mirror of
https://github.com/lancedb/lancedb.git
synced 2026-06-02 20:00:46 +00:00
Compare commits
25 Commits
python-v0.
...
fix/aikido
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
9867d8b24d | ||
|
|
f20ec99dec | ||
|
|
60f961584c | ||
|
|
ac699d7ecf | ||
|
|
968277be79 | ||
|
|
5638907fa5 | ||
|
|
048f52c2aa | ||
|
|
458dcabbd2 | ||
|
|
60ac5c9a7c | ||
|
|
d05fe8ec44 | ||
|
|
ab982d7f65 | ||
|
|
a3339b7bdd | ||
|
|
b20cdc4f93 | ||
|
|
e77a62e35a | ||
|
|
a9f49c8150 | ||
|
|
a7d9f2e99d | ||
|
|
7dba793629 | ||
|
|
87bd6694b6 | ||
|
|
15e75804c4 | ||
|
|
df2b6d3dd4 | ||
|
|
ccec91d957 | ||
|
|
ec82e36317 | ||
|
|
da2a1c4a2c | ||
|
|
8463a10ebe | ||
|
|
7168d64af1 |
@@ -1,5 +1,5 @@
|
||||
[tool.bumpversion]
|
||||
current_version = "0.30.0-beta.0"
|
||||
current_version = "0.30.1-beta.0"
|
||||
parse = """(?x)
|
||||
(?P<major>0|[1-9]\\d*)\\.
|
||||
(?P<minor>0|[1-9]\\d*)\\.
|
||||
|
||||
@@ -29,7 +29,3 @@ runs:
|
||||
args: ${{ inputs.args }}
|
||||
docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/'"
|
||||
working-directory: python
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: windows-wheels
|
||||
path: python\target\wheels
|
||||
|
||||
110
.github/workflows/pypi-publish.yml
vendored
110
.github/workflows/pypi-publish.yml
vendored
@@ -8,6 +8,9 @@ on:
|
||||
# This should trigger a dry run (we skip the final publish step)
|
||||
paths:
|
||||
- .github/workflows/pypi-publish.yml
|
||||
- .github/workflows/build_linux_wheel/action.yml
|
||||
- .github/workflows/build_mac_wheel/action.yml
|
||||
- .github/workflows/build_windows_wheel/action.yml
|
||||
- Cargo.toml # Change in dependency frequently breaks builds
|
||||
- Cargo.lock
|
||||
|
||||
@@ -21,32 +24,21 @@ jobs:
|
||||
linux:
|
||||
name: Python ${{ matrix.config.platform }} manylinux${{ matrix.config.manylinux }}
|
||||
timeout-minutes: 60
|
||||
permissions:
|
||||
id-token: write
|
||||
contents: read
|
||||
strategy:
|
||||
matrix:
|
||||
config:
|
||||
- platform: x86_64
|
||||
manylinux: "2_17"
|
||||
extra_args: ""
|
||||
runner: ubuntu-22.04
|
||||
- platform: x86_64
|
||||
manylinux: "2_28"
|
||||
extra_args: "--features fp16kernels"
|
||||
runner: ubuntu-22.04
|
||||
- platform: aarch64
|
||||
manylinux: "2_17"
|
||||
extra_args: ""
|
||||
# For successful fat LTO builds, we need a large runner to avoid OOM errors.
|
||||
runner: ubuntu-2404-8x-arm64
|
||||
# For successful fat LTO builds, we need a large runner to avoid OOM errors.
|
||||
- platform: aarch64
|
||||
manylinux: "2_28"
|
||||
extra_args: "--features fp16kernels"
|
||||
runner: ubuntu-2404-8x-arm64
|
||||
runs-on: ${{ matrix.config.runner }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/checkout@v6
|
||||
with:
|
||||
fetch-depth: 0
|
||||
lfs: true
|
||||
@@ -60,15 +52,14 @@ jobs:
|
||||
args: "--release --strip ${{ matrix.config.extra_args }}"
|
||||
arm-build: ${{ matrix.config.platform == 'aarch64' }}
|
||||
manylinux: ${{ matrix.config.manylinux }}
|
||||
- uses: ./.github/workflows/upload_wheel
|
||||
- uses: actions/upload-artifact@v7
|
||||
if: startsWith(github.ref, 'refs/tags/python-v')
|
||||
with:
|
||||
fury_token: ${{ secrets.FURY_TOKEN }}
|
||||
name: wheels-linux-${{ matrix.config.platform }}-${{ matrix.config.manylinux }}
|
||||
path: target/wheels/lancedb-*.whl
|
||||
if-no-files-found: error
|
||||
mac:
|
||||
timeout-minutes: 90
|
||||
permissions:
|
||||
id-token: write
|
||||
contents: read
|
||||
runs-on: ${{ matrix.config.runner }}
|
||||
strategy:
|
||||
matrix:
|
||||
@@ -78,7 +69,7 @@ jobs:
|
||||
env:
|
||||
MACOSX_DEPLOYMENT_TARGET: 10.15
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/checkout@v6
|
||||
with:
|
||||
fetch-depth: 0
|
||||
lfs: true
|
||||
@@ -90,18 +81,21 @@ jobs:
|
||||
with:
|
||||
python-minor-version: 10
|
||||
args: "--release --strip --target ${{ matrix.config.target }} --features fp16kernels"
|
||||
- uses: ./.github/workflows/upload_wheel
|
||||
- uses: actions/upload-artifact@v7
|
||||
if: startsWith(github.ref, 'refs/tags/python-v')
|
||||
with:
|
||||
fury_token: ${{ secrets.FURY_TOKEN }}
|
||||
name: wheels-mac-${{ matrix.config.target }}
|
||||
path: target/wheels/lancedb-*.whl
|
||||
if-no-files-found: error
|
||||
windows:
|
||||
timeout-minutes: 60
|
||||
permissions:
|
||||
id-token: write
|
||||
contents: read
|
||||
timeout-minutes: 90
|
||||
runs-on: windows-latest
|
||||
env:
|
||||
# link.exe is single-threaded and the long pole on Windows builds. Use
|
||||
# rustc's bundled lld-link instead.
|
||||
CARGO_TARGET_X86_64_PC_WINDOWS_MSVC_LINKER: rust-lld
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/checkout@v6
|
||||
with:
|
||||
fetch-depth: 0
|
||||
lfs: true
|
||||
@@ -113,18 +107,70 @@ jobs:
|
||||
with:
|
||||
python-minor-version: 10
|
||||
args: "--release --strip"
|
||||
vcpkg_token: ${{ secrets.VCPKG_GITHUB_PACKAGES }}
|
||||
- uses: ./.github/workflows/upload_wheel
|
||||
- uses: actions/upload-artifact@v7
|
||||
if: startsWith(github.ref, 'refs/tags/python-v')
|
||||
with:
|
||||
fury_token: ${{ secrets.FURY_TOKEN }}
|
||||
name: wheels-windows
|
||||
path: target/wheels/lancedb-*.whl
|
||||
if-no-files-found: error
|
||||
publish:
|
||||
name: Publish wheels
|
||||
if: startsWith(github.ref, 'refs/tags/python-v')
|
||||
needs: [linux, mac, windows]
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
id-token: write
|
||||
contents: read
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
- name: Download wheel artifacts
|
||||
uses: actions/download-artifact@v8
|
||||
with:
|
||||
pattern: wheels-*
|
||||
path: target/wheels
|
||||
merge-multiple: true
|
||||
- name: List wheels
|
||||
run: ls -la target/wheels
|
||||
- name: Choose repo
|
||||
id: choose_repo
|
||||
run: |
|
||||
if [[ ${{ github.ref }} == *beta* ]]; then
|
||||
echo "repo=fury" >> $GITHUB_OUTPUT
|
||||
else
|
||||
echo "repo=pypi" >> $GITHUB_OUTPUT
|
||||
fi
|
||||
- name: Publish to Fury
|
||||
if: steps.choose_repo.outputs.repo == 'fury'
|
||||
env:
|
||||
FURY_TOKEN: ${{ secrets.FURY_TOKEN }}
|
||||
run: |
|
||||
shopt -s nullglob
|
||||
WHEELS=(target/wheels/lancedb-*.whl)
|
||||
if [[ ${#WHEELS[@]} -eq 0 ]]; then
|
||||
echo "No wheels found in target/wheels/" >&2
|
||||
exit 1
|
||||
fi
|
||||
for WHEEL in "${WHEELS[@]}"; do
|
||||
echo "Uploading $WHEEL to Fury"
|
||||
curl -f -F package=@"$WHEEL" "https://$FURY_TOKEN@push.fury.io/lancedb/"
|
||||
done
|
||||
# NOTE: pypa/gh-action-pypi-publish must be invoked directly from a
|
||||
# workflow file, not from inside a composite action. When called from a
|
||||
# composite, `github.action_repository` is empty (actions/runner#2473)
|
||||
# and the action falls back to `github.repository`, producing a bogus
|
||||
# `docker://ghcr.io/<repo>:<ref>` image reference that GHA tries to pull.
|
||||
- name: Publish to PyPI
|
||||
if: steps.choose_repo.outputs.repo == 'pypi'
|
||||
uses: pypa/gh-action-pypi-publish@release/v1
|
||||
with:
|
||||
packages-dir: target/wheels/
|
||||
gh-release:
|
||||
if: startsWith(github.ref, 'refs/tags/python-v')
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
contents: write
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/checkout@v6
|
||||
with:
|
||||
fetch-depth: 0
|
||||
lfs: true
|
||||
@@ -187,13 +233,13 @@ jobs:
|
||||
report-failure:
|
||||
name: Report Workflow Failure
|
||||
runs-on: ubuntu-latest
|
||||
needs: [linux, mac, windows]
|
||||
needs: [linux, mac, windows, publish]
|
||||
permissions:
|
||||
contents: read
|
||||
issues: write
|
||||
if: always() && failure() && startsWith(github.ref, 'refs/tags/python-v')
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/checkout@v6
|
||||
- uses: ./.github/actions/create-failure-issue
|
||||
with:
|
||||
job-results: ${{ toJSON(needs) }}
|
||||
|
||||
34
.github/workflows/upload_wheel/action.yml
vendored
34
.github/workflows/upload_wheel/action.yml
vendored
@@ -1,34 +0,0 @@
|
||||
name: upload-wheel
|
||||
|
||||
description: "Upload wheels to Pypi"
|
||||
inputs:
|
||||
fury_token:
|
||||
required: true
|
||||
description: "release token for the fury repo"
|
||||
|
||||
runs:
|
||||
using: "composite"
|
||||
steps:
|
||||
- name: Choose repo
|
||||
shell: bash
|
||||
id: choose_repo
|
||||
run: |
|
||||
if [[ ${{ github.ref }} == *beta* ]]; then
|
||||
echo "repo=fury" >> $GITHUB_OUTPUT
|
||||
else
|
||||
echo "repo=pypi" >> $GITHUB_OUTPUT
|
||||
fi
|
||||
- name: Publish to Fury
|
||||
if: steps.choose_repo.outputs.repo == 'fury'
|
||||
shell: bash
|
||||
env:
|
||||
FURY_TOKEN: ${{ inputs.fury_token }}
|
||||
run: |
|
||||
WHEEL=$(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/
|
||||
11
AGENTS.md
11
AGENTS.md
@@ -37,10 +37,13 @@ Before committing changes, run formatting for every language you touched. At min
|
||||
and run targeted tests through `cd python && uv run ...`.
|
||||
* TypeScript changes: run the relevant `npm`/`pnpm` lint, format, build, and docs commands in `nodejs`.
|
||||
|
||||
Before creating a PR, make sure the PR title follows Conventional Commits, such as
|
||||
`fix: support nested field paths in native index creation` or
|
||||
`feat(python): add dataset multiprocessing support`. The semantic-release check uses the
|
||||
PR title and body as the merge commit message, so a non-conventional PR title will fail CI.
|
||||
Before creating a PR, the exact value passed to `gh pr create --title` must follow
|
||||
Conventional Commits, such as `fix: support nested field paths in native index creation`
|
||||
or `feat(python): add dataset multiprocessing support`. Do not use a plain natural
|
||||
language summary like `Support nested field paths in native index creation` as the PR
|
||||
title. The semantic-release check uses the PR title and body as the merge commit message,
|
||||
so a non-conventional PR title will fail CI. After creating a PR, read the remote PR title
|
||||
back and fix it immediately if it is not conventional.
|
||||
|
||||
## Coding tips
|
||||
|
||||
|
||||
508
Cargo.lock
generated
508
Cargo.lock
generated
File diff suppressed because it is too large
Load Diff
28
Cargo.toml
28
Cargo.toml
@@ -13,20 +13,20 @@ categories = ["database-implementations"]
|
||||
rust-version = "1.91.0"
|
||||
|
||||
[workspace.dependencies]
|
||||
lance = { "version" = "=7.0.0-beta.13", default-features = false, "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-core = { "version" = "=7.0.0-beta.13", "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datagen = { "version" = "=7.0.0-beta.13", "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-file = { "version" = "=7.0.0-beta.13", "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-io = { "version" = "=7.0.0-beta.13", default-features = false, "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-index = { "version" = "=7.0.0-beta.13", "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-linalg = { "version" = "=7.0.0-beta.13", "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace = { "version" = "=7.0.0-beta.13", "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace-impls = { "version" = "=7.0.0-beta.13", default-features = false, "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-table = { "version" = "=7.0.0-beta.13", "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-testing = { "version" = "=7.0.0-beta.13", "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datafusion = { "version" = "=7.0.0-beta.13", "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-encoding = { "version" = "=7.0.0-beta.13", "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-arrow = { "version" = "=7.0.0-beta.13", "tag" = "v7.0.0-beta.13", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance = { "version" = "=7.2.0-beta.3", default-features = false, "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-core = { "version" = "=7.2.0-beta.3", "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datagen = { "version" = "=7.2.0-beta.3", "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-file = { "version" = "=7.2.0-beta.3", "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-io = { "version" = "=7.2.0-beta.3", default-features = false, "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-index = { "version" = "=7.2.0-beta.3", "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-linalg = { "version" = "=7.2.0-beta.3", "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace = { "version" = "=7.2.0-beta.3", "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace-impls = { "version" = "=7.2.0-beta.3", default-features = false, "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-table = { "version" = "=7.2.0-beta.3", "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-testing = { "version" = "=7.2.0-beta.3", "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datafusion = { "version" = "=7.2.0-beta.3", "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-encoding = { "version" = "=7.2.0-beta.3", "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-arrow = { "version" = "=7.2.0-beta.3", "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
ahash = "0.8"
|
||||
# Note that this one does not include pyarrow
|
||||
arrow = { version = "58.0.0", optional = false }
|
||||
|
||||
@@ -112,25 +112,25 @@ def fetch_remote_tags() -> List[TagInfo]:
|
||||
"api",
|
||||
"-X",
|
||||
"GET",
|
||||
f"repos/{LANCE_REPO}/git/refs/tags",
|
||||
"--paginate",
|
||||
f"repos/{LANCE_REPO}/releases",
|
||||
"--jq",
|
||||
".[].ref",
|
||||
".[].tag_name",
|
||||
"-F",
|
||||
"per_page=20",
|
||||
]
|
||||
)
|
||||
tags: List[TagInfo] = []
|
||||
for line in output.splitlines():
|
||||
ref = line.strip()
|
||||
if not ref.startswith("refs/tags/v"):
|
||||
tag = line.strip()
|
||||
if not tag.startswith("v"):
|
||||
continue
|
||||
tag = ref.split("refs/tags/")[-1]
|
||||
version = tag.lstrip("v")
|
||||
try:
|
||||
tags.append(TagInfo(tag=tag, version=version, semver=parse_semver(version)))
|
||||
except ValueError:
|
||||
continue
|
||||
if not tags:
|
||||
raise RuntimeError("No Lance tags could be parsed from GitHub API output")
|
||||
raise RuntimeError("No Lance releases could be parsed from GitHub API output")
|
||||
return tags
|
||||
|
||||
|
||||
|
||||
@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
|
||||
<dependency>
|
||||
<groupId>com.lancedb</groupId>
|
||||
<artifactId>lancedb-core</artifactId>
|
||||
<version>0.30.0-beta.0</version>
|
||||
<version>0.30.1-beta.0</version>
|
||||
</dependency>
|
||||
```
|
||||
|
||||
|
||||
@@ -76,6 +76,57 @@ the query optimizer chooses a suboptimal path.
|
||||
|
||||
***
|
||||
|
||||
### useLsmWrite()
|
||||
|
||||
```ts
|
||||
useLsmWrite(useLsmWrite): MergeInsertBuilder
|
||||
```
|
||||
|
||||
Controls whether the merge uses the MemWAL LSM write path.
|
||||
|
||||
By default (unset), a `mergeInsert` on a table with an LSM write spec is
|
||||
routed through Lance's MemWAL shard writer, and a table without one uses
|
||||
the standard path. Pass `false` to force the standard path even when a
|
||||
spec is set. Pass `true` to require a spec — `mergeInsert` rejects if none
|
||||
is installed.
|
||||
|
||||
#### Parameters
|
||||
|
||||
* **useLsmWrite**: `boolean`
|
||||
Whether to use the LSM write path.
|
||||
|
||||
#### Returns
|
||||
|
||||
[`MergeInsertBuilder`](MergeInsertBuilder.md)
|
||||
|
||||
***
|
||||
|
||||
### validateSingleShard()
|
||||
|
||||
```ts
|
||||
validateSingleShard(validateSingleShard): MergeInsertBuilder
|
||||
```
|
||||
|
||||
Controls how an LSM merge checks that its input targets a single shard.
|
||||
|
||||
When a table has an LSM write spec, every row in a `mergeInsert` call must
|
||||
route to the same shard. When `true` (the default), every row is inspected
|
||||
to verify this. When `false`, only the first row is inspected and the
|
||||
shard it routes to is used for the whole input — a faster path for callers
|
||||
that have already pre-sharded their input. Has no effect on tables without
|
||||
an LSM write spec.
|
||||
|
||||
#### Parameters
|
||||
|
||||
* **validateSingleShard**: `boolean`
|
||||
Whether to check every row routes to one shard. Defaults to `true`.
|
||||
|
||||
#### Returns
|
||||
|
||||
[`MergeInsertBuilder`](MergeInsertBuilder.md)
|
||||
|
||||
***
|
||||
|
||||
### whenMatchedUpdateAll()
|
||||
|
||||
```ts
|
||||
|
||||
@@ -187,6 +187,25 @@ Any attempt to use the table after it is closed will result in an error.
|
||||
|
||||
***
|
||||
|
||||
### closeLsmWriters()
|
||||
|
||||
```ts
|
||||
abstract closeLsmWriters(): Promise<void>
|
||||
```
|
||||
|
||||
Drain and close any cached MemWAL shard writers held for this table.
|
||||
|
||||
When an [LsmWriteSpec](../interfaces/LsmWriteSpec.md) is installed, `mergeInsert` opens MemWAL
|
||||
shard writers and caches them for reuse across calls. This closes them,
|
||||
flushing pending data; writers reopen lazily on the next `mergeInsert`.
|
||||
It is a no-op when no writers are cached.
|
||||
|
||||
#### Returns
|
||||
|
||||
`Promise`<`void`>
|
||||
|
||||
***
|
||||
|
||||
### countRows()
|
||||
|
||||
```ts
|
||||
|
||||
@@ -70,16 +70,20 @@ client used by manifest-enabled native connections.
|
||||
optional readConsistencyInterval: number;
|
||||
```
|
||||
|
||||
(For LanceDB OSS only): The interval, in seconds, at which to check for
|
||||
updates to the table from other processes. If None, then consistency is not
|
||||
checked. For performance reasons, this is the default. For strong
|
||||
consistency, set this to zero seconds. Then every read will check for
|
||||
updates from other processes. As a compromise, you can set this to a
|
||||
non-zero value for eventual consistency. If more than that interval
|
||||
has passed since the last check, then the table will be checked for updates.
|
||||
Note: this consistency only applies to read operations. Write operations are
|
||||
The interval, in seconds, at which to check for updates to the table
|
||||
from other processes. If None, then consistency is not checked. For
|
||||
performance reasons, this is the default. For strong consistency, set
|
||||
this to zero seconds. Then every read will check for updates from other
|
||||
processes. As a compromise, you can set this to a non-zero value for
|
||||
eventual consistency. If more than that interval has passed since the
|
||||
last check, then the table will be checked for updates. Note: this
|
||||
consistency only applies to read operations. Write operations are
|
||||
always consistent.
|
||||
|
||||
Stronger consistency is not free. The smaller the interval, the more
|
||||
often each read pays the cost of checking for updates against object
|
||||
storage, raising per-read latency and cost.
|
||||
|
||||
***
|
||||
|
||||
### region?
|
||||
|
||||
@@ -11,7 +11,10 @@ Specification selecting Lance's MemWAL LSM-style write path for
|
||||
|
||||
`specType` is `"bucket"`, `"identity"`, or `"unsharded"`. For `"bucket"`,
|
||||
`column` and `numBuckets` are required; for `"identity"`, `column` is
|
||||
required.
|
||||
required and must be a deterministic function of the unenforced primary
|
||||
key (every row with a given primary key must always produce the same
|
||||
`column` value, or upserts of that key can land in different shards and a
|
||||
stale version can win).
|
||||
|
||||
## Properties
|
||||
|
||||
|
||||
@@ -32,6 +32,14 @@ numInsertedRows: number;
|
||||
|
||||
***
|
||||
|
||||
### numRows
|
||||
|
||||
```ts
|
||||
numRows: number;
|
||||
```
|
||||
|
||||
***
|
||||
|
||||
### numUpdatedRows
|
||||
|
||||
```ts
|
||||
|
||||
@@ -8,7 +8,7 @@
|
||||
<parent>
|
||||
<groupId>com.lancedb</groupId>
|
||||
<artifactId>lancedb-parent</artifactId>
|
||||
<version>0.30.0-beta.0</version>
|
||||
<version>0.30.1-beta.0</version>
|
||||
<relativePath>../pom.xml</relativePath>
|
||||
</parent>
|
||||
|
||||
|
||||
@@ -6,7 +6,7 @@
|
||||
|
||||
<groupId>com.lancedb</groupId>
|
||||
<artifactId>lancedb-parent</artifactId>
|
||||
<version>0.30.0-beta.0</version>
|
||||
<version>0.30.1-beta.0</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>7.0.0-beta.13</lance-core.version>
|
||||
<lance-core.version>7.2.0-beta.1</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>
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
[package]
|
||||
name = "lancedb-nodejs"
|
||||
edition.workspace = true
|
||||
version = "0.30.0-beta.0"
|
||||
version = "0.30.1-beta.0"
|
||||
publish = false
|
||||
license.workspace = true
|
||||
description.workspace = true
|
||||
|
||||
@@ -171,18 +171,22 @@ describe("given a connection", () => {
|
||||
|
||||
let manifestDir =
|
||||
tmpDir.name + "/test_manifest_paths_v2_empty.lance/_versions";
|
||||
readdirSync(manifestDir).forEach((file) => {
|
||||
expect(file).toMatch(/^\d{20}\.manifest$/);
|
||||
});
|
||||
readdirSync(manifestDir)
|
||||
.filter((f) => f.endsWith(".manifest"))
|
||||
.forEach((file) => {
|
||||
expect(file).toMatch(/^\d{20}\.manifest$/);
|
||||
});
|
||||
|
||||
table = (await db.createTable("test_manifest_paths_v2", [{ id: 1 }], {
|
||||
enableV2ManifestPaths: true,
|
||||
})) as LocalTable;
|
||||
expect(await table.usesV2ManifestPaths()).toBe(true);
|
||||
manifestDir = tmpDir.name + "/test_manifest_paths_v2.lance/_versions";
|
||||
readdirSync(manifestDir).forEach((file) => {
|
||||
expect(file).toMatch(/^\d{20}\.manifest$/);
|
||||
});
|
||||
readdirSync(manifestDir)
|
||||
.filter((f) => f.endsWith(".manifest"))
|
||||
.forEach((file) => {
|
||||
expect(file).toMatch(/^\d{20}\.manifest$/);
|
||||
});
|
||||
});
|
||||
|
||||
it("should be able to migrate tables to the V2 manifest paths", async () => {
|
||||
@@ -199,16 +203,20 @@ describe("given a connection", () => {
|
||||
|
||||
const manifestDir =
|
||||
tmpDir.name + "/test_manifest_path_migration.lance/_versions";
|
||||
readdirSync(manifestDir).forEach((file) => {
|
||||
expect(file).toMatch(/^\d\.manifest$/);
|
||||
});
|
||||
readdirSync(manifestDir)
|
||||
.filter((f) => f.endsWith(".manifest"))
|
||||
.forEach((file) => {
|
||||
expect(file).toMatch(/^\d\.manifest$/);
|
||||
});
|
||||
|
||||
await table.migrateManifestPathsV2();
|
||||
expect(await table.usesV2ManifestPaths()).toBe(true);
|
||||
|
||||
readdirSync(manifestDir).forEach((file) => {
|
||||
expect(file).toMatch(/^\d{20}\.manifest$/);
|
||||
});
|
||||
readdirSync(manifestDir)
|
||||
.filter((f) => f.endsWith(".manifest"))
|
||||
.forEach((file) => {
|
||||
expect(file).toMatch(/^\d{20}\.manifest$/);
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
|
||||
@@ -2625,3 +2625,97 @@ describe("setLsmWriteSpec / unsetLsmWriteSpec", () => {
|
||||
).rejects.toThrow();
|
||||
});
|
||||
});
|
||||
|
||||
describe("LSM merge insert", () => {
|
||||
let tmpDir: tmp.DirResult;
|
||||
|
||||
beforeEach(() => {
|
||||
tmpDir = tmp.dirSync({ unsafeCleanup: true });
|
||||
});
|
||||
afterEach(() => tmpDir.removeCallback());
|
||||
|
||||
async function bucketTable(conn: Connection): Promise<Table> {
|
||||
// The primary key column must be non-nullable.
|
||||
const table = await conn.createEmptyTable(
|
||||
"t",
|
||||
new arrow.Schema([
|
||||
new arrow.Field("id", new arrow.Utf8(), false),
|
||||
new arrow.Field("value", new arrow.Float64(), true),
|
||||
]),
|
||||
);
|
||||
await table.add([
|
||||
{ id: "a", value: 1 },
|
||||
{ id: "b", value: 2 },
|
||||
]);
|
||||
await table.setUnenforcedPrimaryKey("id");
|
||||
// numBuckets = 1: every row routes to the single bucket.
|
||||
await table.setLsmWriteSpec({
|
||||
specType: "bucket",
|
||||
column: "id",
|
||||
numBuckets: 1,
|
||||
});
|
||||
return table;
|
||||
}
|
||||
|
||||
it("routes merge_insert through the shard writer", async () => {
|
||||
const conn = await connect(tmpDir.name);
|
||||
const table = await bucketTable(conn);
|
||||
|
||||
const res = await table
|
||||
.mergeInsert("id")
|
||||
.whenMatchedUpdateAll()
|
||||
.whenNotMatchedInsertAll()
|
||||
.execute([
|
||||
{ id: "c", value: 3 },
|
||||
{ id: "d", value: 4 },
|
||||
]);
|
||||
// LSM path: rows go to the MemWAL, so only numRows is populated.
|
||||
expect(res.numRows).toBe(2);
|
||||
expect(res.version).toBe(0);
|
||||
expect(res.numInsertedRows).toBe(0);
|
||||
|
||||
await table.closeLsmWriters();
|
||||
});
|
||||
|
||||
it("falls back to the standard path with useLsmWrite(false)", async () => {
|
||||
const conn = await connect(tmpDir.name);
|
||||
const table = await bucketTable(conn);
|
||||
|
||||
const res = await table
|
||||
.mergeInsert("id")
|
||||
.whenNotMatchedInsertAll()
|
||||
.useLsmWrite(false)
|
||||
.execute([
|
||||
{ id: "b", value: 9 },
|
||||
{ id: "e", value: 5 },
|
||||
]);
|
||||
// Standard path commits: id="e" inserted ("b" already exists).
|
||||
expect(res.numInsertedRows).toBe(1);
|
||||
expect(await table.countRows()).toBe(3);
|
||||
});
|
||||
|
||||
it("supports validateSingleShard(false)", async () => {
|
||||
const conn = await connect(tmpDir.name);
|
||||
const table = await bucketTable(conn);
|
||||
|
||||
const res = await table
|
||||
.mergeInsert("id")
|
||||
.whenMatchedUpdateAll()
|
||||
.whenNotMatchedInsertAll()
|
||||
.validateSingleShard(false)
|
||||
.execute([{ id: "f", value: 6 }]);
|
||||
expect(res.numRows).toBe(1);
|
||||
});
|
||||
|
||||
it("rejects a non-upsert merge under an LSM spec", async () => {
|
||||
const conn = await connect(tmpDir.name);
|
||||
const table = await bucketTable(conn);
|
||||
|
||||
await expect(
|
||||
table
|
||||
.mergeInsert("id")
|
||||
.whenNotMatchedInsertAll()
|
||||
.execute([{ id: "g", value: 7 }]),
|
||||
).rejects.toThrow();
|
||||
});
|
||||
});
|
||||
|
||||
@@ -87,6 +87,41 @@ export class MergeInsertBuilder {
|
||||
this.#schema,
|
||||
);
|
||||
}
|
||||
/**
|
||||
* Controls whether the merge uses the MemWAL LSM write path.
|
||||
*
|
||||
* By default (unset), a `mergeInsert` on a table with an LSM write spec is
|
||||
* routed through Lance's MemWAL shard writer, and a table without one uses
|
||||
* the standard path. Pass `false` to force the standard path even when a
|
||||
* spec is set. Pass `true` to require a spec — `mergeInsert` rejects if none
|
||||
* is installed.
|
||||
*
|
||||
* @param useLsmWrite - Whether to use the LSM write path.
|
||||
*/
|
||||
useLsmWrite(useLsmWrite: boolean): MergeInsertBuilder {
|
||||
return new MergeInsertBuilder(
|
||||
this.#native.useLsmWrite(useLsmWrite),
|
||||
this.#schema,
|
||||
);
|
||||
}
|
||||
/**
|
||||
* Controls how an LSM merge checks that its input targets a single shard.
|
||||
*
|
||||
* When a table has an LSM write spec, every row in a `mergeInsert` call must
|
||||
* route to the same shard. When `true` (the default), every row is inspected
|
||||
* to verify this. When `false`, only the first row is inspected and the
|
||||
* shard it routes to is used for the whole input — a faster path for callers
|
||||
* that have already pre-sharded their input. Has no effect on tables without
|
||||
* an LSM write spec.
|
||||
*
|
||||
* @param validateSingleShard - Whether to check every row routes to one shard. Defaults to `true`.
|
||||
*/
|
||||
validateSingleShard(validateSingleShard: boolean): MergeInsertBuilder {
|
||||
return new MergeInsertBuilder(
|
||||
this.#native.validateSingleShard(validateSingleShard),
|
||||
this.#schema,
|
||||
);
|
||||
}
|
||||
/**
|
||||
* Executes the merge insert operation
|
||||
*
|
||||
|
||||
@@ -161,7 +161,10 @@ export interface Version {
|
||||
*
|
||||
* `specType` is `"bucket"`, `"identity"`, or `"unsharded"`. For `"bucket"`,
|
||||
* `column` and `numBuckets` are required; for `"identity"`, `column` is
|
||||
* required.
|
||||
* required and must be a deterministic function of the unenforced primary
|
||||
* key (every row with a given primary key must always produce the same
|
||||
* `column` value, or upserts of that key can land in different shards and a
|
||||
* stale version can win).
|
||||
*/
|
||||
export interface LsmWriteSpec {
|
||||
/** One of `"bucket"`, `"identity"`, or `"unsharded"`. */
|
||||
@@ -567,6 +570,16 @@ export abstract class Table {
|
||||
* @returns {Promise<void>}
|
||||
*/
|
||||
abstract unsetLsmWriteSpec(): Promise<void>;
|
||||
/**
|
||||
* Drain and close any cached MemWAL shard writers held for this table.
|
||||
*
|
||||
* When an {@link LsmWriteSpec} is installed, `mergeInsert` opens MemWAL
|
||||
* shard writers and caches them for reuse across calls. This closes them,
|
||||
* flushing pending data; writers reopen lazily on the next `mergeInsert`.
|
||||
* It is a no-op when no writers are cached.
|
||||
* @returns {Promise<void>}
|
||||
*/
|
||||
abstract closeLsmWriters(): Promise<void>;
|
||||
/** Retrieve the version of the table */
|
||||
|
||||
abstract version(): Promise<number>;
|
||||
@@ -1041,6 +1054,10 @@ export class LocalTable extends Table {
|
||||
return await this.inner.unsetLsmWriteSpec();
|
||||
}
|
||||
|
||||
async closeLsmWriters(): Promise<void> {
|
||||
return await this.inner.closeLsmWriters();
|
||||
}
|
||||
|
||||
async version(): Promise<number> {
|
||||
return await this.inner.version();
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-darwin-arm64",
|
||||
"version": "0.30.0-beta.0",
|
||||
"version": "0.30.1-beta.0",
|
||||
"os": ["darwin"],
|
||||
"cpu": ["arm64"],
|
||||
"main": "lancedb.darwin-arm64.node",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-linux-arm64-gnu",
|
||||
"version": "0.30.0-beta.0",
|
||||
"version": "0.30.1-beta.0",
|
||||
"os": ["linux"],
|
||||
"cpu": ["arm64"],
|
||||
"main": "lancedb.linux-arm64-gnu.node",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-linux-arm64-musl",
|
||||
"version": "0.30.0-beta.0",
|
||||
"version": "0.30.1-beta.0",
|
||||
"os": ["linux"],
|
||||
"cpu": ["arm64"],
|
||||
"main": "lancedb.linux-arm64-musl.node",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-linux-x64-gnu",
|
||||
"version": "0.30.0-beta.0",
|
||||
"version": "0.30.1-beta.0",
|
||||
"os": ["linux"],
|
||||
"cpu": ["x64"],
|
||||
"main": "lancedb.linux-x64-gnu.node",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-linux-x64-musl",
|
||||
"version": "0.30.0-beta.0",
|
||||
"version": "0.30.1-beta.0",
|
||||
"os": ["linux"],
|
||||
"cpu": ["x64"],
|
||||
"main": "lancedb.linux-x64-musl.node",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-win32-arm64-msvc",
|
||||
"version": "0.30.0-beta.0",
|
||||
"version": "0.30.1-beta.0",
|
||||
"os": [
|
||||
"win32"
|
||||
],
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-win32-x64-msvc",
|
||||
"version": "0.30.0-beta.0",
|
||||
"version": "0.30.1-beta.0",
|
||||
"os": ["win32"],
|
||||
"cpu": ["x64"],
|
||||
"main": "lancedb.win32-x64-msvc.node",
|
||||
|
||||
4
nodejs/package-lock.json
generated
4
nodejs/package-lock.json
generated
@@ -1,12 +1,12 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb",
|
||||
"version": "0.30.0-beta.0",
|
||||
"version": "0.30.1-beta.0",
|
||||
"lockfileVersion": 3,
|
||||
"requires": true,
|
||||
"packages": {
|
||||
"": {
|
||||
"name": "@lancedb/lancedb",
|
||||
"version": "0.30.0-beta.0",
|
||||
"version": "0.30.1-beta.0",
|
||||
"cpu": [
|
||||
"x64",
|
||||
"arm64"
|
||||
|
||||
@@ -11,7 +11,7 @@
|
||||
"ann"
|
||||
],
|
||||
"private": false,
|
||||
"version": "0.30.0-beta.0",
|
||||
"version": "0.30.1-beta.0",
|
||||
"main": "dist/index.js",
|
||||
"exports": {
|
||||
".": "./dist/index.js",
|
||||
|
||||
@@ -24,15 +24,19 @@ mod util;
|
||||
#[napi(object)]
|
||||
#[derive(Debug)]
|
||||
pub struct ConnectionOptions {
|
||||
/// (For LanceDB OSS only): The interval, in seconds, at which to check for
|
||||
/// updates to the table from other processes. If None, then consistency is not
|
||||
/// checked. For performance reasons, this is the default. For strong
|
||||
/// consistency, set this to zero seconds. Then every read will check for
|
||||
/// updates from other processes. As a compromise, you can set this to a
|
||||
/// non-zero value for eventual consistency. If more than that interval
|
||||
/// has passed since the last check, then the table will be checked for updates.
|
||||
/// Note: this consistency only applies to read operations. Write operations are
|
||||
/// The interval, in seconds, at which to check for updates to the table
|
||||
/// from other processes. If None, then consistency is not checked. For
|
||||
/// performance reasons, this is the default. For strong consistency, set
|
||||
/// this to zero seconds. Then every read will check for updates from other
|
||||
/// processes. As a compromise, you can set this to a non-zero value for
|
||||
/// eventual consistency. If more than that interval has passed since the
|
||||
/// last check, then the table will be checked for updates. Note: this
|
||||
/// consistency only applies to read operations. Write operations are
|
||||
/// always consistent.
|
||||
///
|
||||
/// Stronger consistency is not free. The smaller the interval, the more
|
||||
/// often each read pays the cost of checking for updates against object
|
||||
/// storage, raising per-read latency and cost.
|
||||
pub read_consistency_interval: Option<f64>,
|
||||
/// (For LanceDB OSS only): configuration for object storage.
|
||||
///
|
||||
|
||||
@@ -50,6 +50,20 @@ impl NativeMergeInsertBuilder {
|
||||
this
|
||||
}
|
||||
|
||||
#[napi]
|
||||
pub fn use_lsm_write(&self, use_lsm_write: bool) -> Self {
|
||||
let mut this = self.clone();
|
||||
this.inner.use_lsm_write(use_lsm_write);
|
||||
this
|
||||
}
|
||||
|
||||
#[napi]
|
||||
pub fn validate_single_shard(&self, validate_single_shard: bool) -> Self {
|
||||
let mut this = self.clone();
|
||||
this.inner.validate_single_shard(validate_single_shard);
|
||||
this
|
||||
}
|
||||
|
||||
#[napi(catch_unwind)]
|
||||
pub async fn execute(&self, buf: Buffer) -> napi::Result<MergeResult> {
|
||||
let data = ipc_file_to_batches(buf.to_vec())
|
||||
|
||||
@@ -391,6 +391,11 @@ impl Table {
|
||||
.default_error()
|
||||
}
|
||||
|
||||
#[napi(catch_unwind)]
|
||||
pub async fn close_lsm_writers(&self) -> napi::Result<()> {
|
||||
self.inner_ref()?.close_lsm_writers().await.default_error()
|
||||
}
|
||||
|
||||
#[napi(catch_unwind)]
|
||||
pub async fn version(&self) -> napi::Result<i64> {
|
||||
self.inner_ref()?
|
||||
@@ -940,6 +945,7 @@ pub struct MergeResult {
|
||||
pub num_updated_rows: i64,
|
||||
pub num_deleted_rows: i64,
|
||||
pub num_attempts: i64,
|
||||
pub num_rows: i64,
|
||||
}
|
||||
|
||||
impl From<lancedb::table::MergeResult> for MergeResult {
|
||||
@@ -950,6 +956,7 @@ impl From<lancedb::table::MergeResult> for MergeResult {
|
||||
num_updated_rows: value.num_updated_rows as i64,
|
||||
num_deleted_rows: value.num_deleted_rows as i64,
|
||||
num_attempts: value.num_attempts as i64,
|
||||
num_rows: value.num_rows as i64,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
[tool.bumpversion]
|
||||
current_version = "0.33.0-beta.1"
|
||||
current_version = "0.33.1-beta.0"
|
||||
parse = """(?x)
|
||||
(?P<major>0|[1-9]\\d*)\\.
|
||||
(?P<minor>0|[1-9]\\d*)\\.
