ffffff" fill-rule="nonzero" stroke="none" stroke-width="1" stroke-linecap="butt" stroke-linejoin="miter" stroke-miterlimit="10" stroke-dasharray="" stroke-dashoffset="0" font-family="none" font-weight="none" font-size="none" text-anchor="none" style="mix-blend-mode: normal"><path d="M0,256v-256h256v256z" id="bgRectangle"></path></g><g fill="#ffffff" fill-rule="nonzero" stroke="none" stroke-width="1" stroke-linecap="butt" stroke-linejoin="miter" stroke-miterlimit="10" stroke-dasharray="" stroke-dashoffset="0" font-family="none" font-weight="none" font-size="none" text-anchor="none" style="mix-blend-mode: normal"><g transform="scale(4,4)"><path d="M57,17.114c-1.32,1.973 -2.991,3.707 -4.916,5.097c0.018,0.423 0.028,0.847 0.028,1.274c0,13.013 -9.902,28.018 -28.016,28.018c-5.562,0 -12.81,-1.948 -15.095,-4.423c0.772,0.092 1.556,0.138 2.35,0.138c4.615,0 8.861,-1.575 12.23,-4.216c-4.309,-0.079 -7.946,-2.928 -9.199,-6.84c1.96,0.308 4.447,-0.17 4.447,-0.17c0,0 -7.7,-1.322 -7.899,-9.779c2.226,1.291 4.46,1.231 4.46,1.231c0,0 -4.441,-2.734 -4.379,-8.195c0.037,-3.221 1.331,-4.953 1.331,-4.953c8.414,10.361 20.298,10.29 20.298,10.29c0,0 -0.255,-1.471 -0.255,-2.243c0,-5.437 4.408,-9.847 9.847,-9.847c2.832,0 5.391,1.196 7.187,3.111c2.245,-0.443 4.353,-1.263 6.255,-2.391c-0.859,3.44 -4.329,5.448 -4.329,5.448c0,0 2.969,-0.329 5.655,-1.55z"></path></g></g></svg>
</a>
</div>
<!-- Repository information -->
{% if config.repo_url %}
<div class="md-header__source" style="margin-left: -5px !important;">
{% include "partials/source.html" %}
</div>
{% endif %}
</nav>
<!-- Navigation tabs (sticky) -->
{% if "navigation.tabs.sticky" in features %}
{% if "navigation.tabs" in features %}
{% include "partials/tabs.html" %}
{% endif %}
{% endif %}
</header>

132
docs/package-lock.json generated
View File

@@ -1,132 +0,0 @@
{
"name": "lancedb-docs-test",
"version": "1.0.0",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "lancedb-docs-test",
"version": "1.0.0",
"license": "Apache 2",
"dependencies": {
"apache-arrow": "file:../node/node_modules/apache-arrow",
"vectordb": "file:../node"
},
"devDependencies": {
"@types/node": "^20.11.8",
"typescript": "^5.3.3"
}
},
"../node": {
"name": "vectordb",
"version": "0.4.6",
"cpu": [
"x64",
"arm64"
],
"license": "Apache-2.0",
"os": [
"darwin",
"linux",
"win32"
],
"dependencies": {
"@apache-arrow/ts": "^14.0.2",
"@neon-rs/load": "^0.0.74",
"apache-arrow": "^14.0.2",
"axios": "^1.4.0"
},
"devDependencies": {
"@neon-rs/cli": "^0.0.160",
"@types/chai": "^4.3.4",
"@types/chai-as-promised": "^7.1.5",
"@types/mocha": "^10.0.1",
"@types/node": "^18.16.2",
"@types/sinon": "^10.0.15",
"@types/temp": "^0.9.1",
"@types/uuid": "^9.0.3",
"@typescript-eslint/eslint-plugin": "^5.59.1",
"cargo-cp-artifact": "^0.1",
"chai": "^4.3.7",
"chai-as-promised": "^7.1.1",
"eslint": "^8.39.0",
"eslint-config-standard-with-typescript": "^34.0.1",
"eslint-plugin-import": "^2.26.0",
"eslint-plugin-n": "^15.7.0",
"eslint-plugin-promise": "^6.1.1",
"mocha": "^10.2.0",
"openai": "^4.24.1",
"sinon": "^15.1.0",
"temp": "^0.9.4",
"ts-node": "^10.9.1",
"ts-node-dev": "^2.0.0",
"typedoc": "^0.24.7",
"typedoc-plugin-markdown": "^3.15.3",
"typescript": "*",
"uuid": "^9.0.0"
},
"optionalDependencies": {
"@lancedb/vectordb-darwin-arm64": "0.4.6",
"@lancedb/vectordb-darwin-x64": "0.4.6",
"@lancedb/vectordb-linux-arm64-gnu": "0.4.6",
"@lancedb/vectordb-linux-x64-gnu": "0.4.6",
"@lancedb/vectordb-win32-x64-msvc": "0.4.6"
}
},
"../node/node_modules/apache-arrow": {
"version": "14.0.2",
"license": "Apache-2.0",
"dependencies": {
"@types/command-line-args": "5.2.0",
"@types/command-line-usage": "5.0.2",
"@types/node": "20.3.0",
"@types/pad-left": "2.1.1",
"command-line-args": "5.2.1",
"command-line-usage": "7.0.1",
"flatbuffers": "23.5.26",
"json-bignum": "^0.0.3",
"pad-left": "^2.1.0",
"tslib": "^2.5.3"
},
"bin": {
"arrow2csv": "bin/arrow2csv.js"
}
},
"node_modules/@types/node": {
"version": "20.11.8",
"resolved": "https://registry.npmjs.org/@types/node/-/node-20.11.8.tgz",
"integrity": "sha512-i7omyekpPTNdv4Jb/Rgqg0RU8YqLcNsI12quKSDkRXNfx7Wxdm6HhK1awT3xTgEkgxPn3bvnSpiEAc7a7Lpyow==",
"dev": true,
"dependencies": {
"undici-types": "~5.26.4"
}
},
"node_modules/apache-arrow": {
"resolved": "../node/node_modules/apache-arrow",
"link": true
},
"node_modules/typescript": {
"version": "5.3.3",
"resolved": "https://registry.npmjs.org/typescript/-/typescript-5.3.3.tgz",
"integrity": "sha512-pXWcraxM0uxAS+tN0AG/BF2TyqmHO014Z070UsJ+pFvYuRSq8KH8DmWpnbXe0pEPDHXZV3FcAbJkijJ5oNEnWw==",
"dev": true,
"bin": {
"tsc": "bin/tsc",
"tsserver": "bin/tsserver"
},
"engines": {
"node": ">=14.17"
}
},
"node_modules/undici-types": {
"version": "5.26.5",
"resolved": "https://registry.npmjs.org/undici-types/-/undici-types-5.26.5.tgz",
"integrity": "sha512-JlCMO+ehdEIKqlFxk6IfVoAUVmgz7cU7zD/h9XZ0qzeosSHmUJVOzSQvvYSYWXkFXC+IfLKSIffhv0sVZup6pA==",
"dev": true
},
"node_modules/vectordb": {
"resolved": "../node",
"link": true
}
}
}

View File

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

View File

@@ -1,7 +1,4 @@
mkdocs==1.5.3
mkdocs==1.4.2
mkdocs-jupyter==0.24.1
mkdocs-material==9.5.3
mkdocstrings[python]==0.25.2
griffe
mkdocs-render-swagger-plugin
pydantic
mkdocs-material==9.1.3
mkdocstrings[python]==0.20.0

View File

@@ -1,35 +1,28 @@
# Approximate Nearest Neighbor (ANN) Indexes
# ANN (Approximate Nearest Neighbor) Indexes
An ANN or a vector index is a data structure specifically designed to efficiently organize and
search vector data based on their similarity via the chosen distance metric.
