Compare commits

..

1 Commits

Author SHA1 Message Date
lancedb automation
edf8159780 chore: update lance dependency to v2.0.0-beta.6 2026-01-09 23:54:25 +00:00
45 changed files with 673 additions and 1048 deletions

View File

@@ -1,5 +1,5 @@
[tool.bumpversion]
current_version = "0.24.0-beta.0"
current_version = "0.23.1"
parse = """(?x)
(?P<major>0|[1-9]\\d*)\\.
(?P<minor>0|[1-9]\\d*)\\.

View File

@@ -75,13 +75,6 @@ jobs:
VERSION="${VERSION#v}"
BRANCH_NAME="codex/update-lance-${VERSION//[^a-zA-Z0-9]/-}"
# Use "chore" for beta/rc versions, "feat" for stable releases
if [[ "${VERSION}" == *beta* ]] || [[ "${VERSION}" == *rc* ]]; then
COMMIT_TYPE="chore"
else
COMMIT_TYPE="feat"
fi
cat <<EOF >/tmp/codex-prompt.txt
You are running inside the lancedb repository on a GitHub Actions runner. Update the Lance dependency to version ${VERSION} and prepare a pull request for maintainers to review.
@@ -91,10 +84,10 @@ jobs:
3. After clippy succeeds, run "cargo fmt --all" to format the workspace.
4. Ensure the repository is clean except for intentional changes. Inspect "git status --short" and "git diff" to confirm the dependency update and any required fixes.
5. Create and switch to a new branch named "${BRANCH_NAME}" (replace any duplicated hyphens if necessary).
6. Stage all relevant files with "git add -A". Commit using the message "${COMMIT_TYPE}: update lance dependency to v${VERSION}".
6. Stage all relevant files with "git add -A". Commit using the message "chore: update lance dependency to v${VERSION}".
7. Push the branch to origin. If the branch already exists, force-push your changes.
8. env "GH_TOKEN" is available, use "gh" tools for github related operations like creating pull request.
9. Create a pull request targeting "main" with title "${COMMIT_TYPE}: update lance dependency to v${VERSION}". First, write the PR body to /tmp/pr-body.md using a heredoc (cat <<'EOF' > /tmp/pr-body.md). The body should summarize the dependency bump, clippy/fmt verification, and link the triggering tag (${TAG}). Then run "gh pr create --body-file /tmp/pr-body.md".
9. Create a pull request targeting "main" with title "chore: update lance dependency to v${VERSION}". In the body, summarize the dependency bump, clippy/fmt verification, and link the triggering tag (${TAG}).
10. After creating the PR, display the PR URL, "git status --short", and a concise summary of the commands run and their results.
Constraints:

View File

@@ -167,13 +167,13 @@ jobs:
- name: Build
run: |
$env:VCPKG_ROOT = $env:VCPKG_INSTALLATION_ROOT
cargo build --profile ci --features aws,remote --tests --locked --target ${{ matrix.target }}
cargo build --profile ci --features remote --tests --locked --target ${{ matrix.target }}
- name: Run tests
# Can only run tests when target matches host
if: ${{ matrix.target == 'x86_64-pc-windows-msvc' }}
run: |
$env:VCPKG_ROOT = $env:VCPKG_INSTALLATION_ROOT
cargo test --profile ci --features aws,remote --locked
cargo test --profile ci --features remote --locked
msrv:
# Check the minimum supported Rust version

822
Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -15,39 +15,39 @@ categories = ["database-implementations"]
rust-version = "1.78.0"
[workspace.dependencies]
lance = { "version" = "=1.0.3", default-features = false, "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
lance-core = { "version" = "=1.0.3", "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
lance-datagen = { "version" = "=1.0.3", "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
lance-file = { "version" = "=1.0.3", "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
lance-io = { "version" = "=1.0.3", default-features = false, "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
lance-index = { "version" = "=1.0.3", "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
lance-linalg = { "version" = "=1.0.3", "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace = { "version" = "=1.0.3", "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace-impls = { "version" = "=1.0.3", default-features = false, "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
lance-table = { "version" = "=1.0.3", "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
lance-testing = { "version" = "=1.0.3", "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
lance-datafusion = { "version" = "=1.0.3", "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
lance-encoding = { "version" = "=1.0.3", "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
lance-arrow = { "version" = "=1.0.3", "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
lance = { "version" = "=2.0.0-beta.6", default-features = false, "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-core = { "version" = "=2.0.0-beta.6", "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-datagen = { "version" = "=2.0.0-beta.6", "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-file = { "version" = "=2.0.0-beta.6", "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-io = { "version" = "=2.0.0-beta.6", default-features = false, "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-index = { "version" = "=2.0.0-beta.6", "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-linalg = { "version" = "=2.0.0-beta.6", "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace = { "version" = "=2.0.0-beta.6", "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace-impls = { "version" = "=2.0.0-beta.6", default-features = false, "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-table = { "version" = "=2.0.0-beta.6", "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-testing = { "version" = "=2.0.0-beta.6", "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-datafusion = { "version" = "=2.0.0-beta.6", "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-encoding = { "version" = "=2.0.0-beta.6", "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
lance-arrow = { "version" = "=2.0.0-beta.6", "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
ahash = "0.8"
# Note that this one does not include pyarrow
arrow = { version = "56.2", optional = false }
arrow-array = "56.2"
arrow-data = "56.2"
arrow-ipc = "56.2"
arrow-ord = "56.2"
arrow-schema = "56.2"
arrow-select = "56.2"
arrow-cast = "56.2"
arrow = { version = "57.1", optional = false }
arrow-array = "57.1"
arrow-data = "57.1"
arrow-ipc = "57.1"
arrow-ord = "57.1"
arrow-schema = "57.1"
arrow-select = "57.1"
arrow-cast = "57.1"
async-trait = "0"
datafusion = { version = "50.1", default-features = false }
datafusion-catalog = "50.1"
datafusion-common = { version = "50.1", default-features = false }
datafusion-execution = "50.1"
datafusion-expr = "50.1"
datafusion-physical-plan = "50.1"
datafusion = { version = "51.0", default-features = false }
datafusion-catalog = "51.0"
datafusion-common = { version = "51.0", default-features = false }
datafusion-execution = "51.0"
datafusion-expr = "51.0"
datafusion-physical-plan = "51.0"
env_logger = "0.11"
half = { "version" = "2.6.0", default-features = false, features = [
half = { "version" = "2.7.1", default-features = false, features = [
"num-traits",
] }
futures = "0"

View File

@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
<dependency>
<groupId>com.lancedb</groupId>
<artifactId>lancedb-core</artifactId>
<version>0.24.0-beta.0</version>
<version>0.23.1</version>
</dependency>
```

View File

@@ -8,7 +8,7 @@
<parent>
<groupId>com.lancedb</groupId>
<artifactId>lancedb-parent</artifactId>
<version>0.24.0-beta.0</version>
<version>0.23.1-final.0</version>
<relativePath>../pom.xml</relativePath>
</parent>

View File

@@ -6,7 +6,7 @@
<groupId>com.lancedb</groupId>
<artifactId>lancedb-parent</artifactId>
<version>0.24.0-beta.0</version>
<version>0.23.1-final.0</version>
<packaging>pom</packaging>
<name>${project.artifactId}</name>
<description>LanceDB Java SDK Parent POM</description>

View File

@@ -1,7 +1,7 @@
[package]
name = "lancedb-nodejs"
edition.workspace = true
version = "0.24.0-beta.0"
version = "0.23.1"
license.workspace = true
description.workspace = true
repository.workspace = true
@@ -36,6 +36,6 @@ aws-lc-rs = "=1.13.0"
napi-build = "2.1"
[features]
default = ["remote", "lancedb/aws", "lancedb/gcs", "lancedb/azure", "lancedb/dynamodb", "lancedb/oss", "lancedb/huggingface"]
default = ["remote", "lancedb/default"]
fp16kernels = ["lancedb/fp16kernels"]
remote = ["lancedb/remote"]

View File

@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-darwin-arm64",
"version": "0.24.0-beta.0",
"version": "0.23.1",
"os": ["darwin"],
"cpu": ["arm64"],
"main": "lancedb.darwin-arm64.node",

View File

@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-darwin-x64",
"version": "0.24.0-beta.0",
"version": "0.23.1",
"os": ["darwin"],
"cpu": ["x64"],
"main": "lancedb.darwin-x64.node",

View File

@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-arm64-gnu",
"version": "0.24.0-beta.0",
"version": "0.23.1",
"os": ["linux"],
"cpu": ["arm64"],
"main": "lancedb.linux-arm64-gnu.node",

View File

@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-arm64-musl",
"version": "0.24.0-beta.0",
"version": "0.23.1",
"os": ["linux"],
"cpu": ["arm64"],
"main": "lancedb.linux-arm64-musl.node",

View File

@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-x64-gnu",
"version": "0.24.0-beta.0",
"version": "0.23.1",
"os": ["linux"],
"cpu": ["x64"],
"main": "lancedb.linux-x64-gnu.node",

View File

@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-x64-musl",
"version": "0.24.0-beta.0",
"version": "0.23.1",
"os": ["linux"],
"cpu": ["x64"],
"main": "lancedb.linux-x64-musl.node",

View File

@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-win32-arm64-msvc",
"version": "0.24.0-beta.0",
"version": "0.23.1",
"os": [
"win32"
],

View File

@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-win32-x64-msvc",
"version": "0.24.0-beta.0",
"version": "0.23.1",
"os": ["win32"],
"cpu": ["x64"],
"main": "lancedb.win32-x64-msvc.node",

View File

@@ -1,12 +1,12 @@
{
"name": "@lancedb/lancedb",
"version": "0.24.0-beta.0",
"version": "0.23.1",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "@lancedb/lancedb",
"version": "0.24.0-beta.0",
"version": "0.23.1",
"cpu": [
"x64",
"arm64"

View File

@@ -11,7 +11,7 @@
"ann"
],
"private": false,
"version": "0.24.0-beta.0",
"version": "0.23.1",
"main": "dist/index.js",
"exports": {
".": "./dist/index.js",

View File

@@ -1,5 +1,5 @@
[tool.bumpversion]
current_version = "0.27.0"
current_version = "0.26.1"
parse = """(?x)
(?P<major>0|[1-9]\\d*)\\.