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "lancedb-python"
|
||||
version = "0.33.0-beta.1"
|
||||
version = "0.33.1-beta.0"
|
||||
publish = false
|
||||
edition.workspace = true
|
||||
description = "Python bindings for LanceDB"
|
||||
|
||||
@@ -10,7 +10,8 @@ dependencies = [
|
||||
"pyarrow>=16",
|
||||
"pydantic>=1.10",
|
||||
"tqdm>=4.27.0",
|
||||
"lance-namespace>=0.3.2"
|
||||
"lance-namespace>=0.3.2",
|
||||
"cryptography==46.0.7",
|
||||
]
|
||||
description = "lancedb"
|
||||
authors = [{ name = "LanceDB Devs", email = "dev@lancedb.com" }]
|
||||
|
||||
@@ -94,7 +94,6 @@ def connect(
|
||||
host_override: str, optional
|
||||
The override url for LanceDB Cloud.
|
||||
read_consistency_interval: timedelta, default None
|
||||
(For LanceDB OSS only)
|
||||
The interval at which to check for updates to the table from other
|
||||
processes. If None, then consistency is not checked. For performance
|
||||
reasons, this is the default. For strong consistency, set this to
|
||||
@@ -104,6 +103,10 @@ def connect(
|
||||
the last check, then the table will be checked for updates. Note: this
|
||||
consistency only applies to read operations. Write operations are
|
||||
always consistent.
|
||||
|
||||
Stronger consistency is not free. The smaller the interval, the more
|
||||
often each read pays the cost of checking for updates against object
|
||||
storage, raising per-read latency and cost.
|
||||
client_config: ClientConfig or dict, optional
|
||||
Configuration options for the LanceDB Cloud HTTP client. If a dict, then
|
||||
the keys are the attributes of the ClientConfig class. If None, then the
|
||||
@@ -147,6 +150,13 @@ def connect(
|
||||
>>> db = lancedb.connect("s3://my-bucket/lancedb",
|
||||
... storage_options={"aws_access_key_id": "***"})
|
||||
|
||||
For tests and temporary data, use an in-memory database:
|
||||
|
||||
>>> db = lancedb.connect("memory://")
|
||||
|
||||
In-memory databases are not persisted. Tables are dropped when the last
|
||||
connection or table handle referencing them is closed.
|
||||
|
||||
Connect to LanceDB cloud:
|
||||
|
||||
>>> db = lancedb.connect("db://my_database", api_key="ldb_...",
|
||||
@@ -210,6 +220,7 @@ def connect(
|
||||
request_thread_pool=request_thread_pool,
|
||||
client_config=client_config,
|
||||
storage_options=storage_options,
|
||||
read_consistency_interval=read_consistency_interval,
|
||||
**kwargs,
|
||||
)
|
||||
_check_s3_bucket_with_dots(str(uri), storage_options)
|
||||
@@ -336,7 +347,6 @@ async def connect_async(
|
||||
host_override: str, optional
|
||||
The override url for LanceDB Cloud.
|
||||
read_consistency_interval: timedelta, default None
|
||||
(For LanceDB OSS only)
|
||||
The interval at which to check for updates to the table from other
|
||||
processes. If None, then consistency is not checked. For performance
|
||||
reasons, this is the default. For strong consistency, set this to
|
||||
@@ -346,6 +356,10 @@ async def connect_async(
|
||||
the last check, then the table will be checked for updates. Note: this
|
||||
consistency only applies to read operations. Write operations are
|
||||
always consistent.
|
||||
|
||||
Stronger consistency is not free. The smaller the interval, the more
|
||||
often each read pays the cost of checking for updates against object
|
||||
storage, raising per-read latency and cost.
|
||||
client_config: ClientConfig or dict, optional
|
||||
Configuration options for the LanceDB Cloud HTTP client. If a dict, then
|
||||
the keys are the attributes of the ClientConfig class. If None, then the
|
||||
@@ -378,6 +392,8 @@ async def connect_async(
|
||||
... db = await lancedb.connect_async("s3://my-bucket/lancedb",
|
||||
... storage_options={
|
||||
... "aws_access_key_id": "***"})
|
||||
... # For tests and temporary data, use an in-memory database
|
||||
... db = await lancedb.connect_async("memory://")
|
||||
... # Connect to LanceDB cloud
|
||||
... db = await lancedb.connect_async("db://my_database", api_key="ldb_...",
|
||||
... client_config={
|
||||
|
||||
@@ -220,6 +220,7 @@ class Table:
|
||||
async def set_unenforced_primary_key(self, columns: List[str]) -> None: ...
|
||||
async def set_lsm_write_spec(self, spec: LsmWriteSpec) -> None: ...
|
||||
async def unset_lsm_write_spec(self) -> None: ...
|
||||
async def close_lsm_writers(self) -> None: ...
|
||||
@property
|
||||
def tags(self) -> Tags: ...
|
||||
def query(self) -> Query: ...
|
||||
@@ -420,6 +421,7 @@ class MergeResult:
|
||||
num_inserted_rows: int
|
||||
num_deleted_rows: int
|
||||
num_attempts: int
|
||||
num_rows: int
|
||||
|
||||
class LsmWriteSpec:
|
||||
"""Specification selecting Lance's MemWAL LSM-style write path for
|
||||
|
||||
@@ -281,6 +281,9 @@ class HnswPq:
|
||||
m: int = 20
|
||||
ef_construction: int = 300
|
||||
target_partition_size: Optional[int] = None
|
||||
# Name of the accelerator (e.g. "cuda") to use for IVF training. When set,
|
||||
# create_index() dispatches to pylance to build the index on the accelerator.
|
||||
accelerator: Optional[str] = None
|
||||
|
||||
|
||||
@dataclass
|
||||
@@ -386,6 +389,9 @@ class HnswSq:
|
||||
m: int = 20
|
||||
ef_construction: int = 300
|
||||
target_partition_size: Optional[int] = None
|
||||
# Name of the accelerator (e.g. "cuda") to use for IVF training. When set,
|
||||
# create_index() dispatches to pylance to build the index on the accelerator.
|
||||
accelerator: Optional[str] = None
|
||||
|
||||
|
||||
@dataclass
|
||||
@@ -579,6 +585,9 @@ class IvfFlat:
|
||||
max_iterations: int = 50
|
||||
sample_rate: int = 256
|
||||
target_partition_size: Optional[int] = None
|
||||
# Name of the accelerator (e.g. "cuda") to use for IVF training. When set,
|
||||
# create_index() dispatches to pylance to build the index on the accelerator.
|
||||
accelerator: Optional[str] = None
|
||||
|
||||
|
||||
@dataclass
|
||||
@@ -609,6 +618,9 @@ class IvfSq:
|
||||
max_iterations: int = 50
|
||||
sample_rate: int = 256
|
||||
target_partition_size: Optional[int] = None
|
||||
# Name of the accelerator (e.g. "cuda") to use for IVF training. When set,
|
||||
# create_index() dispatches to pylance to build the index on the accelerator.
|
||||
accelerator: Optional[str] = None
|
||||
|
||||
|
||||
@dataclass
|
||||
@@ -739,6 +751,9 @@ class IvfPq:
|
||||
max_iterations: int = 50
|
||||
sample_rate: int = 256
|
||||
target_partition_size: Optional[int] = None
|
||||
# Name of the accelerator (e.g. "cuda") to use for IVF training. When set,
|
||||
# create_index() dispatches to pylance to build the index on the accelerator.
|
||||
accelerator: Optional[str] = None
|
||||
|
||||
|
||||
@dataclass
|
||||
@@ -792,6 +807,9 @@ class IvfRq:
|
||||
max_iterations: int = 50
|
||||
sample_rate: int = 256
|
||||
target_partition_size: Optional[int] = None
|
||||
# Name of the accelerator (e.g. "cuda") to use for IVF training. When set,
|
||||
# create_index() dispatches to pylance to build the index on the accelerator.
|
||||
accelerator: Optional[str] = None
|
||||
|
||||
|
||||
__all__ = [
|
||||
|
||||
@@ -34,6 +34,8 @@ class LanceMergeInsertBuilder(object):
|
||||
self._when_not_matched_by_source_condition = None
|
||||
self._timeout = None
|
||||
self._use_index = True
|
||||
self._use_lsm_write = None
|
||||
self._validate_single_shard = None
|
||||
|
||||
def when_matched_update_all(
|
||||
self, *, where: Optional[str] = None
|
||||
@@ -96,6 +98,46 @@ class LanceMergeInsertBuilder(object):
|
||||
self._use_index = use_index
|
||||
return self
|
||||
|
||||
def use_lsm_write(self, use_lsm_write: bool) -> LanceMergeInsertBuilder:
|
||||
"""
|
||||
Controls whether the merge uses the MemWAL LSM write path.
|
||||
|
||||
By default (unset), a `merge_insert` on a table with an LSM write spec
|
||||
is routed through Lance's MemWAL shard writer, and a table without one
|
||||
uses the standard path. Pass `False` to force the standard path even
|
||||
when a spec is set. Pass `True` to require a spec — `merge_insert`
|
||||
raises an error if none is installed.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
use_lsm_write: bool
|
||||
Whether to use the LSM write path.
|
||||
"""
|
||||
self._use_lsm_write = use_lsm_write
|
||||
return self
|
||||
|
||||
def validate_single_shard(
|
||||
self, validate_single_shard: bool
|
||||
) -> LanceMergeInsertBuilder:
|
||||
"""
|
||||
Controls how an LSM merge checks that its input targets a single shard.
|
||||
|
||||
When a table has an LSM write spec, every row in a `merge_insert` call
|
||||
must route to the same shard. When `True` (the default), every row is
|
||||
inspected to verify this. When `False`, only the first row is inspected
|
||||
and the shard it routes to is used for the whole input — a faster path
|
||||
for callers that have already pre-sharded their input.
|
||||
|
||||
Has no effect on tables without an LSM write spec.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
validate_single_shard: bool
|
||||
Whether to check every row routes to one shard. Defaults to `True`.
|
||||
"""
|
||||
self._validate_single_shard = validate_single_shard
|
||||
return self
|
||||
|
||||
def execute(
|
||||
self,
|
||||
new_data: DATA,
|
||||
|
||||
@@ -50,6 +50,7 @@ class RemoteDBConnection(DBConnection):
|
||||
connection_timeout: Optional[float] = None,
|
||||
read_timeout: Optional[float] = None,
|
||||
storage_options: Optional[Dict[str, str]] = None,
|
||||
read_consistency_interval: Optional[timedelta] = None,
|
||||
):
|
||||
"""Connect to a remote LanceDB database."""
|
||||
if isinstance(client_config, dict):
|
||||
@@ -103,6 +104,7 @@ class RemoteDBConnection(DBConnection):
|
||||
host_override=host_override,
|
||||
client_config=client_config,
|
||||
storage_options=storage_options,
|
||||
read_consistency_interval=read_consistency_interval,
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
@@ -2,11 +2,24 @@
|
||||
# SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
|
||||
from datetime import timedelta
|
||||
import deprecation
|
||||
import logging
|
||||
from functools import cached_property
|
||||
from typing import Any, Callable, Dict, Iterable, List, Optional, Union, Literal
|
||||
from typing import (
|
||||
Any,
|
||||
Callable,
|
||||
Dict,
|
||||
Iterable,
|
||||
List,
|
||||
Optional,
|
||||
Union,
|
||||
Literal,
|
||||
overload,
|
||||
)
|
||||
import warnings
|
||||
|
||||
from lancedb import __version__
|
||||
|
||||
from lancedb._lancedb import (
|
||||
AddColumnsResult,
|
||||
AddResult,
|
||||
@@ -32,6 +45,7 @@ from lancedb.index import (
|
||||
LabelList,
|
||||
)
|
||||
from lancedb.remote.db import LOOP
|
||||
from lancedb.table import IndexConfigType, KNOWN_METRICS
|
||||
import pyarrow as pa
|
||||
|
||||
from lancedb.common import DATA, VEC, VECTOR_COLUMN_NAME
|
||||
@@ -122,6 +136,11 @@ class RemoteTable(Table):
|
||||
"""List all the stats of a specified index"""
|
||||
return LOOP.run(self._table.index_stats(index_uuid))
|
||||
|
||||
@deprecation.deprecated(
|
||||
deprecated_in="0.25.0",
|
||||
current_version=__version__,
|
||||
details="Use create_index() with config=BTree()/Bitmap()/LabelList() instead.",
|
||||
)
|
||||
def create_scalar_index(
|
||||
self,
|
||||
column: str,
|
||||
@@ -131,7 +150,12 @@ class RemoteTable(Table):
|
||||
wait_timeout: Optional[timedelta] = None,
|
||||
name: Optional[str] = None,
|
||||
):
|
||||
"""Creates a scalar index
|
||||
"""Creates a scalar index.
|
||||
|
||||
.. deprecated:: 0.25.0
|
||||
Use :meth:`create_index` with a BTree, Bitmap, or LabelList config instead.
|
||||
Example: ``table.create_index("column", config=BTree())``
|
||||
|
||||
Parameters
|
||||
----------
|
||||
column : str
|
||||
@@ -162,6 +186,11 @@ class RemoteTable(Table):
|
||||
)
|
||||
)
|
||||
|
||||
@deprecation.deprecated(
|
||||
deprecated_in="0.25.0",
|
||||
current_version=__version__,
|
||||
details="Use create_index() with config=FTS() instead.",
|
||||
)
|
||||
def create_fts_index(
|
||||
self,
|
||||
column: str,
|
||||
@@ -182,6 +211,12 @@ class RemoteTable(Table):
|
||||
prefix_only: bool = False,
|
||||
name: Optional[str] = None,
|
||||
):
|
||||
"""Create a full-text search index on a column.
|
||||
|
||||
.. deprecated:: 0.25.0
|
||||
Use :meth:`create_index` with an FTS config instead.
|
||||
Example: ``table.create_index("text_column", config=FTS())``
|
||||
"""
|
||||
config = FTS(
|
||||
with_position=with_position,
|
||||
base_tokenizer=base_tokenizer,
|
||||
@@ -205,9 +240,43 @@ class RemoteTable(Table):
|
||||
)
|
||||
)
|
||||
|
||||
# New unified API overload
|
||||
@overload
|
||||
def create_index(
|
||||
self,
|
||||
metric="l2",
|
||||
column: str,
|
||||
/,
|
||||
*,
|
||||
config: IndexConfigType,
|
||||
wait_timeout: Optional[timedelta] = ...,
|
||||
name: Optional[str] = ...,
|
||||
train: bool = ...,
|
||||
) -> None: ...
|
||||
|
||||
# Legacy API overload (deprecated)
|
||||
@overload
|
||||
def create_index(
|
||||
self,
|
||||
metric: Literal["l2", "cosine", "dot", "hamming"] = ...,
|
||||
vector_column_name: str = ...,
|
||||
index_cache_size: Optional[int] = ...,
|
||||
num_partitions: Optional[int] = ...,
|
||||
num_sub_vectors: Optional[int] = ...,
|
||||
replace: Optional[bool] = ...,
|
||||
accelerator: Optional[str] = ...,
|
||||
index_type: Literal[
|
||||
"VECTOR", "IVF_FLAT", "IVF_SQ", "IVF_PQ", "IVF_HNSW_SQ", "IVF_HNSW_PQ"
|
||||
] = ...,
|
||||
wait_timeout: Optional[timedelta] = ...,
|
||||
*,
|
||||
num_bits: int = ...,
|
||||
name: Optional[str] = ...,
|
||||
train: bool = ...,
|
||||
) -> None: ...
|
||||
|
||||
def create_index(
|
||||
self,
|
||||
metric: str = "l2",
|
||||
vector_column_name: str = VECTOR_COLUMN_NAME,
|
||||
index_cache_size: Optional[int] = None,
|
||||
num_partitions: Optional[int] = None,
|
||||
@@ -218,89 +287,113 @@ class RemoteTable(Table):
|
||||
wait_timeout: Optional[timedelta] = None,
|
||||
*,
|
||||
num_bits: int = 8,
|
||||
config: Optional[IndexConfigType] = None,
|
||||
name: Optional[str] = None,
|
||||
train: bool = True,
|
||||
):
|
||||
"""Create an index on the table.
|
||||
"""Create an index on a column.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
metric : str
|
||||
The metric to use for the index. Default is "l2".
|
||||
vector_column_name : str
|
||||
The name of the vector column. Default is "vector".
|
||||
This method supports both the new unified API and the legacy API
|
||||
for backwards compatibility. The new API takes the column name as the
|
||||
first positional argument and an index configuration object via
|
||||
``config``; the legacy API takes the distance metric as the first
|
||||
argument plus separate ``vector_column_name`` / ``num_partitions`` /
|
||||
etc. parameters, and emits a ``DeprecationWarning``.
|
||||
|
||||
Examples
|
||||
--------
|
||||
>>> import lancedb
|
||||
>>> import uuid
|
||||
>>> from lancedb.schema import vector
|
||||
>>> db = lancedb.connect("db://...", api_key="...", # doctest: +SKIP
|
||||
... region="...") # doctest: +SKIP
|
||||
>>> table_name = uuid.uuid4().hex
|
||||
>>> schema = pa.schema(
|
||||
... [
|
||||
... pa.field("id", pa.uint32(), False),
|
||||
... pa.field("vector", vector(128), False),
|
||||
... pa.field("s", pa.string(), False),
|
||||
... ]
|
||||
New API (recommended):
|
||||
|
||||
>>> table.create_index( # doctest: +SKIP
|
||||
... "vector", config=IvfPq(distance_type="l2")
|
||||
... )
|
||||
>>> table = db.create_table( # doctest: +SKIP
|
||||
... table_name, # doctest: +SKIP
|
||||
... schema=schema, # doctest: +SKIP
|
||||
>>> table.create_index("category", config=BTree()) # doctest: +SKIP
|
||||
>>> table.create_index("content", config=FTS()) # doctest: +SKIP
|
||||
|
||||
Legacy API (deprecated):
|
||||
|
||||
>>> table.create_index( # doctest: +SKIP
|
||||
... "l2", vector_column_name="vector"
|
||||
... )
|
||||
>>> table.create_index("l2", "vector") # doctest: +SKIP
|
||||
"""
|
||||
# Detect whether this is a legacy API call
|
||||
is_legacy = self._is_legacy_create_index_call(
|
||||
metric,
|
||||
config,
|
||||
num_partitions,
|
||||
num_sub_vectors,
|
||||
vector_column_name,
|
||||
accelerator,
|
||||
index_cache_size,
|
||||
replace,
|
||||
)
|
||||
|
||||
if accelerator is not None:
|
||||
logging.warning(
|
||||
"GPU accelerator is not yet supported on LanceDB cloud."
|
||||
"If you have 100M+ vectors to index,"
|
||||
"please contact us at contact@lancedb.com"
|
||||
)
|
||||
if replace is not None:
|
||||
logging.warning(
|
||||
"replace is not supported on LanceDB cloud."
|
||||
"Existing indexes will always be replaced."
|
||||
if is_legacy:
|
||||
warnings.warn(
|
||||
"The create_index() API with metric/num_partitions parameters is "
|
||||
"deprecated and will be removed in a future version. "
|
||||
"Please migrate to the new unified API:\n"
|
||||
" # Old (deprecated):\n"
|
||||
" table.create_index('l2', vector_column_name='my_vector')\n"
|
||||
" # New (recommended):\n"
|
||||
" table.create_index('my_vector', config=IvfPq(distance_type='l2'))",
|
||||
DeprecationWarning,
|
||||
stacklevel=2,
|
||||
)
|
||||
|
||||
index_type = index_type.upper()
|
||||
if index_type == "VECTOR" or index_type == "IVF_PQ":
|
||||
config = IvfPq(
|
||||
distance_type=metric,
|
||||
num_partitions=num_partitions,
|
||||
num_sub_vectors=num_sub_vectors,
|
||||
num_bits=num_bits,
|
||||
)
|
||||
elif index_type == "IVF_RQ":
|
||||
config = IvfRq(
|
||||
distance_type=metric,
|
||||
num_partitions=num_partitions,
|
||||
num_bits=num_bits,
|
||||
)
|
||||
elif index_type == "IVF_SQ":
|
||||
config = IvfSq(distance_type=metric, num_partitions=num_partitions)
|
||||
elif index_type == "IVF_HNSW_PQ":
|
||||
raise ValueError(
|
||||
"IVF_HNSW_PQ is not supported on LanceDB cloud."
|
||||
"Please use IVF_HNSW_SQ instead."
|
||||
)
|
||||
elif index_type == "IVF_HNSW_SQ":
|
||||
config = HnswSq(distance_type=metric, num_partitions=num_partitions)
|
||||
elif index_type == "IVF_HNSW_FLAT":
|
||||
config = HnswFlat(distance_type=metric, num_partitions=num_partitions)
|
||||
elif index_type == "IVF_FLAT":
|
||||
config = IvfFlat(distance_type=metric, num_partitions=num_partitions)
|
||||
column = vector_column_name
|
||||
|
||||
if accelerator is not None:
|
||||
logging.warning(
|
||||
"GPU accelerator is not yet supported on LanceDB cloud."
|
||||
"If you have 100M+ vectors to index,"
|
||||
"please contact us at contact@lancedb.com"
|
||||
)
|
||||
if replace is not None:
|
||||
logging.warning(
|
||||
"replace is not supported on LanceDB cloud."
|
||||
"Existing indexes will always be replaced."
|
||||
)
|
||||
|
||||
idx_type = index_type.upper()
|
||||
if idx_type == "VECTOR" or idx_type == "IVF_PQ":
|
||||
config = IvfPq(
|
||||
distance_type=metric,
|
||||
num_partitions=num_partitions,
|
||||
num_sub_vectors=num_sub_vectors,
|
||||
num_bits=num_bits,
|
||||
)
|
||||
elif idx_type == "IVF_RQ":
|
||||
config = IvfRq(
|
||||
distance_type=metric,
|
||||
num_partitions=num_partitions,
|
||||
num_bits=num_bits,
|
||||
)
|
||||
elif idx_type == "IVF_SQ":
|
||||
config = IvfSq(distance_type=metric, num_partitions=num_partitions)
|
||||
elif idx_type == "IVF_HNSW_PQ":
|
||||
raise ValueError(
|
||||
"IVF_HNSW_PQ is not supported on LanceDB cloud."
|
||||
"Please use IVF_HNSW_SQ instead."
|
||||
)
|
||||
elif idx_type == "IVF_HNSW_SQ":
|
||||
config = HnswSq(distance_type=metric, num_partitions=num_partitions)
|
||||
elif idx_type == "IVF_HNSW_FLAT":
|
||||
config = HnswFlat(distance_type=metric, num_partitions=num_partitions)
|
||||
elif idx_type == "IVF_FLAT":
|
||||
config = IvfFlat(distance_type=metric, num_partitions=num_partitions)
|
||||
else:
|
||||
raise ValueError(
|
||||
f"Unknown vector index type: {idx_type}. Valid options are"
|
||||
" 'IVF_FLAT', 'IVF_PQ', 'IVF_RQ', 'IVF_SQ',"
|
||||
" 'IVF_HNSW_PQ', 'IVF_HNSW_SQ', 'IVF_HNSW_FLAT'"
|
||||
)
|
||||
else:
|
||||
raise ValueError(
|
||||
f"Unknown vector index type: {index_type}. Valid options are"
|
||||
" 'IVF_FLAT', 'IVF_PQ', 'IVF_RQ', 'IVF_SQ',"
|
||||
" 'IVF_HNSW_PQ', 'IVF_HNSW_SQ', 'IVF_HNSW_FLAT'"
|
||||
)
|
||||
column = metric
|
||||
|
||||
LOOP.run(
|
||||
self._table.create_index(
|
||||
vector_column_name,
|
||||
column,
|
||||
config=config,
|
||||
wait_timeout=wait_timeout,
|
||||
name=name,
|
||||
@@ -308,6 +401,37 @@ class RemoteTable(Table):
|
||||
)
|
||||
)
|
||||
|
||||
def _is_legacy_create_index_call(
|
||||
self,
|
||||
first_arg: str,
|
||||
config: Optional[IndexConfigType],
|
||||
num_partitions: Optional[int],
|
||||
num_sub_vectors: Optional[int],
|
||||
vector_column_name: str,
|
||||
accelerator: Optional[str],
|
||||
index_cache_size: Optional[int],
|
||||
replace: Optional[bool],
|
||||
) -> bool:
|
||||
"""Detect if this is a legacy create_index call."""
|
||||
if config is not None:
|
||||
return False
|
||||
if any(
|
||||
x is not None
|
||||
for x in (
|
||||
num_partitions,
|
||||
num_sub_vectors,
|
||||
accelerator,
|
||||
index_cache_size,
|
||||
replace,
|
||||
)
|
||||
):
|
||||
return True
|
||||
if vector_column_name != VECTOR_COLUMN_NAME:
|
||||
return True
|
||||
if first_arg.lower() in KNOWN_METRICS:
|
||||
return True
|
||||
return False
|
||||
|
||||
def add(
|
||||
self,
|
||||
data: DATA,
|
||||
@@ -668,6 +792,10 @@ class RemoteTable(Table):
|
||||
"""Not supported on LanceDB Cloud."""
|
||||
return LOOP.run(self._table.unset_lsm_write_spec())
|
||||
|
||||
def close_lsm_writers(self) -> None:
|
||||
"""No-op on LanceDB Cloud (no local shard writers)."""
|
||||
return LOOP.run(self._table.close_lsm_writers())
|
||||
|
||||
def drop_index(self, index_name: str):
|
||||
return LOOP.run(self._table.drop_index(index_name))
|
||||
|
||||
|
||||
@@ -102,8 +102,15 @@ class LinearCombinationReranker(Reranker):
|
||||
|
||||
combined_list = []
|
||||
for row_id, result in results.items():
|
||||
# Convert vector distance to a relevance score in [0, 1] where
|
||||
# higher is better. Missing vector entries are penalised with
|
||||
# `_invert_score(fill)` = 1 - fill (= 0.0 for the default fill=1).
|
||||
vector_score = self._invert_score(result.get("_distance", fill))
|
||||
fts_score = result.get("_score", fill)
|
||||
# FTS scores (BM25) are already in a "higher = more relevant" space.
|
||||
# Missing FTS entries are penalised symmetrically: we use
|
||||
# `1 - fill` so that the same `fill` value drives both missing-vector
|
||||
# and missing-FTS penalties in the same direction.
|
||||
fts_score = result.get("_score", 1 - fill)
|
||||
result["_relevance_score"] = self._combine_score(vector_score, fts_score)
|
||||
combined_list.append(result)
|
||||
|
||||
@@ -123,8 +130,12 @@ class LinearCombinationReranker(Reranker):
|
||||
return tbl
|
||||
|
||||
def _combine_score(self, vector_score, fts_score):
|
||||
# these scores represent distance
|
||||
return 1 - (self.weight * vector_score + (1 - self.weight) * fts_score)
|
||||
# Both vector_score (inverted distance) and fts_score are in a
|
||||
# "higher = more relevant" space. A straight weighted average gives
|
||||
# higher _relevance_score to better matches, as expected.
|
||||
# Previously this returned `1 - (...)` which inverted the final
|
||||
# ranking so that the *least* relevant document ranked first.
|
||||
return self.weight * vector_score + (1 - self.weight) * fts_score
|
||||
|
||||
def _invert_score(self, dist: float):
|
||||
# Invert the score between relevance and distance
|
||||
|
||||
@@ -174,6 +174,24 @@ if TYPE_CHECKING:
|
||||
DistanceType,
|
||||
)
|
||||
|
||||
# Type alias for index configuration objects
|
||||
IndexConfigType = Union[
|
||||
IvfFlat,
|
||||
IvfPq,
|
||||
IvfSq,
|
||||
IvfRq,
|
||||
HnswFlat,
|
||||
HnswPq,
|
||||
HnswSq,
|
||||
BTree,
|
||||
Bitmap,
|
||||
LabelList,
|
||||
FTS,
|
||||
]
|
||||
|
||||
# Known distance metrics for legacy API detection
|
||||
KNOWN_METRICS = {"l2", "cosine", "dot", "hamming"}
|
||||
|
||||
|
||||
def _into_pyarrow_reader(
|
||||
data, schema: Optional[pa.Schema] = None
|
||||
@@ -807,11 +825,49 @@ class Table(ABC):
|
||||
"""
|
||||
raise NotImplementedError
|
||||
|
||||
# New unified API overload
|
||||
@overload
|
||||
def create_index(
|
||||
self,
|
||||
metric="l2",
|
||||
num_partitions=256,
|
||||
num_sub_vectors=96,
|
||||
column: str,
|
||||
/,
|
||||
*,
|
||||
config: IndexConfigType,
|
||||
replace: bool = ...,
|
||||
wait_timeout: Optional[timedelta] = ...,
|
||||
name: Optional[str] = ...,
|
||||
train: bool = ...,
|
||||
) -> None: ...
|
||||
|
||||
# Legacy API overload (deprecated)
|
||||
@overload
|
||||
def create_index(
|
||||
self,
|
||||
metric: Literal["l2", "cosine", "dot", "hamming"] = ...,
|
||||
num_partitions: Optional[int] = ...,
|
||||
num_sub_vectors: Optional[int] = ...,
|
||||
vector_column_name: str = ...,
|
||||
replace: bool = ...,
|
||||
accelerator: Optional[str] = ...,
|
||||
index_cache_size: Optional[int] = ...,
|
||||
*,
|
||||
index_type: VectorIndexType = ...,
|
||||
wait_timeout: Optional[timedelta] = ...,
|
||||
num_bits: int = ...,
|
||||
max_iterations: int = ...,
|
||||
sample_rate: int = ...,
|
||||
m: int = ...,
|
||||
ef_construction: int = ...,
|
||||
name: Optional[str] = ...,
|
||||
train: bool = ...,
|
||||
target_partition_size: Optional[int] = ...,
|
||||
) -> None: ...
|
||||
|
||||
def create_index(
|
||||
self,
|
||||
metric: DistanceType = "l2",
|
||||
num_partitions: Optional[int] = None,
|
||||
num_sub_vectors: Optional[int] = None,
|
||||
vector_column_name: str = VECTOR_COLUMN_NAME,
|
||||
replace: bool = True,
|
||||
accelerator: Optional[str] = None,
|
||||
@@ -824,46 +880,53 @@ class Table(ABC):
|
||||
sample_rate: int = 256,
|
||||
m: int = 20,
|
||||
ef_construction: int = 300,
|
||||
config: Optional[IndexConfigType] = None,
|
||||
name: Optional[str] = None,
|
||||
train: bool = True,
|
||||
target_partition_size: Optional[int] = None,
|
||||
):
|
||||
"""Create an index on the table.
|
||||
"""Create an index on a column.
|
||||
|
||||
This method supports both the new unified API and the legacy API
|
||||
for backwards compatibility. The new API takes the column name as the
|
||||
first positional argument and an index configuration object via
|
||||
``config``; the legacy API takes the distance metric as the first
|
||||
argument plus separate ``vector_column_name`` / ``num_partitions`` /
|
||||
etc. parameters, and emits a ``DeprecationWarning``.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
metric: str, default "l2"
|
||||
The distance metric to use when creating the index.
|
||||
Valid values are "l2", "cosine", "dot", or "hamming".
|
||||
l2 is euclidean distance.
|
||||
Hamming is available only for binary vectors.
|
||||
num_partitions: int, default 256
|
||||
The number of IVF partitions to use when creating the index.
|
||||
Default is 256.
|
||||
num_sub_vectors: int, default 96
|
||||
The number of PQ sub-vectors to use when creating the index.
|
||||
Default is 96.
|
||||
vector_column_name: str, default "vector"
|
||||
The vector column name to create the index.
|
||||
replace: bool, default True
|
||||
- If True, replace the existing index if it exists.
|
||||
metric : str
|
||||
For new API: the column name to index.
|
||||
For legacy API: the distance metric ("l2", "cosine", "dot", "hamming").
|
||||
config : IndexConfigType, optional
|
||||
The index configuration object. If provided, uses the new unified API.
|
||||
Can be one of: IvfFlat, IvfPq, IvfSq, IvfRq, HnswPq, HnswSq,
|
||||
BTree, Bitmap, LabelList, FTS.
|
||||
replace : bool, default True
|
||||
Whether to replace an existing index on this column.
|
||||
wait_timeout : timedelta, optional
|
||||
Timeout to wait for async indexing to complete.
|
||||
name : str, optional
|
||||
Custom name for the index.
|
||||
train : bool, default True
|
||||
Whether to train the index with existing data.
|
||||
|
||||
- If False, raise an error if duplicate index exists.
|
||||
accelerator: str, default None
|
||||
If set, use the given accelerator to create the index.
|
||||
Only support "cuda" for now.
|
||||
index_cache_size : int, optional
|
||||
The size of the index cache in number of entries. Default value is 256.
|
||||
num_bits: int
|
||||
The number of bits to encode sub-vectors. Only used with the IVF_PQ index.
|
||||
Only 4 and 8 are supported.
|
||||
wait_timeout: timedelta, optional
|
||||
The timeout to wait if indexing is asynchronous.
|
||||
name: str, optional
|
||||
The name of the index. If not provided, a default name will be generated.
|
||||
train: bool, default True
|
||||
Whether to train the index with existing data. Vector indices always train
|
||||
with existing data.
|
||||
Examples
|
||||
--------
|
||||
New API (recommended):
|
||||
|
||||
>>> table.create_index( # doctest: +SKIP
|
||||
... "vector", config=IvfPq(distance_type="l2")
|
||||
... )
|
||||
>>> table.create_index("category", config=BTree()) # doctest: +SKIP
|
||||
>>> table.create_index("content", config=FTS()) # doctest: +SKIP
|
||||
|
||||
Legacy API (deprecated):
|
||||
|
||||
>>> table.create_index( # doctest: +SKIP
|
||||
... "l2", vector_column_name="vector"
|
||||
... )
|
||||
"""
|
||||
raise NotImplementedError
|
||||
|
||||
@@ -1188,7 +1251,7 @@ class Table(ABC):
|
||||
... .when_not_matched_insert_all() \\
|
||||
... .execute(new_data)
|
||||
>>> res
|
||||
MergeResult(version=2, num_updated_rows=2, num_inserted_rows=1, num_deleted_rows=0, num_attempts=1)
|
||||
MergeResult(version=2, num_updated_rows=2, num_inserted_rows=1, num_deleted_rows=0, num_attempts=1, num_rows=3)
|
||||
>>> # The order of new rows is non-deterministic since we use
|
||||
>>> # a hash-join as part of this operation and so we sort here
|
||||
>>> table.to_arrow().sort_by("a").to_pandas()
|
||||
@@ -2250,11 +2313,51 @@ class LanceTable(Table):
|
||||
dataset, allow_pyarrow_filter=False, batch_size=batch_size
|
||||
)
|
||||
|
||||
# New unified API overload
|
||||
@overload
|
||||
def create_index(
|
||||
self,
|
||||
metric: DistanceType = "l2",
|
||||
num_partitions=None,
|
||||
num_sub_vectors=None,
|
||||
column: str,
|
||||
/,
|
||||
*,
|
||||
config: IndexConfigType,
|
||||
replace: bool = ...,
|
||||
wait_timeout: Optional[timedelta] = ...,
|
||||
name: Optional[str] = ...,
|
||||
train: bool = ...,
|
||||
) -> None: ...
|
||||
|
||||
# Legacy API overload (deprecated)
|
||||
@overload
|
||||
def create_index(
|
||||
self,
|
||||
metric: Literal["l2", "cosine", "dot", "hamming"] = ...,
|
||||
num_partitions: Optional[int] = ...,
|
||||
num_sub_vectors: Optional[int] = ...,
|
||||
vector_column_name: str = ...,
|
||||
replace: bool = ...,
|
||||
accelerator: Optional[str] = ...,
|
||||
index_cache_size: Optional[int] = ...,
|
||||
num_bits: int = ...,
|
||||
index_type: Literal[
|
||||
"IVF_FLAT", "IVF_SQ", "IVF_PQ", "IVF_RQ", "IVF_HNSW_SQ", "IVF_HNSW_PQ"
|
||||
] = ...,
|
||||
max_iterations: int = ...,
|
||||
sample_rate: int = ...,
|
||||
m: int = ...,
|
||||
ef_construction: int = ...,
|
||||
*,
|
||||
wait_timeout: Optional[timedelta] = ...,
|
||||
name: Optional[str] = ...,
|
||||
train: bool = ...,
|
||||
target_partition_size: Optional[int] = ...,
|
||||
) -> None: ...
|
||||
|
||||
def create_index(
|
||||
self,
|
||||
metric: str = "l2",
|
||||
num_partitions: Optional[int] = None,
|
||||
num_sub_vectors: Optional[int] = None,
|
||||
vector_column_name: str = VECTOR_COLUMN_NAME,
|
||||
replace: bool = True,
|
||||
accelerator: Optional[str] = None,
|
||||
@@ -2274,47 +2377,232 @@ class LanceTable(Table):
|
||||
m: int = 20,
|
||||
ef_construction: int = 300,
|
||||
*,
|
||||
config: Optional[IndexConfigType] = None,
|
||||
wait_timeout: Optional[timedelta] = None,
|
||||
name: Optional[str] = None,
|
||||
train: bool = True,
|
||||
target_partition_size: Optional[int] = None,
|
||||
):
|
||||
"""Create an index on the table."""
|
||||
if accelerator is not None:
|
||||
# accelerator is only supported through pylance.
|
||||
self.to_lance().create_index(
|
||||
column=vector_column_name,
|
||||
index_type=index_type,
|
||||
"""Create an index on a column.
|
||||
|
||||
This method supports both the new unified API and the legacy API
|
||||
for backwards compatibility. The new API takes the column name as the
|
||||
first positional argument and an index configuration object via
|
||||
``config``; the legacy API takes the distance metric as the first
|
||||
argument plus separate ``vector_column_name`` / ``num_partitions`` /
|
||||
etc. parameters, and emits a ``DeprecationWarning``.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
metric : str
|
||||
For new API: the column name to index.
|
||||
For legacy API: the distance metric ("l2", "cosine", "dot", "hamming").
|
||||
config : IndexConfigType, optional
|
||||
The index configuration object. If provided, uses the new unified API.
|
||||
Can be one of: IvfFlat, IvfPq, IvfSq, IvfRq, HnswPq, HnswSq,
|
||||
BTree, Bitmap, LabelList, FTS.
|
||||
replace : bool, default True
|
||||
Whether to replace an existing index on this column.
|
||||
wait_timeout : timedelta, optional
|
||||
Timeout to wait for async indexing to complete.
|
||||
name : str, optional
|
||||
Custom name for the index.
|
||||
train : bool, default True
|
||||
Whether to train the index with existing data.
|
||||
|
||||
Examples
|
||||
--------
|
||||
New API (recommended):
|
||||
|
||||
>>> table.create_index( # doctest: +SKIP
|
||||
... "vector", config=IvfPq(distance_type="l2")
|
||||
... )
|
||||
>>> table.create_index("category", config=BTree()) # doctest: +SKIP
|
||||
>>> table.create_index("content", config=FTS()) # doctest: +SKIP
|
||||
|
||||
Legacy API (deprecated):
|
||||
|
||||
>>> table.create_index( # doctest: +SKIP
|
||||
... "l2", vector_column_name="vector"
|
||||
... )
|
||||
"""
|
||||
# Detect whether this is a legacy API call
|
||||
is_legacy = self._is_legacy_create_index_call(
|
||||
metric,
|
||||
config,
|
||||
num_partitions,
|
||||
num_sub_vectors,
|
||||
vector_column_name,
|
||||
accelerator,
|
||||
index_cache_size,
|
||||
)
|
||||
|
||||
if is_legacy:
|
||||
warnings.warn(
|
||||
"The create_index() API with metric/num_partitions parameters is "
|
||||
"deprecated and will be removed in a future version. "
|
||||
"Please migrate to the new unified API:\n"
|
||||
" # Old (deprecated):\n"
|
||||
" table.create_index('l2', vector_column_name='my_vector')\n"
|
||||
" # New (recommended):\n"
|
||||
" table.create_index('my_vector', config=IvfPq(distance_type='l2'))",
|
||||
DeprecationWarning,
|
||||
stacklevel=2,
|
||||
)
|
||||
|
||||
# Legacy API: first arg is the distance metric
|
||||
column = vector_column_name
|
||||
|
||||
# Build config from legacy parameters
|
||||
config = self._build_vector_config_from_legacy_params(
|
||||
metric=metric,
|
||||
index_type=index_type,
|
||||
num_partitions=num_partitions,
|
||||
num_sub_vectors=num_sub_vectors,
|
||||
replace=replace,
|
||||
accelerator=accelerator,
|
||||
index_cache_size=index_cache_size,
|
||||
num_bits=num_bits,
|
||||
max_iterations=max_iterations,
|
||||
sample_rate=sample_rate,
|
||||
m=m,
|
||||
ef_construction=ef_construction,
|
||||
target_partition_size=target_partition_size,
|
||||
accelerator=accelerator,
|
||||
)
|
||||
self.checkout_latest()
|
||||
return
|
||||
elif index_type == "IVF_FLAT":
|
||||
config = IvfFlat(
|
||||
|
||||
# Handle accelerator through pylance
|
||||
if accelerator is not None:
|
||||
self.to_lance().create_index(
|
||||
column=column,
|
||||
index_type=index_type,
|
||||
metric=metric,
|
||||
num_partitions=num_partitions,
|
||||
num_sub_vectors=num_sub_vectors,
|
||||
replace=replace,
|
||||
accelerator=accelerator,
|
||||
index_cache_size=index_cache_size,
|
||||
num_bits=num_bits,
|
||||
m=m,
|
||||
ef_construction=ef_construction,
|
||||
target_partition_size=target_partition_size,
|
||||
)
|
||||
self.checkout_latest()
|
||||
return
|
||||
else:
|
||||
# New API: metric is the column name
|
||||
column = metric
|
||||
|
||||
# Check if config has accelerator set and dispatch to pylance
|
||||
if config is not None and hasattr(config, "accelerator"):
|
||||
acc = getattr(config, "accelerator", None)
|
||||
if acc is not None:
|
||||
# Dispatch to pylance for GPU acceleration
|
||||
index_type_map = {
|
||||
"IvfFlat": "IVF_FLAT",
|
||||
"IvfSq": "IVF_SQ",
|
||||
"IvfPq": "IVF_PQ",
|
||||
"IvfRq": "IVF_RQ",
|
||||
"HnswPq": "IVF_HNSW_PQ",
|
||||
"HnswSq": "IVF_HNSW_SQ",
|
||||
}
|
||||
cfg_type = type(config).__name__
|
||||
lance_index_type = index_type_map.get(cfg_type, "IVF_PQ")
|
||||
|
||||
self.to_lance().create_index(
|
||||
column=column,
|
||||
index_type=lance_index_type,
|
||||
metric=getattr(config, "distance_type", "l2"),
|
||||
num_partitions=getattr(config, "num_partitions", None),
|
||||
num_sub_vectors=getattr(config, "num_sub_vectors", None),
|
||||
replace=replace,
|
||||
accelerator=acc,
|
||||
num_bits=getattr(config, "num_bits", 8),
|
||||
m=getattr(config, "m", 20),
|
||||
ef_construction=getattr(config, "ef_construction", 300),
|
||||
target_partition_size=getattr(
|
||||
config, "target_partition_size", None
|
||||
),
|
||||
)
|
||||
self.checkout_latest()
|
||||
return
|
||||
|
||||
return LOOP.run(
|
||||
self._table.create_index(
|
||||
column,
|
||||
replace=replace,
|
||||
config=config,
|
||||
wait_timeout=wait_timeout,
|
||||
name=name,
|
||||
train=train,
|
||||
)
|
||||
)
|
||||
|
||||
def _is_legacy_create_index_call(
|
||||
self,
|
||||
first_arg: str,
|
||||
config: Optional[IndexConfigType],
|
||||
num_partitions: Optional[int],
|
||||
num_sub_vectors: Optional[int],
|
||||
vector_column_name: str,
|
||||
accelerator: Optional[str],
|
||||
index_cache_size: Optional[int],
|
||||
) -> bool:
|
||||
"""Detect if this is a legacy create_index call."""
|
||||
# If config is provided, it's definitely the new API
|
||||
if config is not None:
|
||||
return False
|
||||
|
||||
# If old-style parameters were explicitly set, it's legacy
|
||||
if any(
|
||||
x is not None
|
||||
for x in (num_partitions, num_sub_vectors, accelerator, index_cache_size)
|
||||
):
|
||||
return True
|
||||
|
||||
# If vector_column_name differs from default, it's legacy
|
||||
if vector_column_name != VECTOR_COLUMN_NAME:
|
||||
return True
|
||||
|
||||
# If first arg is a known metric, assume legacy
|
||||
if first_arg.lower() in KNOWN_METRICS:
|
||||
return True
|
||||
|
||||
# Otherwise assume new API
|
||||
return False
|
||||
|
||||
def _build_vector_config_from_legacy_params(
|
||||
self,
|
||||
metric: str,
|
||||
index_type: str,
|
||||
num_partitions: Optional[int],
|
||||
num_sub_vectors: Optional[int],
|
||||
num_bits: int,
|
||||
max_iterations: int,
|
||||
sample_rate: int,
|
||||
m: int,
|
||||
ef_construction: int,
|
||||
target_partition_size: Optional[int],
|
||||
accelerator: Optional[str],
|
||||
) -> IndexConfigType:
|
||||
"""Build an index config object from legacy parameters."""