By constructing a vector index, the search space is effectively narrowed down, avoiding the need
for brute-force scanning of the entire vector space.
A vector index is faster but less accurate than exhaustive search (kNN or flat search).
You can create an index over your vector data to make search faster.
Vector indexes are faster but less accurate than exhaustive search.
LanceDB provides many parameters to fine-tune the index's size, the speed of queries, and the accuracy of results.
## Disk-based Index
Currently, LanceDB does *not* automatically create the ANN index.
LanceDB has optimized code for KNN as well. For many use-cases, datasets under 100K vectors won't require index creation at all.
If you can live with <100ms latency, skipping index creation is a simpler workflow while guaranteeing 100% recall.
Lance provides an `IVF_PQ` disk-based index. It uses **Inverted File Index (IVF)** to first divide
the dataset into `N` partitions, and then applies **Product Quantization** to compress vectors in each partition.
See the [indexing](concepts/index_ivfpq.md) concepts guide for more information on how this works.
In the future we will look to automatically create and configure the ANN index.
## Creating an IVF_PQ Index
Lance supports `IVF_PQ` index type by default.
=== "Python"
## Creating an ANN Index
Creating indexes is done via the [create_index](https://lancedb.github.io/lancedb/python/#lancedb.table.LanceTable.create_index) method.
```python
import lancedb
import numpy as np
uri = "data/sample-lancedb"
uri = "~/.lancedb"
db = lancedb.connect(uri)
# Create 10,000 sample vectors
data = [{"vector": row, "item": f"item {i}"}
for i, row in enumerate(np.random.random((10_000, 1536)).astype('float32'))]
for i, row in enumerate(np.random.random((10_000, 768)).astype('float32'))]
# Add the vectors to a table
tbl = db.create_table("my_vectors", data=data)
@@ -38,99 +31,15 @@ Lance supports `IVF_PQ` index type by default.
tbl.create_index(num_partitions=256, num_sub_vectors=96)
```
=== "TypeScript"
Since `create_index` has a training step, it can take a few minutes to finish for large tables. You can control the index
creation by providing the following parameters:
=== "@lancedb/lancedb"
Creating indexes is done via the [lancedb.Table.createIndex](../js/classes/Table.md/#createIndex) method.
```typescript
--8<--- "nodejs/examples/ann_indexes.ts:import"
--8<-- "nodejs/examples/ann_indexes.ts:ingest"
```
=== "vectordb (deprecated)"
Creating indexes is done via the [lancedb.Table.createIndex](../javascript/interfaces/Table.md/#createIndex) method.
```typescript
--8<--- "docs/src/ann_indexes.ts:import"
--8<-- "docs/src/ann_indexes.ts:ingest"
```
=== "Rust"
```rust
--8<-- "rust/lancedb/examples/ivf_pq.rs:create_index"
```
IVF_PQ index parameters are more fully defined in the [crate docs](https://docs.rs/lancedb/latest/lancedb/index/vector/struct.IvfPqIndexBuilder.html).
The following IVF_PQ paramters can be specified:
- **distance_type**: The distance metric to use. By default it uses euclidean distance "`L2`".
We also support "cosine" and "dot" distance as well.
- **num_partitions**: The number of partitions in the index. The default is the square root
of the number of rows.
!!! note
In the synchronous python SDK and node's `vectordb` the default is 256. This default has
changed in the asynchronous python SDK and node's `lancedb`.
- **num_sub_vectors**: The number of sub-vectors (M) that will be created during Product Quantization (PQ).
For D dimensional vector, it will be divided into `M` subvectors with dimension `D/M`, each of which is replaced by
a single PQ code. The default is the dimension of the vector divided by 16.
!!! note
In the synchronous python SDK and node's `vectordb` the default is currently 96. This default has
changed in the asynchronous python SDK and node's `lancedb`.
<figure markdown>
![IVF PQ](./assets/ivf_pq.png)
<figcaption>IVF_PQ index with <code>num_partitions=2, num_sub_vectors=4</code></figcaption>
</figure>
### Use GPU to build vector index
Lance Python SDK has experimental GPU support for creating IVF index.
Using GPU for index creation requires [PyTorch>2.0](https://pytorch.org/) being installed.
You can specify the GPU device to train IVF partitions via
- **accelerator**: Specify to `cuda` or `mps` (on Apple Silicon) to enable GPU training.
=== "Linux"
<!-- skip-test -->
``` { .python .copy }
# Create index using CUDA on Nvidia GPUs.
tbl.create_index(
num_partitions=256,
num_sub_vectors=96,
accelerator="cuda"
)
```
=== "MacOS"
<!-- skip-test -->
```python
# Create index using MPS on Apple Silicon.
tbl.create_index(
num_partitions=256,
num_sub_vectors=96,
accelerator="mps"
)
```
Troubleshooting:
If you see `AssertionError: Torch not compiled with CUDA enabled`, you need to [install
PyTorch with CUDA support](https://pytorch.org/get-started/locally/).
- **metric** (default: "L2"): The distance metric to use. By default we use euclidean distance. We also support cosine distance.
- **num_partitions** (default: 256): The number of partitions of the index. The number of partitions should be configured so each partition has 3-5K vectors. For example, a table
with ~1M vectors should use 256 partitions. You can specify arbitrary number of partitions but powers of 2 is most conventional.
A higher number leads to faster queries, but it makes index generation slower.
- **num_sub_vectors** (default: 96): The number of subvectors (M) that will be created during Product Quantization (PQ). A larger number makes
search more accurate, but also makes the index larger and slower to build.
## Querying an ANN Index
@@ -144,138 +53,43 @@ There are a couple of parameters that can be used to fine-tune the search:
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/>
A higher number makes search more accurate but also slower. If you find the recall is less than idea, try refine_factor=10 to start.<br/>
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"
```python
tbl.search(np.random.random((1536))) \
tbl.search(np.random.random((768))) \
.limit(2) \
.nprobes(20) \
.refine_factor(10) \
.to_pandas()
```
.to_df()
```text
vector item _distance
vector item score
0 [0.44949695, 0.8444449, 0.06281311, 0.23338133... item 1141 103.575333
1 [0.48587373, 0.269207, 0.15095535, 0.65531915,... item 3953 108.393867
```
=== "TypeScript"
The search will return the data requested in addition to the score of each item.
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/ann_indexes.ts:search1"
```
=== "vectordb (deprecated)"
```typescript
--8<-- "docs/src/ann_indexes.ts:search1"
```
=== "Rust"
```rust
--8<-- "rust/lancedb/examples/ivf_pq.rs:search1"
```
Vector search options are more fully defined in the [crate docs](https://docs.rs/lancedb/latest/lancedb/query/struct.Query.html#method.nearest_to).
The search will return the data requested in addition to the distance of each item.
**Note:** The score is the distance between the query vector and the element. A lower number means that the result is more relevant.
### Filtering (where clause)
You can further filter the elements returned by a search using a where clause.
=== "Python"
```python
tbl.search(np.random.random((1536))).where("item != 'item 1141'").to_pandas()
```
=== "TypeScript"
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/ann_indexes.ts:search2"
```
=== "vectordb (deprecated)"
```javascript
--8<-- "docs/src/ann_indexes.ts:search2"
tbl.search(np.random.random((768))).where("item != 'item 1141'").to_df()
```
### Projections (select clause)
You can select the columns returned by the query using a select clause.
