Compare commits

...
Author SHA1 Message Date
lancedb automation 2974b7e5c6 chore: update lance dependency to v6.0.0-beta.6 2026-04-29 07:27:24 +00:00
Lance Release 4dcd7f4314 Bump version: 0.28.0-beta.9 → 0.28.0-beta.10 2026-04-28 13:29:26 +00:00
Lance Release 2e36cd9dad Bump version: 0.31.0-beta.9 → 0.31.0-beta.10 2026-04-28 13:29:00 +00:00
Weston PaceandClaude Opus 4.6 f31e27768a fix: address RUSTSEC-2026-0104 cargo-deny advisory (#3326)
## Summary

- Update `rustls-webpki` 0.103.10 → 0.103.13 to fix RUSTSEC-2026-0104
(reachable panic in CRL parsing)
- Add advisory ignore for the legacy `rustls-webpki` 0.101.7 copy pinned
to the aws-smithy/rustls 0.21 chain (same chain already exempted for
RUSTSEC-2026-0098/0099)

Fixes the `deny` CI job failure seen in #3325.

## Test plan

- [x] `cargo deny check advisories` passes locally

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-27 17:56:10 -07:00
LanceDB Robot b84150a53e chore: update lance dependency to v6.0.0-beta.4 (#3325)
## Summary

- Updates Lance Rust dependencies to `6.0.0-beta.4` using
`ci/set_lance_version.py`.
- Updates the Java `lance-core.version` property to `6.0.0-beta.4`.
- Triggering Lance tag:
https://github.com/lance-format/lance/releases/tag/v6.0.0-beta.4

## Verification

- `cargo clippy --workspace --tests --all-features -- -D warnings`
- `cargo fmt --all`
2026-04-27 15:13:07 -07:00
Will JonesandClaude Opus 4.7 d135c18db6 ci: add cargo-deny configuration and CI check (#3307)
Adds a `deny.toml` at the workspace root and a `deny` CI job that runs
`cargo deny check` on every PR. Catches yanked crates, license drift,
banned or wildcard dependencies, unapproved sources, and new RUSTSEC
advisories.

As part of wiring this up:

- Updated `aws-lc-rs` 1.13.0 → 1.16.3 / `aws-lc-sys` 0.28.0 → 0.40.0 to
  clear four 2026 AWS-LC advisories (timing side-channel, PKCS7 bypass,
  CRL scope). Removed the `=0.28.0` workaround pin; the original build
  failure no longer reproduces.
- Updated `bytes`, `zlib-rs`, `rand`, `rustls-webpki`, `lz4_flex` to
  clear their current advisories.
- Marked `lancedb-nodejs` and `lancedb-python` as `publish = false` and
  pinned `lzma-sys` from `*` to `0.1` so `bans.wildcards = "deny"` can
  be enforced.

10 remaining advisories have no safe upgrade available (transitive via
opendal, lance, datafusion, async-openai, aws-sdk on the legacy rustls
0.21 chain). Each is ignored in `deny.toml` with a per-entry rationale
and a link to the RUSTSEC advisory. New advisories still fail CI.

Fixes #3297

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-24 20:53:15 -07:00
Will JonesandClaude Sonnet 4.6 ef399de092 ci: switch PyPI publish to OIDC trusted publishing (#3302)
## Summary

- Replaces `LANCEDB_PYPI_API_TOKEN` (long-lived token) with OIDC trusted
publishing via `pypa/gh-action-pypi-publish`
- Adds `id-token: write` permission to linux/mac/windows jobs
- Removes `twine`-based upload and the `pypi_token` input from
`upload_wheel` composite action
- Enables PEP 740 Sigstore attestations on published wheels as a bonus

After merging, rotate/revoke the `LANCEDB_PYPI_API_TOKEN` secret.

Closes #3294

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-24 20:53:06 -07:00
Will Jones 0d767abd0e ci: add Dependabot config for shipped Rust binaries (#3300)
Adds `.github/dependabot.yml` enabling weekly cargo update PRs for the
root workspace, which produces the Rust binaries we ship: the Node.js
and Python native extensions. The `rust/lancedb` library crate shares
the same lockfile — its consumers pick versions themselves, but bumping
transitive deps here keeps the shipped binaries current.

Also removes the misleading `exclude = ["python"]` line from the root
`Cargo.toml`: `python` is listed in `members`, and `cargo metadata`
confirms it's a workspace member, so the exclude was dead code that
implied the opposite.

Minor/patch updates are grouped to reduce PR noise.