|
||||
if index_type == "IVF_FLAT":
|
||||
return IvfFlat(
|
||||
distance_type=metric,
|
||||
num_partitions=num_partitions,
|
||||
max_iterations=max_iterations,
|
||||
sample_rate=sample_rate,
|
||||
target_partition_size=target_partition_size,
|
||||
accelerator=accelerator,
|
||||
)
|
||||
elif index_type == "IVF_SQ":
|
||||
config = IvfSq(
|
||||
return IvfSq(
|
||||
distance_type=metric,
|
||||
num_partitions=num_partitions,
|
||||
max_iterations=max_iterations,
|
||||
sample_rate=sample_rate,
|
||||
target_partition_size=target_partition_size,
|
||||
accelerator=accelerator,
|
||||
)
|
||||
elif index_type == "IVF_PQ":
|
||||
config = IvfPq(
|
||||
return IvfPq(
|
||||
distance_type=metric,
|
||||
num_partitions=num_partitions,
|
||||
num_sub_vectors=num_sub_vectors,
|
||||
@@ -2322,18 +2610,20 @@ class LanceTable(Table):
|
||||
max_iterations=max_iterations,
|
||||
sample_rate=sample_rate,
|
||||
target_partition_size=target_partition_size,
|
||||
accelerator=accelerator,
|
||||
)
|
||||
elif index_type == "IVF_RQ":
|
||||
config = IvfRq(
|
||||
return IvfRq(
|
||||
distance_type=metric,
|
||||
num_partitions=num_partitions,
|
||||
num_bits=num_bits,
|
||||
max_iterations=max_iterations,
|
||||
sample_rate=sample_rate,
|
||||
target_partition_size=target_partition_size,
|
||||
accelerator=accelerator,
|
||||
)
|
||||
elif index_type == "IVF_HNSW_PQ":
|
||||
config = HnswPq(
|
||||
return HnswPq(
|
||||
distance_type=metric,
|
||||
num_partitions=num_partitions,
|
||||
num_sub_vectors=num_sub_vectors,
|
||||
@@ -2343,9 +2633,10 @@ class LanceTable(Table):
|
||||
m=m,
|
||||
ef_construction=ef_construction,
|
||||
target_partition_size=target_partition_size,
|
||||
accelerator=accelerator,
|
||||
)
|
||||
elif index_type == "IVF_HNSW_SQ":
|
||||
config = HnswSq(
|
||||
return HnswSq(
|
||||
distance_type=metric,
|
||||
num_partitions=num_partitions,
|
||||
max_iterations=max_iterations,
|
||||
@@ -2353,9 +2644,10 @@ class LanceTable(Table):
|
||||
m=m,
|
||||
ef_construction=ef_construction,
|
||||
target_partition_size=target_partition_size,
|
||||
accelerator=accelerator,
|
||||
)
|
||||
elif index_type == "IVF_HNSW_FLAT":
|
||||
config = HnswFlat(
|
||||
return HnswFlat(
|
||||
distance_type=metric,
|
||||
num_partitions=num_partitions,
|
||||
max_iterations=max_iterations,
|
||||
@@ -2367,16 +2659,6 @@ class LanceTable(Table):
|
||||
else:
|
||||
raise ValueError(f"Unknown index type {index_type}")
|
||||
|
||||
return LOOP.run(
|
||||
self._table.create_index(
|
||||
vector_column_name,
|
||||
replace=replace,
|
||||
config=config,
|
||||
name=name,
|
||||
train=train,
|
||||
)
|
||||
)
|
||||
|
||||
def drop_index(self, name: str) -> None:
|
||||
"""
|
||||
Drops an index from the table
|
||||
@@ -2476,6 +2758,11 @@ class LanceTable(Table):
|
||||
"""
|
||||
return LOOP.run(self._table.latest_storage_options())
|
||||
|
||||
@deprecation.deprecated(
|
||||
deprecated_in="0.25.0",
|
||||
current_version=__version__,
|
||||
details="Use create_index() with config=BTree()/Bitmap()/LabelList() instead.",
|
||||
)
|
||||
def create_scalar_index(
|
||||
self,
|
||||
column: str,
|
||||
@@ -2484,6 +2771,12 @@ class LanceTable(Table):
|
||||
index_type: ScalarIndexType = "BTREE",
|
||||
name: Optional[str] = None,
|
||||
):
|
||||
"""Create a scalar index on a column.
|
||||
|
||||
.. deprecated:: 0.25.0
|
||||
Use :meth:`create_index` with a BTree, Bitmap, or LabelList config instead.
|
||||
Example: ``table.create_index("column", config=BTree())``
|
||||
"""
|
||||
if index_type == "BTREE":
|
||||
config = BTree()
|
||||
elif index_type == "BITMAP":
|
||||
@@ -2496,6 +2789,11 @@ class LanceTable(Table):
|
||||
self._table.create_index(column, replace=replace, config=config, name=name)
|
||||
)
|
||||
|
||||
@deprecation.deprecated(
|
||||
deprecated_in="0.25.0",
|
||||
current_version=__version__,
|
||||
details="Use create_index() with config=FTS() instead.",
|
||||
)
|
||||
def create_fts_index(
|
||||
self,
|
||||
field_names: Union[str, List[str]],
|
||||
@@ -2519,6 +2817,12 @@ class LanceTable(Table):
|
||||
prefix_only: bool = False,
|
||||
name: Optional[str] = None,
|
||||
):
|
||||
"""Create a full-text search index on a column.
|
||||
|
||||
.. deprecated:: 0.25.0
|
||||
Use :meth:`create_index` with an FTS config instead.
|
||||
Example: ``table.create_index("text_column", config=FTS())``
|
||||
"""
|
||||
self._ensure_no_legacy_fts_index()
|
||||
|
||||
if use_tantivy:
|
||||
@@ -3297,6 +3601,11 @@ class LanceTable(Table):
|
||||
[`AsyncTable.unset_lsm_write_spec`][lancedb.AsyncTable.unset_lsm_write_spec]."""
|
||||
return LOOP.run(self._table.unset_lsm_write_spec())
|
||||
|
||||
def close_lsm_writers(self) -> None:
|
||||
"""Close cached MemWAL shard writers. See
|
||||
[`AsyncTable.close_lsm_writers`][lancedb.AsyncTable.close_lsm_writers]."""
|
||||
return LOOP.run(self._table.close_lsm_writers())
|
||||
|
||||
def uses_v2_manifest_paths(self) -> bool:
|
||||
"""
|
||||
Check if the table is using the new v2 manifest paths.
|
||||
@@ -3905,6 +4214,16 @@ class AsyncTable:
|
||||
"""
|
||||
await self._inner.unset_lsm_write_spec()
|
||||
|
||||
async def close_lsm_writers(self) -> None:
|
||||
"""Drain and close any cached MemWAL shard writers for this table.
|
||||
|
||||
When an LSM write spec is installed, `merge_insert` opens MemWAL shard
|
||||
writers and caches them for reuse across calls. This closes them,
|
||||
flushing pending data; writers reopen lazily on the next
|
||||
`merge_insert`. It is a no-op when no writers are cached.
|
||||
"""
|
||||
await self._inner.close_lsm_writers()
|
||||
|
||||
@property
|
||||
def name(self) -> str:
|
||||
"""The name of the table."""
|
||||
@@ -4355,7 +4674,7 @@ class AsyncTable:
|
||||
... .when_not_matched_insert_all() \\
|
||||
... .execute(new_data)
|
||||
>>> res
|
||||
MergeResult(version=2, num_updated_rows=2, num_inserted_rows=1, num_deleted_rows=0, num_attempts=1)
|
||||
MergeResult(version=2, num_updated_rows=2, num_inserted_rows=1, num_deleted_rows=0, num_attempts=1, num_rows=3)
|
||||
>>> # The order of new rows is non-deterministic since we use
|
||||
>>> # a hash-join as part of this operation and so we sort here
|
||||
>>> table.to_arrow().sort_by("a").to_pandas()
|
||||
@@ -4735,6 +5054,8 @@ class AsyncTable:
|
||||
when_not_matched_by_source_condition=merge._when_not_matched_by_source_condition,
|
||||
timeout=merge._timeout,
|
||||
use_index=merge._use_index,
|
||||
use_lsm_write=merge._use_lsm_write,
|
||||
validate_single_shard=merge._validate_single_shard,
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
@@ -57,7 +57,7 @@ async def test_upsert_async(mem_db_async):
|
||||
await table.count_rows() # 3
|
||||
res
|
||||
# MergeResult(version=2, num_updated_rows=1,
|
||||
# num_inserted_rows=1, num_deleted_rows=0)
|
||||
# num_inserted_rows=1, num_deleted_rows=0, num_rows=2)
|
||||
# --8<-- [end:upsert_basic_async]
|
||||
assert await table.count_rows() == 3
|
||||
assert res.version == 2
|
||||
@@ -86,7 +86,7 @@ def test_insert_if_not_exists(mem_db):
|
||||
table.count_rows() # 3
|
||||
res
|
||||
# MergeResult(version=2, num_updated_rows=0,
|
||||
# num_inserted_rows=1, num_deleted_rows=0)
|
||||
# num_inserted_rows=1, num_deleted_rows=0, num_rows=1)
|
||||
# --8<-- [end:insert_if_not_exists]
|
||||
assert table.count_rows() == 3
|
||||
assert res.version == 2
|
||||
@@ -116,7 +116,7 @@ async def test_insert_if_not_exists_async(mem_db_async):
|
||||
await table.count_rows() # 3
|
||||
res
|
||||
# MergeResult(version=2, num_updated_rows=0,
|
||||
# num_inserted_rows=1, num_deleted_rows=0)
|
||||
# num_inserted_rows=1, num_deleted_rows=0, num_rows=1)
|
||||
# --8<-- [end:insert_if_not_exists]
|
||||
assert await table.count_rows() == 3
|
||||
assert res.version == 2
|
||||
@@ -150,7 +150,7 @@ def test_replace_range(mem_db):
|
||||
table.count_rows("doc_id = 1") # 1
|
||||
res
|
||||
# MergeResult(version=2, num_updated_rows=1,
|
||||
# num_inserted_rows=0, num_deleted_rows=1)
|
||||
# num_inserted_rows=0, num_deleted_rows=1, num_rows=1)
|
||||
# --8<-- [end:insert_if_not_exists]
|
||||
assert table.count_rows("doc_id = 1") == 1
|
||||
assert res.version == 2
|
||||
@@ -185,7 +185,7 @@ async def test_replace_range_async(mem_db_async):
|
||||
await table.count_rows("doc_id = 1") # 1
|
||||
res
|
||||
# MergeResult(version=2, num_updated_rows=1,
|
||||
# num_inserted_rows=0, num_deleted_rows=1)
|
||||
# num_inserted_rows=0, num_deleted_rows=1, num_rows=1)
|
||||
# --8<-- [end:insert_if_not_exists]
|
||||
assert await table.count_rows("doc_id = 1") == 1
|
||||
assert res.version == 2
|
||||
|
||||
@@ -466,7 +466,8 @@ async def test_create_table_v2_manifest_paths_async(tmp_path):
|
||||
assert await tbl.uses_v2_manifest_paths()
|
||||
manifests_dir = tmp_path / "test_v2_manifest_paths.lance" / "_versions"
|
||||
for manifest in os.listdir(manifests_dir):
|
||||
assert re.match(r"\d{20}\.manifest", manifest)
|
||||
if manifest.endswith(".manifest"):
|
||||
assert re.match(r"\d{20}\.manifest", manifest)
|
||||
|
||||
# Start a table in V1 mode then migrate
|
||||
tbl = await db_no_v2_paths.create_table(
|
||||
@@ -476,13 +477,15 @@ async def test_create_table_v2_manifest_paths_async(tmp_path):
|
||||
assert not await tbl.uses_v2_manifest_paths()
|
||||
manifests_dir = tmp_path / "test_v2_migration.lance" / "_versions"
|
||||
for manifest in os.listdir(manifests_dir):
|
||||
assert re.match(r"\d\.manifest", manifest)
|
||||
if manifest.endswith(".manifest"):
|
||||
assert re.match(r"\d\.manifest", manifest)
|
||||
|
||||
await tbl.migrate_manifest_paths_v2()
|
||||
assert await tbl.uses_v2_manifest_paths()
|
||||
|
||||
for manifest in os.listdir(manifests_dir):
|
||||
assert re.match(r"\d{20}\.manifest", manifest)
|
||||
if manifest.endswith(".manifest"):
|
||||
assert re.match(r"\d{20}\.manifest", manifest)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
|
||||
@@ -215,11 +215,12 @@ def test_reject_legacy_tantivy_index(table):
|
||||
|
||||
@pytest.mark.parametrize("with_position", [True, False])
|
||||
def test_create_inverted_index(table, with_position):
|
||||
table.create_fts_index(
|
||||
"text",
|
||||
with_position=with_position,
|
||||
name="custom_fts_index",
|
||||
)
|
||||
with pytest.warns(DeprecationWarning, match="create_fts_index"):
|
||||
table.create_fts_index(
|
||||
"text",
|
||||
with_position=with_position,
|
||||
name="custom_fts_index",
|
||||
)
|
||||
indices = table.list_indices()
|
||||
fts_indices = [i for i in indices if i.index_type == "FTS"]
|
||||
assert any(i.name == "custom_fts_index" for i in fts_indices)
|
||||
|
||||
@@ -162,12 +162,13 @@ async def test_create_bitmap_index(some_table: AsyncTable):
|
||||
await some_table.create_index("data", config=Bitmap())
|
||||
indices = await some_table.list_indices()
|
||||
assert len(indices) == 3
|
||||
# list_indices returns indices in alphabetical order by name
|
||||
assert indices[0].index_type == "Bitmap"
|
||||
assert indices[0].columns == ["id"]
|
||||
assert indices[0].columns == ["data"]
|
||||
assert indices[1].index_type == "Bitmap"
|
||||
assert indices[1].columns == ["is_active"]
|
||||
assert indices[1].columns == ["id"]
|
||||
assert indices[2].index_type == "Bitmap"
|
||||
assert indices[2].columns == ["data"]
|
||||
assert indices[2].columns == ["is_active"]
|
||||
|
||||
index_name = indices[0].name
|
||||
stats = await some_table.index_stats(index_name)
|
||||
|
||||
@@ -40,16 +40,6 @@ def _make_table(tmp_path):
|
||||
def test_set_lsm_write_spec_validates(tmp_path):
|
||||
_db, table = _make_table(tmp_path)
|
||||
|
||||
# No PK set yet.
|
||||
with pytest.raises(Exception, match="primary key"):
|
||||
table.set_lsm_write_spec(LsmWriteSpec.bucket("id", 4))
|
||||
|
||||
table.set_unenforced_primary_key("id")
|
||||
|
||||
# Column mismatch.
|
||||
with pytest.raises(Exception, match="match"):
|
||||
table.set_lsm_write_spec(LsmWriteSpec.bucket("v", 4))
|
||||
|
||||
# Out-of-range num_buckets.
|
||||
with pytest.raises(Exception, match="num_buckets"):
|
||||
table.set_lsm_write_spec(LsmWriteSpec.bucket("id", 0))
|
||||
@@ -70,7 +60,6 @@ def test_unset_lsm_write_spec(tmp_path):
|
||||
table.unset_lsm_write_spec()
|
||||
|
||||
# Install a spec, then remove it; afterwards a fresh spec can be set.
|
||||
table.set_unenforced_primary_key("id")
|
||||
table.set_lsm_write_spec(LsmWriteSpec.bucket("id", 4))
|
||||
table.unset_lsm_write_spec()
|
||||
# A second unset errors — there is no spec left to remove.
|
||||
|
||||
196
python/python/tests/test_merge_insert_lsm.py
Normal file
196
python/python/tests/test_merge_insert_lsm.py
Normal file
@@ -0,0 +1,196 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
|
||||
"""Tests for the MemWAL LSM ``merge_insert`` dispatch."""
|
||||
|
||||
from datetime import timedelta
|
||||
|
||||
import lancedb
|
||||
import pyarrow as pa
|
||||
import pytest
|
||||
from lancedb._lancedb import LsmWriteSpec
|
||||
|
||||
SCHEMA = pa.schema(
|
||||
[
|
||||
pa.field("id", pa.int64(), nullable=False),
|
||||
pa.field("value", pa.int64(), nullable=False),
|
||||
]
|
||||
)
|
||||
|
||||
REGION_SCHEMA = pa.schema(
|
||||
[
|
||||
pa.field("id", pa.int64(), nullable=False),
|
||||
pa.field("region", pa.utf8(), nullable=False),
|
||||
]
|
||||
)
|
||||
|
||||
|
||||
def _reader(ids):
|
||||
batch = pa.RecordBatch.from_arrays(
|
||||
[
|
||||
pa.array(ids, type=pa.int64()),
|
||||
pa.array(list(range(len(ids))), type=pa.int64()),
|
||||
],
|
||||
schema=SCHEMA,
|
||||
)
|
||||
return pa.RecordBatchReader.from_batches(SCHEMA, [batch])
|
||||
|
||||
|
||||
def _region_reader(rows):
|
||||
batch = pa.RecordBatch.from_arrays(
|
||||
[
|
||||
pa.array([row[0] for row in rows], type=pa.int64()),
|
||||
pa.array([row[1] for row in rows], type=pa.utf8()),
|
||||
],
|
||||
schema=REGION_SCHEMA,
|
||||
)
|
||||
return pa.RecordBatchReader.from_batches(REGION_SCHEMA, [batch])
|
||||
|
||||
|
||||
def _bucket_table(tmp_path):
|
||||
"""A table with ``id`` as the primary key and a single-bucket LSM spec."""
|
||||
db = lancedb.connect(tmp_path, read_consistency_interval=timedelta(seconds=0))
|
||||
table = db.create_table("t", _reader([1, 2, 3]))
|
||||
table.set_unenforced_primary_key("id")
|
||||
# num_buckets = 1: every row routes to the single bucket.
|
||||
table.set_lsm_write_spec(LsmWriteSpec.bucket("id", 1))
|
||||
return table
|
||||
|
||||
|
||||
def test_lsm_merge_insert_bucket(tmp_path):
|
||||
table = _bucket_table(tmp_path)
|
||||
# Empty `on` defaults to the primary key.
|
||||
result = (
|
||||
table.merge_insert([])
|
||||
.when_matched_update_all()
|
||||
.when_not_matched_insert_all()
|
||||
.execute(_reader([3, 4, 5]))
|
||||
)
|
||||
# LSM path: rows go to the MemWAL, so only num_rows is populated.
|
||||
assert result.num_rows == 3
|
||||
assert result.version == 0
|
||||
assert result.num_inserted_rows == 0
|
||||
assert result.num_updated_rows == 0
|
||||
|
||||
|
||||
def test_lsm_merge_insert_unsharded(tmp_path):
|
||||
db = lancedb.connect(tmp_path, read_consistency_interval=timedelta(seconds=0))
|
||||
table = db.create_table("t", _reader([1, 2, 3]))
|
||||
table.set_unenforced_primary_key("id")
|
||||
table.set_lsm_write_spec(LsmWriteSpec.unsharded())
|
||||
result = (
|
||||
table.merge_insert("id")
|
||||
.when_matched_update_all()
|
||||
.when_not_matched_insert_all()
|
||||
.execute(_reader([10, 11, 12, 13]))
|
||||
)
|
||||
assert result.num_rows == 4
|
||||
|
||||
|
||||
def test_lsm_merge_insert_identity(tmp_path):
|
||||
db = lancedb.connect(tmp_path, read_consistency_interval=timedelta(seconds=0))
|
||||
table = db.create_table("t", _region_reader([(1, "us"), (2, "us")]))
|
||||
table.set_unenforced_primary_key("id")
|
||||
table.set_lsm_write_spec(LsmWriteSpec.identity("region"))
|
||||
# All rows share one identity value, so they route to one shard.
|
||||
result = (
|
||||
table.merge_insert([])
|
||||
.when_matched_update_all()
|
||||
.when_not_matched_insert_all()
|
||||
.execute(_region_reader([(3, "us"), (4, "us")]))
|
||||
)
|
||||
assert result.num_rows == 2
|
||||
|
||||
|
||||
def test_lsm_merge_insert_use_lsm_write_false(tmp_path):
|
||||
table = _bucket_table(tmp_path) # rows id = 1, 2, 3
|
||||
# use_lsm_write(False) opts out: the standard path runs and commits.
|
||||
result = (
|
||||
table.merge_insert("id")
|
||||
.when_not_matched_insert_all()
|
||||
.use_lsm_write(False)
|
||||
.execute(_reader([3, 4, 5]))
|
||||
)
|
||||
assert result.num_inserted_rows == 2
|
||||
assert table.count_rows() == 5
|
||||
|
||||
|
||||
def test_lsm_merge_insert_validate_single_shard_off(tmp_path):
|
||||
table = _bucket_table(tmp_path)
|
||||
result = (
|
||||
table.merge_insert([])
|
||||
.when_matched_update_all()
|
||||
.when_not_matched_insert_all()
|
||||
.validate_single_shard(False)
|
||||
.execute(_reader([6, 7, 8]))
|
||||
)
|
||||
assert result.num_rows == 3
|
||||
|
||||
|
||||
def test_lsm_merge_insert_use_lsm_write_true_requires_spec(tmp_path):
|
||||
# A table with a primary key but no LSM write spec installed.
|
||||
db = lancedb.connect(tmp_path, read_consistency_interval=timedelta(seconds=0))
|
||||
table = db.create_table("t", _reader([1, 2, 3]))
|
||||
table.set_unenforced_primary_key("id")
|
||||
with pytest.raises(Exception, match="use_lsm_write"):
|
||||
(
|
||||
table.merge_insert("id")
|
||||
.when_matched_update_all()
|
||||
.when_not_matched_insert_all()
|
||||
.use_lsm_write(True)
|
||||
.execute(_reader([4]))
|
||||
)
|
||||
|
||||
|
||||
def test_lsm_merge_insert_rejects_on_not_primary_key(tmp_path):
|
||||
table = _bucket_table(tmp_path)
|
||||
with pytest.raises(Exception, match="primary key"):
|
||||
(
|
||||
table.merge_insert("value")
|
||||
.when_matched_update_all()
|
||||
.when_not_matched_insert_all()
|
||||
.execute(_reader([1]))
|
||||
)
|
||||
|
||||
|
||||
def test_lsm_merge_insert_rejects_non_upsert(tmp_path):
|
||||
table = _bucket_table(tmp_path)
|
||||
# Insert-only (no when_matched_update_all) is not the upsert shape.
|
||||
with pytest.raises(Exception, match="upsert"):
|
||||
table.merge_insert([]).when_not_matched_insert_all().execute(_reader([4]))
|
||||
|
||||
|
||||
def test_lsm_close_writers(tmp_path):
|
||||
table = _bucket_table(tmp_path)
|
||||
(
|
||||
table.merge_insert([])
|
||||
.when_matched_update_all()
|
||||
.when_not_matched_insert_all()
|
||||
.execute(_reader([7, 8]))
|
||||
)
|
||||
table.close_lsm_writers()
|
||||
# The writer reopens lazily on the next merge_insert.
|
||||
result = (
|
||||
table.merge_insert([])
|
||||
.when_matched_update_all()
|
||||
.when_not_matched_insert_all()
|
||||
.execute(_reader([9]))
|
||||
)
|
||||
assert result.num_rows == 1
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_async_lsm_merge_insert(tmp_path):
|
||||
db = await lancedb.connect_async(
|
||||
tmp_path, read_consistency_interval=timedelta(seconds=0)
|
||||
)
|
||||
table = await db.create_table("t", _reader([1, 2, 3]))
|
||||
await table.set_unenforced_primary_key("id")
|
||||
await table.set_lsm_write_spec(LsmWriteSpec.bucket("id", 1))
|
||||
|
||||
builder = (
|
||||
table.merge_insert([]).when_matched_update_all().when_not_matched_insert_all()
|
||||
)
|
||||
result = await builder.execute(_reader([3, 4, 5]))
|
||||
assert result.num_rows == 3
|
||||
await table.close_lsm_writers()
|
||||
@@ -436,22 +436,25 @@ def test_table_create_indices():
|
||||
# This is a smoke-test.
|
||||
table = db.create_table("test", [{"id": 1}])
|
||||
|
||||
# Test create_scalar_index with custom name
|
||||
table.create_scalar_index(
|
||||
"id", wait_timeout=timedelta(seconds=2), name="custom_scalar_idx"
|
||||
)
|
||||
# Test create_scalar_index with custom name (legacy method)
|
||||
with pytest.warns(DeprecationWarning, match="create_scalar_index"):
|
||||
table.create_scalar_index(
|
||||
"id", wait_timeout=timedelta(seconds=2), name="custom_scalar_idx"
|
||||
)
|
||||
|
||||
# Test create_fts_index with custom name
|
||||
table.create_fts_index(
|
||||
"text", wait_timeout=timedelta(seconds=2), name="custom_fts_idx"
|
||||
)
|
||||
# Test create_fts_index with custom name (legacy method)
|
||||
with pytest.warns(DeprecationWarning, match="create_fts_index"):
|
||||
table.create_fts_index(
|
||||
"text", wait_timeout=timedelta(seconds=2), name="custom_fts_idx"
|
||||
)
|
||||
|
||||
# Test create_index with custom name
|
||||
table.create_index(
|
||||
vector_column_name="vector",
|
||||
wait_timeout=timedelta(seconds=10),
|
||||
name="custom_vector_idx",
|
||||
)
|
||||
# Test create_index with custom name (legacy form: vector_column_name kwarg)
|
||||
with pytest.warns(DeprecationWarning, match="create_index"):
|
||||
table.create_index(
|
||||
vector_column_name="vector",
|
||||
wait_timeout=timedelta(seconds=10),
|
||||
name="custom_vector_idx",
|
||||
)
|
||||
|
||||
# Validate that the name parameter was passed correctly in requests
|
||||
assert len(received_requests) == 3
|
||||
@@ -480,6 +483,98 @@ def test_table_create_indices():
|
||||
table.drop_index("custom_fts_idx")
|
||||
|
||||
|
||||
def test_remote_create_index_new_api():
|
||||
received_requests = []
|
||||
|
||||
def handler(request):
|
||||
if request.path == "/v1/table/test/create_index/":
|
||||
content_len = int(request.headers.get("Content-Length", 0))
|
||||
body = request.rfile.read(content_len) if content_len > 0 else b""
|
||||
received_requests.append(json.loads(body) if body else {})
|
||||
request.send_response(200)
|
||||
request.end_headers()
|
||||
elif request.path == "/v1/table/test/create/?mode=create":
|
||||
request.send_response(200)
|
||||
request.send_header("Content-Type", "application/json")
|
||||
request.end_headers()
|
||||
request.wfile.write(b"{}")
|
||||
elif request.path == "/v1/table/test/describe/":
|
||||
request.send_response(200)
|
||||
request.send_header("Content-Type", "application/json")
|
||||
request.end_headers()
|
||||
request.wfile.write(
|
||||
json.dumps(
|
||||
dict(
|
||||
version=1,
|
||||
schema=dict(
|
||||
fields=[
|
||||
dict(name="id", type={"type": "int64"}, nullable=False),
|
||||
dict(
|
||||
name="category",
|
||||
type={"type": "string"},
|
||||
nullable=False,
|
||||
),
|
||||
dict(
|
||||
name="text", type={"type": "string"}, nullable=False
|
||||
),
|
||||
dict(
|
||||
name="vector",
|
||||
type={
|
||||
"type": "fixed_size_list",
|
||||
"fields": [
|
||||
dict(
|
||||
name="item",
|
||||
type={"type": "float"},
|
||||
nullable=True,
|
||||
)
|
||||
],
|
||||
"length": 2,
|
||||
},
|
||||
nullable=False,
|
||||
),
|
||||
]
|
||||
),
|
||||
)
|
||||
).encode()
|
||||
)
|
||||
else:
|
||||
request.send_response(404)
|
||||
request.end_headers()
|
||||
|
||||
from lancedb.index import BTree, FTS, IvfPq, IvfRq
|
||||
|
||||
with mock_lancedb_connection(handler) as db:
|
||||
table = db.create_table("test", [{"id": 1}])
|
||||
|
||||
# New API: column-first, config= kwarg. Should NOT emit DeprecationWarning.
|
||||
import warnings as _warnings
|
||||
|
||||
with _warnings.catch_warnings():
|
||||
_warnings.simplefilter("error", DeprecationWarning)
|
||||
table.create_index("vector", config=IvfPq(distance_type="l2"))
|
||||
table.create_index("category", config=BTree())
|
||||
table.create_index("text", config=FTS())
|
||||
# IvfRq via new API
|
||||
table.create_index("vector", config=IvfRq(distance_type="l2"))
|
||||
|
||||
# Legacy index_type="IVF_RQ" routes to IvfRq config under the hood.
|
||||
with pytest.warns(DeprecationWarning, match="create_index"):
|
||||
table.create_index(
|
||||
vector_column_name="vector",
|
||||
index_type="IVF_RQ",
|
||||
num_partitions=8,
|
||||
)
|
||||
|
||||
assert len(received_requests) == 5
|
||||
assert [req["column"] for req in received_requests] == [
|
||||
"vector",
|
||||
"category",
|
||||
"text",
|
||||
"vector",
|
||||
"vector",
|
||||
]
|
||||
|
||||
|
||||
def test_table_wait_for_index_timeout():
|
||||
def handler(request):
|
||||
index_stats = dict(
|
||||
|
||||
@@ -603,3 +603,89 @@ def test_cross_encoder_reranker_return_all(tmp_path):
|
||||
assert "_relevance_score" in result.column_names
|
||||
assert "_score" in result.column_names
|
||||
assert "_distance" in result.column_names
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Regression tests for LinearCombinationReranker scoring bugs (issue #3154)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def test_linear_combination_best_match_ranks_first():
|
||||
"""
|
||||
The document that is BOTH the closest vector match AND the only FTS match
|
||||
must rank first. Previously _combine_score subtracted from 1, inverting
|
||||
the ranking so the worst document ranked highest.
|
||||
"""
|
||||
reranker = LinearCombinationReranker(weight=0.7, return_score="all")
|
||||
|
||||
# rowid 0: perfect vector match, sole FTS match → should rank 1st
|
||||
# rowid 1: mediocre vector, no FTS match
|
||||
# rowid 2: bad vector, no FTS match
|
||||
vector_results = pa.Table.from_pydict(
|
||||
{
|
||||
"_rowid": [0, 1, 2],
|
||||
"_distance": [0.0, 0.5, 0.9],
|
||||
}
|
||||
)
|
||||
fts_results = pa.Table.from_pydict(
|
||||
{
|
||||
"_rowid": [0],
|
||||
"_score": [1.0],
|
||||
}
|
||||
)
|
||||
|
||||
combined = reranker.merge_results(vector_results, fts_results, fill=1.0)
|
||||
scores = dict(
|
||||
zip(
|
||||
combined["_rowid"].to_pylist(),
|
||||
combined["_relevance_score"].to_pylist(),
|
||||
)
|
||||
)
|
||||
|
||||
# rowid 0 must have the highest relevance score
|
||||
assert scores[0] > scores[1], (
|
||||
f"Best match (rowid 0, score={scores[0]:.4f}) should beat "
|
||||
f"mid match (rowid 1, score={scores[1]:.4f})"
|
||||
)
|
||||
assert scores[1] > scores[2], (
|
||||
f"Mid match (rowid 1, score={scores[1]:.4f}) should beat "
|
||||
f"bad match (rowid 2, score={scores[2]:.4f})"
|
||||
)
|
||||
|
||||
|
||||
def test_linear_combination_missing_fts_is_penalised():
|
||||
"""
|
||||
A document with no FTS match must score *lower* than a document that
|
||||
has a mediocre FTS match, everything else being equal. Previously
|
||||
missing-FTS entries used fill=1.0 directly, which gave them a reward
|
||||
(via the 1-(...) inversion) instead of a penalty.
|
||||
"""
|
||||
reranker = LinearCombinationReranker(weight=0.5, return_score="all")
|
||||
|
||||
vector_results = pa.Table.from_pydict(
|
||||
{
|
||||
"_rowid": [0, 1],
|
||||
"_distance": [0.2, 0.2], # identical vector scores
|
||||
}
|
||||
)
|
||||
fts_results = pa.Table.from_pydict(
|
||||
{
|
||||
"_rowid": [0], # rowid 1 has no FTS match
|
||||
"_score": [0.3], # small FTS score
|
||||
}
|
||||
)
|
||||
|
||||
combined = reranker.merge_results(vector_results, fts_results, fill=1.0)
|
||||
scores = dict(
|
||||
zip(
|
||||
combined["_rowid"].to_pylist(),
|
||||
combined["_relevance_score"].to_pylist(),
|
||||
)
|
||||
)
|
||||
|
||||
# rowid 0 has a small FTS score; rowid 1 has none.
|
||||
# Even a small FTS contribution should beat having none at all.
|
||||
assert scores[0] > scores[1], (
|
||||
f"Document with FTS score (rowid 0, {scores[0]:.4f}) should beat "
|
||||
f"document with no FTS match (rowid 1, {scores[1]:.4f})"
|
||||
)
|
||||
|
||||
@@ -4,6 +4,7 @@
|
||||
|
||||
import os
|
||||
import sys
|
||||
import warnings
|
||||
from datetime import date, datetime, timedelta
|
||||
from time import sleep
|
||||
from typing import List
|
||||
@@ -11,7 +12,7 @@ from unittest.mock import patch
|
||||
|
||||
import lancedb
|
||||
from lancedb.dependencies import _PANDAS_AVAILABLE
|
||||
from lancedb.index import HnswFlat, HnswPq, HnswSq, IvfPq
|
||||
from lancedb.index import BTree, FTS, HnswFlat, HnswPq, HnswSq, IvfPq
|
||||
import numpy as np
|
||||
import polars as pl
|
||||
import pyarrow as pa
|
||||
@@ -928,7 +929,12 @@ def test_create_index_method(mock_create_index, mem_db: DBConnection):
|
||||
num_bits=4,
|
||||
)
|
||||
mock_create_index.assert_called_with(
|
||||
"vector", replace=True, config=expected_config, name=None, train=True
|
||||
"vector",
|
||||
replace=True,
|
||||
config=expected_config,
|
||||
wait_timeout=None,
|
||||
name=None,
|
||||
train=True,
|
||||
)
|
||||
|
||||
# Test with target_partition_size
|
||||
@@ -948,7 +954,12 @@ def test_create_index_method(mock_create_index, mem_db: DBConnection):
|
||||
target_partition_size=8192,
|
||||
)
|
||||
mock_create_index.assert_called_with(
|
||||
"vector", replace=True, config=expected_config, name=None, train=True
|
||||
"vector",
|
||||
replace=True,
|
||||
config=expected_config,
|
||||
wait_timeout=None,
|
||||
name=None,
|
||||
train=True,
|
||||
)
|
||||
|
||||
# target_partition_size has a default value,
|
||||
@@ -967,7 +978,12 @@ def test_create_index_method(mock_create_index, mem_db: DBConnection):
|
||||
num_bits=4,
|
||||
)
|
||||
mock_create_index.assert_called_with(
|
||||
"vector", replace=True, config=expected_config, name=None, train=True
|
||||
"vector",
|
||||
replace=True,
|
||||
config=expected_config,
|
||||
wait_timeout=None,
|
||||
name=None,
|
||||
train=True,
|
||||
)
|
||||
|
||||
table.create_index(
|
||||
@@ -978,7 +994,12 @@ def test_create_index_method(mock_create_index, mem_db: DBConnection):
|
||||
)
|
||||
expected_config = HnswPq(distance_type="dot")
|
||||
mock_create_index.assert_called_with(
|
||||
"my_vector", replace=False, config=expected_config, name=None, train=True
|
||||
"my_vector",
|
||||
replace=False,
|
||||
config=expected_config,
|
||||
wait_timeout=None,
|
||||
name=None,
|
||||
train=True,
|
||||
)
|
||||
|
||||
table.create_index(
|
||||
@@ -993,7 +1014,12 @@ def test_create_index_method(mock_create_index, mem_db: DBConnection):
|
||||
distance_type="cosine", sample_rate=0.1, m=29, ef_construction=10
|
||||
)
|
||||
mock_create_index.assert_called_with(
|
||||
"my_vector", replace=True, config=expected_config, name=None, train=True
|
||||
"my_vector",
|
||||
replace=True,
|
||||
config=expected_config,
|
||||
wait_timeout=None,
|
||||
name=None,
|
||||
train=True,
|
||||
)
|
||||
|
||||
table.create_index(
|
||||
@@ -1008,7 +1034,12 @@ def test_create_index_method(mock_create_index, mem_db: DBConnection):
|
||||
distance_type="cosine", sample_rate=0.1, m=29, ef_construction=10
|
||||
)
|
||||
mock_create_index.assert_called_with(
|
||||
"my_vector", replace=True, config=expected_config, name=None, train=True
|
||||
"my_vector",
|
||||
replace=True,
|
||||
config=expected_config,
|
||||
wait_timeout=None,
|
||||
name=None,
|
||||
train=True,
|
||||
)
|
||||
|
||||
|
||||
@@ -1032,6 +1063,7 @@ def test_create_index_name_and_train_parameters(
|
||||
"vector",
|
||||
replace=True,
|
||||
config=expected_config,
|
||||
wait_timeout=None,
|
||||
name="my_custom_index",
|
||||
train=True,
|
||||
)
|
||||
@@ -1039,13 +1071,82 @@ def test_create_index_name_and_train_parameters(
|
||||
# Test with train=False
|
||||
table.create_index(vector_column_name="vector", train=False)
|
||||
mock_create_index.assert_called_with(
|
||||
"vector", replace=True, config=expected_config, name=None, train=False
|
||||
"vector",
|
||||
replace=True,
|
||||
config=expected_config,
|
||||
wait_timeout=None,
|
||||
name=None,
|
||||
train=False,
|
||||
)
|
||||
|
||||
# Test with both name and train
|
||||
table.create_index(vector_column_name="vector", name="my_index_name", train=True)
|
||||
mock_create_index.assert_called_with(
|
||||
"vector", replace=True, config=expected_config, name="my_index_name", train=True
|
||||
"vector",
|
||||
replace=True,
|
||||
config=expected_config,
|
||||
wait_timeout=None,
|
||||
name="my_index_name",
|
||||
train=True,
|
||||
)
|
||||
|
||||
|
||||
@patch("lancedb.table.AsyncTable.create_index")
|
||||
def test_create_index_legacy_emits_deprecation_warning(
|
||||
mock_create_index, mem_db: DBConnection
|
||||
):
|
||||
table = mem_db.create_table(
|
||||
"test",
|
||||
data=[{"vector": [3.1, 4.1]}, {"vector": [5.9, 26.5]}],
|
||||
)
|
||||
|
||||
with pytest.warns(DeprecationWarning, match="create_index"):
|
||||
table.create_index(metric="l2", num_partitions=8, vector_column_name="vector")
|
||||
|
||||
|
||||
@patch("lancedb.table.AsyncTable.create_index")
|
||||
def test_create_index_new_api(mock_create_index, mem_db: DBConnection):
|
||||
table = mem_db.create_table(
|
||||
"test",
|
||||
data=[
|
||||
{"vector": [3.1, 4.1], "category": "a", "text": "hello world"},
|
||||
{"vector": [5.9, 26.5], "category": "b", "text": "goodbye"},
|
||||
],
|
||||
)
|
||||
|
||||
# Vector index via new API should not warn
|
||||
with warnings.catch_warnings():
|
||||
warnings.simplefilter("error", DeprecationWarning)
|
||||
table.create_index("vector", config=IvfPq(distance_type="l2"))
|
||||
mock_create_index.assert_called_with(
|
||||
"vector",
|
||||
replace=True,
|
||||
config=IvfPq(distance_type="l2"),
|
||||
wait_timeout=None,
|
||||
name=None,
|
||||
train=True,
|
||||
)
|
||||
|
||||
# Scalar index via new API
|
||||
table.create_index("category", config=BTree())
|
||||
mock_create_index.assert_called_with(
|
||||
"category",
|
||||
replace=True,
|
||||
config=BTree(),
|
||||
wait_timeout=None,
|
||||
name=None,
|
||||
train=True,
|
||||
)
|
||||
|
||||
# FTS index via new API
|
||||
table.create_index("text", config=FTS(with_position=True))
|
||||
mock_create_index.assert_called_with(
|
||||
"text",
|
||||
replace=True,
|
||||
config=FTS(with_position=True),
|
||||
wait_timeout=None,
|
||||
name=None,
|
||||
train=True,
|
||||
)
|
||||
|
||||
|
||||
@@ -1861,8 +1962,9 @@ def test_create_scalar_index(mem_db: DBConnection):
|
||||
"my_table",
|
||||
data=test_data,
|
||||
)
|
||||
# Test with default name
|
||||
table.create_scalar_index("x")
|
||||
# Test with default name; confirm DeprecationWarning fires
|
||||
with pytest.warns(DeprecationWarning, match="create_scalar_index"):
|
||||
table.create_scalar_index("x")
|
||||
indices = table.list_indices()
|
||||
assert len(indices) == 1
|
||||
scalar_index = indices[0]
|
||||
|
||||
@@ -143,18 +143,20 @@ pub struct MergeResult {
|
||||
pub num_inserted_rows: u64,
|
||||
pub num_deleted_rows: u64,
|
||||
pub num_attempts: u32,
|
||||
pub num_rows: u64,
|
||||
}
|
||||
|
||||
#[pymethods]
|
||||
impl MergeResult {
|
||||
pub fn __repr__(&self) -> String {
|
||||
format!(
|
||||
"MergeResult(version={}, num_updated_rows={}, num_inserted_rows={}, num_deleted_rows={}, num_attempts={})",
|
||||
"MergeResult(version={}, num_updated_rows={}, num_inserted_rows={}, num_deleted_rows={}, num_attempts={}, num_rows={})",
|
||||
self.version,
|
||||
self.num_updated_rows,
|
||||
self.num_inserted_rows,
|
||||
self.num_deleted_rows,
|
||||
self.num_attempts
|
||||
self.num_attempts,
|
||||
self.num_rows
|
||||
)
|
||||
}
|
||||
}
|
||||
@@ -167,6 +169,7 @@ impl From<lancedb::table::MergeResult> for MergeResult {
|
||||
num_inserted_rows: result.num_inserted_rows,
|
||||
num_deleted_rows: result.num_deleted_rows,
|
||||
num_attempts: result.num_attempts,
|
||||
num_rows: result.num_rows,
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -194,6 +197,12 @@ impl LsmWriteSpec {
|
||||
}
|
||||
|
||||
/// Identity sharding — shard by the raw value of `column`.