(?P<minor>0|[1-9]\\d*)\\.

View File

@@ -1,6 +1,6 @@
[package]
name = "lancedb-python"
version = "0.27.0"
version = "0.26.1"
edition.workspace = true
description = "Python bindings for LanceDB"
license.workspace = true
@@ -14,15 +14,15 @@ name = "_lancedb"
crate-type = ["cdylib"]
[dependencies]
arrow = { version = "56.2", features = ["pyarrow"] }
arrow = { workspace = true, features = ["pyarrow"] }
async-trait = "0.1"
lancedb = { path = "../rust/lancedb", default-features = false }
lance-core.workspace = true
lance-namespace.workspace = true
lance-io.workspace = true
env_logger.workspace = true
pyo3 = { version = "0.25", features = ["extension-module", "abi3-py39"] }
pyo3-async-runtimes = { version = "0.25", features = [
pyo3 = { version = "0.26", features = ["extension-module", "abi3-py39"] }
pyo3-async-runtimes = { version = "0.26", features = [
"attributes",
"tokio-runtime",
] }
@@ -32,12 +32,12 @@ snafu.workspace = true
tokio = { version = "1.40", features = ["sync"] }
[build-dependencies]
pyo3-build-config = { version = "0.25", features = [
pyo3-build-config = { version = "0.26", features = [
"extension-module",
"abi3-py39",
] }
[features]
default = ["remote", "lancedb/aws", "lancedb/gcs", "lancedb/azure", "lancedb/dynamodb", "lancedb/oss", "lancedb/huggingface"]
default = ["remote", "lancedb/default"]
fp16kernels = ["lancedb/fp16kernels"]
remote = ["lancedb/remote"]

View File

@@ -179,7 +179,6 @@ class Table:
cleanup_since_ms: Optional[int] = None,
delete_unverified: Optional[bool] = None,
) -> OptimizeStats: ...
async def uri(self) -> str: ...
@property
def tags(self) -> Tags: ...
def query(self) -> Query: ...

View File

@@ -655,14 +655,6 @@ class RemoteTable(Table):
def stats(self):
return LOOP.run(self._table.stats())
@property
def uri(self) -> str:
"""The table URI (storage location).
For remote tables, this fetches the location from the server via describe.
"""
return LOOP.run(self._table.uri())
def take_offsets(self, offsets: list[int]) -> LanceTakeQueryBuilder:
return LanceTakeQueryBuilder(self._table.take_offsets(offsets))

View File

@@ -2218,10 +2218,6 @@ class LanceTable(Table):
def stats(self) -> TableStatistics:
return LOOP.run(self._table.stats())
@property
def uri(self) -> str:
return LOOP.run(self._table.uri())
def create_scalar_index(
self,
column: str,
@@ -3610,20 +3606,6 @@ class AsyncTable:
"""
return await self._inner.stats()
async def uri(self) -> str:
"""
Get the table URI (storage location).
For remote tables, this fetches the location from the server via describe.
For local tables, this returns the dataset URI.
Returns
-------
str
The full storage location of the table (e.g., S3/GCS path).
"""
return await self._inner.uri()
async def add(
self,
data: DATA,

View File

@@ -2,27 +2,12 @@
# SPDX-FileCopyrightText: Copyright The LanceDB Authors
from datetime import timedelta
from lancedb.db import AsyncConnection, DBConnection
import lancedb
import pytest
import pytest_asyncio
def pandas_string_type():
"""Return the PyArrow string type that pandas uses for string columns.
pandas 3.0+ uses large_string for string columns, pandas 2.x uses string.
"""
import pandas as pd
import pyarrow as pa
version = tuple(int(x) for x in pd.__version__.split(".")[:2])
if version >= (3, 0):
return pa.large_utf8()
return pa.utf8()
# Use an in-memory database for most tests.
@pytest.fixture
def mem_db() -> DBConnection:

View File

@@ -268,8 +268,6 @@ async def test_create_table_from_iterator_async(mem_db_async: lancedb.AsyncConne
def test_create_exist_ok(tmp_db: lancedb.DBConnection):
from conftest import pandas_string_type
data = pd.DataFrame(
{
"vector": [[3.1, 4.1], [5.9, 26.5]],
@@ -288,11 +286,10 @@ def test_create_exist_ok(tmp_db: lancedb.DBConnection):
assert tbl.schema == tbl2.schema
assert len(tbl) == len(tbl2)
# pandas 3.0+ uses large_string, pandas 2.x uses string
schema = pa.schema(
[
pa.field("vector", pa.list_(pa.float32(), list_size=2)),
pa.field("item", pandas_string_type()),
pa.field("item", pa.utf8()),
pa.field("price", pa.float64()),
]
)
@@ -302,7 +299,7 @@ def test_create_exist_ok(tmp_db: lancedb.DBConnection):
bad_schema = pa.schema(
[
pa.field("vector", pa.list_(pa.float32(), list_size=2)),
pa.field("item", pandas_string_type()),
pa.field("item", pa.utf8()),
pa.field("price", pa.float64()),
pa.field("extra", pa.float32()),
]
@@ -368,8 +365,6 @@ async def test_create_mode_async(tmp_db_async: lancedb.AsyncConnection):
@pytest.mark.asyncio
async def test_create_exist_ok_async(tmp_db_async: lancedb.AsyncConnection):
from conftest import pandas_string_type
data = pd.DataFrame(
{
"vector": [[3.1, 4.1], [5.9, 26.5]],
@@ -387,11 +382,10 @@ async def test_create_exist_ok_async(tmp_db_async: lancedb.AsyncConnection):
assert tbl.name == tbl2.name
assert await tbl.schema() == await tbl2.schema()
# pandas 3.0+ uses large_string, pandas 2.x uses string
schema = pa.schema(
[
pa.field("vector", pa.list_(pa.float32(), list_size=2)),
pa.field("item", pandas_string_type()),
pa.field("item", pa.utf8()),
pa.field("price", pa.float64()),
]
)
@@ -601,8 +595,6 @@ def test_open_table_sync(tmp_db: lancedb.DBConnection):
@pytest.mark.asyncio
async def test_open_table(tmp_path):
from conftest import pandas_string_type
db = await lancedb.connect_async(tmp_path)
data = pd.DataFrame(
{
@@ -622,11 +614,10 @@ async def test_open_table(tmp_path):
)
is not None
)
# pandas 3.0+ uses large_string, pandas 2.x uses string
assert await tbl.schema() == pa.schema(
{
"vector": pa.list_(pa.float32(), list_size=2),
"item": pandas_string_type(),
"item": pa.utf8(),
"price": pa.float64(),
}
)

View File

@@ -26,8 +26,6 @@ import pytest
from lance_namespace import (
CreateEmptyTableRequest,
CreateEmptyTableResponse,
DeclareTableRequest,
DeclareTableResponse,
DescribeTableRequest,
DescribeTableResponse,
LanceNamespace,
@@ -162,19 +160,6 @@ class TrackingNamespace(LanceNamespace):
return modified
def declare_table(self, request: DeclareTableRequest) -> DeclareTableResponse:
"""Track declare_table calls and inject rotating credentials."""
