mirror of
https://github.com/lancedb/lancedb.git
synced 2026-09-04 20:48:50 +00:00
Compare commits
74 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 3e4be3c4b5 | |||
| fa1b04f341 | |||
| 367abe99d2 | |||
| 52ce2c995c | |||
| e71a00998c | |||
| 39a2ac0a1c | |||
| bc7b344fa4 | |||
| f91d2f5fec | |||
| cf81b6419f | |||
| 0498ac1f2f | |||
| aeb1c3ee6a | |||
| f9ae46c0e7 | |||
| 84bf022fb1 | |||
| 310967eceb | |||
| 154dbeee2a | |||
| c9c08ac8b9 | |||
| e253f5d9b6 | |||
| 05b4fb0990 | |||
| 613b9c1099 | |||
| d5948576b9 | |||
| 0d3fc7860a | |||
| 531cec075c | |||
| 0e486511fa | |||
| 367262662d | |||
| 11efaf46ae | |||
| 1ea22ee5ef | |||
| 8cef8806e9 | |||
| a3cd7fce69 | |||
| 48ddc833dd | |||
| 2802764092 | |||
| 37bbb0dba1 | |||
| 155ec16161 | |||
| 636b8b5bbd | |||
| 715b81c86b | |||
| 7e1616376e | |||
| d5ac5b949a | |||
| 7be6f45e0b | |||
| d9e2d51f51 | |||
| e081708cce | |||
| 2d60ea6938 | |||
| dcb1443143 | |||
| c0230f91d2 | |||
| 5d629c9ecb | |||
| 14973ac9d1 | |||
| 70cbee6293 | |||
| 02783bf440 | |||
| 4323ca0147 | |||
| bd3dd6a8e5 | |||
| 3c1162612e | |||
| 53c7c560c9 | |||
| de4f77800d | |||
| b6ab721cf7 | |||
| 027d53500b | |||
| 9098f47e73 | |||
| 826a3e5ee9 | |||
| 9fac56252e | |||
| c55ca20c1b | |||
| 5cdb15feef | |||
| 7a3eea927f | |||
| 5dd9b072d8 | |||
| 6dde379d44 | |||
| 55f09ef1cd | |||
| e9d8651d18 | |||
| 071f467571 | |||
| f83aa25119 | |||
| 0a8fe4d026 | |||
| 3ad7be9825 | |||
| 589041d842 | |||
| 2e4cd56ab1 | |||
| 6fd8586fa7 | |||
| 6329b57604 | |||
| c51b13e70f | |||
| 0859312b83 | |||
| a6e8ec8d48 |
+1
-1
@@ -1,5 +1,5 @@
|
||||
[tool.bumpversion]
|
||||
current_version = "0.25.0-beta.0"
|
||||
current_version = "0.27.0-beta.3"
|
||||
parse = """(?x)
|
||||
(?P<major>0|[1-9]\\d*)\\.
|
||||
(?P<minor>0|[1-9]\\d*)\\.
|
||||
|
||||
@@ -29,6 +29,7 @@ runs:
|
||||
if: ${{ inputs.arm-build == 'false' }}
|
||||
uses: PyO3/maturin-action@v1
|
||||
with:
|
||||
maturin-version: "1.12.4"
|
||||
command: build
|
||||
working-directory: python
|
||||
docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/'"
|
||||
@@ -44,6 +45,7 @@ runs:
|
||||
if: ${{ inputs.arm-build == 'true' }}
|
||||
uses: PyO3/maturin-action@v1
|
||||
with:
|
||||
maturin-version: "1.12.4"
|
||||
command: build
|
||||
working-directory: python
|
||||
docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/'"
|
||||
|
||||
@@ -20,6 +20,7 @@ runs:
|
||||
uses: PyO3/maturin-action@v1
|
||||
with:
|
||||
command: build
|
||||
maturin-version: "1.12.4"
|
||||
# TODO: pass through interpreter
|
||||
args: ${{ inputs.args }}
|
||||
docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/'"
|
||||
|
||||
@@ -25,6 +25,7 @@ runs:
|
||||
uses: PyO3/maturin-action@v1
|
||||
with:
|
||||
command: build
|
||||
maturin-version: "1.12.4"
|
||||
args: ${{ inputs.args }}
|
||||
docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/'"
|
||||
working-directory: python
|
||||
|
||||
@@ -42,7 +42,7 @@ jobs:
|
||||
name: Report Workflow Failure
|
||||
runs-on: ubuntu-latest
|
||||
needs: [build]
|
||||
if: always() && (github.event_name == 'release' || github.event_name == 'workflow_dispatch')
|
||||
if: always() && failure() && startsWith(github.ref, 'refs/tags/v')
|
||||
permissions:
|
||||
contents: read
|
||||
issues: write
|
||||
|
||||
@@ -0,0 +1,173 @@
|
||||
name: Codex Fix CI
|
||||
|
||||
on:
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
workflow_run_url:
|
||||
description: "Failing CI workflow run URL (e.g., https://github.com/lancedb/lancedb/actions/runs/12345678)"
|
||||
required: true
|
||||
type: string
|
||||
branch:
|
||||
description: "Branch to fix (e.g., main, release/v2.0, or feature-branch)"
|
||||
required: true
|
||||
type: string
|
||||
guidelines:
|
||||
description: "Additional guidelines for the fix (optional)"
|
||||
required: false
|
||||
type: string
|
||||
|
||||
permissions:
|
||||
contents: write
|
||||
pull-requests: write
|
||||
actions: read
|
||||
|
||||
jobs:
|
||||
fix-ci:
|
||||
runs-on: warp-ubuntu-latest-x64-4x
|
||||
timeout-minutes: 60
|
||||
env:
|
||||
CC: clang
|
||||
CXX: clang++
|
||||
steps:
|
||||
- name: Show inputs
|
||||
run: |
|
||||
echo "workflow_run_url = ${{ inputs.workflow_run_url }}"
|
||||
echo "branch = ${{ inputs.branch }}"
|
||||
echo "guidelines = ${{ inputs.guidelines }}"
|
||||
|
||||
- name: Checkout Repo
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
ref: ${{ inputs.branch }}
|
||||
fetch-depth: 0
|
||||
persist-credentials: true
|
||||
|
||||
- name: Set up Node.js
|
||||
uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: 20
|
||||
|
||||
- name: Install Codex CLI
|
||||
run: npm install -g @openai/codex
|
||||
|
||||
- name: Install Rust toolchain
|
||||
uses: dtolnay/rust-toolchain@stable
|
||||
with:
|
||||
toolchain: stable
|
||||
components: clippy, rustfmt
|
||||
|
||||
- uses: Swatinem/rust-cache@v2
|
||||
|
||||
- name: Install system dependencies
|
||||
run: |
|
||||
sudo apt-get update
|
||||
sudo apt-get install -y protobuf-compiler libssl-dev
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: '3.11'
|
||||
|
||||
- name: Install Python dependencies
|
||||
run: |
|
||||
pip install maturin ruff pytest pyarrow pandas polars
|
||||
|
||||
- name: Set up Java
|
||||
uses: actions/setup-java@v4
|
||||
with:
|
||||
distribution: temurin
|
||||
java-version: '11'
|
||||
cache: maven
|
||||
|
||||
- name: Install Node.js dependencies for TypeScript bindings
|
||||
run: |
|
||||
cd nodejs
|
||||
npm ci
|
||||
|
||||
- name: Configure git user
|
||||
run: |
|
||||
git config user.name "lancedb automation"
|
||||
git config user.email "robot@lancedb.com"
|
||||
|
||||
- name: Run Codex to fix CI failure
|
||||
env:
|
||||
WORKFLOW_RUN_URL: ${{ inputs.workflow_run_url }}
|
||||
BRANCH: ${{ inputs.branch }}
|
||||
GUIDELINES: ${{ inputs.guidelines }}
|
||||
GITHUB_TOKEN: ${{ secrets.ROBOT_TOKEN }}
|
||||
GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
|
||||
OPENAI_API_KEY: ${{ secrets.CODEX_TOKEN }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
|
||||
cat <<EOF >/tmp/codex-prompt.txt
|
||||
You are running inside the lancedb repository on a GitHub Actions runner. Your task is to fix a CI failure.
|
||||
|
||||
Input parameters:
|
||||
- Failing workflow run URL: ${WORKFLOW_RUN_URL}
|
||||
- Branch to fix: ${BRANCH}
|
||||
- Additional guidelines: ${GUIDELINES:-"None provided"}
|
||||
|
||||
Follow these steps exactly:
|
||||
|
||||
1. Extract the run ID from the workflow URL. The URL format is https://github.com/lancedb/lancedb/actions/runs/<run_id>.
|
||||
|
||||
2. Use "gh run view <run_id> --json jobs,conclusion,name" to get information about the failed run.
|
||||
|
||||
3. Identify which jobs failed. For each failed job, use "gh run view <run_id> --job <job_id> --log-failed" to get the failure logs.
|
||||
|
||||
4. Analyze the failure logs to understand what went wrong. Common failures include:
|
||||
- Compilation errors
|
||||
- Test failures
|
||||
- Clippy warnings treated as errors
|
||||
- Formatting issues
|
||||
- Dependency issues
|
||||
|
||||
5. Based on the analysis, fix the issues in the codebase:
|
||||
- For compilation errors: Fix the code that doesn't compile
|
||||
- For test failures: Fix the failing tests or the code they test
|
||||
- For clippy warnings: Apply the suggested fixes
|
||||
- For formatting issues: Run "cargo fmt --all"
|
||||
- For other issues: Apply appropriate fixes
|
||||
|
||||
6. After making fixes, verify them locally:
|
||||
- Run "cargo fmt --all" to ensure formatting is correct
|
||||
- Run "cargo clippy --workspace --tests --all-features -- -D warnings" to check for issues
|
||||
- Run ONLY the specific failing tests to confirm they pass now:
|
||||
- For Rust test failures: Run the specific test with "cargo test -p <crate> <test_name>"
|
||||
- For Python test failures: Build with "cd python && maturin develop" then run "pytest <specific_test_file>::<test_name>"
|
||||
- For Java test failures: Run "cd java && mvn test -Dtest=<TestClass>#<testMethod>"
|
||||
- For TypeScript test failures: Run "cd nodejs && npm run build && npm test -- --testNamePattern='<test_name>'"
|
||||
- Do NOT run the full test suite - only run the tests that were failing
|
||||
|
||||
7. If the additional guidelines are provided, follow them as well.
|
||||
|
||||
8. Inspect "git status --short" and "git diff" to review your changes.
|
||||
|
||||
9. Create a fix branch: "git checkout -b codex/fix-ci-<run_id>".
|
||||
|
||||
10. Stage all changes with "git add -A" and commit with message "fix: resolve CI failures from run <run_id>".
|
||||
|
||||
11. Push the branch: "git push origin codex/fix-ci-<run_id>". If the remote branch exists, delete it first with "gh api -X DELETE repos/lancedb/lancedb/git/refs/heads/codex/fix-ci-<run_id>" then push. Do NOT use "git push --force" or "git push -f".
|
||||
|
||||
12. Create a pull request targeting "${BRANCH}":
|
||||
- Title: "ci: <short summary describing the fix>" (e.g., "ci: fix clippy warnings in lancedb" or "ci: resolve test flakiness in vector search")
|
||||
- First, write the PR body to /tmp/pr-body.md using a heredoc (cat <<'PREOF' > /tmp/pr-body.md). The body should include:
|
||||
- Link to the failing workflow run
|
||||
- Summary of what failed
|
||||
- Description of the fixes applied
|
||||
- Then run "gh pr create --base ${BRANCH} --body-file /tmp/pr-body.md".
|
||||
|
||||
13. Display the new PR URL, "git status --short", and a summary of what was fixed.
|
||||
|
||||
Constraints:
|
||||
- Use bash commands for all operations.
|
||||
- Do not merge the PR.
|
||||
- Do not modify GitHub workflow files unless they are the cause of the failure.
|
||||
- If any command fails, diagnose and attempt to fix the issue instead of aborting immediately.
|
||||
- If you cannot fix the issue automatically, create the PR anyway with a clear explanation of what you tried and what remains to be fixed.
|
||||
- env "GH_TOKEN" is available, use "gh" tools for GitHub-related operations.
|
||||
EOF
|
||||
|
||||
printenv OPENAI_API_KEY | codex login --with-api-key
|
||||
codex --config shell_environment_policy.ignore_default_excludes=true exec --dangerously-bypass-approvals-and-sandbox "$(cat /tmp/codex-prompt.txt)"
|
||||
@@ -86,16 +86,17 @@ jobs:
|
||||
You are running inside the lancedb repository on a GitHub Actions runner. Update the Lance dependency to version ${VERSION} and prepare a pull request for maintainers to review.
|
||||
|
||||
Follow these steps exactly:
|
||||
1. Use script "ci/set_lance_version.py" to update Lance dependencies. The script already refreshes Cargo metadata, so allow it to finish even if it takes time.
|
||||
2. Run "cargo clippy --workspace --tests --all-features -- -D warnings". If diagnostics appear, fix them yourself and rerun clippy until it exits cleanly. Do not skip any warnings.
|
||||
3. After clippy succeeds, run "cargo fmt --all" to format the workspace.
|
||||
4. Ensure the repository is clean except for intentional changes. Inspect "git status --short" and "git diff" to confirm the dependency update and any required fixes.
|
||||
5. Create and switch to a new branch named "${BRANCH_NAME}" (replace any duplicated hyphens if necessary).
|
||||
6. Stage all relevant files with "git add -A". Commit using the message "${COMMIT_TYPE}: update lance dependency to v${VERSION}".
|
||||
7. Push the branch to origin. If the branch already exists, force-push your changes.
|
||||
8. env "GH_TOKEN" is available, use "gh" tools for github related operations like creating pull request.
|
||||
9. Create a pull request targeting "main" with title "${COMMIT_TYPE}: update lance dependency to v${VERSION}". First, write the PR body to /tmp/pr-body.md using a heredoc (cat <<'EOF' > /tmp/pr-body.md). The body should summarize the dependency bump, clippy/fmt verification, and link the triggering tag (${TAG}). Then run "gh pr create --body-file /tmp/pr-body.md".
|
||||
10. After creating the PR, display the PR URL, "git status --short", and a concise summary of the commands run and their results.
|
||||
1. Use script "ci/set_lance_version.py" to update Lance Rust dependencies. The script already refreshes Cargo metadata, so allow it to finish even if it takes time.
|
||||
2. Update the Java lance-core dependency version in "java/pom.xml": change the "<lance-core.version>...</lance-core.version>" property to "${VERSION}".
|
||||
3. Run "cargo clippy --workspace --tests --all-features -- -D warnings". If diagnostics appear, fix them yourself and rerun clippy until it exits cleanly. Do not skip any warnings.
|
||||
4. After clippy succeeds, run "cargo fmt --all" to format the workspace.
|
||||
5. Ensure the repository is clean except for intentional changes. Inspect "git status --short" and "git diff" to confirm the dependency update and any required fixes.
|
||||
6. Create and switch to a new branch named "${BRANCH_NAME}" (replace any duplicated hyphens if necessary).
|
||||
7. Stage all relevant files with "git add -A". Commit using the message "${COMMIT_TYPE}: update lance dependency to v${VERSION}".
|
||||
8. Push the branch to origin. If the remote branch already exists, delete it first with "gh api -X DELETE repos/lancedb/lancedb/git/refs/heads/${BRANCH_NAME}" then push with "git push origin ${BRANCH_NAME}". Do NOT use "git push --force" or "git push -f".
|
||||
9. env "GH_TOKEN" is available, use "gh" tools for github related operations like creating pull request.
|
||||
10. Create a pull request targeting "main" with title "${COMMIT_TYPE}: update lance dependency to v${VERSION}". First, write the PR body to /tmp/pr-body.md using a heredoc (cat <<'EOF' > /tmp/pr-body.md). The body should summarize the dependency bump, clippy/fmt verification, and link the triggering tag (${TAG}). Then run "gh pr create --body-file /tmp/pr-body.md".
|
||||
11. After creating the PR, display the PR URL, "git status --short", and a concise summary of the commands run and their results.
|
||||
|
||||
Constraints:
|
||||
- Use bash commands; avoid modifying GitHub workflow files other than through the scripted task above.
|
||||
|
||||
@@ -8,6 +8,8 @@ on:
|
||||
paths:
|
||||
- Cargo.toml
|
||||
- nodejs/**
|
||||
- rust/**
|
||||
- docs/src/js/**
|
||||
- .github/workflows/nodejs.yml
|
||||
- docker-compose.yml
|
||||
|
||||
@@ -76,8 +78,11 @@ jobs:
|
||||
fetch-depth: 0
|
||||
lfs: true
|
||||
- uses: actions/setup-node@v3
|
||||
name: Setup Node.js 20 for build
|
||||
with:
|
||||
node-version: ${{ matrix.node-version }}
|
||||
# @napi-rs/cli v3 requires Node >= 20.12 (via @inquirer/prompts@8).
|
||||
# Build always on Node 20; tests run on the matrix version below.
|
||||
node-version: 20
|
||||
cache: 'npm'
|
||||
cache-dependency-path: nodejs/package-lock.json
|
||||
- uses: Swatinem/rust-cache@v2
|
||||
@@ -85,12 +90,16 @@ jobs:
|
||||
run: |
|
||||
sudo apt update
|
||||
sudo apt install -y protobuf-compiler libssl-dev
|
||||
npm install -g @napi-rs/cli
|
||||
- name: Build
|
||||
run: |
|
||||
npm ci --include=optional
|
||||
npm run build:debug -- --profile ci
|
||||
npm run tsc
|
||||
- uses: actions/setup-node@v3
|
||||
name: Setup Node.js ${{ matrix.node-version }} for test
|
||||
with:
|
||||
node-version: ${{ matrix.node-version }}
|
||||
- name: Compile TypeScript
|
||||
run: npm run tsc
|
||||
- name: Setup localstack
|
||||
working-directory: .
|
||||
run: docker compose up --detach --wait
|
||||
@@ -143,7 +152,6 @@ jobs:
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
brew install protobuf
|
||||
npm install -g @napi-rs/cli
|
||||
- name: Build
|
||||
run: |
|
||||
npm ci --include=optional
|
||||
|
||||
@@ -128,16 +128,13 @@ jobs:
|
||||
- target: x86_64-unknown-linux-musl
|
||||
# This one seems to need some extra memory
|
||||
host: ubuntu-2404-8x-x64
|
||||
# https://github.com/napi-rs/napi-rs/blob/main/alpine.Dockerfile
|
||||
docker: ghcr.io/napi-rs/napi-rs/nodejs-rust:lts-alpine
|
||||
features: fp16kernels
|
||||
pre_build: |-
|
||||
set -e &&
|
||||
apk add protobuf-dev curl &&
|
||||
ln -s /usr/lib/gcc/x86_64-alpine-linux-musl/14.2.0/crtbeginS.o /usr/lib/crtbeginS.o &&
|
||||
ln -s /usr/lib/libgcc_s.so /usr/lib/libgcc.so &&
|
||||
CC=gcc &&
|
||||
CXX=g++
|
||||
sudo apt-get update &&
|
||||
sudo apt-get install -y protobuf-compiler pkg-config &&
|
||||
rustup target add x86_64-unknown-linux-musl &&
|
||||
export EXTRA_ARGS="-x"
|
||||
- target: aarch64-unknown-linux-gnu
|
||||
host: ubuntu-2404-8x-x64
|
||||
# https://github.com/napi-rs/napi-rs/blob/main/debian-aarch64.Dockerfile
|
||||
@@ -153,15 +150,13 @@ jobs:
|
||||
rustup target add aarch64-unknown-linux-gnu
|
||||
- target: aarch64-unknown-linux-musl
|
||||
host: ubuntu-2404-8x-x64
|
||||
# https://github.com/napi-rs/napi-rs/blob/main/alpine.Dockerfile
|
||||
docker: ghcr.io/napi-rs/napi-rs/nodejs-rust:lts-alpine
|
||||
features: ","
|
||||
pre_build: |-
|
||||
set -e &&
|
||||
apk add protobuf-dev &&
|
||||
sudo apt-get update &&
|
||||
sudo apt-get install -y protobuf-compiler &&
|
||||
rustup target add aarch64-unknown-linux-musl &&
|
||||
export CC_aarch64_unknown_linux_musl=aarch64-linux-musl-gcc &&
|
||||
export CXX_aarch64_unknown_linux_musl=aarch64-linux-musl-g++
|
||||
export EXTRA_ARGS="-x"
|
||||
name: build - ${{ matrix.settings.target }}
|
||||
runs-on: ${{ matrix.settings.host }}
|
||||
defaults:
|
||||
@@ -192,12 +187,18 @@ jobs:
|
||||
.cargo-cache
|
||||
target/
|
||||
key: nodejs-${{ matrix.settings.target }}-cargo-${{ matrix.settings.host }}
|
||||
- name: Setup toolchain
|
||||
run: ${{ matrix.settings.setup }}
|
||||
if: ${{ matrix.settings.setup }}
|
||||
shell: bash
|
||||
- name: Install dependencies
|
||||
run: npm ci
|
||||
- name: Install Zig
|
||||
uses: mlugg/setup-zig@v2
|
||||
if: ${{ contains(matrix.settings.target, 'musl') }}
|
||||
with:
|
||||
version: 0.14.1
|
||||
- name: Install cargo-zigbuild
|
||||
uses: taiki-e/install-action@v2
|
||||
if: ${{ contains(matrix.settings.target, 'musl') }}
|
||||
with:
|
||||
tool: cargo-zigbuild
|
||||
- name: Build in docker
|
||||
uses: addnab/docker-run-action@v3
|
||||
if: ${{ matrix.settings.docker }}
|
||||
@@ -210,24 +211,24 @@ jobs:
|
||||
run: |
|
||||
set -e
|
||||
${{ matrix.settings.pre_build }}
|
||||
npx napi build --platform --release --no-const-enum \
|
||||
npx napi build --platform --release \
|
||||
--features ${{ matrix.settings.features }} \
|
||||
--target ${{ matrix.settings.target }} \
|
||||
--dts ../lancedb/native.d.ts \
|
||||
--js ../lancedb/native.js \
|
||||
--strip \
|
||||
dist/
|
||||
--output-dir dist/
|
||||
- name: Build
|
||||
run: |
|
||||
${{ matrix.settings.pre_build }}
|
||||
npx napi build --platform --release --no-const-enum \
|
||||
npx napi build --platform --release \
|
||||
--features ${{ matrix.settings.features }} \
|
||||
--target ${{ matrix.settings.target }} \
|
||||
--dts ../lancedb/native.d.ts \
|
||||
--js ../lancedb/native.js \
|
||||
--strip \
|
||||
$EXTRA_ARGS \
|
||||
dist/
|
||||
--output-dir dist/
|
||||
if: ${{ !matrix.settings.docker }}
|
||||
shell: bash
|
||||
- name: Upload artifact
|
||||
@@ -318,7 +319,7 @@ jobs:
|
||||
- name: Setup node
|
||||
uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: 20
|
||||
node-version: 24
|
||||
cache: npm
|
||||
cache-dependency-path: nodejs/package-lock.json
|
||||
registry-url: "https://registry.npmjs.org"
|
||||
@@ -348,14 +349,15 @@ jobs:
|
||||
run: find npm
|
||||
- name: Publish
|
||||
env:
|
||||
NODE_AUTH_TOKEN: ${{ secrets.LANCEDB_NPM_REGISTRY_TOKEN }}
|
||||
DRY_RUN: ${{ !startsWith(github.ref, 'refs/tags/v') }}
|
||||
run: |
|
||||
npm config set provenance true
|
||||
ARGS="--access public"
|
||||
if [[ $DRY_RUN == "true" ]]; then
|
||||
ARGS="$ARGS --dry-run"
|
||||
fi
|
||||
if [[ $GITHUB_REF =~ refs/tags/v(.*)-beta.* ]]; then
|
||||
VERSION=$(node -p "require('./package.json').version")
|
||||
if [[ $VERSION == *-* ]]; then
|
||||
ARGS="$ARGS --tag preview"
|
||||
fi
|
||||
npm publish $ARGS
|
||||
@@ -363,7 +365,7 @@ jobs:
|
||||
name: Report Workflow Failure
|
||||
runs-on: ubuntu-latest
|
||||
needs: [build-lancedb, test-lancedb, publish]
|
||||
if: always() && (github.event_name == 'release' || github.event_name == 'workflow_dispatch')
|
||||
if: always() && failure() && startsWith(github.ref, 'refs/tags/v')
|
||||
permissions:
|
||||
contents: read
|
||||
issues: write
|
||||
|
||||
@@ -181,7 +181,7 @@ jobs:
|
||||
permissions:
|
||||
contents: read
|
||||
issues: write
|
||||
if: always() && (github.event_name == 'release' || github.event_name == 'workflow_dispatch')
|
||||
if: always() && failure() && startsWith(github.ref, 'refs/tags/python-v')
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: ./.github/actions/create-failure-issue
|
||||
|
||||
@@ -8,7 +8,12 @@ on:
|
||||
paths:
|
||||
- Cargo.toml
|
||||
- python/**
|
||||
- rust/**
|
||||
- .github/workflows/python.yml
|
||||
- .github/workflows/build_linux_wheel/**
|
||||
- .github/workflows/build_mac_wheel/**
|
||||
- .github/workflows/build_windows_wheel/**
|
||||
- .github/workflows/run_tests/**
|
||||
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
|
||||
|
||||
@@ -100,7 +100,9 @@ jobs:
|
||||
lfs: true
|
||||
- uses: Swatinem/rust-cache@v2
|
||||
- name: Install dependencies
|
||||
run: sudo apt install -y protobuf-compiler libssl-dev
|
||||
run: |
|
||||
sudo apt update
|
||||
sudo apt install -y protobuf-compiler libssl-dev
|
||||
- uses: rui314/setup-mold@v1
|
||||
- name: Make Swap
|
||||
run: |
|
||||
@@ -183,7 +185,7 @@ jobs:
|
||||
runs-on: ubuntu-24.04
|
||||
strategy:
|
||||
matrix:
|
||||
msrv: ["1.88.0"] # This should match up with rust-version in Cargo.toml
|
||||
msrv: ["1.91.0"] # This should match up with rust-version in Cargo.toml
|
||||
env:
|
||||
# Need up-to-date compilers for kernels
|
||||
CC: clang-18
|
||||
|
||||
Generated
+405
-487
File diff suppressed because it is too large
Load Diff
+25
-23
@@ -5,30 +5,30 @@ exclude = ["python"]
|
||||
resolver = "2"
|
||||
|
||||
[workspace.package]
|
||||
edition = "2021"
|
||||
edition = "2024"
|
||||
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"]
|
||||
rust-version = "1.88.0"
|
||||
rust-version = "1.91.0"
|
||||
|
||||
[workspace.dependencies]
|
||||
lance = { "version" = "=3.0.0-beta.1", default-features = false, "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-core = { "version" = "=3.0.0-beta.1", "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datagen = { "version" = "=3.0.0-beta.1", "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-file = { "version" = "=3.0.0-beta.1", "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-io = { "version" = "=3.0.0-beta.1", default-features = false, "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-index = { "version" = "=3.0.0-beta.1", "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-linalg = { "version" = "=3.0.0-beta.1", "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace = { "version" = "=3.0.0-beta.1", "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace-impls = { "version" = "=3.0.0-beta.1", default-features = false, "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-table = { "version" = "=3.0.0-beta.1", "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-testing = { "version" = "=3.0.0-beta.1", "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datafusion = { "version" = "=3.0.0-beta.1", "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-encoding = { "version" = "=3.0.0-beta.1", "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-arrow = { "version" = "=3.0.0-beta.1", "tag" = "v3.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance = { "version" = "=4.0.0-beta.7", default-features = false, "tag" = "v4.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-core = { "version" = "=4.0.0-beta.7", "tag" = "v4.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datagen = { "version" = "=4.0.0-beta.7", "tag" = "v4.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-file = { "version" = "=4.0.0-beta.7", "tag" = "v4.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-io = { "version" = "=4.0.0-beta.7", default-features = false, "tag" = "v4.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-index = { "version" = "=4.0.0-beta.7", "tag" = "v4.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-linalg = { "version" = "=4.0.0-beta.7", "tag" = "v4.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace = { "version" = "=4.0.0-beta.7", "tag" = "v4.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace-impls = { "version" = "=4.0.0-beta.7", default-features = false, "tag" = "v4.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-table = { "version" = "=4.0.0-beta.7", "tag" = "v4.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-testing = { "version" = "=4.0.0-beta.7", "tag" = "v4.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datafusion = { "version" = "=4.0.0-beta.7", "tag" = "v4.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-encoding = { "version" = "=4.0.0-beta.7", "tag" = "v4.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-arrow = { "version" = "=4.0.0-beta.7", "tag" = "v4.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
|
||||
ahash = "0.8"
|
||||
# Note that this one does not include pyarrow
|
||||
arrow = { version = "57.2", optional = false }
|
||||
@@ -40,13 +40,15 @@ arrow-schema = "57.2"
|
||||
arrow-select = "57.2"
|
||||
arrow-cast = "57.2"
|
||||
async-trait = "0"
|
||||
datafusion = { version = "51.0", default-features = false }
|
||||
datafusion-catalog = "51.0"
|
||||
datafusion-common = { version = "51.0", default-features = false }
|
||||
datafusion-execution = "51.0"
|
||||
datafusion-expr = "51.0"
|
||||
datafusion-physical-plan = "51.0"
|
||||
datafusion-physical-expr = "51.0"
|
||||
datafusion = { version = "52.1", default-features = false }
|
||||
datafusion-catalog = "52.1"
|
||||
datafusion-common = { version = "52.1", default-features = false }
|
||||
datafusion-execution = "52.1"
|
||||
datafusion-expr = "52.1"
|
||||
datafusion-functions = "52.1"
|
||||
datafusion-physical-plan = "52.1"
|
||||
datafusion-physical-expr = "52.1"
|
||||
datafusion-sql = "52.1"
|
||||
env_logger = "0.11"
|
||||
half = { "version" = "2.7.1", default-features = false, features = [
|
||||
"num-traits",
|
||||
|
||||
@@ -0,0 +1,9 @@
|
||||
.PHONY: licenses
|
||||
|
||||
licenses:
|
||||
cargo about generate about.hbs -o RUST_THIRD_PARTY_LICENSES.html -c about.toml
|
||||
cd python && cargo about generate ../about.hbs -o RUST_THIRD_PARTY_LICENSES.html -c ../about.toml
|
||||
cd python && uv sync --all-extras && uv tool run pip-licenses --python .venv/bin/python --format=markdown --with-urls --output-file=PYTHON_THIRD_PARTY_LICENSES.md
|
||||
cd nodejs && cargo about generate ../about.hbs -o RUST_THIRD_PARTY_LICENSES.html -c ../about.toml
|
||||
cd nodejs && npx license-checker --markdown --out NODEJS_THIRD_PARTY_LICENSES.md
|
||||
cd java && ./mvnw license:aggregate-add-third-party -q
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,70 @@
|
||||
<html>
|
||||
|
||||
<head>
|
||||
<style>
|
||||
@media (prefers-color-scheme: dark) {
|
||||
body {
|
||||
background: #333;
|
||||
color: white;
|
||||
}
|
||||
a {
|
||||
color: skyblue;
|
||||
}
|
||||
}
|
||||
.container {
|
||||
font-family: sans-serif;
|
||||
max-width: 800px;
|
||||
margin: 0 auto;
|
||||
}
|
||||
.intro {
|
||||
text-align: center;
|
||||
}
|
||||
.licenses-list {
|
||||
list-style-type: none;
|
||||
margin: 0;
|
||||
padding: 0;
|
||||
}
|
||||
.license-used-by {
|
||||
margin-top: -10px;
|
||||
}
|
||||
.license-text {
|
||||
max-height: 200px;
|
||||
overflow-y: scroll;
|
||||
white-space: pre-wrap;
|
||||
}
|
||||
</style>
|
||||
</head>
|
||||
|
||||
<body>
|
||||
<main class="container">
|
||||
<div class="intro">
|
||||
<h1>Third Party Licenses</h1>
|
||||
<p>This page lists the licenses of the projects used in cargo-about.</p>
|
||||
</div>
|
||||
|
||||
<h2>Overview of licenses:</h2>
|
||||
<ul class="licenses-overview">
|
||||
{{#each overview}}
|
||||
<li><a href="#{{id}}">{{name}}</a> ({{count}})</li>
|
||||
{{/each}}
|
||||
</ul>
|
||||
|
||||
<h2>All license text:</h2>
|
||||
<ul class="licenses-list">
|
||||
{{#each licenses}}
|
||||
<li class="license">
|
||||
<h3 id="{{id}}">{{name}}</h3>
|
||||
<h4>Used by:</h4>
|
||||
<ul class="license-used-by">
|
||||
{{#each used_by}}
|
||||
<li><a href="{{#if crate.repository}} {{crate.repository}} {{else}} https://crates.io/crates/{{crate.name}} {{/if}}">{{crate.name}} {{crate.version}}</a></li>
|
||||
{{/each}}
|
||||
</ul>
|
||||
<pre class="license-text">{{text}}</pre>
|
||||
</li>
|
||||
{{/each}}
|
||||
</ul>
|
||||
</main>
|
||||
</body>
|
||||
|
||||
</html>
|
||||
+18
@@ -0,0 +1,18 @@
|
||||
accepted = [
|
||||
"0BSD",
|
||||
"Apache-2.0",
|
||||
"Apache-2.0 WITH LLVM-exception",
|
||||
"BSD-2-Clause",
|
||||
"BSD-3-Clause",
|
||||
"BSL-1.0",
|
||||
"bzip2-1.0.6",
|
||||
"CC0-1.0",
|
||||
"CDDL-1.0",
|
||||
"CDLA-Permissive-2.0",
|
||||
"ISC",
|
||||
"MIT",
|
||||
"MPL-2.0",
|
||||
"OpenSSL",
|
||||
"Unicode-3.0",
|
||||
"Zlib",
|
||||
]
|
||||
@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
|
||||
<dependency>
|
||||
<groupId>com.lancedb</groupId>
|
||||
<artifactId>lancedb-core</artifactId>
|
||||
<version>0.25.0-beta.0</version>
|
||||
<version>0.27.0-beta.3</version>
|
||||
</dependency>
|
||||
```
|
||||
|
||||
|
||||
@@ -367,6 +367,27 @@ Use [Table.listIndices](Table.md#listindices) to find the names of the indices.