|
||||
///
|
||||
/// `column` must be a deterministic function of the unenforced primary
|
||||
/// key: every row with a given primary key must always produce the same
|
||||
/// `column` value, or upserts of that key can land in different shards
|
||||
/// and a stale version can win. Typically `column` is the primary key
|
||||
/// itself or a stable attribute of it.
|
||||
#[staticmethod]
|
||||
pub fn identity(column: String) -> Self {
|
||||
Self {
|
||||
@@ -933,6 +942,12 @@ impl Table {
|
||||
if let Some(use_index) = parameters.use_index {
|
||||
builder.use_index(use_index);
|
||||
}
|
||||
if let Some(use_lsm_write) = parameters.use_lsm_write {
|
||||
builder.use_lsm_write(use_lsm_write);
|
||||
}
|
||||
if let Some(validate_single_shard) = parameters.validate_single_shard {
|
||||
builder.validate_single_shard(validate_single_shard);
|
||||
}
|
||||
|
||||
future_into_py(self_.py(), async move {
|
||||
let res = builder.execute(Box::new(batches)).await.infer_error()?;
|
||||
@@ -971,6 +986,13 @@ impl Table {
|
||||
})
|
||||
}
|
||||
|
||||
pub fn close_lsm_writers(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
|
||||
let inner = self_.inner_ref()?.clone();
|
||||
future_into_py(self_.py(), async move {
|
||||
inner.close_lsm_writers().await.infer_error()
|
||||
})
|
||||
}
|
||||
|
||||
pub fn uses_v2_manifest_paths(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
|
||||
let inner = self_.inner_ref()?.clone();
|
||||
future_into_py(self_.py(), async move {
|
||||
@@ -1124,6 +1146,8 @@ pub struct MergeInsertParams {
|
||||
when_not_matched_by_source_condition: Option<String>,
|
||||
timeout: Option<std::time::Duration>,
|
||||
use_index: Option<bool>,
|
||||
use_lsm_write: Option<bool>,
|
||||
validate_single_shard: Option<bool>,
|
||||
}
|
||||
|
||||
#[pyclass]
|
||||
|
||||
455
python/uv.lock
generated
455
python/uv.lock
generated
@@ -690,62 +690,62 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "cryptography"
|
||||
version = "46.0.4"
|
||||
version = "46.0.7"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "cffi", marker = "platform_python_implementation != 'PyPy'" },
|
||||
{ name = "typing-extensions", marker = "python_full_version < '3.11'" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/78/19/f748958276519adf6a0c1e79e7b8860b4830dda55ccdf29f2719b5fc499c/cryptography-46.0.4.tar.gz", hash = "sha256:bfd019f60f8abc2ed1b9be4ddc21cfef059c841d86d710bb69909a688cbb8f59", size = 749301, upload-time = "2026-01-28T00:24:37.379Z" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/47/93/ac8f3d5ff04d54bc814e961a43ae5b0b146154c89c61b47bb07557679b18/cryptography-46.0.7.tar.gz", hash = "sha256:e4cfd68c5f3e0bfdad0d38e023239b96a2fe84146481852dffbcca442c245aa5", size = 750652, upload-time = "2026-04-08T01:57:54.692Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/8d/99/157aae7949a5f30d51fcb1a9851e8ebd5c74bf99b5285d8bb4b8b9ee641e/cryptography-46.0.4-cp311-abi3-macosx_10_9_universal2.whl", hash = "sha256:281526e865ed4166009e235afadf3a4c4cba6056f99336a99efba65336fd5485", size = 7173686, upload-time = "2026-01-28T00:23:07.515Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/87/91/874b8910903159043b5c6a123b7e79c4559ddd1896e38967567942635778/cryptography-46.0.4-cp311-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:5f14fba5bf6f4390d7ff8f086c566454bff0411f6d8aa7af79c88b6f9267aecc", size = 4275871, upload-time = "2026-01-28T00:23:09.439Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c0/35/690e809be77896111f5b195ede56e4b4ed0435b428c2f2b6d35046fbb5e8/cryptography-46.0.4-cp311-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:47bcd19517e6389132f76e2d5303ded6cf3f78903da2158a671be8de024f4cd0", size = 4423124, upload-time = "2026-01-28T00:23:11.529Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/1a/5b/a26407d4f79d61ca4bebaa9213feafdd8806dc69d3d290ce24996d3cfe43/cryptography-46.0.4-cp311-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:01df4f50f314fbe7009f54046e908d1754f19d0c6d3070df1e6268c5a4af09fa", size = 4277090, upload-time = "2026-01-28T00:23:13.123Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/0c/d8/4bb7aec442a9049827aa34cee1aa83803e528fa55da9a9d45d01d1bb933e/cryptography-46.0.4-cp311-abi3-manylinux_2_28_ppc64le.whl", hash = "sha256:5aa3e463596b0087b3da0dbe2b2487e9fc261d25da85754e30e3b40637d61f81", size = 4947652, upload-time = "2026-01-28T00:23:14.554Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/2b/08/f83e2e0814248b844265802d081f2fac2f1cbe6cd258e72ba14ff006823a/cryptography-46.0.4-cp311-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:0a9ad24359fee86f131836a9ac3bffc9329e956624a2d379b613f8f8abaf5255", size = 4455157, upload-time = "2026-01-28T00:23:16.443Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/0a/05/19d849cf4096448779d2dcc9bb27d097457dac36f7273ffa875a93b5884c/cryptography-46.0.4-cp311-abi3-manylinux_2_31_armv7l.whl", hash = "sha256:dc1272e25ef673efe72f2096e92ae39dea1a1a450dd44918b15351f72c5a168e", size = 3981078, upload-time = "2026-01-28T00:23:17.838Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/e6/89/f7bac81d66ba7cde867a743ea5b37537b32b5c633c473002b26a226f703f/cryptography-46.0.4-cp311-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:de0f5f4ec8711ebc555f54735d4c673fc34b65c44283895f1a08c2b49d2fd99c", size = 4276213, upload-time = "2026-01-28T00:23:19.257Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/da/9f/7133e41f24edd827020ad21b068736e792bc68eecf66d93c924ad4719fb3/cryptography-46.0.4-cp311-abi3-manylinux_2_34_ppc64le.whl", hash = "sha256:eeeb2e33d8dbcccc34d64651f00a98cb41b2dc69cef866771a5717e6734dfa32", size = 4912190, upload-time = "2026-01-28T00:23:21.244Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/a6/f7/6d43cbaddf6f65b24816e4af187d211f0bc536a29961f69faedc48501d8e/cryptography-46.0.4-cp311-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:3d425eacbc9aceafd2cb429e42f4e5d5633c6f873f5e567077043ef1b9bbf616", size = 4454641, upload-time = "2026-01-28T00:23:22.866Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/9e/4f/ebd0473ad656a0ac912a16bd07db0f5d85184924e14fc88feecae2492834/cryptography-46.0.4-cp311-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:91627ebf691d1ea3976a031b61fb7bac1ccd745afa03602275dda443e11c8de0", size = 4405159, upload-time = "2026-01-28T00:23:25.278Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/d1/f7/7923886f32dc47e27adeff8246e976d77258fd2aa3efdd1754e4e323bf49/cryptography-46.0.4-cp311-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:2d08bc22efd73e8854b0b7caff402d735b354862f1145d7be3b9c0f740fef6a0", size = 4666059, upload-time = "2026-01-28T00:23:26.766Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/eb/a7/0fca0fd3591dffc297278a61813d7f661a14243dd60f499a7a5b48acb52a/cryptography-46.0.4-cp311-abi3-win32.whl", hash = "sha256:82a62483daf20b8134f6e92898da70d04d0ef9a75829d732ea1018678185f4f5", size = 3026378, upload-time = "2026-01-28T00:23:28.317Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/2d/12/652c84b6f9873f0909374864a57b003686c642ea48c84d6c7e2c515e6da5/cryptography-46.0.4-cp311-abi3-win_amd64.whl", hash = "sha256:6225d3ebe26a55dbc8ead5ad1265c0403552a63336499564675b29eb3184c09b", size = 3478614, upload-time = "2026-01-28T00:23:30.275Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/b9/27/542b029f293a5cce59349d799d4d8484b3b1654a7b9a0585c266e974a488/cryptography-46.0.4-cp314-cp314t-macosx_10_9_universal2.whl", hash = "sha256:485e2b65d25ec0d901bca7bcae0f53b00133bf3173916d8e421f6fddde103908", size = 7116417, upload-time = "2026-01-28T00:23:31.958Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/f8/f5/559c25b77f40b6bf828eabaf988efb8b0e17b573545edb503368ca0a2a03/cryptography-46.0.4-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:078e5f06bd2fa5aea5a324f2a09f914b1484f1d0c2a4d6a8a28c74e72f65f2da", size = 4264508, upload-time = "2026-01-28T00:23:34.264Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/49/a1/551fa162d33074b660dc35c9bc3616fefa21a0e8c1edd27b92559902e408/cryptography-46.0.4-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:dce1e4f068f03008da7fa51cc7abc6ddc5e5de3e3d1550334eaf8393982a5829", size = 4409080, upload-time = "2026-01-28T00:23:35.793Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/b0/6a/4d8d129a755f5d6df1bbee69ea2f35ebfa954fa1847690d1db2e8bca46a5/cryptography-46.0.4-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:2067461c80271f422ee7bdbe79b9b4be54a5162e90345f86a23445a0cf3fd8a2", size = 4270039, upload-time = "2026-01-28T00:23:37.263Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/4c/f5/ed3fcddd0a5e39321e595e144615399e47e7c153a1fb8c4862aec3151ff9/cryptography-46.0.4-cp314-cp314t-manylinux_2_28_ppc64le.whl", hash = "sha256:c92010b58a51196a5f41c3795190203ac52edfd5dc3ff99149b4659eba9d2085", size = 4926748, upload-time = "2026-01-28T00:23:38.884Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/43/ae/9f03d5f0c0c00e85ecb34f06d3b79599f20630e4db91b8a6e56e8f83d410/cryptography-46.0.4-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:829c2b12bbc5428ab02d6b7f7e9bbfd53e33efd6672d21341f2177470171ad8b", size = 4442307, upload-time = "2026-01-28T00:23:40.56Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/8b/22/e0f9f2dae8040695103369cf2283ef9ac8abe4d51f68710bec2afd232609/cryptography-46.0.4-cp314-cp314t-manylinux_2_31_armv7l.whl", hash = "sha256:62217ba44bf81b30abaeda1488686a04a702a261e26f87db51ff61d9d3510abd", size = 3959253, upload-time = "2026-01-28T00:23:42.827Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/01/5b/6a43fcccc51dae4d101ac7d378a8724d1ba3de628a24e11bf2f4f43cba4d/cryptography-46.0.4-cp314-cp314t-manylinux_2_34_aarch64.whl", hash = "sha256:9c2da296c8d3415b93e6053f5a728649a87a48ce084a9aaf51d6e46c87c7f2d2", size = 4269372, upload-time = "2026-01-28T00:23:44.655Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/17/b7/0f6b8c1dd0779df2b526e78978ff00462355e31c0a6f6cff8a3e99889c90/cryptography-46.0.4-cp314-cp314t-manylinux_2_34_ppc64le.whl", hash = "sha256:9b34d8ba84454641a6bf4d6762d15847ecbd85c1316c0a7984e6e4e9f748ec2e", size = 4891908, upload-time = "2026-01-28T00:23:46.48Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/83/17/259409b8349aa10535358807a472c6a695cf84f106022268d31cea2b6c97/cryptography-46.0.4-cp314-cp314t-manylinux_2_34_x86_64.whl", hash = "sha256:df4a817fa7138dd0c96c8c8c20f04b8aaa1fac3bbf610913dcad8ea82e1bfd3f", size = 4441254, upload-time = "2026-01-28T00:23:48.403Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/9c/fe/e4a1b0c989b00cee5ffa0764401767e2d1cf59f45530963b894129fd5dce/cryptography-46.0.4-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:b1de0ebf7587f28f9190b9cb526e901bf448c9e6a99655d2b07fff60e8212a82", size = 4396520, upload-time = "2026-01-28T00:23:50.26Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/b3/81/ba8fd9657d27076eb40d6a2f941b23429a3c3d2f56f5a921d6b936a27bc9/cryptography-46.0.4-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:9b4d17bc7bd7cdd98e3af40b441feaea4c68225e2eb2341026c84511ad246c0c", size = 4651479, upload-time = "2026-01-28T00:23:51.674Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/00/03/0de4ed43c71c31e4fe954edd50b9d28d658fef56555eba7641696370a8e2/cryptography-46.0.4-cp314-cp314t-win32.whl", hash = "sha256:c411f16275b0dea722d76544a61d6421e2cc829ad76eec79280dbdc9ddf50061", size = 3001986, upload-time = "2026-01-28T00:23:53.485Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/5c/70/81830b59df7682917d7a10f833c4dab2a5574cd664e86d18139f2b421329/cryptography-46.0.4-cp314-cp314t-win_amd64.whl", hash = "sha256:728fedc529efc1439eb6107b677f7f7558adab4553ef8669f0d02d42d7b959a7", size = 3468288, upload-time = "2026-01-28T00:23:55.09Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/56/f7/f648fdbb61d0d45902d3f374217451385edc7e7768d1b03ff1d0e5ffc17b/cryptography-46.0.4-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:a9556ba711f7c23f77b151d5798f3ac44a13455cc68db7697a1096e6d0563cab", size = 7169583, upload-time = "2026-01-28T00:23:56.558Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/d8/cc/8f3224cbb2a928de7298d6ed4790f5ebc48114e02bdc9559196bfb12435d/cryptography-46.0.4-cp38-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:8bf75b0259e87fa70bddc0b8b4078b76e7fd512fd9afae6c1193bcf440a4dbef", size = 4275419, upload-time = "2026-01-28T00:23:58.364Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/17/43/4a18faa7a872d00e4264855134ba82d23546c850a70ff209e04ee200e76f/cryptography-46.0.4-cp38-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:3c268a3490df22270955966ba236d6bc4a8f9b6e4ffddb78aac535f1a5ea471d", size = 4419058, upload-time = "2026-01-28T00:23:59.867Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ee/64/6651969409821d791ba12346a124f55e1b76f66a819254ae840a965d4b9c/cryptography-46.0.4-cp38-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:812815182f6a0c1d49a37893a303b44eaac827d7f0d582cecfc81b6427f22973", size = 4278151, upload-time = "2026-01-28T00:24:01.731Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/20/0b/a7fce65ee08c3c02f7a8310cc090a732344066b990ac63a9dfd0a655d321/cryptography-46.0.4-cp38-abi3-manylinux_2_28_ppc64le.whl", hash = "sha256:a90e43e3ef65e6dcf969dfe3bb40cbf5aef0d523dff95bfa24256be172a845f4", size = 4939441, upload-time = "2026-01-28T00:24:03.175Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/db/a7/20c5701e2cd3e1dfd7a19d2290c522a5f435dd30957d431dcb531d0f1413/cryptography-46.0.4-cp38-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:a05177ff6296644ef2876fce50518dffb5bcdf903c85250974fc8bc85d54c0af", size = 4451617, upload-time = "2026-01-28T00:24:05.403Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/00/dc/3e16030ea9aa47b63af6524c354933b4fb0e352257c792c4deeb0edae367/cryptography-46.0.4-cp38-abi3-manylinux_2_31_armv7l.whl", hash = "sha256:daa392191f626d50f1b136c9b4cf08af69ca8279d110ea24f5c2700054d2e263", size = 3977774, upload-time = "2026-01-28T00:24:06.851Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/42/c8/ad93f14118252717b465880368721c963975ac4b941b7ef88f3c56bf2897/cryptography-46.0.4-cp38-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:e07ea39c5b048e085f15923511d8121e4a9dc45cee4e3b970ca4f0d338f23095", size = 4277008, upload-time = "2026-01-28T00:24:08.926Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/00/cf/89c99698151c00a4631fbfcfcf459d308213ac29e321b0ff44ceeeac82f1/cryptography-46.0.4-cp38-abi3-manylinux_2_34_ppc64le.whl", hash = "sha256:d5a45ddc256f492ce42a4e35879c5e5528c09cd9ad12420828c972951d8e016b", size = 4903339, upload-time = "2026-01-28T00:24:12.009Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/03/c3/c90a2cb358de4ac9309b26acf49b2a100957e1ff5cc1e98e6c4996576710/cryptography-46.0.4-cp38-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:6bb5157bf6a350e5b28aee23beb2d84ae6f5be390b2f8ee7ea179cda077e1019", size = 4451216, upload-time = "2026-01-28T00:24:13.975Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/96/2c/8d7f4171388a10208671e181ca43cdc0e596d8259ebacbbcfbd16de593da/cryptography-46.0.4-cp38-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:dd5aba870a2c40f87a3af043e0dee7d9eb02d4aff88a797b48f2b43eff8c3ab4", size = 4404299, upload-time = "2026-01-28T00:24:16.169Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/e9/23/cbb2036e450980f65c6e0a173b73a56ff3bccd8998965dea5cc9ddd424a5/cryptography-46.0.4-cp38-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:93d8291da8d71024379ab2cb0b5c57915300155ad42e07f76bea6ad838d7e59b", size = 4664837, upload-time = "2026-01-28T00:24:17.629Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/0a/21/f7433d18fe6d5845329cbdc597e30caf983229c7a245bcf54afecc555938/cryptography-46.0.4-cp38-abi3-win32.whl", hash = "sha256:0563655cb3c6d05fb2afe693340bc050c30f9f34e15763361cf08e94749401fc", size = 3009779, upload-time = "2026-01-28T00:24:20.198Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/3a/6a/bd2e7caa2facffedf172a45c1a02e551e6d7d4828658c9a245516a598d94/cryptography-46.0.4-cp38-abi3-win_amd64.whl", hash = "sha256:fa0900b9ef9c49728887d1576fd8d9e7e3ea872fa9b25ef9b64888adc434e976", size = 3466633, upload-time = "2026-01-28T00:24:21.851Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/59/e0/f9c6c53e1f2a1c2507f00f2faba00f01d2f334b35b0fbfe5286715da2184/cryptography-46.0.4-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:766330cce7416c92b5e90c3bb71b1b79521760cdcfc3a6a1a182d4c9fab23d2b", size = 3476316, upload-time = "2026-01-28T00:24:24.144Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/27/7a/f8d2d13227a9a1a9fe9c7442b057efecffa41f1e3c51d8622f26b9edbe8f/cryptography-46.0.4-pp311-pypy311_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:c236a44acfb610e70f6b3e1c3ca20ff24459659231ef2f8c48e879e2d32b73da", size = 4216693, upload-time = "2026-01-28T00:24:25.758Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c5/de/3787054e8f7972658370198753835d9d680f6cd4a39df9f877b57f0dd69c/cryptography-46.0.4-pp311-pypy311_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:8a15fb869670efa8f83cbffbc8753c1abf236883225aed74cd179b720ac9ec80", size = 4382765, upload-time = "2026-01-28T00:24:27.577Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/8a/5f/60e0afb019973ba6a0b322e86b3d61edf487a4f5597618a430a2a15f2d22/cryptography-46.0.4-pp311-pypy311_pp73-manylinux_2_34_aarch64.whl", hash = "sha256:fdc3daab53b212472f1524d070735b2f0c214239df131903bae1d598016fa822", size = 4216066, upload-time = "2026-01-28T00:24:29.056Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/81/8e/bf4a0de294f147fee66f879d9bae6f8e8d61515558e3d12785dd90eca0be/cryptography-46.0.4-pp311-pypy311_pp73-manylinux_2_34_x86_64.whl", hash = "sha256:44cc0675b27cadb71bdbb96099cca1fa051cd11d2ade09e5cd3a2edb929ed947", size = 4382025, upload-time = "2026-01-28T00:24:30.681Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/79/f4/9ceb90cfd6a3847069b0b0b353fd3075dc69b49defc70182d8af0c4ca390/cryptography-46.0.4-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:be8c01a7d5a55f9a47d1888162b76c8f49d62b234d88f0ff91a9fbebe32ffbc3", size = 3406043, upload-time = "2026-01-28T00:24:32.236Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/0b/5d/4a8f770695d73be252331e60e526291e3df0c9b27556a90a6b47bccca4c2/cryptography-46.0.7-cp311-abi3-macosx_10_9_universal2.whl", hash = "sha256:ea42cbe97209df307fdc3b155f1b6fa2577c0defa8f1f7d3be7d31d189108ad4", size = 7179869, upload-time = "2026-04-08T01:56:17.157Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/5f/45/6d80dc379b0bbc1f9d1e429f42e4cb9e1d319c7a8201beffd967c516ea01/cryptography-46.0.7-cp311-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:b36a4695e29fe69215d75960b22577197aca3f7a25b9cf9d165dcfe9d80bc325", size = 4275492, upload-time = "2026-04-08T01:56:19.36Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/4a/9a/1765afe9f572e239c3469f2cb429f3ba7b31878c893b246b4b2994ffe2fe/cryptography-46.0.7-cp311-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:5ad9ef796328c5e3c4ceed237a183f5d41d21150f972455a9d926593a1dcb308", size = 4426670, upload-time = "2026-04-08T01:56:21.415Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/8f/3e/af9246aaf23cd4ee060699adab1e47ced3f5f7e7a8ffdd339f817b446462/cryptography-46.0.7-cp311-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:73510b83623e080a2c35c62c15298096e2a5dc8d51c3b4e1740211839d0dea77", size = 4280275, upload-time = "2026-04-08T01:56:23.539Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/0f/54/6bbbfc5efe86f9d71041827b793c24811a017c6ac0fd12883e4caa86b8ed/cryptography-46.0.7-cp311-abi3-manylinux_2_28_ppc64le.whl", hash = "sha256:cbd5fb06b62bd0721e1170273d3f4d5a277044c47ca27ee257025146c34cbdd1", size = 4928402, upload-time = "2026-04-08T01:56:25.624Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/2d/cf/054b9d8220f81509939599c8bdbc0c408dbd2bdd41688616a20731371fe0/cryptography-46.0.7-cp311-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:420b1e4109cc95f0e5700eed79908cef9268265c773d3a66f7af1eef53d409ef", size = 4459985, upload-time = "2026-04-08T01:56:27.309Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/f9/46/4e4e9c6040fb01c7467d47217d2f882daddeb8828f7df800cb806d8a2288/cryptography-46.0.7-cp311-abi3-manylinux_2_31_armv7l.whl", hash = "sha256:24402210aa54baae71d99441d15bb5a1919c195398a87b563df84468160a65de", size = 3990652, upload-time = "2026-04-08T01:56:29.095Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/36/5f/313586c3be5a2fbe87e4c9a254207b860155a8e1f3cca99f9910008e7d08/cryptography-46.0.7-cp311-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:8a469028a86f12eb7d2fe97162d0634026d92a21f3ae0ac87ed1c4a447886c83", size = 4279805, upload-time = "2026-04-08T01:56:30.928Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/69/33/60dfc4595f334a2082749673386a4d05e4f0cf4df8248e63b2c3437585f2/cryptography-46.0.7-cp311-abi3-manylinux_2_34_ppc64le.whl", hash = "sha256:9694078c5d44c157ef3162e3bf3946510b857df5a3955458381d1c7cfc143ddb", size = 4892883, upload-time = "2026-04-08T01:56:32.614Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c7/0b/333ddab4270c4f5b972f980adef4faa66951a4aaf646ca067af597f15563/cryptography-46.0.7-cp311-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:42a1e5f98abb6391717978baf9f90dc28a743b7d9be7f0751a6f56a75d14065b", size = 4459756, upload-time = "2026-04-08T01:56:34.306Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/d2/14/633913398b43b75f1234834170947957c6b623d1701ffc7a9600da907e89/cryptography-46.0.7-cp311-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:91bbcb08347344f810cbe49065914fe048949648f6bd5c2519f34619142bbe85", size = 4410244, upload-time = "2026-04-08T01:56:35.977Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/10/f2/19ceb3b3dc14009373432af0c13f46aa08e3ce334ec6eff13492e1812ccd/cryptography-46.0.7-cp311-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:5d1c02a14ceb9148cc7816249f64f623fbfee39e8c03b3650d842ad3f34d637e", size = 4674868, upload-time = "2026-04-08T01:56:38.034Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/1a/bb/a5c213c19ee94b15dfccc48f363738633a493812687f5567addbcbba9f6f/cryptography-46.0.7-cp311-abi3-win32.whl", hash = "sha256:d23c8ca48e44ee015cd0a54aeccdf9f09004eba9fc96f38c911011d9ff1bd457", size = 3026504, upload-time = "2026-04-08T01:56:39.666Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/2b/02/7788f9fefa1d060ca68717c3901ae7fffa21ee087a90b7f23c7a603c32ae/cryptography-46.0.7-cp311-abi3-win_amd64.whl", hash = "sha256:397655da831414d165029da9bc483bed2fe0e75dde6a1523ec2fe63f3c46046b", size = 3488363, upload-time = "2026-04-08T01:56:41.893Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/7b/56/15619b210e689c5403bb0540e4cb7dbf11a6bf42e483b7644e471a2812b3/cryptography-46.0.7-cp314-cp314t-macosx_10_9_universal2.whl", hash = "sha256:d151173275e1728cf7839aaa80c34fe550c04ddb27b34f48c232193df8db5842", size = 7119671, upload-time = "2026-04-08T01:56:44Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/74/66/e3ce040721b0b5599e175ba91ab08884c75928fbeb74597dd10ef13505d2/cryptography-46.0.7-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:db0f493b9181c7820c8134437eb8b0b4792085d37dbb24da050476ccb664e59c", size = 4268551, upload-time = "2026-04-08T01:56:46.071Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/03/11/5e395f961d6868269835dee1bafec6a1ac176505a167f68b7d8818431068/cryptography-46.0.7-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:ebd6daf519b9f189f85c479427bbd6e9c9037862cf8fe89ee35503bd209ed902", size = 4408887, upload-time = "2026-04-08T01:56:47.718Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/40/53/8ed1cf4c3b9c8e611e7122fb56f1c32d09e1fff0f1d77e78d9ff7c82653e/cryptography-46.0.7-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:b7b412817be92117ec5ed95f880defe9cf18a832e8cafacf0a22337dc1981b4d", size = 4271354, upload-time = "2026-04-08T01:56:49.312Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/50/46/cf71e26025c2e767c5609162c866a78e8a2915bbcfa408b7ca495c6140c4/cryptography-46.0.7-cp314-cp314t-manylinux_2_28_ppc64le.whl", hash = "sha256:fbfd0e5f273877695cb93baf14b185f4878128b250cc9f8e617ea0c025dfb022", size = 4905845, upload-time = "2026-04-08T01:56:50.916Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c0/ea/01276740375bac6249d0a971ebdf6b4dc9ead0ee0a34ef3b5a88c1a9b0d4/cryptography-46.0.7-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:ffca7aa1d00cf7d6469b988c581598f2259e46215e0140af408966a24cf086ce", size = 4444641, upload-time = "2026-04-08T01:56:52.882Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/3d/4c/7d258f169ae71230f25d9f3d06caabcff8c3baf0978e2b7d65e0acac3827/cryptography-46.0.7-cp314-cp314t-manylinux_2_31_armv7l.whl", hash = "sha256:60627cf07e0d9274338521205899337c5d18249db56865f943cbe753aa96f40f", size = 3967749, upload-time = "2026-04-08T01:56:54.597Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/b5/2a/2ea0767cad19e71b3530e4cad9605d0b5e338b6a1e72c37c9c1ceb86c333/cryptography-46.0.7-cp314-cp314t-manylinux_2_34_aarch64.whl", hash = "sha256:80406c3065e2c55d7f49a9550fe0c49b3f12e5bfff5dedb727e319e1afb9bf99", size = 4270942, upload-time = "2026-04-08T01:56:56.416Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/41/3d/fe14df95a83319af25717677e956567a105bb6ab25641acaa093db79975d/cryptography-46.0.7-cp314-cp314t-manylinux_2_34_ppc64le.whl", hash = "sha256:c5b1ccd1239f48b7151a65bc6dd54bcfcc15e028c8ac126d3fada09db0e07ef1", size = 4871079, upload-time = "2026-04-08T01:56:58.31Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/9c/59/4a479e0f36f8f378d397f4eab4c850b4ffb79a2f0d58704b8fa0703ddc11/cryptography-46.0.7-cp314-cp314t-manylinux_2_34_x86_64.whl", hash = "sha256:d5f7520159cd9c2154eb61eb67548ca05c5774d39e9c2c4339fd793fe7d097b2", size = 4443999, upload-time = "2026-04-08T01:57:00.508Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/28/17/b59a741645822ec6d04732b43c5d35e4ef58be7bfa84a81e5ae6f05a1d33/cryptography-46.0.7-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:fcd8eac50d9138c1d7fc53a653ba60a2bee81a505f9f8850b6b2888555a45d0e", size = 4399191, upload-time = "2026-04-08T01:57:02.654Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/59/6a/bb2e166d6d0e0955f1e9ff70f10ec4b2824c9cfcdb4da772c7dd69cc7d80/cryptography-46.0.7-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:65814c60f8cc400c63131584e3e1fad01235edba2614b61fbfbfa954082db0ee", size = 4655782, upload-time = "2026-04-08T01:57:04.592Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/95/b6/3da51d48415bcb63b00dc17c2eff3a651b7c4fed484308d0f19b30e8cb2c/cryptography-46.0.7-cp314-cp314t-win32.whl", hash = "sha256:fdd1736fed309b4300346f88f74cd120c27c56852c3838cab416e7a166f67298", size = 3002227, upload-time = "2026-04-08T01:57:06.91Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/32/a8/9f0e4ed57ec9cebe506e58db11ae472972ecb0c659e4d52bbaee80ca340a/cryptography-46.0.7-cp314-cp314t-win_amd64.whl", hash = "sha256:e06acf3c99be55aa3b516397fe42f5855597f430add9c17fa46bf2e0fb34c9bb", size = 3475332, upload-time = "2026-04-08T01:57:08.807Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/a7/7f/cd42fc3614386bc0c12f0cb3c4ae1fc2bbca5c9662dfed031514911d513d/cryptography-46.0.7-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:462ad5cb1c148a22b2e3bcc5ad52504dff325d17daf5df8d88c17dda1f75f2a4", size = 7165618, upload-time = "2026-04-08T01:57:10.645Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/a5/d0/36a49f0262d2319139d2829f773f1b97ef8aef7f97e6e5bd21455e5a8fb5/cryptography-46.0.7-cp38-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:84d4cced91f0f159a7ddacad249cc077e63195c36aac40b4150e7a57e84fffe7", size = 4270628, upload-time = "2026-04-08T01:57:12.885Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/8a/6c/1a42450f464dda6ffbe578a911f773e54dd48c10f9895a23a7e88b3e7db5/cryptography-46.0.7-cp38-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:128c5edfe5e5938b86b03941e94fac9ee793a94452ad1365c9fc3f4f62216832", size = 4415405, upload-time = "2026-04-08T01:57:14.923Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/9a/92/4ed714dbe93a066dc1f4b4581a464d2d7dbec9046f7c8b7016f5286329e2/cryptography-46.0.7-cp38-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:5e51be372b26ef4ba3de3c167cd3d1022934bc838ae9eaad7e644986d2a3d163", size = 4272715, upload-time = "2026-04-08T01:57:16.638Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/b7/e6/a26b84096eddd51494bba19111f8fffe976f6a09f132706f8f1bf03f51f7/cryptography-46.0.7-cp38-abi3-manylinux_2_28_ppc64le.whl", hash = "sha256:cdf1a610ef82abb396451862739e3fc93b071c844399e15b90726ef7470eeaf2", size = 4918400, upload-time = "2026-04-08T01:57:19.021Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c7/08/ffd537b605568a148543ac3c2b239708ae0bd635064bab41359252ef88ed/cryptography-46.0.7-cp38-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:1d25aee46d0c6f1a501adcddb2d2fee4b979381346a78558ed13e50aa8a59067", size = 4450634, upload-time = "2026-04-08T01:57:21.185Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/16/01/0cd51dd86ab5b9befe0d031e276510491976c3a80e9f6e31810cce46c4ad/cryptography-46.0.7-cp38-abi3-manylinux_2_31_armv7l.whl", hash = "sha256:cdfbe22376065ffcf8be74dc9a909f032df19bc58a699456a21712d6e5eabfd0", size = 3985233, upload-time = "2026-04-08T01:57:22.862Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/92/49/819d6ed3a7d9349c2939f81b500a738cb733ab62fbecdbc1e38e83d45e12/cryptography-46.0.7-cp38-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:abad9dac36cbf55de6eb49badd4016806b3165d396f64925bf2999bcb67837ba", size = 4271955, upload-time = "2026-04-08T01:57:24.814Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/80/07/ad9b3c56ebb95ed2473d46df0847357e01583f4c52a85754d1a55e29e4d0/cryptography-46.0.7-cp38-abi3-manylinux_2_34_ppc64le.whl", hash = "sha256:935ce7e3cfdb53e3536119a542b839bb94ec1ad081013e9ab9b7cfd478b05006", size = 4879888, upload-time = "2026-04-08T01:57:26.88Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/b8/c7/201d3d58f30c4c2bdbe9b03844c291feb77c20511cc3586daf7edc12a47b/cryptography-46.0.7-cp38-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:35719dc79d4730d30f1c2b6474bd6acda36ae2dfae1e3c16f2051f215df33ce0", size = 4449961, upload-time = "2026-04-08T01:57:29.068Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/a5/ef/649750cbf96f3033c3c976e112265c33906f8e462291a33d77f90356548c/cryptography-46.0.7-cp38-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:7bbc6ccf49d05ac8f7d7b5e2e2c33830d4fe2061def88210a126d130d7f71a85", size = 4401696, upload-time = "2026-04-08T01:57:31.029Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/41/52/a8908dcb1a389a459a29008c29966c1d552588d4ae6d43f3a1a4512e0ebe/cryptography-46.0.7-cp38-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:a1529d614f44b863a7b480c6d000fe93b59acee9c82ffa027cfadc77521a9f5e", size = 4664256, upload-time = "2026-04-08T01:57:33.144Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/4b/fa/f0ab06238e899cc3fb332623f337a7364f36f4bb3f2534c2bb95a35b132c/cryptography-46.0.7-cp38-abi3-win32.whl", hash = "sha256:f247c8c1a1fb45e12586afbb436ef21ff1e80670b2861a90353d9b025583d246", size = 3013001, upload-time = "2026-04-08T01:57:34.933Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/d2/f1/00ce3bde3ca542d1acd8f8cfa38e446840945aa6363f9b74746394b14127/cryptography-46.0.7-cp38-abi3-win_amd64.whl", hash = "sha256:506c4ff91eff4f82bdac7633318a526b1d1309fc07ca76a3ad182cb5b686d6d3", size = 3472985, upload-time = "2026-04-08T01:57:36.714Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/63/0c/dca8abb64e7ca4f6b2978769f6fea5ad06686a190cec381f0a796fdcaaba/cryptography-46.0.7-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:fc9ab8856ae6cf7c9358430e49b368f3108f050031442eaeb6b9d87e4dcf4e4f", size = 3476879, upload-time = "2026-04-08T01:57:38.664Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/3a/ea/075aac6a84b7c271578d81a2f9968acb6e273002408729f2ddff517fed4a/cryptography-46.0.7-pp311-pypy311_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:d3b99c535a9de0adced13d159c5a9cf65c325601aa30f4be08afd680643e9c15", size = 4219700, upload-time = "2026-04-08T01:57:40.625Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/6c/7b/1c55db7242b5e5612b29fc7a630e91ee7a6e3c8e7bf5406d22e206875fbd/cryptography-46.0.7-pp311-pypy311_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:d02c738dacda7dc2a74d1b2b3177042009d5cab7c7079db74afc19e56ca1b455", size = 4385982, upload-time = "2026-04-08T01:57:42.725Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/cb/da/9870eec4b69c63ef5925bf7d8342b7e13bc2ee3d47791461c4e49ca212f4/cryptography-46.0.7-pp311-pypy311_pp73-manylinux_2_34_aarch64.whl", hash = "sha256:04959522f938493042d595a736e7dbdff6eb6cc2339c11465b3ff89343b65f65", size = 4219115, upload-time = "2026-04-08T01:57:44.939Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/f4/72/05aa5832b82dd341969e9a734d1812a6aadb088d9eb6f0430fc337cc5a8f/cryptography-46.0.7-pp311-pypy311_pp73-manylinux_2_34_x86_64.whl", hash = "sha256:3986ac1dee6def53797289999eabe84798ad7817f3e97779b5061a95b0ee4968", size = 4385479, upload-time = "2026-04-08T01:57:46.86Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/20/2a/1b016902351a523aa2bd446b50a5bc1175d7a7d1cf90fe2ef904f9b84ebc/cryptography-46.0.7-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:258514877e15963bd43b558917bc9f54cf7cf866c38aa576ebf47a77ddbc43a4", size = 3412829, upload-time = "2026-04-08T01:57:48.874Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -1133,114 +1133,43 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/f7/ec/67fbef5d497f86283db54c22eec6f6140243aae73265799baaaa19cd17fb/ghp_import-2.1.0-py3-none-any.whl", hash = "sha256:8337dd7b50877f163d4c0289bc1f1c7f127550241988d568c1db512c4324a619", size = 11034, upload-time = "2022-05-02T15:47:14.552Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "google-ai-generativelanguage"
|
||||
version = "0.6.15"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "google-api-core", extra = ["grpc"] },
|
||||
{ name = "google-auth" },
|
||||
{ name = "proto-plus" },
|
||||
{ name = "protobuf" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/11/d1/48fe5d7a43d278e9f6b5ada810b0a3530bbeac7ed7fcbcd366f932f05316/google_ai_generativelanguage-0.6.15.tar.gz", hash = "sha256:8f6d9dc4c12b065fe2d0289026171acea5183ebf2d0b11cefe12f3821e159ec3", size = 1375443, upload-time = "2025-01-13T21:50:47.459Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/7c/a3/67b8a6ff5001a1d8864922f2d6488dc2a14367ceb651bc3f09a947f2f306/google_ai_generativelanguage-0.6.15-py3-none-any.whl", hash = "sha256:5a03ef86377aa184ffef3662ca28f19eeee158733e45d7947982eb953c6ebb6c", size = 1327356, upload-time = "2025-01-13T21:50:44.174Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "google-api-core"
|
||||
version = "2.25.2"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "google-auth" },
|
||||
{ name = "googleapis-common-protos" },
|
||||
{ name = "proto-plus" },
|
||||
{ name = "protobuf" },
|
||||
{ name = "requests" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/09/cd/63f1557235c2440fe0577acdbc32577c5c002684c58c7f4d770a92366a24/google_api_core-2.25.2.tar.gz", hash = "sha256:1c63aa6af0d0d5e37966f157a77f9396d820fba59f9e43e9415bc3dc5baff300", size = 166266, upload-time = "2025-10-03T00:07:34.778Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/c8/d8/894716a5423933f5c8d2d5f04b16f052a515f78e815dab0c2c6f1fd105dc/google_api_core-2.25.2-py3-none-any.whl", hash = "sha256:e9a8f62d363dc8424a8497f4c2a47d6bcda6c16514c935629c257ab5d10210e7", size = 162489, upload-time = "2025-10-03T00:07:32.924Z" },
|
||||
]
|
||||
|
||||
[package.optional-dependencies]
|
||||
grpc = [
|
||||
{ name = "grpcio" },
|
||||
{ name = "grpcio-status" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "google-api-python-client"
|
||||
version = "2.189.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "google-api-core" },
|
||||
{ name = "google-auth" },
|
||||
{ name = "google-auth-httplib2" },
|
||||
{ name = "httplib2" },
|
||||
{ name = "uritemplate" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/6f/f8/0783aeca3410ee053d4dd1fccafd85197847b8f84dd038e036634605d083/google_api_python_client-2.189.0.tar.gz", hash = "sha256:45f2d8559b5c895dde6ad3fb33de025f5cb2c197fa5862f18df7f5295a172741", size = 13979470, upload-time = "2026-02-03T19:24:55.432Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/04/44/3677ff27998214f2fa7957359da48da378a0ffff1bd0bdaba42e752bc13e/google_api_python_client-2.189.0-py3-none-any.whl", hash = "sha256:a258c09660a49c6159173f8bbece171278e917e104a11f0640b34751b79c8a1a", size = 14547633, upload-time = "2026-02-03T19:24:52.845Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "google-auth"
|
||||
version = "2.48.0"
|
||||
version = "2.53.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "cryptography" },
|
||||
{ name = "pyasn1-modules" },
|
||||
{ name = "rsa" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/0c/41/242044323fbd746615884b1c16639749e73665b718209946ebad7ba8a813/google_auth-2.48.0.tar.gz", hash = "sha256:4f7e706b0cd3208a3d940a19a822c37a476ddba5450156c3e6624a71f7c841ce", size = 326522, upload-time = "2026-01-26T19:22:47.157Z" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/c6/ad/ff781329bbbdc0974a098d996e89c9e1f7024262f9e3eec442fbb9ad1ac6/google_auth-2.53.0.tar.gz", hash = "sha256:e7e6aa16f6bee7b2b264830fd04f08087a1d5a836df516251a5d15327b246c9c", size = 335844, upload-time = "2026-05-15T20:53:07.928Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/83/1d/d6466de3a5249d35e832a52834115ca9d1d0de6abc22065f049707516d47/google_auth-2.48.0-py3-none-any.whl", hash = "sha256:2e2a537873d449434252a9632c28bfc268b0adb1e53f9fb62afc5333a975903f", size = 236499, upload-time = "2026-01-26T19:22:45.099Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/4a/c9/db44165ba7c581268c6d46017ef63339110378305062830104fc7fa144cb/google_auth-2.53.0-py3-none-any.whl", hash = "sha256:6e7449917c599b35126a99ec268ec6880301f2fea41dce198fe8fd83ff642b68", size = 246071, upload-time = "2026-05-15T20:53:05.609Z" },
|
||||
]
|
||||
|
||||
[package.optional-dependencies]
|
||||
requests = [
|
||||
{ name = "requests" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "google-auth-httplib2"
|
||||
version = "0.3.0"
|
||||