with self.lock:
self.create_call_count += 1
count = self.create_call_count
response = self.inner.declare_table(request)
response.storage_options = self._modify_storage_options(
response.storage_options, count
)
return response
def create_empty_table(
self, request: CreateEmptyTableRequest
) -> CreateEmptyTableResponse:

View File

@@ -1967,9 +1967,3 @@ def test_add_table_with_empty_embeddings(tmp_path):
on_bad_vectors="drop",
)
assert table.count_rows() == 1
def test_table_uri(tmp_path):
db = lancedb.connect(tmp_path)
table = db.create_table("my_table", data=[{"x": 0}])
assert table.uri == str(tmp_path / "my_table.lance")

View File

@@ -528,19 +528,12 @@ def test_sanitize_data(
else:
expected_schema = schema
else:
from conftest import pandas_string_type
# polars uses large_string, pandas 3.0+ uses large_string, others use string
if isinstance(data, pl.DataFrame):
text_type = pa.large_utf8()
elif isinstance(data, pd.DataFrame):
text_type = pandas_string_type()
else:
text_type = pa.string()
expected_schema = pa.schema(
{
"id": pa.int64(),
"text": text_type,
"text": pa.large_utf8()
if isinstance(data, pl.DataFrame)
else pa.string(),
"vector": pa.list_(pa.float32(), 10),
}
)

View File

@@ -10,8 +10,7 @@ use arrow::{
use futures::stream::StreamExt;
use lancedb::arrow::SendableRecordBatchStream;
use pyo3::{
exceptions::PyStopAsyncIteration, pyclass, pymethods, Bound, PyAny, PyObject, PyRef, PyResult,
Python,
exceptions::PyStopAsyncIteration, pyclass, pymethods, Bound, Py, PyAny, PyRef, PyResult, Python,
};
use pyo3_async_runtimes::tokio::future_into_py;
@@ -36,8 +35,11 @@ impl RecordBatchStream {
#[pymethods]
impl RecordBatchStream {
#[getter]
pub fn schema(&self, py: Python) -> PyResult<PyObject> {
(*self.schema).clone().into_pyarrow(py)
pub fn schema(&self, py: Python) -> PyResult<Py<PyAny>> {
(*self.schema)
.clone()
.into_pyarrow(py)
.map(|bound| bound.unbind())
}
pub fn __aiter__(self_: PyRef<'_, Self>) -> PyRef<'_, Self> {
@@ -53,7 +55,12 @@ impl RecordBatchStream {
.next()
.await
.ok_or_else(|| PyStopAsyncIteration::new_err(""))?;
Python::with_gil(|py| inner_next.infer_error()?.to_pyarrow(py))
Python::attach(|py| {
inner_next
.infer_error()?
.to_pyarrow(py)
.map(|bound| bound.unbind())
})
})
}
}

View File

@@ -12,7 +12,7 @@ use pyo3::{
exceptions::{PyRuntimeError, PyValueError},
pyclass, pyfunction, pymethods,
types::{PyDict, PyDictMethods},
Bound, FromPyObject, Py, PyAny, PyObject, PyRef, PyResult, Python,
Bound, FromPyObject, Py, PyAny, PyRef, PyResult, Python,
};
use pyo3_async_runtimes::tokio::future_into_py;
@@ -114,7 +114,7 @@ impl Connection {
data: Bound<'_, PyAny>,
namespace: Vec<String>,
storage_options: Option<HashMap<String, String>>,
storage_options_provider: Option<PyObject>,
storage_options_provider: Option<Py<PyAny>>,
location: Option<String>,
) -> PyResult<Bound<'a, PyAny>> {
let inner = self_.get_inner()?.clone();
@@ -152,7 +152,7 @@ impl Connection {
schema: Bound<'_, PyAny>,
namespace: Vec<String>,
storage_options: Option<HashMap<String, String>>,
storage_options_provider: Option<PyObject>,
storage_options_provider: Option<Py<PyAny>>,
location: Option<String>,
) -> PyResult<Bound<'a, PyAny>> {
let inner = self_.get_inner()?.clone();
@@ -187,7 +187,7 @@ impl Connection {
name: String,
namespace: Vec<String>,
storage_options: Option<HashMap<String, String>>,
storage_options_provider: Option<PyObject>,
storage_options_provider: Option<Py<PyAny>>,
index_cache_size: Option<u32>,
location: Option<String>,
) -> PyResult<Bound<'_, PyAny>> {
@@ -327,12 +327,11 @@ impl Connection {
let py = self_.py();
future_into_py(py, async move {
use lance_namespace::models::CreateNamespaceRequest;
// Mode is now a string field
let mode_str = mode.and_then(|m| match m.to_lowercase().as_str() {
"create" => Some("Create".to_string()),
"exist_ok" => Some("ExistOk".to_string()),
"overwrite" => Some("Overwrite".to_string()),
_ => None,
let mode_enum = mode.map(|m| match m.to_lowercase().as_str() {
"create" => "Create".to_string(),
"exist_ok" => "ExistOk".to_string(),
"overwrite" => "Overwrite".to_string(),
other => other.to_string(),
});
let request = CreateNamespaceRequest {
id: if namespace.is_empty() {
@@ -340,7 +339,7 @@ impl Connection {
} else {
Some(namespace)
},
mode: mode_str,
mode: mode_enum,
properties,
..Default::default()
};
@@ -364,16 +363,15 @@ impl Connection {
let py = self_.py();
future_into_py(py, async move {
use lance_namespace::models::DropNamespaceRequest;
// Mode and Behavior are now string fields
let mode_str = mode.and_then(|m| match m.to_uppercase().as_str() {
"SKIP" => Some("Skip".to_string()),
"FAIL" => Some("Fail".to_string()),
_ => None,
let mode_enum = mode.map(|m| match m.to_uppercase().as_str() {
"SKIP" => "Skip".to_string(),
"FAIL" => "Fail".to_string(),
other => other.to_string(),
});
let behavior_str = behavior.and_then(|b| match b.to_uppercase().as_str() {
"RESTRICT" => Some("Restrict".to_string()),
"CASCADE" => Some("Cascade".to_string()),
_ => None,
let behavior_enum = behavior.map(|b| match b.to_uppercase().as_str() {
"RESTRICT" => "Restrict".to_string(),
"CASCADE" => "Cascade".to_string(),
other => other.to_string(),
});
let request = DropNamespaceRequest {
id: if namespace.is_empty() {
@@ -381,8 +379,8 @@ impl Connection {
} else {
Some(namespace)
},
mode: mode_str,
behavior: behavior_str,
mode: mode_enum,
behavior: behavior_enum,
..Default::default()
};
let response = inner.drop_namespace(request).await.infer_error()?;

View File

@@ -1,3 +1,4 @@
#![allow(deprecated)]
// SPDX-License-Identifier: Apache-2.0
// SPDX-FileCopyrightText: Copyright The LanceDB Authors

View File

@@ -281,7 +281,7 @@ impl PyPermutationReader {
let reader = slf.reader.clone();
future_into_py(slf.py(), async move {
let schema = reader.output_schema(selection).await.infer_error()?;
Python::with_gil(|py| schema.to_pyarrow(py))
Python::with_gil(|py| schema.to_pyarrow(py).map(|bound| bound.unbind()))
})
}

View File

@@ -216,7 +216,7 @@ impl<'py> IntoPyObject<'py> for PyQueryVectors {
let py_objs = self
.0
.into_iter()
.map(|v| v.to_data().into_pyarrow(py))
.map(|v| v.to_data().into_pyarrow(py).map(|bound| bound.unbind()))
.collect::<Result<Vec<_>, _>>()?;
PyList::new(py, py_objs)
}
@@ -453,7 +453,7 @@ impl Query {
let inner = self_.inner.clone();
future_into_py(self_.py(), async move {
let schema = inner.output_schema().await.infer_error()?;
Python::with_gil(|py| schema.to_pyarrow(py))
Python::with_gil(|py| schema.to_pyarrow(py).map(|bound| bound.unbind()))
})
}
@@ -532,7 +532,7 @@ impl TakeQuery {