|
||||
|
||||
***
|
||||
|
||||
### initialStorageOptions()
|
||||
|
||||
```ts
|
||||
abstract initialStorageOptions(): Promise<undefined | null | Record<string, string>>
|
||||
```
|
||||
|
||||
Get the initial storage options that were passed in when opening this table.
|
||||
|
||||
For dynamically refreshed options (e.g., credential vending), use
|
||||
[Table.latestStorageOptions](Table.md#lateststorageoptions).
|
||||
|
||||
Warning: This is an internal API and the return value is subject to change.
|
||||
|
||||
#### Returns
|
||||
|
||||
`Promise`<`undefined` \| `null` \| `Record`<`string`, `string`>>
|
||||
|
||||
The storage options, or undefined if no storage options were configured.
|
||||
|
||||
***
|
||||
|
||||
### isOpen()
|
||||
|
||||
```ts
|
||||
@@ -381,6 +402,28 @@ Return true if the table has not been closed
|
||||
|
||||
***
|
||||
|
||||
### latestStorageOptions()
|
||||
|
||||
```ts
|
||||
abstract latestStorageOptions(): Promise<undefined | null | Record<string, string>>
|
||||
```
|
||||
|
||||
Get the latest storage options, refreshing from provider if configured.
|
||||
|
||||
This method is useful for credential vending scenarios where storage options
|
||||
may be refreshed dynamically. If no dynamic provider is configured, this
|
||||
returns the initial static options.
|
||||
|
||||
Warning: This is an internal API and the return value is subject to change.
|
||||
|
||||
#### Returns
|
||||
|
||||
`Promise`<`undefined` \| `null` \| `Record`<`string`, `string`>>
|
||||
|
||||
The storage options, or undefined if no storage options were configured.
|
||||
|
||||
***
|
||||
|
||||
### listIndices()
|
||||
|
||||
```ts
|
||||
|
||||
@@ -8,6 +8,14 @@
|
||||
|
||||
## Properties
|
||||
|
||||
### numDeletedRows
|
||||
|
||||
```ts
|
||||
numDeletedRows: number;
|
||||
```
|
||||
|
||||
***
|
||||
|
||||
### version
|
||||
|
||||
```ts
|
||||
|
||||
@@ -0,0 +1,71 @@
|
||||
|
||||
List of third-party dependencies grouped by their license type.
|
||||
|
||||
Apache 2.0:
|
||||
|
||||
* error-prone annotations (com.google.errorprone:error_prone_annotations:2.28.0 - https://errorprone.info/error_prone_annotations)
|
||||
|
||||
Apache License 2.0:
|
||||
|
||||
* JsonNullable Jackson module (org.openapitools:jackson-databind-nullable:0.2.6 - https://github.com/OpenAPITools/jackson-databind-nullable)
|
||||
|
||||
Apache License V2.0:
|
||||
|
||||
* FlatBuffers Java API (com.google.flatbuffers:flatbuffers-java:23.5.26 - https://github.com/google/flatbuffers)
|
||||
|
||||
Apache License, Version 2.0:
|
||||
|
||||
* Apache Commons Codec (commons-codec:commons-codec:1.15 - https://commons.apache.org/proper/commons-codec/)
|
||||
* Apache HttpClient (org.apache.httpcomponents.client5:httpclient5:5.2.1 - https://hc.apache.org/httpcomponents-client-5.0.x/5.2.1/httpclient5/)
|
||||
* Apache HttpComponents Core HTTP/1.1 (org.apache.httpcomponents.core5:httpcore5:5.2 - https://hc.apache.org/httpcomponents-core-5.2.x/5.2/httpcore5/)
|
||||
* Apache HttpComponents Core HTTP/2 (org.apache.httpcomponents.core5:httpcore5-h2:5.2 - https://hc.apache.org/httpcomponents-core-5.2.x/5.2/httpcore5-h2/)
|
||||
* Arrow Format (org.apache.arrow:arrow-format:15.0.0 - https://arrow.apache.org/arrow-format/)
|
||||
* Arrow Java C Data Interface (org.apache.arrow:arrow-c-data:15.0.0 - https://arrow.apache.org/arrow-c-data/)
|
||||
* Arrow Java Dataset (org.apache.arrow:arrow-dataset:15.0.0 - https://arrow.apache.org/arrow-dataset/)
|
||||
* Arrow Memory - Core (org.apache.arrow:arrow-memory-core:15.0.0 - https://arrow.apache.org/arrow-memory/arrow-memory-core/)
|
||||
* Arrow Memory - Netty (org.apache.arrow:arrow-memory-netty:15.0.0 - https://arrow.apache.org/arrow-memory/arrow-memory-netty/)
|
||||
* Arrow Vectors (org.apache.arrow:arrow-vector:15.0.0 - https://arrow.apache.org/arrow-vector/)
|
||||
* Guava: Google Core Libraries for Java (com.google.guava:guava:33.3.1-jre - https://github.com/google/guava)
|
||||
* J2ObjC Annotations (com.google.j2objc:j2objc-annotations:3.0.0 - https://github.com/google/j2objc/)
|
||||
* Netty/Buffer (io.netty:netty-buffer:4.1.104.Final - https://netty.io/netty-buffer/)
|
||||
* Netty/Common (io.netty:netty-common:4.1.104.Final - https://netty.io/netty-common/)
|
||||
|
||||
Apache-2.0:
|
||||
|
||||
* Apache Commons Lang (org.apache.commons:commons-lang3:3.18.0 - https://commons.apache.org/proper/commons-lang/)
|
||||
* lance-namespace-apache-client (org.lance:lance-namespace-apache-client:0.4.5 - https://github.com/openapitools/openapi-generator)
|
||||
* lance-namespace-core (org.lance:lance-namespace-core:0.4.5 - https://lance.org/format/namespace/lance-namespace-core/)
|
||||
|
||||
EDL 1.0:
|
||||
|
||||
* Jakarta Activation API jar (jakarta.activation:jakarta.activation-api:1.2.2 - https://github.com/eclipse-ee4j/jaf/jakarta.activation-api)
|
||||
|
||||
Eclipse Distribution License - v 1.0:
|
||||
|
||||
* Eclipse Collections API (org.eclipse.collections:eclipse-collections-api:11.1.0 - https://github.com/eclipse/eclipse-collections/eclipse-collections-api)
|
||||
* Eclipse Collections Main Library (org.eclipse.collections:eclipse-collections:11.1.0 - https://github.com/eclipse/eclipse-collections/eclipse-collections)
|
||||
* Jakarta XML Binding API (jakarta.xml.bind:jakarta.xml.bind-api:2.3.3 - https://github.com/eclipse-ee4j/jaxb-api/jakarta.xml.bind-api)
|
||||
|
||||
Eclipse Public License - v 1.0:
|
||||
|
||||
* Eclipse Collections API (org.eclipse.collections:eclipse-collections-api:11.1.0 - https://github.com/eclipse/eclipse-collections/eclipse-collections-api)
|
||||
* Eclipse Collections Main Library (org.eclipse.collections:eclipse-collections:11.1.0 - https://github.com/eclipse/eclipse-collections/eclipse-collections)
|
||||
|
||||
The Apache Software License, Version 2.0:
|
||||
|
||||
* FindBugs-jsr305 (com.google.code.findbugs:jsr305:3.0.2 - http://findbugs.sourceforge.net/)
|
||||
* Guava InternalFutureFailureAccess and InternalFutures (com.google.guava:failureaccess:1.0.2 - https://github.com/google/guava/failureaccess)
|
||||
* Guava ListenableFuture only (com.google.guava:listenablefuture:9999.0-empty-to-avoid-conflict-with-guava - https://github.com/google/guava/listenablefuture)
|
||||
* Jackson datatype: JSR310 (com.fasterxml.jackson.datatype:jackson-datatype-jsr310:2.16.0 - https://github.com/FasterXML/jackson-modules-java8/jackson-datatype-jsr310)
|
||||
* Jackson module: Old JAXB Annotations (javax.xml.bind) (com.fasterxml.jackson.module:jackson-module-jaxb-annotations:2.17.1 - https://github.com/FasterXML/jackson-modules-base)
|
||||
* Jackson-annotations (com.fasterxml.jackson.core:jackson-annotations:2.16.0 - https://github.com/FasterXML/jackson)
|
||||
* Jackson-core (com.fasterxml.jackson.core:jackson-core:2.16.0 - https://github.com/FasterXML/jackson-core)
|
||||
* jackson-databind (com.fasterxml.jackson.core:jackson-databind:2.15.2 - https://github.com/FasterXML/jackson)
|
||||
* Jackson-JAXRS: base (com.fasterxml.jackson.jaxrs:jackson-jaxrs-base:2.17.1 - https://github.com/FasterXML/jackson-jaxrs-providers/jackson-jaxrs-base)
|
||||
* Jackson-JAXRS: JSON (com.fasterxml.jackson.jaxrs:jackson-jaxrs-json-provider:2.17.1 - https://github.com/FasterXML/jackson-jaxrs-providers/jackson-jaxrs-json-provider)
|
||||
* JAR JNI Loader (org.questdb:jar-jni:1.1.1 - https://github.com/questdb/rust-maven-plugin)
|
||||
* Lance Core (org.lance:lance-core:2.0.0 - https://lance.org/)
|
||||
|
||||
The MIT License:
|
||||
|
||||
* Checker Qual (org.checkerframework:checker-qual:3.43.0 - https://checkerframework.org/)
|
||||
@@ -0,0 +1,71 @@
|
||||
|
||||
List of third-party dependencies grouped by their license type.
|
||||
|
||||
Apache 2.0:
|
||||
|
||||
* error-prone annotations (com.google.errorprone:error_prone_annotations:2.28.0 - https://errorprone.info/error_prone_annotations)
|
||||
|
||||
Apache License 2.0:
|
||||
|
||||
* JsonNullable Jackson module (org.openapitools:jackson-databind-nullable:0.2.6 - https://github.com/OpenAPITools/jackson-databind-nullable)
|
||||
|
||||
Apache License V2.0:
|
||||
|
||||
* FlatBuffers Java API (com.google.flatbuffers:flatbuffers-java:23.5.26 - https://github.com/google/flatbuffers)
|
||||
|
||||
Apache License, Version 2.0:
|
||||
|
||||
* Apache Commons Codec (commons-codec:commons-codec:1.15 - https://commons.apache.org/proper/commons-codec/)
|
||||
* Apache HttpClient (org.apache.httpcomponents.client5:httpclient5:5.2.1 - https://hc.apache.org/httpcomponents-client-5.0.x/5.2.1/httpclient5/)
|
||||
* Apache HttpComponents Core HTTP/1.1 (org.apache.httpcomponents.core5:httpcore5:5.2 - https://hc.apache.org/httpcomponents-core-5.2.x/5.2/httpcore5/)
|
||||
* Apache HttpComponents Core HTTP/2 (org.apache.httpcomponents.core5:httpcore5-h2:5.2 - https://hc.apache.org/httpcomponents-core-5.2.x/5.2/httpcore5-h2/)
|
||||
* Arrow Format (org.apache.arrow:arrow-format:15.0.0 - https://arrow.apache.org/arrow-format/)
|
||||
* Arrow Java C Data Interface (org.apache.arrow:arrow-c-data:15.0.0 - https://arrow.apache.org/arrow-c-data/)
|
||||
* Arrow Java Dataset (org.apache.arrow:arrow-dataset:15.0.0 - https://arrow.apache.org/arrow-dataset/)
|
||||
* Arrow Memory - Core (org.apache.arrow:arrow-memory-core:15.0.0 - https://arrow.apache.org/arrow-memory/arrow-memory-core/)
|
||||
* Arrow Memory - Netty (org.apache.arrow:arrow-memory-netty:15.0.0 - https://arrow.apache.org/arrow-memory/arrow-memory-netty/)
|
||||
* Arrow Vectors (org.apache.arrow:arrow-vector:15.0.0 - https://arrow.apache.org/arrow-vector/)
|
||||
* Guava: Google Core Libraries for Java (com.google.guava:guava:33.3.1-jre - https://github.com/google/guava)
|
||||
* J2ObjC Annotations (com.google.j2objc:j2objc-annotations:3.0.0 - https://github.com/google/j2objc/)
|
||||
* Netty/Buffer (io.netty:netty-buffer:4.1.104.Final - https://netty.io/netty-buffer/)
|
||||
* Netty/Common (io.netty:netty-common:4.1.104.Final - https://netty.io/netty-common/)
|
||||
|
||||
Apache-2.0:
|
||||
|
||||
* Apache Commons Lang (org.apache.commons:commons-lang3:3.18.0 - https://commons.apache.org/proper/commons-lang/)
|
||||
* lance-namespace-apache-client (org.lance:lance-namespace-apache-client:0.4.5 - https://github.com/openapitools/openapi-generator)
|
||||
* lance-namespace-core (org.lance:lance-namespace-core:0.4.5 - https://lance.org/format/namespace/lance-namespace-core/)
|
||||
|
||||
EDL 1.0:
|
||||
|
||||
* Jakarta Activation API jar (jakarta.activation:jakarta.activation-api:1.2.2 - https://github.com/eclipse-ee4j/jaf/jakarta.activation-api)
|
||||
|
||||
Eclipse Distribution License - v 1.0:
|
||||
|
||||
* Eclipse Collections API (org.eclipse.collections:eclipse-collections-api:11.1.0 - https://github.com/eclipse/eclipse-collections/eclipse-collections-api)
|
||||
* Eclipse Collections Main Library (org.eclipse.collections:eclipse-collections:11.1.0 - https://github.com/eclipse/eclipse-collections/eclipse-collections)
|
||||
* Jakarta XML Binding API (jakarta.xml.bind:jakarta.xml.bind-api:2.3.3 - https://github.com/eclipse-ee4j/jaxb-api/jakarta.xml.bind-api)
|
||||
|
||||
Eclipse Public License - v 1.0:
|
||||
|
||||
* Eclipse Collections API (org.eclipse.collections:eclipse-collections-api:11.1.0 - https://github.com/eclipse/eclipse-collections/eclipse-collections-api)
|
||||
* Eclipse Collections Main Library (org.eclipse.collections:eclipse-collections:11.1.0 - https://github.com/eclipse/eclipse-collections/eclipse-collections)
|
||||
|
||||
The Apache Software License, Version 2.0:
|
||||
|
||||
* FindBugs-jsr305 (com.google.code.findbugs:jsr305:3.0.2 - http://findbugs.sourceforge.net/)
|
||||
* Guava InternalFutureFailureAccess and InternalFutures (com.google.guava:failureaccess:1.0.2 - https://github.com/google/guava/failureaccess)
|
||||
* Guava ListenableFuture only (com.google.guava:listenablefuture:9999.0-empty-to-avoid-conflict-with-guava - https://github.com/google/guava/listenablefuture)
|
||||
* Jackson datatype: JSR310 (com.fasterxml.jackson.datatype:jackson-datatype-jsr310:2.16.0 - https://github.com/FasterXML/jackson-modules-java8/jackson-datatype-jsr310)
|
||||
* Jackson module: Old JAXB Annotations (javax.xml.bind) (com.fasterxml.jackson.module:jackson-module-jaxb-annotations:2.17.1 - https://github.com/FasterXML/jackson-modules-base)
|
||||
* Jackson-annotations (com.fasterxml.jackson.core:jackson-annotations:2.16.0 - https://github.com/FasterXML/jackson)
|
||||
* Jackson-core (com.fasterxml.jackson.core:jackson-core:2.16.0 - https://github.com/FasterXML/jackson-core)
|
||||
* jackson-databind (com.fasterxml.jackson.core:jackson-databind:2.15.2 - https://github.com/FasterXML/jackson)
|
||||
* Jackson-JAXRS: base (com.fasterxml.jackson.jaxrs:jackson-jaxrs-base:2.17.1 - https://github.com/FasterXML/jackson-jaxrs-providers/jackson-jaxrs-base)
|
||||
* Jackson-JAXRS: JSON (com.fasterxml.jackson.jaxrs:jackson-jaxrs-json-provider:2.17.1 - https://github.com/FasterXML/jackson-jaxrs-providers/jackson-jaxrs-json-provider)
|
||||
* JAR JNI Loader (org.questdb:jar-jni:1.1.1 - https://github.com/questdb/rust-maven-plugin)
|
||||
* Lance Core (org.lance:lance-core:2.0.0 - https://lance.org/)
|
||||
|
||||
The MIT License:
|
||||
|
||||
* Checker Qual (org.checkerframework:checker-qual:3.43.0 - https://checkerframework.org/)
|
||||
@@ -8,7 +8,7 @@
|
||||
<parent>
|
||||
<groupId>com.lancedb</groupId>
|
||||
<artifactId>lancedb-parent</artifactId>
|
||||
<version>0.25.0-beta.0</version>
|
||||
<version>0.27.0-beta.3</version>
|
||||
<relativePath>../pom.xml</relativePath>
|
||||
</parent>
|
||||
|
||||
|
||||
+17
-3
@@ -6,7 +6,7 @@
|
||||
|
||||
<groupId>com.lancedb</groupId>
|
||||
<artifactId>lancedb-parent</artifactId>
|
||||
<version>0.25.0-beta.0</version>
|
||||
<version>0.27.0-beta.3</version>
|
||||
<packaging>pom</packaging>
|
||||
<name>${project.artifactId}</name>
|
||||
<description>LanceDB Java SDK Parent POM</description>
|
||||
@@ -28,7 +28,7 @@
|
||||
<properties>
|
||||
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
|
||||
<arrow.version>15.0.0</arrow.version>
|
||||
<lance-core.version>1.0.4</lance-core.version>
|
||||
<lance-core.version>4.0.0-beta.7</lance-core.version>
|
||||
<spotless.skip>false</spotless.skip>
|
||||
<spotless.version>2.30.0</spotless.version>
|
||||
<spotless.java.googlejavaformat.version>1.7</spotless.java.googlejavaformat.version>
|
||||
@@ -160,6 +160,19 @@
|
||||
<groupId>com.diffplug.spotless</groupId>
|
||||
<artifactId>spotless-maven-plugin</artifactId>
|
||||
</plugin>
|
||||
<plugin>
|
||||
<groupId>org.codehaus.mojo</groupId>
|
||||
<artifactId>license-maven-plugin</artifactId>
|
||||
<version>2.4.0</version>
|
||||
<configuration>
|
||||
<outputDirectory>${project.basedir}</outputDirectory>
|
||||
<thirdPartyFilename>JAVA_THIRD_PARTY_LICENSES.md</thirdPartyFilename>
|
||||
<fileTemplate>/org/codehaus/mojo/license/third-party-file-groupByLicense.ftl</fileTemplate>
|
||||
<includedScopes>compile,runtime</includedScopes>
|
||||
<excludedScopes>test,provided</excludedScopes>
|
||||
<sortArtifactByName>true</sortArtifactByName>
|
||||
</configuration>
|
||||
</plugin>
|
||||
</plugins>
|
||||
<pluginManagement>
|
||||
<plugins>
|
||||
@@ -292,11 +305,12 @@
|
||||
<plugin>
|
||||
<groupId>org.sonatype.central</groupId>
|
||||
<artifactId>central-publishing-maven-plugin</artifactId>
|
||||
<version>0.4.0</version>
|
||||
<version>0.8.0</version>
|
||||
<extensions>true</extensions>
|
||||
<configuration>
|
||||
<publishingServerId>ossrh</publishingServerId>
|
||||
<tokenAuth>true</tokenAuth>
|
||||
<autoPublish>true</autoPublish>
|
||||
</configuration>
|
||||
</plugin>
|
||||
<plugin>
|
||||
|
||||
+4
-4
@@ -1,7 +1,7 @@
|
||||
[package]
|
||||
name = "lancedb-nodejs"
|
||||
edition.workspace = true
|
||||
version = "0.25.0-beta.0"
|
||||
version = "0.27.0-beta.3"
|
||||
license.workspace = true
|
||||
description.workspace = true
|
||||
repository.workspace = true
|
||||
@@ -19,11 +19,11 @@ arrow-schema.workspace = true
|
||||
env_logger.workspace = true
|
||||
futures.workspace = true
|
||||
lancedb = { path = "../rust/lancedb", default-features = false }
|
||||
napi = { version = "2.16.8", default-features = false, features = [
|
||||
napi = { version = "3.8.3", default-features = false, features = [
|
||||
"napi9",
|
||||
"async"
|
||||
] }
|
||||
napi-derive = "2.16.4"
|
||||
napi-derive = "3.5.2"
|
||||
# Prevent dynamic linking of lzma, which comes from datafusion
|
||||
lzma-sys = { version = "*", features = ["static"] }
|
||||
log.workspace = true
|
||||
@@ -33,7 +33,7 @@ aws-lc-sys = "=0.28.0"
|
||||
aws-lc-rs = "=1.13.0"
|
||||
|
||||
[build-dependencies]
|
||||
napi-build = "2.1"
|
||||
napi-build = "2.3.1"
|
||||
|
||||
[features]
|
||||
default = ["remote", "lancedb/aws", "lancedb/gcs", "lancedb/azure", "lancedb/dynamodb", "lancedb/oss", "lancedb/huggingface"]
|
||||
|
||||
@@ -0,0 +1,668 @@
|
||||
[@75lb/deep-merge@1.1.2](https://github.com/75lb/deep-merge) - MIT
|
||||
[@aashutoshrathi/word-wrap@1.2.6](https://github.com/aashutoshrathi/word-wrap) - MIT
|
||||
[@ampproject/remapping@2.2.1](https://github.com/ampproject/remapping) - Apache-2.0
|
||||
[@aws-crypto/crc32@3.0.0](https://github.com/aws/aws-sdk-js-crypto-helpers) - Apache-2.0
|
||||
[@aws-crypto/crc32c@3.0.0](https://github.com/aws/aws-sdk-js-crypto-helpers) - Apache-2.0
|
||||
[@aws-crypto/ie11-detection@3.0.0](https://github.com/aws/aws-sdk-js-crypto-helpers) - Apache-2.0
|
||||
[@aws-crypto/sha1-browser@3.0.0](https://github.com/aws/aws-sdk-js-crypto-helpers) - Apache-2.0
|
||||
[@aws-crypto/sha256-browser@3.0.0](https://github.com/aws/aws-sdk-js-crypto-helpers) - Apache-2.0
|
||||
[@aws-crypto/sha256-browser@5.2.0](https://github.com/aws/aws-sdk-js-crypto-helpers) - Apache-2.0
|
||||
[@aws-crypto/sha256-js@3.0.0](https://github.com/aws/aws-sdk-js-crypto-helpers) - Apache-2.0
|
||||
[@aws-crypto/sha256-js@5.2.0](https://github.com/aws/aws-sdk-js-crypto-helpers) - Apache-2.0
|
||||
[@aws-crypto/supports-web-crypto@3.0.0](https://github.com/aws/aws-sdk-js-crypto-helpers) - Apache-2.0
|
||||
[@aws-crypto/supports-web-crypto@5.2.0](https://github.com/aws/aws-sdk-js-crypto-helpers) - Apache-2.0
|
||||
[@aws-crypto/util@3.0.0](https://github.com/aws/aws-sdk-js-crypto-helpers) - Apache-2.0
|
||||
[@aws-crypto/util@5.2.0](https://github.com/aws/aws-sdk-js-crypto-helpers) - Apache-2.0
|
||||
[@aws-sdk/client-dynamodb@3.602.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/client-kms@3.549.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/client-s3@3.550.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/client-sso-oidc@3.549.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/client-sso-oidc@3.600.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/client-sso@3.549.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/client-sso@3.598.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/client-sts@3.549.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/client-sts@3.600.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/core@3.549.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/core@3.598.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/credential-provider-env@3.535.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/credential-provider-env@3.598.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/credential-provider-http@3.535.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/credential-provider-http@3.598.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/credential-provider-ini@3.549.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/credential-provider-ini@3.598.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/credential-provider-node@3.549.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/credential-provider-node@3.600.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/credential-provider-process@3.535.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/credential-provider-process@3.598.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/credential-provider-sso@3.549.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/credential-provider-sso@3.598.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/credential-provider-web-identity@3.549.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/credential-provider-web-identity@3.598.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/endpoint-cache@3.572.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/middleware-bucket-endpoint@3.535.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/middleware-endpoint-discovery@3.598.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/middleware-expect-continue@3.535.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/middleware-flexible-checksums@3.535.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/middleware-host-header@3.535.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/middleware-host-header@3.598.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/middleware-location-constraint@3.535.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/middleware-logger@3.535.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/middleware-logger@3.598.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/middleware-recursion-detection@3.535.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/middleware-recursion-detection@3.598.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/middleware-sdk-s3@3.535.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/middleware-signing@3.535.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/middleware-ssec@3.537.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/middleware-user-agent@3.540.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/middleware-user-agent@3.598.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/region-config-resolver@3.535.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/region-config-resolver@3.598.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/signature-v4-multi-region@3.535.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/token-providers@3.549.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/token-providers@3.598.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/types@3.535.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/types@3.598.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/util-arn-parser@3.535.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/util-endpoints@3.540.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/util-endpoints@3.598.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/util-locate-window@3.535.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/util-user-agent-browser@3.535.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/util-user-agent-browser@3.598.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/util-user-agent-node@3.535.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/util-user-agent-node@3.598.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/util-utf8-browser@3.259.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@aws-sdk/xml-builder@3.535.0](https://github.com/aws/aws-sdk-js-v3) - Apache-2.0
|
||||
[@babel/code-frame@7.26.2](https://github.com/babel/babel) - MIT
|
||||
[@babel/compat-data@7.23.5](https://github.com/babel/babel) - MIT
|
||||
[@babel/core@7.23.7](https://github.com/babel/babel) - MIT
|
||||
[@babel/generator@7.23.6](https://github.com/babel/babel) - MIT
|
||||
[@babel/helper-compilation-targets@7.23.6](https://github.com/babel/babel) - MIT
|
||||
[@babel/helper-environment-visitor@7.22.20](https://github.com/babel/babel) - MIT
|
||||
[@babel/helper-function-name@7.23.0](https://github.com/babel/babel) - MIT
|
||||
[@babel/helper-hoist-variables@7.22.5](https://github.com/babel/babel) - MIT
|
||||
[@babel/helper-module-imports@7.22.15](https://github.com/babel/babel) - MIT
|
||||
[@babel/helper-module-transforms@7.23.3](https://github.com/babel/babel) - MIT
|
||||
[@babel/helper-plugin-utils@7.22.5](https://github.com/babel/babel) - MIT
|
||||
[@babel/helper-simple-access@7.22.5](https://github.com/babel/babel) - MIT
|
||||
[@babel/helper-split-export-declaration@7.22.6](https://github.com/babel/babel) - MIT
|
||||
[@babel/helper-string-parser@7.25.9](https://github.com/babel/babel) - MIT
|
||||
[@babel/helper-validator-identifier@7.25.9](https://github.com/babel/babel) - MIT
|
||||
[@babel/helper-validator-option@7.23.5](https://github.com/babel/babel) - MIT
|
||||
[@babel/helpers@7.27.0](https://github.com/babel/babel) - MIT
|
||||
[@babel/parser@7.27.0](https://github.com/babel/babel) - MIT
|
||||
[@babel/plugin-syntax-async-generators@7.8.4](https://github.com/babel/babel/tree/master/packages/babel-plugin-syntax-async-generators) - MIT
|
||||
[@babel/plugin-syntax-bigint@7.8.3](https://github.com/babel/babel/tree/master/packages/babel-plugin-syntax-bigint) - MIT
|
||||
[@babel/plugin-syntax-class-properties@7.12.13](https://github.com/babel/babel) - MIT
|
||||
[@babel/plugin-syntax-import-meta@7.10.4](https://github.com/babel/babel) - MIT
|
||||
[@babel/plugin-syntax-json-strings@7.8.3](https://github.com/babel/babel/tree/master/packages/babel-plugin-syntax-json-strings) - MIT
|
||||
[@babel/plugin-syntax-jsx@7.23.3](https://github.com/babel/babel) - MIT
|
||||
[@babel/plugin-syntax-logical-assignment-operators@7.10.4](https://github.com/babel/babel) - MIT
|
||||
[@babel/plugin-syntax-nullish-coalescing-operator@7.8.3](https://github.com/babel/babel/tree/master/packages/babel-plugin-syntax-nullish-coalescing-operator) - MIT
|
||||
[@babel/plugin-syntax-numeric-separator@7.10.4](https://github.com/babel/babel) - MIT
|
||||
[@babel/plugin-syntax-object-rest-spread@7.8.3](https://github.com/babel/babel/tree/master/packages/babel-plugin-syntax-object-rest-spread) - MIT
|
||||
[@babel/plugin-syntax-optional-catch-binding@7.8.3](https://github.com/babel/babel/tree/master/packages/babel-plugin-syntax-optional-catch-binding) - MIT
|
||||
[@babel/plugin-syntax-optional-chaining@7.8.3](https://github.com/babel/babel/tree/master/packages/babel-plugin-syntax-optional-chaining) - MIT
|
||||
[@babel/plugin-syntax-top-level-await@7.14.5](https://github.com/babel/babel) - MIT
|
||||
[@babel/plugin-syntax-typescript@7.23.3](https://github.com/babel/babel) - MIT
|
||||
[@babel/template@7.27.0](https://github.com/babel/babel) - MIT
|
||||
[@babel/traverse@7.23.7](https://github.com/babel/babel) - MIT
|
||||
[@babel/types@7.27.0](https://github.com/babel/babel) - MIT
|
||||
[@bcoe/v8-coverage@0.2.3](https://github.com/demurgos/v8-coverage) - MIT
|
||||
[@biomejs/biome@1.8.3](https://github.com/biomejs/biome) - MIT OR Apache-2.0
|
||||
[@biomejs/cli-darwin-arm64@1.8.3](https://github.com/biomejs/biome) - MIT OR Apache-2.0
|
||||
[@eslint-community/eslint-utils@4.4.0](https://github.com/eslint-community/eslint-utils) - MIT
|
||||
[@eslint-community/regexpp@4.10.0](https://github.com/eslint-community/regexpp) - MIT
|
||||
[@eslint/eslintrc@2.1.4](https://github.com/eslint/eslintrc) - MIT
|
||||
[@eslint/js@8.57.0](https://github.com/eslint/eslint) - MIT
|
||||
[@huggingface/jinja@0.3.2](https://github.com/huggingface/huggingface.js) - MIT
|
||||
[@huggingface/transformers@3.0.2](https://github.com/huggingface/transformers.js) - Apache-2.0
|
||||
[@humanwhocodes/config-array@0.11.14](https://github.com/humanwhocodes/config-array) - Apache-2.0
|
||||
[@humanwhocodes/module-importer@1.0.1](https://github.com/humanwhocodes/module-importer) - Apache-2.0
|
||||
[@humanwhocodes/object-schema@2.0.2](https://github.com/humanwhocodes/object-schema) - BSD-3-Clause
|
||||
[@img/sharp-darwin-arm64@0.33.5](https://github.com/lovell/sharp) - Apache-2.0
|
||||
[@img/sharp-libvips-darwin-arm64@1.0.4](https://github.com/lovell/sharp-libvips) - LGPL-3.0-or-later
|
||||
[@isaacs/cliui@8.0.2](https://github.com/yargs/cliui) - ISC
|
||||
[@isaacs/fs-minipass@4.0.1](https://github.com/npm/fs-minipass) - ISC
|
||||
[@istanbuljs/load-nyc-config@1.1.0](https://github.com/istanbuljs/load-nyc-config) - ISC
|
||||
[@istanbuljs/schema@0.1.3](https://github.com/istanbuljs/schema) - MIT
|
||||
[@jest/console@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[@jest/core@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[@jest/environment@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[@jest/expect-utils@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[@jest/expect@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[@jest/fake-timers@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[@jest/globals@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[@jest/reporters@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[@jest/schemas@29.6.3](https://github.com/jestjs/jest) - MIT
|
||||
[@jest/source-map@29.6.3](https://github.com/jestjs/jest) - MIT
|
||||
[@jest/test-result@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[@jest/test-sequencer@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[@jest/transform@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[@jest/types@29.6.3](https://github.com/jestjs/jest) - MIT
|
||||
[@jridgewell/gen-mapping@0.3.3](https://github.com/jridgewell/gen-mapping) - MIT
|
||||
[@jridgewell/resolve-uri@3.1.1](https://github.com/jridgewell/resolve-uri) - MIT
|
||||
[@jridgewell/set-array@1.1.2](https://github.com/jridgewell/set-array) - MIT
|
||||
[@jridgewell/sourcemap-codec@1.4.15](https://github.com/jridgewell/sourcemap-codec) - MIT
|
||||
[@jridgewell/trace-mapping@0.3.22](https://github.com/jridgewell/trace-mapping) - MIT
|
||||
[@lancedb/lancedb@0.26.2](https://github.com/lancedb/lancedb) - Apache-2.0
|
||||
[@napi-rs/cli@2.18.3](https://github.com/napi-rs/napi-rs) - MIT
|
||||
[@nodelib/fs.scandir@2.1.5](https://github.com/nodelib/nodelib/tree/master/packages/fs/fs.scandir) - MIT
|
||||
[@nodelib/fs.stat@2.0.5](https://github.com/nodelib/nodelib/tree/master/packages/fs/fs.stat) - MIT
|
||||
[@nodelib/fs.walk@1.2.8](https://github.com/nodelib/nodelib/tree/master/packages/fs/fs.walk) - MIT
|
||||
[@pkgjs/parseargs@0.11.0](https://github.com/pkgjs/parseargs) - MIT
|
||||
[@protobufjs/aspromise@1.1.2](https://github.com/dcodeIO/protobuf.js) - BSD-3-Clause
|
||||
[@protobufjs/base64@1.1.2](https://github.com/dcodeIO/protobuf.js) - BSD-3-Clause
|
||||
[@protobufjs/codegen@2.0.4](https://github.com/dcodeIO/protobuf.js) - BSD-3-Clause
|
||||
[@protobufjs/eventemitter@1.1.0](https://github.com/dcodeIO/protobuf.js) - BSD-3-Clause
|
||||
[@protobufjs/fetch@1.1.0](https://github.com/dcodeIO/protobuf.js) - BSD-3-Clause
|
||||
[@protobufjs/float@1.0.2](https://github.com/dcodeIO/protobuf.js) - BSD-3-Clause
|
||||
[@protobufjs/inquire@1.1.0](https://github.com/dcodeIO/protobuf.js) - BSD-3-Clause
|
||||
[@protobufjs/path@1.1.2](https://github.com/dcodeIO/protobuf.js) - BSD-3-Clause
|
||||
[@protobufjs/pool@1.1.0](https://github.com/dcodeIO/protobuf.js) - BSD-3-Clause
|
||||
[@protobufjs/utf8@1.1.0](https://github.com/dcodeIO/protobuf.js) - BSD-3-Clause
|
||||
[@shikijs/core@1.10.3](https://github.com/shikijs/shiki) - MIT
|
||||
[@sinclair/typebox@0.27.8](https://github.com/sinclairzx81/typebox) - MIT
|
||||
[@sinonjs/commons@3.0.1](https://github.com/sinonjs/commons) - BSD-3-Clause
|
||||
[@sinonjs/fake-timers@10.3.0](https://github.com/sinonjs/fake-timers) - BSD-3-Clause
|
||||
[@smithy/abort-controller@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/abort-controller@3.1.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/chunked-blob-reader-native@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/chunked-blob-reader@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/config-resolver@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/config-resolver@3.0.3](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/core@1.4.2](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/core@2.2.3](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/credential-provider-imds@2.3.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/credential-provider-imds@3.1.2](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/eventstream-codec@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/eventstream-serde-browser@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/eventstream-serde-config-resolver@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/eventstream-serde-node@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/eventstream-serde-universal@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/fetch-http-handler@2.5.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/fetch-http-handler@3.1.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/hash-blob-browser@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/hash-node@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/hash-node@3.0.2](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/hash-stream-node@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/invalid-dependency@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/invalid-dependency@3.0.2](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/is-array-buffer@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/is-array-buffer@3.0.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/md5-js@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/middleware-content-length@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/middleware-content-length@3.0.2](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/middleware-endpoint@2.5.1](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/middleware-endpoint@3.0.3](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/middleware-retry@2.3.1](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/middleware-retry@3.0.6](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/middleware-serde@2.3.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/middleware-serde@3.0.2](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/middleware-stack@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/middleware-stack@3.0.2](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/node-config-provider@2.3.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/node-config-provider@3.1.2](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/node-http-handler@2.5.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/node-http-handler@3.1.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/property-provider@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/property-provider@3.1.2](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/protocol-http@3.3.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/protocol-http@4.0.2](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/querystring-builder@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/querystring-builder@3.0.2](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/querystring-parser@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/querystring-parser@3.0.2](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/service-error-classification@2.1.5](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/service-error-classification@3.0.2](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/shared-ini-file-loader@2.4.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/shared-ini-file-loader@3.1.2](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/signature-v4@2.2.1](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/signature-v4@3.1.1](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/smithy-client@2.5.1](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/smithy-client@3.1.4](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/types@2.12.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/types@3.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/url-parser@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/url-parser@3.0.2](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-base64@2.3.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-base64@3.0.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-body-length-browser@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-body-length-browser@3.0.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-body-length-node@2.3.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-body-length-node@3.0.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-buffer-from@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-buffer-from@3.0.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-config-provider@2.3.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-config-provider@3.0.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-defaults-mode-browser@2.2.1](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-defaults-mode-browser@3.0.6](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-defaults-mode-node@2.3.1](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-defaults-mode-node@3.0.6](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-endpoints@1.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-endpoints@2.0.3](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-hex-encoding@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-hex-encoding@3.0.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-middleware@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-middleware@3.0.2](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-retry@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-retry@3.0.2](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-stream@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-stream@3.0.4](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-uri-escape@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-uri-escape@3.0.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-utf8@2.3.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-utf8@3.0.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-waiter@2.2.0](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@smithy/util-waiter@3.1.1](https://github.com/awslabs/smithy-typescript) - Apache-2.0