Part of #3292. Only covers the cargo ecosystem; pip, npm, and
github-actions can follow.
2026-04-24 20:52:54 -07:00
37 changed files with 1085 additions and 757 deletions
+1 -1
View File
@@ -1,5 +1,5 @@
[tool.bumpversion]
current_version = "0.28.0-beta.9"
current_version = "0.28.0-beta.10"
parse = """(?x)
(?P<major>0|[1-9]\\d*)\\.
(?P<minor>0|[1-9]\\d*)\\.
+18
View File
@@ -0,0 +1,18 @@
version: 2
# Scope: the root Cargo workspace, which produces the Rust binaries we
# ship to users (the Node.js and Python native extensions). The
# `rust/lancedb` library crate shares the same lockfile; its consumers
# pick their own dependency versions, but bumping transitive deps here
# keeps the binaries we ship current.
updates:
- package-ecosystem: cargo
directory: /
schedule:
interval: weekly
open-pull-requests-limit: 10
groups:
rust-minor-patch:
update-types:
- minor
- patch
+9 -3
View File
@@ -21,6 +21,9 @@ jobs:
linux:
name: Python ${{ matrix.config.platform }} manylinux${{ matrix.config.manylinux }}
timeout-minutes: 60
permissions:
id-token: write
contents: read
strategy:
matrix:
config:
@@ -60,10 +63,12 @@ jobs:
- uses: ./.github/workflows/upload_wheel
if: startsWith(github.ref, 'refs/tags/python-v')
with:
pypi_token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
fury_token: ${{ secrets.FURY_TOKEN }}
mac:
timeout-minutes: 90
permissions:
id-token: write
contents: read
runs-on: ${{ matrix.config.runner }}
strategy:
matrix:
@@ -88,10 +93,12 @@ jobs:
- uses: ./.github/workflows/upload_wheel
if: startsWith(github.ref, 'refs/tags/python-v')
with:
pypi_token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
fury_token: ${{ secrets.FURY_TOKEN }}
windows:
timeout-minutes: 60
permissions:
id-token: write
contents: read
runs-on: windows-latest
steps:
- uses: actions/checkout@v4
@@ -110,7 +117,6 @@ jobs:
- uses: ./.github/workflows/upload_wheel
if: startsWith(github.ref, 'refs/tags/python-v')
with:
pypi_token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
fury_token: ${{ secrets.FURY_TOKEN }}
gh-release:
if: startsWith(github.ref, 'refs/tags/python-v')
+14
View File
@@ -9,7 +9,10 @@ on:
- Cargo.toml
- Cargo.lock
- rust-toolchain.toml
- deny.toml
- rust/**
- nodejs/Cargo.toml
- python/Cargo.toml
- .github/workflows/rust.yml
permissions:
@@ -56,6 +59,17 @@ jobs:
- name: Run clippy (without remote feature)
run: cargo clippy --profile ci --workspace --tests -- -D warnings
deny:
# Supply-chain checks: advisories, licenses, banned crates, and source
# restrictions. Configuration lives in `deny.toml` at the workspace root.
timeout-minutes: 10
runs-on: ubuntu-24.04
steps:
- uses: actions/checkout@v4
- uses: EmbarkStudios/cargo-deny-action@v2
with:
command: check advisories bans licenses sources
build-no-lock:
runs-on: ubuntu-24.04
timeout-minutes: 30
+10 -21
View File
@@ -2,9 +2,6 @@ name: upload-wheel
description: "Upload wheels to Pypi"
inputs:
pypi_token:
required: true
description: "release token for the repo"
fury_token:
required: true
description: "release token for the fury repo"
@@ -12,12 +9,6 @@ inputs:
runs:
using: "composite"
steps:
- name: Install dependencies
shell: bash
run: |
python -m pip install --upgrade pip
pip install twine
python3 -m pip install --upgrade pkginfo
- name: Choose repo
shell: bash
id: choose_repo
@@ -27,19 +18,17 @@ runs:
else
echo "repo=pypi" >> $GITHUB_OUTPUT
fi
- name: Publish to PyPI
- name: Publish to Fury
if: steps.choose_repo.outputs.repo == 'fury'
shell: bash
env:
FURY_TOKEN: ${{ inputs.fury_token }}
PYPI_TOKEN: ${{ inputs.pypi_token }}
run: |
if [[ ${{ steps.choose_repo.outputs.repo }} == fury ]]; then
WHEEL=$(ls target/wheels/lancedb-*.whl 2> /dev/null | head -n 1)
echo "Uploading $WHEEL to Fury"
curl -f -F package=@$WHEEL https://$FURY_TOKEN@push.fury.io/lancedb/
else
twine upload --repository ${{ steps.choose_repo.outputs.repo }} \
--username __token__ \
--password $PYPI_TOKEN \
target/wheels/lancedb-*.whl
fi
WHEEL=$(ls target/wheels/lancedb-*.whl 2> /dev/null | head -n 1)
echo "Uploading $WHEEL to Fury"
curl -f -F package=@$WHEEL https://$FURY_TOKEN@push.fury.io/lancedb/
- name: Publish to PyPI
if: steps.choose_repo.outputs.repo == 'pypi'
uses: pypa/gh-action-pypi-publish@release/v1
with:
packages-dir: target/wheels/
Generated
+747 -628
View File
File diff suppressed because it is too large Load Diff
+31 -33
View File
@@ -1,7 +1,5 @@
[workspace]
members = ["rust/lancedb", "nodejs", "python"]
# Python package needs to be built by maturin.
exclude = ["python"]
resolver = "2"
[workspace.package]
@@ -15,40 +13,40 @@ categories = ["database-implementations"]
rust-version = "1.91.0"
[workspace.dependencies]