let inner = self_.inner.clone();
future_into_py(self_.py(), async move {
let schema = inner.output_schema().await.infer_error()?;
Python::with_gil(|py| schema.to_pyarrow(py))
Python::with_gil(|py| schema.to_pyarrow(py).map(|bound| bound.unbind()))
})
}
@@ -627,7 +627,7 @@ impl FTSQuery {
let inner = self_.inner.clone();
future_into_py(self_.py(), async move {
let schema = inner.output_schema().await.infer_error()?;
Python::with_gil(|py| schema.to_pyarrow(py))
Python::with_gil(|py| schema.to_pyarrow(py).map(|bound| bound.unbind()))
})
}
@@ -806,7 +806,7 @@ impl VectorQuery {
let inner = self_.inner.clone();
future_into_py(self_.py(), async move {
let schema = inner.output_schema().await.infer_error()?;
Python::with_gil(|py| schema.to_pyarrow(py))
Python::with_gil(|py| schema.to_pyarrow(py).map(|bound| bound.unbind()))
})
}

View File

@@ -17,7 +17,7 @@ use pyo3::types::PyDict;
/// Internal wrapper around a Python object implementing StorageOptionsProvider
pub struct PyStorageOptionsProvider {
/// The Python object implementing fetch_storage_options()
inner: PyObject,
inner: Py<PyAny>,
}
impl Clone for PyStorageOptionsProvider {
@@ -29,7 +29,7 @@ impl Clone for PyStorageOptionsProvider {
}
impl PyStorageOptionsProvider {
pub fn new(obj: PyObject) -> PyResult<Self> {
pub fn new(obj: Py<PyAny>) -> PyResult<Self> {
Python::with_gil(|py| {
// Verify the object has a fetch_storage_options method
if !obj.bind(py).hasattr("fetch_storage_options")? {
@@ -143,7 +143,7 @@ impl std::fmt::Debug for PyStorageOptionsProviderWrapper {
/// This is the main entry point for converting Python StorageOptionsProvider objects
/// to Rust trait objects that can be used by the Lance ecosystem.
pub fn py_object_to_storage_options_provider(
py_obj: PyObject,
py_obj: Py<PyAny>,
) -> PyResult<Arc<dyn StorageOptionsProvider>> {
let py_provider = PyStorageOptionsProvider::new(py_obj)?;
Ok(Arc::new(PyStorageOptionsProviderWrapper::new(py_provider)))

View File

@@ -287,7 +287,7 @@ impl Table {
let inner = self_.inner_ref()?.clone();
future_into_py(self_.py(), async move {
let schema = inner.schema().await.infer_error()?;
Python::with_gil(|py| schema.to_pyarrow(py))
Python::with_gil(|py| schema.to_pyarrow(py).map(|bound| bound.unbind()))
})
}
@@ -497,11 +497,6 @@ impl Table {
})
}
pub fn uri(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
let inner = self_.inner_ref()?.clone();
future_into_py(self_.py(), async move { inner.uri().await.infer_error() })
}
pub fn __repr__(&self) -> String {
match &self.inner {
None => format!("ClosedTable({})", self.name),

View File

@@ -1,6 +1,6 @@
[package]
name = "lancedb"
version = "0.24.0-beta.0"
version = "0.23.1"
edition.workspace = true
description = "LanceDB: A serverless, low-latency vector database for AI applications"
license.workspace = true
@@ -104,16 +104,11 @@ test-log = "0.2"
[features]
default = []
default = ["aws", "gcs", "azure", "dynamodb", "oss"]
aws = ["lance/aws", "lance-io/aws", "lance-namespace-impls/dir-aws"]
oss = ["lance/oss", "lance-io/oss", "lance-namespace-impls/dir-oss"]
gcs = ["lance/gcp", "lance-io/gcp", "lance-namespace-impls/dir-gcp"]
azure = ["lance/azure", "lance-io/azure", "lance-namespace-impls/dir-azure"]
huggingface = [
"lance/huggingface",
"lance-io/huggingface",
"lance-namespace-impls/dir-huggingface",
]
dynamodb = ["lance/dynamodb", "aws"]
remote = ["dep:reqwest", "dep:http", "lance-namespace-impls/rest", "lance-namespace-impls/rest-adapter"]
fp16kernels = ["lance-linalg/fp16kernels"]
@@ -153,6 +148,3 @@ name = "ivf_pq"
[[example]]
name = "hybrid_search"
required-features = ["sentence-transformers"]
[package.metadata.docs.rs]
all-features = true

View File

@@ -36,42 +36,10 @@ use crate::remote::{
};
use crate::table::{TableDefinition, WriteOptions};
use crate::Table;
use lance::io::ObjectStoreParams;
pub use lance_encoding::version::LanceFileVersion;
#[cfg(feature = "remote")]
use lance_io::object_store::StorageOptions;
use lance_io::object_store::{StorageOptionsAccessor, StorageOptionsProvider};
fn merge_storage_options(
store_params: &mut ObjectStoreParams,
pairs: impl IntoIterator<Item = (String, String)>,
) {
let mut options = store_params.storage_options().cloned().unwrap_or_default();
for (key, value) in pairs {
options.insert(key, value);
}
let provider = store_params
.storage_options_accessor
.as_ref()
.and_then(|accessor| accessor.provider().cloned());
let accessor = if let Some(provider) = provider {
StorageOptionsAccessor::with_initial_and_provider(options, provider)
} else {
StorageOptionsAccessor::with_static_options(options)
};
store_params.storage_options_accessor = Some(Arc::new(accessor));
}
fn set_storage_options_provider(
store_params: &mut ObjectStoreParams,
provider: Arc<dyn StorageOptionsProvider>,
) {
let accessor = match store_params.storage_options().cloned() {
Some(options) => StorageOptionsAccessor::with_initial_and_provider(options, provider),
None => StorageOptionsAccessor::with_provider(provider),
};
store_params.storage_options_accessor = Some(Arc::new(accessor));
}
use lance_io::object_store::StorageOptionsProvider;
/// A builder for configuring a [`Connection::table_names`] operation
pub struct TableNamesBuilder {
@@ -278,14 +246,16 @@ impl<const HAS_DATA: bool> CreateTableBuilder<HAS_DATA> {
///
/// See available options at <https://lancedb.com/docs/storage/>
pub fn storage_option(mut self, key: impl Into<String>, value: impl Into<String>) -> Self {
let store_params = self
let store_options = self
.request
.write_options
.lance_write_params
.get_or_insert(Default::default())
.store_params
.get_or_insert(Default::default())
.storage_options
.get_or_insert(Default::default());
merge_storage_options(store_params, [(key.into(), value.into())]);
store_options.insert(key.into(), value.into());
self
}
@@ -299,17 +269,19 @@ impl<const HAS_DATA: bool> CreateTableBuilder<HAS_DATA> {
mut self,
pairs: impl IntoIterator<Item = (impl Into<String>, impl Into<String>)>,
) -> Self {
let store_params = self
let store_options = self
.request
.write_options
.lance_write_params
.get_or_insert(Default::default())
.store_params
.get_or_insert(Default::default())
.storage_options
.get_or_insert(Default::default());
let updates = pairs
.into_iter()
.map(|(key, value)| (key.into(), value.into()));
merge_storage_options(store_params, updates);
for (key, value) in pairs {
store_options.insert(key.into(), value.into());
}
self
}
@@ -346,21 +318,23 @@ impl<const HAS_DATA: bool> CreateTableBuilder<HAS_DATA> {
/// This has no effect in LanceDB Cloud.