=== "Python"
```python
tbl.search(np.random.random((1536))).select(["vector"]).to_pandas()
```
```text
vector _distance
tbl.search(np.random.random((768))).select(["vector"]).to_df()
vector score
0 [0.30928212, 0.022668175, 0.1756372, 0.4911822... 93.971092
1 [0.2525465, 0.01723831, 0.261568, 0.002007689,... 95.173485
...
```
=== "TypeScript"
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/ann_indexes.ts:search3"
```
=== "vectordb (deprecated)"
```typescript
--8<-- "docs/src/ann_indexes.ts:search3"
```
## FAQ
### Why do I need to manually create an index?
Currently, LanceDB does _not_ automatically create the ANN index.
LanceDB is well-optimized for kNN (exhaustive search) via a disk-based index. For many use-cases,
datasets of the order of ~100K vectors don't require index creation. If you can live with up to
100ms latency, skipping index creation is a simpler workflow while guaranteeing 100% recall.
### When is it necessary to create an ANN vector index?
`LanceDB` comes out-of-the-box with highly optimized SIMD code for computing vector similarity.
In our benchmarks, computing distances for 100K pairs of 1K dimension vectors takes **less than 20ms**.
We observe that for small datasets (~100K rows) or for applications that can accept 100ms latency,
vector indices are usually not necessary.
For large-scale or higher dimension vectors, it can beneficial to create vector index for performance.
### How big is my index, and how many memory will it take?
In LanceDB, all vector indices are **disk-based**, meaning that when responding to a vector query, only the relevant pages from the index file are loaded from disk and cached in memory. Additionally, each sub-vector is usually encoded into 1 byte PQ code.
For example, with a 1024-dimension dataset, if we choose `num_sub_vectors=64`, each sub-vector has `1024 / 64 = 16` float32 numbers.
Product quantization can lead to approximately `16 * sizeof(float32) / 1 = 64` times of space reduction.
### How to choose `num_partitions` and `num_sub_vectors` for `IVF_PQ` index?
`num_partitions` is used to decide how many partitions the first level `IVF` index uses.
Higher number of partitions could lead to more efficient I/O during queries and better accuracy, but it takes much more time to train.
On `SIFT-1M` dataset, our benchmark shows that keeping each partition 1K-4K rows lead to a good latency / recall.
`num_sub_vectors` specifies how many Product Quantization (PQ) short codes to generate on each vector. Because
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.

View File

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

View File

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

View File

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

Before

Width:  |  Height:  |  Size: 2.3 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 342 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 147 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 245 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 98 KiB

View File

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

Before

Width:  |  Height:  |  Size: 1.2 KiB

View File

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

Before

Width:  |  Height:  |  Size: 1.7 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 107 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 23 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 60 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 21 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 34 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 204 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 112 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 217 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 101 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 256 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 224 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 170 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 4.9 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 20 KiB

View File

@@ -1,22 +0,0 @@
<svg width="147" height="20" viewBox="0 0 147 20" fill="none" xmlns="http://www.w3.org/2000/svg">
<rect x="0.5" y="0.5" width="145.482" height="19" rx="9.5" fill="white" stroke="#EFEFEF"/>
<path d="M14.1863 10.9251V12.7593H16.0205V10.9251H14.1863Z" fill="#FF3270"/>
<path d="M17.8707 10.9251V12.7593H19.7049V10.9251H17.8707Z" fill="#861FFF"/>
<path d="M14.1863 7.24078V9.07496H16.0205V7.24078H14.1863Z" fill="#097EFF"/>
<path fill-rule="evenodd" clip-rule="evenodd" d="M12.903 6.77179C12.903 6.32194 13.2676 5.95728 13.7175 5.95728C14.1703 5.95728 15.2556 5.95728 16.1094 5.95728C16.7538 5.95728 17.2758 6.47963 17.2758 7.12398V9.6698H19.8217C20.4661 9.6698 20.9884 10.1922 20.9884 10.8365C20.9884 11.6337 20.9884 12.4309 20.9884 13.2282C20.9884 13.678 20.6237 14.0427 20.1738 14.0427H17.3039H16.5874H13.7175C13.2676 14.0427 12.903 13.678 12.903 13.2282V9.71653V9.64174V6.77179ZM14.1863 7.24066V9.07485H16.0205V7.24066H14.1863ZM14.1863 12.7593V10.9251H16.0205V12.7593H14.1863ZM17.8708 12.7593V10.9251H19.705V12.7593H17.8708Z" fill="black"/>
<path d="M18.614 8.35468L20.7796 6.18905M20.7796 6.18905V7.66073M20.7796 6.18905L19.2724 6.18905" stroke="black" stroke-width="0.686298" stroke-linecap="round" stroke-linejoin="round"/>
<path d="M31.6082 13.9838C30.8546 13.9838 30.1895 13.802 29.6132 13.4385C29.0368 13.066 28.5846 12.5429 28.2565 11.869C27.9373 11.1862 27.7777 10.3749 27.7777 9.43501C27.7777 8.49511 27.9373 7.69265 28.2565 7.02762C28.5846 6.3626 29.0368 5.85275 29.6132 5.49807C30.1895 5.14339 30.8546 4.96605 31.6082 4.96605C32.3708 4.96605 33.0403 5.14339 33.6166 5.49807C34.193 5.85275 34.6408 6.3626 34.96 7.02762C35.2881 7.69265 35.4521 8.49511 35.4521 9.43501C35.4521 10.3749 35.2881 11.1862 34.96 11.869C34.6408 12.5429 34.193 13.066 33.6166 13.4385C33.0403 13.802 32.3708 13.9838 31.6082 13.9838ZM31.6082 12.6404C32.291 12.6404 32.8363 12.3523 33.2442 11.7759C33.6521 11.1907 33.856 10.4104 33.856 9.43501C33.856 8.45964 33.6521 7.69708 33.2442 7.14733C32.8363 6.58871 32.291 6.3094 31.6082 6.3094C30.9255 6.3094 30.3802 6.58871 29.9723 7.14733C29.5644 7.69708 29.3605 8.45964 29.3605 9.43501C29.3605 10.4104 29.5644 11.1907 29.9723 11.7759C30.3802 12.3523 30.9255 12.6404 31.6082 12.6404Z" fill="#2C3236"/>