lance = { "version" = "=6.0.0-beta.1", default-features = false, "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-core = { "version" = "=6.0.0-beta.1", "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-datagen = { "version" = "=6.0.0-beta.1", "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-file = { "version" = "=6.0.0-beta.1", "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-io = { "version" = "=6.0.0-beta.1", default-features = false, "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-index = { "version" = "=6.0.0-beta.1", "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-linalg = { "version" = "=6.0.0-beta.1", "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace = { "version" = "=6.0.0-beta.1", "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace-impls = { "version" = "=6.0.0-beta.1", default-features = false, "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-table = { "version" = "=6.0.0-beta.1", "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-testing = { "version" = "=6.0.0-beta.1", "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-datafusion = { "version" = "=6.0.0-beta.1", "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-encoding = { "version" = "=6.0.0-beta.1", "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-arrow = { "version" = "=6.0.0-beta.1", "tag" = "v6.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance = { "version" = "=6.0.0-beta.6", default-features = false, "tag" = "v6.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-core = { "version" = "=6.0.0-beta.6", "tag" = "v6.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-datagen = { "version" = "=6.0.0-beta.6", "tag" = "v6.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-file = { "version" = "=6.0.0-beta.6", "tag" = "v6.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-io = { "version" = "=6.0.0-beta.6", default-features = false, "tag" = "v6.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-index = { "version" = "=6.0.0-beta.6", "tag" = "v6.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-linalg = { "version" = "=6.0.0-beta.6", "tag" = "v6.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace = { "version" = "=6.0.0-beta.6", "tag" = "v6.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace-impls = { "version" = "=6.0.0-beta.6", default-features = false, "tag" = "v6.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-table = { "version" = "=6.0.0-beta.6", "tag" = "v6.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-testing = { "version" = "=6.0.0-beta.6", "tag" = "v6.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-datafusion = { "version" = "=6.0.0-beta.6", "tag" = "v6.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-encoding = { "version" = "=6.0.0-beta.6", "tag" = "v6.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-arrow = { "version" = "=6.0.0-beta.6", "tag" = "v6.0.0-beta.6", "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 }
arrow-array = "57.2"
arrow-data = "57.2"
arrow-ipc = "57.2"
arrow-ord = "57.2"
arrow-schema = "57.2"
arrow-select = "57.2"
arrow-cast = "57.2"
arrow = { version = "58.1", optional = false }
arrow-array = "58.1"
arrow-data = "58.1"
arrow-ipc = "58.1"
arrow-ord = "58.1"
arrow-schema = "58.1"
arrow-select = "58.1"
arrow-cast = "58.1"
async-trait = "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"
datafusion = { version = "53.1", default-features = false }
datafusion-catalog = "53.1"
datafusion-common = { version = "53.1", default-features = false }
datafusion-execution = "53.1"
datafusion-expr = "53.1"
datafusion-functions = "53.1"
datafusion-physical-plan = "53.1"
datafusion-physical-expr = "53.1"
datafusion-sql = "53.1"
env_logger = "0.11"
half = { "version" = "2.7.1", default-features = false, features = [
"num-traits",
+172
View File
@@ -0,0 +1,172 @@
# cargo-deny configuration for LanceDB.
#
# Run locally with `cargo deny check`. See
# https://embarkstudios.github.io/cargo-deny/ for the full reference.
# The set of target triples we care about. cargo-deny will only consider
# dependencies that are used on at least one of these targets. Keeping this
# explicit avoids noise from platform-specific crates (e.g. wasm, android,
# ios) that we never actually ship.
[graph]
targets = [
"x86_64-unknown-linux-gnu",
"aarch64-unknown-linux-gnu",
"x86_64-apple-darwin",
"aarch64-apple-darwin",
"x86_64-pc-windows-msvc",
"aarch64-pc-windows-msvc",
]
all-features = true
[output]
feature-depth = 1
# ---------------------------------------------------------------------------
# Advisories: security vulnerabilities and yanked crates.
# ---------------------------------------------------------------------------
[advisories]
version = 2