name = "google-genai"
|
||||
version = "2.7.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "google-auth" },
|
||||
{ name = "httplib2" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/d5/ad/c1f2b1175096a8d04cf202ad5ea6065f108d26be6fc7215876bde4a7981d/google_auth_httplib2-0.3.0.tar.gz", hash = "sha256:177898a0175252480d5ed916aeea183c2df87c1f9c26705d74ae6b951c268b0b", size = 11134, upload-time = "2025-12-15T22:13:51.825Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/99/d5/3c97526c8796d3caf5f4b3bed2b05e8a7102326f00a334e7a438237f3b22/google_auth_httplib2-0.3.0-py3-none-any.whl", hash = "sha256:426167e5df066e3f5a0fc7ea18768c08e7296046594ce4c8c409c2457dd1f776", size = 9529, upload-time = "2025-12-15T22:13:51.048Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "google-generativeai"
|
||||
version = "0.8.6"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "google-ai-generativelanguage" },
|
||||
{ name = "google-api-core" },
|
||||
{ name = "google-api-python-client" },
|
||||
{ name = "google-auth" },
|
||||
{ name = "protobuf" },
|
||||
{ name = "anyio" },
|
||||
{ name = "distro" },
|
||||
{ name = "google-auth", extra = ["requests"] },
|
||||
{ name = "httpx" },
|
||||
{ name = "pydantic" },
|
||||
{ name = "tqdm" },
|
||||
{ name = "requests" },
|
||||
{ name = "sniffio" },
|
||||
{ name = "tenacity" },
|
||||
{ name = "typing-extensions" },
|
||||
{ name = "websockets" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/a7/7b/6eb3b3d545b6bb4c374acba1ccf91b0f33b605e551536a6243cfcef2f07f/google_genai-2.7.0.tar.gz", hash = "sha256:3c6f32f5ced9877ededd1b384b5e5b7f09c20046ec3390b662b16d8cd1882ac5", size = 555853, upload-time = "2026-05-28T15:39:24.58Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/97/0f/ef33b5bb71437966590c6297104c81051feae95d54b11ece08533ef937d3/google_generativeai-0.8.6-py3-none-any.whl", hash = "sha256:37a0eaaa95e5bbf888828e20a4a1b2c196cc9527d194706e58a68ff388aeb0fa", size = 155098, upload-time = "2025-12-16T17:53:58.61Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "googleapis-common-protos"
|
||||
version = "1.72.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "protobuf" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/e5/7b/adfd75544c415c487b33061fe7ae526165241c1ea133f9a9125a56b39fd8/googleapis_common_protos-1.72.0.tar.gz", hash = "sha256:e55a601c1b32b52d7a3e65f43563e2aa61bcd737998ee672ac9b951cd49319f5", size = 147433, upload-time = "2025-11-06T18:29:24.087Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/c4/ab/09169d5a4612a5f92490806649ac8d41e3ec9129c636754575b3553f4ea4/googleapis_common_protos-1.72.0-py3-none-any.whl", hash = "sha256:4299c5a82d5ae1a9702ada957347726b167f9f8d1fc352477702a1e851ff4038", size = 297515, upload-time = "2025-11-06T18:29:13.14Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/3c/dd/7a8be39e9d698e80e9db796514efbc6083dbd787bdb9a101e8ba47248e5e/google_genai-2.7.0-py3-none-any.whl", hash = "sha256:21cac381e09a869151706aba797b6a4f96cfe92c484e13204d092caee7ff11cb", size = 822545, upload-time = "2026-05-28T15:39:22.907Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -1278,81 +1207,6 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/4d/51/c936033e16d12b627ea334aaaaf42229c37620d0f15593456ab69ab48161/griffelib-2.0.0-py3-none-any.whl", hash = "sha256:01284878c966508b6d6f1dbff9b6fa607bc062d8261c5c7253cb285b06422a7f", size = 142004, upload-time = "2026-02-09T19:09:40.561Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "grpcio"
|
||||
version = "1.78.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "typing-extensions" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/06/8a/3d098f35c143a89520e568e6539cc098fcd294495910e359889ce8741c84/grpcio-1.78.0.tar.gz", hash = "sha256:7382b95189546f375c174f53a5fa873cef91c4b8005faa05cc5b3beea9c4f1c5", size = 12852416, upload-time = "2026-02-06T09:57:18.093Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/5a/a8/690a085b4d1fe066130de97a87de32c45062cf2ecd218df9675add895550/grpcio-1.78.0-cp310-cp310-linux_armv7l.whl", hash = "sha256:7cc47943d524ee0096f973e1081cb8f4f17a4615f2116882a5f1416e4cfe92b5", size = 5946986, upload-time = "2026-02-06T09:54:34.043Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c7/1b/e5213c5c0ced9d2d92778d30529ad5bb2dcfb6c48c4e2d01b1f302d33d64/grpcio-1.78.0-cp310-cp310-macosx_11_0_universal2.whl", hash = "sha256:c3f293fdc675ccba4db5a561048cca627b5e7bd1c8a6973ffedabe7d116e22e2", size = 11816533, upload-time = "2026-02-06T09:54:37.04Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/18/37/1ba32dccf0a324cc5ace744c44331e300b000a924bf14840f948c559ede7/grpcio-1.78.0-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:10a9a644b5dd5aec3b82b5b0b90d41c0fa94c85ef42cb42cf78a23291ddb5e7d", size = 6519964, upload-time = "2026-02-06T09:54:40.268Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ed/f5/c0e178721b818072f2e8b6fde13faaba942406c634009caf065121ce246b/grpcio-1.78.0-cp310-cp310-manylinux2014_i686.manylinux_2_17_i686.whl", hash = "sha256:4c5533d03a6cbd7f56acfc9cfb44ea64f63d29091e40e44010d34178d392d7eb", size = 7198058, upload-time = "2026-02-06T09:54:42.389Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/5b/b2/40d43c91ae9cd667edc960135f9f08e58faa1576dc95af29f66ec912985f/grpcio-1.78.0-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:ff870aebe9a93a85283837801d35cd5f8814fe2ad01e606861a7fb47c762a2b7", size = 6727212, upload-time = "2026-02-06T09:54:44.91Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ed/88/9da42eed498f0efcfcd9156e48ae63c0cde3bea398a16c99fb5198c885b6/grpcio-1.78.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:391e93548644e6b2726f1bb84ed60048d4bcc424ce5e4af0843d28ca0b754fec", size = 7300845, upload-time = "2026-02-06T09:54:47.562Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/23/3f/1c66b7b1b19a8828890e37868411a6e6925df5a9030bfa87ab318f34095d/grpcio-1.78.0-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:df2c8f3141f7cbd112a6ebbd760290b5849cda01884554f7c67acc14e7b1758a", size = 8284605, upload-time = "2026-02-06T09:54:50.475Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/94/c4/ca1bd87394f7b033e88525384b4d1e269e8424ab441ea2fba1a0c5b50986/grpcio-1.78.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:bd8cb8026e5f5b50498a3c4f196f57f9db344dad829ffae16b82e4fdbaea2813", size = 7726672, upload-time = "2026-02-06T09:54:53.11Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/41/09/f16e487d4cc65ccaf670f6ebdd1a17566b965c74fc3d93999d3b2821e052/grpcio-1.78.0-cp310-cp310-win32.whl", hash = "sha256:f8dff3d9777e5d2703a962ee5c286c239bf0ba173877cc68dc02c17d042e29de", size = 4076715, upload-time = "2026-02-06T09:54:55.549Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/2a/32/4ce60d94e242725fd3bcc5673c04502c82a8e87b21ea411a63992dc39f8f/grpcio-1.78.0-cp310-cp310-win_amd64.whl", hash = "sha256:94f95cf5d532d0e717eed4fc1810e8e6eded04621342ec54c89a7c2f14b581bf", size = 4799157, upload-time = "2026-02-06T09:54:59.838Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/86/c7/d0b780a29b0837bf4ca9580904dfb275c1fc321ded7897d620af7047ec57/grpcio-1.78.0-cp311-cp311-linux_armv7l.whl", hash = "sha256:2777b783f6c13b92bd7b716667452c329eefd646bfb3f2e9dabea2e05dbd34f6", size = 5951525, upload-time = "2026-02-06T09:55:01.989Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c5/b1/96920bf2ee61df85a9503cb6f733fe711c0ff321a5a697d791b075673281/grpcio-1.78.0-cp311-cp311-macosx_11_0_universal2.whl", hash = "sha256:9dca934f24c732750389ce49d638069c3892ad065df86cb465b3fa3012b70c9e", size = 11830418, upload-time = "2026-02-06T09:55:04.462Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/83/0c/7c1528f098aeb75a97de2bae18c530f56959fb7ad6c882db45d9884d6edc/grpcio-1.78.0-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:459ab414b35f4496138d0ecd735fed26f1318af5e52cb1efbc82a09f0d5aa911", size = 6524477, upload-time = "2026-02-06T09:55:07.111Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/8d/52/e7c1f3688f949058e19a011c4e0dec973da3d0ae5e033909677f967ae1f4/grpcio-1.78.0-cp311-cp311-manylinux2014_i686.manylinux_2_17_i686.whl", hash = "sha256:082653eecbdf290e6e3e2c276ab2c54b9e7c299e07f4221872380312d8cf395e", size = 7198266, upload-time = "2026-02-06T09:55:10.016Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/e5/61/8ac32517c1e856677282c34f2e7812d6c328fa02b8f4067ab80e77fdc9c9/grpcio-1.78.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:85f93781028ec63f383f6bc90db785a016319c561cc11151fbb7b34e0d012303", size = 6730552, upload-time = "2026-02-06T09:55:12.207Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/bd/98/b8ee0158199250220734f620b12e4a345955ac7329cfd908d0bf0fda77f0/grpcio-1.78.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:f12857d24d98441af6a1d5c87442d624411db486f7ba12550b07788f74b67b04", size = 7304296, upload-time = "2026-02-06T09:55:15.044Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/bd/0f/7b72762e0d8840b58032a56fdbd02b78fc645b9fa993d71abf04edbc54f4/grpcio-1.78.0-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:5397fff416b79e4b284959642a4e95ac4b0f1ece82c9993658e0e477d40551ec", size = 8288298, upload-time = "2026-02-06T09:55:17.276Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/24/ae/ae4ce56bc5bb5caa3a486d60f5f6083ac3469228faa734362487176c15c5/grpcio-1.78.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:fbe6e89c7ffb48518384068321621b2a69cab509f58e40e4399fdd378fa6d074", size = 7730953, upload-time = "2026-02-06T09:55:19.545Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/b5/6e/8052e3a28eb6a820c372b2eb4b5e32d195c661e137d3eca94d534a4cfd8a/grpcio-1.78.0-cp311-cp311-win32.whl", hash = "sha256:6092beabe1966a3229f599d7088b38dfc8ffa1608b5b5cdda31e591e6500f856", size = 4076503, upload-time = "2026-02-06T09:55:21.521Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/08/62/f22c98c5265dfad327251fa2f840b591b1df5f5e15d88b19c18c86965b27/grpcio-1.78.0-cp311-cp311-win_amd64.whl", hash = "sha256:1afa62af6e23f88629f2b29ec9e52ec7c65a7176c1e0a83292b93c76ca882558", size = 4799767, upload-time = "2026-02-06T09:55:24.107Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/4e/f4/7384ed0178203d6074446b3c4f46c90a22ddf7ae0b3aee521627f54cfc2a/grpcio-1.78.0-cp312-cp312-linux_armv7l.whl", hash = "sha256:f9ab915a267fc47c7e88c387a3a28325b58c898e23d4995f765728f4e3dedb97", size = 5913985, upload-time = "2026-02-06T09:55:26.832Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/81/ed/be1caa25f06594463f685b3790b320f18aea49b33166f4141bfdc2bfb236/grpcio-1.78.0-cp312-cp312-macosx_11_0_universal2.whl", hash = "sha256:3f8904a8165ab21e07e58bf3e30a73f4dffc7a1e0dbc32d51c61b5360d26f43e", size = 11811853, upload-time = "2026-02-06T09:55:29.224Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/24/a7/f06d151afc4e64b7e3cc3e872d331d011c279aaab02831e40a81c691fb65/grpcio-1.78.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:859b13906ce098c0b493af92142ad051bf64c7870fa58a123911c88606714996", size = 6475766, upload-time = "2026-02-06T09:55:31.825Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/8a/a8/4482922da832ec0082d0f2cc3a10976d84a7424707f25780b82814aafc0a/grpcio-1.78.0-cp312-cp312-manylinux2014_i686.manylinux_2_17_i686.whl", hash = "sha256:b2342d87af32790f934a79c3112641e7b27d63c261b8b4395350dad43eff1dc7", size = 7170027, upload-time = "2026-02-06T09:55:34.7Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/54/bf/f4a3b9693e35d25b24b0b39fa46d7d8a3c439e0a3036c3451764678fec20/grpcio-1.78.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:12a771591ae40bc65ba67048fa52ef4f0e6db8279e595fd349f9dfddeef571f9", size = 6690766, upload-time = "2026-02-06T09:55:36.902Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c7/b9/521875265cc99fe5ad4c5a17010018085cae2810a928bf15ebe7d8bcd9cc/grpcio-1.78.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:185dea0d5260cbb2d224c507bf2a5444d5abbb1fa3594c1ed7e4c709d5eb8383", size = 7266161, upload-time = "2026-02-06T09:55:39.824Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/05/86/296a82844fd40a4ad4a95f100b55044b4f817dece732bf686aea1a284147/grpcio-1.78.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:51b13f9aed9d59ee389ad666b8c2214cc87b5de258fa712f9ab05f922e3896c6", size = 8253303, upload-time = "2026-02-06T09:55:42.353Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/f3/e4/ea3c0caf5468537f27ad5aab92b681ed7cc0ef5f8c9196d3fd42c8c2286b/grpcio-1.78.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:fd5f135b1bd58ab088930b3c613455796dfa0393626a6972663ccdda5b4ac6ce", size = 7698222, upload-time = "2026-02-06T09:55:44.629Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/d7/47/7f05f81e4bb6b831e93271fb12fd52ba7b319b5402cbc101d588f435df00/grpcio-1.78.0-cp312-cp312-win32.whl", hash = "sha256:94309f498bcc07e5a7d16089ab984d42ad96af1d94b5a4eb966a266d9fcabf68", size = 4066123, upload-time = "2026-02-06T09:55:47.644Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ad/e7/d6914822c88aa2974dbbd10903d801a28a19ce9cd8bad7e694cbbcf61528/grpcio-1.78.0-cp312-cp312-win_amd64.whl", hash = "sha256:9566fe4ababbb2610c39190791e5b829869351d14369603702e890ef3ad2d06e", size = 4797657, upload-time = "2026-02-06T09:55:49.86Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/05/a9/8f75894993895f361ed8636cd9237f4ab39ef87fd30db17467235ed1c045/grpcio-1.78.0-cp313-cp313-linux_armv7l.whl", hash = "sha256:ce3a90455492bf8bfa38e56fbbe1dbd4f872a3d8eeaf7337dc3b1c8aa28c271b", size = 5920143, upload-time = "2026-02-06T09:55:52.035Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/55/06/0b78408e938ac424100100fd081189451b472236e8a3a1f6500390dc4954/grpcio-1.78.0-cp313-cp313-macosx_11_0_universal2.whl", hash = "sha256:2bf5e2e163b356978b23652c4818ce4759d40f4712ee9ec5a83c4be6f8c23a3a", size = 11803926, upload-time = "2026-02-06T09:55:55.494Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/88/93/b59fe7832ff6ae3c78b813ea43dac60e295fa03606d14d89d2e0ec29f4f3/grpcio-1.78.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:8f2ac84905d12918e4e55a16da17939eb63e433dc11b677267c35568aa63fc84", size = 6478628, upload-time = "2026-02-06T09:55:58.533Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ed/df/e67e3734527f9926b7d9c0dde6cd998d1d26850c3ed8eeec81297967ac67/grpcio-1.78.0-cp313-cp313-manylinux2014_i686.manylinux_2_17_i686.whl", hash = "sha256:b58f37edab4a3881bc6c9bca52670610e0c9ca14e2ea3cf9debf185b870457fb", size = 7173574, upload-time = "2026-02-06T09:56:01.786Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/a6/62/cc03fffb07bfba982a9ec097b164e8835546980aec25ecfa5f9c1a47e022/grpcio-1.78.0-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:735e38e176a88ce41840c21bb49098ab66177c64c82426e24e0082500cc68af5", size = 6692639, upload-time = "2026-02-06T09:56:04.529Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/bf/9a/289c32e301b85bdb67d7ec68b752155e674ee3ba2173a1858f118e399ef3/grpcio-1.78.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:2045397e63a7a0ee7957c25f7dbb36ddc110e0cfb418403d110c0a7a68a844e9", size = 7268838, upload-time = "2026-02-06T09:56:08.397Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/0e/79/1be93f32add280461fa4773880196572563e9c8510861ac2da0ea0f892b6/grpcio-1.78.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:a9f136fbafe7ccf4ac7e8e0c28b31066e810be52d6e344ef954a3a70234e1702", size = 8251878, upload-time = "2026-02-06T09:56:10.914Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/65/65/793f8e95296ab92e4164593674ae6291b204bb5f67f9d4a711489cd30ffa/grpcio-1.78.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:748b6138585379c737adc08aeffd21222abbda1a86a0dca2a39682feb9196c20", size = 7695412, upload-time = "2026-02-06T09:56:13.593Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/1c/9f/1e233fe697ecc82845942c2822ed06bb522e70d6771c28d5528e4c50f6a4/grpcio-1.78.0-cp313-cp313-win32.whl", hash = "sha256:271c73e6e5676afe4fc52907686670c7cea22ab2310b76a59b678403ed40d670", size = 4064899, upload-time = "2026-02-06T09:56:15.601Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/4d/27/d86b89e36de8a951501fb06a0f38df19853210f341d0b28f83f4aa0ffa08/grpcio-1.78.0-cp313-cp313-win_amd64.whl", hash = "sha256:f2d4e43ee362adfc05994ed479334d5a451ab7bc3f3fee1b796b8ca66895acb4", size = 4797393, upload-time = "2026-02-06T09:56:17.882Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/29/f2/b56e43e3c968bfe822fa6ce5bca10d5c723aa40875b48791ce1029bb78c7/grpcio-1.78.0-cp314-cp314-linux_armv7l.whl", hash = "sha256:e87cbc002b6f440482b3519e36e1313eb5443e9e9e73d6a52d43bd2004fcfd8e", size = 5920591, upload-time = "2026-02-06T09:56:20.758Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/5d/81/1f3b65bd30c334167bfa8b0d23300a44e2725ce39bba5b76a2460d85f745/grpcio-1.78.0-cp314-cp314-macosx_11_0_universal2.whl", hash = "sha256:c41bc64626db62e72afec66b0c8a0da76491510015417c127bfc53b2fe6d7f7f", size = 11813685, upload-time = "2026-02-06T09:56:24.315Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/0e/1c/bbe2f8216a5bd3036119c544d63c2e592bdf4a8ec6e4a1867592f4586b26/grpcio-1.78.0-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:8dfffba826efcf366b1e3ccc37e67afe676f290e13a3b48d31a46739f80a8724", size = 6487803, upload-time = "2026-02-06T09:56:27.367Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/16/5c/a6b2419723ea7ddce6308259a55e8e7593d88464ce8db9f4aa857aba96fa/grpcio-1.78.0-cp314-cp314-manylinux2014_i686.manylinux_2_17_i686.whl", hash = "sha256:74be1268d1439eaaf552c698cdb11cd594f0c49295ae6bb72c34ee31abbe611b", size = 7173206, upload-time = "2026-02-06T09:56:29.876Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/df/1e/b8801345629a415ea7e26c83d75eb5dbe91b07ffe5210cc517348a8d4218/grpcio-1.78.0-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:be63c88b32e6c0f1429f1398ca5c09bc64b0d80950c8bb7807d7d7fb36fb84c7", size = 6693826, upload-time = "2026-02-06T09:56:32.305Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/34/84/0de28eac0377742679a510784f049738a80424b17287739fc47d63c2439e/grpcio-1.78.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:3c586ac70e855c721bda8f548d38c3ca66ac791dc49b66a8281a1f99db85e452", size = 7277897, upload-time = "2026-02-06T09:56:34.915Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ca/9c/ad8685cfe20559a9edb66f735afdcb2b7d3de69b13666fdfc542e1916ebd/grpcio-1.78.0-cp314-cp314-musllinux_1_2_i686.whl", hash = "sha256:35eb275bf1751d2ffbd8f57cdbc46058e857cf3971041521b78b7db94bdaf127", size = 8252404, upload-time = "2026-02-06T09:56:37.553Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/3c/05/33a7a4985586f27e1de4803887c417ec7ced145ebd069bc38a9607059e2b/grpcio-1.78.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:207db540302c884b8848036b80db352a832b99dfdf41db1eb554c2c2c7800f65", size = 7696837, upload-time = "2026-02-06T09:56:40.173Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/73/77/7382241caf88729b106e49e7d18e3116216c778e6a7e833826eb96de22f7/grpcio-1.78.0-cp314-cp314-win32.whl", hash = "sha256:57bab6deef2f4f1ca76cc04565df38dc5713ae6c17de690721bdf30cb1e0545c", size = 4142439, upload-time = "2026-02-06T09:56:43.258Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/48/b2/b096ccce418882fbfda4f7496f9357aaa9a5af1896a9a7f60d9f2b275a06/grpcio-1.78.0-cp314-cp314-win_amd64.whl", hash = "sha256:dce09d6116df20a96acfdbf85e4866258c3758180e8c49845d6ba8248b6d0bbb", size = 4929852, upload-time = "2026-02-06T09:56:45.885Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "grpcio-status"
|
||||
version = "1.71.2"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "googleapis-common-protos" },
|
||||
{ name = "grpcio" },
|
||||
{ name = "protobuf" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/fd/d1/b6e9877fedae3add1afdeae1f89d1927d296da9cf977eca0eb08fb8a460e/grpcio_status-1.71.2.tar.gz", hash = "sha256:c7a97e176df71cdc2c179cd1847d7fc86cca5832ad12e9798d7fed6b7a1aab50", size = 13677, upload-time = "2025-06-28T04:24:05.426Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/67/58/317b0134129b556a93a3b0afe00ee675b5657f0155509e22fcb853bafe2d/grpcio_status-1.71.2-py3-none-any.whl", hash = "sha256:803c98cb6a8b7dc6dbb785b1111aed739f241ab5e9da0bba96888aa74704cfd3", size = 14424, upload-time = "2025-06-28T04:23:42.136Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "h11"
|
||||
version = "0.16.0"
|
||||
@@ -1404,18 +1258,6 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/7e/f5/f66802a942d491edb555dd61e3a9961140fd64c90bce1eafd741609d334d/httpcore-1.0.9-py3-none-any.whl", hash = "sha256:2d400746a40668fc9dec9810239072b40b4484b640a8c38fd654a024c7a1bf55", size = 78784, upload-time = "2025-04-24T22:06:20.566Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "httplib2"
|
||||
version = "0.31.2"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "pyparsing" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/c1/1f/e86365613582c027dda5ddb64e1010e57a3d53e99ab8a72093fa13d565ec/httplib2-0.31.2.tar.gz", hash = "sha256:385e0869d7397484f4eab426197a4c020b606edd43372492337c0b4010ae5d24", size = 250800, upload-time = "2026-01-23T11:04:44.165Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/2f/90/fd509079dfcab01102c0fdd87f3a9506894bc70afcf9e9785ef6b2b3aff6/httplib2-0.31.2-py3-none-any.whl", hash = "sha256:dbf0c2fa3862acf3c55c078ea9c0bc4481d7dc5117cae71be9514912cf9f8349", size = 91099, upload-time = "2026-01-23T11:04:42.78Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "httpx"
|
||||
version = "0.28.1"
|
||||
@@ -1891,19 +1733,19 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-namespace"
|
||||
version = "0.6.1"
|
||||
version = "0.7.7"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "lance-namespace-urllib3-client" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/28/9f/7906ba4117df8d965510285eaf07264a77de2fd283b9d44ec7fc63a4a57a/lance_namespace-0.6.1.tar.gz", hash = "sha256:f0deea442bd3f1056a8e2fed056ae2778e3356517ec2e680db049058b824d131", size = 10666, upload-time = "2026-03-17T17:55:44.977Z" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/06/5c/9822af615fc1bd3ee1073994696c739aecde377be32435ec3303aed1bc5d/lance_namespace-0.7.7.tar.gz", hash = "sha256:d00b525f2e26993a6c61668e798bca6c808605ab8a79f29f86a1a1af92d91ae2", size = 10754, upload-time = "2026-05-20T17:32:59.45Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/d1/91/aee1c0a04d17f2810173bd304bd444eb78332045df1b0c1b07cebd01f530/lance_namespace-0.6.1-py3-none-any.whl", hash = "sha256:9699c9e3f12236e5e08ea979cc4e036a8e3c67ed2f37ae6f25c5353ab908e1be", size = 12498, upload-time = "2026-03-17T17:55:44.062Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/11/43/186acc1156da20c351db196e2b6241b2453b16dc1b4cc8e0a626667ca471/lance_namespace-0.7.7-py3-none-any.whl", hash = "sha256:477a7ca6b5e1f673a2c9ba52f42d6e8e3ff7c27a601392a21eb90fba98d0309b", size = 12581, upload-time = "2026-05-20T17:32:57.389Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "lance-namespace-urllib3-client"
|
||||
version = "0.6.1"
|
||||
version = "0.7.7"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "pydantic" },
|
||||
@@ -1911,15 +1753,16 @@ dependencies = [
|
||||
{ name = "typing-extensions" },
|
||||
{ name = "urllib3" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/63/a1/8706a2be25bd184acccc411e48f1a42a4cbf3b6556cba15b9fcf4c15cfcc/lance_namespace_urllib3_client-0.6.1.tar.gz", hash = "sha256:31fbd058ce1ea0bf49045cdeaa756360ece0bc61e9e10276f41af6d217debe87", size = 182567, upload-time = "2026-03-17T17:55:46.87Z" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/07/95/38ab81ccc1e09beeecd8ddfc61b8bc73831dc5053db1e3f9021f64a4896b/lance_namespace_urllib3_client-0.7.7.tar.gz", hash = "sha256:4d8c066628c17c6a10cf643b51a7f7ae1bfb8a614d9cc54a5af38a4ba2b4b102", size = 202930, upload-time = "2026-05-20T17:32:58.308Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/cd/c7/cb9580602dec25f0fdd6005c1c9ba1d4c8c0c3dc8d543107e5a9f248bba8/lance_namespace_urllib3_client-0.6.1-py3-none-any.whl", hash = "sha256:b9c103e1377ad46d2bd70eec894bfec0b1e2133dae0964d7e4de543c6e16293b", size = 317111, upload-time = "2026-03-17T17:55:45.546Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/35/96/5483e48e40433b1d078183c15a92c99e59a156041b0260e7f18ee34e7c08/lance_namespace_urllib3_client-0.7.7-py3-none-any.whl", hash = "sha256:9221c3e00fd89f0c811953d94b32d2ea527765280460a174f5872dc8a74c0ed6", size = 334767, upload-time = "2026-05-20T17:32:55.883Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "lancedb"
|
||||
source = { editable = "." }
|
||||
dependencies = [
|
||||
{ name = "cryptography" },
|
||||
{ name = "deprecation" },
|
||||
{ name = "lance-namespace" },
|
||||
{ name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" },
|
||||
@@ -1958,7 +1801,7 @@ embeddings = [
|
||||
{ name = "botocore" },
|
||||
{ name = "cohere" },
|
||||
{ name = "colpali-engine" },
|
||||
{ name = "google-generativeai" },
|
||||
{ name = "google-genai" },
|
||||
{ name = "huggingface-hub" },
|
||||
{ name = "ibm-watsonx-ai", version = "1.3.42", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" },
|
||||
{ name = "ibm-watsonx-ai", version = "1.5.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.11'" },
|
||||
@@ -2008,10 +1851,11 @@ requires-dist = [
|
||||
{ name = "botocore", marker = "extra == 'embeddings'", specifier = ">=1.31.57" },
|
||||
{ name = "cohere", marker = "extra == 'embeddings'", specifier = ">=4.0" },
|
||||
{ name = "colpali-engine", marker = "extra == 'embeddings'", specifier = ">=0.3.10" },
|
||||
{ name = "cryptography", specifier = "==46.0.7" },
|
||||
{ name = "datafusion", marker = "extra == 'tests'", specifier = ">=52,<53" },
|
||||
{ name = "deprecation", specifier = ">=2.1.0" },
|
||||
{ name = "duckdb", marker = "extra == 'tests'", specifier = ">=0.9.0" },
|
||||
{ name = "google-generativeai", marker = "extra == 'embeddings'", specifier = ">=0.3.0" },
|
||||
{ name = "google-genai", marker = "extra == 'embeddings'", specifier = ">=1.0.0" },
|
||||
{ name = "huggingface-hub", marker = "extra == 'embeddings'", specifier = ">=0.19.0" },
|
||||
{ name = "ibm-watsonx-ai", marker = "python_full_version >= '3.10' and extra == 'embeddings'", specifier = ">=1.1.2" },
|
||||
{ name = "instructorembedding", marker = "extra == 'embeddings'", specifier = ">=1.0.1" },
|
||||
@@ -2036,8 +1880,8 @@ requires-dist = [
|
||||
{ name = "pyarrow", specifier = ">=16" },
|
||||
{ name = "pyarrow-stubs", marker = "extra == 'tests'", specifier = ">=16.0" },
|
||||
{ name = "pydantic", specifier = ">=1.10" },
|
||||
{ name = "pylance", marker = "extra == 'pylance'", specifier = ">=4.0.0b7" },
|
||||
{ name = "pylance", marker = "extra == 'tests'", specifier = ">=4.0.0b7" },
|
||||
{ name = "pylance", marker = "extra == 'pylance'", specifier = ">=5.0.0b5" },
|
||||
{ name = "pylance", marker = "extra == 'tests'", specifier = ">=5.0.0b5" },
|
||||
{ name = "pyright", marker = "extra == 'dev'", specifier = ">=1.1.350" },
|
||||
{ name = "pytest", marker = "extra == 'tests'", specifier = ">=7.0" },
|
||||
{ name = "pytest-asyncio", marker = "extra == 'tests'", specifier = ">=0.21" },
|
||||
@@ -3439,32 +3283,6 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/5b/5a/bc7b4a4ef808fa59a816c17b20c4bef6884daebbdf627ff2a161da67da19/propcache-0.4.1-py3-none-any.whl", hash = "sha256:af2a6052aeb6cf17d3e46ee169099044fd8224cbaf75c76a2ef596e8163e2237", size = 13305, upload-time = "2025-10-08T19:49:00.792Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "proto-plus"
|
||||
version = "1.27.1"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "protobuf" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/3a/02/8832cde80e7380c600fbf55090b6ab7b62bd6825dbedde6d6657c15a1f8e/proto_plus-1.27.1.tar.gz", hash = "sha256:912a7460446625b792f6448bade9e55cd4e41e6ac10e27009ef71a7f317fa147", size = 56929, upload-time = "2026-02-02T17:34:49.035Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/5d/79/ac273cbbf744691821a9cca88957257f41afe271637794975ca090b9588b/proto_plus-1.27.1-py3-none-any.whl", hash = "sha256:e4643061f3a4d0de092d62aa4ad09fa4756b2cbb89d4627f3985018216f9fefc", size = 50480, upload-time = "2026-02-02T17:34:47.339Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "protobuf"
|
||||
version = "5.29.6"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/7e/57/394a763c103e0edf87f0938dafcd918d53b4c011dfc5c8ae80f3b0452dbb/protobuf-5.29.6.tar.gz", hash = "sha256:da9ee6a5424b6b30fd5e45c5ea663aef540ca95f9ad99d1e887e819cdf9b8723", size = 425623, upload-time = "2026-02-04T22:54:40.584Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/d4/88/9ee58ff7863c479d6f8346686d4636dd4c415b0cbeed7a6a7d0617639c2a/protobuf-5.29.6-cp310-abi3-win32.whl", hash = "sha256:62e8a3114992c7c647bce37dcc93647575fc52d50e48de30c6fcb28a6a291eb1", size = 423357, upload-time = "2026-02-04T22:54:25.805Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/1c/66/2dc736a4d576847134fb6d80bd995c569b13cdc7b815d669050bf0ce2d2c/protobuf-5.29.6-cp310-abi3-win_amd64.whl", hash = "sha256:7e6ad413275be172f67fdee0f43484b6de5a904cc1c3ea9804cb6fe2ff366eda", size = 435175, upload-time = "2026-02-04T22:54:28.592Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/06/db/49b05966fd208ae3f44dcd33837b6243b4915c57561d730a43f881f24dea/protobuf-5.29.6-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:b5a169e664b4057183a34bdc424540e86eea47560f3c123a0d64de4e137f9269", size = 418619, upload-time = "2026-02-04T22:54:30.266Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/b7/d7/48cbf6b0c3c39761e47a99cb483405f0fde2be22cf00d71ef316ce52b458/protobuf-5.29.6-cp38-abi3-manylinux2014_aarch64.whl", hash = "sha256:a8866b2cff111f0f863c1b3b9e7572dc7eaea23a7fae27f6fc613304046483e6", size = 320284, upload-time = "2026-02-04T22:54:31.782Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/e3/dd/cadd6ec43069247d91f6345fa7a0d2858bef6af366dbd7ba8f05d2c77d3b/protobuf-5.29.6-cp38-abi3-manylinux2014_x86_64.whl", hash = "sha256:e3387f44798ac1106af0233c04fb8abf543772ff241169946f698b3a9a3d3ab9", size = 320478, upload-time = "2026-02-04T22:54:32.909Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/5a/cb/e3065b447186cb70aa65acc70c86baf482d82bf75625bf5a2c4f6919c6a3/protobuf-5.29.6-py3-none-any.whl", hash = "sha256:6b9edb641441b2da9fa8f428760fc136a49cf97a52076010cf22a2ff73438a86", size = 173126, upload-time = "2026-02-04T22:54:39.462Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "psutil"
|
||||
version = "7.2.2"
|
||||
@@ -3768,7 +3586,7 @@ crypto = [
|
||||
|
||||
[[package]]
|
||||
name = "pylance"
|
||||
version = "4.0.0"
|
||||
version = "7.0.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "lance-namespace" },
|
||||
@@ -3777,12 +3595,12 @@ dependencies = [
|
||||
{ name = "pyarrow" },
|
||||
]
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/19/29/5152da1261a628c293876917b6185538bd68f4cf1420da6265b5be79d09b/pylance-4.0.0-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:7310892f3089eeddb1af1fe5c398b71cc483a3015646caceaa2f62fc92b227b2", size = 54420876, upload-time = "2026-03-30T18:18:37.525Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/99/ae/7edbbfc18c3be43eedb886e74a17826c09fdf35588b35912f2733779ea43/pylance-4.0.0-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:57f6a521b1b4b77a62d791850213a854093719c7d76b9641e8abcd445eb73e56", size = 56752552, upload-time = "2026-03-30T18:24:21.331Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ef/88/6d8bda83224bac52806f09d3e211d8886b81500384948a753c4b24c11f35/pylance-4.0.0-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e433d6bddd66de99c58e472bc3e8ed1590c7ff4ff7948479254c1c2111a601a8", size = 60305704, upload-time = "2026-03-30T18:35:23.425Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/52/f3/8d8369c756c4173ea070f6964213f9b622ac278bd04a058c48d00a549177/pylance-4.0.0-cp39-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:f36dce83c11cd5d598cb0f64bad7c51fc21ed43df868b9029184a385c6bf4d84", size = 56771233, upload-time = "2026-03-30T18:25:40.012Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/66/e6/53e0713440685b1c76e20d72755eca2e531cc182ea9a612b4cb6a15abe50/pylance-4.0.0-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:9ca03f97f22e0b75f06378c4006d587aba26408122fd066f0e43e2b7a019c67e", size = 60260813, upload-time = "2026-03-30T18:36:07.976Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/1e/04/5f22b88c8965d3982f68f67bfe24d756e7b788e10392d2bec6f97f5eb0e3/pylance-4.0.0-cp39-abi3-win_amd64.whl", hash = "sha256:9261c32d3bd6aaab33025a45b20c2f2554804e1bc2a1ec2bfcb06f0c9d2e59b9", size = 65137830, upload-time = "2026-03-30T18:37:33.048Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ac/ad/2f64921bf346e7075aef24a72595db44821724a3d89a9a92dd24e79632aa/pylance-7.0.0-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:98422021975be76e72b1572f41b8c9abb3bee5bdc9bfa5e9ce731110a65ed4d1", size = 62134146, upload-time = "2026-05-27T21:59:37.459Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/73/1c/c5a01bee0160b55d9a98895cbd33091d038f0a0995b121ab72e629008d02/pylance-7.0.0-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4bec86ee5b6fbd8bfc493e653f0a1fba0303cfe5492b9b46fc25ab908edc7183", size = 65373684, upload-time = "2026-05-27T22:04:01.584Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/eb/da/1fe8b8f7dbfe734d76af76acc994fc360a0d0c79a4874ef69f5a72a58fe3/pylance-7.0.0-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:881491432c53184e52f8d1db8d5f872f39a03f36fb104bec77b33d379519d8b5", size = 69458555, upload-time = "2026-05-27T22:16:50.567Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/76/f0/dd505cf3fd0226ab9d94759acd713125af1d3bfacfd80bbd52e3b9f89509/pylance-7.0.0-cp39-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:18453999e7fff4f76b16d6b7882c9df0628bd142ff95e2461bd7dd5ee3fe0af3", size = 65394430, upload-time = "2026-05-27T22:05:30.923Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/17/ba/2357b81034f28eb00790e258ed140289a6a887a7468ca9df6349fd186b27/pylance-7.0.0-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:04a58051d408c60fe76d41a220dcaf8fea8fb6d1aa0ca78a709b60bc3cc8d19a", size = 69473470, upload-time = "2026-05-27T22:17:18.935Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/1f/ec/5c00b6303a67d787f9475141832cbdc513d674ac3dcaeef8a7b169905e65/pylance-7.0.0-cp39-abi3-win_amd64.whl", hash = "sha256:467d4864af047eaab4e1370e2f1e88e2c6f507c079874421116cb41d78bc3629", size = 74792863, upload-time = "2026-05-27T22:19:23.875Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -3798,15 +3616,6 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/40/6d/b6ee155462a0156b94312bdd82d2b92ea56e909740045a87ccb98bf52405/pymdown_extensions-10.20.1-py3-none-any.whl", hash = "sha256:24af7feacbca56504b313b7b418c4f5e1317bb5fea60f03d57be7fcc40912aa0", size = 268768, upload-time = "2026-01-24T05:56:54.537Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pyparsing"
|
||||
version = "3.3.2"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/f3/91/9c6ee907786a473bf81c5f53cf703ba0957b23ab84c264080fb5a450416f/pyparsing-3.3.2.tar.gz", hash = "sha256:c777f4d763f140633dcb6d8a3eda953bf7a214dc4eff598413c070bcdc117cbc", size = 6851574, upload-time = "2026-01-21T03:57:59.36Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/10/bd/c038d7cc38edc1aa5bf91ab8068b63d4308c66c4c8bb3cbba7dfbc049f9c/pyparsing-3.3.2-py3-none-any.whl", hash = "sha256:850ba148bd908d7e2411587e247a1e4f0327839c40e2e5e6d05a007ecc69911d", size = 122781, upload-time = "2026-01-21T03:57:55.912Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pyright"
|
||||
version = "1.1.408"
|
||||
@@ -4777,6 +4586,15 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/40/44/4a5f08c96eb108af5cb50b41f76142f0afa346dfa99d5296fe7202a11854/tabulate-0.9.0-py3-none-any.whl", hash = "sha256:024ca478df22e9340661486f85298cff5f6dcdba14f3813e8830015b9ed1948f", size = 35252, upload-time = "2022-10-06T17:21:44.262Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "tenacity"
|
||||
version = "9.1.4"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/47/c6/ee486fd809e357697ee8a44d3d69222b344920433d3b6666ccd9b374630c/tenacity-9.1.4.tar.gz", hash = "sha256:adb31d4c263f2bd041081ab33b498309a57c77f9acf2db65aadf0898179cf93a", size = 49413, upload-time = "2026-02-07T10:45:33.841Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/d7/c1/eb8f9debc45d3b7918a32ab756658a0904732f75e555402972246b0b8e71/tenacity-9.1.4-py3-none-any.whl", hash = "sha256:6095a360c919085f28c6527de529e76a06ad89b23659fa881ae0649b867a9d55", size = 28926, upload-time = "2026-02-07T10:45:32.24Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "threadpoolctl"
|
||||
version = "3.6.0"
|
||||
@@ -5102,15 +4920,6 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/c7/b0/003792df09decd6849a5e39c28b513c06e84436a54440380862b5aeff25d/tzdata-2025.3-py2.py3-none-any.whl", hash = "sha256:06a47e5700f3081aab02b2e513160914ff0694bce9947d6b76ebd6bf57cfc5d1", size = 348521, upload-time = "2025-12-13T17:45:33.889Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "uritemplate"
|
||||
version = "4.2.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/98/60/f174043244c5306c9988380d2cb10009f91563fc4b31293d27e17201af56/uritemplate-4.2.0.tar.gz", hash = "sha256:480c2ed180878955863323eea31b0ede668795de182617fef9c6ca09e6ec9d0e", size = 33267, upload-time = "2025-06-02T15:12:06.318Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/a9/99/3ae339466c9183ea5b8ae87b34c0b897eda475d2aec2307cae60e5cd4f29/uritemplate-4.2.0-py3-none-any.whl", hash = "sha256:962201ba1c4edcab02e60f9a0d3821e82dfc5d2d6662a21abd533879bdb8a686", size = 11488, upload-time = "2025-06-02T15:12:03.405Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "urllib3"
|
||||
version = "2.6.3"
|
||||
@@ -5185,6 +4994,74 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/f4/24/2a3e3df732393fed8b3ebf2ec078f05546de641fe1b667ee316ec1dcf3b7/webencodings-0.5.1-py2.py3-none-any.whl", hash = "sha256:a0af1213f3c2226497a97e2b3aa01a7e4bee4f403f95be16fc9acd2947514a78", size = 11774, upload-time = "2017-04-05T20:21:32.581Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "websockets"
|
||||