#[deprecated(since = "0.15.1", note = "Use `database_options` instead")]
pub fn enable_v2_manifest_paths(mut self, use_v2_manifest_paths: bool) -> Self {
let store_params = self
let storage_options = self
.request
.write_options
.lance_write_params
.get_or_insert_with(Default::default)
.store_params
.get_or_insert_with(Default::default)
.storage_options
.get_or_insert_with(Default::default);
let value = if use_v2_manifest_paths {
"true".to_string()
} else {
"false".to_string()
};
merge_storage_options(
store_params,
[(OPT_NEW_TABLE_V2_MANIFEST_PATHS.to_string(), value)],
storage_options.insert(
OPT_NEW_TABLE_V2_MANIFEST_PATHS.to_string(),
if use_v2_manifest_paths {
"true".to_string()
} else {
"false".to_string()
},
);
self
}
@@ -370,19 +344,19 @@ impl<const HAS_DATA: bool> CreateTableBuilder<HAS_DATA> {
/// The default is `LanceFileVersion::Stable`.
#[deprecated(since = "0.15.1", note = "Use `database_options` instead")]
pub fn data_storage_version(mut self, data_storage_version: LanceFileVersion) -> Self {
let store_params = self
let storage_options = self
.request
.write_options
.lance_write_params
.get_or_insert_with(Default::default)
.store_params
.get_or_insert_with(Default::default)
.storage_options
.get_or_insert_with(Default::default);
merge_storage_options(
store_params,
[(
OPT_NEW_TABLE_STORAGE_VERSION.to_string(),
data_storage_version.to_string(),
)],
storage_options.insert(
OPT_NEW_TABLE_STORAGE_VERSION.to_string(),
data_storage_version.to_string(),
);
self
}
@@ -407,14 +381,13 @@ impl<const HAS_DATA: bool> CreateTableBuilder<HAS_DATA> {
/// This allows tables to automatically refresh cloud storage credentials
/// when they expire, enabling long-running operations on remote storage.
pub fn storage_options_provider(mut self, provider: Arc<dyn StorageOptionsProvider>) -> Self {
let store_params = self
.request
self.request
.write_options
.lance_write_params
.get_or_insert(Default::default())
.store_params
.get_or_insert(Default::default());
set_storage_options_provider(store_params, provider);
.get_or_insert(Default::default())
.storage_options_provider = Some(provider);
self
}
}
@@ -477,13 +450,15 @@ impl OpenTableBuilder {
///
/// See available options at <https://lancedb.com/docs/storage/>
pub fn storage_option(mut self, key: impl Into<String>, value: impl Into<String>) -> Self {
let store_params = self
let storage_options = self
.request
.lance_read_params
.get_or_insert(Default::default())
.store_options
.get_or_insert(Default::default())
.storage_options
.get_or_insert(Default::default());
merge_storage_options(store_params, [(key.into(), value.into())]);
storage_options.insert(key.into(), value.into());
self
}
@@ -497,16 +472,18 @@ impl OpenTableBuilder {
mut self,
pairs: impl IntoIterator<Item = (impl Into<String>, impl Into<String>)>,
) -> Self {
let store_params = self
let storage_options = self
.request
.lance_read_params
.get_or_insert(Default::default())
.store_options
.get_or_insert(Default::default())
.storage_options
.get_or_insert(Default::default());
let updates = pairs
.into_iter()
.map(|(key, value)| (key.into(), value.into()));
merge_storage_options(store_params, updates);
for (key, value) in pairs {
storage_options.insert(key.into(), value.into());
}
self
}
@@ -530,13 +507,12 @@ impl OpenTableBuilder {
/// This allows tables to automatically refresh cloud storage credentials
/// when they expire, enabling long-running operations on remote storage.
pub fn storage_options_provider(mut self, provider: Arc<dyn StorageOptionsProvider>) -> Self {
let store_params = self
.request
self.request
.lance_read_params
.get_or_insert(Default::default())
.store_options
.get_or_insert(Default::default());
set_storage_options_provider(store_params, provider);
.get_or_insert(Default::default())
.storage_options_provider = Some(provider);
self
}
@@ -1301,6 +1277,8 @@ mod test_utils {
#[cfg(test)]
mod tests {
use std::fs::create_dir_all;
use crate::database::listing::{ListingDatabaseOptions, NewTableConfig};
use crate::query::QueryBase;
use crate::query::{ExecutableQuery, QueryExecutionOptions};
@@ -1548,27 +1526,18 @@ mod tests {
#[tokio::test]
async fn drop_table() {
let tc = new_test_connection().await.unwrap();
let db = tc.connection;
let tmp_dir = tempdir().unwrap();
if tc.is_remote {
// All the typical endpoints such as s3:///, file-object-store:///, etc. treat drop_table
// as idempotent.
assert!(db.drop_table("invalid_table", &[]).await.is_ok());
} else {
// The behavior of drop_table when using a file:/// endpoint differs from all other
// object providers, in that it returns an error when deleting a non-existent table.
assert!(matches!(
db.drop_table("invalid_table", &[]).await,
Err(crate::Error::TableNotFound { .. }),
));
}
let uri = tmp_dir.path().to_str().unwrap();
let db = connect(uri).execute().await.unwrap();
let schema = Arc::new(Schema::new(vec![Field::new("x", DataType::Int32, false)]));
db.create_empty_table("table1", schema.clone())
.execute()
.await
.unwrap();
// drop non-exist table
assert!(matches!(
db.drop_table("invalid_table", &[]).await,
Err(crate::Error::TableNotFound { .. }),
));
create_dir_all(tmp_dir.path().join("table1.lance")).unwrap();
db.drop_table("table1", &[]).await.unwrap();
let tables = db.table_names().execute().await.unwrap();

View File

@@ -12,7 +12,7 @@ use lance::dataset::{builder::DatasetBuilder, ReadParams, WriteMode};
use lance::io::{ObjectStore, ObjectStoreParams, WrappingObjectStore};
use lance_datafusion::utils::StreamingWriteSource;
use lance_encoding::version::LanceFileVersion;
use lance_io::object_store::{StorageOptionsAccessor, StorageOptionsProvider};
use lance_io::object_store::StorageOptionsProvider;
use lance_table::io::commit::commit_handler_from_url;
use object_store::local::LocalFileSystem;
use snafu::ResultExt;
@@ -356,13 +356,7 @@ impl ListingDatabase {
.clone()
.unwrap_or_else(|| Arc::new(lance::session::Session::default()));
let os_params = ObjectStoreParams {
storage_options_accessor: if options.storage_options.is_empty() {
None
} else {
Some(Arc::new(StorageOptionsAccessor::with_static_options(
options.storage_options.clone(),
)))
},
storage_options: Some(options.storage_options.clone()),
..Default::default()
};
let (object_store, base_path) = ObjectStore::from_uri_and_params(
@@ -469,20 +463,9 @@ impl ListingDatabase {
validate_table_name(name)?;
let mut uri = self.uri.clone();
// If the URI does not end with a path separator, add one
// Use forward slash for URIs (http://, s3://, gs://, file://, etc.)
// Use platform-specific separator for local paths without scheme
let has_scheme = uri.contains("://");
let ends_with_separator = uri.ends_with('/') || uri.ends_with('\\');
if !ends_with_separator {
if has_scheme {
// URIs always use forward slash
uri.push('/');
} else {
// Local path without scheme - use platform separator
uri.push(std::path::MAIN_SEPARATOR);
}
// If the URI does not end with a slash, add one
if !uri.ends_with('/') {
uri.push('/');
}
// Append the table name with the lance file extension
uri.push_str(&format!("{}.{}", name, LANCE_FILE_EXTENSION));
@@ -498,13 +481,7 @@ impl ListingDatabase {
async fn drop_tables(&self, names: Vec<String>) -> Result<()> {
let object_store_params = ObjectStoreParams {
storage_options_accessor: if self.storage_options.is_empty() {
None
} else {
Some(Arc::new(StorageOptionsAccessor::with_static_options(
self.storage_options.clone(),
)))
},
storage_options: Some(self.storage_options.clone()),
..Default::default()
};
let mut uri = self.uri.clone();
@@ -553,7 +530,7 @@ impl ListingDatabase {
.lance_write_params
.as_ref()
.and_then(|p| p.store_params.as_ref())
.and_then(|sp| sp.storage_options());
.and_then(|sp| sp.storage_options.as_ref());
let storage_version_override = storage_options
.and_then(|opts| opts.get(OPT_NEW_TABLE_STORAGE_VERSION))
@@ -604,20 +581,21 @@ impl ListingDatabase {
// will cause a new connection to be created, and that connection will
// be dropped from the cache when python GCs the table object, which
// confounds reuse across tables.