# Fail the check if any crate in the lockfile has been yanked from crates.io.
# Yanked crates are a signal the author retracted the release (often due to
# bugs or security issues) and should not be depended on.
yanked = "deny"
# Advisory IDs we have explicitly reviewed and chosen to accept. Every
# entry must include a rationale and, where possible, an upstream issue
# pointing to a fix. Revisit this list whenever dependencies are updated.
ignore = [
# rsa: Marvin Attack timing side-channel in PKCS#1 v1.5 decryption.
# Reached only through opendal → reqsign → rsa. We do not use RSA
# decryption in LanceDB ourselves; this is dormant in the signing path.
# No fixed release exists upstream as of this writing.
# https://rustsec.org/advisories/RUSTSEC-2023-0071
{ id = "RUSTSEC-2023-0071", reason = "rsa crate via opendal/reqsign; no fixed upstream release" },
# instant: unmaintained. Pulled in via backoff → instant. Upstream
# recommends switching to `web-time`; fix has to come from backoff.
# https://rustsec.org/advisories/RUSTSEC-2024-0384
{ id = "RUSTSEC-2024-0384", reason = "transitive via backoff; waiting on backoff replacement" },
# paste: unmaintained (author archived the repo). Used transitively by
# datafusion and the arrow ecosystem; widespread, no drop-in replacement.
# https://rustsec.org/advisories/RUSTSEC-2024-0436
{ id = "RUSTSEC-2024-0436", reason = "transitive via datafusion; awaiting ecosystem migration" },
# tantivy: segfault on malformed input due to missing bounds check.
# Pulled in via lance for full-text search. We only feed tantivy
# documents we construct ourselves, not attacker-controlled bytes.
# Tracked for a lance dependency bump.
# https://rustsec.org/advisories/RUSTSEC-2025-0003
{ id = "RUSTSEC-2025-0003", reason = "tantivy via lance; inputs are internally produced, not user-supplied bytes" },
# backoff: unmaintained. Reached only via async-openai. Replacement
# requires async-openai to migrate (or us to drop async-openai).
# https://rustsec.org/advisories/RUSTSEC-2025-0012
{ id = "RUSTSEC-2025-0012", reason = "transitive via async-openai; waiting on upstream migration" },
# number_prefix: unmaintained. Transitive via indicatif → hf-hub.
# No security impact, just maintenance status.
# https://rustsec.org/advisories/RUSTSEC-2025-0119
{ id = "RUSTSEC-2025-0119", reason = "transitive via hf-hub/indicatif; cosmetic formatting crate" },
# rustls-pemfile: unmaintained. Reached from two separate chains:
# rustls-native-certs 0.6 (via hyper-rustls 0.24) and object_store 0.12.
# Both upstream dependencies need to move before we can drop it.
# https://rustsec.org/advisories/RUSTSEC-2025-0134
{ id = "RUSTSEC-2025-0134", reason = "transitive via rustls-native-certs/object_store; waiting on upstream migration" },
# rustls-webpki 0.101.7 (old major line): name-constraint checks for
# URI / wildcard names. Pulled in only via the legacy rustls 0.21 chain
# from aws-smithy-http-client. The 0.103 line we actively use is patched.
# Clearing the 0.101 copy requires the aws-sdk chain to migrate off
# rustls 0.21.
# https://rustsec.org/advisories/RUSTSEC-2026-0098
# https://rustsec.org/advisories/RUSTSEC-2026-0099
{ id = "RUSTSEC-2026-0098", reason = "only affects rustls-webpki 0.101 from legacy aws-smithy/rustls 0.21 chain" },
{ id = "RUSTSEC-2026-0099", reason = "only affects rustls-webpki 0.101 from legacy aws-smithy/rustls 0.21 chain" },
# rustls-webpki 0.101.7: reachable panic in CRL parsing. Same legacy
# rustls 0.21 chain from aws-smithy-http-client as above. The 0.103 line
# we actively use is upgraded to 0.103.13 which contains the fix.
# https://rustsec.org/advisories/RUSTSEC-2026-0104
{ id = "RUSTSEC-2026-0104", reason = "only affects rustls-webpki 0.101 from legacy aws-smithy/rustls 0.21 chain" },
]
# ---------------------------------------------------------------------------
# Licenses: only allow licenses we've reviewed as compatible with Apache-2.0.
# ---------------------------------------------------------------------------
[licenses]
version = 2
# SPDX identifiers for licenses that are compatible with our Apache-2.0
# distribution. Additions require legal review.
allow = [
"Apache-2.0",
"Apache-2.0 WITH LLVM-exception",
"MIT",
"BSD-2-Clause",
"BSD-3-Clause",
"ISC",
"Unicode-3.0",
"Unicode-DFS-2016",
"Zlib",
"CC0-1.0",
"MPL-2.0",
"BSL-1.0",
"OpenSSL",
# 0BSD ("BSD Zero Clause") is effectively public domain — no attribution
# required. Pulled in by `mock_instant`.
"0BSD",
# bzip2-1.0.6 is the permissive upstream bzip2 license (BSD-like). Pulled
# in by `libbz2-rs-sys`, the pure-Rust bzip2 implementation.
"bzip2-1.0.6",
# CDLA-Permissive-2.0 is a permissive data license used by `webpki-roots`
# for the Mozilla CA root bundle. Data-only, distribution-compatible.
"CDLA-Permissive-2.0",