|
||||
[@swc/helpers@0.5.12](https://github.com/swc-project/swc) - Apache-2.0
|
||||
[@types/axios@0.14.0](https://github.com/mzabriskie/axios) - MIT
|
||||
[@types/babel__core@7.20.5](https://github.com/DefinitelyTyped/DefinitelyTyped) - MIT
|
||||
[@types/babel__generator@7.6.8](https://github.com/DefinitelyTyped/DefinitelyTyped) - MIT
|
||||
[@types/babel__template@7.4.4](https://github.com/DefinitelyTyped/DefinitelyTyped) - MIT
|
||||
[@types/babel__traverse@7.20.5](https://github.com/DefinitelyTyped/DefinitelyTyped) - MIT
|
||||
[@types/command-line-args@5.2.3](https://github.com/DefinitelyTyped/DefinitelyTyped) - MIT
|
||||
[@types/command-line-usage@5.0.2](https://github.com/DefinitelyTyped/DefinitelyTyped) - MIT
|
||||
[@types/command-line-usage@5.0.4](https://github.com/DefinitelyTyped/DefinitelyTyped) - MIT
|
||||
[@types/graceful-fs@4.1.9](https://github.com/DefinitelyTyped/DefinitelyTyped) - MIT
|
||||
[@types/hast@3.0.4](https://github.com/DefinitelyTyped/DefinitelyTyped) - MIT
|
||||
[@types/istanbul-lib-coverage@2.0.6](https://github.com/DefinitelyTyped/DefinitelyTyped) - MIT
|
||||
[@types/istanbul-lib-report@3.0.3](https://github.com/DefinitelyTyped/DefinitelyTyped) - MIT
|
||||
[@types/istanbul-reports@3.0.4](https://github.com/DefinitelyTyped/DefinitelyTyped) - MIT
|
||||
[@types/jest@29.5.12](https://github.com/DefinitelyTyped/DefinitelyTyped) - MIT
|
||||
[@types/json-schema@7.0.15](https://github.com/DefinitelyTyped/DefinitelyTyped) - MIT
|
||||
[@types/node-fetch@2.6.11](https://github.com/DefinitelyTyped/DefinitelyTyped) - MIT
|
||||
[@types/node@18.19.26](https://github.com/DefinitelyTyped/DefinitelyTyped) - MIT
|
||||
[@types/node@20.16.10](https://github.com/DefinitelyTyped/DefinitelyTyped) - MIT
|
||||
[@types/node@20.17.9](https://github.com/DefinitelyTyped/DefinitelyTyped) - MIT
|
||||
[@types/node@22.7.4](https://github.com/DefinitelyTyped/DefinitelyTyped) - MIT
|
||||
[@types/semver@7.5.6](https://github.com/DefinitelyTyped/DefinitelyTyped) - MIT
|
||||
[@types/stack-utils@2.0.3](https://github.com/DefinitelyTyped/DefinitelyTyped) - MIT
|
||||
[@types/tmp@0.2.6](https://github.com/DefinitelyTyped/DefinitelyTyped) - MIT
|
||||
[@types/unist@3.0.2](https://github.com/DefinitelyTyped/DefinitelyTyped) - MIT
|
||||
[@types/yargs-parser@21.0.3](https://github.com/DefinitelyTyped/DefinitelyTyped) - MIT
|
||||
[@types/yargs@17.0.32](https://github.com/DefinitelyTyped/DefinitelyTyped) - MIT
|
||||
[@typescript-eslint/eslint-plugin@7.1.0](https://github.com/typescript-eslint/typescript-eslint) - MIT
|
||||
[@typescript-eslint/parser@7.1.0](https://github.com/typescript-eslint/typescript-eslint) - BSD-2-Clause
|
||||
[@typescript-eslint/scope-manager@7.1.0](https://github.com/typescript-eslint/typescript-eslint) - MIT
|
||||
[@typescript-eslint/type-utils@7.1.0](https://github.com/typescript-eslint/typescript-eslint) - MIT
|
||||
[@typescript-eslint/types@7.1.0](https://github.com/typescript-eslint/typescript-eslint) - MIT
|
||||
[@typescript-eslint/typescript-estree@7.1.0](https://github.com/typescript-eslint/typescript-eslint) - BSD-2-Clause
|
||||
[@typescript-eslint/utils@7.1.0](https://github.com/typescript-eslint/typescript-eslint) - MIT
|
||||
[@typescript-eslint/visitor-keys@7.1.0](https://github.com/typescript-eslint/typescript-eslint) - MIT
|
||||
[@ungap/structured-clone@1.2.0](https://github.com/ungap/structured-clone) - ISC
|
||||
[abort-controller@3.0.0](https://github.com/mysticatea/abort-controller) - MIT
|
||||
[acorn-jsx@5.3.2](https://github.com/acornjs/acorn-jsx) - MIT
|
||||
[acorn@8.11.3](https://github.com/acornjs/acorn) - MIT
|
||||
[agentkeepalive@4.5.0](https://github.com/node-modules/agentkeepalive) - MIT
|
||||
[ajv@6.12.6](https://github.com/ajv-validator/ajv) - MIT
|
||||
[ansi-escapes@4.3.2](https://github.com/sindresorhus/ansi-escapes) - MIT
|
||||
[ansi-regex@5.0.1](https://github.com/chalk/ansi-regex) - MIT
|
||||
[ansi-regex@6.1.0](https://github.com/chalk/ansi-regex) - MIT
|
||||
[ansi-styles@4.3.0](https://github.com/chalk/ansi-styles) - MIT
|
||||
[ansi-styles@5.2.0](https://github.com/chalk/ansi-styles) - MIT
|
||||
[ansi-styles@6.2.1](https://github.com/chalk/ansi-styles) - MIT
|
||||
[anymatch@3.1.3](https://github.com/micromatch/anymatch) - ISC
|
||||
[apache-arrow@15.0.0](https://github.com/apache/arrow) - Apache-2.0
|
||||
[apache-arrow@16.0.0](https://github.com/apache/arrow) - Apache-2.0
|
||||
[apache-arrow@17.0.0](https://github.com/apache/arrow) - Apache-2.0
|
||||
[apache-arrow@18.0.0](https://github.com/apache/arrow) - Apache-2.0
|
||||
[argparse@1.0.10](https://github.com/nodeca/argparse) - MIT
|
||||
[argparse@2.0.1](https://github.com/nodeca/argparse) - Python-2.0
|
||||
[array-back@3.1.0](https://github.com/75lb/array-back) - MIT
|
||||
[array-back@6.2.2](https://github.com/75lb/array-back) - MIT
|
||||
[array-union@2.1.0](https://github.com/sindresorhus/array-union) - MIT
|
||||
[asynckit@0.4.0](https://github.com/alexindigo/asynckit) - MIT
|
||||
[axios@1.8.4](https://github.com/axios/axios) - MIT
|
||||
[babel-jest@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[babel-plugin-istanbul@6.1.1](https://github.com/istanbuljs/babel-plugin-istanbul) - BSD-3-Clause
|
||||
[babel-plugin-jest-hoist@29.6.3](https://github.com/jestjs/jest) - MIT
|
||||
[babel-preset-current-node-syntax@1.0.1](https://github.com/nicolo-ribaudo/babel-preset-current-node-syntax) - MIT
|
||||
[babel-preset-jest@29.6.3](https://github.com/jestjs/jest) - MIT
|
||||
[balanced-match@1.0.2](https://github.com/juliangruber/balanced-match) - MIT
|
||||
[base-64@0.1.0](https://github.com/mathiasbynens/base64) - MIT
|
||||
[bowser@2.11.0](https://github.com/lancedikson/bowser) - MIT
|
||||
[brace-expansion@1.1.11](https://github.com/juliangruber/brace-expansion) - MIT
|
||||
[brace-expansion@2.0.1](https://github.com/juliangruber/brace-expansion) - MIT
|
||||
[braces@3.0.3](https://github.com/micromatch/braces) - MIT
|
||||
[browserslist@4.22.2](https://github.com/browserslist/browserslist) - MIT
|
||||
[bs-logger@0.2.6](https://github.com/huafu/bs-logger) - MIT
|
||||
[bser@2.1.1](https://github.com/facebook/watchman) - Apache-2.0
|
||||
[buffer-from@1.1.2](https://github.com/LinusU/buffer-from) - MIT
|
||||
[callsites@3.1.0](https://github.com/sindresorhus/callsites) - MIT
|
||||
[camelcase@5.3.1](https://github.com/sindresorhus/camelcase) - MIT
|
||||
[camelcase@6.3.0](https://github.com/sindresorhus/camelcase) - MIT
|
||||
[caniuse-lite@1.0.30001579](https://github.com/browserslist/caniuse-lite) - CC-BY-4.0
|
||||
[chalk-template@0.4.0](https://github.com/chalk/chalk-template) - MIT
|
||||
[chalk@4.1.2](https://github.com/chalk/chalk) - MIT
|
||||
[char-regex@1.0.2](https://github.com/Richienb/char-regex) - MIT
|
||||
[charenc@0.0.2](https://github.com/pvorb/node-charenc) - BSD-3-Clause
|
||||
[chownr@3.0.0](https://github.com/isaacs/chownr) - BlueOak-1.0.0
|
||||
[ci-info@3.9.0](https://github.com/watson/ci-info) - MIT
|
||||
[cjs-module-lexer@1.2.3](https://github.com/nodejs/cjs-module-lexer) - MIT
|
||||
[cliui@8.0.1](https://github.com/yargs/cliui) - ISC
|
||||
[co@4.6.0](https://github.com/tj/co) - MIT
|
||||
[collect-v8-coverage@1.0.2](https://github.com/SimenB/collect-v8-coverage) - MIT
|
||||
[color-convert@2.0.1](https://github.com/Qix-/color-convert) - MIT
|
||||
[color-name@1.1.4](https://github.com/colorjs/color-name) - MIT
|
||||
[color-string@1.9.1](https://github.com/Qix-/color-string) - MIT
|
||||
[color@4.2.3](https://github.com/Qix-/color) - MIT
|
||||
[combined-stream@1.0.8](https://github.com/felixge/node-combined-stream) - MIT
|
||||
[command-line-args@5.2.1](https://github.com/75lb/command-line-args) - MIT
|
||||
[command-line-usage@7.0.1](https://github.com/75lb/command-line-usage) - MIT
|
||||
[concat-map@0.0.1](https://github.com/substack/node-concat-map) - MIT
|
||||
[convert-source-map@2.0.0](https://github.com/thlorenz/convert-source-map) - MIT
|
||||
[create-jest@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[cross-spawn@7.0.6](https://github.com/moxystudio/node-cross-spawn) - MIT
|
||||
[crypt@0.0.2](https://github.com/pvorb/node-crypt) - BSD-3-Clause
|
||||
[debug@4.3.4](https://github.com/debug-js/debug) - MIT
|
||||
[dedent@1.5.1](https://github.com/dmnd/dedent) - MIT
|
||||
[deep-is@0.1.4](https://github.com/thlorenz/deep-is) - MIT
|
||||
[deepmerge@4.3.1](https://github.com/TehShrike/deepmerge) - MIT
|
||||
[delayed-stream@1.0.0](https://github.com/felixge/node-delayed-stream) - MIT
|
||||
[detect-libc@2.0.3](https://github.com/lovell/detect-libc) - Apache-2.0
|
||||
[detect-newline@3.1.0](https://github.com/sindresorhus/detect-newline) - MIT
|
||||
[diff-sequences@29.6.3](https://github.com/jestjs/jest) - MIT
|
||||
[digest-fetch@1.3.0](https://github.com/devfans/digest-fetch) - ISC
|
||||
[dir-glob@3.0.1](https://github.com/kevva/dir-glob) - MIT
|
||||
[doctrine@3.0.0](https://github.com/eslint/doctrine) - Apache-2.0
|
||||
[eastasianwidth@0.2.0](https://github.com/komagata/eastasianwidth) - MIT
|
||||
[electron-to-chromium@1.4.642](https://github.com/kilian/electron-to-chromium) - ISC
|
||||
[emittery@0.13.1](https://github.com/sindresorhus/emittery) - MIT
|
||||
[emoji-regex@8.0.0](https://github.com/mathiasbynens/emoji-regex) - MIT
|
||||
[emoji-regex@9.2.2](https://github.com/mathiasbynens/emoji-regex) - MIT
|
||||
[entities@4.5.0](https://github.com/fb55/entities) - BSD-2-Clause
|
||||
[error-ex@1.3.2](https://github.com/qix-/node-error-ex) - MIT
|
||||
[escalade@3.1.1](https://github.com/lukeed/escalade) - MIT
|
||||
[escape-string-regexp@2.0.0](https://github.com/sindresorhus/escape-string-regexp) - MIT
|
||||
[escape-string-regexp@4.0.0](https://github.com/sindresorhus/escape-string-regexp) - MIT
|
||||
[eslint-scope@7.2.2](https://github.com/eslint/eslint-scope) - BSD-2-Clause
|
||||
[eslint-visitor-keys@3.4.3](https://github.com/eslint/eslint-visitor-keys) - Apache-2.0
|
||||
[eslint@8.57.0](https://github.com/eslint/eslint) - MIT
|
||||
[espree@9.6.1](https://github.com/eslint/espree) - BSD-2-Clause
|
||||
[esprima@4.0.1](https://github.com/jquery/esprima) - BSD-2-Clause
|
||||
[esquery@1.5.0](https://github.com/estools/esquery) - BSD-3-Clause
|
||||
[esrecurse@4.3.0](https://github.com/estools/esrecurse) - BSD-2-Clause
|
||||
[estraverse@5.3.0](https://github.com/estools/estraverse) - BSD-2-Clause
|
||||
[esutils@2.0.3](https://github.com/estools/esutils) - BSD-2-Clause
|
||||
[event-target-shim@5.0.1](https://github.com/mysticatea/event-target-shim) - MIT
|
||||
[execa@5.1.1](https://github.com/sindresorhus/execa) - MIT
|
||||
[exit@0.1.2](https://github.com/cowboy/node-exit) - MIT
|
||||
[expect@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[fast-deep-equal@3.1.3](https://github.com/epoberezkin/fast-deep-equal) - MIT
|
||||
[fast-glob@3.3.2](https://github.com/mrmlnc/fast-glob) - MIT
|
||||
[fast-json-stable-stringify@2.1.0](https://github.com/epoberezkin/fast-json-stable-stringify) - MIT
|
||||
[fast-levenshtein@2.0.6](https://github.com/hiddentao/fast-levenshtein) - MIT
|
||||
[fast-xml-parser@4.2.5](https://github.com/NaturalIntelligence/fast-xml-parser) - MIT
|
||||
[fastq@1.16.0](https://github.com/mcollina/fastq) - ISC
|
||||
[fb-watchman@2.0.2](https://github.com/facebook/watchman) - Apache-2.0
|
||||
[file-entry-cache@6.0.1](https://github.com/royriojas/file-entry-cache) - MIT
|
||||
[fill-range@7.1.1](https://github.com/jonschlinkert/fill-range) - MIT
|
||||
[find-replace@3.0.0](https://github.com/75lb/find-replace) - MIT
|
||||
[find-up@4.1.0](https://github.com/sindresorhus/find-up) - MIT
|
||||
[find-up@5.0.0](https://github.com/sindresorhus/find-up) - MIT
|
||||
[flat-cache@3.2.0](https://github.com/jaredwray/flat-cache) - MIT
|
||||
[flatbuffers@1.12.0](https://github.com/google/flatbuffers) - Apache*
|
||||
[flatbuffers@23.5.26](https://github.com/google/flatbuffers) - Apache*
|
||||
[flatbuffers@24.3.25](https://github.com/google/flatbuffers) - Apache-2.0
|
||||
[flatted@3.2.9](https://github.com/WebReflection/flatted) - ISC
|
||||
[follow-redirects@1.15.6](https://github.com/follow-redirects/follow-redirects) - MIT
|
||||
[foreground-child@3.3.0](https://github.com/tapjs/foreground-child) - ISC
|
||||
[form-data-encoder@1.7.2](https://github.com/octet-stream/form-data-encoder) - MIT
|
||||
[form-data@4.0.0](https://github.com/form-data/form-data) - MIT
|
||||
[formdata-node@4.4.1](https://github.com/octet-stream/form-data) - MIT
|
||||
[fs.realpath@1.0.0](https://github.com/isaacs/fs.realpath) - ISC
|
||||
[fsevents@2.3.3](https://github.com/fsevents/fsevents) - MIT
|
||||
[function-bind@1.1.2](https://github.com/Raynos/function-bind) - MIT
|
||||
[gensync@1.0.0-beta.2](https://github.com/loganfsmyth/gensync) - MIT
|
||||
[get-caller-file@2.0.5](https://github.com/stefanpenner/get-caller-file) - ISC
|
||||
[get-package-type@0.1.0](https://github.com/cfware/get-package-type) - MIT
|
||||
[get-stream@6.0.1](https://github.com/sindresorhus/get-stream) - MIT
|
||||
[glob-parent@5.1.2](https://github.com/gulpjs/glob-parent) - ISC
|
||||
[glob-parent@6.0.2](https://github.com/gulpjs/glob-parent) - ISC
|
||||
[glob@10.4.5](https://github.com/isaacs/node-glob) - ISC
|
||||
[glob@7.2.3](https://github.com/isaacs/node-glob) - ISC
|
||||
[globals@11.12.0](https://github.com/sindresorhus/globals) - MIT
|
||||
[globals@13.24.0](https://github.com/sindresorhus/globals) - MIT
|
||||
[globby@11.1.0](https://github.com/sindresorhus/globby) - MIT
|
||||
[graceful-fs@4.2.11](https://github.com/isaacs/node-graceful-fs) - ISC
|
||||
[graphemer@1.4.0](https://github.com/flmnt/graphemer) - MIT
|
||||
[guid-typescript@1.0.9](https://github.com/NicolasDeveloper/guid-typescript) - ISC
|
||||
[has-flag@4.0.0](https://github.com/sindresorhus/has-flag) - MIT
|
||||
[hasown@2.0.0](https://github.com/inspect-js/hasOwn) - MIT
|
||||
[html-escaper@2.0.2](https://github.com/WebReflection/html-escaper) - MIT
|
||||
[human-signals@2.1.0](https://github.com/ehmicky/human-signals) - Apache-2.0
|
||||
[humanize-ms@1.2.1](https://github.com/node-modules/humanize-ms) - MIT
|
||||
[ignore@5.3.0](https://github.com/kaelzhang/node-ignore) - MIT
|
||||
[import-fresh@3.3.0](https://github.com/sindresorhus/import-fresh) - MIT
|
||||
[import-local@3.1.0](https://github.com/sindresorhus/import-local) - MIT
|
||||
[imurmurhash@0.1.4](https://github.com/jensyt/imurmurhash-js) - MIT
|
||||
[inflight@1.0.6](https://github.com/npm/inflight) - ISC
|
||||
[inherits@2.0.4](https://github.com/isaacs/inherits) - ISC
|
||||
[interpret@1.4.0](https://github.com/gulpjs/interpret) - MIT
|
||||
[is-arrayish@0.2.1](https://github.com/qix-/node-is-arrayish) - MIT
|
||||
[is-arrayish@0.3.2](https://github.com/qix-/node-is-arrayish) - MIT
|
||||
[is-buffer@1.1.6](https://github.com/feross/is-buffer) - MIT
|
||||
[is-core-module@2.13.1](https://github.com/inspect-js/is-core-module) - MIT
|
||||
[is-extglob@2.1.1](https://github.com/jonschlinkert/is-extglob) - MIT
|
||||
[is-fullwidth-code-point@3.0.0](https://github.com/sindresorhus/is-fullwidth-code-point) - MIT
|
||||
[is-generator-fn@2.1.0](https://github.com/sindresorhus/is-generator-fn) - MIT
|
||||
[is-glob@4.0.3](https://github.com/micromatch/is-glob) - MIT
|
||||
[is-number@7.0.0](https://github.com/jonschlinkert/is-number) - MIT
|
||||
[is-path-inside@3.0.3](https://github.com/sindresorhus/is-path-inside) - MIT
|
||||
[is-stream@2.0.1](https://github.com/sindresorhus/is-stream) - MIT
|
||||
[isexe@2.0.0](https://github.com/isaacs/isexe) - ISC
|
||||
[istanbul-lib-coverage@3.2.2](https://github.com/istanbuljs/istanbuljs) - BSD-3-Clause
|
||||
[istanbul-lib-instrument@5.2.1](https://github.com/istanbuljs/istanbuljs) - BSD-3-Clause
|
||||
[istanbul-lib-instrument@6.0.1](https://github.com/istanbuljs/istanbuljs) - BSD-3-Clause
|
||||
[istanbul-lib-report@3.0.1](https://github.com/istanbuljs/istanbuljs) - BSD-3-Clause
|
||||
[istanbul-lib-source-maps@4.0.1](https://github.com/istanbuljs/istanbuljs) - BSD-3-Clause
|
||||
[istanbul-reports@3.1.6](https://github.com/istanbuljs/istanbuljs) - BSD-3-Clause
|
||||
[jackspeak@3.4.3](https://github.com/isaacs/jackspeak) - BlueOak-1.0.0
|
||||
[jest-changed-files@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[jest-circus@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[jest-cli@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[jest-config@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[jest-diff@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[jest-docblock@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[jest-each@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[jest-environment-node@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[jest-get-type@29.6.3](https://github.com/jestjs/jest) - MIT
|
||||
[jest-haste-map@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[jest-leak-detector@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[jest-matcher-utils@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[jest-message-util@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[jest-mock@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[jest-pnp-resolver@1.2.3](https://github.com/arcanis/jest-pnp-resolver) - MIT
|
||||
[jest-regex-util@29.6.3](https://github.com/jestjs/jest) - MIT
|
||||
[jest-resolve-dependencies@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[jest-resolve@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[jest-runner@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[jest-runtime@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[jest-snapshot@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[jest-util@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[jest-validate@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[jest-watcher@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[jest-worker@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[jest@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[js-tokens@4.0.0](https://github.com/lydell/js-tokens) - MIT
|
||||
[js-yaml@3.14.1](https://github.com/nodeca/js-yaml) - MIT
|
||||
[js-yaml@4.1.0](https://github.com/nodeca/js-yaml) - MIT
|
||||
[jsesc@2.5.2](https://github.com/mathiasbynens/jsesc) - MIT
|
||||
[json-bignum@0.0.3](https://github.com/datalanche/json-bignum) - MIT
|
||||
[json-buffer@3.0.1](https://github.com/dominictarr/json-buffer) - MIT
|
||||
[json-parse-even-better-errors@2.3.1](https://github.com/npm/json-parse-even-better-errors) - MIT
|
||||
[json-schema-traverse@0.4.1](https://github.com/epoberezkin/json-schema-traverse) - MIT
|
||||
[json-stable-stringify-without-jsonify@1.0.1](https://github.com/samn/json-stable-stringify) - MIT
|
||||
[json5@2.2.3](https://github.com/json5/json5) - MIT
|
||||
[keyv@4.5.4](https://github.com/jaredwray/keyv) - MIT
|
||||
[kleur@3.0.3](https://github.com/lukeed/kleur) - MIT
|
||||
[leven@3.1.0](https://github.com/sindresorhus/leven) - MIT
|
||||
[levn@0.4.1](https://github.com/gkz/levn) - MIT
|
||||
[lines-and-columns@1.2.4](https://github.com/eventualbuddha/lines-and-columns) - MIT
|
||||
[linkify-it@5.0.0](https://github.com/markdown-it/linkify-it) - MIT
|
||||
[locate-path@5.0.0](https://github.com/sindresorhus/locate-path) - MIT
|
||||
[locate-path@6.0.0](https://github.com/sindresorhus/locate-path) - MIT
|
||||
[lodash.camelcase@4.3.0](https://github.com/lodash/lodash) - MIT
|
||||
[lodash.memoize@4.1.2](https://github.com/lodash/lodash) - MIT
|
||||
[lodash.merge@4.6.2](https://github.com/lodash/lodash) - MIT
|
||||
[lodash@4.17.21](https://github.com/lodash/lodash) - MIT
|
||||
[long@5.2.3](https://github.com/dcodeIO/long.js) - Apache-2.0
|
||||
[lru-cache@10.4.3](https://github.com/isaacs/node-lru-cache) - ISC
|
||||
[lru-cache@5.1.1](https://github.com/isaacs/node-lru-cache) - ISC
|
||||
[lunr@2.3.9](https://github.com/olivernn/lunr.js) - MIT
|
||||
[make-dir@4.0.0](https://github.com/sindresorhus/make-dir) - MIT
|
||||
[make-error@1.3.6](https://github.com/JsCommunity/make-error) - ISC
|
||||
[makeerror@1.0.12](https://github.com/daaku/nodejs-makeerror) - BSD-3-Clause
|
||||
[markdown-it@14.1.0](https://github.com/markdown-it/markdown-it) - MIT
|
||||
[md5@2.3.0](https://github.com/pvorb/node-md5) - BSD-3-Clause
|
||||
[mdurl@2.0.0](https://github.com/markdown-it/mdurl) - MIT
|
||||
[merge-stream@2.0.0](https://github.com/grncdr/merge-stream) - MIT
|
||||
[merge2@1.4.1](https://github.com/teambition/merge2) - MIT
|
||||
[micromatch@4.0.8](https://github.com/micromatch/micromatch) - MIT
|
||||
[mime-db@1.52.0](https://github.com/jshttp/mime-db) - MIT
|
||||
[mime-types@2.1.35](https://github.com/jshttp/mime-types) - MIT
|
||||
[mimic-fn@2.1.0](https://github.com/sindresorhus/mimic-fn) - MIT
|
||||
[minimatch@3.1.2](https://github.com/isaacs/minimatch) - ISC
|
||||
[minimatch@9.0.3](https://github.com/isaacs/minimatch) - ISC
|
||||
[minimatch@9.0.5](https://github.com/isaacs/minimatch) - ISC
|
||||
[minimist@1.2.8](https://github.com/minimistjs/minimist) - MIT
|
||||
[minipass@7.1.2](https://github.com/isaacs/minipass) - ISC
|
||||
[minizlib@3.0.1](https://github.com/isaacs/minizlib) - MIT
|
||||
[mkdirp@3.0.1](https://github.com/isaacs/node-mkdirp) - MIT
|
||||
[mnemonist@0.38.3](https://github.com/yomguithereal/mnemonist) - MIT
|
||||
[ms@2.1.2](https://github.com/zeit/ms) - MIT
|
||||
[ms@2.1.3](https://github.com/vercel/ms) - MIT
|
||||
[natural-compare@1.4.0](https://github.com/litejs/natural-compare-lite) - MIT
|
||||
[node-domexception@1.0.0](https://github.com/jimmywarting/node-domexception) - MIT
|
||||
[node-fetch@2.7.0](https://github.com/bitinn/node-fetch) - MIT
|
||||
[node-int64@0.4.0](https://github.com/broofa/node-int64) - MIT
|
||||
[node-releases@2.0.14](https://github.com/chicoxyzzy/node-releases) - MIT
|
||||
[normalize-path@3.0.0](https://github.com/jonschlinkert/normalize-path) - MIT
|
||||
[npm-run-path@4.0.1](https://github.com/sindresorhus/npm-run-path) - MIT
|
||||
[obliterator@1.6.1](https://github.com/yomguithereal/obliterator) - MIT
|
||||
[once@1.4.0](https://github.com/isaacs/once) - ISC
|
||||
[onetime@5.1.2](https://github.com/sindresorhus/onetime) - MIT
|
||||
[onnxruntime-common@1.19.2](https://github.com/Microsoft/onnxruntime) - MIT
|
||||
[onnxruntime-common@1.20.0-dev.20241016-2b8fc5529b](https://github.com/Microsoft/onnxruntime) - MIT
|
||||
[onnxruntime-node@1.19.2](https://github.com/Microsoft/onnxruntime) - MIT
|
||||
[onnxruntime-web@1.21.0-dev.20241024-d9ca84ef96](https://github.com/Microsoft/onnxruntime) - MIT
|
||||
[openai@4.29.2](https://github.com/openai/openai-node) - Apache-2.0
|
||||
[optionator@0.9.3](https://github.com/gkz/optionator) - MIT
|
||||
[p-limit@2.3.0](https://github.com/sindresorhus/p-limit) - MIT
|
||||
[p-limit@3.1.0](https://github.com/sindresorhus/p-limit) - MIT
|
||||
[p-locate@4.1.0](https://github.com/sindresorhus/p-locate) - MIT
|
||||
[p-locate@5.0.0](https://github.com/sindresorhus/p-locate) - MIT
|
||||
[p-try@2.2.0](https://github.com/sindresorhus/p-try) - MIT
|
||||
[package-json-from-dist@1.0.1](https://github.com/isaacs/package-json-from-dist) - BlueOak-1.0.0
|
||||
[parent-module@1.0.1](https://github.com/sindresorhus/parent-module) - MIT
|
||||
[parse-json@5.2.0](https://github.com/sindresorhus/parse-json) - MIT
|
||||
[path-exists@4.0.0](https://github.com/sindresorhus/path-exists) - MIT
|
||||
[path-is-absolute@1.0.1](https://github.com/sindresorhus/path-is-absolute) - MIT
|
||||
[path-key@3.1.1](https://github.com/sindresorhus/path-key) - MIT
|
||||
[path-parse@1.0.7](https://github.com/jbgutierrez/path-parse) - MIT
|
||||
[path-scurry@1.11.1](https://github.com/isaacs/path-scurry) - BlueOak-1.0.0
|
||||
[path-type@4.0.0](https://github.com/sindresorhus/path-type) - MIT
|
||||
[picocolors@1.0.0](https://github.com/alexeyraspopov/picocolors) - ISC
|
||||
[picomatch@2.3.1](https://github.com/micromatch/picomatch) - MIT
|
||||
[pirates@4.0.6](https://github.com/danez/pirates) - MIT
|
||||
[pkg-dir@4.2.0](https://github.com/sindresorhus/pkg-dir) - MIT
|
||||
[platform@1.3.6](https://github.com/bestiejs/platform.js) - MIT
|
||||
[prelude-ls@1.2.1](https://github.com/gkz/prelude-ls) - MIT
|
||||
[pretty-format@29.7.0](https://github.com/jestjs/jest) - MIT
|
||||
[prompts@2.4.2](https://github.com/terkelg/prompts) - MIT
|
||||
[protobufjs@7.4.0](https://github.com/protobufjs/protobuf.js) - BSD-3-Clause
|
||||
[proxy-from-env@1.1.0](https://github.com/Rob--W/proxy-from-env) - MIT
|
||||
[punycode.js@2.3.1](https://github.com/mathiasbynens/punycode.js) - MIT
|
||||
[punycode@2.3.1](https://github.com/mathiasbynens/punycode.js) - MIT
|
||||
[pure-rand@6.0.4](https://github.com/dubzzz/pure-rand) - MIT
|
||||
[queue-microtask@1.2.3](https://github.com/feross/queue-microtask) - MIT
|
||||
[react-is@18.2.0](https://github.com/facebook/react) - MIT
|
||||
[rechoir@0.6.2](https://github.com/tkellen/node-rechoir) - MIT
|
||||
[reflect-metadata@0.2.2](https://github.com/rbuckton/reflect-metadata) - Apache-2.0
|
||||
[require-directory@2.1.1](https://github.com/troygoode/node-require-directory) - MIT
|
||||
[resolve-cwd@3.0.0](https://github.com/sindresorhus/resolve-cwd) - MIT
|
||||
[resolve-from@4.0.0](https://github.com/sindresorhus/resolve-from) - MIT
|
||||
[resolve-from@5.0.0](https://github.com/sindresorhus/resolve-from) - MIT
|
||||
[resolve.exports@2.0.2](https://github.com/lukeed/resolve.exports) - MIT
|
||||
[resolve@1.22.8](https://github.com/browserify/resolve) - MIT
|
||||
[reusify@1.0.4](https://github.com/mcollina/reusify) - MIT
|
||||
[rimraf@3.0.2](https://github.com/isaacs/rimraf) - ISC
|
||||
[rimraf@5.0.10](https://github.com/isaacs/rimraf) - ISC
|
||||
[run-parallel@1.2.0](https://github.com/feross/run-parallel) - MIT
|
||||
[semver@6.3.1](https://github.com/npm/node-semver) - ISC
|
||||
[semver@7.6.3](https://github.com/npm/node-semver) - ISC
|
||||
[sharp@0.33.5](https://github.com/lovell/sharp) - Apache-2.0
|
||||
[shebang-command@2.0.0](https://github.com/kevva/shebang-command) - MIT
|
||||
[shebang-regex@3.0.0](https://github.com/sindresorhus/shebang-regex) - MIT
|
||||
[shelljs@0.8.5](https://github.com/shelljs/shelljs) - BSD-3-Clause
|
||||
[shiki@1.10.3](https://github.com/shikijs/shiki) - MIT
|
||||
[shx@0.3.4](https://github.com/shelljs/shx) - MIT
|
||||
[signal-exit@3.0.7](https://github.com/tapjs/signal-exit) - ISC
|
||||
[signal-exit@4.1.0](https://github.com/tapjs/signal-exit) - ISC
|
||||
[simple-swizzle@0.2.2](https://github.com/qix-/node-simple-swizzle) - MIT
|
||||
[sisteransi@1.0.5](https://github.com/terkelg/sisteransi) - MIT
|
||||
[slash@3.0.0](https://github.com/sindresorhus/slash) - MIT
|
||||
[source-map-support@0.5.13](https://github.com/evanw/node-source-map-support) - MIT
|
||||
[source-map@0.6.1](https://github.com/mozilla/source-map) - BSD-3-Clause
|
||||
[sprintf-js@1.0.3](https://github.com/alexei/sprintf.js) - BSD-3-Clause
|
||||
[stack-utils@2.0.6](https://github.com/tapjs/stack-utils) - MIT
|
||||
[stream-read-all@3.0.1](https://github.com/75lb/stream-read-all) - MIT
|
||||
[string-length@4.0.2](https://github.com/sindresorhus/string-length) - MIT
|
||||
[string-width@4.2.3](https://github.com/sindresorhus/string-width) - MIT
|
||||
[string-width@5.1.2](https://github.com/sindresorhus/string-width) - MIT
|
||||
[strip-ansi@6.0.1](https://github.com/chalk/strip-ansi) - MIT
|
||||
[strip-ansi@7.1.0](https://github.com/chalk/strip-ansi) - MIT
|
||||
[strip-bom@4.0.0](https://github.com/sindresorhus/strip-bom) - MIT
|
||||
[strip-final-newline@2.0.0](https://github.com/sindresorhus/strip-final-newline) - MIT
|
||||
[strip-json-comments@3.1.1](https://github.com/sindresorhus/strip-json-comments) - MIT
|
||||
[strnum@1.0.5](https://github.com/NaturalIntelligence/strnum) - MIT
|
||||
[supports-color@7.2.0](https://github.com/chalk/supports-color) - MIT
|
||||
[supports-color@8.1.1](https://github.com/chalk/supports-color) - MIT
|
||||
[supports-preserve-symlinks-flag@1.0.0](https://github.com/inspect-js/node-supports-preserve-symlinks-flag) - MIT
|
||||
[table-layout@3.0.2](https://github.com/75lb/table-layout) - MIT
|
||||
[tar@7.4.3](https://github.com/isaacs/node-tar) - ISC
|
||||
[test-exclude@6.0.0](https://github.com/istanbuljs/test-exclude) - ISC
|
||||
[text-table@0.2.0](https://github.com/substack/text-table) - MIT
|
||||
[tmp@0.2.3](https://github.com/raszi/node-tmp) - MIT
|
||||
[tmpl@1.0.5](https://github.com/daaku/nodejs-tmpl) - BSD-3-Clause
|
||||
[to-regex-range@5.0.1](https://github.com/micromatch/to-regex-range) - MIT
|
||||
[tr46@0.0.3](https://github.com/Sebmaster/tr46.js) - MIT
|
||||
[ts-api-utils@1.0.3](https://github.com/JoshuaKGoldberg/ts-api-utils) - MIT
|
||||
[ts-jest@29.1.2](https://github.com/kulshekhar/ts-jest) - MIT
|
||||
[tslib@1.14.1](https://github.com/Microsoft/tslib) - 0BSD
|
||||
[tslib@2.6.2](https://github.com/Microsoft/tslib) - 0BSD
|
||||
[type-check@0.4.0](https://github.com/gkz/type-check) - MIT
|
||||
[type-detect@4.0.8](https://github.com/chaijs/type-detect) - MIT
|
||||
[type-fest@0.20.2](https://github.com/sindresorhus/type-fest) - (MIT OR CC0-1.0)
|
||||
[type-fest@0.21.3](https://github.com/sindresorhus/type-fest) - (MIT OR CC0-1.0)
|
||||
[typedoc-plugin-markdown@4.2.1](https://github.com/typedoc2md/typedoc-plugin-markdown) - MIT
|
||||
[typedoc@0.26.4](https://github.com/TypeStrong/TypeDoc) - Apache-2.0
|
||||
[typescript-eslint@7.1.0](https://github.com/typescript-eslint/typescript-eslint) - MIT
|
||||
[typescript@5.5.4](https://github.com/Microsoft/TypeScript) - Apache-2.0
|
||||
[typical@4.0.0](https://github.com/75lb/typical) - MIT
|
||||
[typical@7.1.1](https://github.com/75lb/typical) - MIT
|
||||
[uc.micro@2.1.0](https://github.com/markdown-it/uc.micro) - MIT
|
||||
[undici-types@5.26.5](https://github.com/nodejs/undici) - MIT
|
||||
[undici-types@6.19.8](https://github.com/nodejs/undici) - MIT
|
||||
[update-browserslist-db@1.0.13](https://github.com/browserslist/update-db) - MIT
|
||||
[uri-js@4.4.1](https://github.com/garycourt/uri-js) - BSD-2-Clause
|
||||
[uuid@9.0.1](https://github.com/uuidjs/uuid) - MIT
|
||||
[v8-to-istanbul@9.2.0](https://github.com/istanbuljs/v8-to-istanbul) - ISC
|
||||
[walker@1.0.8](https://github.com/daaku/nodejs-walker) - Apache-2.0
|
||||
[web-streams-polyfill@3.3.3](https://github.com/MattiasBuelens/web-streams-polyfill) - MIT
|
||||
[web-streams-polyfill@4.0.0-beta.3](https://github.com/MattiasBuelens/web-streams-polyfill) - MIT
|
||||
[webidl-conversions@3.0.1](https://github.com/jsdom/webidl-conversions) - BSD-2-Clause
|
||||
[whatwg-url@5.0.0](https://github.com/jsdom/whatwg-url) - MIT
|
||||
[which@2.0.2](https://github.com/isaacs/node-which) - ISC
|
||||
[wordwrapjs@5.1.0](https://github.com/75lb/wordwrapjs) - MIT
|
||||
[wrap-ansi@7.0.0](https://github.com/chalk/wrap-ansi) - MIT
|
||||
[wrap-ansi@8.1.0](https://github.com/chalk/wrap-ansi) - MIT
|
||||
[wrappy@1.0.2](https://github.com/npm/wrappy) - ISC
|
||||
[write-file-atomic@4.0.2](https://github.com/npm/write-file-atomic) - ISC
|
||||
[y18n@5.0.8](https://github.com/yargs/y18n) - ISC
|
||||
[yallist@3.1.1](https://github.com/isaacs/yallist) - ISC
|
||||
[yallist@5.0.0](https://github.com/isaacs/yallist) - BlueOak-1.0.0
|
||||
[yaml@2.4.5](https://github.com/eemeli/yaml) - ISC
|
||||
[yargs-parser@21.1.1](https://github.com/yargs/yargs-parser) - ISC
|
||||
[yargs@17.7.2](https://github.com/yargs/yargs) - MIT
|
||||
[yocto-queue@0.1.0](https://github.com/sindresorhus/yocto-queue) - MIT
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1697,6 +1697,65 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
|
||||
expect(results2[0].text).toBe(data[1].text);
|
||||
});
|
||||
|
||||
test("full text search fast search", async () => {
|
||||
const db = await connect(tmpDir.name);
|
||||
const data = [{ text: "hello world", vector: [0.1, 0.2, 0.3], id: 1 }];
|
||||
const table = await db.createTable("test", data);
|
||||
await table.createIndex("text", {
|
||||
config: Index.fts(),
|
||||
});
|
||||
|
||||
// Insert unindexed data after creating the index.