if !self.storage_options.is_empty() || self.storage_options_provider.is_some() {
let store_params = write_params
if !self.storage_options.is_empty() {
let storage_options = write_params
.store_params
.get_or_insert_with(Default::default)
.storage_options
.get_or_insert_with(Default::default);
let mut storage_options = store_params.storage_options().cloned().unwrap_or_default();
if !self.storage_options.is_empty() {
self.inherit_storage_options(&mut storage_options);
}
let accessor = if let Some(ref provider) = self.storage_options_provider {
StorageOptionsAccessor::with_initial_and_provider(storage_options, provider.clone())
} else {
StorageOptionsAccessor::with_static_options(storage_options)
};
store_params.storage_options_accessor = Some(Arc::new(accessor));
self.inherit_storage_options(storage_options);
}
// Set storage options provider if available
if self.storage_options_provider.is_some() {
write_params
.store_params
.get_or_insert_with(Default::default)
.storage_options_provider = self.storage_options_provider.clone();
}
write_params.data_storage_version = self
@@ -903,13 +881,7 @@ impl Database for ListingDatabase {
validate_table_name(&request.target_table_name)?;
let storage_params = ObjectStoreParams {
storage_options_accessor: if self.storage_options.is_empty() {
None
} else {
Some(Arc::new(StorageOptionsAccessor::with_static_options(
self.storage_options.clone(),
)))
},
storage_options: Some(self.storage_options.clone()),
..Default::default()
};
let read_params = ReadParams {
@@ -973,28 +945,25 @@ impl Database for ListingDatabase {
// will cause a new connection to be created, and that connection will
// be dropped from the cache when python GCs the table object, which
// confounds reuse across tables.
if !self.storage_options.is_empty() || self.storage_options_provider.is_some() {
let store_params = request
if !self.storage_options.is_empty() {
let storage_options = request
.lance_read_params
.get_or_insert_with(Default::default)
.store_options
.get_or_insert_with(Default::default)
.storage_options
.get_or_insert_with(Default::default);
let mut storage_options = store_params.storage_options().cloned().unwrap_or_default();
if !self.storage_options.is_empty() {
self.inherit_storage_options(&mut storage_options);
}
// Preserve request-level provider if no connection-level provider exists
let request_provider = store_params
.storage_options_accessor
.as_ref()
.and_then(|a| a.provider().cloned());
let provider = self.storage_options_provider.clone().or(request_provider);
let accessor = if let Some(provider) = provider {
StorageOptionsAccessor::with_initial_and_provider(storage_options, provider)
} else {
StorageOptionsAccessor::with_static_options(storage_options)
};
store_params.storage_options_accessor = Some(Arc::new(accessor));
self.inherit_storage_options(storage_options);
}
// Set storage options provider if available
if self.storage_options_provider.is_some() {
request
.lance_read_params
.get_or_insert_with(Default::default)
.store_options
.get_or_insert_with(Default::default)
.storage_options_provider = self.storage_options_provider.clone();
}
// Some ReadParams are exposed in the OpenTableBuilder, but we also
@@ -1102,7 +1071,6 @@ mod tests {
use crate::table::{Table, TableDefinition};
use arrow_array::{Int32Array, RecordBatch, StringArray};
use arrow_schema::{DataType, Field, Schema};
use std::path::PathBuf;
use tempfile::tempdir;
async fn setup_database() -> (tempfile::TempDir, ListingDatabase) {
@@ -1901,9 +1869,7 @@ mod tests {
let write_options = WriteOptions {
lance_write_params: Some(lance::dataset::WriteParams {
store_params: Some(lance::io::ObjectStoreParams {
storage_options_accessor: Some(Arc::new(
StorageOptionsAccessor::with_static_options(storage_options),
)),
storage_options: Some(storage_options),
..Default::default()
}),
..Default::default()
@@ -1977,9 +1943,7 @@ mod tests {
let write_options = WriteOptions {
lance_write_params: Some(lance::dataset::WriteParams {
store_params: Some(lance::io::ObjectStoreParams {
storage_options_accessor: Some(Arc::new(
StorageOptionsAccessor::with_static_options(storage_options),
)),
storage_options: Some(storage_options),
..Default::default()
}),
..Default::default()
@@ -2082,19 +2046,6 @@ mod tests {
assert_eq!(db_options.new_table_config.enable_stable_row_ids, None);
}
#[tokio::test]
async fn test_table_uri() {
let (_tempdir, db) = setup_database().await;
let mut pb = PathBuf::new();
pb.push(db.uri.clone());
pb.push("test.lance");
let expected = pb.to_str().unwrap();
let uri = db.table_uri("test").ok().unwrap();
assert_eq!(uri, expected);
}
#[tokio::test]
async fn test_namespace_client() {
let (_tempdir, db) = setup_database().await;

View File

@@ -9,15 +9,14 @@ use std::sync::Arc;
use async_trait::async_trait;
use lance_namespace::{
models::{
CreateEmptyTableRequest, CreateNamespaceRequest, CreateNamespaceResponse,
DeclareTableRequest, DescribeNamespaceRequest, DescribeNamespaceResponse,
DescribeTableRequest, DropNamespaceRequest, DropNamespaceResponse, DropTableRequest,
ListNamespacesRequest, ListNamespacesResponse, ListTablesRequest, ListTablesResponse,
CreateNamespaceRequest, CreateNamespaceResponse, DeclareTableRequest,
DescribeNamespaceRequest, DescribeNamespaceResponse, DescribeTableRequest,
DropNamespaceRequest, DropNamespaceResponse, DropTableRequest, ListNamespacesRequest,
ListNamespacesResponse, ListTablesRequest, ListTablesResponse,
},
LanceNamespace,
};
use lance_namespace_impls::ConnectBuilder;
use log::warn;
use crate::database::ReadConsistency;
use crate::error::{Error, Result};
@@ -155,6 +154,7 @@ impl Database for LanceNamespaceDatabase {
table_id.push(request.name.clone());
let describe_request = DescribeTableRequest {
id: Some(table_id.clone()),
version: None,
..Default::default()
};
@@ -205,53 +205,24 @@ impl Database for LanceNamespaceDatabase {
let mut table_id = request.namespace.clone();
table_id.push(request.name.clone());
// Try declare_table first, falling back to create_empty_table for backwards
// compatibility with older namespace clients that don't support declare_table
let declare_request = DeclareTableRequest {
id: Some(table_id.clone()),
location: None,
vend_credentials: None,
..Default::default()
};
let location = match self.namespace.declare_table(declare_request).await {
Ok(response) => response.location.ok_or_else(|| Error::Runtime {
message: "Table location is missing from declare_table response".to_string(),
})?,
Err(e) => {
// Check if the error is "not supported" and try create_empty_table as fallback
let err_str = e.to_string().to_lowercase();
if err_str.contains("not supported") || err_str.contains("not implemented") {
warn!(
"declare_table is not supported by the namespace client, \
falling back to deprecated create_empty_table. \
create_empty_table is deprecated and will be removed in Lance 3.0.0. \
Please upgrade your namespace client to support declare_table."
);
#[allow(deprecated)]
let create_empty_request = CreateEmptyTableRequest {
id: Some(table_id.clone()),
..Default::default()
};
let declare_response = self
.namespace
.declare_table(declare_request)
.await
.map_err(|e| Error::Runtime {
message: format!("Failed to declare table: {}", e),
})?;
#[allow(deprecated)]
let create_response = self
.namespace
.create_empty_table(create_empty_request)
.await
.map_err(|e| Error::Runtime {
message: format!("Failed to create empty table: {}", e),
})?;
create_response.location.ok_or_else(|| Error::Runtime {
message: "Table location is missing from create_empty_table response"
.to_string(),
})?