]
confidence-threshold = 0.8
# Crates whose license cannot be determined from Cargo metadata but whose
# license we've manually confirmed from upstream. Keep this list minimal.
[[licenses.clarify]]
# polars-arrow-format omits the `license` field in its Cargo.toml, but the
# upstream repo (pola-rs/polars-arrow-format) is dual-licensed Apache-2.0 OR
# MIT. See https://github.com/pola-rs/polars-arrow-format/blob/main/LICENSE
crate = "polars-arrow-format"
expression = "Apache-2.0 OR MIT"
license-files = []
# ---------------------------------------------------------------------------
# Bans: disallow specific crates and flag dependency hygiene issues.
# ---------------------------------------------------------------------------
[bans]
# Warn (not deny) on duplicate versions of the same crate. In a large
# workspace like this one, duplicates are common and often unavoidable
# transitively. We surface them to discourage growth, but don't fail CI.
multiple-versions = "warn"
# Wildcard version requirements (`foo = "*"`) are a footgun — they let any
# future release in without review. Ban them outright.
wildcards = "deny"
# Internal workspace crates reference each other via `path = "..."`, which
# cargo-deny sees as a wildcard version. That's fine for private workspace
# members (not published to crates.io), so allow it specifically for paths.
allow-wildcard-paths = true
# Features that, if enabled, should cause the check to fail.
deny = []
# Crates to skip when checking for duplicate versions.
skip = []
# Similar to `skip`, but also skips the entire transitive subtree.
skip-tree = []
# ---------------------------------------------------------------------------
# Sources: restrict where crates can come from.
# ---------------------------------------------------------------------------
[sources]
# Deny any registry other than the ones explicitly listed below.
unknown-registry = "deny"
# Deny any git dependency whose host isn't in the allow-list below. This
# prevents accidental pulls from arbitrary forks.
unknown-git = "deny"
allow-registry = ["https://github.com/rust-lang/crates.io-index"]
# Lance is developed in a sibling repo and pulled as a git dependency until
# releases are cut to crates.io. Allow that specific host.
allow-git = [
"https://github.com/lance-format/lance",
]
+1 -1
View File
@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
<dependency>
<groupId>com.lancedb</groupId>
<artifactId>lancedb-core</artifactId>
<version>0.28.0-beta.9</version>
<version>0.28.0-beta.10</version>
</dependency>
```
+1 -1
View File
@@ -8,7 +8,7 @@
<parent>
<groupId>com.lancedb</groupId>
<artifactId>lancedb-parent</artifactId>
<version>0.28.0-beta.9</version>
<version>0.28.0-beta.10</version>
<relativePath>../pom.xml</relativePath>
</parent>
+2 -2
View File
@@ -6,7 +6,7 @@
<groupId>com.lancedb</groupId>
<artifactId>lancedb-parent</artifactId>
<version>0.28.0-beta.9</version>
<version>0.28.0-beta.10</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>6.0.0-beta.1</lance-core.version>
<lance-core.version>6.0.0-beta.6</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>
+5 -4
View File
@@ -1,7 +1,8 @@
[package]
name = "lancedb-nodejs"
edition.workspace = true
version = "0.28.0-beta.9"
version = "0.28.0-beta.10"
publish = false
license.workspace = true
description.workspace = true
repository.workspace = true
@@ -15,7 +16,7 @@ crate-type = ["cdylib"]
async-trait.workspace = true
arrow-ipc.workspace = true
arrow-array.workspace = true
arrow-buffer = "57.2"
arrow-buffer = "58.1"
half.workspace = true
arrow-schema.workspace = true
env_logger.workspace = true
@@ -31,8 +32,8 @@ lzma-sys = { version = "0.1", features = ["static"] }
log.workspace = true
# Pin to resolve build failures; update periodically for security patches.
aws-lc-sys = "=0.38.0"
aws-lc-rs = "=1.16.1"
aws-lc-sys = "=0.40.0"
aws-lc-rs = "=1.16.3"
[build-dependencies]
napi-build = "2.3.1"
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-darwin-arm64",
"version": "0.28.0-beta.9",
"version": "0.28.0-beta.10",
"os": ["darwin"],
"cpu": ["arm64"],
"main": "lancedb.darwin-arm64.node",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-arm64-gnu",
"version": "0.28.0-beta.9",
"version": "0.28.0-beta.10",
"os": ["linux"],
"cpu": ["arm64"],
"main": "lancedb.linux-arm64-gnu.node",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-arm64-musl",
"version": "0.28.0-beta.9",
"version": "0.28.0-beta.10",
"os": ["linux"],
"cpu": ["arm64"],
"main": "lancedb.linux-arm64-musl.node",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-x64-gnu",
"version": "0.28.0-beta.9",
"version": "0.28.0-beta.10",
"os": ["linux"],
"cpu": ["x64"],