<path d="M37.0592 16.4045V7.29363H38.3227L38.4291 7.98526H38.4823C38.7572 7.75472 39.0631 7.55521 39.4 7.38674C39.7459 7.21826 40.0961 7.13403 40.4508 7.13403C41.2665 7.13403 41.8961 7.43551 42.3395 8.03846C42.7917 8.64142 43.0178 9.44831 43.0178 10.4591C43.0178 11.204 42.8848 11.8424 42.6188 12.3744C42.3528 12.8976 42.0069 13.2966 41.5813 13.5715C41.1646 13.8463 40.7124 13.9838 40.2247 13.9838C39.9409 13.9838 39.6572 13.9217 39.3734 13.7976C39.0897 13.6646 38.8148 13.4872 38.5488 13.2656L38.5887 14.3562V16.4045H37.0592ZM39.9055 12.7202C40.3399 12.7202 40.7035 12.5296 40.9961 12.1483C41.2887 11.767 41.435 11.2084 41.435 10.4724C41.435 9.81629 41.3242 9.30644 41.1025 8.94289C40.8808 8.57935 40.5217 8.39757 40.0252 8.39757C39.5641 8.39757 39.0853 8.64142 38.5887 9.1291V12.1749C38.8281 12.37 39.0587 12.5119 39.2803 12.6005C39.502 12.6803 39.7104 12.7202 39.9055 12.7202Z" fill="#2C3236"/>
<path d="M47.3598 13.9838C46.7568 13.9838 46.2115 13.8508 45.7238 13.5848C45.2361 13.3099 44.8504 12.9197 44.5667 12.4143C44.2829 11.9 44.141 11.2838 44.141 10.5656C44.141 9.85619 44.2829 9.24437 44.5667 8.73009C44.8593 8.2158 45.2361 7.82122 45.6972 7.54634C46.1583 7.27147 46.6415 7.13403 47.147 7.13403C47.741 7.13403 48.2376 7.26703 48.6366 7.53304C49.0356 7.79018 49.3371 8.15373 49.541 8.62368C49.745 9.08476 49.847 9.62122 49.847 10.233C49.847 10.5523 49.8248 10.8005 49.7805 10.9779H45.6307C45.7016 11.5542 45.91 12.002 46.2558 12.3212C46.6016 12.6404 47.0361 12.8 47.5593 12.8C47.843 12.8 48.1046 12.7601 48.344 12.6803C48.5923 12.5917 48.8361 12.472 49.0755 12.3212L49.5942 13.2789C49.2839 13.4828 48.9381 13.6513 48.5568 13.7843C48.1755 13.9173 47.7765 13.9838 47.3598 13.9838ZM45.6174 9.94043H48.5169C48.5169 9.43501 48.4061 9.04043 48.1844 8.75669C47.9627 8.46408 47.6302 8.31777 47.1869 8.31777C46.8056 8.31777 46.4642 8.45964 46.1627 8.74339C45.8701 9.01826 45.6883 9.41728 45.6174 9.94043Z" fill="#2C3236"/>
<path d="M51.3078 13.8242V7.29363H52.5714L52.6778 8.17147H52.731C53.0236 7.88772 53.3428 7.64388 53.6886 7.43994C54.0344 7.236 54.429 7.13403 54.8724 7.13403C55.5728 7.13403 56.0827 7.36014 56.4019 7.81235C56.7211 8.26457 56.8807 8.90299 56.8807 9.72762V13.8242H55.3512V9.92713C55.3512 9.38624 55.2714 9.00496 55.1118 8.78329C54.9522 8.56161 54.6906 8.45078 54.327 8.45078C54.0433 8.45078 53.7906 8.52171 53.5689 8.66358C53.3561 8.79659 53.1123 8.99609 52.8374 9.2621V13.8242H51.3078Z" fill="#2C3236"/>
<path d="M61.4131 13.8242V7.29363H62.9426V13.8242H61.4131ZM62.1845 6.14979C61.9096 6.14979 61.6879 6.06999 61.5195 5.91038C61.351 5.75078 61.2668 5.53797 61.2668 5.27196C61.2668 5.01482 61.351 4.80644 61.5195 4.64684C61.6879 4.48723 61.9096 4.40743 62.1845 4.40743C62.4594 4.40743 62.6811 4.48723 62.8495 4.64684C63.018 4.80644 63.1022 5.01482 63.1022 5.27196C63.1022 5.53797 63.018 5.75078 62.8495 5.91038C62.6811 6.06999 62.4594 6.14979 62.1845 6.14979Z" fill="#2C3236"/>
<path d="M64.8941 13.8242V7.29363H66.1576L66.264 8.17147H66.3172C66.6098 7.88772 66.929 7.64388 67.2748 7.43994C67.6207 7.236 68.0152 7.13403 68.4586 7.13403C69.1591 7.13403 69.6689 7.36014 69.9881 7.81235C70.3074 8.26457 70.467 8.90299 70.467 9.72762V13.8242H68.9374V9.92713C68.9374 9.38624 68.8576 9.00496 68.698 8.78329C68.5384 8.56161 68.2768 8.45078 67.9133 8.45078C67.6295 8.45078 67.3768 8.52171 67.1551 8.66358C66.9423 8.79659 66.6985 8.99609 66.4236 9.2621V13.8242H64.8941Z" fill="#2C3236"/>
<path d="M75.1323 13.8242V5.12565H76.6752V8.62368H80.1998V5.12565H81.7427V13.8242H80.1998V9.96703H76.6752V13.8242H75.1323Z" fill="#2C3236"/>
<path d="M83.9517 13.8242V5.12565H89.2054V6.4291H85.4945V8.88969H88.6601V10.1931H85.4945V13.8242H83.9517Z" fill="#2C3236"/>
<path d="M95.9349 13.9838C95.3497 13.9838 94.7822 13.8729 94.2324 13.6513C93.6915 13.4296 93.2127 13.1148 92.796 12.7069L93.7004 11.6562C94.0108 11.9488 94.3654 12.1882 94.7645 12.3744C95.1635 12.5518 95.5625 12.6404 95.9615 12.6404C96.458 12.6404 96.8349 12.5385 97.092 12.3345C97.3492 12.1306 97.4778 11.8601 97.4778 11.5232C97.4778 11.1596 97.3492 10.8981 97.092 10.7385C96.8438 10.5789 96.5245 10.4148 96.1344 10.2463L94.9374 9.72762C94.6536 9.60348 94.3743 9.44388 94.0994 9.2488C93.8334 9.05373 93.6117 8.80546 93.4344 8.50398C93.2659 8.2025 93.1817 7.83895 93.1817 7.41334C93.1817 6.95225 93.3058 6.53994 93.5541 6.17639C93.8113 5.80398 94.1571 5.51137 94.5915 5.29856C95.0349 5.07689 95.5403 4.96605 96.1078 4.96605C96.6132 4.96605 97.1009 5.06802 97.5709 5.27196C98.0408 5.46703 98.4442 5.73304 98.7812 6.06999L97.9965 7.05423C97.7216 6.82368 97.429 6.64191 97.1186 6.5089C96.8172 6.3759 96.4802 6.3094 96.1078 6.3094C95.6999 6.3094 95.3674 6.4025 95.1103 6.58871C94.862 6.76605 94.7379 7.01432 94.7379 7.33353C94.7379 7.55521 94.7999 7.74142 94.9241 7.89215C95.0571 8.03403 95.23 8.15816 95.4428 8.26457C95.6556 8.36211 95.8817 8.45964 96.1211 8.55718L97.3048 9.0493C97.8191 9.27097 98.2403 9.56358 98.5684 9.92713C98.8965 10.2818 99.0605 10.7739 99.0605 11.4035C99.0605 11.8734 98.9364 12.3035 98.6881 12.6936C98.4398 13.0838 98.0807 13.3986 97.6108 13.638C97.1497 13.8685 96.591 13.9838 95.9349 13.9838Z" fill="#2C3236"/>
<path d="M100.509 16.4045V7.29363H101.773L101.879 7.98526H101.932C102.207 7.75472 102.513 7.55521 102.85 7.38674C103.196 7.21826 103.546 7.13403 103.901 7.13403C104.717 7.13403 105.346 7.43551 105.79 8.03846C106.242 8.64142 106.468 9.44831 106.468 10.4591C106.468 11.204 106.335 11.8424 106.069 12.3744C105.803 12.8976 105.457 13.2966 105.031 13.5715C104.615 13.8463 104.162 13.9838 103.675 13.9838C103.391 13.9838 103.107 13.9217 102.824 13.7976C102.54 13.6646 102.265 13.4872 101.999 13.2656L102.039 14.3562V16.4045H100.509ZM103.356 12.7202C103.79 12.7202 104.154 12.5296 104.446 12.1483C104.739 11.767 104.885 11.2084 104.885 10.4724C104.885 9.81629 104.774 9.30644 104.553 8.94289C104.331 8.57935 103.972 8.39757 103.475 8.39757C103.014 8.39757 102.535 8.64142 102.039 9.1291V12.1749C102.278 12.37 102.509 12.5119 102.73 12.6005C102.952 12.6803 103.16 12.7202 103.356 12.7202Z" fill="#2C3236"/>