} else {
return Err(Error::Runtime {
message: format!("Failed to declare table: {}", e),
});
}
}
};
let location = declare_response.location.ok_or_else(|| Error::Runtime {
message: "Table location is missing from declare_table response".to_string(),
})?;
let native_table = NativeTable::create_from_namespace(
self.namespace.clone(),
@@ -466,6 +437,8 @@ mod tests {
// Create a child namespace first
conn.create_namespace(CreateNamespaceRequest {
id: Some(vec!["test_ns".into()]),
mode: None,
properties: None,
..Default::default()
})
.await
@@ -526,6 +499,8 @@ mod tests {
// Create a child namespace first
conn.create_namespace(CreateNamespaceRequest {
id: Some(vec!["test_ns".into()]),
mode: None,
properties: None,
..Default::default()
})
.await
@@ -589,6 +564,8 @@ mod tests {
// Create a child namespace first
conn.create_namespace(CreateNamespaceRequest {
id: Some(vec!["test_ns".into()]),
mode: None,
properties: None,
..Default::default()
})
.await
@@ -672,6 +649,8 @@ mod tests {
// Create a child namespace first
conn.create_namespace(CreateNamespaceRequest {
id: Some(vec!["test_ns".into()]),
mode: None,
properties: None,
..Default::default()
})
.await
@@ -727,6 +706,8 @@ mod tests {
// Create a child namespace first
conn.create_namespace(CreateNamespaceRequest {
id: Some(vec!["test_ns".into()]),
mode: None,
properties: None,
..Default::default()
})
.await
@@ -807,6 +788,8 @@ mod tests {
// Create a child namespace first
conn.create_namespace(CreateNamespaceRequest {
id: Some(vec!["test_ns".into()]),
mode: None,
properties: None,
..Default::default()
})
.await
@@ -840,6 +823,8 @@ mod tests {
// Create a child namespace first
conn.create_namespace(CreateNamespaceRequest {
id: Some(vec!["test_ns".into()]),
mode: None,
properties: None,
..Default::default()
})
.await

View File

@@ -25,14 +25,13 @@
//!
//! ## Crate Features
//!
//! - `aws` - Enable AWS S3 object store support.
//! - `dynamodb` - Enable DynamoDB manifest store support.
//! - `azure` - Enable Azure Blob Storage object store support.
//! - `gcs` - Enable Google Cloud Storage object store support.
//! - `oss` - Enable Alibaba Cloud OSS object store support.
//! - `remote` - Enable remote client to connect to LanceDB cloud.
//! - `huggingface` - Enable HuggingFace Hub integration for loading datasets from the Hub.
//! - `fp16kernels` - Enable FP16 kernels for faster vector search on CPU.
//! ### Experimental Features
//!
//! These features are not enabled by default. They are experimental or in-development features that
//! are not yet ready to be released.
//!
//! - `remote` - Enable remote client to connect to LanceDB cloud. This is not yet fully implemented
//! and should not be enabled.
//!
//! ### Quick Start
//!

View File

@@ -1718,6 +1718,8 @@ mod tests {
let namespace = vec!["test_ns".to_string()];
conn.create_namespace(CreateNamespaceRequest {
id: Some(namespace.clone()),
mode: None,
properties: None,
..Default::default()
})
.await
@@ -1743,6 +1745,8 @@ mod tests {
let list_response = conn
.list_tables(ListTablesRequest {
id: Some(namespace.clone()),
page_token: None,
limit: None,
..Default::default()
})
.await
@@ -1754,6 +1758,8 @@ mod tests {
let list_response = namespace_client
.list_tables(ListTablesRequest {
id: Some(namespace.clone()),
page_token: None,
limit: None,
..Default::default()
})
.await
@@ -1794,6 +1800,8 @@ mod tests {
let namespace = vec!["multi_table_ns".to_string()];
conn.create_namespace(CreateNamespaceRequest {
id: Some(namespace.clone()),
mode: None,
properties: None,
..Default::default()
})
.await
@@ -1819,6 +1827,8 @@ mod tests {
let list_response = conn
.list_tables(ListTablesRequest {
id: Some(namespace.clone()),
page_token: None,
limit: None,
..Default::default()
})
.await

View File

@@ -204,7 +204,6 @@ pub struct RemoteTable<S: HttpSend = Sender> {
server_version: ServerVersion,
version: RwLock<Option<u64>>,
location: RwLock<Option<String>>,
}
impl<S: HttpSend> RemoteTable<S> {
@@ -222,7 +221,6 @@ impl<S: HttpSend> RemoteTable<S> {
identifier,
server_version,
version: RwLock::new(None),
location: RwLock::new(None),
}
}
@@ -641,7 +639,6 @@ impl<S: HttpSend> RemoteTable<S> {
struct TableDescription {
version: u64,
schema: JsonSchema,
location: Option<String>,
}
impl<S: HttpSend> std::fmt::Display for RemoteTable<S> {
@@ -670,7 +667,6 @@ mod test_utils {
identifier: name,
server_version: version.map(ServerVersion).unwrap_or_default(),
version: RwLock::new(None),
location: RwLock::new(None),
}
}
}
@@ -1465,28 +1461,8 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
message: "table_definition is not supported on LanceDB cloud.".into(),
})
}
async fn uri(&self) -> Result<String> {
// Check if we already have the location cached
{
let location = self.location.read().await;
if let Some(ref loc) = *location {
return Ok(loc.clone());
}
}
// Fetch from server via describe
let description = self.describe().await?;
let location = description.location.ok_or_else(|| Error::NotSupported {
message: "Table URI not supported by the server".into(),
})?;
// Cache the location for future use
{
let mut cached_location = self.location.write().await;
*cached_location = Some(location.clone());
}
Ok(location)
fn dataset_uri(&self) -> &str {
"NOT_SUPPORTED"
}
async fn storage_options(&self) -> Option<HashMap<String, String>> {
@@ -3356,69 +3332,4 @@ mod tests {
let result = table.drop_columns(&["old_col1", "old_col2"]).await.unwrap();
assert_eq!(result.version, 5);
}
#[tokio::test]
async fn test_uri() {
let table = Table::new_with_handler("my_table", |request| {
assert_eq!(request.method(), "POST");
assert_eq!(request.url().path(), "/v1/table/my_table/describe/");
http::Response::builder()
.status(200)
.body(r#"{"version": 1, "schema": {"fields": []}, "location": "s3://bucket/path/to/table"}"#)
.unwrap()
});
let uri = table.uri().await.unwrap();
assert_eq!(uri, "s3://bucket/path/to/table");
}
#[tokio::test]
async fn test_uri_missing_location() {
let table = Table::new_with_handler("my_table", |request| {
assert_eq!(request.method(), "POST");
assert_eq!(request.url().path(), "/v1/table/my_table/describe/");
// Server returns response without location field
http::Response::builder()
.status(200)
.body(r#"{"version": 1, "schema": {"fields": []}}"#)
.unwrap()
});
let result = table.uri().await;
assert!(result.is_err());
assert!(matches!(&result, Err(Error::NotSupported { .. })));
}
#[tokio::test]
async fn test_uri_caching() {
use std::sync::atomic::{AtomicUsize, Ordering};
use std::sync::Arc;
let call_count = Arc::new(AtomicUsize::new(0));
let call_count_clone = call_count.clone();
let table = Table::new_with_handler("my_table", move |request| {
assert_eq!(request.url().path(), "/v1/table/my_table/describe/");
call_count_clone.fetch_add(1, Ordering::SeqCst);
http::Response::builder()
.status(200)
.body(
r#"{"version": 1, "schema": {"fields": []}, "location": "gs://bucket/table"}"#,
)
.unwrap()
});
// First call should fetch from server
let uri1 = table.uri().await.unwrap();
assert_eq!(uri1, "gs://bucket/table");
assert_eq!(call_count.load(Ordering::SeqCst), 1);
// Second call should use cached value
let uri2 = table.uri().await.unwrap();
assert_eq!(uri2, "gs://bucket/table");
assert_eq!(call_count.load(Ordering::SeqCst), 1); // Still 1, no new call
}
}

View File

@@ -40,7 +40,7 @@ use lance_index::vector::pq::PQBuildParams;
use lance_index::vector::sq::builder::SQBuildParams;
use lance_index::DatasetIndexExt;
use lance_index::IndexType;
use lance_io::object_store::{LanceNamespaceStorageOptionsProvider, StorageOptionsAccessor};
use lance_io::object_store::LanceNamespaceStorageOptionsProvider;
use lance_namespace::models::{
QueryTableRequest as NsQueryTableRequest, QueryTableRequestColumns,
QueryTableRequestFullTextQuery, QueryTableRequestVector, StringFtsQuery,
@@ -608,8 +608,8 @@ pub trait BaseTable: std::fmt::Display + std::fmt::Debug + Send + Sync {
async fn list_versions(&self) -> Result<Vec<Version>>;
/// Get the table definition.
async fn table_definition(&self) -> Result<TableDefinition>;
/// Get the table URI (storage location)
async fn uri(&self) -> Result<String>;
/// Get the table URI
fn dataset_uri(&self) -> &str;
/// Get the storage options used when opening this table, if any.
async fn storage_options(&self) -> Option<HashMap<String, String>>;
/// Poll until the columns are fully indexed. Will return Error::Timeout if the columns
@@ -1317,12 +1317,11 @@ impl Table {
self.inner.list_indices().await
}
/// Get the table URI (storage location)
/// Get the underlying dataset URI
///
/// Returns the full storage location of the table (e.g., S3/GCS path).