"main": "lancedb.linux-x64-gnu.node",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-x64-musl",
"version": "0.28.0-beta.9",
"version": "0.28.0-beta.10",
"os": ["linux"],
"cpu": ["x64"],
"main": "lancedb.linux-x64-musl.node",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-win32-arm64-msvc",
"version": "0.28.0-beta.9",
"version": "0.28.0-beta.10",
"os": [
"win32"
],
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-win32-x64-msvc",
"version": "0.28.0-beta.9",
"version": "0.28.0-beta.10",
"os": ["win32"],
"cpu": ["x64"],
"main": "lancedb.win32-x64-msvc.node",
+2 -2
View File
@@ -1,12 +1,12 @@
{
"name": "@lancedb/lancedb",
"version": "0.28.0-beta.9",
"version": "0.28.0-beta.10",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "@lancedb/lancedb",
"version": "0.28.0-beta.9",
"version": "0.28.0-beta.10",
"cpu": [
"x64",
"arm64"
+1 -1
View File
@@ -11,7 +11,7 @@
"ann"
],
"private": false,
"version": "0.28.0-beta.9",
"version": "0.28.0-beta.10",
"main": "dist/index.js",
"exports": {
".": "./dist/index.js",
+1 -1
View File
@@ -1,5 +1,5 @@
[tool.bumpversion]
current_version = "0.31.0-beta.9"
current_version = "0.31.0-beta.10"
parse = """(?x)
(?P<major>0|[1-9]\\d*)\\.
(?P<minor>0|[1-9]\\d*)\\.
+6 -5
View File
@@ -1,6 +1,7 @@
[package]
name = "lancedb-python"
version = "0.31.0-beta.9"
version = "0.31.0-beta.10"
publish = false
edition.workspace = true
description = "Python bindings for LanceDB"
license.workspace = true
@@ -14,7 +15,7 @@ name = "_lancedb"
crate-type = ["cdylib"]
[dependencies]
arrow = { version = "57.2", features = ["pyarrow"] }
arrow = { workspace = true, features = ["pyarrow"] }
async-trait = "0.1"
bytes = "1"
lancedb = { path = "../rust/lancedb", default-features = false }
@@ -24,8 +25,8 @@ lance-namespace-impls.workspace = true
lance-io.workspace = true
env_logger.workspace = true
log.workspace = true
pyo3 = { version = "0.26", features = ["extension-module", "abi3-py39"] }
pyo3-async-runtimes = { version = "0.26", features = [
pyo3 = { version = "0.28", features = ["extension-module", "abi3-py39"] }
pyo3-async-runtimes = { version = "0.28", features = [
"attributes",
"tokio-runtime",
] }
@@ -37,7 +38,7 @@ snafu.workspace = true
tokio = { version = "1.40", features = ["sync"] }
[build-dependencies]
pyo3-build-config = { version = "0.26", features = [
pyo3-build-config = { version = "0.28", features = [
"extension-module",
"abi3-py39",
] }
+1 -1
View File
@@ -17,7 +17,7 @@ use pyo3::{Bound, PyAny, PyResult, exceptions::PyValueError, prelude::*, pyfunct
/// [`expr_lit`] and combined with the methods on this struct. On the Python
/// side a thin wrapper class (`lancedb.expr.Expr`) delegates to these methods
/// and adds Python operator overloads.
#[pyclass(name = "PyExpr")]
#[pyclass(name = "PyExpr", from_py_object)]
#[derive(Clone)]
pub struct PyExpr(pub DfExpr);
+1 -1
View File
@@ -33,7 +33,7 @@ impl PyHeaderProvider {
Ok(headers_py) => {
// Convert Python dict to Rust HashMap
let bound_headers = headers_py.bind(py);
let dict: &Bound<PyDict> = bound_headers.downcast().map_err(|e| {
let dict: &Bound<PyDict> = bound_headers.cast().map_err(|e| {
format!("HeaderProvider.get_headers must return a dict: {}", e)
})?;
+1 -1
View File
@@ -22,7 +22,7 @@ pub fn class_name(ob: &'_ Bound<'_, PyAny>) -> PyResult<String> {
let full_name = ob
.getattr(intern!(ob.py(), "__class__"))?
.getattr(intern!(ob.py(), "__name__"))?;
let full_name = full_name.downcast()?.to_string_lossy();
let full_name = full_name.cast()?.to_string_lossy();
match full_name.rsplit_once('.') {
Some((_, name)) => Ok(name.to_string()),
+2 -2
View File
@@ -183,7 +183,7 @@ async fn call_py_method_primitive<Req, Resp>(
) -> lance_core::Result<Resp>
where
Req: serde::Serialize + Send + 'static,
Resp: for<'py> pyo3::FromPyObject<'py> + Send + 'static,
Resp: for<'a, 'py> pyo3::FromPyObject<'a, 'py> + Send + 'static,
{
let request_json = serde_json::to_string(&request).map_err(|e| {
lance_core::Error::io(format!(
@@ -203,7 +203,7 @@ where
// Call the Python method
let result = py_namespace.call_method1(py, method_name, (request_arg,))?;
let value: Resp = result.extract(py)?;
let value: Resp = result.extract(py).map_err(Into::into)?;
Ok::<_, PyErr>(value)
})
})
+5 -5
View File
@@ -25,12 +25,12 @@ 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>()?)
Ok(table.getattr("_inner")?.cast_into::<Table>()?)
} else if table.hasattr("_table")? {
Ok(table
.getattr("_table")?
.getattr("_inner")?
.downcast_into::<Table>()?)
.cast_into::<Table>()?)
} else {
Err(PyRuntimeError::new_err(
"Provided table does not appear to be a Table or RemoteTable instance",
@@ -90,9 +90,9 @@ impl PyAsyncPermutationBuilder {
database
.getattr("_conn")?
.getattr("_inner")?
.downcast_into::<Connection>()?