|
||||
await table.add([{ text: "xyz", vector: [0.4, 0.5, 0.6], id: 2 }]);
|
||||
|
||||
const withFlatSearch = await table
|
||||
.search("xyz", "fts")
|
||||
.limit(10)
|
||||
.toArray();
|
||||
expect(withFlatSearch.length).toBeGreaterThan(0);
|
||||
|
||||
const fastSearchResults = await table
|
||||
.search("xyz", "fts")
|
||||
.fastSearch()
|
||||
.limit(10)
|
||||
.toArray();
|
||||
expect(fastSearchResults.length).toBe(0);
|
||||
|
||||
const nearestToTextFastSearch = await table
|
||||
.query()
|
||||
.nearestToText("xyz")
|
||||
.fastSearch()
|
||||
.limit(10)
|
||||
.toArray();
|
||||
expect(nearestToTextFastSearch.length).toBe(0);
|
||||
|
||||
// fastSearch should be chainable with other methods.
|
||||
const chainedFastSearch = await table
|
||||
.search("xyz", "fts")
|
||||
.fastSearch()
|
||||
.select(["text"])
|
||||
.limit(5)
|
||||
.toArray();
|
||||
expect(chainedFastSearch.length).toBe(0);
|
||||
|
||||
await table.optimize();
|
||||
|
||||
const indexedFastSearch = await table
|
||||
.search("xyz", "fts")
|
||||
.fastSearch()
|
||||
.limit(10)
|
||||
.toArray();
|
||||
expect(indexedFastSearch.length).toBeGreaterThan(0);
|
||||
|
||||
const indexedNearestToTextFastSearch = await table
|
||||
.query()
|
||||
.nearestToText("xyz")
|
||||
.fastSearch()
|
||||
.limit(10)
|
||||
.toArray();
|
||||
expect(indexedNearestToTextFastSearch.length).toBeGreaterThan(0);
|
||||
});
|
||||
|
||||
test("prewarm full text search index", async () => {
|
||||
const db = await connect(tmpDir.name);
|
||||
const data = [
|
||||
|
||||
@@ -273,7 +273,9 @@ export async function connect(
|
||||
let nativeProvider: NativeJsHeaderProvider | undefined;
|
||||
if (finalHeaderProvider) {
|
||||
if (typeof finalHeaderProvider === "function") {
|
||||
nativeProvider = new NativeJsHeaderProvider(finalHeaderProvider);
|
||||
nativeProvider = new NativeJsHeaderProvider(async () =>
|
||||
finalHeaderProvider(),
|
||||
);
|
||||
} else if (
|
||||
finalHeaderProvider &&
|
||||
typeof finalHeaderProvider.getHeaders === "function"
|
||||
|
||||
+10
-12
@@ -684,19 +684,17 @@ export class VectorQuery extends StandardQueryBase<NativeVectorQuery> {
|
||||
|
||||
rerank(reranker: Reranker): VectorQuery {
|
||||
super.doCall((inner) =>
|
||||
inner.rerank({
|
||||
rerankHybrid: async (_, args) => {
|
||||
const vecResults = await fromBufferToRecordBatch(args.vecResults);
|
||||
const ftsResults = await fromBufferToRecordBatch(args.ftsResults);
|
||||
const result = await reranker.rerankHybrid(
|
||||
args.query,
|
||||
vecResults as RecordBatch,
|
||||
ftsResults as RecordBatch,
|
||||
);
|
||||
inner.rerank(async (args) => {
|
||||
const vecResults = await fromBufferToRecordBatch(args.vecResults);
|
||||
const ftsResults = await fromBufferToRecordBatch(args.ftsResults);
|
||||
const result = await reranker.rerankHybrid(
|
||||
args.query,
|
||||
vecResults as RecordBatch,
|
||||
ftsResults as RecordBatch,
|
||||
);
|
||||
|
||||
const buffer = fromRecordBatchToBuffer(result);
|
||||
return buffer;
|
||||
},
|
||||
const buffer = fromRecordBatchToBuffer(result);
|
||||
return buffer;
|
||||
}),
|
||||
);
|
||||
|
||||
|
||||
@@ -542,6 +542,35 @@ export abstract class Table {
|
||||
*
|
||||
*/
|
||||
abstract stats(): Promise<TableStatistics>;
|
||||
|
||||
/**
|
||||
* Get the initial storage options that were passed in when opening this table.
|
||||
*
|
||||
* For dynamically refreshed options (e.g., credential vending), use
|
||||
* {@link Table.latestStorageOptions}.
|
||||
*
|
||||
* Warning: This is an internal API and the return value is subject to change.
|
||||
*
|
||||
* @returns The storage options, or undefined if no storage options were configured.
|
||||
*/
|
||||
abstract initialStorageOptions(): Promise<
|
||||
Record<string, string> | null | undefined
|
||||
>;
|
||||
|
||||
/**
|
||||
* Get the latest storage options, refreshing from provider if configured.
|
||||
*
|
||||
* This method is useful for credential vending scenarios where storage options
|
||||
* may be refreshed dynamically. If no dynamic provider is configured, this
|
||||
* returns the initial static options.
|
||||
*
|
||||
* Warning: This is an internal API and the return value is subject to change.
|
||||
*
|
||||
* @returns The storage options, or undefined if no storage options were configured.
|
||||
*/
|
||||
abstract latestStorageOptions(): Promise<
|
||||
Record<string, string> | null | undefined
|
||||
>;
|
||||
}
|
||||
|
||||
export class LocalTable extends Table {
|
||||
@@ -878,6 +907,18 @@ export class LocalTable extends Table {
|
||||
return await this.inner.stats();
|
||||
}
|
||||
|
||||
async initialStorageOptions(): Promise<
|
||||
Record<string, string> | null | undefined
|
||||
> {
|
||||
return await this.inner.initialStorageOptions();
|
||||
}
|
||||
|
||||
async latestStorageOptions(): Promise<
|
||||
Record<string, string> | null | undefined
|
||||
> {
|
||||
return await this.inner.latestStorageOptions();
|
||||
}
|
||||
|
||||
mergeInsert(on: string | string[]): MergeInsertBuilder {
|
||||
on = Array.isArray(on) ? on : [on];
|
||||
return new MergeInsertBuilder(this.inner.mergeInsert(on), this.schema());
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-darwin-arm64",
|
||||
"version": "0.25.0-beta.0",
|
||||
"version": "0.27.0-beta.3",
|
||||
"os": ["darwin"],
|
||||
"cpu": ["arm64"],
|
||||
"main": "lancedb.darwin-arm64.node",
|
||||
@@ -8,5 +8,9 @@
|
||||
"license": "Apache-2.0",
|
||||
"engines": {
|
||||
"node": ">= 18"
|
||||
},
|
||||
"repository": {
|
||||
"type": "git",
|
||||
"url": "https://github.com/lancedb/lancedb"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,3 +0,0 @@
|
||||
# `@lancedb/lancedb-darwin-x64`
|
||||
|
||||
This is the **x86_64-apple-darwin** binary for `@lancedb/lancedb`
|
||||
@@ -1,12 +0,0 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-darwin-x64",
|
||||
"version": "0.25.0-beta.0",
|
||||
"os": ["darwin"],
|
||||
"cpu": ["x64"],
|
||||
"main": "lancedb.darwin-x64.node",
|
||||
"files": ["lancedb.darwin-x64.node"],
|
||||
"license": "Apache-2.0",
|
||||
"engines": {
|
||||
"node": ">= 18"
|
||||
}
|
||||
}
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-linux-arm64-gnu",
|
||||
"version": "0.25.0-beta.0",
|
||||
"version": "0.27.0-beta.3",
|
||||
"os": ["linux"],
|
||||
"cpu": ["arm64"],
|
||||
"main": "lancedb.linux-arm64-gnu.node",
|
||||
@@ -9,5 +9,9 @@
|
||||
"engines": {
|
||||
"node": ">= 18"
|
||||
},
|
||||
"libc": ["glibc"]
|
||||
"libc": ["glibc"],
|
||||
"repository": {
|
||||
"type": "git",
|
||||
"url": "https://github.com/lancedb/lancedb"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-linux-arm64-musl",
|
||||
"version": "0.25.0-beta.0",
|
||||
"version": "0.27.0-beta.3",
|
||||
"os": ["linux"],
|
||||
"cpu": ["arm64"],
|
||||
"main": "lancedb.linux-arm64-musl.node",
|
||||
@@ -9,5 +9,9 @@
|
||||
"engines": {
|
||||
"node": ">= 18"
|
||||
},
|
||||
"libc": ["musl"]
|
||||
"libc": ["musl"],
|
||||
"repository": {
|
||||
"type": "git",
|
||||
"url": "https://github.com/lancedb/lancedb"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-linux-x64-gnu",
|
||||
"version": "0.25.0-beta.0",
|
||||
"version": "0.27.0-beta.3",
|
||||
"os": ["linux"],
|
||||
"cpu": ["x64"],
|
||||
"main": "lancedb.linux-x64-gnu.node",
|
||||
@@ -9,5 +9,9 @@
|
||||
"engines": {
|
||||
"node": ">= 18"
|
||||
},
|
||||
"libc": ["glibc"]
|
||||
"libc": ["glibc"],
|
||||
"repository": {
|
||||
"type": "git",
|
||||
"url": "https://github.com/lancedb/lancedb"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-linux-x64-musl",
|
||||
"version": "0.25.0-beta.0",
|
||||
"version": "0.27.0-beta.3",
|
||||
"os": ["linux"],
|
||||
"cpu": ["x64"],
|
||||
"main": "lancedb.linux-x64-musl.node",
|
||||
@@ -9,5 +9,9 @@
|
||||
"engines": {
|
||||
"node": ">= 18"
|
||||
},
|
||||
"libc": ["musl"]
|
||||
"libc": ["musl"],
|
||||
"repository": {
|
||||
"type": "git",
|
||||
"url": "https://github.com/lancedb/lancedb"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-win32-arm64-msvc",
|
||||
"version": "0.25.0-beta.0",
|
||||
"version": "0.27.0-beta.3",
|
||||
"os": [
|
||||
"win32"
|
||||
],
|
||||
@@ -14,5 +14,9 @@
|
||||
"license": "Apache-2.0",
|
||||
"engines": {
|
||||
"node": ">= 18"
|
||||
},
|
||||
"repository": {
|
||||
"type": "git",
|
||||
"url": "https://github.com/lancedb/lancedb"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-win32-x64-msvc",
|
||||
"version": "0.25.0-beta.0",
|
||||
"version": "0.27.0-beta.3",
|
||||
"os": ["win32"],
|
||||
"cpu": ["x64"],
|
||||
"main": "lancedb.win32-x64-msvc.node",
|
||||
@@ -8,5 +8,9 @@
|
||||
"license": "Apache-2.0",
|
||||
"engines": {
|
||||
"node": ">= 18"
|
||||
},
|
||||
"repository": {
|
||||
"type": "git",
|
||||
"url": "https://github.com/lancedb/lancedb"
|
||||
}
|
||||
}
|
||||
|
||||
Generated
+1756
-25
File diff suppressed because it is too large
Load Diff
+19
-19
@@ -11,7 +11,7 @@
|
||||
"ann"
|
||||
],
|
||||
"private": false,
|
||||
"version": "0.25.0-beta.0",
|
||||
"version": "0.27.0-beta.3",
|
||||
"main": "dist/index.js",
|
||||
"exports": {
|
||||
".": "./dist/index.js",
|
||||
@@ -21,29 +21,29 @@
|
||||
},
|
||||
"types": "dist/index.d.ts",
|
||||
"napi": {
|
||||
"name": "lancedb",
|
||||
"triples": {
|
||||
"defaults": false,
|
||||
"additional": [
|
||||
"x86_64-apple-darwin",
|
||||
"aarch64-apple-darwin",
|
||||
"x86_64-unknown-linux-gnu",
|
||||
"aarch64-unknown-linux-gnu",
|
||||
"x86_64-unknown-linux-musl",
|
||||
"aarch64-unknown-linux-musl",
|
||||
"x86_64-pc-windows-msvc",
|
||||
"aarch64-pc-windows-msvc"
|
||||
]
|
||||
}
|
||||
"binaryName": "lancedb",
|
||||
"targets": [
|
||||
"aarch64-apple-darwin",
|
||||
"x86_64-unknown-linux-gnu",
|
||||
"aarch64-unknown-linux-gnu",
|
||||
"x86_64-unknown-linux-musl",
|
||||
"aarch64-unknown-linux-musl",
|
||||
"x86_64-pc-windows-msvc",
|
||||
"aarch64-pc-windows-msvc"
|
||||
]
|
||||
},
|
||||
"license": "Apache-2.0",
|
||||
"repository": {
|
||||
"type": "git",
|
||||
"url": "https://github.com/lancedb/lancedb"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@aws-sdk/client-dynamodb": "^3.33.0",
|
||||
"@aws-sdk/client-kms": "^3.33.0",
|
||||
"@aws-sdk/client-s3": "^3.33.0",
|
||||
"@biomejs/biome": "^1.7.3",
|
||||
"@jest/globals": "^29.7.0",
|
||||
"@napi-rs/cli": "^2.18.3",
|
||||
"@napi-rs/cli": "^3.5.1",
|
||||
"@types/axios": "^0.14.0",
|
||||
"@types/jest": "^29.1.2",
|
||||
"@types/node": "^22.7.4",
|
||||
@@ -72,9 +72,9 @@
|
||||
"os": ["darwin", "linux", "win32"],
|
||||
"scripts": {
|
||||
"artifacts": "napi artifacts",
|
||||
"build:debug": "napi build --platform --no-const-enum --dts ../lancedb/native.d.ts --js ../lancedb/native.js lancedb",
|
||||
"build:debug": "napi build --platform --dts ../lancedb/native.d.ts --js ../lancedb/native.js --output-dir lancedb",
|
||||
"postbuild:debug": "shx mkdir -p dist && shx cp lancedb/*.node dist/",
|
||||
"build:release": "napi build --platform --no-const-enum --release --dts ../lancedb/native.d.ts --js ../lancedb/native.js dist/",
|
||||
"build:release": "napi build --platform --release --dts ../lancedb/native.d.ts --js ../lancedb/native.js --output-dir dist",
|
||||
"postbuild:release": "shx mkdir -p dist && shx cp lancedb/*.node dist/",
|
||||
"build": "npm run build:debug && npm run tsc",
|
||||
"build-release": "npm run build:release && npm run tsc",
|
||||
@@ -88,7 +88,7 @@
|
||||
"prepublishOnly": "napi prepublish -t npm",
|
||||
"test": "jest --verbose",
|
||||
"integration": "S3_TEST=1 npm run test",
|
||||
"universal": "napi universal",
|
||||
"universal": "napi universalize",
|
||||
"version": "napi version"
|
||||
},
|
||||
"dependencies": {
|
||||
|
||||
@@ -8,11 +8,12 @@ use lancedb::database::{CreateTableMode, Database};
|
||||
use napi::bindgen_prelude::*;
|
||||
use napi_derive::*;
|
||||
|
||||
use crate::ConnectionOptions;
|
||||
use crate::error::NapiErrorExt;
|
||||
use crate::header::JsHeaderProvider;
|
||||
use crate::table::Table;
|
||||
use crate::ConnectionOptions;
|
||||
use lancedb::connection::{ConnectBuilder, Connection as LanceDBConnection};
|
||||
|
||||
use lancedb::ipc::{ipc_file_to_batches, ipc_file_to_schema};
|
||||
|
||||
#[napi]
|
||||
|
||||
+10
-8
@@ -1,20 +1,19 @@
|
||||
// SPDX-License-Identifier: Apache-2.0
|
||||
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
|
||||
use napi::{
|
||||
bindgen_prelude::*,
|
||||
threadsafe_function::{ErrorStrategy, ThreadsafeFunction},
|
||||
};
|
||||
use napi::{bindgen_prelude::*, threadsafe_function::ThreadsafeFunction};
|
||||
use napi_derive::napi;
|
||||
use std::collections::HashMap;
|
||||
use std::sync::Arc;
|
||||
|
||||
type GetHeadersFn = ThreadsafeFunction<(), Promise<HashMap<String, String>>, (), Status, false>;
|
||||
|
||||
/// JavaScript HeaderProvider implementation that wraps a JavaScript callback.
|
||||
/// This is the only native header provider - all header provider implementations
|
||||
/// should provide a JavaScript function that returns headers.
|
||||
#[napi]
|
||||
pub struct JsHeaderProvider {
|
||||
get_headers_fn: Arc<ThreadsafeFunction<(), ErrorStrategy::CalleeHandled>>,
|
||||
get_headers_fn: Arc<GetHeadersFn>,
|
||||
}
|
||||
|
||||
impl Clone for JsHeaderProvider {
|
||||
@@ -29,9 +28,12 @@ impl Clone for JsHeaderProvider {
|
||||
impl JsHeaderProvider {
|
||||
/// Create a new JsHeaderProvider from a JavaScript callback
|
||||
#[napi(constructor)]
|
||||
pub fn new(get_headers_callback: JsFunction) -> Result<Self> {
|
||||
pub fn new(
|
||||
get_headers_callback: Function<(), Promise<HashMap<String, String>>>,
|
||||
) -> Result<Self> {
|
||||
let get_headers_fn = get_headers_callback
|
||||
.create_threadsafe_function(0, |ctx| Ok(vec![ctx.value]))
|
||||
.build_threadsafe_function()
|
||||
.build()
|
||||
.map_err(|e| {
|
||||
Error::new(
|
||||
Status::GenericFailure,
|
||||
@@ -51,7 +53,7 @@ impl lancedb::remote::HeaderProvider for JsHeaderProvider {
|
||||
async fn get_headers(&self) -> lancedb::error::Result<HashMap<String, String>> {
|
||||
// Call the JavaScript function asynchronously
|
||||
let promise: Promise<HashMap<String, String>> =
|
||||
self.get_headers_fn.call_async(Ok(())).await.map_err(|e| {
|
||||
self.get_headers_fn.call_async(()).await.map_err(|e| {
|
||||
lancedb::error::Error::Runtime {
|
||||
message: format!("Failed to call JavaScript get_headers: {}", e),
|
||||
}
|
||||
|
||||
+1
-1
@@ -3,12 +3,12 @@
|
||||
|
||||
use std::sync::Mutex;
|
||||
|
||||
use lancedb::index::Index as LanceDbIndex;
|
||||
use lancedb::index::scalar::{BTreeIndexBuilder, FtsIndexBuilder};
|
||||
use lancedb::index::vector::{
|
||||
IvfFlatIndexBuilder, IvfHnswPqIndexBuilder, IvfHnswSqIndexBuilder, IvfPqIndexBuilder,
|
||||
IvfRqIndexBuilder,
|
||||
};
|
||||
use lancedb::index::Index as LanceDbIndex;
|
||||
use napi_derive::napi;
|
||||
|
||||
use crate::util::parse_distance_type;
|
||||
|
||||
+1
-1
@@ -60,7 +60,7 @@ pub struct OpenTableOptions {
|
||||
pub storage_options: Option<HashMap<String, String>>,
|
||||
}
|
||||
|
||||
#[napi::module_init]
|
||||
#[napi_derive::module_init]
|
||||
fn init() {
|
||||
let env = Env::new()
|
||||
.filter_or("LANCEDB_LOG", "warn")
|
||||
|
||||
+21
-22
@@ -17,11 +17,11 @@ use lancedb::query::VectorQuery as LanceDbVectorQuery;
|
||||
use napi::bindgen_prelude::*;
|
||||
use napi_derive::napi;
|
||||
|
||||
use crate::error::convert_error;
|
||||
use crate::error::NapiErrorExt;
|
||||
use crate::error::convert_error;
|
||||
use crate::iterator::RecordBatchIterator;
|
||||
use crate::rerankers::RerankHybridCallbackArgs;
|
||||
use crate::rerankers::Reranker;
|
||||
use crate::rerankers::RerankerCallbacks;
|
||||
use crate::util::{parse_distance_type, schema_to_buffer};
|
||||
|
||||
#[napi]
|
||||
@@ -42,7 +42,7 @@ impl Query {
|
||||
}
|
||||
|
||||
#[napi]
|
||||
pub fn full_text_search(&mut self, query: napi::JsObject) -> napi::Result<()> {
|
||||
pub fn full_text_search(&mut self, query: Object) -> napi::Result<()> {
|
||||
let query = parse_fts_query(query)?;
|
||||
self.inner = self.inner.clone().full_text_search(query);
|
||||
Ok(())
|
||||
@@ -235,7 +235,7 @@ impl VectorQuery {
|
||||
}
|
||||
|
||||
#[napi]
|
||||
pub fn full_text_search(&mut self, query: napi::JsObject) -> napi::Result<()> {
|
||||
pub fn full_text_search(&mut self, query: Object) -> napi::Result<()> {
|
||||
let query = parse_fts_query(query)?;
|
||||
self.inner = self.inner.clone().full_text_search(query);
|
||||
Ok(())
|
||||
@@ -272,11 +272,13 @@ impl VectorQuery {
|
||||
}
|
||||
|
||||
#[napi]
|
||||
pub fn rerank(&mut self, callbacks: RerankerCallbacks) {
|
||||
self.inner = self
|
||||
.inner
|
||||
.clone()
|
||||
.rerank(Arc::new(Reranker::new(callbacks)));
|
||||
pub fn rerank(
|
||||
&mut self,
|
||||
rerank_hybrid: Function<RerankHybridCallbackArgs, Promise<Buffer>>,
|
||||
) -> napi::Result<()> {
|
||||
let reranker = Reranker::new(rerank_hybrid)?;
|
||||
self.inner = self.inner.clone().rerank(Arc::new(reranker));
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[napi(catch_unwind)]
|
||||
@@ -523,12 +525,12 @@ impl JsFullTextQuery {
|
||||
}
|
||||
}
|
||||
|
||||
fn parse_fts_query(query: napi::JsObject) -> napi::Result<FullTextSearchQuery> {
|
||||
if let Ok(Some(query)) = query.get::<_, &JsFullTextQuery>("query") {
|
||||
fn parse_fts_query(query: Object) -> napi::Result<FullTextSearchQuery> {
|
||||
if let Ok(Some(query)) = query.get::<&JsFullTextQuery>("query") {
|
||||
Ok(FullTextSearchQuery::new_query(query.inner.clone()))
|
||||
} else if let Ok(Some(query_text)) = query.get::<_, String>("query") {
|
||||
} else if let Ok(Some(query_text)) = query.get::<String>("query") {
|
||||
let mut query_text = query_text;
|
||||
let columns = query.get::<_, Option<Vec<String>>>("columns")?.flatten();
|
||||
let columns = query.get::<Option<Vec<String>>>("columns")?.flatten();
|
||||
|
||||
let is_phrase =
|
||||
query_text.len() >= 2 && query_text.starts_with('"') && query_text.ends_with('"');
|
||||
@@ -549,15 +551,12 @@ fn parse_fts_query(query: napi::JsObject) -> napi::Result<FullTextSearchQuery> {
|
||||
}
|
||||
};
|
||||
let mut query = FullTextSearchQuery::new_query(query);
|
||||
if let Some(cols) = columns {
|
||||
if !cols.is_empty() {
|
||||
query = query.with_columns(&cols).map_err(|e| {
|
||||
napi::Error::from_reason(format!(
|
||||
"Failed to set full text search columns: {}",
|
||||
e
|
||||
))
|
||||
})?;
|
||||
}
|
||||
if let Some(cols) = columns
|
||||
&& !cols.is_empty()
|
||||
{
|
||||
query = query.with_columns(&cols).map_err(|e| {
|
||||
napi::Error::from_reason(format!("Failed to set full text search columns: {}", e))
|
||||
})?;
|
||||
}
|
||||
Ok(query)
|
||||
} else {
|
||||
|
||||
+22
-29
@@ -3,10 +3,7 @@
|
||||
|
||||
use arrow_array::RecordBatch;
|
||||
use async_trait::async_trait;
|
||||
use napi::{
|
||||
bindgen_prelude::*,
|
||||
threadsafe_function::{ErrorStrategy, ThreadsafeFunction},
|
||||
};
|
||||
use napi::{bindgen_prelude::*, threadsafe_function::ThreadsafeFunction};
|
||||
use napi_derive::napi;
|
||||
|
||||
use lancedb::ipc::batches_to_ipc_file;
|
||||
@@ -15,27 +12,28 @@ use lancedb::{error::Error, ipc::ipc_file_to_batches};
|
||||
|
||||
use crate::error::NapiErrorExt;
|
||||
|
||||
type RerankHybridFn = ThreadsafeFunction<
|
||||
RerankHybridCallbackArgs,
|
||||
Promise<Buffer>,
|
||||
RerankHybridCallbackArgs,
|
||||
Status,
|
||||
false,
|
||||
>;
|
||||
|
||||
/// Reranker implementation that "wraps" a NodeJS Reranker implementation.