version = "16.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/04/24/4b2031d72e840ce4c1ccb255f693b15c334757fc50023e4db9537080b8c4/websockets-16.0.tar.gz", hash = "sha256:5f6261a5e56e8d5c42a4497b364ea24d94d9563e8fbd44e78ac40879c60179b5", size = 179346, upload-time = "2026-01-10T09:23:47.181Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/20/74/221f58decd852f4b59cc3354cccaf87e8ef695fede361d03dc9a7396573b/websockets-16.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:04cdd5d2d1dacbad0a7bf36ccbcd3ccd5a30ee188f2560b7a62a30d14107b31a", size = 177343, upload-time = "2026-01-10T09:22:21.28Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/19/0f/22ef6107ee52ab7f0b710d55d36f5a5d3ef19e8a205541a6d7ffa7994e5a/websockets-16.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:8ff32bb86522a9e5e31439a58addbb0166f0204d64066fb955265c4e214160f0", size = 175021, upload-time = "2026-01-10T09:22:22.696Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/10/40/904a4cb30d9b61c0e278899bf36342e9b0208eb3c470324a9ecbaac2a30f/websockets-16.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:583b7c42688636f930688d712885cf1531326ee05effd982028212ccc13e5957", size = 175320, upload-time = "2026-01-10T09:22:23.94Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/9d/2f/4b3ca7e106bc608744b1cdae041e005e446124bebb037b18799c2d356864/websockets-16.0-cp310-cp310-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:7d837379b647c0c4c2355c2499723f82f1635fd2c26510e1f587d89bc2199e72", size = 183815, upload-time = "2026-01-10T09:22:25.469Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/86/26/d40eaa2a46d4302becec8d15b0fc5e45bdde05191e7628405a19cf491ccd/websockets-16.0-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:df57afc692e517a85e65b72e165356ed1df12386ecb879ad5693be08fac65dde", size = 185054, upload-time = "2026-01-10T09:22:27.101Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/b0/ba/6500a0efc94f7373ee8fefa8c271acdfd4dca8bd49a90d4be7ccabfc397e/websockets-16.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:2b9f1e0d69bc60a4a87349d50c09a037a2607918746f07de04df9e43252c77a3", size = 184565, upload-time = "2026-01-10T09:22:28.293Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/04/b4/96bf2cee7c8d8102389374a2616200574f5f01128d1082f44102140344cc/websockets-16.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:335c23addf3d5e6a8633f9f8eda77efad001671e80b95c491dd0924587ece0b3", size = 183848, upload-time = "2026-01-10T09:22:30.394Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/02/8e/81f40fb00fd125357814e8c3025738fc4ffc3da4b6b4a4472a82ba304b41/websockets-16.0-cp310-cp310-win32.whl", hash = "sha256:37b31c1623c6605e4c00d466c9d633f9b812ea430c11c8a278774a1fde1acfa9", size = 178249, upload-time = "2026-01-10T09:22:32.083Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/b4/5f/7e40efe8df57db9b91c88a43690ac66f7b7aa73a11aa6a66b927e44f26fa/websockets-16.0-cp310-cp310-win_amd64.whl", hash = "sha256:8e1dab317b6e77424356e11e99a432b7cb2f3ec8c5ab4dabbcee6add48f72b35", size = 178685, upload-time = "2026-01-10T09:22:33.345Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/f2/db/de907251b4ff46ae804ad0409809504153b3f30984daf82a1d84a9875830/websockets-16.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:31a52addea25187bde0797a97d6fc3d2f92b6f72a9370792d65a6e84615ac8a8", size = 177340, upload-time = "2026-01-10T09:22:34.539Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/f3/fa/abe89019d8d8815c8781e90d697dec52523fb8ebe308bf11664e8de1877e/websockets-16.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:417b28978cdccab24f46400586d128366313e8a96312e4b9362a4af504f3bbad", size = 175022, upload-time = "2026-01-10T09:22:36.332Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/58/5d/88ea17ed1ded2079358b40d31d48abe90a73c9e5819dbcde1606e991e2ad/websockets-16.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:af80d74d4edfa3cb9ed973a0a5ba2b2a549371f8a741e0800cb07becdd20f23d", size = 175319, upload-time = "2026-01-10T09:22:37.602Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/d2/ae/0ee92b33087a33632f37a635e11e1d99d429d3d323329675a6022312aac2/websockets-16.0-cp311-cp311-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:08d7af67b64d29823fed316505a89b86705f2b7981c07848fb5e3ea3020c1abe", size = 184631, upload-time = "2026-01-10T09:22:38.789Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c8/c5/27178df583b6c5b31b29f526ba2da5e2f864ecc79c99dae630a85d68c304/websockets-16.0-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:7be95cfb0a4dae143eaed2bcba8ac23f4892d8971311f1b06f3c6b78952ee70b", size = 185870, upload-time = "2026-01-10T09:22:39.893Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/87/05/536652aa84ddc1c018dbb7e2c4cbcd0db884580bf8e95aece7593fde526f/websockets-16.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:d6297ce39ce5c2e6feb13c1a996a2ded3b6832155fcfc920265c76f24c7cceb5", size = 185361, upload-time = "2026-01-10T09:22:41.016Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/6d/e2/d5332c90da12b1e01f06fb1b85c50cfc489783076547415bf9f0a659ec19/websockets-16.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:1c1b30e4f497b0b354057f3467f56244c603a79c0d1dafce1d16c283c25f6e64", size = 184615, upload-time = "2026-01-10T09:22:42.442Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/77/fb/d3f9576691cae9253b51555f841bc6600bf0a983a461c79500ace5a5b364/websockets-16.0-cp311-cp311-win32.whl", hash = "sha256:5f451484aeb5cafee1ccf789b1b66f535409d038c56966d6101740c1614b86c6", size = 178246, upload-time = "2026-01-10T09:22:43.654Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/54/67/eaff76b3dbaf18dcddabc3b8c1dba50b483761cccff67793897945b37408/websockets-16.0-cp311-cp311-win_amd64.whl", hash = "sha256:8d7f0659570eefb578dacde98e24fb60af35350193e4f56e11190787bee77dac", size = 178684, upload-time = "2026-01-10T09:22:44.941Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/84/7b/bac442e6b96c9d25092695578dda82403c77936104b5682307bd4deb1ad4/websockets-16.0-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:71c989cbf3254fbd5e84d3bff31e4da39c43f884e64f2551d14bb3c186230f00", size = 177365, upload-time = "2026-01-10T09:22:46.787Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/b0/fe/136ccece61bd690d9c1f715baaeefd953bb2360134de73519d5df19d29ca/websockets-16.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:8b6e209ffee39ff1b6d0fa7bfef6de950c60dfb91b8fcead17da4ee539121a79", size = 175038, upload-time = "2026-01-10T09:22:47.999Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/40/1e/9771421ac2286eaab95b8575b0cb701ae3663abf8b5e1f64f1fd90d0a673/websockets-16.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:86890e837d61574c92a97496d590968b23c2ef0aeb8a9bc9421d174cd378ae39", size = 175328, upload-time = "2026-01-10T09:22:49.809Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/18/29/71729b4671f21e1eaa5d6573031ab810ad2936c8175f03f97f3ff164c802/websockets-16.0-cp312-cp312-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:9b5aca38b67492ef518a8ab76851862488a478602229112c4b0d58d63a7a4d5c", size = 184915, upload-time = "2026-01-10T09:22:51.071Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/97/bb/21c36b7dbbafc85d2d480cd65df02a1dc93bf76d97147605a8e27ff9409d/websockets-16.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:e0334872c0a37b606418ac52f6ab9cfd17317ac26365f7f65e203e2d0d0d359f", size = 186152, upload-time = "2026-01-10T09:22:52.224Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/4a/34/9bf8df0c0cf88fa7bfe36678dc7b02970c9a7d5e065a3099292db87b1be2/websockets-16.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:a0b31e0b424cc6b5a04b8838bbaec1688834b2383256688cf47eb97412531da1", size = 185583, upload-time = "2026-01-10T09:22:53.443Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/47/88/4dd516068e1a3d6ab3c7c183288404cd424a9a02d585efbac226cb61ff2d/websockets-16.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:485c49116d0af10ac698623c513c1cc01c9446c058a4e61e3bf6c19dff7335a2", size = 184880, upload-time = "2026-01-10T09:22:55.033Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/91/d6/7d4553ad4bf1c0421e1ebd4b18de5d9098383b5caa1d937b63df8d04b565/websockets-16.0-cp312-cp312-win32.whl", hash = "sha256:eaded469f5e5b7294e2bdca0ab06becb6756ea86894a47806456089298813c89", size = 178261, upload-time = "2026-01-10T09:22:56.251Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c3/f0/f3a17365441ed1c27f850a80b2bc680a0fa9505d733fe152fdf5e98c1c0b/websockets-16.0-cp312-cp312-win_amd64.whl", hash = "sha256:5569417dc80977fc8c2d43a86f78e0a5a22fee17565d78621b6bb264a115d4ea", size = 178693, upload-time = "2026-01-10T09:22:57.478Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/cc/9c/baa8456050d1c1b08dd0ec7346026668cbc6f145ab4e314d707bb845bf0d/websockets-16.0-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:878b336ac47938b474c8f982ac2f7266a540adc3fa4ad74ae96fea9823a02cc9", size = 177364, upload-time = "2026-01-10T09:22:59.333Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/7e/0c/8811fc53e9bcff68fe7de2bcbe75116a8d959ac699a3200f4847a8925210/websockets-16.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:52a0fec0e6c8d9a784c2c78276a48a2bdf099e4ccc2a4cad53b27718dbfd0230", size = 175039, upload-time = "2026-01-10T09:23:01.171Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/aa/82/39a5f910cb99ec0b59e482971238c845af9220d3ab9fa76dd9162cda9d62/websockets-16.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:e6578ed5b6981005df1860a56e3617f14a6c307e6a71b4fff8c48fdc50f3ed2c", size = 175323, upload-time = "2026-01-10T09:23:02.341Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/bd/28/0a25ee5342eb5d5f297d992a77e56892ecb65e7854c7898fb7d35e9b33bd/websockets-16.0-cp313-cp313-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:95724e638f0f9c350bb1c2b0a7ad0e83d9cc0c9259f3ea94e40d7b02a2179ae5", size = 184975, upload-time = "2026-01-10T09:23:03.756Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/f9/66/27ea52741752f5107c2e41fda05e8395a682a1e11c4e592a809a90c6a506/websockets-16.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c0204dc62a89dc9d50d682412c10b3542d748260d743500a85c13cd1ee4bde82", size = 186203, upload-time = "2026-01-10T09:23:05.01Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/37/e5/8e32857371406a757816a2b471939d51c463509be73fa538216ea52b792a/websockets-16.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:52ac480f44d32970d66763115edea932f1c5b1312de36df06d6b219f6741eed8", size = 185653, upload-time = "2026-01-10T09:23:06.301Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/9b/67/f926bac29882894669368dc73f4da900fcdf47955d0a0185d60103df5737/websockets-16.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:6e5a82b677f8f6f59e8dfc34ec06ca6b5b48bc4fcda346acd093694cc2c24d8f", size = 184920, upload-time = "2026-01-10T09:23:07.492Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/3c/a1/3d6ccdcd125b0a42a311bcd15a7f705d688f73b2a22d8cf1c0875d35d34a/websockets-16.0-cp313-cp313-win32.whl", hash = "sha256:abf050a199613f64c886ea10f38b47770a65154dc37181bfaff70c160f45315a", size = 178255, upload-time = "2026-01-10T09:23:09.245Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/6b/ae/90366304d7c2ce80f9b826096a9e9048b4bb760e44d3b873bb272cba696b/websockets-16.0-cp313-cp313-win_amd64.whl", hash = "sha256:3425ac5cf448801335d6fdc7ae1eb22072055417a96cc6b31b3861f455fbc156", size = 178689, upload-time = "2026-01-10T09:23:10.483Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/f3/1d/e88022630271f5bd349ed82417136281931e558d628dd52c4d8621b4a0b2/websockets-16.0-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:8cc451a50f2aee53042ac52d2d053d08bf89bcb31ae799cb4487587661c038a0", size = 177406, upload-time = "2026-01-10T09:23:12.178Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/f2/78/e63be1bf0724eeb4616efb1ae1c9044f7c3953b7957799abb5915bffd38e/websockets-16.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:daa3b6ff70a9241cf6c7fc9e949d41232d9d7d26fd3522b1ad2b4d62487e9904", size = 175085, upload-time = "2026-01-10T09:23:13.511Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/bb/f4/d3c9220d818ee955ae390cf319a7c7a467beceb24f05ee7aaaa2414345ba/websockets-16.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:fd3cb4adb94a2a6e2b7c0d8d05cb94e6f1c81a0cf9dc2694fb65c7e8d94c42e4", size = 175328, upload-time = "2026-01-10T09:23:14.727Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/63/bc/d3e208028de777087e6fb2b122051a6ff7bbcca0d6df9d9c2bf1dd869ae9/websockets-16.0-cp314-cp314-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:781caf5e8eee67f663126490c2f96f40906594cb86b408a703630f95550a8c3e", size = 185044, upload-time = "2026-01-10T09:23:15.939Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ad/6e/9a0927ac24bd33a0a9af834d89e0abc7cfd8e13bed17a86407a66773cc0e/websockets-16.0-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:caab51a72c51973ca21fa8a18bd8165e1a0183f1ac7066a182ff27107b71e1a4", size = 186279, upload-time = "2026-01-10T09:23:17.148Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/b9/ca/bf1c68440d7a868180e11be653c85959502efd3a709323230314fda6e0b3/websockets-16.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:19c4dc84098e523fd63711e563077d39e90ec6702aff4b5d9e344a60cb3c0cb1", size = 185711, upload-time = "2026-01-10T09:23:18.372Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c4/f8/fdc34643a989561f217bb477cbc47a3a07212cbda91c0e4389c43c296ebf/websockets-16.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:a5e18a238a2b2249c9a9235466b90e96ae4795672598a58772dd806edc7ac6d3", size = 184982, upload-time = "2026-01-10T09:23:19.652Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/dd/d1/574fa27e233764dbac9c52730d63fcf2823b16f0856b3329fc6268d6ae4f/websockets-16.0-cp314-cp314-win32.whl", hash = "sha256:a069d734c4a043182729edd3e9f247c3b2a4035415a9172fd0f1b71658a320a8", size = 177915, upload-time = "2026-01-10T09:23:21.458Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/8a/f1/ae6b937bf3126b5134ce1f482365fde31a357c784ac51852978768b5eff4/websockets-16.0-cp314-cp314-win_amd64.whl", hash = "sha256:c0ee0e63f23914732c6d7e0cce24915c48f3f1512ec1d079ed01fc629dab269d", size = 178381, upload-time = "2026-01-10T09:23:22.715Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/06/9b/f791d1db48403e1f0a27577a6beb37afae94254a8c6f08be4a23e4930bc0/websockets-16.0-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:a35539cacc3febb22b8f4d4a99cc79b104226a756aa7400adc722e83b0d03244", size = 177737, upload-time = "2026-01-10T09:23:24.523Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/bd/40/53ad02341fa33b3ce489023f635367a4ac98b73570102ad2cdd770dacc9a/websockets-16.0-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:b784ca5de850f4ce93ec85d3269d24d4c82f22b7212023c974c401d4980ebc5e", size = 175268, upload-time = "2026-01-10T09:23:25.781Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/74/9b/6158d4e459b984f949dcbbb0c5d270154c7618e11c01029b9bbd1bb4c4f9/websockets-16.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:569d01a4e7fba956c5ae4fc988f0d4e187900f5497ce46339c996dbf24f17641", size = 175486, upload-time = "2026-01-10T09:23:27.033Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/e5/2d/7583b30208b639c8090206f95073646c2c9ffd66f44df967981a64f849ad/websockets-16.0-cp314-cp314t-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:50f23cdd8343b984957e4077839841146f67a3d31ab0d00e6b824e74c5b2f6e8", size = 185331, upload-time = "2026-01-10T09:23:28.259Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/45/b0/cce3784eb519b7b5ad680d14b9673a31ab8dcb7aad8b64d81709d2430aa8/websockets-16.0-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:152284a83a00c59b759697b7f9e9cddf4e3c7861dd0d964b472b70f78f89e80e", size = 186501, upload-time = "2026-01-10T09:23:29.449Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/19/60/b8ebe4c7e89fb5f6cdf080623c9d92789a53636950f7abacfc33fe2b3135/websockets-16.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:bc59589ab64b0022385f429b94697348a6a234e8ce22544e3681b2e9331b5944", size = 186062, upload-time = "2026-01-10T09:23:31.368Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/88/a8/a080593f89b0138b6cba1b28f8df5673b5506f72879322288b031337c0b8/websockets-16.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:32da954ffa2814258030e5a57bc73a3635463238e797c7375dc8091327434206", size = 185356, upload-time = "2026-01-10T09:23:32.627Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c2/b6/b9afed2afadddaf5ebb2afa801abf4b0868f42f8539bfe4b071b5266c9fe/websockets-16.0-cp314-cp314t-win32.whl", hash = "sha256:5a4b4cc550cb665dd8a47f868c8d04c8230f857363ad3c9caf7a0c3bf8c61ca6", size = 178085, upload-time = "2026-01-10T09:23:33.816Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/9f/3e/28135a24e384493fa804216b79a6a6759a38cc4ff59118787b9fb693df93/websockets-16.0-cp314-cp314t-win_amd64.whl", hash = "sha256:b14dc141ed6d2dde437cddb216004bcac6a1df0935d79656387bd41632ba0bbd", size = 178531, upload-time = "2026-01-10T09:23:35.016Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/72/07/c98a68571dcf256e74f1f816b8cc5eae6eb2d3d5cfa44d37f801619d9166/websockets-16.0-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:349f83cd6c9a415428ee1005cadb5c2c56f4389bc06a9af16103c3bc3dcc8b7d", size = 174947, upload-time = "2026-01-10T09:23:36.166Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/7e/52/93e166a81e0305b33fe416338be92ae863563fe7bce446b0f687b9df5aea/websockets-16.0-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:4a1aba3340a8dca8db6eb5a7986157f52eb9e436b74813764241981ca4888f03", size = 175260, upload-time = "2026-01-10T09:23:37.409Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/56/0c/2dbf513bafd24889d33de2ff0368190a0e69f37bcfa19009ef819fe4d507/websockets-16.0-pp311-pypy311_pp73-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:f4a32d1bd841d4bcbffdcb3d2ce50c09c3909fbead375ab28d0181af89fd04da", size = 176071, upload-time = "2026-01-10T09:23:39.158Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/a5/8f/aea9c71cc92bf9b6cc0f7f70df8f0b420636b6c96ef4feee1e16f80f75dd/websockets-16.0-pp311-pypy311_pp73-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0298d07ee155e2e9fda5be8a9042200dd2e3bb0b8a38482156576f863a9d457c", size = 176968, upload-time = "2026-01-10T09:23:41.031Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/9a/3f/f70e03f40ffc9a30d817eef7da1be72ee4956ba8d7255c399a01b135902a/websockets-16.0-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:a653aea902e0324b52f1613332ddf50b00c06fdaf7e92624fbf8c77c78fa5767", size = 178735, upload-time = "2026-01-10T09:23:42.259Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/6f/28/258ebab549c2bf3e64d2b0217b973467394a9cea8c42f70418ca2c5d0d2e/websockets-16.0-py3-none-any.whl", hash = "sha256:1637db62fad1dc833276dded54215f2c7fa46912301a24bd94d45d46a011ceec", size = 171598, upload-time = "2026-01-10T09:23:45.395Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "yarl"
|
||||
version = "1.22.0"
|
||||
|
||||
@@ -1,2 +1,2 @@
|
||||
[toolchain]
|
||||
channel = "1.94.0"
|
||||
channel = "1.95.0"
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "lancedb"
|
||||
version = "0.30.0-beta.0"
|
||||
version = "0.30.1-beta.0"
|
||||
edition.workspace = true
|
||||
description = "LanceDB: A serverless, low-latency vector database for AI applications"
|
||||
license.workspace = true
|
||||
@@ -75,7 +75,7 @@ reqwest = { version = "0.12.0", default-features = false, features = [
|
||||
"stream",
|
||||
], optional = true }
|
||||
http = { version = "1", optional = true } # Matching what is in reqwest
|
||||
uuid = { version = "1.7.0", features = ["v4"] }
|
||||
uuid = { version = "1.7.0", features = ["v4", "v5"] }
|
||||
polars-arrow = { version = ">=0.37,<0.40.0", optional = true }
|
||||
polars = { version = ">=0.37,<0.40.0", optional = true }
|
||||
hf-hub = { version = "0.4.1", optional = true, default-features = false, features = [
|
||||
@@ -104,6 +104,7 @@ datafusion.workspace = true
|
||||
http-body = "1" # Matching reqwest
|
||||
rstest = "0.23.0"
|
||||
test-log = "0.2"
|
||||
serial_test = "3"
|
||||
|
||||
|
||||
[features]
|
||||
|
||||
@@ -812,8 +812,7 @@ impl ConnectBuilder {
|
||||
self
|
||||
}
|
||||
|
||||
/// The interval at which to check for updates from other processes. This
|
||||
/// only affects LanceDB OSS.
|
||||
/// The interval at which to check for updates from other processes.
|
||||
///
|
||||
/// If left unset, consistency is not checked. For maximum read
|
||||
/// performance, this is the default. For strong consistency, set this to
|
||||
@@ -825,8 +824,11 @@ impl ConnectBuilder {
|
||||
/// This only affects read operations. Write operations are always
|
||||
/// consistent.
|
||||
///
|
||||
/// LanceDB Cloud uses eventual consistency under the hood, and is not
|
||||
/// currently configurable.
|
||||
/// # Cost
|
||||
///
|
||||
/// Stronger consistency is not free. The smaller the interval, the more
|
||||
/// often each read pays the cost of checking for updates against object
|
||||
/// storage, raising per-read latency and cost.
|
||||
pub fn read_consistency_interval(
|
||||
mut self,
|
||||
read_consistency_interval: std::time::Duration,
|
||||
@@ -886,6 +888,7 @@ impl ConnectBuilder {
|
||||
options.host_override,
|
||||
self.request.client_config,
|
||||
storage_options.into(),
|
||||
self.request.read_consistency_interval,
|
||||
)?);
|
||||
Ok(Connection {
|
||||
internal,
|
||||
|
||||
@@ -464,11 +464,9 @@ mod tests {
|
||||
let mut iter = ids.into_iter().map(|o| o.unwrap());
|
||||
while let Some(first) = iter.next() {
|
||||
let rows_left_in_clump = if first == 4470 { 19 } else { 29 };
|
||||
let mut expected_next = first + 1;
|
||||
for _ in 0..rows_left_in_clump {
|
||||
for expected_next in (first + 1)..=(first + rows_left_in_clump) {
|
||||
let next = iter.next().unwrap();
|
||||
assert_eq!(next, expected_next);
|
||||
expected_next += 1;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -245,6 +245,9 @@ pub struct RestfulLanceDbClient<S: HttpSend = Sender> {
|
||||
pub(crate) sender: S,
|
||||
pub(crate) id_delimiter: String,
|
||||
pub(crate) header_provider: Option<Arc<dyn HeaderProvider>>,
|
||||
/// Connection-level read consistency interval. Drives the
|
||||
/// `x-lancedb-min-timestamp` freshness header sent on read requests.
|
||||
pub(crate) read_consistency_interval: Option<Duration>,
|
||||
}
|
||||
|
||||
impl<S: HttpSend> std::fmt::Debug for RestfulLanceDbClient<S> {
|
||||
@@ -338,6 +341,7 @@ impl RestfulLanceDbClient<Sender> {
|
||||
host_override: Option<String>,
|
||||
default_headers: HeaderMap,
|
||||
client_config: ClientConfig,
|
||||
read_consistency_interval: Option<Duration>,
|
||||
) -> Result<Self> {
|
||||
// Get the timeouts
|
||||
let timeout =
|
||||
@@ -435,6 +439,7 @@ impl RestfulLanceDbClient<Sender> {
|
||||
.clone()
|
||||
.unwrap_or("$".to_string()),
|
||||
header_provider: client_config.header_provider,
|
||||
read_consistency_interval,
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -840,6 +845,16 @@ pub mod test_utils {
|
||||
pub fn client_with_handler<T>(
|
||||
handler: impl Fn(reqwest::Request) -> http::response::Response<T> + Send + Sync + 'static,
|
||||
) -> RestfulLanceDbClient<MockSender>
|
||||
where
|
||||
T: Into<reqwest::Body>,
|
||||
{
|
||||
client_with_handler_and_interval(handler, None)
|
||||
}
|
||||
|
||||
pub fn client_with_handler_and_interval<T>(
|
||||
handler: impl Fn(reqwest::Request) -> http::response::Response<T> + Send + Sync + 'static,
|
||||
read_consistency_interval: Option<Duration>,
|
||||
) -> RestfulLanceDbClient<MockSender>
|
||||
where
|
||||
T: Into<reqwest::Body>,
|
||||
{
|
||||
@@ -857,6 +872,7 @@ pub mod test_utils {
|
||||
},
|
||||
id_delimiter: "$".to_string(),
|
||||
header_provider: None,
|
||||
read_consistency_interval,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -881,6 +897,7 @@ pub mod test_utils {
|
||||
},
|
||||
id_delimiter: config.id_delimiter.unwrap_or_else(|| "$".to_string()),
|
||||
header_provider: config.header_provider,
|
||||
read_consistency_interval: None,
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -888,8 +905,18 @@ pub mod test_utils {
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use serial_test::serial;
|
||||
use std::time::Duration;
|
||||
|
||||
// Serializes the env-var-mutating tests below: cargo test runs tests in
|
||||
// parallel, but several of these tests read and write the same process-
|
||||
// global env vars (`LANCEDB_USER_ID*`), so they would race without this.
|
||||
static ENV_MUTEX: std::sync::Mutex<()> = std::sync::Mutex::new(());
|
||||
|
||||
fn lock_env() -> std::sync::MutexGuard<'static, ()> {
|
||||
ENV_MUTEX.lock().unwrap_or_else(|e| e.into_inner())
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_timeout_config_default() {
|
||||
let config = TimeoutConfig::default();
|
||||
@@ -1046,6 +1073,7 @@ mod tests {
|
||||
sender: Sender,
|
||||
id_delimiter: "+".to_string(),
|
||||
header_provider: Some(Arc::new(provider) as Arc<dyn HeaderProvider>),
|
||||
read_consistency_interval: None,
|
||||
};
|
||||
|
||||
// Apply dynamic headers
|
||||
@@ -1081,6 +1109,7 @@ mod tests {
|
||||
sender: Sender,
|
||||
id_delimiter: "+".to_string(),
|
||||
header_provider: Some(Arc::new(provider) as Arc<dyn HeaderProvider>),
|
||||
read_consistency_interval: None,
|
||||
};
|
||||
|
||||
// Apply dynamic headers
|
||||
@@ -1118,6 +1147,7 @@ mod tests {
|
||||
sender: Sender,
|
||||
id_delimiter: "+".to_string(),
|
||||
header_provider: Some(Arc::new(provider) as Arc<dyn HeaderProvider>),
|
||||
read_consistency_interval: None,
|
||||
};
|
||||
|
||||
// Header provider errors should fail the request
|
||||
@@ -1143,7 +1173,9 @@ mod tests {
|
||||
}
|
||||
|
||||
#[test]
|
||||
#[serial(user_id_env)]
|
||||
fn test_resolve_user_id_none() {
|
||||
let _guard = lock_env();
|
||||
let config = ClientConfig::default();
|
||||
// Clear env vars that might be set from other tests
|
||||
// SAFETY: This is only called in tests
|
||||
@@ -1155,7 +1187,9 @@ mod tests {
|
||||
}
|
||||
|
||||
#[test]
|
||||
#[serial(user_id_env)]
|
||||
fn test_resolve_user_id_from_env() {
|
||||
let _guard = lock_env();
|
||||
// SAFETY: This is only called in tests
|
||||
unsafe {
|
||||
std::env::set_var("LANCEDB_USER_ID", "env-user-id");
|
||||
@@ -1169,7 +1203,9 @@ mod tests {
|
||||
}
|
||||
|
||||
#[test]
|
||||
#[serial(user_id_env)]
|
||||
fn test_resolve_user_id_from_env_key() {
|
||||
let _guard = lock_env();
|
||||
// SAFETY: This is only called in tests
|
||||
unsafe {
|
||||
std::env::remove_var("LANCEDB_USER_ID");
|
||||
@@ -1189,7 +1225,9 @@ mod tests {
|
||||
}
|
||||
|
||||
#[test]
|
||||
#[serial(user_id_env)]
|
||||
fn test_resolve_user_id_direct_takes_precedence() {
|
||||
let _guard = lock_env();
|
||||
// SAFETY: This is only called in tests
|
||||
unsafe {
|
||||
std::env::set_var("LANCEDB_USER_ID", "env-user-id");
|
||||
@@ -1206,7 +1244,9 @@ mod tests {
|
||||
}
|
||||
|
||||
#[test]
|
||||
#[serial(user_id_env)]
|
||||
fn test_resolve_user_id_empty_env_ignored() {
|
||||
let _guard = lock_env();
|
||||
// SAFETY: This is only called in tests
|
||||
unsafe {
|
||||
std::env::set_var("LANCEDB_USER_ID", "");
|
||||
|
||||
@@ -206,6 +206,7 @@ impl RemoteDatabase {
|
||||
host_override: Option<String>,
|
||||
client_config: ClientConfig,
|
||||
options: RemoteOptions,
|
||||
read_consistency_interval: Option<std::time::Duration>,
|
||||
) -> Result<Self> {
|
||||
let parsed = super::client::parse_db_url(uri)?;
|
||||
let header_map = RestfulLanceDbClient::<Sender>::default_headers(
|
||||
@@ -233,6 +234,7 @@ impl RemoteDatabase {
|
||||
host_override,
|
||||
header_map,
|
||||
client_config.clone(),
|
||||
read_consistency_interval,
|
||||
)?;
|
||||
|
||||
let table_cache = Cache::builder()
|
||||
|
||||
@@ -25,7 +25,7 @@ use crate::table::MergeResult;
|
||||
use crate::table::Tags;
|
||||
use crate::table::UpdateResult;
|
||||
use crate::table::query::create_multi_vector_plan;
|
||||
use crate::table::{AnyQuery, Filter, PreprocessingOutput, TableStatistics};
|
||||
use crate::table::{AnyQuery, Filter, Predicate, PreprocessingOutput, TableStatistics};
|
||||
use crate::utils::background_cache::BackgroundCache;
|
||||
use crate::utils::{
|
||||
resolve_arrow_field_path, supported_btree_data_type, supported_vector_data_type,
|
||||
@@ -62,15 +62,76 @@ use std::collections::HashMap;
|
||||
use std::io::Cursor;
|
||||
use std::pin::Pin;
|
||||
use std::sync::{Arc, Mutex};
|
||||
use std::time::Duration;
|
||||
use std::time::{Duration, SystemTime};
|
||||
use tokio::sync::RwLock;
|
||||
|
||||
const REQUEST_TIMEOUT_HEADER: HeaderName = HeaderName::from_static("x-request-timeout-ms");
|
||||
const MIN_VERSION_HEADER: HeaderName = HeaderName::from_static("x-lancedb-min-version");
|
||||
const MIN_TIMESTAMP_HEADER: HeaderName = HeaderName::from_static("x-lancedb-min-timestamp");
|
||||
const METRIC_TYPE_KEY: &str = "metric_type";
|
||||
const INDEX_TYPE_KEY: &str = "index_type";
|
||||
const SCHEMA_CACHE_TTL: Duration = Duration::from_secs(30);
|
||||
const SCHEMA_CACHE_REFRESH_WINDOW: Duration = Duration::from_secs(5);
|
||||
|
||||
/// Per-table state driving the freshness headers (`x-lancedb-min-version` and
|
||||
/// `x-lancedb-min-timestamp`) sent on read requests.
|
||||
#[derive(Debug, Default, Clone, Copy)]
|
||||
struct FreshnessState {
|
||||
/// Provides read-your-write within a single handle: writes that return a
|
||||
/// version update this, and reads send it as `x-lancedb-min-version`.
|
||||
min_version: Option<u64>,
|
||||
/// Wall-clock time captured at the last [`BaseTable::checkout_latest`]
|
||||
/// call. Subsequent reads send
|
||||
/// `max(baseline, now - read_consistency_interval)` as
|
||||
/// `x-lancedb-min-timestamp`.
|
||||
///
|
||||
/// Without this, `checkout_latest()` would have no effect on subsequent
|
||||
/// reads when `read_consistency_interval` is unset (the default): a
|
||||
/// server-side cache could still serve a snapshot older than the moment
|
||||
/// the user explicitly asked for "latest". The baseline forces the
|
||||
/// server to skip any cache entry older than the checkout time, so the
|
||||
/// `checkout_latest()` signal is preserved across reads on the same
|
||||
/// handle regardless of the configured consistency interval.
|
||||
checkout_baseline: Option<SystemTime>,
|
||||
}
|
||||
|
||||
/// Snapshot of the headers that should be attached to a single read request.
|
||||
#[derive(Debug, Default, Clone, Copy)]
|
||||
struct FreshnessHeaders {
|
||||
min_version: Option<u64>,
|
||||
min_timestamp: Option<SystemTime>,
|
||||
}
|
||||
|
||||
impl FreshnessHeaders {
|
||||
fn apply(self, mut request: RequestBuilder) -> RequestBuilder {
|
||||
if let Some(v) = self.min_version {
|
||||
request = request.header(MIN_VERSION_HEADER, v.to_string());
|
||||
}
|
||||
if let Some(ts) = self.min_timestamp {
|
||||
let dt: chrono::DateTime<chrono::Utc> = ts.into();
|
||||
request = request.header(MIN_TIMESTAMP_HEADER, dt.to_rfc3339());
|
||||
}
|
||||
request
|
||||
}
|
||||
}
|
||||
|
||||
fn compute_min_timestamp(
|
||||
state: &FreshnessState,
|
||||
interval: Option<Duration>,
|
||||
now: SystemTime,
|
||||
) -> Option<SystemTime> {
|
||||
let interval_based = match interval {
|
||||
None => None,
|
||||
Some(d) if d.is_zero() => Some(now),
|
||||
Some(d) => Some(now.checked_sub(d).unwrap_or(now)),
|
||||
};
|
||||
match (interval_based, state.checkout_baseline) {
|
||||
(None, None) => None,
|
||||
(Some(t), None) | (None, Some(t)) => Some(t),
|
||||
(Some(a), Some(b)) => Some(a.max(b)),
|
||||
}
|
||||
}
|
||||
|
||||
pub struct RemoteTags<'a, S: HttpSend = Sender> {
|
||||
inner: &'a RemoteTable<S>,
|
||||
}
|
||||
@@ -80,8 +141,7 @@ impl<S: HttpSend + 'static> Tags for RemoteTags<'_, S> {
|
||||
async fn list(&self) -> Result<HashMap<String, TagContents>> {
|
||||
let request = self
|
||||
.inner
|
||||
.client
|
||||
.post(&format!("/v1/table/{}/tags/list/", self.inner.identifier));
|
||||
.post_read(&format!("/v1/table/{}/tags/list/", self.inner.identifier));
|
||||
let (request_id, response) = self.inner.send(request, true).await?;
|
||||
let response = self
|
||||
.inner
|
||||
@@ -112,48 +172,13 @@ impl<S: HttpSend + 'static> Tags for RemoteTags<'_, S> {
|
||||
}
|
||||
|
||||
async fn get_version(&self, tag: &str) -> Result<u64> {
|
||||
let request = self
|
||||
.inner
|
||||
.client
|
||||
.post(&format!(
|
||||
"/v1/table/{}/tags/version/",
|
||||
self.inner.identifier
|
||||
))
|
||||
.json(&serde_json::json!({ "tag": tag }));
|
||||
|
||||
let (request_id, response) = self.inner.send(request, true).await?;
|
||||
let response = self
|
||||
.inner
|
||||
.check_table_response(&request_id, response)
|
||||
.await?;
|
||||
|
||||
match response.text().await {
|
||||
Ok(body) => {
|
||||
let value: serde_json::Value =
|
||||
serde_json::from_str(&body).map_err(|e| Error::Http {
|
||||
source: format!("Failed to parse tag version: {}", e).into(),
|
||||
request_id: request_id.clone(),
|
||||
status_code: None,
|
||||
})?;
|
||||
|
||||
value
|
||||
.get("version")
|
||||
.and_then(|v| v.as_u64())
|
||||
.ok_or_else(|| Error::Http {
|
||||
source: format!("Invalid tag version response: {}", body).into(),
|
||||
request_id,
|
||||
status_code: None,
|
||||
})
|
||||
}
|
||||
Err(err) => {
|
||||
let status_code = err.status();
|
||||
Err(Error::Http {
|
||||
source: Box::new(err),
|
||||
request_id,
|
||||
status_code,
|
||||
})
|
||||
}
|
||||
}
|
||||
let request = self.inner.post_read(&format!(
|
||||
"/v1/table/{}/tags/version/",
|
||||
self.inner.identifier
|
||||
));
|
||||
self.inner
|
||||
.resolve_tag_version_with_request(tag, request)
|
||||
.await
|
||||
}
|
||||
|
||||
async fn create(&mut self, tag: &str, version: u64) -> Result<()> {
|
||||
@@ -215,6 +240,7 @@ pub struct RemoteTable<S: HttpSend = Sender> {
|
||||
version: RwLock<Option<u64>>,
|
||||
location: RwLock<Option<String>>,
|
||||
schema_cache: BackgroundCache<SchemaRef, Error>,
|
||||
freshness: Mutex<FreshnessState>,
|
||||
}
|
||||
|
||||
impl<S: HttpSend> std::fmt::Debug for RemoteTable<S> {
|
||||
@@ -243,6 +269,7 @@ impl<S: HttpSend> RemoteTable<S> {
|
||||
version: RwLock::new(None),
|
||||
location: RwLock::new(None),
|
||||
schema_cache: BackgroundCache::new(SCHEMA_CACHE_TTL, SCHEMA_CACHE_REFRESH_WINDOW),
|
||||
freshness: Mutex::new(FreshnessState::default()),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -252,12 +279,56 @@ impl<S: HttpSend> RemoteTable<S> {
|
||||
}
|
||||
|
||||
async fn describe_version(&self, version: Option<u64>) -> Result<TableDescription> {
|
||||
let mut request = self
|
||||
.client
|
||||
.post(&format!("/v1/table/{}/describe/", self.identifier));
|
||||
let request = self.post_read(&format!("/v1/table/{}/describe/", self.identifier));
|
||||
self.describe_with_request(request, version).await
|
||||
}
|
||||
|
||||
async fn resolve_tag_version_with_request(
|
||||
&self,
|
||||
tag: &str,
|
||||
request: RequestBuilder,
|
||||
) -> Result<u64> {
|
||||
let request = request.json(&serde_json::json!({ "tag": tag }));
|
||||
|
||||
let (request_id, response) = self.send(request, true).await?;
|
||||
let response = self.check_table_response(&request_id, response).await?;
|
||||
|
||||
match response.text().await {
|
||||
Ok(body) => {
|
||||
let value: serde_json::Value =
|
||||
serde_json::from_str(&body).map_err(|e| Error::Http {
|
||||
source: format!("Failed to parse tag version: {}", e).into(),
|
||||
request_id: request_id.clone(),
|
||||
status_code: None,
|
||||
})?;
|
||||
|
||||
value
|
||||
.get("version")
|
||||
.and_then(|v| v.as_u64())
|
||||
.ok_or_else(|| Error::Http {
|
||||
source: format!("Invalid tag version response: {}", body).into(),
|
||||
request_id,
|
||||
status_code: None,
|
||||
})
|
||||
}
|
||||
Err(err) => {
|
||||
let status_code = err.status();
|
||||
Err(Error::Http {
|
||||
source: Box::new(err),
|
||||
request_id,
|
||||
status_code,
|
||||
})
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
async fn describe_with_request(
|
||||
&self,
|
||||
request: RequestBuilder,
|
||||
version: Option<u64>,
|
||||
) -> Result<TableDescription> {
|
||||
let body = serde_json::json!({ "version": version });
|
||||
request = request.json(&body);
|
||||
let request = request.json(&body);
|
||||
|
||||
let (request_id, response) = self.send(request, true).await?;
|
||||
|
||||
@@ -711,14 +782,44 @@ impl<S: HttpSend> RemoteTable<S> {
|
||||
*read_guard
|
||||
}
|
||||
|
||||
/// Snapshot the freshness headers to attach to a single read request.
|
||||
/// Computed at call time so that retries reuse the same snapshot.
|
||||
fn snapshot_freshness_headers(&self) -> FreshnessHeaders {
|
||||
let state = *self.freshness.lock().unwrap();
|
||||
FreshnessHeaders {
|
||||
min_version: state.min_version,
|
||||
min_timestamp: compute_min_timestamp(
|
||||
&state,
|
||||
self.client.read_consistency_interval,
|
||||
SystemTime::now(),
|
||||
),
|
||||
}
|
||||
}
|
||||
|
||||
/// Build a POST request and attach the read-freshness headers
|
||||
/// (`x-lancedb-min-version`, `x-lancedb-min-timestamp`).
|
||||
fn post_read(&self, uri: &str) -> RequestBuilder {
|
||||
self.snapshot_freshness_headers()
|
||||
.apply(self.client.post(uri))
|
||||
}
|
||||
|
||||
/// Record a version returned by a write so subsequent reads can request at
|
||||
/// least that version via `x-lancedb-min-version`. A returned `0` from a
|
||||
/// backward-compatible old server is ignored.
|
||||
fn track_write_version(&self, version: u64) {
|
||||
if version == 0 {
|
||||
return;
|
||||
}
|
||||
let mut state = self.freshness.lock().unwrap();
|
||||
state.min_version = Some(state.min_version.map_or(version, |v| v.max(version)));
|
||||
}
|
||||
|
||||
async fn execute_query(
|
||||
&self,
|
||||
query: &AnyQuery,
|
||||
options: &QueryExecutionOptions,
|
||||
) -> Result<Vec<Pin<Box<dyn RecordBatchStream + Send>>>> {
|
||||
let mut request = self
|
||||
.client
|
||||
.post(&format!("/v1/table/{}/query/", self.identifier));
|
||||
let mut request = self.post_read(&format!("/v1/table/{}/query/", self.identifier));
|
||||
|
||||
if let Some(timeout) = options.timeout {
|
||||
// Also send to server, so it can abort the query if it takes too long.