/// For remote tables, this fetches the location from the server via describe.
pub async fn uri(&self) -> Result<String> {
self.inner.uri().await
/// Warning: This is an internal API and the return value is subject to change.
pub fn dataset_uri(&self) -> &str {
self.inner.dataset_uri()
}
/// Get the storage options used when opening this table, if any.
@@ -1425,7 +1424,7 @@ impl Table {
})
.collect::<Vec<_>>();
let unioned = Arc::new(UnionExec::new(projected_plans));
let unioned = UnionExec::try_new(projected_plans).unwrap();
// We require 1 partition in the final output
let repartitioned = RepartitionExec::try_new(
unioned,
@@ -1666,14 +1665,18 @@ impl NativeTable {
// Use DatasetBuilder::from_namespace which automatically fetches location
// and storage options from the namespace
let builder = DatasetBuilder::from_namespace(namespace_client.clone(), table_id)
.await
.map_err(|e| match e {
lance::Error::Namespace { source, .. } => Error::Runtime {
message: format!("Failed to get table info from namespace: {:?}", source),
},
source => Error::Lance { source },
})?;
let builder = DatasetBuilder::from_namespace(
namespace_client.clone(),
table_id,
false, // Don't ignore namespace storage options
)
.await
.map_err(|e| match e {
lance::Error::Namespace { source, .. } => Error::Runtime {
message: format!("Failed to get table info from namespace: {:?}", source),
},
source => Error::Lance { source },
})?;
let dataset = builder
.with_read_params(params)
@@ -1877,13 +1880,7 @@ impl NativeTable {
let store_params = params
.store_params
.get_or_insert_with(ObjectStoreParams::default);
let accessor = match store_params.storage_options().cloned() {
Some(options) => {
StorageOptionsAccessor::with_initial_and_provider(options, storage_options_provider)
}
None => StorageOptionsAccessor::with_provider(storage_options_provider),
};
store_params.storage_options_accessor = Some(Arc::new(accessor));
store_params.storage_options_provider = Some(storage_options_provider);
// Patch the params if we have a write store wrapper
let params = match write_store_wrapper.clone() {
@@ -2335,6 +2332,18 @@ impl NativeTable {
}
}
/// Convert selected columns into the namespace request format.
fn namespace_columns(&self, columns: &[String]) -> Option<Box<QueryTableRequestColumns>> {
if columns.is_empty() {
None
} else {
Some(Box::new(QueryTableRequestColumns {
column_names: Some(columns.to_vec()),
column_aliases: None,
}))
}
}
/// Convert an AnyQuery to the namespace QueryTableRequest format.
fn convert_to_namespace_query(&self, query: &AnyQuery) -> Result<NsQueryTableRequest> {
match query {
@@ -2351,10 +2360,7 @@ impl NativeTable {
// Convert select to columns list
let columns = match &vq.base.select {
Select::All => None,
Select::Columns(cols) => Some(Box::new(QueryTableRequestColumns {
column_names: Some(cols.clone()),
column_aliases: None,
})),
Select::Columns(cols) => self.namespace_columns(cols),
Select::Dynamic(_) => {
return Err(Error::NotSupported {
message:
@@ -2389,6 +2395,8 @@ impl NativeTable {
});
Ok(NsQueryTableRequest {
identity: None,
context: None,
id: None, // Will be set in namespace_query
k: vq.base.limit.unwrap_or(10) as i32,
vector: Box::new(vector),
@@ -2407,7 +2415,7 @@ impl NativeTable {
with_row_id: Some(vq.base.with_row_id),
bypass_vector_index: Some(!vq.use_index),
full_text_query,
..Default::default()
version: None,
})
}
AnyQuery::Query(q) => {
@@ -2427,10 +2435,7 @@ impl NativeTable {
let columns = match &q.select {
Select::All => None,
Select::Columns(cols) => Some(Box::new(QueryTableRequestColumns {
column_names: Some(cols.clone()),
column_aliases: None,
})),
Select::Columns(cols) => self.namespace_columns(cols),
Select::Dynamic(_) => {
return Err(Error::NotSupported {
message: "Dynamic columns are not supported for server-side query"
@@ -2462,6 +2467,8 @@ impl NativeTable {
});
Ok(NsQueryTableRequest {
identity: None,
context: None,
id: None, // Will be set by caller
vector,
k: q.limit.unwrap_or(10) as i32,
@@ -2469,11 +2476,18 @@ impl NativeTable {
columns,
prefilter: Some(q.prefilter),
offset: q.offset.map(|o| o as i32),
ef: None,
refine_factor: None,
distance_type: None,
nprobes: None,
vector_column: None, // No vector column for plain queries
with_row_id: Some(q.with_row_id),
bypass_vector_index: Some(true), // No vector index for plain queries
full_text_query,
..Default::default()
version: None,
fast_search: None,
lower_bound: None,
upper_bound: None,
})
}
}
@@ -3226,8 +3240,8 @@ impl BaseTable for NativeTable {
Ok(results.into_iter().flatten().collect())
}
async fn uri(&self) -> Result<String> {
Ok(self.uri.clone())
fn dataset_uri(&self) -> &str {
self.uri.as_str()
}
async fn storage_options(&self) -> Option<HashMap<String, String>> {
@@ -3235,7 +3249,7 @@ impl BaseTable for NativeTable {
.get()
.await
.ok()
.and_then(|dataset| dataset.initial_storage_options().cloned())
.and_then(|dataset| dataset.storage_options().cloned())
}
async fn index_stats(&self, index_name: &str) -> Result<Option<IndexStatistics>> {
@@ -5148,13 +5162,13 @@ mod tests {
assert_eq!(ns_request.k, 10);
assert_eq!(ns_request.offset, Some(5));
assert_eq!(ns_request.filter, Some("id > 0".to_string()));
assert_eq!(
ns_request
.columns
.as_ref()
.and_then(|c| c.column_names.as_ref()),
Some(&vec!["id".to_string()])
);
let column_names = ns_request
.columns
.as_ref()
.and_then(|c| c.column_names.as_ref())
.cloned()
.unwrap();
assert_eq!(column_names, vec!["id".to_string()]);
assert_eq!(ns_request.vector_column, Some("vector".to_string()));
assert_eq!(ns_request.distance_type, Some("l2".to_string()));
assert!(ns_request.vector.single_vector.is_some());
@@ -5195,13 +5209,13 @@ mod tests {
assert_eq!(ns_request.k, 20);
assert_eq!(ns_request.offset, Some(5));
assert_eq!(ns_request.filter, Some("id > 5".to_string()));
assert_eq!(
ns_request
.columns
.as_ref()
.and_then(|c| c.column_names.as_ref()),
Some(&vec!["id".to_string()])
);
let column_names = ns_request
.columns
.as_ref()
.and_then(|c| c.column_names.as_ref())
.cloned()
.unwrap();
assert_eq!(column_names, vec!["id".to_string()]);
assert_eq!(ns_request.with_row_id, Some(true));
assert_eq!(ns_request.bypass_vector_index, Some(true));
assert!(ns_request.vector_column.is_none()); // No vector column for plain queries

View File

@@ -100,7 +100,8 @@ impl DatasetRef {
let should_checkout = match &target_ref {
refs::Ref::Version(_, Some(target_ver)) => version != target_ver,
refs::Ref::Version(_, None) => true, // No specific version, always checkout
refs::Ref::Tag(_) => true, // Always checkout for tags
refs::Ref::VersionNumber(target_ver) => version != target_ver,
refs::Ref::Tag(_) => true, // Always checkout for tags
};
if should_checkout {