|
||||
/// This contains references to the callbacks that can be used to invoke the
|
||||
/// reranking methods on the NodeJS implementation and handles serializing the
|
||||
/// record batches to Arrow IPC buffers.
|
||||
#[napi]
|
||||
pub struct Reranker {
|
||||
/// callback to the Javascript which will call the rerankHybrid method of
|
||||
/// some Reranker implementation
|
||||
rerank_hybrid: ThreadsafeFunction<RerankHybridCallbackArgs, ErrorStrategy::CalleeHandled>,
|
||||
rerank_hybrid: RerankHybridFn,
|
||||
}
|
||||
|
||||
#[napi]
|
||||
impl Reranker {
|
||||
#[napi]
|
||||
pub fn new(callbacks: RerankerCallbacks) -> Self {
|
||||
let rerank_hybrid = callbacks
|
||||
.rerank_hybrid
|
||||
.create_threadsafe_function(0, move |ctx| Ok(vec![ctx.value]))
|
||||
.unwrap();
|
||||
|
||||
Self { rerank_hybrid }
|
||||
pub fn new(
|
||||
rerank_hybrid: Function<RerankHybridCallbackArgs, Promise<Buffer>>,
|
||||
) -> napi::Result<Self> {
|
||||
let rerank_hybrid = rerank_hybrid.build_threadsafe_function().build()?;
|
||||
Ok(Self { rerank_hybrid })
|
||||
}
|
||||
}
|
||||
|
||||
@@ -49,16 +47,16 @@ impl lancedb::rerankers::Reranker for Reranker {
|
||||
) -> lancedb::error::Result<RecordBatch> {
|
||||
let callback_args = RerankHybridCallbackArgs {
|
||||
query: query.to_string(),
|
||||
vec_results: batches_to_ipc_file(&[vector_results])?,
|
||||
fts_results: batches_to_ipc_file(&[fts_results])?,
|
||||
vec_results: Buffer::from(batches_to_ipc_file(&[vector_results])?.as_ref()),
|
||||
fts_results: Buffer::from(batches_to_ipc_file(&[fts_results])?.as_ref()),
|
||||
};
|
||||
let promised_buffer: Promise<Buffer> = self
|
||||
.rerank_hybrid
|
||||
.call_async(Ok(callback_args))
|
||||
.call_async(callback_args)
|
||||
.await
|
||||
.map_err(|e| Error::Runtime {
|
||||
message: format!("napi error status={}, reason={}", e.status, e.reason),
|
||||
})?;
|
||||
message: format!("napi error status={}, reason={}", e.status, e.reason),
|
||||
})?;
|
||||
let buffer = promised_buffer.await.map_err(|e| Error::Runtime {
|
||||
message: format!("napi error status={}, reason={}", e.status, e.reason),
|
||||
})?;
|
||||
@@ -77,16 +75,11 @@ impl std::fmt::Debug for Reranker {
|
||||
}
|
||||
}
|
||||
|
||||
#[napi(object)]
|
||||
pub struct RerankerCallbacks {
|
||||
pub rerank_hybrid: JsFunction,
|
||||
}
|
||||
|
||||
#[napi(object)]
|
||||
pub struct RerankHybridCallbackArgs {
|
||||
pub query: String,
|
||||
pub vec_results: Vec<u8>,
|
||||
pub fts_results: Vec<u8>,
|
||||
pub vec_results: Buffer,
|
||||
pub fts_results: Buffer,
|
||||
}
|
||||
|
||||
fn buffer_to_record_batch(buffer: Buffer) -> Result<RecordBatch> {
|
||||
|
||||
@@ -95,8 +95,7 @@ impl napi::bindgen_prelude::FromNapiValue for Session {
|
||||
napi_val: napi::sys::napi_value,
|
||||
) -> napi::Result<Self> {
|
||||
let object: napi::bindgen_prelude::ClassInstance<Self> =
|
||||
napi::bindgen_prelude::ClassInstance::from_napi_value(env, napi_val)?;
|
||||
let copy = object.clone();
|
||||
Ok(copy)
|
||||
unsafe { napi::bindgen_prelude::ClassInstance::from_napi_value(env, napi_val)? };
|
||||
Ok((*object).clone())
|
||||
}
|
||||
}
|
||||
|
||||
@@ -71,6 +71,17 @@ impl Table {
|
||||
pub async fn add(&self, buf: Buffer, mode: String) -> napi::Result<AddResult> {
|
||||
let batches = ipc_file_to_batches(buf.to_vec())
|
||||
.map_err(|e| napi::Error::from_reason(format!("Failed to read IPC file: {}", e)))?;
|
||||
let batches = batches
|
||||
.into_iter()
|
||||
.map(|batch| {
|
||||
batch.map_err(|e| {
|
||||
napi::Error::from_reason(format!(
|
||||
"Failed to read record batch from IPC file: {}",
|
||||
e
|
||||
))
|
||||
})
|
||||
})
|
||||
.collect::<Result<Vec<_>>>()?;
|
||||
let mut op = self.inner_ref()?.add(batches);
|
||||
|
||||
op = if mode == "append" {
|
||||
@@ -166,6 +177,19 @@ impl Table {
|
||||
Ok(stats.into())
|
||||
}
|
||||
|
||||
#[napi(catch_unwind)]
|
||||
pub async fn initial_storage_options(&self) -> napi::Result<Option<HashMap<String, String>>> {
|
||||
Ok(self.inner_ref()?.initial_storage_options().await)
|
||||
}
|
||||
|
||||
#[napi(catch_unwind)]
|
||||
pub async fn latest_storage_options(&self) -> napi::Result<Option<HashMap<String, String>>> {
|
||||
self.inner_ref()?
|
||||
.latest_storage_options()
|
||||
.await
|
||||
.default_error()
|
||||
}
|
||||
|
||||
#[napi(catch_unwind)]
|
||||
pub async fn update(
|
||||
&self,
|
||||
@@ -729,12 +753,14 @@ impl From<lancedb::table::AddResult> for AddResult {
|
||||
|
||||
#[napi(object)]
|
||||
pub struct DeleteResult {
|
||||
pub num_deleted_rows: i64,
|
||||
pub version: i64,
|
||||
}
|
||||
|
||||
impl From<lancedb::table::DeleteResult> for DeleteResult {
|
||||
fn from(value: lancedb::table::DeleteResult) -> Self {
|
||||
Self {
|
||||
num_deleted_rows: value.num_deleted_rows as i64,
|
||||
version: value.version as i64,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
[tool.bumpversion]
|
||||
current_version = "0.28.0-beta.0"
|
||||
current_version = "0.30.0-beta.3"
|
||||
parse = """(?x)
|
||||
(?P<major>0|[1-9]\\d*)\\.
|
||||
(?P<minor>0|[1-9]\\d*)\\.
|
||||
|
||||
+2
-2
@@ -1,13 +1,13 @@
|
||||
[package]
|
||||
name = "lancedb-python"
|
||||
version = "0.27.0"
|
||||
version = "0.30.0-beta.3"
|
||||
edition.workspace = true
|
||||
description = "Python bindings for LanceDB"
|
||||
license.workspace = true
|
||||
repository.workspace = true
|
||||
keywords.workspace = true
|
||||
categories.workspace = true
|
||||
rust-version = "1.88.0"
|
||||
rust-version = "1.91.0"
|
||||
|
||||
[lib]
|
||||
name = "_lancedb"
|
||||
|
||||
@@ -0,0 +1,206 @@
|
||||
| Name | Version | License | URL |
|
||||
|--------------------------------|-----------------|--------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------|
|
||||
| InstructorEmbedding | 1.0.1 | Apache License 2.0 | https://github.com/HKUNLP/instructor-embedding |
|
||||
| Jinja2 | 3.1.6 | BSD License | https://github.com/pallets/jinja/ |
|
||||
| Markdown | 3.10.2 | BSD-3-Clause | https://Python-Markdown.github.io/ |
|
||||
| MarkupSafe | 3.0.3 | BSD-3-Clause | https://github.com/pallets/markupsafe/ |
|
||||
| PyJWT | 2.11.0 | MIT | https://github.com/jpadilla/pyjwt |
|
||||
| PyYAML | 6.0.3 | MIT License | https://pyyaml.org/ |
|
||||
| Pygments | 2.19.2 | BSD License | https://pygments.org |
|
||||
| accelerate | 1.12.0 | Apache Software License | https://github.com/huggingface/accelerate |
|
||||
| adlfs | 2026.2.0 | BSD License | UNKNOWN |
|
||||
| aiohappyeyeballs | 2.6.1 | Python Software Foundation License | https://github.com/aio-libs/aiohappyeyeballs |
|
||||
| aiohttp | 3.13.3 | Apache-2.0 AND MIT | https://github.com/aio-libs/aiohttp |
|
||||
| aiosignal | 1.4.0 | Apache Software License | https://github.com/aio-libs/aiosignal |
|
||||
| annotated-types | 0.7.0 | MIT License | https://github.com/annotated-types/annotated-types |
|
||||
| anyio | 4.12.1 | MIT | https://anyio.readthedocs.io/en/stable/versionhistory.html |
|
||||
| appnope | 0.1.4 | BSD License | http://github.com/minrk/appnope |
|
||||
| asttokens | 3.0.1 | Apache 2.0 | https://github.com/gristlabs/asttokens |
|
||||
| attrs | 25.4.0 | MIT | https://www.attrs.org/en/stable/changelog.html |
|
||||
| awscli | 1.44.35 | Apache Software License | http://aws.amazon.com/cli/ |
|
||||
| azure-core | 1.38.0 | MIT License | https://github.com/Azure/azure-sdk-for-python/tree/main/sdk/core/azure-core |
|
||||
| azure-datalake-store | 0.0.53 | MIT License | https://github.com/Azure/azure-data-lake-store-python |
|
||||
| azure-identity | 1.25.1 | MIT | https://github.com/Azure/azure-sdk-for-python |
|
||||
| azure-storage-blob | 12.28.0 | MIT License | https://github.com/Azure/azure-sdk-for-python/tree/main/sdk/storage/azure-storage-blob |
|
||||
| babel | 2.18.0 | BSD License | https://babel.pocoo.org/ |
|
||||
| backrefs | 6.1 | MIT | https://github.com/facelessuser/backrefs |
|
||||
| beautifulsoup4 | 4.14.3 | MIT License | https://www.crummy.com/software/BeautifulSoup/bs4/ |
|
||||
| bleach | 6.3.0 | Apache Software License | https://github.com/mozilla/bleach |
|
||||
| boto3 | 1.42.45 | Apache-2.0 | https://github.com/boto/boto3 |
|
||||
| botocore | 1.42.45 | Apache-2.0 | https://github.com/boto/botocore |
|
||||
| cachetools | 7.0.0 | MIT | https://github.com/tkem/cachetools/ |
|
||||
| certifi | 2026.1.4 | Mozilla Public License 2.0 (MPL 2.0) | https://github.com/certifi/python-certifi |
|
||||
| cffi | 2.0.0 | MIT | https://cffi.readthedocs.io/en/latest/whatsnew.html |
|
||||
| cfgv | 3.5.0 | MIT | https://github.com/asottile/cfgv |
|
||||
| charset-normalizer | 3.4.4 | MIT | https://github.com/jawah/charset_normalizer/blob/master/CHANGELOG.md |
|
||||
| click | 8.3.1 | BSD-3-Clause | https://github.com/pallets/click/ |
|
||||
| cohere | 5.20.4 | MIT License | https://github.com/cohere-ai/cohere-python |
|
||||
| colorama | 0.4.6 | BSD License | https://github.com/tartley/colorama |
|
||||
| colpali_engine | 0.3.13 | MIT License | https://github.com/illuin-tech/colpali |
|
||||
| comm | 0.2.3 | BSD License | https://github.com/ipython/comm |
|
||||
| cryptography | 46.0.4 | Apache-2.0 OR BSD-3-Clause | https://github.com/pyca/cryptography |
|
||||
| datafusion | 51.0.0 | Apache Software License | https://datafusion.apache.org/python |
|
||||
| debugpy | 1.8.20 | MIT License | https://aka.ms/debugpy |
|
||||
| decorator | 5.2.1 | BSD License | UNKNOWN |
|
||||
| defusedxml | 0.7.1 | Python Software Foundation License | https://github.com/tiran/defusedxml |
|
||||
| deprecation | 2.1.0 | Apache Software License | http://deprecation.readthedocs.io/ |
|
||||
| distlib | 0.4.0 | Python Software Foundation License | https://github.com/pypa/distlib |
|
||||
| distro | 1.9.0 | Apache Software License | https://github.com/python-distro/distro |
|
||||
| docutils | 0.19 | BSD License; GNU General Public License (GPL); Public Domain; Python Software Foundation License | https://docutils.sourceforge.io/ |
|
||||
| duckdb | 1.4.4 | MIT License | https://github.com/duckdb/duckdb-python |
|
||||
| executing | 2.2.1 | MIT License | https://github.com/alexmojaki/executing |
|
||||
| fastavro | 1.12.1 | MIT | https://github.com/fastavro/fastavro |
|
||||
| fastjsonschema | 2.21.2 | BSD License | https://github.com/horejsek/python-fastjsonschema |
|
||||
| filelock | 3.20.3 | Unlicense | https://github.com/tox-dev/py-filelock |
|
||||
| frozenlist | 1.8.0 | Apache-2.0 | https://github.com/aio-libs/frozenlist |
|
||||
| fsspec | 2026.2.0 | BSD-3-Clause | https://github.com/fsspec/filesystem_spec |
|
||||
| ftfy | 6.3.1 | Apache-2.0 | https://ftfy.readthedocs.io/en/latest/ |
|
||||
| ghp-import | 2.1.0 | Apache Software License | https://github.com/c-w/ghp-import |
|
||||
| google-ai-generativelanguage | 0.6.15 | Apache Software License | https://github.com/googleapis/google-cloud-python/tree/main/packages/google-ai-generativelanguage |
|
||||
| google-api-core | 2.25.2 | Apache Software License | https://github.com/googleapis/python-api-core |
|
||||
| google-api-python-client | 2.189.0 | Apache Software License | https://github.com/googleapis/google-api-python-client/ |
|
||||
| google-auth | 2.48.0 | Apache Software License | https://github.com/googleapis/google-auth-library-python |
|
||||
| google-auth-httplib2 | 0.3.0 | Apache Software License | https://github.com/GoogleCloudPlatform/google-auth-library-python-httplib2 |
|
||||
| google-generativeai | 0.8.6 | Apache Software License | https://github.com/google/generative-ai-python |
|
||||
| googleapis-common-protos | 1.72.0 | Apache Software License | https://github.com/googleapis/google-cloud-python/tree/main/packages/googleapis-common-protos |
|
||||
| griffe | 2.0.0 | ISC | https://mkdocstrings.github.io/griffe |
|
||||
| griffecli | 2.0.0 | ISC | UNKNOWN |
|
||||
| griffelib | 2.0.0 | ISC | UNKNOWN |
|
||||
| grpcio | 1.78.0 | Apache-2.0 | https://grpc.io |
|
||||
| grpcio-status | 1.71.2 | Apache Software License | https://grpc.io |
|
||||
| h11 | 0.16.0 | MIT License | https://github.com/python-hyper/h11 |
|
||||
| hf-xet | 1.2.0 | Apache-2.0 | https://github.com/huggingface/xet-core |
|
||||
| httpcore | 1.0.9 | BSD-3-Clause | https://www.encode.io/httpcore/ |
|
||||
| httplib2 | 0.31.2 | MIT License | https://github.com/httplib2/httplib2 |
|
||||
| httpx | 0.28.1 | BSD License | https://github.com/encode/httpx |
|
||||
| huggingface_hub | 0.36.2 | Apache Software License | https://github.com/huggingface/huggingface_hub |
|
||||
| ibm-cos-sdk | 2.14.3 | Apache Software License | https://github.com/ibm/ibm-cos-sdk-python |
|
||||
| ibm-cos-sdk-core | 2.14.3 | Apache Software License | https://github.com/ibm/ibm-cos-sdk-python-core |
|
||||
| ibm-cos-sdk-s3transfer | 2.14.3 | Apache Software License | https://github.com/IBM/ibm-cos-sdk-python-s3transfer |
|
||||
| ibm_watsonx_ai | 1.5.1 | BSD License | https://ibm.github.io/watsonx-ai-python-sdk/changelog.html |
|
||||
| identify | 2.6.16 | MIT | https://github.com/pre-commit/identify |
|
||||
| idna | 3.11 | BSD-3-Clause | https://github.com/kjd/idna |
|
||||
| iniconfig | 2.3.0 | MIT | https://github.com/pytest-dev/iniconfig |
|
||||
| ipykernel | 6.31.0 | BSD-3-Clause | https://ipython.org |
|
||||
| ipython | 9.10.0 | BSD-3-Clause | https://ipython.org |
|
||||
| ipython_pygments_lexers | 1.1.1 | BSD License | https://github.com/ipython/ipython-pygments-lexers |
|
||||
| isodate | 0.7.2 | BSD License | https://github.com/gweis/isodate/ |
|
||||
| jedi | 0.19.2 | MIT License | https://github.com/davidhalter/jedi |
|
||||
| jiter | 0.13.0 | MIT License | https://github.com/pydantic/jiter/ |
|
||||
| jmespath | 1.0.1 | MIT License | https://github.com/jmespath/jmespath.py |
|
||||
| joblib | 1.5.3 | BSD-3-Clause | https://joblib.readthedocs.io |
|
||||
| jsonschema | 4.26.0 | MIT | https://github.com/python-jsonschema/jsonschema |
|
||||
| jsonschema-specifications | 2025.9.1 | MIT | https://github.com/python-jsonschema/jsonschema-specifications |
|
||||
| jupyter_client | 8.8.0 | BSD License | https://jupyter.org |
|
||||
| jupyter_core | 5.9.1 | BSD-3-Clause | https://jupyter.org |
|
||||
| jupyterlab_pygments | 0.3.0 | BSD License | https://github.com/jupyterlab/jupyterlab_pygments |
|
||||
| jupytext | 1.19.1 | MIT License | https://github.com/mwouts/jupytext |
|
||||
| lance-namespace | 0.4.5 | Apache-2.0 | https://github.com/lance-format/lance-namespace |
|
||||
| lance-namespace-urllib3-client | 0.4.5 | Apache-2.0 | https://github.com/lance-format/lance-namespace |
|
||||
| lancedb | 0.29.2 | Apache Software License | https://github.com/lancedb/lancedb |
|
||||
| lomond | 0.3.3 | BSD License | https://github.com/wildfoundry/dataplicity-lomond |
|
||||
| markdown-it-py | 4.0.0 | MIT License | https://github.com/executablebooks/markdown-it-py |
|
||||
| matplotlib-inline | 0.2.1 | UNKNOWN | https://github.com/ipython/matplotlib-inline |
|
||||
| mdit-py-plugins | 0.5.0 | MIT License | https://github.com/executablebooks/mdit-py-plugins |
|
||||
| mdurl | 0.1.2 | MIT License | https://github.com/executablebooks/mdurl |
|
||||
| mergedeep | 1.3.4 | MIT License | https://github.com/clarketm/mergedeep |
|
||||
| mistune | 3.2.0 | BSD License | https://github.com/lepture/mistune |
|
||||
| mkdocs | 1.6.1 | BSD-2-Clause | https://github.com/mkdocs/mkdocs |
|
||||
| mkdocs-autorefs | 1.4.3 | ISC | https://mkdocstrings.github.io/autorefs |
|
||||
| mkdocs-get-deps | 0.2.0 | MIT | https://github.com/mkdocs/get-deps |
|
||||
| mkdocs-jupyter | 0.25.1 | Apache-2.0 | https://github.com/danielfrg/mkdocs-jupyter |
|
||||
| mkdocs-material | 9.7.1 | MIT | https://github.com/squidfunk/mkdocs-material |
|
||||
| mkdocs-material-extensions | 1.3.1 | MIT | https://github.com/facelessuser/mkdocs-material-extensions |
|
||||
| mkdocstrings | 1.0.3 | ISC | https://mkdocstrings.github.io |
|
||||
| mkdocstrings-python | 2.0.2 | ISC | https://mkdocstrings.github.io/python |
|
||||
| mpmath | 1.3.0 | BSD License | http://mpmath.org/ |
|
||||
| msal | 1.34.0 | MIT License | https://github.com/AzureAD/microsoft-authentication-library-for-python |
|
||||
| msal-extensions | 1.3.1 | MIT License | https://github.com/AzureAD/microsoft-authentication-extensions-for-python/releases |
|
||||
| multidict | 6.7.1 | Apache License 2.0 | https://github.com/aio-libs/multidict |
|
||||
| nbclient | 0.10.4 | BSD License | https://jupyter.org |
|
||||
| nbconvert | 7.17.0 | BSD License | https://jupyter.org |
|
||||
| nbformat | 5.10.4 | BSD License | https://jupyter.org |
|
||||
| nest-asyncio | 1.6.0 | BSD License | https://github.com/erdewit/nest_asyncio |
|
||||
| networkx | 3.6.1 | BSD-3-Clause | https://networkx.org/ |
|
||||
| nodeenv | 1.10.0 | BSD License | https://github.com/ekalinin/nodeenv |
|
||||
| numpy | 2.4.2 | BSD-3-Clause AND 0BSD AND MIT AND Zlib AND CC0-1.0 | https://numpy.org |
|
||||
| ollama | 0.6.1 | MIT | https://ollama.com |
|
||||
| open_clip_torch | 3.2.0 | MIT License | https://github.com/mlfoundations/open_clip |
|
||||
| openai | 2.18.0 | Apache Software License | https://github.com/openai/openai-python |
|
||||
| packaging | 26.0 | Apache-2.0 OR BSD-2-Clause | https://github.com/pypa/packaging |
|
||||
| paginate | 0.5.7 | MIT License | https://github.com/Signum/paginate |
|
||||
| pandas | 2.3.3 | BSD License | https://pandas.pydata.org |
|
||||
| pandocfilters | 1.5.1 | BSD License | http://github.com/jgm/pandocfilters |
|
||||
| parso | 0.8.6 | MIT License | https://github.com/davidhalter/parso |
|
||||
| pathspec | 1.0.4 | Mozilla Public License 2.0 (MPL 2.0) | UNKNOWN |
|
||||
| peft | 0.17.1 | Apache Software License | https://github.com/huggingface/peft |
|
||||
| pexpect | 4.9.0 | ISC License (ISCL) | https://pexpect.readthedocs.io/ |
|
||||
| pillow | 12.1.0 | MIT-CMU | https://python-pillow.github.io |
|
||||
| platformdirs | 4.5.1 | MIT | https://github.com/tox-dev/platformdirs |
|
||||
| pluggy | 1.6.0 | MIT License | UNKNOWN |
|
||||
| polars | 1.3.0 | MIT License | https://www.pola.rs/ |
|
||||
| pre_commit | 4.5.1 | MIT | https://github.com/pre-commit/pre-commit |
|
||||
| prompt_toolkit | 3.0.52 | BSD License | https://github.com/prompt-toolkit/python-prompt-toolkit |
|
||||
| propcache | 0.4.1 | Apache Software License | https://github.com/aio-libs/propcache |
|
||||
| proto-plus | 1.27.1 | Apache Software License | https://github.com/googleapis/proto-plus-python |
|
||||
| protobuf | 5.29.6 | 3-Clause BSD License | https://developers.google.com/protocol-buffers/ |
|
||||
| psutil | 7.2.2 | BSD-3-Clause | https://github.com/giampaolo/psutil |
|
||||
| ptyprocess | 0.7.0 | ISC License (ISCL) | https://github.com/pexpect/ptyprocess |
|
||||
| pure_eval | 0.2.3 | MIT License | http://github.com/alexmojaki/pure_eval |
|
||||
| pyarrow | 23.0.0 | Apache-2.0 | https://arrow.apache.org/ |
|
||||
| pyarrow-stubs | 20.0.0.20251215 | BSD-2-Clause | https://github.com/zen-xu/pyarrow-stubs |
|
||||
| pyasn1 | 0.6.2 | BSD-2-Clause | https://github.com/pyasn1/pyasn1 |
|
||||
| pyasn1_modules | 0.4.2 | BSD License | https://github.com/pyasn1/pyasn1-modules |
|
||||
| pycparser | 3.0 | BSD-3-Clause | https://github.com/eliben/pycparser |
|
||||
| pydantic | 2.12.5 | MIT | https://github.com/pydantic/pydantic |
|
||||
| pydantic_core | 2.41.5 | MIT | https://github.com/pydantic/pydantic-core |
|
||||
| pylance | 2.0.0 | Apache Software License | UNKNOWN |
|
||||
| pymdown-extensions | 10.20.1 | MIT | https://github.com/facelessuser/pymdown-extensions |
|
||||
| pyparsing | 3.3.2 | MIT | https://github.com/pyparsing/pyparsing/ |
|
||||
| pyright | 1.1.408 | MIT | https://github.com/RobertCraigie/pyright-python |
|
||||
| pytest | 9.0.2 | MIT | https://docs.pytest.org/en/latest/ |
|
||||
| pytest-asyncio | 1.3.0 | Apache-2.0 | https://github.com/pytest-dev/pytest-asyncio |
|
||||
| pytest-mock | 3.15.1 | MIT License | https://github.com/pytest-dev/pytest-mock/ |
|
||||
| python-dateutil | 2.9.0.post0 | Apache Software License; BSD License | https://github.com/dateutil/dateutil |
|
||||
| pytz | 2025.2 | MIT License | http://pythonhosted.org/pytz |
|
||||
| pyyaml_env_tag | 1.1 | MIT | https://github.com/waylan/pyyaml-env-tag |
|
||||
| pyzmq | 27.1.0 | BSD License | https://pyzmq.readthedocs.org |
|
||||
| referencing | 0.37.0 | MIT | https://github.com/python-jsonschema/referencing |
|
||||
| regex | 2026.1.15 | Apache-2.0 AND CNRI-Python | https://github.com/mrabarnett/mrab-regex |
|
||||
| requests | 2.32.5 | Apache Software License | https://requests.readthedocs.io |
|
||||
| rpds-py | 0.30.0 | MIT | https://github.com/crate-py/rpds |
|
||||
| rsa | 4.7.2 | Apache Software License | https://stuvel.eu/rsa |
|
||||
| ruff | 0.15.0 | MIT License | https://docs.astral.sh/ruff |
|
||||
| s3transfer | 0.16.0 | Apache Software License | https://github.com/boto/s3transfer |
|
||||
| safetensors | 0.7.0 | Apache Software License | https://github.com/huggingface/safetensors |
|
||||
| scikit-learn | 1.8.0 | BSD-3-Clause | https://scikit-learn.org |
|
||||
| scipy | 1.17.0 | BSD License | https://scipy.org/ |
|
||||
| sentence-transformers | 5.2.2 | Apache Software License | https://www.SBERT.net |
|
||||
| sentencepiece | 0.2.1 | UNKNOWN | https://github.com/google/sentencepiece |
|
||||
| six | 1.17.0 | MIT License | https://github.com/benjaminp/six |
|
||||
| sniffio | 1.3.1 | Apache Software License; MIT License | https://github.com/python-trio/sniffio |
|
||||
| soupsieve | 2.8.3 | MIT | https://github.com/facelessuser/soupsieve |
|
||||
| stack-data | 0.6.3 | MIT License | http://github.com/alexmojaki/stack_data |
|
||||
| sympy | 1.14.0 | BSD License | https://sympy.org |
|
||||
| tabulate | 0.9.0 | MIT License | https://github.com/astanin/python-tabulate |
|
||||
| tantivy | 0.25.1 | UNKNOWN | UNKNOWN |
|
||||
| threadpoolctl | 3.6.0 | BSD License | https://github.com/joblib/threadpoolctl |
|
||||
| timm | 1.0.24 | Apache Software License | https://github.com/huggingface/pytorch-image-models |
|
||||
| tinycss2 | 1.4.0 | BSD License | https://www.courtbouillon.org/tinycss2 |
|
||||
| tokenizers | 0.22.2 | Apache Software License | https://github.com/huggingface/tokenizers |
|
||||
| torch | 2.8.0 | BSD License | https://pytorch.org/ |
|
||||
| torchvision | 0.23.0 | BSD | https://github.com/pytorch/vision |
|
||||
| tornado | 6.5.4 | Apache Software License | http://www.tornadoweb.org/ |
|
||||
| tqdm | 4.67.3 | MPL-2.0 AND MIT | https://tqdm.github.io |
|
||||
| traitlets | 5.14.3 | BSD License | https://github.com/ipython/traitlets |
|
||||
| transformers | 4.57.6 | Apache Software License | https://github.com/huggingface/transformers |
|
||||
| types-requests | 2.32.4.20260107 | Apache-2.0 | https://github.com/python/typeshed |
|
||||
| typing-inspection | 0.4.2 | MIT | https://github.com/pydantic/typing-inspection |
|
||||
| typing_extensions | 4.15.0 | PSF-2.0 | https://github.com/python/typing_extensions |
|
||||
| tzdata | 2025.3 | Apache-2.0 | https://github.com/python/tzdata |
|
||||
| uritemplate | 4.2.0 | BSD 3-Clause OR Apache-2.0 | https://uritemplate.readthedocs.org |
|
||||
| urllib3 | 2.6.3 | MIT | https://github.com/urllib3/urllib3/blob/main/CHANGES.rst |
|
||||
| virtualenv | 20.36.1 | MIT | https://github.com/pypa/virtualenv |
|
||||
| watchdog | 6.0.0 | Apache Software License | https://github.com/gorakhargosh/watchdog |
|
||||
| webencodings | 0.5.1 | BSD License | https://github.com/SimonSapin/python-webencodings |
|
||||
| yarl | 1.22.0 | Apache Software License | https://github.com/aio-libs/yarl |
|
||||
File diff suppressed because it is too large
Load Diff
@@ -59,9 +59,9 @@ tests = [
|
||||
"polars>=0.19, <=1.3.0",
|
||||
"tantivy",
|
||||
"pyarrow-stubs",
|
||||
"pylance>=1.0.0b14",
|
||||
"pylance>=1.0.0b14,<3.0.0",
|
||||
"requests",
|
||||
"datafusion",
|
||||
"datafusion<52",
|
||||
]
|
||||
dev = [
|
||||
"ruff",
|
||||
|
||||
@@ -180,6 +180,8 @@ class Table:
|
||||
delete_unverified: Optional[bool] = None,
|
||||
) -> OptimizeStats: ...
|
||||
async def uri(self) -> str: ...
|
||||
async def initial_storage_options(self) -> Optional[Dict[str, str]]: ...
|
||||
async def latest_storage_options(self) -> Optional[Dict[str, str]]: ...
|
||||
@property
|
||||
def tags(self) -> Tags: ...
|
||||
def query(self) -> Query: ...
|
||||
|
||||
@@ -1,8 +1,10 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
|
||||
from functools import singledispatch
|
||||
from typing import List, Optional, Tuple, Union
|
||||
|
||||
from lancedb.pydantic import LanceModel, model_to_dict
|
||||
import pyarrow as pa
|
||||
|
||||
from ._lancedb import RecordBatchStream
|
||||
@@ -80,3 +82,32 @@ def peek_reader(
|
||||
yield from reader
|
||||
|
||||
return batch, pa.RecordBatchReader.from_batches(batch.schema, all_batches())
|
||||
|
||||
|
||||
@singledispatch
|
||||
def to_arrow(data) -> pa.Table:
|
||||
"""Convert a single data object to a pa.Table."""
|
||||
raise NotImplementedError(f"to_arrow not implemented for type {type(data)}")
|
||||
|
||||
|
||||
@to_arrow.register(pa.RecordBatch)
|
||||
def _arrow_from_batch(data: pa.RecordBatch) -> pa.Table:
|
||||
return pa.Table.from_batches([data])
|
||||
|
||||
|
||||
@to_arrow.register(pa.Table)
|
||||
def _arrow_from_table(data: pa.Table) -> pa.Table:
|
||||
return data
|
||||
|
||||
|
||||
@to_arrow.register(list)
|
||||
def _arrow_from_list(data: list) -> pa.Table:
|
||||
if not data:
|
||||
raise ValueError("Cannot create table from empty list without a schema")
|
||||
|
||||
if isinstance(data[0], LanceModel):
|
||||
schema = data[0].__class__.to_arrow_schema()
|
||||
dicts = [model_to_dict(d) for d in data]
|
||||
return pa.Table.from_pylist(dicts, schema=schema)
|
||||
|
||||
return pa.Table.from_pylist(data)
|
||||
|
||||
@@ -2,6 +2,7 @@
|
||||
# SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
|
||||
|
||||
import warnings
|
||||
from typing import List, Union
|
||||
|
||||
import numpy as np
|
||||
@@ -15,6 +16,8 @@ from .utils import weak_lru
|
||||
@register("gte-text")
|
||||
class GteEmbeddings(TextEmbeddingFunction):
|
||||
"""
|
||||
Deprecated: GTE embeddings should be used through sentence-transformers.
|
||||
|
||||
An embedding function that uses GTE-LARGE MLX format(for Apple silicon devices only)
|
||||
as well as the standard cpu/gpu version from: https://huggingface.co/thenlper/gte-large.