.cast_into::<Connection>()?
} else {
database.getattr("_inner")?.downcast_into::<Connection>()?
database.getattr("_inner")?.cast_into::<Connection>()?
};
let database = conn.borrow().database()?;
slf.modify(|builder| builder.persist(database, table_name))
@@ -243,7 +243,7 @@ impl PyPermutationReader {
let Some(selection) = selection else {
return Ok(Select::All);
};
let selection = selection.downcast_into::<PyDict>()?;
let selection = selection.cast_into::<PyDict>()?;
let selection = selection
.iter()
.map(|(key, value)| {
+9 -6
View File
@@ -22,6 +22,7 @@ use lancedb::query::{
VectorQuery as LanceDbVectorQuery,
};
use lancedb::table::AnyQuery;
use pyo3::Borrowed;
use pyo3::Bound;
use pyo3::IntoPyObject;
use pyo3::PyAny;
@@ -43,9 +44,11 @@ use crate::util::parse_distance_type;
use crate::{arrow::RecordBatchStream, util::PyLanceDB};
use crate::{error::PythonErrorExt, index::class_name};
impl FromPyObject<'_> for PyLanceDB<FtsQuery> {
fn extract_bound(ob: &Bound<'_, PyAny>) -> PyResult<Self> {
match class_name(ob)?.as_str() {
impl FromPyObject<'_, '_> for PyLanceDB<FtsQuery> {
type Error = PyErr;
fn extract(ob: Borrowed<'_, '_, PyAny>) -> PyResult<Self> {
match class_name(&ob)?.as_str() {
"MatchQuery" => {
let query = ob.getattr("query")?.extract()?;
let column = ob.getattr("column")?.extract()?;
@@ -424,7 +427,7 @@ impl Query {
"Query text is required for nearest_to_text",
))?;
let query = if let Ok(query_text) = fts_query.downcast::<PyString>() {
let query = if let Ok(query_text) = fts_query.cast::<PyString>() {
let mut query_text = query_text.to_string();
let columns = query
.get_item("columns")?
@@ -606,7 +609,7 @@ impl TakeQuery {
}
}
#[pyclass]
#[pyclass(from_py_object)]
#[derive(Clone)]
pub struct FTSQuery {
inner: LanceDbQuery,
@@ -735,7 +738,7 @@ impl FTSQuery {
}
}
#[pyclass]
#[pyclass(from_py_object)]
#[derive(Clone)]
pub struct VectorQuery {
inner: LanceDbVectorQuery,
+1 -1
View File
@@ -11,7 +11,7 @@ use pyo3::{PyResult, pyclass, pymethods};
/// Sessions allow you to configure cache sizes for index and metadata caches,
/// which can significantly impact memory use and performance. They can
/// also be re-used across multiple connections to share the same cache state.
#[pyclass]
#[pyclass(from_py_object)]
#[derive(Clone)]
pub struct Session {
pub(crate) inner: Arc<LanceSession>,
+10 -10
View File
@@ -29,7 +29,7 @@ use pyo3_async_runtimes::tokio::future_into_py;
mod scannable;
/// Statistics about a compaction operation.
#[pyclass(get_all)]
#[pyclass(get_all, from_py_object)]
#[derive(Clone, Debug)]
pub struct CompactionStats {
/// The number of fragments removed
@@ -43,7 +43,7 @@ pub struct CompactionStats {
}
/// Statistics about a cleanup operation
#[pyclass(get_all)]
#[pyclass(get_all, from_py_object)]
#[derive(Clone, Debug)]
pub struct RemovalStats {
/// The number of bytes removed
@@ -53,7 +53,7 @@ pub struct RemovalStats {
}
/// Statistics about an optimize operation
#[pyclass(get_all)]
#[pyclass(get_all, from_py_object)]
#[derive(Clone, Debug)]
pub struct OptimizeStats {
/// Statistics about the compaction operation
@@ -62,7 +62,7 @@ pub struct OptimizeStats {
pub prune: RemovalStats,
}
#[pyclass(get_all)]
#[pyclass(get_all, from_py_object)]
#[derive(Clone, Debug)]
pub struct UpdateResult {
pub rows_updated: u64,
@@ -88,7 +88,7 @@ impl From<lancedb::table::UpdateResult> for UpdateResult {
}
}
#[pyclass(get_all)]
#[pyclass(get_all, from_py_object)]
#[derive(Clone, Debug)]
pub struct AddResult {
pub version: u64,
@@ -109,7 +109,7 @@ impl From<lancedb::table::AddResult> for AddResult {
}
}
#[pyclass(get_all)]
#[pyclass(get_all, from_py_object)]
#[derive(Clone, Debug)]
pub struct DeleteResult {
pub num_deleted_rows: u64,
@@ -135,7 +135,7 @@ impl From<lancedb::table::DeleteResult> for DeleteResult {
}
}
#[pyclass(get_all)]
#[pyclass(get_all, from_py_object)]
#[derive(Clone, Debug)]
pub struct MergeResult {
pub version: u64,
@@ -171,7 +171,7 @@ impl From<lancedb::table::MergeResult> for MergeResult {
}
}
#[pyclass(get_all)]
#[pyclass(get_all, from_py_object)]
#[derive(Clone, Debug)]
pub struct AddColumnsResult {
pub version: u64,
@@ -192,7 +192,7 @@ impl From<lancedb::table::AddColumnsResult> for AddColumnsResult {
}
}
#[pyclass(get_all)]
#[pyclass(get_all, from_py_object)]
#[derive(Clone, Debug)]
pub struct AlterColumnsResult {
pub version: u64,
@@ -213,7 +213,7 @@ impl From<lancedb::table::AlterColumnsResult> for AlterColumnsResult {
}
}
#[pyclass(get_all)]
#[pyclass(get_all, from_py_object)]
#[derive(Clone, Debug)]
pub struct DropColumnsResult {
pub version: u64,
+5 -3
View File
@@ -14,7 +14,7 @@ use lancedb::{
arrow::{SendableRecordBatchStream, SimpleRecordBatchStream},
data::scannable::Scannable,