<path d="M109.444 13.9838C108.876 13.9838 108.411 13.8064 108.047 13.4518C107.692 13.0971 107.515 12.636 107.515 12.0685C107.515 11.368 107.821 10.8271 108.433 10.4458C109.045 10.0557 110.02 9.78969 111.359 9.64782C111.35 9.30201 111.257 9.00496 111.08 8.75669C110.911 8.49954 110.605 8.37097 110.162 8.37097C109.843 8.37097 109.528 8.43304 109.218 8.55718C108.916 8.68132 108.619 8.83206 108.326 9.0094L107.768 7.98526C108.131 7.75472 108.539 7.55521 108.991 7.38674C109.452 7.21826 109.94 7.13403 110.454 7.13403C111.27 7.13403 111.878 7.37787 112.277 7.86555C112.685 8.34437 112.888 9.04043 112.888 9.95373V13.8242H111.625L111.518 13.1059H111.465C111.173 13.3542 110.858 13.5626 110.521 13.7311C110.193 13.8995 109.834 13.9838 109.444 13.9838ZM109.936 12.7867C110.202 12.7867 110.441 12.7247 110.654 12.6005C110.876 12.4675 111.111 12.2902 111.359 12.0685V10.6055C110.472 10.7207 109.856 10.8936 109.51 11.1242C109.164 11.3458 108.991 11.6207 108.991 11.9488C108.991 12.2414 109.08 12.4542 109.257 12.5872C109.435 12.7202 109.661 12.7867 109.936 12.7867Z" fill="#2C3236"/>
<path d="M117.446 13.9838C116.851 13.9838 116.315 13.8508 115.836 13.5848C115.366 13.3099 114.989 12.9197 114.706 12.4143C114.431 11.9 114.293 11.2838 114.293 10.5656C114.293 9.83846 114.444 9.2222 114.746 8.71679C115.047 8.2025 115.446 7.81235 115.943 7.54634C116.448 7.27147 116.989 7.13403 117.565 7.13403C117.982 7.13403 118.346 7.20496 118.656 7.34684C118.966 7.48871 119.241 7.66161 119.48 7.86555L118.736 8.86309C118.567 8.71235 118.394 8.59708 118.217 8.51728C118.04 8.42861 117.849 8.38427 117.645 8.38427C117.122 8.38427 116.692 8.58378 116.355 8.98279C116.027 9.38181 115.863 9.9094 115.863 10.5656C115.863 11.2128 116.022 11.736 116.342 12.135C116.67 12.534 117.091 12.7335 117.605 12.7335C117.862 12.7335 118.102 12.6803 118.323 12.5739C118.554 12.4587 118.762 12.3256 118.948 12.1749L119.574 13.1857C119.272 13.4518 118.935 13.6513 118.563 13.7843C118.19 13.9173 117.818 13.9838 117.446 13.9838Z" fill="#2C3236"/>
<path d="M123.331 13.9838C122.728 13.9838 122.183 13.8508 121.695 13.5848C121.207 13.3099 120.822 12.9197 120.538 12.4143C120.254 11.9 120.112 11.2838 120.112 10.5656C120.112 9.85619 120.254 9.24437 120.538 8.73009C120.83 8.2158 121.207 7.82122 121.668 7.54634C122.13 7.27147 122.613 7.13403 123.118 7.13403C123.712 7.13403 124.209 7.26703 124.608 7.53304C125.007 7.79018 125.308 8.15373 125.512 8.62368C125.716 9.08476 125.818 9.62122 125.818 10.233C125.818 10.5523 125.796 10.8005 125.752 10.9779H121.602C121.673 11.5542 121.881 12.002 122.227 12.3212C122.573 12.6404 123.007 12.8 123.53 12.8C123.814 12.8 124.076 12.7601 124.315 12.6803C124.563 12.5917 124.807 12.472 125.047 12.3212L125.565 13.2789C125.255 13.4828 124.909 13.6513 124.528 13.7843C124.147 13.9173 123.748 13.9838 123.331 13.9838ZM121.589 9.94043H124.488C124.488 9.43501 124.377 9.04043 124.156 8.75669C123.934 8.46408 123.601 8.31777 123.158 8.31777C122.777 8.31777 122.435 8.45964 122.134 8.74339C121.841 9.01826 121.66 9.41728 121.589 9.94043Z" fill="#2C3236"/>
<path d="M129.101 13.9838C128.658 13.9838 128.215 13.8995 127.771 13.7311C127.328 13.5537 126.947 13.3365 126.627 13.0793L127.346 12.0951C127.638 12.3168 127.931 12.4941 128.223 12.6271C128.516 12.7601 128.826 12.8266 129.154 12.8266C129.509 12.8266 129.771 12.7513 129.939 12.6005C130.108 12.4498 130.192 12.2636 130.192 12.0419C130.192 11.8557 130.121 11.705 129.979 11.5897C129.846 11.4656 129.673 11.3591 129.46 11.2705C129.248 11.1729 129.026 11.0798 128.795 10.9912C128.512 10.8848 128.228 10.7562 127.944 10.6055C127.669 10.4458 127.443 10.2463 127.266 10.0069C127.088 9.75866 127 9.45274 127 9.0892C127 8.51284 127.213 8.04289 127.638 7.67935C128.064 7.3158 128.64 7.13403 129.367 7.13403C129.828 7.13403 130.241 7.21383 130.604 7.37344C130.968 7.53304 131.282 7.71482 131.548 7.91876L130.844 8.84979C130.613 8.68132 130.378 8.54831 130.139 8.45078C129.908 8.34437 129.664 8.29117 129.407 8.29117C129.079 8.29117 128.835 8.36211 128.676 8.50398C128.516 8.63698 128.436 8.80545 128.436 9.0094C128.436 9.26654 128.569 9.46161 128.835 9.59462C129.101 9.72762 129.412 9.85619 129.766 9.98033C130.068 10.0867 130.36 10.2197 130.644 10.3793C130.928 10.5301 131.163 10.7296 131.349 10.9779C131.544 11.2261 131.642 11.5542 131.642 11.9621C131.642 12.5207 131.424 12.9995 130.99 13.3986C130.555 13.7887 129.926 13.9838 129.101 13.9838Z" fill="#2C3236"/>
</svg>

Before

Width:  |  Height:  |  Size: 12 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 1.7 MiB

View File

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

Before

Width:  |  Height:  |  Size: 2.6 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 26 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 210 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 54 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 953 KiB

View File

@@ -1,584 +1,77 @@
# Quick start
# Basic LanceDB Functionality
!!! info "LanceDB can be run in a number of ways:"
* Embedded within an existing backend (like your Django, Flask, Node.js or FastAPI application)
* Directly from a client application like a Jupyter notebook for analytical workloads
* Deployed as a remote serverless database
![](assets/lancedb_embedded_explanation.png)
## Installation
=== "Python"
```shell
pip install lancedb
```
=== "Typescript[^1]"
=== "@lancedb/lancedb"
```shell
npm install @lancedb/lancedb
```
!!! note "Bundling `@lancedb/lancedb` apps with Webpack"
Since LanceDB contains a prebuilt Node binary, you must configure `next.config.js` to exclude it from webpack. This is required for both using Next.js and deploying a LanceDB app on Vercel.
```javascript
/** @type {import('next').NextConfig} */
module.exports = ({
webpack(config) {
config.externals.push({ '@lancedb/lancedb': '@lancedb/lancedb' })
return config;
}
})
```
!!! note "Yarn users"
Unlike other package managers, Yarn does not automatically resolve peer dependencies. If you are using Yarn, you will need to manually install 'apache-arrow':
```shell
yarn add apache-arrow
```
=== "vectordb (deprecated)"
```shell
npm install vectordb
```
!!! note "Bundling `vectordb` apps with Webpack"
Since LanceDB contains a prebuilt Node binary, you must configure `next.config.js` to exclude it from webpack. This is required for both using Next.js and deploying a LanceDB app on Vercel.