|
||||
|
||||
@@ -61,6 +64,13 @@ class GteEmbeddings(TextEmbeddingFunction):
|
||||
|
||||
def __init__(self, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
warnings.warn(
|
||||
"GTE embeddings as a standalone embedding function are deprecated. "
|
||||
"Use the 'sentence-transformers' embedding function with a GTE model "
|
||||
"instead.",
|
||||
DeprecationWarning,
|
||||
stacklevel=3,
|
||||
)
|
||||
self._ndims = None
|
||||
if kwargs:
|
||||
self.mlx = kwargs.get("mlx", False)
|
||||
|
||||
@@ -110,6 +110,9 @@ class OpenAIEmbeddings(TextEmbeddingFunction):
|
||||
valid_embeddings = {
|
||||
idx: v.embedding for v, idx in zip(rs.data, valid_indices)
|
||||
}
|
||||
except openai.AuthenticationError:
|
||||
logging.error("Authentication failed: Invalid API key provided")
|
||||
raise
|
||||
except openai.BadRequestError:
|
||||
logging.exception("Bad request: %s", texts)
|
||||
return [None] * len(texts)
|
||||
|
||||
@@ -6,6 +6,7 @@ import io
|
||||
import os
|
||||
from typing import TYPE_CHECKING, List, Union
|
||||
import urllib.parse as urlparse
|
||||
import warnings
|
||||
|
||||
import numpy as np
|
||||
import pyarrow as pa
|
||||
@@ -24,6 +25,7 @@ if TYPE_CHECKING:
|
||||
|
||||
@register("siglip")
|
||||
class SigLipEmbeddings(EmbeddingFunction):
|
||||
# Deprecated: prefer CLIP embeddings via `open-clip`.
|
||||
model_name: str = "google/siglip-base-patch16-224"
|
||||
device: str = "cpu"
|
||||
batch_size: int = 64
|
||||
@@ -36,6 +38,12 @@ class SigLipEmbeddings(EmbeddingFunction):
|
||||
|
||||
def __init__(self, *args, **kwargs):
|
||||
super().__init__(*args, **kwargs)
|
||||
warnings.warn(
|
||||
"SigLip embeddings are deprecated. Use CLIP embeddings via the "
|
||||
"'open-clip' embedding function instead.",
|
||||
DeprecationWarning,
|
||||
stacklevel=3,
|
||||
)
|
||||
transformers = attempt_import_or_raise("transformers")
|
||||
self._torch = attempt_import_or_raise("torch")
|
||||
|
||||
|
||||
@@ -269,6 +269,11 @@ def retry_with_exponential_backoff(
|
||||
# and say that it is assumed that if this portion errors out, it's due
|
||||
# to rate limit but the user should check the error message to be sure.
|
||||
except Exception as e: # noqa: PERF203
|
||||
# Don't retry on authentication errors (e.g., OpenAI 401)
|
||||
# These are permanent failures that won't be fixed by retrying
|
||||
if _is_non_retryable_error(e):
|
||||
raise
|
||||
|
||||
num_retries += 1
|
||||
|
||||
if num_retries > max_retries:
|
||||
@@ -289,6 +294,29 @@ def retry_with_exponential_backoff(
|
||||
return wrapper
|
||||
|
||||
|
||||
def _is_non_retryable_error(error: Exception) -> bool:
|
||||
"""Check if an error should not be retried.
|
||||
|
||||
Args:
|
||||
error: The exception to check
|
||||
|
||||
Returns:
|
||||
True if the error should not be retried, False otherwise
|
||||
"""
|
||||
# Check for OpenAI authentication errors
|
||||
error_type = type(error).__name__
|
||||
if error_type == "AuthenticationError":
|
||||
return True
|
||||
|
||||
# Check for other common non-retryable HTTP status codes
|
||||
# 401 Unauthorized, 403 Forbidden
|
||||
if hasattr(error, "status_code"):
|
||||
if error.status_code in (401, 403):
|
||||
return True
|
||||
|
||||
return False
|
||||
|
||||
|
||||
def url_retrieve(url: str):
|
||||
"""
|
||||
Parameters
|
||||
|
||||
@@ -44,7 +44,7 @@ from lance_namespace import (
|
||||
ListNamespacesRequest,
|
||||
CreateNamespaceRequest,
|
||||
DropNamespaceRequest,
|
||||
CreateEmptyTableRequest,
|
||||
DeclareTableRequest,
|
||||
)
|
||||
from lancedb.table import AsyncTable, LanceTable, Table
|
||||
from lancedb.util import validate_table_name
|
||||
@@ -318,20 +318,20 @@ class LanceNamespaceDBConnection(DBConnection):
|
||||
|
||||
if location is None:
|
||||
# Table doesn't exist or mode is "create", reserve a new location
|
||||
create_empty_request = CreateEmptyTableRequest(
|
||||
declare_request = DeclareTableRequest(
|
||||
id=table_id,
|
||||
location=None,
|
||||
properties=self.storage_options if self.storage_options else None,
|
||||
)
|
||||
create_empty_response = self._ns.create_empty_table(create_empty_request)
|
||||
declare_response = self._ns.declare_table(declare_request)
|
||||
|
||||
if not create_empty_response.location:
|
||||
if not declare_response.location:
|
||||
raise ValueError(
|
||||
"Table location is missing from create_empty_table response"
|
||||
"Table location is missing from declare_table response"
|
||||
)
|
||||
|
||||
location = create_empty_response.location
|
||||
namespace_storage_options = create_empty_response.storage_options
|
||||
location = declare_response.location
|
||||
namespace_storage_options = declare_response.storage_options
|
||||
|
||||
# Merge storage options: self.storage_options < user options < namespace options
|
||||
merged_storage_options = dict(self.storage_options)
|
||||
@@ -759,20 +759,20 @@ class AsyncLanceNamespaceDBConnection:
|
||||
|
||||
if location is None:
|
||||
# Table doesn't exist or mode is "create", reserve a new location
|
||||
create_empty_request = CreateEmptyTableRequest(
|
||||
declare_request = DeclareTableRequest(
|
||||
id=table_id,
|
||||
location=None,
|
||||
properties=self.storage_options if self.storage_options else None,
|
||||
)
|
||||
create_empty_response = self._ns.create_empty_table(create_empty_request)
|
||||
declare_response = self._ns.declare_table(declare_request)
|
||||
|
||||
if not create_empty_response.location:
|
||||
if not declare_response.location:
|
||||
raise ValueError(
|
||||
"Table location is missing from create_empty_table response"
|
||||
"Table location is missing from declare_table response"
|
||||
)
|
||||
|
||||
location = create_empty_response.location
|
||||
namespace_storage_options = create_empty_response.storage_options
|
||||
location = declare_response.location
|
||||
namespace_storage_options = declare_response.storage_options
|
||||
|
||||
# Merge storage options: self.storage_options < user options < namespace options
|
||||
merged_storage_options = dict(self.storage_options)
|
||||
|
||||
@@ -9,7 +9,7 @@ import json
|
||||
from ._lancedb import async_permutation_builder, PermutationReader
|
||||
from .table import LanceTable
|
||||
from .background_loop import LOOP
|
||||
from .util import batch_to_tensor
|
||||
from .util import batch_to_tensor, batch_to_tensor_rows
|
||||
from typing import Any, Callable, Iterator, Literal, Optional, TYPE_CHECKING, Union
|
||||
|
||||
if TYPE_CHECKING:
|
||||
@@ -333,7 +333,11 @@ class Transforms:
|
||||
"""
|
||||
|
||||
@staticmethod
|
||||
def arrow2python(batch: pa.RecordBatch) -> dict[str, list[Any]]:
|
||||
def arrow2python(batch: pa.RecordBatch) -> list[dict[str, Any]]:
|
||||
return batch.to_pylist()
|
||||
|
||||
@staticmethod
|
||||
def arrow2pythoncol(batch: pa.RecordBatch) -> dict[str, list[Any]]:
|
||||
return batch.to_pydict()
|
||||
|
||||
@staticmethod
|
||||
@@ -687,7 +691,17 @@ class Permutation:
|
||||
return
|
||||
|
||||
def with_format(
|
||||
self, format: Literal["numpy", "python", "pandas", "arrow", "torch", "polars"]
|
||||
self,
|
||||
format: Literal[
|
||||
"numpy",
|
||||
"python",
|
||||
"python_col",
|
||||
"pandas",
|
||||
"arrow",
|
||||
"torch",
|
||||
"torch_col",
|
||||
"polars",
|
||||
],
|
||||
) -> "Permutation":
|
||||
"""
|
||||
Set the format for batches
|
||||
@@ -696,16 +710,18 @@ class Permutation:
|
||||
|
||||
The format can be one of:
|
||||
- "numpy" - the batch will be a dict of numpy arrays (one per column)
|
||||
- "python" - the batch will be a dict of lists (one per column)
|
||||
- "python" - the batch will be a list of dicts (one per row)
|
||||
- "python_col" - the batch will be a dict of lists (one entry per column)
|
||||
- "pandas" - the batch will be a pandas DataFrame
|
||||
- "arrow" - the batch will be a pyarrow RecordBatch
|
||||
- "torch" - the batch will be a two dimensional torch tensor
|
||||
- "torch" - the batch will be a list of tensors, one per row
|
||||
- "torch_col" - the batch will be a 2D torch tensor (first dim indexes columns)
|
||||
- "polars" - the batch will be a polars DataFrame
|
||||
|
||||
Conversion may or may not involve a data copy. Lance uses Arrow internally
|
||||
and so it is able to zero-copy to the arrow and polars.
|
||||
and so it is able to zero-copy to the arrow and polars formats.
|
||||
|
||||
Conversion to torch will be zero-copy but will only support a subset of data
|
||||
Conversion to torch_col will be zero-copy but will only support a subset of data
|
||||
types (numeric types).
|
||||
|
||||
Conversion to numpy and/or pandas will typically be zero-copy for numeric
|
||||
@@ -718,6 +734,8 @@ class Permutation:
|
||||
assert format is not None, "format is required"
|
||||
if format == "python":
|
||||
return self.with_transform(Transforms.arrow2python)
|
||||
if format == "python_col":
|
||||
return self.with_transform(Transforms.arrow2pythoncol)
|
||||
elif format == "numpy":
|
||||
return self.with_transform(Transforms.arrow2numpy)
|
||||
elif format == "pandas":
|
||||
@@ -725,6 +743,8 @@ class Permutation:
|
||||
elif format == "arrow":
|
||||
return self.with_transform(Transforms.arrow2arrow)
|
||||
elif format == "torch":
|
||||
return self.with_transform(batch_to_tensor_rows)
|
||||
elif format == "torch_col":
|
||||
return self.with_transform(batch_to_tensor)
|
||||
elif format == "polars":
|
||||
return self.with_transform(Transforms.arrow2polars())
|
||||
@@ -746,15 +766,20 @@ class Permutation:
|
||||
|
||||
def __getitem__(self, index: int) -> Any:
|
||||
"""
|
||||
Return a single row from the permutation
|
||||
|
||||
The output will always be a python dictionary regardless of the format.
|
||||
|
||||
This method is mostly useful for debugging and exploration. For actual
|
||||
processing use [iter](#iter) or a torch data loader to perform batched
|
||||
processing.
|
||||
Returns a single row from the permutation by offset
|
||||
"""
|
||||
pass
|
||||
return self.__getitems__([index])
|
||||
|
||||
def __getitems__(self, indices: list[int]) -> Any:
|
||||
"""
|
||||
Returns rows from the permutation by offset
|
||||
"""
|
||||
|
||||
async def do_getitems():
|
||||
return await self.reader.take_offsets(indices, selection=self.selection)
|
||||
|
||||
batch = LOOP.run(do_getitems())
|
||||
return self.transform_fn(batch)
|
||||
|
||||
@deprecated(details="Use with_skip instead")
|
||||
def skip(self, skip: int) -> "Permutation":
|
||||
|
||||
@@ -606,6 +606,7 @@ class LanceQueryBuilder(ABC):
|
||||
query,
|
||||
ordering_field_name=ordering_field_name,
|
||||
fts_columns=fts_columns,
|
||||
fast_search=fast_search,
|
||||
)
|
||||
|
||||
if isinstance(query, list):
|
||||
@@ -1456,12 +1457,14 @@ class LanceFtsQueryBuilder(LanceQueryBuilder):
|
||||
query: str | FullTextQuery,
|
||||
ordering_field_name: Optional[str] = None,
|
||||
fts_columns: Optional[Union[str, List[str]]] = None,
|
||||
fast_search: bool = None,
|
||||
):
|
||||
super().__init__(table)
|
||||
self._query = query
|
||||
self._phrase_query = False
|
||||
self.ordering_field_name = ordering_field_name
|
||||
self._reranker = None
|
||||
self._fast_search = fast_search
|
||||
if isinstance(fts_columns, str):
|
||||
fts_columns = [fts_columns]
|
||||
self._fts_columns = fts_columns
|
||||
@@ -1483,6 +1486,19 @@ class LanceFtsQueryBuilder(LanceQueryBuilder):
|
||||
self._phrase_query = phrase_query
|
||||
return self
|
||||
|
||||
def fast_search(self) -> LanceFtsQueryBuilder:
|
||||
"""
|
||||
Skip a flat search of unindexed data. This will improve
|
||||
search performance but search results will not include unindexed data.
|
||||
|
||||
Returns
|
||||
-------
|
||||
LanceFtsQueryBuilder
|
||||
The LanceFtsQueryBuilder object.
|
||||
"""
|
||||
self._fast_search = True
|
||||
return self
|
||||
|
||||
def to_query_object(self) -> Query:
|
||||
return Query(
|
||||
columns=self._columns,
|
||||
@@ -1494,6 +1510,7 @@ class LanceFtsQueryBuilder(LanceQueryBuilder):
|
||||
query=self._query, columns=self._fts_columns
|
||||
),
|
||||
offset=self._offset,
|
||||
fast_search=self._fast_search,
|
||||
)
|
||||
|
||||
def output_schema(self) -> pa.Schema:
|
||||
@@ -1782,6 +1799,26 @@ class LanceHybridQueryBuilder(LanceQueryBuilder):
|
||||
vector_results = LanceHybridQueryBuilder._rank(vector_results, "_distance")
|
||||
fts_results = LanceHybridQueryBuilder._rank(fts_results, "_score")
|
||||
|
||||
# If both result sets are empty (e.g. after hard filtering),
|
||||
# return early to avoid errors in reranking or score restoration.
|
||||
if vector_results.num_rows == 0 and fts_results.num_rows == 0:
|
||||
# Build a minimal empty table with the _relevance_score column
|
||||
combined_schema = pa.unify_schemas(
|
||||
[vector_results.schema, fts_results.schema],
|
||||
)
|
||||
empty = pa.table(
|
||||
{
|
||||
col: pa.array([], type=combined_schema.field(col).type)
|
||||
for col in combined_schema.names
|
||||
}
|
||||
)
|
||||
empty = empty.append_column(
|
||||
"_relevance_score", pa.array([], type=pa.float32())
|
||||
)
|
||||
if not with_row_ids and "_rowid" in empty.column_names:
|
||||
empty = empty.drop(["_rowid"])
|
||||
return empty
|
||||
|
||||
original_distances = None
|
||||
original_scores = None
|
||||
original_distance_row_ids = None
|
||||
@@ -2118,19 +2155,17 @@ class LanceHybridQueryBuilder(LanceQueryBuilder):
|
||||
""" # noqa: E501
|
||||
self._create_query_builders()
|
||||
|
||||
results = ["Vector Search Plan:"]
|
||||
results.append(
|
||||
self._table._explain_plan(
|
||||
self._vector_query.to_query_object(), verbose=verbose
|
||||
)
|
||||
reranker_label = str(self._reranker) if self._reranker else "No reranker"
|
||||
vector_plan = self._table._explain_plan(
|
||||
self._vector_query.to_query_object(), verbose=verbose
|
||||
)
|
||||
results.append("FTS Search Plan:")
|
||||
results.append(
|
||||
self._table._explain_plan(
|
||||
self._fts_query.to_query_object(), verbose=verbose
|
||||
)
|
||||
fts_plan = self._table._explain_plan(
|
||||
self._fts_query.to_query_object(), verbose=verbose
|
||||
)
|
||||
return "\n".join(results)
|
||||
# Indent sub-plans under the reranker
|
||||
indented_vector = "\n".join(" " + line for line in vector_plan.splitlines())
|
||||
indented_fts = "\n".join(" " + line for line in fts_plan.splitlines())
|
||||
return f"{reranker_label}\n {indented_vector}\n {indented_fts}"
|
||||
|
||||
def analyze_plan(self):
|
||||
"""Execute the query and display with runtime metrics.
|
||||
@@ -3164,23 +3199,20 @@ class AsyncHybridQuery(AsyncStandardQuery, AsyncVectorQueryBase):
|
||||
... plan = await table.query().nearest_to([1.0, 2.0]).nearest_to_text("hello").explain_plan(True)
|
||||
... print(plan)
|
||||
>>> asyncio.run(doctest_example()) # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
|
||||
Vector Search Plan:
|
||||
ProjectionExec: expr=[vector@0 as vector, text@3 as text, _distance@2 as _distance]
|
||||
Take: columns="vector, _rowid, _distance, (text)"
|
||||
CoalesceBatchesExec: target_batch_size=1024
|
||||
GlobalLimitExec: skip=0, fetch=10
|
||||
FilterExec: _distance@2 IS NOT NULL
|
||||
SortExec: TopK(fetch=10), expr=[_distance@2 ASC NULLS LAST, _rowid@1 ASC NULLS LAST], preserve_partitioning=[false]
|
||||
KNNVectorDistance: metric=l2
|
||||
LanceRead: uri=..., projection=[vector], ...
|
||||
<BLANKLINE>
|
||||
FTS Search Plan:
|
||||
ProjectionExec: expr=[vector@2 as vector, text@3 as text, _score@1 as _score]
|
||||
Take: columns="_rowid, _score, (vector), (text)"
|
||||
CoalesceBatchesExec: target_batch_size=1024
|
||||
GlobalLimitExec: skip=0, fetch=10
|
||||
MatchQuery: column=text, query=hello
|
||||
<BLANKLINE>
|
||||
RRFReranker(K=60)
|
||||
ProjectionExec: expr=[vector@0 as vector, text@3 as text, _distance@2 as _distance]
|
||||
Take: columns="vector, _rowid, _distance, (text)"
|
||||
CoalesceBatchesExec: target_batch_size=1024
|
||||
GlobalLimitExec: skip=0, fetch=10
|
||||
FilterExec: _distance@2 IS NOT NULL
|
||||
SortExec: TopK(fetch=10), expr=[_distance@2 ASC NULLS LAST, _rowid@1 ASC NULLS LAST], preserve_partitioning=[false]
|
||||
KNNVectorDistance: metric=l2
|
||||
LanceRead: uri=..., projection=[vector], ...
|
||||
ProjectionExec: expr=[vector@2 as vector, text@3 as text, _score@1 as _score]
|
||||
Take: columns="_rowid, _score, (vector), (text)"
|
||||
CoalesceBatchesExec: target_batch_size=1024
|
||||
GlobalLimitExec: skip=0, fetch=10
|
||||
MatchQuery: column=text, query=hello
|
||||
|
||||
Parameters
|
||||
----------
|
||||
@@ -3192,12 +3224,12 @@ class AsyncHybridQuery(AsyncStandardQuery, AsyncVectorQueryBase):
|
||||
plan : str
|
||||
""" # noqa: E501
|
||||
|
||||
results = ["Vector Search Plan:"]
|
||||
results.append(await self._inner.to_vector_query().explain_plan(verbose))
|
||||
results.append("FTS Search Plan:")
|
||||
results.append(await self._inner.to_fts_query().explain_plan(verbose))
|
||||
|
||||
return "\n".join(results)
|
||||
vector_plan = await self._inner.to_vector_query().explain_plan(verbose)
|
||||
fts_plan = await self._inner.to_fts_query().explain_plan(verbose)
|
||||
# Indent sub-plans under the reranker
|
||||
indented_vector = "\n".join(" " + line for line in vector_plan.splitlines())
|
||||
indented_fts = "\n".join(" " + line for line in fts_plan.splitlines())
|
||||
return f"{self._reranker}\n {indented_vector}\n {indented_fts}"
|
||||
|
||||
async def analyze_plan(self):
|
||||
"""
|
||||
|
||||
@@ -218,8 +218,6 @@ class RemoteTable(Table):
|
||||
train: bool = True,
|
||||
):
|
||||
"""Create an index on the table.
|
||||
Currently, the only parameters that matter are
|
||||
the metric and the vector column name.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
@@ -250,11 +248,6 @@ class RemoteTable(Table):
|
||||
>>> table.create_index("l2", "vector") # doctest: +SKIP
|
||||
"""
|
||||
|
||||
if num_sub_vectors is not None:
|
||||
logging.warning(
|
||||
"num_sub_vectors is not supported on LanceDB cloud."
|
||||
"This parameter will be tuned automatically."
|
||||
)
|
||||
if accelerator is not None:
|
||||
logging.warning(
|
||||
"GPU accelerator is not yet supported on LanceDB cloud."
|
||||
|
||||
@@ -42,10 +42,18 @@ class AnswerdotaiRerankers(Reranker):
|
||||
rerankers = attempt_import_or_raise(
|
||||
"rerankers"
|
||||
) # import here for faster ops later
|
||||
self.model_name = model_name
|
||||
self.model_type = model_type
|
||||
self.reranker = rerankers.Reranker(
|
||||
model_name=model_name, model_type=model_type, **kwargs
|
||||
)
|
||||
|
||||
def __str__(self):
|
||||
return (
|
||||
f"AnswerdotaiRerankers(model_type={self.model_type}, "
|
||||
f"model_name={self.model_name})"
|
||||
)
|
||||
|
||||
def _rerank(self, result_set: pa.Table, query: str):
|
||||
result_set = self._handle_empty_results(result_set)
|
||||
if len(result_set) == 0:
|
||||
|
||||
@@ -40,6 +40,9 @@ class Reranker(ABC):
|
||||
if ARROW_VERSION.major <= 13:
|
||||
self._concat_tables_args = {"promote": True}
|
||||
|
||||
def __str__(self):
|
||||
return self.__class__.__name__
|
||||
|
||||
def rerank_vector(
|
||||
self,
|
||||
query: str,
|
||||
|
||||
@@ -44,6 +44,9 @@ class CohereReranker(Reranker):
|
||||
self.top_n = top_n
|
||||
self.api_key = api_key
|
||||
|
||||
def __str__(self):
|
||||
return f"CohereReranker(model_name={self.model_name})"
|
||||
|
||||
@cached_property
|
||||
def _client(self):
|
||||
cohere = attempt_import_or_raise("cohere")
|
||||
|
||||
@@ -50,6 +50,9 @@ class CrossEncoderReranker(Reranker):
|
||||
if self.device is None:
|
||||
self.device = "cuda" if torch.cuda.is_available() else "cpu"
|
||||
|
||||
def __str__(self):
|
||||
return f"CrossEncoderReranker(model_name={self.model_name})"
|
||||
|
||||
@cached_property
|
||||
def model(self):
|
||||
sbert = attempt_import_or_raise("sentence_transformers")
|
||||
|
||||
@@ -45,6 +45,9 @@ class JinaReranker(Reranker):
|
||||
self.top_n = top_n
|
||||
self.api_key = api_key
|
||||
|
||||
def __str__(self):
|
||||
return f"JinaReranker(model_name={self.model_name})"
|
||||
|
||||
@cached_property
|
||||
def _client(self):
|
||||
import requests
|
||||
|
||||
@@ -38,6 +38,9 @@ class LinearCombinationReranker(Reranker):
|
||||
self.weight = weight
|
||||
self.fill = fill
|
||||
|
||||
def __str__(self):
|
||||
return f"LinearCombinationReranker(weight={self.weight}, fill={self.fill})"
|
||||
|
||||
def rerank_hybrid(
|
||||
self,
|
||||
query: str, # noqa: F821
|
||||
|
||||
@@ -54,6 +54,12 @@ class MRRReranker(Reranker):
|
||||
self.weight_vector = weight_vector
|
||||
self.weight_fts = weight_fts
|
||||
|
||||
def __str__(self):
|
||||
return (
|
||||
f"MRRReranker(weight_vector={self.weight_vector}, "
|
||||
f"weight_fts={self.weight_fts})"
|
||||
)
|
||||
|
||||
def rerank_hybrid(
|
||||
self,
|
||||
query: str, # noqa: F821
|
||||
|
||||
@@ -43,6 +43,9 @@ class OpenaiReranker(Reranker):
|
||||
self.column = column
|
||||
self.api_key = api_key
|
||||
|
||||
def __str__(self):
|
||||
return f"OpenaiReranker(model_name={self.model_name})"
|
||||
|
||||
def _rerank(self, result_set: pa.Table, query: str):
|
||||
result_set = self._handle_empty_results(result_set)
|
||||
if len(result_set) == 0:
|
||||
|
||||
@@ -36,6 +36,9 @@ class RRFReranker(Reranker):
|
||||
super().__init__(return_score)
|
||||
self.K = K
|
||||
|
||||
def __str__(self):
|
||||
return f"RRFReranker(K={self.K})"
|
||||
|
||||
def rerank_hybrid(
|
||||
self,
|
||||
query: str, # noqa: F821
|
||||
|
||||
@@ -52,6 +52,9 @@ class VoyageAIReranker(Reranker):
|
||||
self.api_key = api_key
|
||||
self.truncation = truncation
|
||||
|
||||
def __str__(self):
|
||||
return f"VoyageAIReranker(model_name={self.model_name})"
|
||||
|
||||
@cached_property
|
||||
def _client(self):
|
||||
voyageai = attempt_import_or_raise("voyageai")
|
||||
|
||||
@@ -0,0 +1,214 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
|
||||
from dataclasses import dataclass
|
||||
from functools import singledispatch
|
||||
import sys
|
||||
from typing import Callable, Iterator, Optional
|
||||
from lancedb.arrow import to_arrow
|
||||
import pyarrow as pa
|
||||
import pyarrow.dataset as ds
|
||||
|
||||
from .pydantic import LanceModel
|
||||
|
||||
|
||||
@dataclass
|
||||
class Scannable:
|
||||
schema: pa.Schema
|
||||
num_rows: Optional[int]
|
||||
# Factory function to create a new reader each time (supports re-scanning)
|
||||
reader: Callable[[], pa.RecordBatchReader]
|
||||
# Whether reader can be called more than once. For example, an iterator can
|
||||
# only be consumed once, while a DataFrame can be converted to a new reader
|
||||
# each time.
|
||||
rescannable: bool = True
|
||||
|
||||
|
||||
@singledispatch
|
||||
def to_scannable(data) -> Scannable:
|
||||
# Fallback: try iterable protocol
|
||||
if hasattr(data, "__iter__"):
|
||||
return _from_iterable(iter(data))
|
||||
raise NotImplementedError(f"to_scannable not implemented for type {type(data)}")
|
||||
|
||||
|
||||
@to_scannable.register(pa.RecordBatchReader)
|
||||
def _from_reader(data: pa.RecordBatchReader) -> Scannable:
|
||||
# RecordBatchReader can only be consumed once - not rescannable
|
||||
return Scannable(
|
||||
schema=data.schema, num_rows=None, reader=lambda: data, rescannable=False
|
||||
)
|
||||
|
||||
|
||||
@to_scannable.register(pa.RecordBatch)
|
||||
def _from_batch(data: pa.RecordBatch) -> Scannable:
|
||||
return Scannable(
|
||||
schema=data.schema,
|
||||
num_rows=data.num_rows,
|
||||
reader=lambda: pa.RecordBatchReader.from_batches(data.schema, [data]),
|
||||
)
|
||||
|
||||
|
||||
@to_scannable.register(pa.Table)
|
||||
def _from_table(data: pa.Table) -> Scannable:
|
||||
return Scannable(schema=data.schema, num_rows=data.num_rows, reader=data.to_reader)
|
||||
|
||||
|
||||
@to_scannable.register(ds.Dataset)
|
||||
def _from_dataset(data: ds.Dataset) -> Scannable:
|
||||
return Scannable(
|
||||
schema=data.schema,
|
||||
num_rows=data.count_rows(),
|
||||
reader=lambda: data.scanner().to_reader(),
|
||||
)
|
||||
|
||||
|
||||
@to_scannable.register(ds.Scanner)
|
||||
def _from_scanner(data: ds.Scanner) -> Scannable:
|
||||
# Scanner can only be consumed once - not rescannable
|
||||
return Scannable(
|
||||
schema=data.projected_schema,
|
||||
num_rows=None,
|
||||
reader=data.to_reader,
|
||||
rescannable=False,
|
||||
)
|
||||
|
||||
|
||||
@to_scannable.register(list)
|
||||
def _from_list(data: list) -> Scannable:
|
||||
if not data:
|
||||
raise ValueError("Cannot create table from empty list without a schema")
|
||||
table = to_arrow(data)
|
||||
return Scannable(
|
||||
schema=table.schema, num_rows=table.num_rows, reader=table.to_reader
|
||||
)
|
||||
|
||||
|
||||
@to_scannable.register(dict)
|
||||
def _from_dict(data: dict) -> Scannable:
|
||||
raise ValueError("Cannot add a single dictionary to a table. Use a list.")
|
||||
|
||||
|
||||
@to_scannable.register(LanceModel)
|
||||
def _from_lance_model(data: LanceModel) -> Scannable:
|
||||
raise ValueError("Cannot add a single LanceModel to a table. Use a list.")
|
||||
|
||||
|
||||
def _from_iterable(data: Iterator) -> Scannable:
|
||||
first_item = next(data, None)
|
||||
if first_item is None:
|
||||
raise ValueError("Cannot create table from empty iterator")
|
||||
first = to_arrow(first_item)
|
||||
schema = first.schema
|
||||
|
||||
def iter():
|
||||
yield from first.to_batches()
|
||||
for item in data:
|
||||
batch = to_arrow(item)
|
||||
if batch.schema != schema:
|
||||
try:
|
||||
batch = batch.cast(schema)
|
||||
except pa.lib.ArrowInvalid:
|
||||
raise ValueError(
|
||||
f"Input iterator yielded a batch with schema that "
|
||||
f"does not match the schema of other batches.\n"
|
||||
f"Expected:\n{schema}\nGot:\n{batch.schema}"
|
||||
)
|
||||
yield from batch.to_batches()
|
||||
|
||||
reader = pa.RecordBatchReader.from_batches(schema, iter())
|
||||
return to_scannable(reader)
|
||||
|
||||
|
||||
_registered_modules: set[str] = set()
|
||||
|
||||
|
||||
def _register_optional_converters():
|
||||
"""Register converters for optional dependencies that are already imported."""
|
||||
|
||||
if "pandas" in sys.modules and "pandas" not in _registered_modules:
|
||||
_registered_modules.add("pandas")
|
||||
import pandas as pd
|
||||
|
||||
@to_arrow.register(pd.DataFrame)
|
||||
def _arrow_from_pandas(data: pd.DataFrame) -> pa.Table:
|
||||
table = pa.Table.from_pandas(data, preserve_index=False)
|
||||
return table.replace_schema_metadata(None)
|
||||
|
||||
@to_scannable.register(pd.DataFrame)
|
||||
def _from_pandas(data: pd.DataFrame) -> Scannable:
|
||||
return to_scannable(_arrow_from_pandas(data))
|
||||
|
||||
if "polars" in sys.modules and "polars" not in _registered_modules:
|
||||
_registered_modules.add("polars")
|
||||
import polars as pl
|
||||
|
||||
@to_arrow.register(pl.DataFrame)
|
||||
def _arrow_from_polars(data: pl.DataFrame) -> pa.Table:
|
||||
return data.to_arrow()
|
||||
|
||||
@to_scannable.register(pl.DataFrame)
|
||||
def _from_polars(data: pl.DataFrame) -> Scannable:
|
||||
arrow = data.to_arrow()
|
||||
return Scannable(
|
||||
schema=arrow.schema, num_rows=len(data), reader=arrow.to_reader
|
||||
)
|
||||
|
||||
@to_scannable.register(pl.LazyFrame)
|
||||
def _from_polars_lazy(data: pl.LazyFrame) -> Scannable:
|
||||
arrow = data.collect().to_arrow()
|
||||
return Scannable(
|
||||
schema=arrow.schema, num_rows=arrow.num_rows, reader=arrow.to_reader
|
||||
)
|
||||
|
||||
if "datasets" in sys.modules and "datasets" not in _registered_modules:
|
||||
_registered_modules.add("datasets")
|
||||
from datasets import Dataset as HFDataset
|
||||
from datasets import DatasetDict as HFDatasetDict
|
||||
|
||||
@to_scannable.register(HFDataset)
|
||||
def _from_hf_dataset(data: HFDataset) -> Scannable:
|
||||
table = data.data.table # Access underlying Arrow table
|
||||
return Scannable(
|
||||
schema=table.schema, num_rows=len(data), reader=table.to_reader
|
||||
)
|
||||
|
||||
@to_scannable.register(HFDatasetDict)
|
||||
def _from_hf_dataset_dict(data: HFDatasetDict) -> Scannable:
|
||||
# HuggingFace DatasetDict: combine all splits with a 'split' column
|
||||
schema = data[list(data.keys())[0]].features.arrow_schema
|
||||
if "split" not in schema.names:
|
||||
schema = schema.append(pa.field("split", pa.string()))
|
||||
|
||||
def gen():
|
||||
for split_name, dataset in data.items():
|
||||
for batch in dataset.data.to_batches():
|
||||
split_arr = pa.array(
|
||||
[split_name] * len(batch), type=pa.string()
|
||||
)
|
||||
yield pa.RecordBatch.from_arrays(
|
||||
list(batch.columns) + [split_arr], schema=schema
|
||||
)
|
||||
|
||||
total_rows = sum(len(dataset) for dataset in data.values())
|
||||
return Scannable(
|
||||
schema=schema,
|
||||
num_rows=total_rows,
|
||||
reader=lambda: pa.RecordBatchReader.from_batches(schema, gen()),
|
||||
)
|
||||
|
||||
if "lance" in sys.modules and "lance" not in _registered_modules:
|
||||
_registered_modules.add("lance")
|
||||
import lance
|
||||
|
||||
@to_scannable.register(lance.LanceDataset)
|
||||
def _from_lance(data: lance.LanceDataset) -> Scannable:
|
||||
return Scannable(
|
||||
schema=data.schema,
|
||||
num_rows=data.count_rows(),
|
||||
reader=lambda: data.scanner().to_reader(),
|
||||
)
|
||||
|
||||
|
||||
# Register on module load
|
||||
_register_optional_converters()
|
||||
+100
-17
@@ -25,6 +25,8 @@ from typing import (
|
||||
)
|
||||
from urllib.parse import urlparse
|
||||
|
||||
from lancedb.scannable import _register_optional_converters, to_scannable
|
||||
|
||||
from . import __version__
|
||||
from lancedb.arrow import peek_reader
|
||||
from lancedb.background_loop import LOOP
|
||||
@@ -904,7 +906,9 @@ class Table(ABC):
|
||||
----------
|
||||
field_names: str or list of str
|
||||
The name(s) of the field to index.
|
||||
can be only str if use_tantivy=True for now.
|
||||
If ``use_tantivy`` is False (default), only a single field name
|
||||
(str) is supported. To index multiple fields, create a separate
|
||||
FTS index for each field.