|
||||
@@ -824,9 +925,10 @@ async fn fetch_schema<S: HttpSend>(
|
||||
identifier: &str,
|
||||
table_name: &str,
|
||||
version: Option<u64>,
|
||||
freshness_headers: FreshnessHeaders,
|
||||
) -> Result<SchemaRef> {
|
||||
let request = client
|
||||
.post(&format!("/v1/table/{}/describe/", identifier))
|
||||
let request = freshness_headers
|
||||
.apply(client.post(&format!("/v1/table/{}/describe/", identifier)))
|
||||
.json(&serde_json::json!({ "version": version }));
|
||||
|
||||
let (request_id, response) = client.send_with_retry(request, None, true).await?;
|
||||
@@ -874,7 +976,9 @@ mod test_utils {
|
||||
use super::*;
|
||||
use crate::remote::ClientConfig;
|
||||
use crate::remote::client::test_utils::client_with_handler;
|
||||
use crate::remote::client::test_utils::{MockSender, client_with_handler_and_config};
|
||||
use crate::remote::client::test_utils::{
|
||||
MockSender, client_with_handler_and_config, client_with_handler_and_interval,
|
||||
};
|
||||
|
||||
impl RemoteTable<MockSender> {
|
||||
pub fn new_mock<F, T>(name: String, handler: F, version: Option<semver::Version>) -> Self
|
||||
@@ -892,6 +996,30 @@ mod test_utils {
|
||||
version: RwLock::new(None),
|
||||
location: RwLock::new(None),
|
||||
schema_cache: BackgroundCache::new(SCHEMA_CACHE_TTL, SCHEMA_CACHE_REFRESH_WINDOW),
|
||||
freshness: Mutex::new(FreshnessState::default()),
|
||||
}
|
||||
}
|
||||
|
||||
pub fn new_mock_with_consistency_interval<F, T>(
|
||||
name: String,
|
||||
handler: F,
|
||||
read_consistency_interval: Option<Duration>,
|
||||
) -> Self
|
||||
where
|
||||
F: Fn(reqwest::Request) -> http::Response<T> + Send + Sync + 'static,
|
||||
T: Into<reqwest::Body>,
|
||||
{
|
||||
let client = client_with_handler_and_interval(handler, read_consistency_interval);
|
||||
Self {
|
||||
client,
|
||||
name: name.clone(),
|
||||
namespace: vec![],
|
||||
identifier: name,
|
||||
server_version: ServerVersion::default(),
|
||||
version: RwLock::new(None),
|
||||
location: RwLock::new(None),
|
||||
schema_cache: BackgroundCache::new(SCHEMA_CACHE_TTL, SCHEMA_CACHE_REFRESH_WINDOW),
|
||||
freshness: Mutex::new(FreshnessState::default()),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -923,6 +1051,7 @@ mod test_utils {
|
||||
version: RwLock::new(None),
|
||||
location: RwLock::new(None),
|
||||
schema_cache: BackgroundCache::new(SCHEMA_CACHE_TTL, SCHEMA_CACHE_REFRESH_WINDOW),
|
||||
freshness: Mutex::new(FreshnessState::default()),
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -986,6 +1115,7 @@ impl<S: HttpSend + 'static> RemoteTable<S> {
|
||||
if output.overwrite {
|
||||
self.invalidate_schema_cache();
|
||||
}
|
||||
self.track_write_version(add_result.version);
|
||||
|
||||
return Ok(add_result);
|
||||
}
|
||||
@@ -1023,6 +1153,7 @@ impl<S: HttpSend + 'static> RemoteTable<S> {
|
||||
if output.overwrite {
|
||||
self.invalidate_schema_cache();
|
||||
}
|
||||
self.track_write_version(result.version);
|
||||
return Ok(result);
|
||||
}
|
||||
Err(e) => {
|
||||
@@ -1139,8 +1270,13 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
|
||||
self.describe().await.map(|desc| desc.version)
|
||||
}
|
||||
async fn checkout(&self, version: u64) -> Result<()> {
|
||||
// check that the version exists
|
||||
self.describe_version(Some(version))
|
||||
// Validate the version exists. The describe is sent without freshness
|
||||
// headers so a stale `min_version` from a previous write doesn't ride
|
||||
// along on an explicit time-travel request.
|
||||
let request = self
|
||||
.client
|
||||
.post(&format!("/v1/table/{}/describe/", self.identifier));
|
||||
self.describe_with_request(request, Some(version))
|
||||
.await
|
||||
.map_err(|e| match e {
|
||||
// try to map the error to a more user-friendly error telling them
|
||||
@@ -1156,6 +1292,10 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
|
||||
*write_guard = Some(version);
|
||||
drop(write_guard);
|
||||
|
||||
// Explicit time-travel: drop any read-your-write / freshness
|
||||
// constraints so the user sees exactly the requested version.
|
||||
*self.freshness.lock().unwrap() = FreshnessState::default();
|
||||
|
||||
// Invalidate schema cache since we're switching versions
|
||||
self.invalidate_schema_cache();
|
||||
|
||||
@@ -1166,6 +1306,13 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
|
||||
*write_guard = None;
|
||||
drop(write_guard);
|
||||
|
||||
// Drop any per-handle write tracking; subsequent reads use the
|
||||
// baseline timestamp captured now to guarantee freshness.
|
||||
*self.freshness.lock().unwrap() = FreshnessState {
|
||||
min_version: None,
|
||||
checkout_baseline: Some(SystemTime::now()),
|
||||
};
|
||||
|
||||
// Invalidate schema cache since we're switching versions
|
||||
self.invalidate_schema_cache();
|
||||
|
||||
@@ -1186,9 +1333,7 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
|
||||
}
|
||||
|
||||
async fn list_versions(&self) -> Result<Vec<Version>> {
|
||||
let request = self
|
||||
.client
|
||||
.post(&format!("/v1/table/{}/version/list/", self.identifier));
|
||||
let request = self.post_read(&format!("/v1/table/{}/version/list/", self.identifier));
|
||||
let (request_id, response) = self.send(request, true).await?;
|
||||
let response = self.check_table_response(&request_id, response).await?;
|
||||
|
||||
@@ -1221,19 +1366,25 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
|
||||
let client = self.client.clone();
|
||||
let identifier = self.identifier.clone();
|
||||
let table_name = self.name.clone();
|
||||
let freshness_headers = self.snapshot_freshness_headers();
|
||||
|
||||
self.schema_cache
|
||||
.get(move || async move {
|
||||
fetch_schema(&client, &identifier, &table_name, version).await
|
||||
fetch_schema(
|
||||
&client,
|
||||
&identifier,
|
||||
&table_name,
|
||||
version,
|
||||
freshness_headers,
|
||||
)
|
||||
.await
|
||||
})
|
||||
.await
|
||||
.map_err(unwrap_shared_error)
|
||||
}
|
||||
|
||||
async fn count_rows(&self, filter: Option<Filter>) -> Result<usize> {
|
||||
let mut request = self
|
||||
.client
|
||||
.post(&format!("/v1/table/{}/count_rows/", self.identifier));
|
||||
let mut request = self.post_read(&format!("/v1/table/{}/count_rows/", self.identifier));
|
||||
|
||||
let version = self.current_version().await;
|
||||
|
||||
@@ -1359,9 +1510,7 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
|
||||
}
|
||||
|
||||
async fn explain_plan(&self, query: &AnyQuery, verbose: bool) -> Result<String> {
|
||||
let base_request = self
|
||||
.client
|
||||
.post(&format!("/v1/table/{}/explain_plan/", self.identifier));
|
||||
let base_request = self.post_read(&format!("/v1/table/{}/explain_plan/", self.identifier));
|
||||
|
||||
let query_bodies = self.prepare_query_bodies(query).await?;
|
||||
let requests: Vec<reqwest::RequestBuilder> = query_bodies
|
||||
@@ -1408,9 +1557,7 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
|
||||
query: &AnyQuery,
|
||||
_options: QueryExecutionOptions,
|
||||
) -> Result<String> {
|
||||
let request = self
|
||||
.client
|
||||
.post(&format!("/v1/table/{}/analyze_plan/", self.identifier));
|
||||
let request = self.post_read(&format!("/v1/table/{}/analyze_plan/", self.identifier));
|
||||
|
||||
let query_bodies = self.prepare_query_bodies(query).await?;
|
||||
let requests: Vec<reqwest::RequestBuilder> = query_bodies
|
||||
@@ -1480,12 +1627,17 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
|
||||
status_code: None,
|
||||
})?;
|
||||
|
||||
self.track_write_version(update_response.version);
|
||||
Ok(update_response)
|
||||
}
|
||||
|
||||
async fn delete(&self, predicate: &str) -> Result<DeleteResult> {
|
||||
async fn delete(&self, predicate: Predicate<'_>) -> Result<DeleteResult> {
|
||||
self.check_mutable().await?;
|
||||
let body = serde_json::json!({ "predicate": predicate });
|
||||
let predicate_sql = match predicate {
|
||||
Predicate::String(s) => s.to_string(),
|
||||
Predicate::Expr(expr) => expr_to_sql_string(expr)?,
|
||||
};
|
||||
let body = serde_json::json!({ "predicate": predicate_sql });
|
||||
let request = self
|
||||
.client
|
||||
.post(&format!("/v1/table/{}/delete/", self.identifier))
|
||||
@@ -1506,6 +1658,7 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
|
||||
request_id,
|
||||
status_code: None,
|
||||
})?;
|
||||
self.track_write_version(delete_response.version);
|
||||
Ok(delete_response)
|
||||
}
|
||||
|
||||
@@ -1652,6 +1805,7 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
|
||||
num_inserted_rows: 0,
|
||||
num_updated_rows: 0,
|
||||
num_attempts: 0,
|
||||
num_rows: 0,
|
||||
});
|
||||
}
|
||||
|
||||
@@ -1662,6 +1816,7 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
|
||||
status_code: None,
|
||||
})?;
|
||||
|
||||
self.track_write_version(merge_insert_response.version);
|
||||
Ok(merge_insert_response)
|
||||
}
|
||||
|
||||
@@ -1687,12 +1842,22 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
|
||||
Ok(Box::new(RemoteTags { inner: self }))
|
||||
}
|
||||
async fn checkout_tag(&self, tag: &str) -> Result<()> {
|
||||
let tags = self.tags().await?;
|
||||
let version = tags.get_version(tag).await?;
|
||||
// Resolve the tag without attaching freshness headers; a stale
|
||||
// `min_version` from a previous write should not ride along on an
|
||||
// explicit time-travel request.
|
||||
let request = self
|
||||
.client
|
||||
.post(&format!("/v1/table/{}/tags/version/", self.identifier));
|
||||
let version = self.resolve_tag_version_with_request(tag, request).await?;
|
||||
|
||||
let mut write_guard = self.version.write().await;
|
||||
*write_guard = Some(version);
|
||||
drop(write_guard);
|
||||
|
||||
// Explicit time-travel: drop any read-your-write / freshness
|
||||
// constraints so the user sees exactly the tagged version.
|
||||
*self.freshness.lock().unwrap() = FreshnessState::default();
|
||||
|
||||
// Invalidate schema cache since we're switching versions
|
||||
self.invalidate_schema_cache();
|
||||
|
||||
@@ -1743,6 +1908,7 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
|
||||
})?;
|
||||
|
||||
self.invalidate_schema_cache();
|
||||
self.track_write_version(result.version);
|
||||
|
||||
Ok(result)
|
||||
}
|
||||
@@ -1797,6 +1963,7 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
|
||||
})?;
|
||||
|
||||
self.invalidate_schema_cache();
|
||||
self.track_write_version(result.version);
|
||||
|
||||
Ok(result)
|
||||
}
|
||||
@@ -1824,15 +1991,14 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
|
||||
})?;
|
||||
|
||||
self.invalidate_schema_cache();
|
||||
self.track_write_version(result.version);
|
||||
|
||||
Ok(result)
|
||||
}
|
||||
|
||||
async fn list_indices(&self) -> Result<Vec<IndexConfig>> {
|
||||
// Make request to list the indices
|
||||
let mut request = self
|
||||
.client
|
||||
.post(&format!("/v1/table/{}/index/list/", self.identifier));
|
||||
let mut request = self.post_read(&format!("/v1/table/{}/index/list/", self.identifier));
|
||||
let version = self.current_version().await;
|
||||
let body = serde_json::json!({ "version": version });
|
||||
request = request.json(&body);
|
||||
@@ -1896,7 +2062,7 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
|
||||
}
|
||||
|
||||
async fn index_stats(&self, index_name: &str) -> Result<Option<IndexStatistics>> {
|
||||
let mut request = self.client.post(&format!(
|
||||
let mut request = self.post_read(&format!(
|
||||
"/v1/table/{}/index/{}/stats/",
|
||||
self.identifier, index_name
|
||||
));
|
||||
@@ -2008,9 +2174,7 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
|
||||
}
|
||||
|
||||
async fn stats(&self) -> Result<TableStatistics> {
|
||||
let request = self
|
||||
.client
|
||||
.post(&format!("/v1/table/{}/stats/", self.identifier));
|
||||
let request = self.post_read(&format!("/v1/table/{}/stats/", self.identifier));
|
||||
let (request_id, response) = self.send(request, true).await?;
|
||||
let response = self.check_table_response(&request_id, response).await?;
|
||||
let body = response.text().await.err_to_http(request_id.clone())?;
|
||||
@@ -2851,6 +3015,33 @@ mod tests {
|
||||
assert_eq!(result.version, if old_server { 0 } else { 43 });
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_delete_expr() {
|
||||
use datafusion_expr::{col, lit};
|
||||
|
||||
let table = Table::new_with_handler("my_table", move |request| {
|
||||
if request.url().path() == "/v1/table/my_table/delete/" {
|
||||
assert_eq!(request.method(), "POST");
|
||||
|
||||
let body = request.body().unwrap().as_bytes().unwrap();
|
||||
let body: serde_json::Value = serde_json::from_slice(body).unwrap();
|
||||
assert!(body.get("predicate").unwrap().is_string());
|
||||
|
||||
http::Response::builder()
|
||||
.status(200)
|
||||
.body(r#"{"num_deleted_rows": 4, "version": 2}"#)
|
||||
.unwrap()
|
||||
} else {
|
||||
panic!("Unexpected request path: {}", request.url().path());
|
||||
}
|
||||
});
|
||||
|
||||
let expr = col("id").gt(lit(5));
|
||||
let result = table.delete(&expr).await.unwrap();
|
||||
assert_eq!(result.num_deleted_rows, 4);
|
||||
assert_eq!(result.version, 2);
|
||||
}
|
||||
|
||||
#[rstest]
|
||||
#[case(true)]
|
||||
#[case(false)]
|
||||
@@ -5974,4 +6165,299 @@ mod tests {
|
||||
assert_eq!(create_count.load(Ordering::SeqCst), 2);
|
||||
assert_eq!(abort_count.load(Ordering::SeqCst), 1);
|
||||
}
|
||||
|
||||
// ---- Read freshness header tests ------------------------------------
|
||||
|
||||
#[test]
|
||||
fn test_compute_min_timestamp_combines_baseline_and_interval() {
|
||||
let now = SystemTime::now();
|
||||
let baseline = now - Duration::from_secs(60);
|
||||
|
||||
// No interval, no baseline -> no header.
|
||||
assert_eq!(
|
||||
compute_min_timestamp(&FreshnessState::default(), None, now),
|
||||
None
|
||||
);
|
||||
|
||||
// Baseline only -> baseline.
|
||||
let state = FreshnessState {
|
||||
min_version: None,
|
||||
checkout_baseline: Some(baseline),
|
||||
};
|
||||
assert_eq!(compute_min_timestamp(&state, None, now), Some(baseline));
|
||||
|
||||
// ZERO interval, no baseline -> now.
|
||||
assert_eq!(
|
||||
compute_min_timestamp(&FreshnessState::default(), Some(Duration::ZERO), now),
|
||||
Some(now)
|
||||
);
|
||||
|
||||
// Positive interval, no baseline -> now - interval.
|
||||
assert_eq!(
|
||||
compute_min_timestamp(
|
||||
&FreshnessState::default(),
|
||||
Some(Duration::from_secs(10)),
|
||||
now
|
||||
),
|
||||
Some(now - Duration::from_secs(10))
|
||||
);
|
||||
|
||||
// Both: pick the more-recent (i.e. tighter) constraint.
|
||||
// baseline = now-60, now-interval = now-10. now-10 is newer.
|
||||
let state = FreshnessState {
|
||||
min_version: None,
|
||||
checkout_baseline: Some(baseline),
|
||||
};
|
||||
assert_eq!(
|
||||
compute_min_timestamp(&state, Some(Duration::from_secs(10)), now),
|
||||
Some(now - Duration::from_secs(10))
|
||||
);
|
||||
|
||||
// Both, baseline newer: pick baseline.
|
||||
let recent_baseline = now - Duration::from_secs(5);
|
||||
let state = FreshnessState {
|
||||
min_version: None,
|
||||
checkout_baseline: Some(recent_baseline),
|
||||
};
|
||||
assert_eq!(
|
||||
compute_min_timestamp(&state, Some(Duration::from_secs(60)), now),
|
||||
Some(recent_baseline)
|
||||
);
|
||||
}
|
||||
|
||||
/// Allowed slop when comparing a header timestamp against a locally
|
||||
/// captured wall-clock bound. Tests run fast enough that 1s is plenty.
|
||||
const FRESHNESS_TOLERANCE: Duration = Duration::from_secs(1);
|
||||
|
||||
fn capturing_handler<F>(
|
||||
body_for: F,
|
||||
) -> (
|
||||
impl Fn(reqwest::Request) -> http::Response<String> + Clone + Send + Sync + 'static,
|
||||
Arc<std::sync::Mutex<Option<http::HeaderMap>>>,
|
||||
)
|
||||
where
|
||||
F: Fn(&str) -> String + Clone + Send + Sync + 'static,
|
||||
{
|
||||
let captured = Arc::new(std::sync::Mutex::new(None));
|
||||
let captured_c = captured.clone();
|
||||
let handler = move |request: reqwest::Request| {
|
||||
*captured_c.lock().unwrap() = Some(request.headers().clone());
|
||||
let path = request.url().path().to_string();
|
||||
http::Response::builder()
|
||||
.status(200)
|
||||
.body(body_for(&path))
|
||||
.unwrap()
|
||||
};
|
||||
(handler, captured)
|
||||
}
|
||||
|
||||
fn parse_min_timestamp(headers: &http::HeaderMap) -> SystemTime {
|
||||
let value = headers
|
||||
.get("x-lancedb-min-timestamp")
|
||||
.expect("expected x-lancedb-min-timestamp header")
|
||||
.to_str()
|
||||
.unwrap();
|
||||
chrono::DateTime::parse_from_rfc3339(value)
|
||||
.unwrap()
|
||||
.with_timezone(&chrono::Utc)
|
||||
.into()
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_freshness_default_sends_no_headers() {
|
||||
let (handler, captured) = capturing_handler(|_| "42".to_string());
|
||||
let table = Table::new_with_handler("my_table", handler);
|
||||
|
||||
let _ = table.count_rows(None).await.unwrap();
|
||||
|
||||
let headers = captured.lock().unwrap().clone().unwrap();
|
||||
assert!(!headers.contains_key("x-lancedb-min-timestamp"));
|
||||
assert!(!headers.contains_key("x-lancedb-min-version"));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_freshness_zero_interval_sends_now() {
|
||||
let (handler, captured) = capturing_handler(|_| "42".to_string());
|
||||
let table =
|
||||
Table::new_with_handler_and_interval("my_table", handler, Some(Duration::from_secs(0)));
|
||||
|
||||
let before = SystemTime::now();
|
||||
table.count_rows(None).await.unwrap();
|
||||
let after = SystemTime::now();
|
||||
|
||||
let headers = captured.lock().unwrap().clone().unwrap();
|
||||
let sent = parse_min_timestamp(&headers);
|
||||
assert!(
|
||||
sent >= before - FRESHNESS_TOLERANCE && sent <= after + FRESHNESS_TOLERANCE,
|
||||
"expected timestamp roughly equal to wall clock"
|
||||
);
|
||||
assert!(!headers.contains_key("x-lancedb-min-version"));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_freshness_positive_interval_sends_now_minus_interval() {
|
||||
let (handler, captured) = capturing_handler(|_| "42".to_string());
|
||||
let interval = Duration::from_secs(30);
|
||||
let table = Table::new_with_handler_and_interval("my_table", handler, Some(interval));
|
||||
|
||||
let before = SystemTime::now();
|
||||
table.count_rows(None).await.unwrap();
|
||||
let after = SystemTime::now();
|
||||
|
||||
let headers = captured.lock().unwrap().clone().unwrap();
|
||||
let sent = parse_min_timestamp(&headers);
|
||||
assert!(
|
||||
sent >= before - interval - FRESHNESS_TOLERANCE
|
||||
&& sent <= after - interval + FRESHNESS_TOLERANCE,
|
||||
"expected timestamp roughly equal to now - interval"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_freshness_checkout_latest_sets_baseline() {
|
||||
let (handler, captured) = capturing_handler(|path| match path {
|
||||
"/v1/table/my_table/count_rows/" => "42".to_string(),
|
||||
_ => panic!("unexpected path: {}", path),
|
||||
});
|
||||
// No interval — only the baseline should drive the timestamp.
|
||||
let table = Table::new_with_handler_and_interval("my_table", handler, None);
|
||||
|
||||
let before_checkout = SystemTime::now();
|
||||
table.checkout_latest().await.unwrap();
|
||||
let after_checkout = SystemTime::now();
|
||||
|
||||
table.count_rows(None).await.unwrap();
|
||||
|
||||
let headers = captured.lock().unwrap().clone().unwrap();
|
||||
let sent = parse_min_timestamp(&headers);
|
||||
assert!(
|
||||
sent >= before_checkout - FRESHNESS_TOLERANCE
|
||||
&& sent <= after_checkout + FRESHNESS_TOLERANCE,
|
||||
"expected timestamp captured at checkout_latest() time"
|
||||
);
|
||||
assert!(!headers.contains_key("x-lancedb-min-version"));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_freshness_min_version_tracked_after_write() {
|
||||
let (handler, captured) = capturing_handler(|path| match path {
|
||||
"/v1/table/my_table/update/" => r#"{"rows_updated":1,"version":7}"#.to_string(),
|
||||
"/v1/table/my_table/count_rows/" => "42".to_string(),
|
||||
_ => panic!("unexpected path: {}", path),
|
||||
});
|
||||
let table = Table::new_with_handler("my_table", handler);
|
||||
|
||||
let _ = table.update().column("a", "a + 1").execute().await.unwrap();
|
||||
// Update headers also pass through captured; reset by reading after.
|
||||
table.count_rows(None).await.unwrap();
|
||||
|
||||
let headers = captured.lock().unwrap().clone().unwrap();
|
||||
assert_eq!(
|
||||
headers
|
||||
.get("x-lancedb-min-version")
|
||||
.unwrap()
|
||||
.to_str()
|
||||
.unwrap(),
|
||||
"7"
|
||||
);
|
||||
}
|
||||
|
||||
/// Like `capturing_handler`, but keeps a per-path snapshot of the headers
|
||||
/// from every request so tests can assert on a specific endpoint.
|
||||
#[allow(clippy::type_complexity)]
|
||||
fn path_capturing_handler<F>(
|
||||
body_for: F,
|
||||
) -> (
|
||||
impl Fn(reqwest::Request) -> http::Response<String> + Clone + Send + Sync + 'static,
|
||||
Arc<std::sync::Mutex<HashMap<String, http::HeaderMap>>>,
|
||||
)
|
||||
where
|
||||
F: Fn(&str) -> String + Clone + Send + Sync + 'static,
|
||||
{
|
||||
let captured: Arc<std::sync::Mutex<HashMap<String, http::HeaderMap>>> =
|
||||
Arc::new(std::sync::Mutex::new(HashMap::new()));
|
||||
let captured_c = captured.clone();
|
||||
let handler = move |request: reqwest::Request| {
|
||||
let path = request.url().path().to_string();
|
||||
captured_c
|
||||
.lock()
|
||||
.unwrap()
|
||||
.insert(path.clone(), request.headers().clone());
|
||||
http::Response::builder()
|
||||
.status(200)
|
||||
.body(body_for(&path))
|
||||
.unwrap()
|
||||
};
|
||||
(handler, captured)
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_freshness_checkout_validation_sends_no_min_version() {
|
||||
// After a write bumps min_version, calling checkout(v) must not let
|
||||
// that stale header ride along on the validating /describe/ request.
|
||||
let (handler, captured) = path_capturing_handler(|path| match path {
|
||||
"/v1/table/my_table/update/" => r#"{"rows_updated":1,"version":7}"#.to_string(),
|
||||
"/v1/table/my_table/describe/" => r#"{"version":5,"schema":{"fields":[]}}"#.to_string(),
|
||||
_ => panic!("unexpected path: {}", path),
|
||||
});
|
||||
let table = Table::new_with_handler("my_table", handler);
|
||||
|
||||
table.update().column("a", "a + 1").execute().await.unwrap();
|
||||
table.checkout(5).await.unwrap();
|
||||
|
||||
let captured = captured.lock().unwrap();
|
||||
let describe_headers = captured
|
||||
.get("/v1/table/my_table/describe/")
|
||||
.expect("describe should have been called by checkout(v)");
|
||||
assert!(
|
||||
!describe_headers.contains_key("x-lancedb-min-version"),
|
||||
"checkout(v) describe must not carry stale min_version",
|
||||
);
|
||||
assert!(!describe_headers.contains_key("x-lancedb-min-timestamp"));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_freshness_checkout_tag_resolve_sends_no_min_version() {
|
||||
// Same invariant for checkout_tag: the tag-resolve request must not
|
||||
// pick up a stale min_version from a prior write.
|
||||
let (handler, captured) = path_capturing_handler(|path| match path {
|
||||
"/v1/table/my_table/update/" => r#"{"rows_updated":1,"version":7}"#.to_string(),
|
||||
"/v1/table/my_table/tags/version/" => r#"{"version":5}"#.to_string(),
|
||||
_ => panic!("unexpected path: {}", path),
|
||||
});
|
||||
let table = Table::new_with_handler("my_table", handler);
|
||||
|
||||
table.update().column("a", "a + 1").execute().await.unwrap();
|
||||
table.checkout_tag("v_initial").await.unwrap();
|
||||
|
||||
let captured = captured.lock().unwrap();
|
||||
let resolve_headers = captured
|
||||
.get("/v1/table/my_table/tags/version/")
|
||||
.expect("tags/version should have been called by checkout_tag");
|
||||
assert!(
|
||||
!resolve_headers.contains_key("x-lancedb-min-version"),
|
||||
"checkout_tag resolve must not carry stale min_version",
|
||||
);
|
||||
assert!(!resolve_headers.contains_key("x-lancedb-min-timestamp"));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_freshness_checkout_clears_min_version() {
|
||||
let (handler, captured) = capturing_handler(|path| match path {
|
||||
"/v1/table/my_table/update/" => r#"{"rows_updated":1,"version":7}"#.to_string(),
|
||||
// checkout(5) needs to describe version 5 first
|
||||
"/v1/table/my_table/describe/" => r#"{"version":5,"schema":{"fields":[]}}"#.to_string(),
|
||||
"/v1/table/my_table/count_rows/" => "42".to_string(),
|
||||
_ => panic!("unexpected path: {}", path),
|
||||
});
|
||||
let table = Table::new_with_handler("my_table", handler);
|
||||
|
||||
table.update().column("a", "a + 1").execute().await.unwrap();
|
||||
table.checkout(5).await.unwrap();
|
||||
table.count_rows(None).await.unwrap();
|
||||
|
||||
let headers = captured.lock().unwrap().clone().unwrap();
|
||||
assert!(!headers.contains_key("x-lancedb-min-version"));
|
||||
assert!(!headers.contains_key("x-lancedb-min-timestamp"));
|
||||
}
|
||||
}
|
||||
|
||||
@@ -89,7 +89,6 @@ use futures::future::join_all;
|
||||
pub use lance::dataset::refs::{TagContents, Tags as LanceTags};
|
||||
pub use lance::dataset::scanner::DatasetRecordBatchStream;
|
||||
use lance::dataset::statistics::DatasetStatisticsExt;
|
||||
use lance_index::frag_reuse::FRAG_REUSE_INDEX_NAME;
|
||||
pub use lance_index::optimize::OptimizeOptions;
|
||||
pub use optimize::{CompactionOptions, OptimizeAction, OptimizeStats};
|
||||
pub use schema_evolution::{AddColumnsResult, AlterColumnsResult, DropColumnsResult};
|
||||
@@ -253,6 +252,36 @@ pub enum Filter {
|
||||
Datafusion(Expr),
|
||||
}
|
||||
|
||||
/// A predicate for filtering rows in delete operations.
|
||||
///
|
||||
/// Accepts either a SQL string or a DataFusion [`Expr`]. Use the [`From`]
|
||||
/// implementations to convert from `&str` or `&Expr` automatically.
|
||||
/// See [`Table::delete`] for usage examples.
|
||||
pub enum Predicate<'a> {
|
||||
/// A SQL predicate string
|
||||
String(&'a str),
|
||||
/// A DataFusion logical expression
|
||||
Expr(&'a Expr),
|
||||
}
|
||||
|
||||
impl<'a> From<&'a str> for Predicate<'a> {
|
||||
fn from(s: &'a str) -> Self {
|
||||
Predicate::String(s)
|
||||
}
|
||||
}
|
||||
|
||||
impl<'a> From<&'a String> for Predicate<'a> {
|
||||
fn from(s: &'a String) -> Self {
|
||||
Predicate::String(s.as_str())
|
||||
}
|
||||
}
|
||||
|
||||
impl<'a> From<&'a Expr> for Predicate<'a> {
|
||||
fn from(e: &'a Expr) -> Self {
|
||||
Predicate::Expr(e)
|
||||
}
|
||||
}
|
||||
|
||||
#[async_trait]
|
||||
pub trait Tags: Send + Sync {
|
||||
/// List the tags of the table.
|
||||
@@ -282,17 +311,15 @@ pub use self::merge::MergeResult;
|
||||
/// date) and [`LsmWriteSpec::with_writer_config_defaults`] (default
|
||||
/// `ShardWriter` configuration recorded in the MemWAL index).
|
||||
///
|
||||
/// All variants require the table to have an unenforced primary key.
|
||||
///
|
||||
/// Install a spec with [`Table::set_lsm_write_spec`] and remove it with
|
||||
/// [`Table::unset_lsm_write_spec`]. The actual `merge_insert` dispatch
|
||||
/// onto the MemWAL writer is a follow-up.
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
pub enum LsmWriteSpec {
|
||||
/// Hash-bucket sharding by the unenforced primary key column.
|
||||
/// Hash-bucket sharding by a scalar column.
|
||||
///
|
||||
/// `column` must equal the table's currently-set single-column
|
||||
/// unenforced primary key. `num_buckets` must be in `[1, 1024]`.
|
||||
/// `column` must be a non-nested column with a supported scalar type.
|
||||
/// `num_buckets` must be in `[1, 1024]`.
|
||||
/// Iceberg-compatible Murmur3-x86-32 (seed 0) is used so each row's
|
||||
/// `bucket(column, num_buckets)` value is stable across processes.
|
||||
Bucket {
|
||||
@@ -339,6 +366,14 @@ impl LsmWriteSpec {
|
||||
|
||||
/// Construct an identity-sharding spec (shard by the raw value of
|
||||
/// `column`) with no maintained indexes.
|
||||
///
|
||||
/// `column` must be a deterministic function of the unenforced primary
|
||||
/// key: every row with a given primary key must always produce the same
|
||||
/// `column` value. MemWAL dedups upserts by primary key but tracks
|
||||
/// generations per shard, so if the same key is written with two
|
||||
/// different `column` values its versions land in different shards and a
|
||||
/// stale value can win. Typically `column` is the primary key itself, or
|
||||
/// a stable attribute of it (e.g. a tenant id).
|
||||
pub fn identity(column: impl Into<String>) -> Self {
|
||||
Self::Identity {
|
||||
column: column.into(),
|
||||
@@ -491,8 +526,8 @@ pub trait BaseTable: std::fmt::Display + std::fmt::Debug + Send + Sync {
|
||||
|
||||
/// Add new records to the table.
|
||||
async fn add(&self, add: AddDataBuilder) -> Result<AddResult>;
|
||||
/// Delete rows from the table.
|
||||
async fn delete(&self, predicate: &str) -> Result<DeleteResult>;
|
||||
/// Delete rows from the table matching the given [`Predicate`].
|
||||
async fn delete(&self, predicate: Predicate<'_>) -> Result<DeleteResult>;
|
||||
/// Update rows in the table.
|
||||
async fn update(&self, update: UpdateBuilder) -> Result<UpdateResult>;
|
||||
/// Create an index on the provided column(s).
|
||||
@@ -553,6 +588,13 @@ pub trait BaseTable: std::fmt::Display + std::fmt::Debug + Send + Sync {
|
||||
message: "unset_lsm_write_spec is not supported on this table type".into(),
|
||||
})
|
||||
}
|
||||
/// Drain and close any cached MemWAL shard writers for this table.
|
||||
///
|
||||
/// The default implementation is a no-op; table types that maintain
|
||||
/// MemWAL shard writers override it.
|
||||
async fn close_lsm_writers(&self) -> Result<()> {
|
||||
Ok(())
|
||||
}
|
||||
/// Gets the table tag manager.
|
||||
async fn tags(&self) -> Result<Box<dyn Tags + '_>>;
|
||||
/// Optimize the dataset.
|
||||
@@ -656,6 +698,30 @@ mod test_utils {
|
||||
}
|
||||
}
|
||||
|
||||
pub fn new_with_handler_and_interval<T>(
|
||||
name: impl Into<String>,
|
||||
handler: impl Fn(reqwest::Request) -> http::Response<T> + Clone + Send + Sync + 'static,
|
||||
read_consistency_interval: Option<std::time::Duration>,
|
||||
) -> Self
|
||||
where
|
||||
T: Into<reqwest::Body>,
|
||||
{
|
||||
let inner = Arc::new(
|
||||
crate::remote::table::RemoteTable::new_mock_with_consistency_interval(
|
||||
name.into(),
|
||||
handler.clone(),
|
||||
read_consistency_interval,
|
||||
),
|
||||
);
|
||||
let database = Arc::new(crate::remote::db::RemoteDatabase::new_mock(handler));
|
||||
Self {
|
||||
inner,
|
||||
database: Some(database),
|
||||
// Registry is unused.
|
||||
embedding_registry: Arc::new(MemoryRegistry::new()),
|
||||
}
|
||||
}
|
||||
|
||||
pub fn new_with_handler_version<T>(
|
||||
name: impl Into<String>,
|
||||
version: semver::Version,
|
||||
@@ -860,7 +926,8 @@ impl Table {
|
||||
/// Delete the rows from table that match the predicate.
|
||||
///
|
||||
/// # Arguments
|
||||
/// - `predicate` - The SQL predicate string to filter the rows to be deleted.
|
||||
/// - `predicate` - A SQL string (`&str`) or DataFusion expression (`&Expr`)
|
||||
/// that selects the rows to delete.
|
||||
///
|
||||
/// # Example
|
||||
///
|
||||
@@ -869,6 +936,7 @@ impl Table {
|
||||
/// # use arrow_array::{FixedSizeListArray, types::Float32Type, RecordBatch,
|
||||
/// # RecordBatchIterator, Int32Array};
|
||||
/// # use arrow_schema::{Schema, Field, DataType};
|
||||
/// use datafusion_expr::{col, lit};
|
||||
/// # tokio::runtime::Runtime::new().unwrap().block_on(async {
|
||||
/// let tmpdir = tempfile::tempdir().unwrap();
|
||||
/// let db = lancedb::connect(tmpdir.path().to_str().unwrap())
|
||||
@@ -898,11 +966,17 @@ impl Table {
|
||||
/// .execute()
|
||||
/// .await
|
||||
/// .unwrap();
|
||||
///
|
||||
/// // Using a SQL string:
|
||||
/// tbl.delete("id > 5").await.unwrap();
|
||||
///
|
||||
/// // Using a DataFusion expression:
|
||||
/// let expr = col("id").lt(lit(4));
|
||||
/// tbl.delete(&expr).await.unwrap();
|
||||
/// # });
|
||||
/// ```
|
||||
pub async fn delete(&self, predicate: &str) -> Result<DeleteResult> {
|
||||
self.inner.delete(predicate).await
|
||||
pub async fn delete(&self, predicate: impl Into<Predicate<'_>>) -> Result<DeleteResult> {
|
||||
self.inner.delete(predicate.into()).await
|
||||
}
|
||||
|
||||
/// Create an index on the provided column(s).
|
||||
@@ -1298,21 +1372,15 @@ impl Table {
|
||||
///
|
||||
/// [`LsmWriteSpec`] chooses one of three sharding strategies:
|
||||
///
|
||||
/// - [`LsmWriteSpec::bucket`] — hash-bucket writes by the single-column
|
||||
/// unenforced primary key.
|
||||
/// - [`LsmWriteSpec::bucket`] — hash-bucket writes by a scalar column.
|
||||
/// - [`LsmWriteSpec::identity`] — shard by the raw value of a scalar column.
|
||||
/// - [`LsmWriteSpec::unsharded`] — route every write to a single shard.
|
||||
///
|
||||
/// All variants require the table to have an unenforced primary key
|
||||
/// ([`Table::set_unenforced_primary_key`]); bucket sharding additionally
|
||||
/// requires it to be the single column being bucketed.
|
||||
///
|
||||
/// # Example
|
||||
///
|
||||
/// ```
|
||||
/// # use lancedb::table::{LsmWriteSpec, Table};
|
||||
/// # async fn example(table: &Table) -> Result<(), Box<dyn std::error::Error>> {
|
||||
/// table.set_unenforced_primary_key(["id"]).await?;
|
||||
/// table
|
||||
/// .set_lsm_write_spec(
|
||||
/// LsmWriteSpec::bucket("id", 16).with_maintained_indexes(["id_idx"]),
|
||||
@@ -1333,6 +1401,16 @@ impl Table {
|
||||
self.inner.unset_lsm_write_spec().await
|
||||
}
|
||||
|
||||
/// Drain and close any cached MemWAL shard writers held for this table.
|
||||
///
|
||||
/// When an [`LsmWriteSpec`] is installed, `merge_insert` opens MemWAL shard
|
||||
/// writers and caches them for reuse across calls. This closes them,
|
||||
/// flushing pending data; writers reopen lazily on the next `merge_insert`.
|
||||
/// It is a no-op when no writers are cached.
|
||||
pub async fn close_lsm_writers(&self) -> Result<()> {
|
||||
self.inner.close_lsm_writers().await
|
||||
}
|
||||
|
||||
/// Retrieve the version of the table
|
||||
///
|
||||
/// LanceDb supports versioning. Every operation that modifies the table increases
|
||||
@@ -2776,9 +2854,12 @@ impl BaseTable for NativeTable {
|
||||
merge::lsm::unset_lsm_write_spec(self).await
|
||||
}
|
||||
|
||||
async fn close_lsm_writers(&self) -> Result<()> {
|
||||
merge::lsm::close_lsm_writers(self).await
|
||||
}
|
||||
|
||||
/// Delete rows from the table
|
||||
async fn delete(&self, predicate: &str) -> Result<DeleteResult> {
|
||||
// Delegate to the submodule implementation
|
||||
async fn delete(&self, predicate: Predicate<'_>) -> Result<DeleteResult> {
|
||||
delete::execute_delete(self, predicate).await
|
||||
}
|
||||
|
||||
@@ -2811,71 +2892,32 @@ impl BaseTable for NativeTable {
|
||||
|
||||
async fn list_indices(&self) -> Result<Vec<IndexConfig>> {
|
||||
let dataset = self.dataset.get().await?;
|
||||
let indices = dataset.load_indices().await?;
|
||||
let results = futures::stream::iter(indices.as_slice())
|
||||
.then(|idx| async {
|
||||
// skip Lance internal indexes
|
||||
if idx.name == FRAG_REUSE_INDEX_NAME {
|
||||
return None;
|
||||
}
|
||||
|
||||
let stats = match dataset.index_statistics(idx.name.as_str()).await {
|
||||
Ok(stats) => stats,
|
||||
Err(e) => {
|
||||
log::warn!(
|
||||
"Failed to get statistics for index {} ({}): {}",
|
||||
idx.name,
|
||||
idx.uuid,
|
||||
e
|
||||
);
|
||||
return None;
|
||||
}
|
||||
};
|
||||
|
||||
let stats: serde_json::Value = match serde_json::from_str(&stats) {
|
||||
Ok(stats) => stats,
|
||||
Err(e) => {
|
||||
log::warn!(
|
||||
"Failed to deserialize index statistics for index {} ({}): {}",
|
||||
idx.name,
|
||||
idx.uuid,
|
||||
e
|
||||
);
|
||||
return None;
|
||||
}
|
||||
};
|
||||
|
||||
let Some(index_type) = stats.get("index_type").and_then(|v| v.as_str()) else {
|
||||
log::warn!(
|
||||
"Index statistics was missing 'index_type' field for index {} ({})",
|
||||
idx.name,
|
||||
idx.uuid
|
||||
);
|
||||
return None;
|
||||
};
|
||||
|
||||
let index_type: crate::index::IndexType = match index_type.parse() {
|
||||
let indices = dataset
|
||||
.describe_indices(None)
|
||||
.await?