```javascript
/** @type {import('next').NextConfig} */
module.exports = ({
webpack(config) {
config.externals.push({ vectordb: 'vectordb' })
return config;
}
})
```
!!! note "Yarn users"
Unlike other package managers, Yarn does not automatically resolve peer dependencies. If you are using Yarn, you will need to manually install 'apache-arrow':
```shell
yarn add apache-arrow
```
=== "Rust"
```shell
cargo add lancedb
```
!!! info "To use the lancedb create, you first need to install protobuf."
=== "macOS"
```shell
brew install protobuf
```
=== "Ubuntu/Debian"
```shell
sudo apt install -y protobuf-compiler libssl-dev
```
!!! info "Please also make sure you're using the same version of Arrow as in the [lancedb crate](https://github.com/lancedb/lancedb/blob/main/Cargo.toml)"
### Preview releases
Stable releases are created about every 2 weeks. For the latest features and bug
fixes, you can install the preview release. These releases receive the same
level of testing as stable releases, but are not guaranteed to be available for
more than 6 months after they are released. Once your application is stable, we
recommend switching to stable releases.
=== "Python"
```shell
pip install --pre --extra-index-url https://pypi.fury.io/lancedb/ lancedb
```
=== "Typescript[^1]"
=== "@lancedb/lancedb"
```shell
npm install @lancedb/lancedb@preview
```
=== "vectordb (deprecated)"
```shell
npm install vectordb@preview
```
=== "Rust"
We don't push preview releases to crates.io, but you can referent the tag
in GitHub within your Cargo dependencies:
```toml
[dependencies]
lancedb = { git = "https://github.com/lancedb/lancedb.git", tag = "vX.Y.Z-beta.N" }
```
## Connect to a database
=== "Python"
## How to connect to a database
In local mode, LanceDB stores data in a directory on your local machine. To connect to a local database, you can use the following code:
```python
--8<-- "python/python/tests/docs/test_basic.py:imports"
--8<-- "python/python/tests/docs/test_basic.py:connect"
--8<-- "python/python/tests/docs/test_basic.py:connect_async"
import lancedb
uri = "~/.lancedb"
db = lancedb.connect(uri)
```
!!! note "Asynchronous Python API"
The asynchronous Python API is new and has some slight differences compared
to the synchronous API. Feel free to start using the asynchronous version.
Once all features have migrated we will start to move the synchronous API to
use the same syntax as the asynchronous API. To help with this migration we
have created a [migration guide](migration.md) detailing the differences.
=== "Typescript[^1]"
=== "@lancedb/lancedb"
```typescript
import * as lancedb from "@lancedb/lancedb";
import * as arrow from "apache-arrow";
--8<-- "nodejs/examples/basic.ts:connect"
```
=== "vectordb (deprecated)"
```typescript
--8<-- "docs/src/basic_legacy.ts:open_db"
```
=== "Rust"
```rust
#[tokio::main]
async fn main() -> Result<()> {
--8<-- "rust/lancedb/examples/simple.rs:connect"
}
```
!!! info "See [examples/simple.rs](https://github.com/lancedb/lancedb/tree/main/rust/lancedb/examples/simple.rs) for a full working example."
LanceDB will create the directory if it doesn't exist (including parent directories).
If you need a reminder of the uri, you can call `db.uri()`.
If you need a reminder of the uri, use the `db.uri` property.
## Create a table
### Create a table from initial data
If you have data to insert into the table at creation time, you can simultaneously create a
table and insert the data into it. The schema of the data will be used as the schema of the
table.
=== "Python"
## How to create a table
To create a table, you can use the following code:
```python
--8<-- "python/python/tests/docs/test_basic.py:create_table"
--8<-- "python/python/tests/docs/test_basic.py:create_table_async"
tbl = db.create_table("my_table",
data=[{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
{"vector": [5.9, 26.5], "item": "bar", "price": 20.0}])
```
Under the hood, LanceDB is converting the input data into an Apache Arrow table
and persisting it to disk in [Lance format](github.com/eto-ai/lance).
If the table already exists, LanceDB will raise an error by default.
If you want to overwrite the table, you can pass in `mode="overwrite"`
to the `create_table` method.
You can also pass in a pandas DataFrame directly:
```python
--8<-- "python/python/tests/docs/test_basic.py:create_table_pandas"
--8<-- "python/python/tests/docs/test_basic.py:create_table_async_pandas"
import pandas as pd
df = pd.DataFrame([{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
{"vector": [5.9, 26.5], "item": "bar", "price": 20.0}])
tbl = db.create_table("table_from_df", data=df)
```
=== "Typescript[^1]"
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/basic.ts:create_table"
```
=== "vectordb (deprecated)"
```typescript
--8<-- "docs/src/basic_legacy.ts:create_table"
```
If the table already exists, LanceDB will raise an error by default.
If you want to overwrite the table, you can pass in `mode:"overwrite"`
to the `createTable` function.
=== "Rust"
```rust
--8<-- "rust/lancedb/examples/simple.rs:create_table"
```
If the table already exists, LanceDB will raise an error by default. See
[the mode option](https://docs.rs/lancedb/latest/lancedb/connection/struct.CreateTableBuilder.html#method.mode)
for details on how to overwrite (or open) existing tables instead.
!!! Providing table records in Rust
The Rust SDK currently expects data to be provided as an Arrow
[RecordBatchReader](https://docs.rs/arrow-array/latest/arrow_array/trait.RecordBatchReader.html)
Support for additional formats (such as serde or polars) is on the roadmap.
!!! info "Under the hood, LanceDB reads in the Apache Arrow data and persists it to disk using the [Lance format](https://www.github.com/lancedb/lance)."
!!! info "Automatic embedding generation with Embedding API"
When working with embedding models, it is recommended to use the LanceDB embedding API to automatically create vector representation of the data and queries in the background. See the [quickstart example](#using-the-embedding-api) or the embedding API [guide](./embeddings/)
### Create an empty table
Sometimes you may not have the data to insert into the table at creation time.
In this case, you can create an empty table and specify the schema, so that you can add
data to the table at a later time (as long as it conforms to the schema). This is
similar to a `CREATE TABLE` statement in SQL.
=== "Python"
## How to open an existing table
Once created, you can open a table using the following code:
```python
--8<-- "python/python/tests/docs/test_basic.py:create_empty_table"
--8<-- "python/python/tests/docs/test_basic.py:create_empty_table_async"
```
!!! note "You can define schema in Pydantic"
LanceDB comes with Pydantic support, which allows you to define the schema of your data using Pydantic models. This makes it easy to work with LanceDB tables and data. Learn more about all supported types in [tables guide](./guides/tables.md).