|
||||
replace: bool, default False
|
||||
If True, replace the existing index if it exists. Note that this is
|
||||
not yet an atomic operation; the index will be temporarily
|
||||
@@ -1327,7 +1331,7 @@ class Table(ABC):
|
||||
1 2 [3.0, 4.0]
|
||||
2 3 [5.0, 6.0]
|
||||
>>> table.delete("x = 2")
|
||||
DeleteResult(version=2)
|
||||
DeleteResult(num_deleted_rows=1, version=2)
|
||||
>>> table.to_pandas()
|
||||
x vector
|
||||
0 1 [1.0, 2.0]
|
||||
@@ -1341,7 +1345,7 @@ class Table(ABC):
|
||||
>>> to_remove
|
||||
'1, 5'
|
||||
>>> table.delete(f"x IN ({to_remove})")
|
||||
DeleteResult(version=3)
|
||||
DeleteResult(num_deleted_rows=1, version=3)
|
||||
>>> table.to_pandas()
|
||||
x vector
|
||||
0 3 [5.0, 6.0]
|
||||
@@ -2222,6 +2226,37 @@ class LanceTable(Table):
|
||||
def uri(self) -> str:
|
||||
return LOOP.run(self._table.uri())
|
||||
|
||||
def initial_storage_options(self) -> Optional[Dict[str, str]]:
|
||||
"""Get the initial storage options that were passed in when opening this table.
|
||||
|
||||
For dynamically refreshed options (e.g., credential vending), use
|
||||
:meth:`latest_storage_options`.
|
||||
|
||||
Warning: This is an internal API and the return value is subject to change.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Optional[Dict[str, str]]
|
||||
The storage options, or None if no storage options were configured.
|
||||
"""
|
||||
return LOOP.run(self._table.initial_storage_options())
|
||||
|
||||
def latest_storage_options(self) -> Optional[Dict[str, str]]:
|
||||
"""Get the latest storage options, refreshing from provider if configured.
|
||||
|
||||
This method is useful for credential vending scenarios where storage options
|
||||
may be refreshed dynamically. If no dynamic provider is configured, this
|
||||
returns the initial static options.
|
||||
|
||||
Warning: This is an internal API and the return value is subject to change.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Optional[Dict[str, str]]
|
||||
The storage options, or None if no storage options were configured.
|
||||
"""
|
||||
return LOOP.run(self._table.latest_storage_options())
|
||||
|
||||
def create_scalar_index(
|
||||
self,
|
||||
column: str,
|
||||
@@ -2267,7 +2302,11 @@ class LanceTable(Table):
|
||||
):
|
||||
if not use_tantivy:
|
||||
if not isinstance(field_names, str):
|
||||
raise ValueError("field_names must be a string when use_tantivy=False")
|
||||
raise ValueError(
|
||||
"Native FTS indexes can only be created on a single field "
|
||||
"at a time. To search over multiple text fields, create a "
|
||||
"separate FTS index for each field."
|
||||
)
|
||||
|
||||
if tokenizer_name is None:
|
||||
tokenizer_configs = {
|
||||
@@ -3624,6 +3663,37 @@ class AsyncTable:
|
||||
"""
|
||||
return await self._inner.uri()
|
||||
|
||||
async def initial_storage_options(self) -> Optional[Dict[str, str]]:
|
||||
"""Get the initial storage options that were passed in when opening this table.
|
||||
|
||||
For dynamically refreshed options (e.g., credential vending), use
|
||||
:meth:`latest_storage_options`.
|
||||
|
||||
Warning: This is an internal API and the return value is subject to change.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Optional[Dict[str, str]]
|
||||
The storage options, or None if no storage options were configured.
|
||||
"""
|
||||
return await self._inner.initial_storage_options()
|
||||
|
||||
async def latest_storage_options(self) -> Optional[Dict[str, str]]:
|
||||
"""Get the latest storage options, refreshing from provider if configured.
|
||||
|
||||
This method is useful for credential vending scenarios where storage options
|
||||
may be refreshed dynamically. If no dynamic provider is configured, this
|
||||
returns the initial static options.
|
||||
|
||||
Warning: This is an internal API and the return value is subject to change.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Optional[Dict[str, str]]
|
||||
The storage options, or None if no storage options were configured.
|
||||
"""
|
||||
return await self._inner.latest_storage_options()
|
||||
|
||||
async def add(
|
||||
self,
|
||||
data: DATA,
|
||||
@@ -3659,18 +3729,31 @@ class AsyncTable:
|
||||
on_bad_vectors = "error"
|
||||
if fill_value is None:
|
||||
fill_value = 0.0
|
||||
data = _sanitize_data(
|
||||
data,
|
||||
schema,
|
||||
metadata=schema.metadata,
|
||||
on_bad_vectors=on_bad_vectors,
|
||||
fill_value=fill_value,
|
||||
allow_subschema=True,
|
||||
)
|
||||
if isinstance(data, pa.Table):
|
||||
data = data.to_reader()
|
||||
|
||||
return await self._inner.add(data, mode or "append")
|
||||
# _santitize_data is an old code path, but we will use it until the
|
||||
# new code path is ready.
|
||||
if on_bad_vectors != "error" or (
|
||||
schema.metadata is not None and b"embedding_functions" in schema.metadata
|
||||
):
|
||||
data = _sanitize_data(
|
||||
data,
|
||||
schema,
|
||||
metadata=schema.metadata,
|
||||
on_bad_vectors=on_bad_vectors,
|
||||
fill_value=fill_value,
|
||||
allow_subschema=True,
|
||||
)
|
||||
_register_optional_converters()
|
||||
data = to_scannable(data)
|
||||
try:
|
||||
return await self._inner.add(data, mode or "append")
|
||||
except RuntimeError as e:
|
||||
if "Cast error" in str(e):
|
||||
raise ValueError(e)
|
||||
elif "Vector column contains NaN" in str(e):
|
||||
raise ValueError(e)
|
||||
else:
|
||||
raise
|
||||
|
||||
def merge_insert(self, on: Union[str, Iterable[str]]) -> LanceMergeInsertBuilder:
|
||||
"""
|
||||
@@ -4132,7 +4215,7 @@ class AsyncTable:
|
||||
1 2 [3.0, 4.0]
|
||||
2 3 [5.0, 6.0]
|
||||
>>> table.delete("x = 2")
|
||||
DeleteResult(version=2)
|
||||
DeleteResult(num_deleted_rows=1, version=2)
|
||||
>>> table.to_pandas()
|
||||
x vector
|
||||
0 1 [1.0, 2.0]
|
||||
@@ -4146,7 +4229,7 @@ class AsyncTable:
|
||||
>>> to_remove
|
||||
'1, 5'
|
||||
>>> table.delete(f"x IN ({to_remove})")
|
||||
DeleteResult(version=3)
|
||||
DeleteResult(num_deleted_rows=1, version=3)
|
||||
>>> table.to_pandas()
|
||||
x vector
|
||||
0 3 [5.0, 6.0]
|
||||
|
||||
@@ -324,6 +324,16 @@ def _(value: list):
|
||||
return "[" + ", ".join(map(value_to_sql, value)) + "]"
|
||||
|
||||
|
||||
@value_to_sql.register(dict)
|
||||
def _(value: dict):
|
||||
# https://datafusion.apache.org/user-guide/sql/scalar_functions.html#named-struct
|
||||
return (
|
||||
"named_struct("
|
||||
+ ", ".join(f"'{k}', {value_to_sql(v)}" for k, v in value.items())
|
||||
+ ")"
|
||||
)
|
||||
|
||||
|
||||
@value_to_sql.register(np.ndarray)
|
||||
def _(value: np.ndarray):
|
||||
return value_to_sql(value.tolist())
|
||||
@@ -419,3 +429,22 @@ def batch_to_tensor(batch: pa.RecordBatch):
|
||||
"""
|
||||
torch = attempt_import_or_raise("torch", "torch")
|
||||
return torch.stack([torch.from_dlpack(col) for col in batch.columns])
|
||||
|
||||
|
||||
def batch_to_tensor_rows(batch: pa.RecordBatch):
|
||||
"""
|
||||
Convert a PyArrow RecordBatch to a list of PyTorch Tensor, one per row
|
||||
|
||||
Each column is converted to a tensor (using zero-copy via DLPack)
|
||||
and the columns are then stacked into a single tensor. The 2D tensor
|
||||
is then converted to a list of tensors, one per row
|
||||
|
||||
Fails if torch or numpy is not installed.
|
||||
Fails if a column's data type is not supported by PyTorch.
|
||||
"""
|
||||
torch = attempt_import_or_raise("torch", "torch")
|
||||
numpy = attempt_import_or_raise("numpy", "numpy")
|
||||
columns = [col.to_numpy(zero_copy_only=False) for col in batch.columns]
|
||||
stacked = torch.tensor(numpy.column_stack(columns))
|
||||
rows = list(stacked.unbind(dim=0))
|
||||
return rows
|
||||
|
||||
@@ -515,3 +515,34 @@ def test_openai_propagates_api_key(monkeypatch):
|
||||
query = "greetings"
|
||||
actual = table.search(query).limit(1).to_pydantic(Words)[0]
|
||||
assert len(actual.text) > 0
|
||||
|
||||
|
||||
@patch("time.sleep")
|
||||
def test_openai_no_retry_on_401(mock_sleep):
|
||||
"""
|
||||
Test that OpenAI embedding function does not retry on 401 authentication
|
||||
errors.
|
||||
"""
|
||||
from lancedb.embeddings.utils import retry_with_exponential_backoff
|
||||
|
||||
# Create a mock that raises an AuthenticationError
|
||||
class MockAuthenticationError(Exception):
|
||||
"""Mock OpenAI AuthenticationError"""
|
||||
|
||||
pass
|
||||
|
||||
MockAuthenticationError.__name__ = "AuthenticationError"
|
||||
|
||||
mock_func = MagicMock(side_effect=MockAuthenticationError("Invalid API key"))
|
||||
|
||||
# Wrap the function with retry logic
|
||||
wrapped_func = retry_with_exponential_backoff(mock_func, max_retries=3)
|
||||
|
||||
# Should raise without retrying
|
||||
with pytest.raises(MockAuthenticationError):
|
||||
wrapped_func()
|
||||
|
||||
# Verify that the function was only called once (no retries)
|
||||
assert mock_func.call_count == 1
|
||||
# Verify that sleep was never called (no retries)
|
||||
assert mock_sleep.call_count == 0
|
||||
|
||||
@@ -27,6 +27,7 @@ from lancedb.query import (
|
||||
PhraseQuery,
|
||||
BooleanQuery,
|
||||
Occur,
|
||||
LanceFtsQueryBuilder,
|
||||
)
|
||||
import numpy as np
|
||||
import pyarrow as pa
|
||||
@@ -882,3 +883,109 @@ def test_fts_query_to_json():
|
||||
'"must_not":[]}}'
|
||||
)
|
||||
assert json_str == expected
|
||||
|
||||
|
||||
def test_fts_fast_search(table):
|
||||
table.create_fts_index("text", use_tantivy=False)
|
||||
|
||||
# Insert some unindexed data
|
||||
table.add(
|
||||
[
|
||||
{
|
||||
"text": "xyz",
|
||||
"vector": [0 for _ in range(128)],
|
||||
"id": 101,
|
||||
"text2": "xyz",
|
||||
"nested": {"text": "xyz"},
|
||||
"count": 10,
|
||||
}
|
||||
]
|
||||
)
|
||||
|
||||
# Without fast_search, the query object should not have fast_search set
|
||||
builder = table.search("xyz", query_type="fts").limit(10)
|
||||
query = builder.to_query_object()
|
||||
assert query.fast_search is None
|
||||
|
||||
# With fast_search, the query object should have fast_search=True
|
||||
builder = table.search("xyz", query_type="fts").fast_search().limit(10)
|
||||
query = builder.to_query_object()
|
||||
assert query.fast_search is True
|
||||
|
||||
# fast_search should be chainable with other methods
|
||||
builder = (
|
||||
table.search("xyz", query_type="fts").fast_search().select(["text"]).limit(5)
|
||||
)
|
||||
query = builder.to_query_object()
|
||||
assert query.fast_search is True
|
||||
assert query.limit == 5
|
||||
assert query.columns == ["text"]
|
||||
|
||||
# fast_search should be enabled by keyword argument too
|
||||
query = LanceFtsQueryBuilder(table, "xyz", fast_search=True).to_query_object()
|
||||
assert query.fast_search is True
|
||||
|
||||
# Verify it executes without error and skips unindexed data
|
||||
results = table.search("xyz", query_type="fts").fast_search().limit(5).to_list()
|
||||
assert len(results) == 0
|
||||
|
||||
# Update index and verify it returns results
|
||||
table.optimize()
|
||||
results = table.search("xyz", query_type="fts").fast_search().limit(5).to_list()
|
||||
assert len(results) > 0
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_fts_fast_search_async(async_table):
|
||||
await async_table.create_index("text", config=FTS())
|
||||
|
||||
# Insert some unindexed data
|
||||
await async_table.add(
|
||||
[
|
||||
{
|
||||
"text": "xyz",
|
||||
"vector": [0 for _ in range(128)],
|
||||
"id": 101,
|
||||
"text2": "xyz",
|
||||
"nested": {"text": "xyz"},
|
||||
"count": 10,
|
||||
}
|
||||
]
|
||||
)
|
||||
|
||||
# Without fast_search, should return results
|
||||
results = await async_table.query().nearest_to_text("xyz").limit(5).to_list()
|
||||
assert len(results) > 0
|
||||
|
||||
# With fast_search, should return no results data unindexed
|
||||
fast_results = (
|
||||
await async_table.query()
|
||||
.nearest_to_text("xyz")
|
||||
.fast_search()
|
||||
.limit(5)
|
||||
.to_list()
|
||||
)
|
||||
assert len(fast_results) == 0
|
||||
|
||||
# Update index and verify it returns results
|
||||
await async_table.optimize()
|
||||
|
||||
fast_results = (
|
||||
await async_table.query()
|
||||
.nearest_to_text("xyz")
|
||||
.fast_search()
|
||||
.limit(5)
|
||||
.to_list()
|
||||
)
|
||||
assert len(fast_results) > 0
|
||||
|
||||
# fast_search should be chainable with other methods
|
||||
results = (
|
||||
await async_table.query()
|
||||
.nearest_to_text("xyz")
|
||||
.fast_search()
|
||||
.select(["text"])
|
||||
.limit(5)
|
||||
.to_list()
|
||||
)
|
||||
assert len(results) > 0
|
||||
|
||||
@@ -163,9 +163,7 @@ async def test_explain_plan(table: AsyncTable):
|
||||
table.query().nearest_to_text("dog").nearest_to([0.1, 0.1]).explain_plan(True)
|
||||
)
|
||||
|
||||
assert "Vector Search Plan" in plan
|
||||
assert "KNNVectorDistance" in plan
|
||||
assert "FTS Search Plan" in plan
|
||||
assert "LanceRead" in plan
|
||||
|
||||
|
||||
|
||||
@@ -664,23 +664,20 @@ def test_iter_basic(some_permutation: Permutation):
|
||||
expected_batches = (950 + batch_size - 1) // batch_size # ceiling division
|
||||
assert len(batches) == expected_batches
|
||||
|
||||
# Check that all batches are dicts (default python format)
|
||||
assert all(isinstance(batch, dict) for batch in batches)
|
||||
# Check that all batches are lists of dicts (default python format)
|
||||
assert all(isinstance(batch, list) for batch in batches)
|
||||
|
||||
# Check that batches have the correct structure
|
||||
for batch in batches:
|
||||
assert "id" in batch
|
||||
assert "value" in batch
|
||||
assert isinstance(batch["id"], list)
|
||||
assert isinstance(batch["value"], list)
|
||||
assert "id" in batch[0]
|
||||
assert "value" in batch[0]
|
||||
|
||||
# Check that all batches except the last have the correct size
|
||||
for batch in batches[:-1]:
|
||||
assert len(batch["id"]) == batch_size
|
||||
assert len(batch["value"]) == batch_size
|
||||
assert len(batch) == batch_size
|
||||
|
||||
# Last batch might be smaller
|
||||
assert len(batches[-1]["id"]) <= batch_size
|
||||
assert len(batches[-1]) <= batch_size
|
||||
|
||||
|
||||
def test_iter_skip_last_batch(some_permutation: Permutation):
|
||||
@@ -699,11 +696,11 @@ def test_iter_skip_last_batch(some_permutation: Permutation):
|
||||
if 950 % batch_size != 0:
|
||||
assert len(batches_without_skip) == num_full_batches + 1
|
||||
# Last batch should be smaller
|
||||
assert len(batches_without_skip[-1]["id"]) == 950 % batch_size
|
||||
assert len(batches_without_skip[-1]) == 950 % batch_size
|
||||
|
||||
# All batches with skip_last_batch should be full size
|
||||
for batch in batches_with_skip:
|
||||
assert len(batch["id"]) == batch_size
|
||||
assert len(batch) == batch_size
|
||||
|
||||
|
||||
def test_iter_different_batch_sizes(some_permutation: Permutation):
|
||||
@@ -720,12 +717,12 @@ def test_iter_different_batch_sizes(some_permutation: Permutation):
|
||||
# Test with batch size equal to total rows
|
||||
single_batch = list(some_permutation.iter(950, skip_last_batch=False))
|
||||
assert len(single_batch) == 1
|
||||
assert len(single_batch[0]["id"]) == 950
|
||||
assert len(single_batch[0]) == 950
|
||||
|
||||
# Test with batch size larger than total rows
|
||||
oversized_batch = list(some_permutation.iter(10000, skip_last_batch=False))
|
||||
assert len(oversized_batch) == 1
|
||||
assert len(oversized_batch[0]["id"]) == 950
|
||||
assert len(oversized_batch[0]) == 950
|
||||
|
||||
|
||||
def test_dunder_iter(some_permutation: Permutation):
|
||||
@@ -738,15 +735,13 @@ def test_dunder_iter(some_permutation: Permutation):
|
||||
|
||||
# All batches should be full size
|
||||
for batch in batches:
|
||||
assert len(batch["id"]) == 100
|
||||
assert len(batch["value"]) == 100
|
||||
assert len(batch) == 100
|
||||
|
||||
some_permutation = some_permutation.with_batch_size(400)
|
||||
batches = list(some_permutation)
|
||||
assert len(batches) == 2 # floor(950 / 400) since skip_last_batch=True
|
||||
for batch in batches:
|
||||
assert len(batch["id"]) == 400
|
||||
assert len(batch["value"]) == 400
|
||||
assert len(batch) == 400
|
||||
|
||||
|
||||
def test_iter_with_different_formats(some_permutation: Permutation):
|
||||
@@ -761,7 +756,7 @@ def test_iter_with_different_formats(some_permutation: Permutation):
|
||||
# Test with python format (default)
|
||||
python_perm = some_permutation.with_format("python")
|
||||
python_batches = list(python_perm.iter(batch_size, skip_last_batch=False))
|
||||
assert all(isinstance(batch, dict) for batch in python_batches)
|
||||
assert all(isinstance(batch, list) for batch in python_batches)
|
||||
|
||||
# Test with pandas format
|
||||
pandas_perm = some_permutation.with_format("pandas")
|
||||
@@ -780,8 +775,8 @@ def test_iter_with_column_selection(some_permutation: Permutation):
|
||||
|
||||
# Check that batches only contain the id column
|
||||
for batch in batches:
|
||||
assert "id" in batch
|
||||
assert "value" not in batch
|
||||
assert "id" in batch[0]
|
||||
assert "value" not in batch[0]
|
||||
|
||||
|
||||
def test_iter_with_column_rename(some_permutation: Permutation):
|
||||
@@ -791,9 +786,9 @@ def test_iter_with_column_rename(some_permutation: Permutation):
|
||||
|
||||
# Check that batches have the renamed column
|
||||
for batch in batches:
|
||||
assert "id" in batch
|
||||
assert "data" in batch
|
||||
assert "value" not in batch
|
||||
assert "id" in batch[0]
|
||||
assert "data" in batch[0]
|
||||
assert "value" not in batch[0]
|
||||
|
||||
|
||||
def test_iter_with_limit_offset(some_permutation: Permutation):
|
||||
@@ -812,14 +807,14 @@ def test_iter_with_limit_offset(some_permutation: Permutation):
|
||||
assert len(limit_batches) == 5
|
||||
|
||||
no_skip = some_permutation.iter(101, skip_last_batch=False)
|
||||
row_100 = next(no_skip)["id"][100]
|
||||
row_100 = next(no_skip)[100]["id"]
|
||||
|
||||
# Test with both limit and offset
|
||||
limited_perm = some_permutation.with_skip(100).with_take(300)
|
||||
limited_batches = list(limited_perm.iter(100, skip_last_batch=False))
|
||||
# Should have 3 batches (300 / 100)
|
||||
assert len(limited_batches) == 3
|
||||
assert limited_batches[0]["id"][0] == row_100
|
||||
assert limited_batches[0][0]["id"] == row_100
|
||||
|
||||
|
||||
def test_iter_empty_permutation(mem_db):
|
||||
@@ -842,7 +837,7 @@ def test_iter_single_row(mem_db):
|
||||
# With skip_last_batch=False, should get one batch
|
||||
batches = list(perm.iter(10, skip_last_batch=False))
|
||||
assert len(batches) == 1
|
||||
assert len(batches[0]["id"]) == 1
|
||||
assert len(batches[0]) == 1
|
||||
|
||||
# With skip_last_batch=True, should skip the single row (since it's < batch_size)
|
||||
batches_skip = list(perm.iter(10, skip_last_batch=True))
|
||||
@@ -860,8 +855,7 @@ def test_identity_permutation(mem_db):
|
||||
|
||||
batches = list(permutation.iter(10, skip_last_batch=False))
|
||||
assert len(batches) == 1
|
||||
assert len(batches[0]["id"]) == 10
|
||||
assert len(batches[0]["value"]) == 10
|
||||
assert len(batches[0]) == 10
|
||||
|
||||
permutation = permutation.remove_columns(["value"])
|
||||
assert permutation.num_columns == 1
|
||||
@@ -904,10 +898,10 @@ def test_transform_fn(mem_db):
|
||||
py_result = list(permutation.with_format("python").iter(10, skip_last_batch=False))[
|
||||
0
|
||||
]
|
||||
assert len(py_result) == 2
|
||||
assert len(py_result["id"]) == 10
|
||||
assert len(py_result["value"]) == 10
|
||||
assert isinstance(py_result, dict)
|
||||
assert len(py_result) == 10
|
||||
assert "id" in py_result[0]
|
||||
assert "value" in py_result[0]
|
||||
assert isinstance(py_result, list)
|
||||
|
||||
try:
|
||||
import torch
|
||||
@@ -915,9 +909,11 @@ def test_transform_fn(mem_db):
|
||||
torch_result = list(
|
||||
permutation.with_format("torch").iter(10, skip_last_batch=False)
|
||||
)[0]
|
||||
assert torch_result.shape == (2, 10)
|
||||
assert torch_result.dtype == torch.int64
|
||||
assert isinstance(torch_result, torch.Tensor)
|
||||
assert isinstance(torch_result, list)
|
||||
assert len(torch_result) == 10
|
||||
assert isinstance(torch_result[0], torch.Tensor)
|
||||
assert torch_result[0].shape == (2,)
|
||||
assert torch_result[0].dtype == torch.int64
|
||||
except ImportError:
|
||||
# Skip check if torch is not installed
|
||||
pass
|
||||
@@ -945,3 +941,113 @@ def test_custom_transform(mem_db):
|
||||
batch = batches[0]
|
||||
|
||||
assert batch == pa.record_batch([range(10)], ["id"])
|
||||
|
||||
|
||||
def test_getitems_basic(some_permutation: Permutation):
|
||||
"""Test __getitems__ returns correct rows by offset."""
|
||||
result = some_permutation.__getitems__([0, 1, 2])
|
||||
assert isinstance(result, list)
|
||||
assert "id" in result[0]
|
||||
assert "value" in result[0]
|
||||
assert len(result) == 3
|
||||
|
||||
|
||||
def test_getitems_single_index(some_permutation: Permutation):
|
||||
"""Test __getitems__ with a single index."""
|
||||
result = some_permutation.__getitems__([0])
|
||||
assert len(result) == 1
|
||||
|
||||
|
||||
def test_getitems_preserves_order(some_permutation: Permutation):
|
||||
"""Test __getitems__ returns rows in the requested order."""
|
||||
# Get rows in forward order
|
||||
forward = some_permutation.__getitems__([0, 1, 2, 3, 4])
|
||||
# Get the same rows in reverse order
|
||||
reverse = some_permutation.__getitems__([4, 3, 2, 1, 0])
|
||||
|
||||
assert [r["id"] for r in forward] == list(reversed([r["id"] for r in reverse]))
|
||||
assert [r["value"] for r in forward] == list(
|
||||
reversed([r["value"] for r in reverse])
|
||||
)
|
||||
|
||||
|
||||
def test_getitems_non_contiguous(some_permutation: Permutation):
|
||||
"""Test __getitems__ with non-contiguous indices."""
|
||||
result = some_permutation.__getitems__([0, 10, 50, 100, 500])
|
||||
assert len(result) == 5
|
||||
|
||||
# Each id/value pair should match what we'd get individually
|
||||
for i, offset in enumerate([0, 10, 50, 100, 500]):
|
||||
single = some_permutation.__getitems__([offset])
|
||||
assert result[i]["id"] == single[0]["id"]
|
||||
assert result[i]["value"] == single[0]["value"]
|
||||
|
||||
|
||||
def test_getitems_with_column_selection(some_permutation: Permutation):
|
||||
"""Test __getitems__ respects column selection."""
|
||||
id_only = some_permutation.select_columns(["id"])
|
||||
result = id_only.__getitems__([0, 1, 2])
|
||||
assert "id" in result[0]
|
||||
assert "value" not in result[0]
|
||||
assert len(result) == 3
|
||||
|
||||
|
||||
def test_getitems_with_column_rename(some_permutation: Permutation):
|
||||
"""Test __getitems__ respects column renames."""
|
||||
renamed = some_permutation.rename_column("value", "data")
|
||||
result = renamed.__getitems__([0, 1])
|
||||
assert "data" in result[0]
|
||||
assert "value" not in result[0]
|
||||
assert len(result) == 2
|
||||
|
||||
|
||||
def test_getitems_with_format(some_permutation: Permutation):
|
||||
"""Test __getitems__ applies the transform function."""
|
||||
arrow_perm = some_permutation.with_format("arrow")
|
||||
result = arrow_perm.__getitems__([0, 1, 2])
|
||||
assert isinstance(result, pa.RecordBatch)
|
||||
assert result.num_rows == 3
|
||||
|
||||
|
||||
def test_getitems_with_custom_transform(some_permutation: Permutation):
|
||||
"""Test __getitems__ with a custom transform."""
|
||||
|
||||
def transform(batch: pa.RecordBatch) -> list:
|
||||
return batch.column("id").to_pylist()
|
||||
|
||||
custom = some_permutation.with_transform(transform)
|
||||
result = custom.__getitems__([0, 1, 2])
|
||||
assert isinstance(result, list)
|
||||
assert len(result) == 3
|
||||
|
||||
|
||||
def test_getitems_identity_permutation(mem_db):
|
||||
"""Test __getitems__ on an identity permutation."""
|
||||
tbl = mem_db.create_table(
|
||||
"test_table", pa.table({"id": range(10), "value": range(10)})
|
||||
)
|
||||
perm = Permutation.identity(tbl)
|
||||
|
||||
result = perm.__getitems__([0, 5, 9])
|
||||
assert [r["id"] for r in result] == [0, 5, 9]
|
||||
assert [r["value"] for r in result] == [0, 5, 9]
|
||||
|
||||
|
||||
def test_getitems_with_limit_offset(some_permutation: Permutation):
|
||||
"""Test __getitems__ on a permutation with skip/take applied."""
|
||||
limited = some_permutation.with_skip(100).with_take(200)
|
||||
|
||||
# Should be able to access offsets within the limited range
|
||||
result = limited.__getitems__([0, 1, 199])
|
||||
assert len(result) == 3
|
||||
|
||||
# The first item of the limited permutation should match offset 100 of original
|
||||
full_result = some_permutation.__getitems__([100])
|
||||
limited_result = limited.__getitems__([0])
|
||||
assert limited_result[0]["id"] == full_result[0]["id"]
|
||||
|
||||
|
||||
def test_getitems_invalid_offset(some_permutation: Permutation):
|
||||
"""Test __getitems__ with an out-of-range offset raises an error."""
|
||||
with pytest.raises(Exception):
|
||||
some_permutation.__getitems__([999999])
|
||||
|
||||
@@ -531,6 +531,78 @@ def test_empty_result_reranker():
|
||||
)
|
||||
|
||||
|
||||
def test_empty_hybrid_result_reranker():
|
||||
"""Test that hybrid search with empty results after filtering doesn't crash.