|
||||
.into_iter()
|
||||
.filter_map(|idx_desc| {
|
||||
let index_type: crate::index::IndexType = match idx_desc.index_type().parse() {
|
||||
Ok(index_type) => index_type,
|
||||
Err(e) => {
|
||||
log::warn!(
|
||||
"Failed to parse index type for index {} ({}): {}",
|
||||
idx.name,
|
||||
idx.uuid,
|
||||
"Failed to parse index type for index {}: {}",
|
||||
idx_desc.name(),
|
||||
e
|
||||
);
|
||||
return None;
|
||||
}
|
||||
};
|
||||
|
||||
let mut columns = Vec::with_capacity(idx.fields.len());
|
||||
for field_id in &idx.fields {
|
||||
let field_path = match dataset.schema().field_path(*field_id) {
|
||||
let field_ids = idx_desc.field_ids();
|
||||
let mut columns = Vec::with_capacity(field_ids.len());
|
||||
for field_id in field_ids {
|
||||
let field_path = match dataset.schema().field_path(*field_id as i32) {
|
||||
Ok(field_path) => field_path,
|
||||
Err(e) => {
|
||||
log::warn!(
|
||||
"Failed to resolve field path for index {} ({}) field id {}: {}",
|
||||
idx.name,
|
||||
idx.uuid,
|
||||
"Failed to resolve field path for index {} field id {}: {}",
|
||||
idx_desc.name(),
|
||||
field_id,
|
||||
e
|
||||
);
|
||||
@@ -2885,17 +2927,14 @@ impl BaseTable for NativeTable {
|
||||
columns.push(field_path);
|
||||
}
|
||||
|
||||
let name = idx.name.clone();
|
||||
Some(IndexConfig {
|
||||
name: idx_desc.name().to_string(),
|
||||
index_type,
|
||||
columns,
|
||||
name,
|
||||
})
|
||||
})
|
||||
.collect::<Vec<_>>()
|
||||
.await;
|
||||
|
||||
Ok(results.into_iter().flatten().collect())
|
||||
.collect();
|
||||
Ok(indices)
|
||||
}
|
||||
|
||||
async fn uri(&self) -> Result<String> {
|
||||
@@ -3005,11 +3044,12 @@ impl BaseTable for NativeTable {
|
||||
let p99 = *sorted_sizes.get(num_fragments * 99 / 100).unwrap_or(&0);
|
||||
let min = sorted_sizes.first().copied().unwrap_or(0);
|
||||
let max = sorted_sizes.last().copied().unwrap_or(0);
|
||||
let mean = if num_fragments == 0 {
|
||||
0
|
||||
} else {
|
||||
sorted_sizes.iter().copied().sum::<usize>() / num_fragments
|
||||
};
|
||||
let mean = sorted_sizes
|
||||
.iter()
|
||||
.copied()
|
||||
.sum::<usize>()
|
||||
.checked_div(num_fragments)
|
||||
.unwrap_or(0);
|
||||
|
||||
let frag_stats = FragmentStatistics {
|
||||
num_fragments,
|
||||
@@ -4009,26 +4049,27 @@ mod tests {
|
||||
let index_configs = table.list_indices().await.unwrap();
|
||||
assert_eq!(index_configs.len(), 5);
|
||||
|
||||
// list_indices returns indices in alphabetical order by name
|
||||
let mut configs_iter = index_configs.into_iter();
|
||||
let index = configs_iter.next().unwrap();
|
||||
assert_eq!(index.index_type, crate::index::IndexType::Bitmap);
|
||||
assert_eq!(index.columns, vec!["category".to_string()]);
|
||||
|
||||
let index = configs_iter.next().unwrap();
|
||||
assert_eq!(index.index_type, crate::index::IndexType::Bitmap);
|
||||
assert_eq!(index.columns, vec!["is_active".to_string()]);
|
||||
|
||||
let index = configs_iter.next().unwrap();
|
||||
assert_eq!(index.index_type, crate::index::IndexType::Bitmap);
|
||||
assert_eq!(index.columns, vec!["data".to_string()]);
|
||||
|
||||
let index = configs_iter.next().unwrap();
|
||||
assert_eq!(index.index_type, crate::index::IndexType::Bitmap);
|
||||
assert_eq!(index.columns, vec!["large_data".to_string()]);
|
||||
assert_eq!(index.columns, vec!["is_active".to_string()]);
|
||||
|
||||
let index = configs_iter.next().unwrap();
|
||||
assert_eq!(index.index_type, crate::index::IndexType::Bitmap);
|
||||
assert_eq!(index.columns, vec!["large_category".to_string()]);
|
||||
|
||||
let index = configs_iter.next().unwrap();
|
||||
assert_eq!(index.index_type, crate::index::IndexType::Bitmap);
|
||||
assert_eq!(index.columns, vec!["large_data".to_string()]);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
@@ -4600,21 +4641,6 @@ mod tests {
|
||||
.unwrap();
|
||||
let table = conn.create_table("t", reader).execute().await.unwrap();
|
||||
|
||||
// Reject when no PK is set.
|
||||
let err = table
|
||||
.set_lsm_write_spec(LsmWriteSpec::bucket("id", 4))
|
||||
.await
|
||||
.expect_err("should reject without PK");
|
||||
assert!(matches!(err, Error::Lance { .. }), "got {:?}", err);
|
||||
|
||||
// Set PK, then a mismatched column on the spec must be rejected.
|
||||
table.set_unenforced_primary_key(["id"]).await.unwrap();
|
||||
let err = table
|
||||
.set_lsm_write_spec(LsmWriteSpec::bucket("name", 4))
|
||||
.await
|
||||
.expect_err("should reject column != PK");
|
||||
assert!(matches!(err, Error::Lance { .. }), "got {:?}", err);
|
||||
|
||||
// Reject num_buckets out of range.
|
||||
for bad in [0u32, 1025] {
|
||||
let err = table
|
||||
@@ -4680,9 +4706,6 @@ mod tests {
|
||||
.unwrap();
|
||||
let table = conn.create_table("t", reader).execute().await.unwrap();
|
||||
|
||||
// Lance's MemWAL still requires *some* unenforced primary key on
|
||||
// the dataset; Unsharded just skips the per-row hashing step.
|
||||
table.set_unenforced_primary_key(["id"]).await.unwrap();
|
||||
table
|
||||
.set_lsm_write_spec(LsmWriteSpec::unsharded())
|
||||
.await
|
||||
@@ -4729,7 +4752,6 @@ mod tests {
|
||||
.unwrap();
|
||||
let table = conn.create_table("t", reader).execute().await.unwrap();
|
||||
|
||||
table.set_unenforced_primary_key(["id"]).await.unwrap();
|
||||
table
|
||||
.set_lsm_write_spec(
|
||||
LsmWriteSpec::identity("region")
|
||||
@@ -4785,7 +4807,6 @@ mod tests {
|
||||
table.unset_lsm_write_spec().await.unwrap_err();
|
||||
|
||||
// Install a spec, then unset it.
|
||||
table.set_unenforced_primary_key(["id"]).await.unwrap();
|
||||
table
|
||||
.set_lsm_write_spec(LsmWriteSpec::bucket("id", 4))
|
||||
.await
|
||||
|
||||
@@ -982,4 +982,105 @@ mod tests {
|
||||
table2.add(struct_batch).execute().await.unwrap();
|
||||
assert_eq!(table2.count_rows(None).await.unwrap(), 2);
|
||||
}
|
||||
|
||||
/// Regression test: appending `arrow.json` (PyArrow `pa.json_()`) data into a table
|
||||
/// whose schema was created with `pa.json_()` (internally stored as `lance.json`, backed
|
||||
/// by `LargeBinary`) must succeed without a schema-mismatch error.
|
||||
///
|
||||
/// Previously `build_field_exprs` would attempt a `Utf8 → LargeBinary` DataFusion cast,
|
||||
/// which produced a field whose Arrow extension metadata still read `arrow.json` instead
|
||||
/// of `lance.json`. Lance-core then rejected the append with
|
||||
/// `"json vs large_binary" schema mismatch`.
|
||||
///
|
||||
/// PyArrow's `pa.json_()` may be backed by either `Utf8` or `LargeUtf8` depending on the
|
||||
/// constructor used, so the test is parameterized over the input backing type.
|
||||
#[rstest::rstest]
|
||||
#[case::utf8(DataType::Utf8)]
|
||||
#[case::large_utf8(DataType::LargeUtf8)]
|
||||
#[tokio::test]
|
||||
async fn test_add_arrow_json_into_lance_json_table(#[case] input_type: DataType) {
|
||||
use arrow_array::{Array, cast::AsArray};
|
||||
use lance_arrow::ARROW_EXT_NAME_KEY;
|
||||
use lance_arrow::json::{ARROW_JSON_EXT_NAME, JSON_EXT_NAME};
|
||||
|
||||
// Build a table whose "data" column is lance.json (LargeBinary +
|
||||
// ARROW:extension:name = "lance.json").
|
||||
let lance_json_field = lance_arrow::json::json_field("data", true);
|
||||
let table_schema = Arc::new(Schema::new(vec![lance_json_field]));
|
||||
|
||||
let db = connect("memory://").execute().await.unwrap();
|
||||
let table = db
|
||||
.create_empty_table("json_test", table_schema)
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// Sanity-check the stored schema.
|
||||
let stored_field = table.schema().await.unwrap();
|
||||
let data_field = stored_field.field_with_name("data").unwrap();
|
||||
assert_eq!(data_field.data_type(), &DataType::LargeBinary);
|
||||
assert_eq!(
|
||||
data_field
|
||||
.metadata()
|
||||
.get(ARROW_EXT_NAME_KEY)
|
||||
.map(|s| s.as_str()),
|
||||
Some(JSON_EXT_NAME),
|
||||
);
|
||||
|
||||
// Build an arrow.json input field (Utf8/LargeUtf8 + arrow.json extension).
|
||||
// This is what PyArrow produces for pa.json_() arrays.
|
||||
let arrow_json_metadata = std::collections::HashMap::from([(
|
||||
ARROW_EXT_NAME_KEY.to_string(),
|
||||
ARROW_JSON_EXT_NAME.to_string(),
|
||||
)]);
|
||||
let arrow_json_field =
|
||||
Field::new("data", input_type.clone(), true).with_metadata(arrow_json_metadata);
|
||||
let arrow_json_schema = Arc::new(Schema::new(vec![arrow_json_field]));
|
||||
|
||||
let rows: Vec<Option<&str>> = vec![None, Some(r#"{"a": 1}"#), Some(r#"{"b": 2}"#)];
|
||||
let string_array: Arc<dyn arrow_array::Array> = match input_type {
|
||||
DataType::Utf8 => Arc::new(arrow_array::StringArray::from(rows.clone())),
|
||||
DataType::LargeUtf8 => Arc::new(arrow_array::LargeStringArray::from(rows.clone())),
|
||||
other => panic!("unsupported arrow.json backing type for this test: {other:?}"),
|
||||
};
|
||||
let batch = RecordBatch::try_new(arrow_json_schema, vec![string_array]).unwrap();
|
||||
|
||||
// This must not fail with a schema-mismatch error.
|
||||
table.add(batch).execute().await.unwrap();
|
||||
|
||||
assert_eq!(table.count_rows(None).await.unwrap(), rows.len());
|
||||
|
||||
// A lance.json column is read back as Utf8 carrying arrow.json extension metadata.
|
||||
let results: Vec<RecordBatch> = table
|
||||
.query()
|
||||
.select(Select::columns(&["data"]))
|
||||
.execute()
|
||||
.await
|
||||
.unwrap()
|
||||
.try_collect()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
assert_eq!(results.len(), 1);
|
||||
let batch = &results[0];
|
||||
assert_eq!(batch.num_rows(), rows.len());
|
||||
|
||||
let json_col = batch.column(0);
|
||||
assert_eq!(json_col.data_type(), &DataType::Utf8);
|
||||
let json_strs = json_col.as_string::<i32>();
|
||||
|
||||
for (i, expected) in rows.iter().enumerate() {
|
||||
match expected {
|
||||
None => assert!(json_strs.is_null(i), "row {i} expected null"),
|
||||
Some(raw) => {
|
||||
assert!(!json_strs.is_null(i), "row {i} expected non-null");
|
||||
let actual: serde_json::Value = serde_json::from_str(json_strs.value(i))
|
||||
.expect("read-back JSON should be valid");
|
||||
let expected: serde_json::Value =
|
||||
serde_json::from_str(raw).expect("expected JSON should be valid");
|
||||
assert_eq!(actual, expected, "row {i} JSON mismatch");
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -13,6 +13,7 @@ use datafusion_physical_expr::expressions::{CastExpr, Literal};
|
||||
use datafusion_physical_plan::expressions::Column;
|
||||
use datafusion_physical_plan::projection::ProjectionExec;
|
||||
use datafusion_physical_plan::{ExecutionPlan, PhysicalExpr};
|
||||
use lance_arrow::json::{is_arrow_json_field, is_json_field};
|
||||
|
||||
use crate::{Error, Result};
|
||||
|
||||
@@ -64,6 +65,18 @@ fn build_field_exprs(
|
||||
let input_field = &input_fields[input_idx];
|
||||
let input_expr = get_input_expr(input_idx);
|
||||
|
||||
// Special case: input is arrow.json (PyArrow pa.json_() extension type backed by
|
||||
// Utf8/LargeUtf8) and the table field is lance.json (backed by LargeBinary).
|
||||
// Lance-core's write path already handles the arrow.json → lance.json conversion
|
||||
// (including JSONB encoding), so we pass the expression through unchanged and let
|
||||
// lance-core deal with it. Attempting to cast Utf8 → LargeBinary here would
|
||||
// produce a field whose metadata still identifies it as arrow.json, which then
|
||||
// causes a schema-mismatch error inside lance-core.
|
||||
if is_arrow_json_field(input_field) && is_json_field(table_field) {
|
||||
result.push((input_expr, Arc::clone(input_field) as FieldRef));
|
||||
continue;
|
||||
}
|
||||
|
||||
let expr = match (input_field.data_type(), table_field.data_type()) {
|
||||
// Both are structs: recurse into sub-fields to handle subschemas and casts.
|
||||
(DataType::Struct(in_children), DataType::Struct(tbl_children))
|
||||
@@ -618,4 +631,75 @@ mod tests {
|
||||
.unwrap();
|
||||
assert_eq!(a.values(), &[1, 3]);
|
||||
}
|
||||
|
||||
/// `arrow.json` input (PyArrow `pa.json_()`, Utf8/LargeUtf8 + extension metadata) against a
|
||||
/// `lance.json` table field (LargeBinary + extension metadata) must be passed through
|
||||
/// without a cast so that lance-core can perform its own arrow.json → JSONB conversion.
|
||||
///
|
||||
/// Before the fix, `cast_to_table_schema` attempted a `Utf8 → LargeBinary` DataFusion
|
||||
/// cast that preserved the wrong extension metadata, causing lance-core to reject the
|
||||
/// batch with a "json vs large_binary" schema-mismatch error.
|
||||
#[rstest::rstest]
|
||||
#[case::utf8(DataType::Utf8)]
|
||||
#[case::large_utf8(DataType::LargeUtf8)]
|
||||
#[tokio::test]
|
||||
async fn test_arrow_json_passthrough_to_lance_json(#[case] input_type: DataType) {
|
||||
use lance_arrow::ARROW_EXT_NAME_KEY;
|
||||
use lance_arrow::json::{ARROW_JSON_EXT_NAME, json_field};
|
||||
|
||||
// Build a table schema with a lance.json field (LargeBinary + lance.json metadata).
|
||||
let lance_field = json_field("data", true);
|
||||
let table_schema = Schema::new(vec![lance_field]);
|
||||
|
||||
// Build an input batch with an arrow.json field (Utf8/LargeUtf8 + arrow.json metadata).
|
||||
let arrow_meta = std::collections::HashMap::from([(
|
||||
ARROW_EXT_NAME_KEY.to_string(),
|
||||
ARROW_JSON_EXT_NAME.to_string(),
|
||||
)]);
|
||||
let arrow_field = Field::new("data", input_type.clone(), true).with_metadata(arrow_meta);
|
||||
let input_schema = Arc::new(Schema::new(vec![arrow_field]));
|
||||
|
||||
let values = vec![Some(r#"{"x": 1}"#), None, Some(r#"{"y": 2}"#)];
|
||||
let input_array: Arc<dyn arrow_array::Array> = match input_type {
|
||||
DataType::Utf8 => Arc::new(StringArray::from(values)),
|
||||
DataType::LargeUtf8 => Arc::new(arrow_array::LargeStringArray::from(values)),
|
||||
other => panic!("unsupported arrow.json backing type for this test: {other:?}"),
|
||||
};
|
||||
let input_batch = RecordBatch::try_new(input_schema, vec![input_array]).unwrap();
|
||||
|
||||
let plan = plan_from_batch(input_batch).await;
|
||||
let projected = cast_to_table_schema(plan, &table_schema).unwrap();
|
||||
|
||||
// The projected schema's "data" field must carry arrow.json metadata
|
||||
// (the input field), not be silently dropped or miscast.
|
||||
let out_field = projected.schema().field_with_name("data").unwrap().clone();
|
||||
assert_eq!(out_field.data_type(), &input_type);
|
||||
assert_eq!(
|
||||
out_field
|
||||
.metadata()
|
||||
.get(ARROW_EXT_NAME_KEY)
|
||||
.map(|s| s.as_str()),
|
||||
Some(ARROW_JSON_EXT_NAME),
|
||||
"output field must still carry arrow.json metadata so lance-core can handle it"
|
||||
);
|
||||
|
||||
// The data must flow through correctly (3 rows, no panic).
|
||||
let result = collect(projected).await;
|
||||
assert_eq!(result.num_rows(), 3);
|
||||
let (v0, v2) = match input_type {
|
||||
DataType::Utf8 => {
|
||||
let col: &StringArray = result.column(0).as_any().downcast_ref().unwrap();
|
||||
(col.value(0).to_string(), col.value(2).to_string())
|
||||
}
|
||||
DataType::LargeUtf8 => {
|
||||
let col: &arrow_array::LargeStringArray =
|
||||
result.column(0).as_any().downcast_ref().unwrap();
|
||||
(col.value(0).to_string(), col.value(2).to_string())
|
||||
}
|
||||
_ => unreachable!(),
|
||||
};
|
||||
assert_eq!(v0, r#"{"x": 1}"#);
|
||||
assert!(result.column(0).is_null(1));
|
||||
assert_eq!(v2, r#"{"y": 2}"#);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -8,6 +8,7 @@ use std::{
|
||||
|
||||
use lance::{Dataset, dataset::refs};
|
||||
|
||||
use crate::table::merge::lsm::ShardWriterCache;
|
||||
use crate::{Error, error::Result, utils::background_cache::BackgroundCache};
|
||||
|
||||
/// A wrapper around a [Dataset] that provides consistency checks.
|
||||
@@ -18,6 +19,10 @@ use crate::{Error, error::Result, utils::background_cache::BackgroundCache};
|
||||
pub struct DatasetConsistencyWrapper {
|
||||
state: Arc<Mutex<DatasetState>>,
|
||||
consistency: ConsistencyMode,
|
||||
/// The single MemWAL `ShardWriter` for this dataset, co-located so it is
|
||||
/// cached for the session and shares the dataset's lifecycle. A dataset
|
||||
/// writes to one shard at a time. Shared by `Arc` across clones.
|
||||
shard_writer: Arc<ShardWriterCache>,
|
||||
}
|
||||
|
||||
/// The current dataset and whether it is pinned to a specific version.
|
||||
@@ -67,9 +72,15 @@ impl DatasetConsistencyWrapper {
|
||||
pinned_version: None,
|
||||
})),
|
||||
consistency,
|
||||
shard_writer: Arc::new(ShardWriterCache::default()),
|
||||
}
|
||||
}
|
||||
|
||||
/// The MemWAL `ShardWriter` cache co-located with this dataset.
|
||||
pub(crate) fn shard_writer(&self) -> &Arc<ShardWriterCache> {
|
||||
&self.shard_writer
|
||||
}
|
||||
|
||||
/// Get the current dataset.
|
||||
///
|
||||
/// Behavior depends on the consistency mode:
|
||||
|
||||
@@ -1,9 +1,12 @@
|
||||
use std::sync::Arc;
|
||||
|
||||
use futures::FutureExt;
|
||||
use lance::dataset::DeleteBuilder;
|
||||
// SPDX-License-Identifier: Apache-2.0
|
||||
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
use super::NativeTable;
|
||||
use super::{NativeTable, Predicate};
|
||||
use crate::Result;
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, Default)]
|
||||
@@ -21,17 +24,39 @@ pub struct DeleteResult {
|
||||
/// Internal implementation of the delete logic
|
||||
///
|
||||
/// This logic was moved from NativeTable::delete to keep table.rs clean.
|
||||
pub(crate) async fn execute_delete(table: &NativeTable, predicate: &str) -> Result<DeleteResult> {
|
||||
pub(crate) async fn execute_delete(
|
||||
table: &NativeTable,
|
||||
predicate: Predicate<'_>,
|
||||
) -> Result<DeleteResult> {
|
||||
table.dataset.ensure_mutable()?;
|
||||
let mut dataset = (*table.dataset.get().await?).clone();
|
||||
let delete_result = dataset.delete(predicate).boxed().await?;
|
||||
let num_deleted_rows = delete_result.num_deleted_rows;
|
||||
let version = dataset.version().version;
|
||||
table.dataset.update(dataset);
|
||||
Ok(DeleteResult {
|
||||
num_deleted_rows,
|
||||
version,
|
||||
})
|
||||
match predicate {
|
||||
Predicate::String(s) => {
|
||||
let mut dataset = (*table.dataset.get().await?).clone();
|
||||
let delete_result = dataset.delete(s).boxed().await?;
|
||||
let num_deleted_rows = delete_result.num_deleted_rows;
|
||||
let version = dataset.version().version;
|
||||
table.dataset.update(dataset);
|
||||
Ok(DeleteResult {
|
||||
num_deleted_rows,
|
||||
version,
|
||||
})
|
||||
}
|
||||
Predicate::Expr(expr) => {
|
||||
let dataset = table.dataset.get().await?;
|
||||
let delete_result = DeleteBuilder::from_expr(Arc::clone(&dataset), expr.clone())
|
||||
.execute()
|
||||
.await?;
|
||||
let num_deleted_rows = delete_result.num_deleted_rows;
|
||||
let version = delete_result.new_dataset.version().version;
|
||||
table.dataset.update(
|
||||
Arc::try_unwrap(delete_result.new_dataset).unwrap_or_else(|arc| (*arc).clone()),
|
||||
);
|
||||
Ok(DeleteResult {
|
||||
num_deleted_rows,
|
||||
version,
|
||||
})
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
@@ -176,4 +201,100 @@ mod tests {
|
||||
"Table version must increment after delete operation"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_delete_expr() {
|
||||
use datafusion_expr::{col, lit};
|
||||
|
||||
let conn = connect("memory://").execute().await.unwrap();
|
||||
|
||||
// 1. Create a table with values 0 to 9
|
||||
let schema = Arc::new(Schema::new(vec![Field::new("i", DataType::Int32, false)]));
|
||||
let batch = RecordBatch::try_new(
|
||||
schema.clone(),
|
||||
vec![Arc::new(Int32Array::from_iter_values(0..10))],
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let table = conn
|
||||
.create_table("test_delete_expr", batch)
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// 2. Verify initial state
|
||||
assert_eq!(table.count_rows(None).await.unwrap(), 10);
|
||||
let initial_version = table.version().await.unwrap();
|
||||
|
||||
// 3. Execute Delete with Expr (removes values > 5)
|
||||
let expr = col("i").gt(lit(5));
|
||||
table.delete(&expr).await.unwrap();
|
||||
|
||||
// 4. Verify results
|
||||
assert_eq!(table.count_rows(None).await.unwrap(), 6); // 0, 1, 2, 3, 4, 5 remain
|
||||
let current_version = table.version().await.unwrap();
|
||||
assert!(
|
||||
current_version > initial_version,
|
||||
"Table version must increment after delete_expr operation"
|
||||
);
|
||||
|
||||
// 5. Verify specific data consistency
|
||||
let batches = table
|
||||
.query()
|
||||
.execute()
|
||||
.await
|
||||
.unwrap()
|
||||
.try_collect::<Vec<_>>()
|
||||
.await
|
||||
.unwrap();
|
||||
let batch = &batches[0];
|
||||
let array = batch
|
||||
.column(0)
|
||||
.as_any()
|
||||
.downcast_ref::<Int32Array>()
|
||||
.unwrap();
|
||||
|
||||
// Ensure no value > 5 exists
|
||||
for val in array.iter() {
|
||||
assert!(val.unwrap() <= 5);
|
||||
}
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_delete_expr_increments_version() {
|
||||
use datafusion_expr::lit;
|
||||
|
||||
let conn = connect("memory://").execute().await.unwrap();
|
||||
|
||||
// Create a table with 5 rows
|
||||
let batch = record_batch!(("id", Int32, [1, 2, 3, 4, 5])).unwrap();
|
||||
|
||||
let table = conn
|
||||
.create_table("test_delete_expr_noop", batch)
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// Capture the initial state (Rows = 5, Version = 1)
|
||||
let initial_rows = table.count_rows(None).await.unwrap();
|
||||
let initial_version = table.version().await.unwrap();
|
||||
|
||||
assert_eq!(initial_rows, 5);
|
||||
let expr = lit(false);
|
||||
table.delete(&expr).await.unwrap();
|
||||
|
||||
// Rows should still be 5
|
||||
let current_rows = table.count_rows(None).await.unwrap();
|
||||
assert_eq!(
|
||||
current_rows, initial_rows,
|
||||
"Data should not change when predicate is false"
|
||||
);
|
||||
|
||||
// version check
|
||||
let current_version = table.version().await.unwrap();
|
||||
assert!(
|
||||
current_version > initial_version,
|
||||
"Table version must increment after delete_expr operation"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -41,6 +41,16 @@ pub struct MergeResult {
|
||||
/// A value of 1 means the operation succeeded on the first try.
|
||||
#[serde(default)]
|
||||
pub num_attempts: u32,
|
||||
/// Total number of rows written.
|
||||
///
|
||||
/// On the standard `merge_insert` path this equals
|
||||
/// `num_inserted_rows + num_updated_rows`. On the MemWAL LSM write path the
|
||||
/// insert/update breakdown is not known until compaction; in that mode
|
||||
/// `num_inserted_rows`, `num_updated_rows`, `num_deleted_rows`, `version`
|
||||
/// and `num_attempts` are all `0` and this field holds the total number of
|
||||
/// rows written through the shard writer.
|
||||
#[serde(default)]
|
||||
pub num_rows: u64,
|
||||
}
|
||||
|
||||
/// A builder used to create and run a merge insert operation
|
||||
@@ -57,6 +67,8 @@ pub struct MergeInsertBuilder {
|
||||
pub(crate) when_not_matched_by_source_delete_filt: Option<String>,
|
||||
pub(crate) timeout: Option<Duration>,
|
||||
pub(crate) use_index: bool,
|
||||
pub(crate) use_lsm_write: Option<bool>,
|
||||
pub(crate) validate_single_shard: bool,
|
||||
}
|
||||
|
||||
impl MergeInsertBuilder {
|
||||
@@ -71,6 +83,8 @@ impl MergeInsertBuilder {
|
||||
when_not_matched_by_source_delete_filt: None,
|
||||
timeout: None,
|
||||
use_index: true,
|
||||
use_lsm_write: None,
|
||||
validate_single_shard: true,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -150,6 +164,34 @@ impl MergeInsertBuilder {
|
||||
self
|
||||
}
|
||||
|
||||
/// Controls whether `merge_insert` uses the MemWAL LSM write path.
|
||||
///
|
||||
/// By default (unset), a `merge_insert` on a table with an
|
||||
/// [`LsmWriteSpec`](super::LsmWriteSpec) installed is routed through
|
||||
/// Lance's MemWAL shard writer, and a table without one uses the standard
|
||||
/// path. Calling this with `false` forces the standard path even when a
|
||||
/// spec is set. Calling it with `true` requires a spec — `merge_insert`
|
||||
/// errors if none is installed.
|
||||
pub fn use_lsm_write(&mut self, use_lsm_write: bool) -> &mut Self {
|
||||
self.use_lsm_write = Some(use_lsm_write);
|
||||
self
|
||||
}
|
||||
|
||||
/// Controls how an LSM `merge_insert` checks that its input targets a
|
||||
/// single shard.
|
||||
///
|
||||
/// When a table has an LSM write spec, every row in a `merge_insert` call
|
||||
/// must route to the same shard. When `true` (the default), every row is
|
||||
/// inspected to verify this. When `false`, only the first row is inspected
|
||||
/// and the shard it routes to is used for the whole input — a faster path
|
||||
/// for callers that have already pre-sharded their input.
|
||||
///
|
||||
/// Has no effect on tables without an LSM write spec.
|
||||
pub fn validate_single_shard(&mut self, validate_single_shard: bool) -> &mut Self {
|
||||
self.validate_single_shard = validate_single_shard;
|
||||
self
|
||||
}
|
||||
|
||||
/// Executes the merge insert operation
|
||||
///
|
||||
/// Returns version and statistics about the merge operation including the number of rows
|
||||
@@ -167,6 +209,23 @@ pub(crate) async fn execute_merge_insert(
|
||||
params: MergeInsertBuilder,
|
||||
new_data: Box<dyn RecordBatchReader + Send>,
|
||||
) -> Result<MergeResult> {
|
||||
match lsm::lsm_dispatch_decision(table, ¶ms).await? {
|
||||
lsm::LsmDispatch::Lsm(plan) => {
|
||||
let future =
|
||||
lsm::execute_lsm_merge_insert(table, plan, params.validate_single_shard, new_data);
|
||||
return match params.timeout {
|
||||
Some(timeout) => match tokio::time::timeout(timeout, future).await {
|
||||
Ok(result) => result,
|
||||
Err(_) => Err(Error::Runtime {
|
||||
message: "merge insert timed out".to_string(),
|
||||
}),
|
||||
},
|
||||
None => future.await,
|
||||
};
|
||||
}
|
||||
lsm::LsmDispatch::Standard => {}
|
||||
}
|
||||
|
||||
let dataset = table.dataset.get().await?;
|
||||
let mut builder = LanceMergeInsertBuilder::try_new(dataset.clone(), params.on)?;
|
||||
match (
|
||||
@@ -219,6 +278,7 @@ pub(crate) async fn execute_merge_insert(
|
||||
num_inserted_rows: stats.num_inserted_rows,
|
||||
num_deleted_rows: stats.num_deleted_rows,
|
||||
num_attempts: stats.num_attempts,
|
||||
num_rows: stats.num_inserted_rows + stats.num_updated_rows,
|
||||
})
|
||||
}
|
||||
|
||||
@@ -327,3 +387,366 @@ mod tests {
|
||||
assert_eq!(table.count_rows(None).await.unwrap(), 25);
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod lsm_tests {
|
||||
use std::sync::Arc;
|
||||
|
||||
use arrow_array::{
|
||||
Int64Array, RecordBatch, RecordBatchIterator, RecordBatchReader, StringArray,
|
||||
};
|
||||
use arrow_schema::{DataType, Field, Schema};
|
||||
use tempfile::{TempDir, tempdir};
|
||||
|
||||
use crate::connect;
|
||||
use crate::error::Error;
|
||||
use crate::table::{LsmWriteSpec, Table};
|
||||
|
||||
/// A reader of `[id: Int64, value: Int64]` rows; `value` is `0..n`.
|
||||
fn id_value_reader(ids: Vec<i64>) -> Box<dyn RecordBatchReader + Send> {
|
||||
let schema = Arc::new(Schema::new(vec![
|
||||
Field::new("id", DataType::Int64, false),
|
||||
Field::new("value", DataType::Int64, false),
|
||||
]));
|
||||
let n = ids.len() as i64;
|
||||
let batch = RecordBatch::try_new(
|
||||
schema.clone(),
|
||||
vec![
|
||||
Arc::new(Int64Array::from(ids)),
|
||||
Arc::new(Int64Array::from_iter_values(0..n)),
|
||||
],
|
||||
)
|
||||
.unwrap();
|
||||
Box::new(RecordBatchIterator::new(vec![Ok(batch)], schema))
|
||||
}
|
||||
|
||||
/// A reader of `[id: Int64, region: Utf8]` rows.
|
||||
fn id_region_reader(rows: Vec<(i64, &str)>) -> Box<dyn RecordBatchReader + Send> {
|
||||
let schema = Arc::new(Schema::new(vec![
|
||||
Field::new("id", DataType::Int64, false),
|
||||
Field::new("region", DataType::Utf8, false),
|
||||
]));
|
||||
let ids: Vec<i64> = rows.iter().map(|(id, _)| *id).collect();
|
||||
let regions: Vec<&str> = rows.iter().map(|(_, region)| *region).collect();
|
||||
let batch = RecordBatch::try_new(
|
||||
schema.clone(),
|
||||
vec![
|
||||
Arc::new(Int64Array::from(ids)),
|
||||
Arc::new(StringArray::from(regions)),
|
||||
],
|
||||
)
|
||||
.unwrap();
|
||||
Box::new(RecordBatchIterator::new(vec![Ok(batch)], schema))
|
||||
}
|
||||
|
||||
/// A multi-batch reader of `[id: Int64, region: Utf8]` rows.
|
||||
fn id_region_multi_reader(batches: Vec<Vec<(i64, &str)>>) -> Box<dyn RecordBatchReader + Send> {
|
||||
let schema = Arc::new(Schema::new(vec![
|
||||
Field::new("id", DataType::Int64, false),
|
||||
Field::new("region", DataType::Utf8, false),
|
||||
]));
|
||||
let records: Vec<_> = batches
|
||||
.into_iter()
|
||||
.map(|rows| {
|
||||
let ids: Vec<i64> = rows.iter().map(|(id, _)| *id).collect();
|
||||
let regions: Vec<&str> = rows.iter().map(|(_, region)| *region).collect();
|
||||
Ok(RecordBatch::try_new(
|
||||
schema.clone(),
|
||||
vec![
|
||||
Arc::new(Int64Array::from(ids)),
|
||||
Arc::new(StringArray::from(regions)),
|
||||
],
|
||||
)
|
||||
.unwrap())
|
||||
})
|
||||
.collect();
|
||||
Box::new(RecordBatchIterator::new(records, schema))
|
||||
}
|
||||
|
||||
/// Create an `[id, value]` table with `id` as the unenforced primary key.
|
||||
async fn id_value_table(dir: &TempDir) -> Table {
|
||||
let conn = connect(dir.path().to_str().unwrap())
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
let table = conn
|
||||
.create_table("t", id_value_reader(vec![1, 2, 3]))
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
table.set_unenforced_primary_key(["id"]).await.unwrap();
|
||||
table
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn lsm_merge_insert_bucket() {
|
||||
let dir = tempdir().unwrap();
|
||||
let table = id_value_table(&dir).await;
|
||||
// num_buckets = 1: every row routes to the single bucket.
|
||||
table
|
||||
.set_lsm_write_spec(LsmWriteSpec::bucket("id", 1))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// Empty `on` defaults to the primary key.
|
||||
let mut builder = table.merge_insert(&[]);
|
||||
builder
|
||||
.when_matched_update_all(None)
|
||||
.when_not_matched_insert_all();
|
||||
let result = builder
|
||||
.execute(id_value_reader(vec![3, 4, 5]))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// LSM path: rows go to the MemWAL, the breakdown is unknown until
|
||||
// compaction, so only `num_rows` is populated.
|
||||
assert_eq!(result.num_rows, 3);
|
||||
assert_eq!(result.version, 0);
|
||||
assert_eq!(result.num_inserted_rows, 0);
|
||||
assert_eq!(result.num_updated_rows, 0);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn lsm_merge_insert_unsharded() {
|
||||
let dir = tempdir().unwrap();
|
||||
let table = id_value_table(&dir).await;
|
||||
table
|
||||
.set_lsm_write_spec(LsmWriteSpec::unsharded())
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let mut builder = table.merge_insert(&["id"]);
|
||||
builder
|
||||
.when_matched_update_all(None)
|
||||
.when_not_matched_insert_all();
|
||||
let result = builder
|
||||
.execute(id_value_reader(vec![10, 11, 12, 13]))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(result.num_rows, 4);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn lsm_merge_insert_identity() {
|
||||
let dir = tempdir().unwrap();
|
||||
let conn = connect(dir.path().to_str().unwrap())
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
let table = conn
|
||||
.create_table("t", id_region_reader(vec![(1, "us"), (2, "us")]))
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
table.set_unenforced_primary_key(["id"]).await.unwrap();
|
||||
table
|
||||
.set_lsm_write_spec(LsmWriteSpec::identity("region"))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// All rows share one identity value, so they route to one shard.
|
||||
let mut builder = table.merge_insert(&[]);
|
||||
builder
|
||||
.when_matched_update_all(None)
|
||||
.when_not_matched_insert_all();
|
||||
let result = builder
|
||||
.execute(id_region_reader(vec![(3, "us"), (4, "us")]))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(result.num_rows, 2);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn lsm_merge_insert_use_lsm_write_false_falls_back() {
|
||||
let dir = tempdir().unwrap();
|
||||
let table = id_value_table(&dir).await;
|
||||
table
|
||||
.set_lsm_write_spec(LsmWriteSpec::bucket("id", 1))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// use_lsm_write(false) opts out: the standard path runs and commits.
|
||||
let mut builder = table.merge_insert(&["id"]);
|
||||
builder.when_not_matched_insert_all().use_lsm_write(false);
|
||||
let result = builder
|
||||
.execute(id_value_reader(vec![3, 4, 5]))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
assert_eq!(result.num_inserted_rows, 2);
|
||||
assert_eq!(table.count_rows(None).await.unwrap(), 5);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn lsm_merge_insert_rejects_on_not_primary_key() {
|
||||
let dir = tempdir().unwrap();
|
||||
let table = id_value_table(&dir).await;
|
||||
table
|
||||
.set_lsm_write_spec(LsmWriteSpec::bucket("id", 1))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let mut builder = table.merge_insert(&["value"]);
|
||||
builder
|
||||
.when_matched_update_all(None)
|
||||
.when_not_matched_insert_all();
|
||||
let err = builder.execute(id_value_reader(vec![1])).await.unwrap_err();
|
||||
assert!(matches!(err, Error::InvalidInput { .. }), "got {err:?}");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn lsm_merge_insert_rejects_non_upsert() {
|
||||
let dir = tempdir().unwrap();
|
||||
let table = id_value_table(&dir).await;
|
||||
table
|
||||
.set_lsm_write_spec(LsmWriteSpec::bucket("id", 1))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// Insert-only (no when_matched_update_all) is not the upsert shape.
|
||||
let mut builder = table.merge_insert(&[]);
|
||||
builder.when_not_matched_insert_all();
|
||||
let err = builder.execute(id_value_reader(vec![4])).await.unwrap_err();
|
||||
assert!(matches!(err, Error::InvalidInput { .. }), "got {err:?}");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn lsm_close_writers_then_reopen() {
|
||||
let dir = tempdir().unwrap();
|
||||
let table = id_value_table(&dir).await;
|
||||
table
|
||||
.set_lsm_write_spec(LsmWriteSpec::bucket("id", 1))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let mut builder = table.merge_insert(&[]);
|
||||
builder
|
||||
.when_matched_update_all(None)
|
||||
.when_not_matched_insert_all();
|
||||
builder.execute(id_value_reader(vec![7, 8])).await.unwrap();
|
||||
|
||||
table.close_lsm_writers().await.unwrap();
|
||||
|
||||
// The writer reopens lazily on the next merge_insert.
|
||||
let mut builder = table.merge_insert(&[]);
|
||||
builder
|
||||
.when_matched_update_all(None)
|
||||
.when_not_matched_insert_all();
|
||||
let result = builder.execute(id_value_reader(vec![9])).await.unwrap();
|
||||
assert_eq!(result.num_rows, 1);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn lsm_merge_insert_multi_batch() {
|
||||
let dir = tempdir().unwrap();
|
||||
let conn = connect(dir.path().to_str().unwrap())
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
let table = conn
|
||||
.create_table("t", id_region_reader(vec![(1, "us")]))
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
table.set_unenforced_primary_key(["id"]).await.unwrap();
|
||||
table
|
||||
.set_lsm_write_spec(LsmWriteSpec::identity("region"))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// Multiple batches that all route to one shard are written together.
|
||||
let mut builder = table.merge_insert(&[]);
|
||||
builder
|
||||
.when_matched_update_all(None)
|
||||
.when_not_matched_insert_all();
|
||||
let result = builder
|
||||
.execute(id_region_multi_reader(vec![
|
||||
vec![(2, "us"), (3, "us")],
|
||||
vec![(4, "us")],
|
||||
]))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(result.num_rows, 3);
|
||||
|
||||
// Batches that route to different shards are rejected; the validation
|
||||
// runs before any write, so no partial write is left behind.
|
||||
let mut builder = table.merge_insert(&[]);
|
||||
builder
|
||||
.when_matched_update_all(None)
|
||||
.when_not_matched_insert_all();
|
||||
let err = builder
|
||||
.execute(id_region_multi_reader(vec![
|
||||
vec![(5, "us")],
|
||||
vec![(6, "eu")],
|
||||
]))
|
||||
.await
|
||||
.unwrap_err();
|
||||
assert!(matches!(err, Error::InvalidInput { .. }), "got {err:?}");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn lsm_merge_insert_use_lsm_write_true_requires_spec() {
|
||||
let dir = tempdir().unwrap();
|
||||
// id_value_table sets a primary key but no LSM write spec.
|
||||
let table = id_value_table(&dir).await;
|
||||
|
||||
let mut builder = table.merge_insert(&["id"]);
|
||||
builder
|
||||
.when_matched_update_all(None)
|
||||
.when_not_matched_insert_all()
|
||||
.use_lsm_write(true);
|
||||
let err = builder.execute(id_value_reader(vec![4])).await.unwrap_err();
|
||||
assert!(matches!(err, Error::InvalidInput { .. }), "got {err:?}");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn lsm_merge_insert_rejects_second_shard() {
|
||||
let dir = tempdir().unwrap();
|
||||
let conn = connect(dir.path().to_str().unwrap())
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
let table = conn
|
||||
.create_table("t", id_region_reader(vec![(1, "us")]))
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
table.set_unenforced_primary_key(["id"]).await.unwrap();
|
||||
table
|
||||
.set_lsm_write_spec(LsmWriteSpec::identity("region"))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// The first merge_insert opens the single writer for shard "us".
|
||||
let mut builder = table.merge_insert(&[]);
|
||||
builder
|
||||
.when_matched_update_all(None)
|
||||
.when_not_matched_insert_all();
|
||||
builder
|
||||
.execute(id_region_reader(vec![(2, "us")]))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// A merge_insert routing to a different shard is rejected.
|
||||
let mut builder = table.merge_insert(&[]);
|
||||
builder
|
||||
.when_matched_update_all(None)
|
||||
.when_not_matched_insert_all();
|
||||
let err = builder
|
||||
.execute(id_region_reader(vec![(3, "eu")]))
|
||||
.await
|
||||
.unwrap_err();
|
||||
assert!(matches!(err, Error::InvalidInput { .. }), "got {err:?}");
|
||||
|
||||
// After closing the writer, a different shard can be written.
|
||||
table.close_lsm_writers().await.unwrap();
|
||||
let mut builder = table.merge_insert(&[]);
|
||||
builder
|
||||
.when_matched_update_all(None)
|
||||
.when_not_matched_insert_all();
|
||||
builder
|
||||
.execute(id_region_reader(vec![(4, "eu")]))
|
||||
.await
|
||||
.unwrap();
|
||||
}
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user