};
use pyo3::{FromPyObject, Py, PyAny, Python, types::PyAnyMethods};
use pyo3::{Borrowed, FromPyObject, Py, PyAny, Python, types::PyAnyMethods};
/// Adapter that implements Scannable for a Python reader factory callable.
///
@@ -126,8 +126,10 @@ impl Scannable for PyScannable {
}
}
impl<'py> FromPyObject<'py> for PyScannable {
fn extract_bound(ob: &pyo3::Bound<'py, PyAny>) -> pyo3::PyResult<Self> {
impl FromPyObject<'_, '_> for PyScannable {
type Error = pyo3::PyErr;
fn extract(ob: Borrowed<'_, '_, PyAny>) -> pyo3::PyResult<Self> {
// Convert from Scannable dataclass.
let schema: PyArrowType<Schema> = ob.getattr("schema")?.extract()?;
let schema = Arc::new(schema.0);
+1 -1
View File
@@ -1,6 +1,6 @@
[package]
name = "lancedb"
version = "0.28.0-beta.9"
version = "0.28.0-beta.10"
edition.workspace = true
description = "LanceDB: A serverless, low-latency vector database for AI applications"
license.workspace = true
+4 -4
View File
@@ -43,7 +43,7 @@ pub struct RemoteInsertExec<S: HttpSend = Sender> {
client: RestfulLanceDbClient<S>,
input: Arc<dyn ExecutionPlan>,
overwrite: bool,
properties: PlanProperties,
properties: Arc<PlanProperties>,
add_result: Arc<Mutex<Option<AddResult>>>,
metrics: ExecutionPlanMetricsSet,
upload_id: Option<String>,
@@ -105,12 +105,12 @@ impl<S: HttpSend + 'static> RemoteInsertExec<S> {
1
};
let schema = COUNT_SCHEMA.clone();
let properties = PlanProperties::new(
let properties = Arc::new(PlanProperties::new(
EquivalenceProperties::new(schema),
datafusion_physical_plan::Partitioning::UnknownPartitioning(num_partitions),
datafusion_physical_plan::execution_plan::EmissionType::Final,
datafusion_physical_plan::execution_plan::Boundedness::Bounded,
);
));
Self {
table_name,
@@ -232,7 +232,7 @@ impl<S: HttpSend + 'static> ExecutionPlan for RemoteInsertExec<S> {
self
}
fn properties(&self) -> &PlanProperties {
fn properties(&self) -> &Arc<PlanProperties> {
&self.properties
}
+9 -4
View File
@@ -39,21 +39,26 @@ use lance_index::scalar::FullTextSearchQuery;
struct MetadataEraserExec {
input: Arc<dyn ExecutionPlan>,
schema: Arc<ArrowSchema>,
properties: PlanProperties,
properties: Arc<PlanProperties>,
}
impl MetadataEraserExec {
fn compute_properties_from_input(
input: &Arc<dyn ExecutionPlan>,
schema: &Arc<ArrowSchema>,
) -> PlanProperties {
) -> Arc<PlanProperties> {
let input_properties = input.properties();
let eq_properties = input_properties
.eq_properties
.clone()
.with_new_schema(schema.clone())
.unwrap();
input_properties.clone().with_eq_properties(eq_properties)
Arc::new(
input_properties
.as_ref()
.clone()
.with_eq_properties(eq_properties),
)
}
fn new(input: Arc<dyn ExecutionPlan>) -> Self {
@@ -87,7 +92,7 @@ impl ExecutionPlan for MetadataEraserExec {
self
}
fn properties(&self) -> &PlanProperties {
fn properties(&self) -> &Arc<PlanProperties> {
&self.properties
}
+4 -4
View File
@@ -81,7 +81,7 @@ pub struct InsertExec {
dataset: Arc<Dataset>,
input: Arc<dyn ExecutionPlan>,
write_params: WriteParams,
properties: PlanProperties,
properties: Arc<PlanProperties>,
partial_transactions: Arc<Mutex<Vec<Transaction>>>,
metrics: ExecutionPlanMetricsSet,
}
@@ -95,12 +95,12 @@ impl InsertExec {
) -> Self {
let schema = COUNT_SCHEMA.clone();
let num_partitions = input.output_partitioning().partition_count();
let properties = PlanProperties::new(
let properties = Arc::new(PlanProperties::new(
EquivalenceProperties::new(schema),
Partitioning::UnknownPartitioning(num_partitions),
EmissionType::Final,
Boundedness::Bounded,
);
));
Self {
ds_wrapper,
@@ -136,7 +136,7 @@ impl ExecutionPlan for InsertExec {
self
}
fn properties(&self) -> &PlanProperties {
fn properties(&self) -> &Arc<PlanProperties> {
&self.properties
}
@@ -20,7 +20,7 @@ pub(crate) struct ScannableExec {
// We don't require Scannable to be Sync, so we wrap it in a Mutex to allow safe concurrent access.
source: Mutex<Box<dyn Scannable>>,
num_rows: Option<usize>,
properties: PlanProperties,
properties: Arc<PlanProperties>,
tracker: Option<Arc<WriteProgressTracker>>,
}
@@ -37,12 +37,12 @@ impl ScannableExec {
pub fn new(source: Box<dyn Scannable>, tracker: Option<Arc<WriteProgressTracker>>) -> Self {
let schema = source.schema();
let eq_properties = EquivalenceProperties::new(schema);
let properties = PlanProperties::new(
let properties = Arc::new(PlanProperties::new(
eq_properties,
Partitioning::UnknownPartitioning(1),
EmissionType::Incremental,
datafusion_physical_plan::execution_plan::Boundedness::Bounded,
);
));
let num_rows = source.num_rows();
let source = Mutex::new(source);
@@ -70,7 +70,7 @@ impl ExecutionPlan for ScannableExec {
self
}
fn properties(&self) -> &PlanProperties {
fn properties(&self) -> &Arc<PlanProperties> {
&self.properties
}