|
||||
|
||||
Regression test for https://github.com/lancedb/lancedb/issues/2425
|
||||
"""
|
||||
from lancedb.query import LanceHybridQueryBuilder
|
||||
|
||||
# Simulate empty vector and FTS results with the expected schema
|
||||
vector_schema = pa.schema(
|
||||
[
|
||||
("text", pa.string()),
|
||||
("vector", pa.list_(pa.float32(), 4)),
|
||||
("_rowid", pa.uint64()),
|
||||
("_distance", pa.float32()),
|
||||
]
|
||||
)
|
||||
fts_schema = pa.schema(
|
||||
[
|
||||
("text", pa.string()),
|
||||
("vector", pa.list_(pa.float32(), 4)),
|
||||
("_rowid", pa.uint64()),
|
||||
("_score", pa.float32()),
|
||||
]
|
||||
)
|
||||
empty_vector = pa.table(
|
||||
{
|
||||
"text": pa.array([], type=pa.string()),
|
||||
"vector": pa.array([], type=pa.list_(pa.float32(), 4)),
|
||||
"_rowid": pa.array([], type=pa.uint64()),
|
||||
"_distance": pa.array([], type=pa.float32()),
|
||||
},
|
||||
schema=vector_schema,
|
||||
)
|
||||
empty_fts = pa.table(
|
||||
{
|
||||
"text": pa.array([], type=pa.string()),
|
||||
"vector": pa.array([], type=pa.list_(pa.float32(), 4)),
|
||||
"_rowid": pa.array([], type=pa.uint64()),
|
||||
"_score": pa.array([], type=pa.float32()),
|
||||
},
|
||||
schema=fts_schema,
|
||||
)
|
||||
|
||||
for reranker in [LinearCombinationReranker(), RRFReranker()]:
|
||||
result = LanceHybridQueryBuilder._combine_hybrid_results(
|
||||
fts_results=empty_fts,
|
||||
vector_results=empty_vector,
|
||||
norm="score",
|
||||
fts_query="nonexistent query",
|
||||
reranker=reranker,
|
||||
limit=10,
|
||||
with_row_ids=False,
|
||||
)
|
||||
assert len(result) == 0
|
||||
assert "_relevance_score" in result.column_names
|
||||
assert "_rowid" not in result.column_names
|
||||
|
||||
# Also test with with_row_ids=True
|
||||
result = LanceHybridQueryBuilder._combine_hybrid_results(
|
||||
fts_results=empty_fts,
|
||||
vector_results=empty_vector,
|
||||
norm="score",
|
||||
fts_query="nonexistent query",
|
||||
reranker=LinearCombinationReranker(),
|
||||
limit=10,
|
||||
with_row_ids=True,
|
||||
)
|
||||
assert len(result) == 0
|
||||
assert "_relevance_score" in result.column_names
|
||||
assert "_rowid" in result.column_names
|
||||
|
||||
|
||||
@pytest.mark.parametrize("use_tantivy", [True, False])
|
||||
def test_cross_encoder_reranker_return_all(tmp_path, use_tantivy):
|
||||
pytest.importorskip("sentence_transformers")
|
||||
|
||||
@@ -810,7 +810,7 @@ def test_create_index_name_and_train_parameters(
|
||||
)
|
||||
|
||||
|
||||
def test_add_with_nans(mem_db: DBConnection):
|
||||
def test_create_with_nans(mem_db: DBConnection):
|
||||
# by default we raise an error on bad input vectors
|
||||
bad_data = [
|
||||
{"vector": [np.nan], "item": "bar", "price": 20.0},
|
||||
@@ -854,6 +854,57 @@ def test_add_with_nans(mem_db: DBConnection):
|
||||
assert np.allclose(v, np.array([0.0, 0.0]))
|
||||
|
||||
|
||||
def test_add_with_nans(mem_db: DBConnection):
|
||||
schema = pa.schema(
|
||||
[
|
||||
pa.field("vector", pa.list_(pa.float32(), 2), nullable=True),
|
||||
pa.field("item", pa.string(), nullable=True),
|
||||
pa.field("price", pa.float64(), nullable=False),
|
||||
],
|
||||
)
|
||||
table = mem_db.create_table("test", schema=schema)
|
||||
# by default we raise an error on bad input vectors
|
||||
bad_data = [
|
||||
{"vector": [np.nan], "item": "bar", "price": 20.0},
|
||||
{"vector": [5], "item": "bar", "price": 20.0},
|
||||
{"vector": [np.nan, np.nan], "item": "bar", "price": 20.0},
|
||||
{"vector": [np.nan, 5.0], "item": "bar", "price": 20.0},
|
||||
]
|
||||
for row in bad_data:
|
||||
with pytest.raises(ValueError):
|
||||
table.add(
|
||||
data=[row],
|
||||
)
|
||||
|
||||
table.add(
|
||||
[
|
||||
{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
|
||||
{"vector": [2.1, 4.1], "item": "foo", "price": 9.0},
|
||||
{"vector": [np.nan], "item": "bar", "price": 20.0},
|
||||
{"vector": [5], "item": "bar", "price": 20.0},
|
||||
{"vector": [np.nan, np.nan], "item": "bar", "price": 20.0},
|
||||
],
|
||||
on_bad_vectors="drop",
|
||||
)
|
||||
assert len(table) == 2
|
||||
table.delete("true")
|
||||
|
||||
# We can fill bad input with some value
|
||||
table.add(
|
||||
data=[
|
||||
{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
|
||||
{"vector": [np.nan], "item": "bar", "price": 20.0},
|
||||
{"vector": [np.nan, np.nan], "item": "bar", "price": 20.0},
|
||||
],
|
||||
on_bad_vectors="fill",
|
||||
fill_value=0.0,
|
||||
)
|
||||
assert len(table) == 3
|
||||
arrow_tbl = table.search().where("item == 'bar'").to_arrow()
|
||||
v = arrow_tbl["vector"].to_pylist()[0]
|
||||
assert np.allclose(v, np.array([0.0, 0.0]))
|
||||
|
||||
|
||||
def test_restore(mem_db: DBConnection):
|
||||
table = mem_db.create_table(
|
||||
"my_table",
|
||||
|
||||
@@ -4,6 +4,7 @@
|
||||
import pyarrow as pa
|
||||
import pytest
|
||||
from lancedb.util import tbl_to_tensor
|
||||
from lancedb.permutation import Permutation
|
||||
|
||||
torch = pytest.importorskip("torch")
|
||||
|
||||
@@ -16,3 +17,26 @@ def test_table_dataloader(mem_db):
|
||||
for batch in dataloader:
|
||||
assert batch.size(0) == 1
|
||||
assert batch.size(1) == 10
|
||||
|
||||
|
||||
def test_permutation_dataloader(mem_db):
|
||||
table = mem_db.create_table("test_table", pa.table({"a": range(1000)}))
|
||||
|
||||
permutation = Permutation.identity(table)
|
||||
dataloader = torch.utils.data.DataLoader(permutation, batch_size=10, shuffle=True)
|
||||
for batch in dataloader:
|
||||
assert batch["a"].size(0) == 10
|
||||
|
||||
permutation = permutation.with_format("torch")
|
||||
dataloader = torch.utils.data.DataLoader(permutation, batch_size=10, shuffle=True)
|
||||
for batch in dataloader:
|
||||
assert batch.size(0) == 10
|
||||
assert batch.size(1) == 1
|
||||
|
||||
permutation = permutation.with_format("torch_col")
|
||||
dataloader = torch.utils.data.DataLoader(
|
||||
permutation, collate_fn=lambda x: x, batch_size=10, shuffle=True
|
||||
)
|
||||
for batch in dataloader:
|
||||
assert batch.size(0) == 1
|
||||
assert batch.size(1) == 10
|
||||
|
||||
@@ -121,6 +121,32 @@ def test_value_to_sql_string(tmp_path):
|
||||
assert table.to_pandas().query("search == @value")["replace"].item() == value
|
||||
|
||||
|
||||
def test_value_to_sql_dict():
|
||||
# Simple flat struct
|
||||
assert value_to_sql({"a": 1, "b": "hello"}) == "named_struct('a', 1, 'b', 'hello')"
|
||||
|
||||
# Nested struct
|
||||
assert (
|
||||
value_to_sql({"outer": {"inner": 1}})
|
||||
== "named_struct('outer', named_struct('inner', 1))"
|
||||
)
|
||||
|
||||
# List inside struct
|
||||
assert value_to_sql({"a": [1, 2]}) == "named_struct('a', [1, 2])"
|
||||
|
||||
# Mixed types
|
||||
assert (
|
||||
value_to_sql({"name": "test", "count": 42, "rate": 3.14, "active": True})
|
||||
== "named_struct('name', 'test', 'count', 42, 'rate', 3.14, 'active', TRUE)"
|
||||
)
|
||||
|
||||
# Null value inside struct
|
||||
assert value_to_sql({"a": None}) == "named_struct('a', NULL)"
|
||||
|
||||
# Empty dict
|
||||
assert value_to_sql({}) == "named_struct()"
|
||||
|
||||
|
||||
def test_append_vector_columns():
|
||||
registry = EmbeddingFunctionRegistry.get_instance()
|
||||
registry.register("test")(MockTextEmbeddingFunction)
|
||||
@@ -292,18 +318,14 @@ class TestModel(lancedb.pydantic.LanceModel):
|
||||
lambda: pa.table({"a": [1], "b": [2]}),
|
||||
lambda: pa.table({"a": [1], "b": [2]}).to_reader(),
|
||||
lambda: iter(pa.table({"a": [1], "b": [2]}).to_batches()),
|
||||
lambda: (
|
||||
lance.write_dataset(
|
||||
pa.table({"a": [1], "b": [2]}),
|
||||
"memory://test",
|
||||
)
|
||||
),
|
||||
lambda: (
|
||||
lance.write_dataset(
|
||||
pa.table({"a": [1], "b": [2]}),
|
||||
"memory://test",
|
||||
).scanner()
|
||||
lambda: lance.write_dataset(
|
||||
pa.table({"a": [1], "b": [2]}),
|
||||
"memory://test",
|
||||
),
|
||||
lambda: lance.write_dataset(
|
||||
pa.table({"a": [1], "b": [2]}),
|
||||
"memory://test",
|
||||
).scanner(),
|
||||
lambda: pd.DataFrame({"a": [1], "b": [2]}),
|
||||
lambda: pl.DataFrame({"a": [1], "b": [2]}),
|
||||
lambda: pl.LazyFrame({"a": [1], "b": [2]}),
|
||||
|
||||
+1
-1
@@ -10,7 +10,7 @@ use arrow::{
|
||||
use futures::stream::StreamExt;
|
||||
use lancedb::arrow::SendableRecordBatchStream;
|
||||
use pyo3::{
|
||||
exceptions::PyStopAsyncIteration, pyclass, pymethods, Bound, Py, PyAny, PyRef, PyResult, Python,
|
||||
Bound, Py, PyAny, PyRef, PyResult, Python, exceptions::PyStopAsyncIteration, pyclass, pymethods,
|
||||
};
|
||||
use pyo3_async_runtimes::tokio::future_into_py;
|
||||
|
||||
|
||||
@@ -9,10 +9,10 @@ use lancedb::{
|
||||
database::{CreateTableMode, Database, ReadConsistency},
|
||||
};
|
||||
use pyo3::{
|
||||
Bound, FromPyObject, Py, PyAny, PyRef, PyResult, Python,
|
||||
exceptions::{PyRuntimeError, PyValueError},
|
||||
pyclass, pyfunction, pymethods,
|
||||
types::{PyDict, PyDictMethods},
|
||||
Bound, FromPyObject, Py, PyAny, PyRef, PyResult, Python,
|
||||
};
|
||||
use pyo3_async_runtimes::tokio::future_into_py;
|
||||
|
||||
@@ -121,7 +121,8 @@ impl Connection {
|
||||
|
||||
let mode = Self::parse_create_mode_str(mode)?;
|
||||
|
||||
let batches = ArrowArrayStreamReader::from_pyarrow_bound(&data)?;
|
||||
let batches: Box<dyn arrow::array::RecordBatchReader + Send> =
|
||||
Box::new(ArrowArrayStreamReader::from_pyarrow_bound(&data)?);
|
||||
|
||||
let mut builder = inner.create_table(name, batches).mode(mode);
|
||||
|
||||
|
||||
+1
-1
@@ -2,10 +2,10 @@
|
||||
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
|
||||
use pyo3::{
|
||||
PyErr, PyResult, Python,
|
||||
exceptions::{PyIOError, PyNotImplementedError, PyOSError, PyRuntimeError, PyValueError},
|
||||
intern,
|
||||
types::{PyAnyMethods, PyNone},
|
||||
PyErr, PyResult, Python,
|
||||
};
|
||||
|
||||
use lancedb::error::Error as LanceError;
|
||||
|
||||
+18
-12
@@ -3,17 +3,17 @@
|
||||
|
||||
use lancedb::index::vector::{IvfFlatIndexBuilder, IvfRqIndexBuilder, IvfSqIndexBuilder};
|
||||
use lancedb::index::{
|
||||
Index as LanceDbIndex,
|
||||
scalar::{BTreeIndexBuilder, FtsIndexBuilder},
|
||||
vector::{IvfHnswPqIndexBuilder, IvfHnswSqIndexBuilder, IvfPqIndexBuilder},
|
||||
Index as LanceDbIndex,
|
||||
};
|
||||
use pyo3::types::PyStringMethods;
|
||||
use pyo3::IntoPyObject;
|
||||
use pyo3::types::PyStringMethods;
|
||||
use pyo3::{
|
||||
Bound, FromPyObject, PyAny, PyResult, Python,
|
||||
exceptions::{PyKeyError, PyValueError},
|
||||
intern, pyclass, pymethods,
|
||||
types::PyAnyMethods,
|
||||
Bound, FromPyObject, PyAny, PyResult, Python,
|
||||
};
|
||||
|
||||
use crate::util::parse_distance_type;
|
||||
@@ -41,7 +41,12 @@ pub fn extract_index_params(source: &Option<Bound<'_, PyAny>>) -> PyResult<Lance
|
||||
let inner_opts = FtsIndexBuilder::default()
|
||||
.base_tokenizer(params.base_tokenizer)
|
||||
.language(¶ms.language)
|
||||
.map_err(|_| PyValueError::new_err(format!("LanceDB does not support the requested language: '{}'", params.language)))?
|
||||
.map_err(|_| {
|
||||
PyValueError::new_err(format!(
|
||||
"LanceDB does not support the requested language: '{}'",
|
||||
params.language
|
||||
))
|
||||
})?
|
||||
.with_position(params.with_position)
|
||||
.lower_case(params.lower_case)
|
||||
.max_token_length(params.max_token_length)
|
||||
@@ -52,7 +57,7 @@ pub fn extract_index_params(source: &Option<Bound<'_, PyAny>>) -> PyResult<Lance
|
||||
.ngram_max_length(params.ngram_max_length)
|
||||
.ngram_prefix_only(params.prefix_only);
|
||||
Ok(LanceDbIndex::FTS(inner_opts))
|
||||
},
|
||||
}
|
||||
"IvfFlat" => {
|
||||
let params = source.extract::<IvfFlatParams>()?;
|
||||
let distance_type = parse_distance_type(params.distance_type)?;
|
||||
@@ -64,10 +69,11 @@ pub fn extract_index_params(source: &Option<Bound<'_, PyAny>>) -> PyResult<Lance
|
||||
ivf_flat_builder = ivf_flat_builder.num_partitions(num_partitions);
|
||||
}
|
||||
if let Some(target_partition_size) = params.target_partition_size {
|
||||
ivf_flat_builder = ivf_flat_builder.target_partition_size(target_partition_size);
|
||||
ivf_flat_builder =
|
||||
ivf_flat_builder.target_partition_size(target_partition_size);
|
||||
}
|
||||
Ok(LanceDbIndex::IvfFlat(ivf_flat_builder))
|
||||
},
|
||||
}
|
||||
"IvfPq" => {
|
||||
let params = source.extract::<IvfPqParams>()?;
|
||||
let distance_type = parse_distance_type(params.distance_type)?;
|
||||
@@ -86,7 +92,7 @@ pub fn extract_index_params(source: &Option<Bound<'_, PyAny>>) -> PyResult<Lance
|
||||
ivf_pq_builder = ivf_pq_builder.num_sub_vectors(num_sub_vectors);
|
||||
}
|
||||
Ok(LanceDbIndex::IvfPq(ivf_pq_builder))
|
||||
},
|
||||
}
|
||||
"IvfSq" => {
|
||||
let params = source.extract::<IvfSqParams>()?;
|
||||
let distance_type = parse_distance_type(params.distance_type)?;
|
||||
@@ -101,7 +107,7 @@ pub fn extract_index_params(source: &Option<Bound<'_, PyAny>>) -> PyResult<Lance
|
||||
ivf_sq_builder = ivf_sq_builder.target_partition_size(target_partition_size);
|
||||
}
|
||||
Ok(LanceDbIndex::IvfSq(ivf_sq_builder))
|
||||
},
|
||||
}
|
||||
"IvfRq" => {
|
||||
let params = source.extract::<IvfRqParams>()?;
|
||||
let distance_type = parse_distance_type(params.distance_type)?;
|
||||
@@ -117,7 +123,7 @@ pub fn extract_index_params(source: &Option<Bound<'_, PyAny>>) -> PyResult<Lance
|
||||
ivf_rq_builder = ivf_rq_builder.target_partition_size(target_partition_size);
|
||||
}
|
||||
Ok(LanceDbIndex::IvfRq(ivf_rq_builder))
|
||||
},
|
||||
}
|
||||
"HnswPq" => {
|
||||
let params = source.extract::<IvfHnswPqParams>()?;
|
||||
let distance_type = parse_distance_type(params.distance_type)?;
|
||||
@@ -138,7 +144,7 @@ pub fn extract_index_params(source: &Option<Bound<'_, PyAny>>) -> PyResult<Lance
|
||||
hnsw_pq_builder = hnsw_pq_builder.num_sub_vectors(num_sub_vectors);
|
||||
}
|
||||
Ok(LanceDbIndex::IvfHnswPq(hnsw_pq_builder))
|
||||
},
|
||||
}
|
||||
"HnswSq" => {
|
||||
let params = source.extract::<IvfHnswSqParams>()?;
|
||||
let distance_type = parse_distance_type(params.distance_type)?;
|
||||
@@ -155,7 +161,7 @@ pub fn extract_index_params(source: &Option<Bound<'_, PyAny>>) -> PyResult<Lance
|
||||
hnsw_sq_builder = hnsw_sq_builder.target_partition_size(target_partition_size);
|
||||
}
|
||||
Ok(LanceDbIndex::IvfHnswSq(hnsw_sq_builder))
|
||||
},
|
||||
}
|
||||
not_supported => Err(PyValueError::new_err(format!(
|
||||
"Invalid index type '{}'. Must be one of BTree, Bitmap, LabelList, FTS, IvfPq, IvfSq, IvfHnswPq, or IvfHnswSq",
|
||||
not_supported
|
||||
|
||||
+3
-3
@@ -2,14 +2,14 @@
|
||||
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
|
||||
use arrow::RecordBatchStream;
|
||||
use connection::{connect, Connection};
|
||||
use connection::{Connection, connect};
|
||||
use env_logger::Env;
|
||||
use index::IndexConfig;
|
||||
use permutation::{PyAsyncPermutationBuilder, PyPermutationReader};
|
||||
use pyo3::{
|
||||
pymodule,
|
||||
Bound, PyResult, Python, pymodule,
|
||||
types::{PyModule, PyModuleMethods},
|
||||
wrap_pyfunction, Bound, PyResult, Python,
|
||||
wrap_pyfunction,
|
||||
};
|
||||
use query::{FTSQuery, HybridQuery, Query, VectorQuery};
|
||||
use session::Session;
|
||||
|
||||
@@ -6,7 +6,7 @@ use std::sync::{Arc, Mutex};
|
||||
use crate::{
|
||||
arrow::RecordBatchStream, connection::Connection, error::PythonErrorExt, table::Table,
|
||||
};
|
||||
use arrow::pyarrow::ToPyArrow;
|
||||
use arrow::pyarrow::{PyArrowType, ToPyArrow};
|
||||
use lancedb::{
|
||||
dataloader::permutation::{
|
||||
builder::{PermutationBuilder as LancePermutationBuilder, ShuffleStrategy},
|
||||
@@ -16,17 +16,32 @@ use lancedb::{
|
||||
query::Select,
|
||||
};
|
||||
use pyo3::{
|
||||
Bound, PyAny, PyRef, PyRefMut, PyResult, Python,
|
||||
exceptions::PyRuntimeError,
|
||||
pyclass, pymethods,
|
||||
types::{PyAnyMethods, PyDict, PyDictMethods, PyType},
|
||||
Bound, PyAny, PyRef, PyRefMut, PyResult, Python,
|
||||
};
|
||||
use pyo3_async_runtimes::tokio::future_into_py;
|
||||
|
||||
fn table_from_py<'a>(table: Bound<'a, PyAny>) -> PyResult<Bound<'a, Table>> {
|
||||
if table.hasattr("_inner")? {
|
||||
Ok(table.getattr("_inner")?.downcast_into::<Table>()?)
|
||||
} else if table.hasattr("_table")? {
|
||||
Ok(table
|
||||
.getattr("_table")?
|
||||
.getattr("_inner")?
|
||||
.downcast_into::<Table>()?)
|
||||
} else {
|
||||
Err(PyRuntimeError::new_err(
|
||||
"Provided table does not appear to be a Table or RemoteTable instance",
|
||||
))
|
||||
}
|
||||
}
|
||||
|
||||
/// Create a permutation builder for the given table
|
||||
#[pyo3::pyfunction]
|
||||
pub fn async_permutation_builder(table: Bound<'_, PyAny>) -> PyResult<PyAsyncPermutationBuilder> {
|
||||
let table = table.getattr("_inner")?.downcast_into::<Table>()?;
|
||||
let table = table_from_py(table)?;
|
||||
let inner_table = table.borrow().inner_ref()?.clone();
|
||||
let inner_builder = LancePermutationBuilder::new(inner_table);
|
||||
|
||||
@@ -250,10 +265,8 @@ impl PyPermutationReader {
|
||||
permutation_table: Option<Bound<'py, PyAny>>,
|
||||
split: u64,
|
||||
) -> PyResult<Bound<'py, PyAny>> {
|
||||
let base_table = base_table.getattr("_inner")?.downcast_into::<Table>()?;
|
||||
let permutation_table = permutation_table
|
||||
.map(|p| PyResult::Ok(p.getattr("_inner")?.downcast_into::<Table>()?))
|
||||
.transpose()?;
|
||||
let base_table = table_from_py(base_table)?;
|
||||
let permutation_table = permutation_table.map(table_from_py).transpose()?;
|
||||
|
||||
let base_table = base_table.borrow().inner_ref()?.base_table().clone();
|
||||
let permutation_table = permutation_table
|
||||
@@ -328,4 +341,21 @@ impl PyPermutationReader {
|
||||
Ok(RecordBatchStream::new(stream))
|
||||
})
|
||||
}
|
||||
|
||||
#[pyo3(signature = (indices, *, selection=None))]
|
||||
pub fn take_offsets<'py>(
|
||||
slf: PyRef<'py, Self>,
|
||||
indices: Vec<u64>,
|
||||
selection: Option<Bound<'py, PyAny>>,
|
||||
) -> PyResult<Bound<'py, PyAny>> {
|
||||
let selection = Self::parse_selection(selection)?;
|
||||
let reader = slf.reader.clone();
|
||||
future_into_py(slf.py(), async move {
|
||||
let batch = reader
|
||||
.take_offsets(&indices, selection)
|
||||
.await
|
||||
.infer_error()?;
|
||||
Ok(PyArrowType(batch))
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
+8
-8
@@ -4,9 +4,9 @@
|
||||
use std::sync::Arc;
|
||||
use std::time::Duration;
|
||||
|
||||
use arrow::array::make_array;
|
||||
use arrow::array::Array;
|
||||
use arrow::array::ArrayData;
|
||||
use arrow::array::make_array;
|
||||
use arrow::pyarrow::FromPyArrow;
|
||||
use arrow::pyarrow::IntoPyArrow;
|
||||
use arrow::pyarrow::ToPyArrow;
|
||||
@@ -22,23 +22,23 @@ use lancedb::query::{
|
||||
VectorQuery as LanceDbVectorQuery,
|
||||
};
|
||||
use lancedb::table::AnyQuery;
|
||||
use pyo3::prelude::{PyAnyMethods, PyDictMethods};
|
||||
use pyo3::pyfunction;
|
||||
use pyo3::pymethods;
|
||||
use pyo3::types::PyList;
|
||||
use pyo3::types::{PyDict, PyString};
|
||||
use pyo3::Bound;
|
||||
use pyo3::IntoPyObject;
|
||||
use pyo3::PyAny;
|
||||
use pyo3::PyRef;
|
||||
use pyo3::PyResult;
|
||||
use pyo3::Python;
|
||||
use pyo3::{exceptions::PyRuntimeError, FromPyObject};
|
||||
use pyo3::prelude::{PyAnyMethods, PyDictMethods};
|
||||
use pyo3::pyfunction;
|
||||
use pyo3::pymethods;
|
||||
use pyo3::types::PyList;
|
||||
use pyo3::types::{PyDict, PyString};
|
||||
use pyo3::{FromPyObject, exceptions::PyRuntimeError};
|
||||
use pyo3::{PyErr, pyclass};
|
||||
use pyo3::{
|
||||
exceptions::{PyNotImplementedError, PyValueError},
|
||||
intern,
|
||||
};
|
||||
use pyo3::{pyclass, PyErr};
|
||||
use pyo3_async_runtimes::tokio::future_into_py;
|
||||
|
||||
use crate::util::parse_distance_type;
|
||||
|
||||
@@ -4,7 +4,7 @@
|
||||
use std::sync::Arc;
|
||||
|
||||
use lancedb::{ObjectStoreRegistry, Session as LanceSession};
|
||||
use pyo3::{pyclass, pymethods, PyResult};
|
||||
use pyo3::{PyResult, pyclass, pymethods};
|
||||
|
||||
/// A session for managing caches and object stores across LanceDB operations.
|
||||
///
|
||||
|
||||
@@ -66,12 +66,11 @@ impl StorageOptionsProvider for PyStorageOptionsProviderWrapper {
|
||||
.inner
|
||||
.bind(py)
|
||||
.call_method0("fetch_storage_options")
|
||||
.map_err(|e| lance_core::Error::IO {
|
||||
source: Box::new(std::io::Error::other(format!(
|
||||
.map_err(|e| {
|
||||
lance_core::Error::io_source(Box::new(std::io::Error::other(format!(
|
||||
"Failed to call fetch_storage_options: {}",
|
||||
e
|
||||
))),
|
||||
location: snafu::location!(),
|
||||
))))
|
||||
})?;
|
||||
|
||||
// If result is None, return None
|
||||
@@ -81,26 +80,25 @@ impl StorageOptionsProvider for PyStorageOptionsProviderWrapper {
|
||||
|
||||
// Extract the result dict - should be a flat Map<String, String>
|
||||
let result_dict = result.downcast::<PyDict>().map_err(|_| {
|
||||
lance_core::Error::InvalidInput {
|
||||
source: "fetch_storage_options() must return None or a dict of string key-value pairs".into(),
|
||||
location: snafu::location!(),
|
||||
}
|
||||
lance_core::Error::invalid_input(
|
||||
"fetch_storage_options() must return None or a dict of string key-value pairs",
|
||||
)
|
||||
})?;
|
||||
|
||||
// Convert all entries to HashMap<String, String>
|
||||
let mut storage_options = HashMap::new();
|
||||
for (key, value) in result_dict.iter() {
|
||||
let key_str: String = key.extract().map_err(|e| {
|
||||
lance_core::Error::InvalidInput {
|
||||
source: format!("Storage option key must be a string: {}", e).into(),
|
||||
location: snafu::location!(),
|
||||
}
|
||||
lance_core::Error::invalid_input(format!(
|
||||
"Storage option key must be a string: {}",
|
||||
e
|
||||
))
|
||||
})?;
|
||||
let value_str: String = value.extract().map_err(|e| {
|
||||
lance_core::Error::InvalidInput {
|
||||
source: format!("Storage option value must be a string: {}", e).into(),
|
||||
location: snafu::location!(),
|
||||
}
|
||||
lance_core::Error::invalid_input(format!(
|
||||
"Storage option value must be a string: {}",
|
||||
e
|
||||
))
|
||||
})?;
|
||||
storage_options.insert(key_str, value_str);
|
||||
}
|
||||
@@ -109,13 +107,10 @@ impl StorageOptionsProvider for PyStorageOptionsProviderWrapper {
|
||||
})
|
||||
})
|
||||
.await
|
||||
.map_err(|e| lance_core::Error::IO {
|
||||
source: Box::new(std::io::Error::other(format!(
|
||||
.map_err(|e| lance_core::Error::io_source(Box::new(std::io::Error::other(format!(
|
||||
"Task join error: {}",
|
||||
e
|
||||
))),
|
||||
location: snafu::location!(),
|
||||
})?
|
||||
)))))?
|
||||
}
|
||||
|
||||
fn provider_id(&self) -> String {
|
||||
|
||||
+29
-10
@@ -5,8 +5,9 @@ use std::{collections::HashMap, sync::Arc};
|
||||
use crate::{
|
||||
connection::Connection,
|
||||
error::PythonErrorExt,
|
||||
index::{extract_index_params, IndexConfig},
|
||||
index::{IndexConfig, extract_index_params},
|
||||
query::{Query, TakeQuery},
|
||||
table::scannable::PyScannable,
|
||||
};
|
||||
use arrow::{
|
||||
datatypes::{DataType, Schema},
|
||||
@@ -18,13 +19,15 @@ use lancedb::table::{
|
||||
Table as LanceDbTable,
|
||||
};
|
||||
use pyo3::{
|
||||
Bound, FromPyObject, PyAny, PyRef, PyResult, Python,
|
||||
exceptions::{PyKeyError, PyRuntimeError, PyValueError},
|
||||
pyclass, pymethods,
|
||||
types::{IntoPyDict, PyAnyMethods, PyDict, PyDictMethods},
|
||||
Bound, FromPyObject, PyAny, PyRef, PyResult, Python,
|
||||
};
|
||||
use pyo3_async_runtimes::tokio::future_into_py;
|
||||
|
||||
mod scannable;
|
||||
|
||||
/// Statistics about a compaction operation.
|
||||
#[pyclass(get_all)]
|
||||
#[derive(Clone, Debug)]
|
||||
@@ -109,19 +112,24 @@ impl From<lancedb::table::AddResult> for AddResult {
|
||||
#[pyclass(get_all)]
|
||||
#[derive(Clone, Debug)]
|
||||
pub struct DeleteResult {
|
||||
pub num_deleted_rows: u64,
|
||||
pub version: u64,
|
||||
}
|
||||
|
||||
#[pymethods]
|
||||
impl DeleteResult {
|
||||
pub fn __repr__(&self) -> String {
|
||||
format!("DeleteResult(version={})", self.version)
|
||||
format!(
|
||||
"DeleteResult(num_deleted_rows={}, version={})",
|
||||
self.num_deleted_rows, self.version
|
||||
)
|
||||
}
|
||||
}
|
||||
|
||||
impl From<lancedb::table::DeleteResult> for DeleteResult {
|
||||
fn from(result: lancedb::table::DeleteResult) -> Self {
|
||||
Self {
|
||||
num_deleted_rows: result.num_deleted_rows,
|
||||
version: result.version,
|
||||
}
|
||||
}
|
||||
@@ -293,11 +301,10 @@ impl Table {
|
||||
|
||||
pub fn add<'a>(
|
||||
self_: PyRef<'a, Self>,
|
||||
data: Bound<'_, PyAny>,
|
||||
data: PyScannable,
|
||||
mode: String,
|
||||
) -> PyResult<Bound<'a, PyAny>> {
|
||||
let batches = ArrowArrayStreamReader::from_pyarrow_bound(&data)?;
|
||||
let mut op = self_.inner_ref()?.add(batches);
|
||||
let mut op = self_.inner_ref()?.add(data);
|
||||
if mode == "append" {
|
||||
op = op.mode(AddDataMode::Append);
|
||||
} else if mode == "overwrite" {
|
||||
@@ -502,6 +509,20 @@ impl Table {
|
||||
future_into_py(self_.py(), async move { inner.uri().await.infer_error() })
|
||||
}
|
||||
|
||||
pub fn initial_storage_options(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
|
||||
let inner = self_.inner_ref()?.clone();
|
||||
future_into_py(self_.py(), async move {
|
||||
Ok(inner.initial_storage_options().await)
|
||||
})
|
||||
}
|
||||
|
||||
pub fn latest_storage_options(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
|
||||
let inner = self_.inner_ref()?.clone();
|
||||
future_into_py(self_.py(), async move {
|
||||
inner.latest_storage_options().await.infer_error()
|
||||
})
|
||||
}
|
||||
|
||||
pub fn __repr__(&self) -> String {
|
||||
match &self.inner {
|
||||
None => format!("ClosedTable({})", self.name),
|
||||
@@ -521,7 +542,7 @@ impl Table {
|
||||
let inner = self_.inner_ref()?.clone();
|
||||
future_into_py(self_.py(), async move {
|
||||
let versions = inner.list_versions().await.infer_error()?;
|
||||
let versions_as_dict = Python::attach(|py| {
|
||||
Python::attach(|py| {
|
||||
versions
|
||||
.iter()
|
||||
.map(|v| {
|
||||
@@ -538,9 +559,7 @@ impl Table {
|
||||
Ok(dict.unbind())
|
||||
})
|
||||
.collect::<PyResult<Vec<_>>>()
|
||||
});
|
||||
|
||||
versions_as_dict
|
||||
})
|
||||
})
|
||||
}
|
||||
|
||||
|
||||
@@ -0,0 +1,145 @@
|
||||
// SPDX-License-Identifier: Apache-2.0
|
||||
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
|
||||
use std::sync::Arc;
|
||||
|
||||
use arrow::{
|
||||
datatypes::{Schema, SchemaRef},
|
||||
ffi_stream::ArrowArrayStreamReader,
|
||||
pyarrow::{FromPyArrow, PyArrowType},
|
||||
};
|
||||
use futures::StreamExt;
|
||||
use lancedb::{
|
||||
Error,
|
||||
arrow::{SendableRecordBatchStream, SimpleRecordBatchStream},
|
||||
data::scannable::Scannable,
|
||||
};
|
||||
use pyo3::{FromPyObject, Py, PyAny, Python, types::PyAnyMethods};
|
||||
|
||||
/// Adapter that implements Scannable for a Python reader factory callable.
|
||||
///
|
||||
/// This holds a Python callable that returns a RecordBatchReader when called.
|
||||
/// For rescannable sources, the callable can be invoked multiple times to
|
||||
/// get fresh readers.
|
||||
pub struct PyScannable {
|
||||
/// Python callable that returns a RecordBatchReader
|
||||
reader_factory: Py<PyAny>,
|
||||
schema: SchemaRef,
|
||||
num_rows: Option<usize>,
|
||||
rescannable: bool,
|
||||
}
|
||||
|
||||
impl std::fmt::Debug for PyScannable {
|
||||
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
|
||||
f.debug_struct("PyScannable")
|
||||
.field("schema", &self.schema)
|
||||
.field("num_rows", &self.num_rows)
|
||||
.field("rescannable", &self.rescannable)
|
||||
.finish()
|
||||
}
|
||||
}
|
||||
|
||||
impl Scannable for PyScannable {
|
||||
fn schema(&self) -> SchemaRef {
|
||||
self.schema.clone()
|
||||
}
|
||||
|
||||
fn scan_as_stream(&mut self) -> SendableRecordBatchStream {
|
||||
let reader: Result<ArrowArrayStreamReader, Error> = {
|
||||
Python::attach(|py| {
|
||||
let result =
|
||||
self.reader_factory
|
||||
.call0(py)
|
||||
.map_err(|e| lancedb::Error::Runtime {
|
||||
message: format!("Python reader factory failed: {}", e),
|
||||
})?;
|
||||
ArrowArrayStreamReader::from_pyarrow_bound(result.bind(py)).map_err(|e| {
|
||||
lancedb::Error::Runtime {
|
||||
message: format!("Failed to create Arrow reader from Python: {}", e),
|
||||
}
|
||||
})
|
||||
})
|
||||
};
|
||||
|
||||
// Reader is blocking but stream is non-blocking, so we need to spawn a task to pull.
|
||||
let (tx, rx) = tokio::sync::mpsc::channel(1);
|
||||
|
||||
let join_handle = tokio::task::spawn_blocking(move || {
|
||||
let reader = match reader {
|
||||
Ok(reader) => reader,
|
||||
Err(e) => {
|
||||
let _ = tx.blocking_send(Err(e));
|
||||
return;
|
||||
}
|
||||
};
|
||||
for batch in reader {
|
||||
match batch {
|
||||
Ok(batch) => {
|
||||
if tx.blocking_send(Ok(batch)).is_err() {
|
||||
// Receiver dropped, stop processing
|
||||
break;
|
||||
}
|
||||
}
|
||||
Err(source) => {
|
||||
let _ = tx.blocking_send(Err(Error::Arrow { source }));
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
let schema = self.schema.clone();
|
||||
let stream = futures::stream::unfold(
|
||||
(rx, Some(join_handle)),
|
||||
|(mut rx, join_handle)| async move {
|
||||
match rx.recv().await {
|
||||
Some(Ok(batch)) => Some((Ok(batch), (rx, join_handle))),
|
||||
Some(Err(e)) => Some((Err(e), (rx, join_handle))),
|
||||
None => {
|
||||
// Channel closed. Check if the task panicked — a panic
|
||||
// drops the sender without sending an error, so without
|
||||
// this check we'd silently return a truncated stream.
|
||||
if let Some(handle) = join_handle
|
||||
&& let Err(join_err) = handle.await
|
||||
{
|
||||
return Some((
|
||||
Err(Error::Runtime {
|
||||
message: format!("Reader task panicked: {}", join_err),
|
||||
}),
|
||||
(rx, None),
|
||||
));
|
||||
}
|
||||
None
|
||||
}
|
||||
}
|
||||
},
|
||||
);
|
||||
Box::pin(SimpleRecordBatchStream::new(stream.fuse(), schema))
|
||||
}
|
||||
|
||||
fn num_rows(&self) -> Option<usize> {
|
||||
self.num_rows
|
||||
}
|
||||
|
||||
fn rescannable(&self) -> bool {
|
||||
self.rescannable
|
||||
}
|
||||
}
|
||||
|
||||
impl<'py> FromPyObject<'py> for PyScannable {
|
||||
fn extract_bound(ob: &pyo3::Bound<'py, PyAny>) -> pyo3::PyResult<Self> {
|
||||
// Convert from Scannable dataclass.
|
||||
let schema: PyArrowType<Schema> = ob.getattr("schema")?.extract()?;
|
||||
let schema = Arc::new(schema.0);
|
||||
let num_rows: Option<usize> = ob.getattr("num_rows")?.extract()?;
|
||||
let rescannable: bool = ob.getattr("rescannable")?.extract()?;
|
||||
let reader_factory: Py<PyAny> = ob.getattr("reader")?.unbind();
|
||||
|
||||
Ok(Self {
|
||||
schema,
|
||||
reader_factory,
|
||||
num_rows,
|
||||
rescannable,
|
||||
})
|
||||
}
|
||||
}
|
||||
+2
-1
@@ -5,8 +5,9 @@ use std::sync::Mutex;
|
||||
|
||||
use lancedb::DistanceType;
|
||||
use pyo3::{
|
||||
PyResult,
|
||||
exceptions::{PyRuntimeError, PyValueError},
|
||||
pyfunction, PyResult,
|
||||
pyfunction,
|
||||
};
|
||||
|
||||
/// A wrapper around a rust builder
|
||||
|
||||
Generated
+5349
File diff suppressed because it is too large
Load Diff
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user