=== "Typescript[^1]"
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/basic.ts:create_empty_table"
```
=== "vectordb (deprecated)"
```typescript
--8<-- "docs/src/basic_legacy.ts:create_empty_table"
```
=== "Rust"
```rust
--8<-- "rust/lancedb/examples/simple.rs:create_empty_table"
```
## Open an existing table
Once created, you can open a table as follows:
=== "Python"
```python
--8<-- "python/python/tests/docs/test_basic.py:open_table"
--8<-- "python/python/tests/docs/test_basic.py:open_table_async"
```
=== "Typescript[^1]"
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/basic.ts:open_table"
```
=== "vectordb (deprecated)"
```typescript
const tbl = await db.openTable("myTable");
```
=== "Rust"
```rust
--8<-- "rust/lancedb/examples/simple.rs:open_existing_tbl"
tbl = db.open_table("my_table")
```
If you forget the name of your table, you can always get a listing of all table names:
=== "Python"
```python
db.table_names()
```
## How to add data to a table
After a table has been created, you can always add more data to it using
```python
--8<-- "python/python/tests/docs/test_basic.py:table_names"
--8<-- "python/python/tests/docs/test_basic.py:table_names_async"
df = pd.DataFrame([{"vector": [1.3, 1.4], "item": "fizz", "price": 100.0},
{"vector": [9.5, 56.2], "item": "buzz", "price": 200.0}])
tbl.add(df)
```
=== "Typescript[^1]"
=== "@lancedb/lancedb"
## How to search for (approximate) nearest neighbors
```typescript
--8<-- "nodejs/examples/basic.ts:table_names"
```
=== "vectordb (deprecated)"
```typescript
console.log(await db.tableNames());
```
=== "Rust"
```rust
--8<-- "rust/lancedb/examples/simple.rs:list_names"
```
## Add data to a table
After a table has been created, you can always add more data to it as follows:
=== "Python"
Once you've embedded the query, you can find its nearest neighbors using the following code:
```python
--8<-- "python/python/tests/docs/test_basic.py:add_data"
--8<-- "python/python/tests/docs/test_basic.py:add_data_async"
```
=== "Typescript[^1]"
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/basic.ts:add_data"
```
=== "vectordb (deprecated)"
```typescript
--8<-- "docs/src/basic_legacy.ts:add"
```
=== "Rust"
```rust
--8<-- "rust/lancedb/examples/simple.rs:add"
```
## Search for nearest neighbors
Once you've embedded the query, you can find its nearest neighbors as follows:
=== "Python"
```python
--8<-- "python/python/tests/docs/test_basic.py:vector_search"
--8<-- "python/python/tests/docs/test_basic.py:vector_search_async"
tbl.search([100, 100]).limit(2).to_df()
```
This returns a pandas DataFrame with the results.
=== "Typescript[^1]"
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/basic.ts:vector_search"
```
=== "vectordb (deprecated)"
```typescript
--8<-- "docs/src/basic_legacy.ts:search"
```
=== "Rust"
```rust
use futures::TryStreamExt;
--8<-- "rust/lancedb/examples/simple.rs:search"
```
!!! Query vectors in Rust
Rust does not yet support automatic execution of embedding functions. You will need to
calculate embeddings yourself. Support for this is on the roadmap and can be tracked at
https://github.com/lancedb/lancedb/issues/994
Query vectors can be provided as Arrow arrays or a Vec/slice of Rust floats.
Support for additional formats (e.g. `polars::series::Series`) is on the roadmap.
By default, LanceDB runs a brute-force scan over dataset to find the K nearest neighbours (KNN).
For tables with more than 50K vectors, creating an ANN index is recommended to speed up search performance.
LanceDB allows you to create an ANN index on a table as follows:
=== "Python"
```py
--8<-- "python/python/tests/docs/test_basic.py:create_index"
--8<-- "python/python/tests/docs/test_basic.py:create_index_async"
```
=== "Typescript[^1]"
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/basic.ts:create_index"
```
=== "vectordb (deprecated)"
```{.typescript .ignore}
--8<-- "docs/src/basic_legacy.ts:create_index"
```
=== "Rust"
```rust
--8<-- "rust/lancedb/examples/simple.rs:create_index"
```
!!! note "Why do I need to create an index manually?"
LanceDB does not automatically create the ANN index for two reasons. The first is that it's optimized
for really fast retrievals via a disk-based index, and the second is that data and query workloads can
be very diverse, so there's no one-size-fits-all index configuration. LanceDB provides many parameters
to fine-tune index size, query latency and accuracy. See the section on
[ANN indexes](ann_indexes.md) for more details.
## Delete rows from a table
Use the `delete()` method on tables to delete rows from a table. To choose
which rows to delete, provide a filter that matches on the metadata columns.
This can delete any number of rows that match the filter.
=== "Python"
```python
--8<-- "python/python/tests/docs/test_basic.py:delete_rows"
--8<-- "python/python/tests/docs/test_basic.py:delete_rows_async"
```
=== "Typescript[^1]"
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/basic.ts:delete_rows"
```
=== "vectordb (deprecated)"
```typescript
--8<-- "docs/src/basic_legacy.ts:delete"
```
=== "Rust"
```rust
--8<-- "rust/lancedb/examples/simple.rs:delete"
```
The deletion predicate is a SQL expression that supports the same expressions
as the `where()` clause (`only_if()` in Rust) on a search. They can be as
simple or complex as needed. To see what expressions are supported, see the
[SQL filters](sql.md) section.
=== "Python"
Read more: [lancedb.table.Table.delete][]
=== "Typescript[^1]"
=== "@lancedb/lancedb"
Read more: [lancedb.Table.delete](javascript/interfaces/Table.md#delete)
=== "vectordb (deprecated)"
Read more: [vectordb.Table.delete](javascript/interfaces/Table.md#delete)
=== "Rust"
Read more: [lancedb::Table::delete](https://docs.rs/lancedb/latest/lancedb/table/struct.Table.html#method.delete)
## Drop a table
Use the `drop_table()` method on the database to remove a table.
=== "Python"
```python
--8<-- "python/python/tests/docs/test_basic.py:drop_table"
--8<-- "python/python/tests/docs/test_basic.py:drop_table_async"
```
This permanently removes the table and is not recoverable, unlike deleting rows.
By default, if the table does not exist an exception is raised. To suppress this,
you can pass in `ignore_missing=True`.
=== "Typescript[^1]"
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/basic.ts:drop_table"
```
=== "vectordb (deprecated)"
```typescript
--8<-- "docs/src/basic_legacy.ts:drop_table"
```
This permanently removes the table and is not recoverable, unlike deleting rows.
If the table does not exist an exception is raised.
=== "Rust"
```rust
--8<-- "rust/lancedb/examples/simple.rs:drop_table"
```
## Using the Embedding API
You can use the embedding API when working with embedding models. It automatically vectorizes the data at ingestion and query time and comes with built-in integrations with popular embedding models like Openai, Hugging Face, Sentence Transformers, CLIP and more.
=== "Python"
```python
--8<-- "python/python/tests/docs/test_embeddings_optional.py:imports"
--8<-- "python/python/tests/docs/test_embeddings_optional.py:openai_embeddings"
```
=== "Typescript[^1]"
=== "@lancedb/lancedb"
```typescript
--8<-- "nodejs/examples/embedding.ts:imports"
--8<-- "nodejs/examples/embedding.ts:openai_embeddings"
```
=== "Rust"
```rust
--8<-- "rust/lancedb/examples/openai.rs:imports"
--8<-- "rust/lancedb/examples/openai.rs:openai_embeddings"
```
Learn about using the existing integrations and creating custom embedding functions in the [embedding API guide](./embeddings/index.md).
## What's next
This section covered the very basics of using LanceDB. If you're learning about vector databases for the first time, you may want to read the page on [indexing](concepts/index_ivfpq.md) to get familiar with the concepts.
If you've already worked with other vector databases, you may want to read the [guides](guides/tables.md) to learn how to work with LanceDB in more detail.
[^1]: The `vectordb` package is a legacy package that is deprecated in favor of `@lancedb/lancedb`. The `vectordb` package will continue to receive bug fixes and security updates until September 2024. We recommend all new projects use `@lancedb/lancedb`. See the [migration guide](migration.md) for more information.
This section covered the very basics of the LanceDB API.
LanceDB supports many additional features when creating indices to speed up search and options for search.
These are contained in the next section of the documentation.

View File

@@ -1,126 +0,0 @@
// --8<-- [start:import]
import * as lancedb from "vectordb";
import {
Schema,
Field,
Float32,
FixedSizeList,
Int32,
Float16,
} from "apache-arrow";
import * as arrow from "apache-arrow";
// --8<-- [end:import]
import * as fs from "fs";
import { Table as ArrowTable, Utf8 } from "apache-arrow";
const example = async () => {
fs.rmSync("data/sample-lancedb", { recursive: true, force: true });
// --8<-- [start:open_db]
const lancedb = require("vectordb");
const uri = "data/sample-lancedb";
const db = await lancedb.connect(uri);
// --8<-- [end:open_db]
// --8<-- [start:create_table]
const tbl = await db.createTable(
"myTable",
[
{ vector: [3.1, 4.1], item: "foo", price: 10.0 },
{ vector: [5.9, 26.5], item: "bar", price: 20.0 },
],
{ writeMode: lancedb.WriteMode.Overwrite },
);
// --8<-- [end:create_table]
{
// --8<-- [start:create_table_with_schema]
const schema = new arrow.Schema([
new arrow.Field(
"vector",
new arrow.FixedSizeList(
2,
new arrow.Field("item", new arrow.Float32(), true),
),
),
new arrow.Field("item", new arrow.Utf8(), true),
new arrow.Field("price", new arrow.Float32(), true),
]);
const data = [
{ vector: [3.1, 4.1], item: "foo", price: 10.0 },
{ vector: [5.9, 26.5], item: "bar", price: 20.0 },
];
const tbl = await db.createTable({
name: "myTableWithSchema",
data,
schema,
});
// --8<-- [end:create_table_with_schema]
}
// --8<-- [start:add]
const newData = Array.from({ length: 500 }, (_, i) => ({
vector: [i, i + 1],
item: "fizz",
price: i * 0.1,
}));
await tbl.add(newData);
// --8<-- [end:add]
// --8<-- [start:create_index]
await tbl.createIndex({
type: "ivf_pq",
num_partitions: 2,
num_sub_vectors: 2,
});
// --8<-- [end:create_index]
// --8<-- [start:create_empty_table]
const schema = new arrow.Schema([
new arrow.Field("id", new arrow.Int32()),
new arrow.Field("name", new arrow.Utf8()),
]);
const empty_tbl = await db.createTable({ name: "empty_table", schema });
// --8<-- [end:create_empty_table]
{
// --8<-- [start:create_f16_table]
const dim = 16;
const total = 10;
const schema = new Schema([
new Field("id", new Int32()),
new Field(
"vector",
new FixedSizeList(dim, new Field("item", new Float16(), true)),
false,
),
]);
const data = lancedb.makeArrowTable(
Array.from(Array(total), (_, i) => ({
id: i,
vector: Array.from(Array(dim), Math.random),
})),
{ schema },
);
const table = await db.createTable("f16_tbl", data);
// --8<-- [end:create_f16_table]
}
// --8<-- [start:search]
const query = await tbl.search([100, 100]).limit(2).execute();
// --8<-- [end:search]
console.log(query);
// --8<-- [start:delete]
await tbl.delete('item = "fizz"');
// --8<-- [end:delete]
// --8<-- [start:drop_table]
await db.dropTable("myTable");
// --8<-- [end:drop_table]
};
async function main() {
await example();
console.log("Basic example: done");
}
main();

View File

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

View File

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

View File

@@ -1,62 +0,0 @@
# Data management
This section covers concepts related to managing your data over time in LanceDB.
## A primer on Lance
Because LanceDB is built on top of the [Lance](https://lancedb.github.io/lance/) data format, it helps to understand some of its core ideas. Just like Apache Arrow, Lance is a fast columnar data format, but it has the added benefit of being versionable, query and train ML models on. Lance is designed to be used with simple and complex data types, like tabular data, images, videos audio, 3D point clouds (which are deeply nested) and more.
The following concepts are important to keep in mind:
- Data storage is columnar and is interoperable with other columnar formats (such as Parquet) via Arrow
- Data is divided into fragments that represent a subset of the data
- Data is versioned, with each insert operation creating a new version of the dataset and an update to the manifest that tracks versions via metadata
!!! note
1. First, each version contains metadata and just the new/updated data in your transaction. So if you have 100 versions, they aren't 100 duplicates of the same data. However, they do have 100x the metadata overhead of a single version, which can result in slower queries.
2. Second, these versions exist to keep LanceDB scalable and consistent. We do not immediately blow away old versions when creating new ones because other clients might be in the middle of querying the old version. It's important to retain older versions for as long as they might be queried.
## What are fragments?
Fragments are chunks of data in a Lance dataset. Each fragment includes multiple files that contain several columns in the chunk of data that it represents.
## Compaction
As you insert more data, your dataset will grow and you'll need to perform *compaction* to maintain query throughput (i.e., keep latencies down to a minimum). Compaction is the process of merging fragments together to reduce the amount of metadata that needs to be managed, and to reduce the number of files that need to be opened while scanning the dataset.
### How does compaction improve performance?
Compaction performs the following tasks in the background:
- Removes deleted rows from fragments
- Removes dropped columns from fragments
- Merges small fragments into larger ones
Depending on the use case and dataset, optimal compaction will have different requirements. As a rule of thumb:
- Its always better to use *batch* inserts rather than adding 1 row at a time (to avoid too small fragments). If single-row inserts are unavoidable, run compaction on a regular basis to merge them into larger fragments.
- Keep the number of fragments under 100, which is suitable for most use cases (for *really* large datasets of >500M rows, more fragments might be needed)
## Deletion
Although Lance allows you to delete rows from a dataset, it does not actually delete the data immediately. It simply marks the row as deleted in the `DataFile` that represents a fragment. For a given version of the dataset, each fragment can have up to one deletion file (if no rows were ever deleted from that fragment, it will not have a deletion file). This is important to keep in mind because it means that the data is still there, and can be recovered if needed, as long as that version still exists based on your backup policy.
## Reindexing
Reindexing is the process of updating the index to account for new data, keeping good performance for queries. This applies to either a full-text search (FTS) index or a vector index. For ANN search, new data will always be included in query results, but queries on tables with unindexed data will fallback to slower search methods for the new parts of the table. This is another important operation to run periodically as your data grows, as it also improves performance. This is especially important if you're appending large amounts of data to an existing dataset.
!!! tip
When adding new data to a dataset that has an existing index (either FTS or vector), LanceDB doesn't immediately update the index until a reindex operation is complete.
Both LanceDB OSS and Cloud support reindexing, but the process (at least for now) is different for each, depending on the type of index.
When a reindex job is triggered in the background, the entire data is reindexed, but in the interim as new queries come in, LanceDB will combine results from the existing index with exhaustive kNN search on the new data. This is done to ensure that you're still searching on all your data, but it does come at a performance cost. The more data that you add without reindexing, the impact on latency (due to exhaustive search) can be noticeable.
### Vector reindex
* LanceDB Cloud supports incremental reindexing, where a background process will trigger a new index build for you automatically when new data is added to a dataset
* LanceDB OSS requires you to manually trigger a reindex operation -- we are working on adding incremental reindexing to LanceDB OSS as well
### FTS reindex
FTS reindexing is supported in both LanceDB OSS and Cloud, but requires that it's manually rebuilt once you have a significant enough amount of new data added that needs to be reindexed. We [updated](https://github.com/lancedb/lancedb/pull/762) Tantivy's default heap size from 128MB to 1GB in LanceDB to make it much faster to reindex, by up to 10x from the default settings.

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