Compare commits

..

25 Commits

Author SHA1 Message Date
Jack Ye 381e7cb9a6 Revert "fix: pass storage_options in LanceNamespaceDatabase::create_table"
This reverts commit 1078983993.
2026-01-30 17:28:15 -08:00
Jack Ye a11d28eb33 feat: add initial and latest storage options apis 2026-01-30 17:06:45 -08:00
Jack Ye 1078983993 fix: pass storage_options in LanceNamespaceDatabase::create_table
When creating tables via LanceNamespaceDatabase, the storage_options
(e.g., S3 endpoint, credentials) stored on the database were not being
passed to the underlying NativeTable::create_from_namespace call.

This caused issues when using federated namespace databases with custom
storage configurations (e.g., minio instead of AWS S3) - the table
creation would fail because it tried to use default AWS endpoints.

The fix injects self.storage_options into the write params before
calling create_from_namespace, ensuring the correct storage
configuration is used.

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-30 13:17:40 -08:00
Lance Release 8500b16eca Bump version: 0.24.1-beta.0 → 0.24.1 2026-01-26 23:39:18 +00:00
Lance Release 57e7282342 Bump version: 0.24.0 → 0.24.1-beta.0 2026-01-26 23:38:50 +00:00
Lance Release cc5f8070d7 Bump version: 0.27.1-beta.0 → 0.27.1 2026-01-26 23:38:24 +00:00
Lance Release dc0fb01f6b Bump version: 0.27.0 → 0.27.1-beta.0 2026-01-26 23:38:23 +00:00
LanceDB Robot 94b7781551 feat: update lance dependency to v1.0.4 (#2944)
## Summary
- bump Lance dependencies to v1.0.4
- run `cargo clippy --workspace --tests --all-features -- -D warnings`
- run `cargo fmt --all`

## Testing
- `cargo clippy --workspace --tests --all-features -- -D warnings`

## Reference
- https://github.com/lance-format/lance/releases/tag/v1.0.4
2026-01-26 15:37:28 -08:00
Jack Ye 7bf020b3d5 chore: fix clippy when remote flag is not set (#2943)
Also add a step in CI to ensure this does not happen in the future
2026-01-26 13:59:31 -08:00
LanceDB Robot 12a98479dc chore: update lance dependency to v1.0.4-rc.1 (#2942)
## Summary
- bump Lance dependencies to v1.0.4-rc.1
- verified `cargo clippy --workspace --tests --all-features -- -D
warnings`
- ran `cargo fmt --all`

## References
- https://github.com/lance-format/lance/releases/tag/v1.0.4-rc.1
2026-01-26 12:17:22 -08:00
Jack Ye e4552e577a chore(revert): revert update lance dependency to v2.0.0-rc.1 (#2936) (#2941)
This reverts commit bd84bba14d, so that we
can bump version to 1.0.4-rc.1
2026-01-26 11:13:59 -08:00
Will Jones f979a902ad ci(rust): fix MSRV check (#2940)
Realized our MSRV check was inert because `rust-toolchain.toml` was
overriding the Rust version. We set the `RUSTUP_TOOLCHAIN` environment
variable, which overrides that.

Also needed to update to MSRV 1.88 (due to dependencies like Lance and
DataFusion) and fix some clippy warnings.
2026-01-23 15:57:09 -08:00
Colin Patrick McCabe 5a7a8da567 feat: check AZURE_STORAGE_ACCOUNT_NAME in remote conns (#2918)
Unlike in Amazon S3, in Azure bucket names are not globally unique.
Instead, the combination of (storage_account_name, bucket_name) is
unique.

Therefore, when using Azure blob store, we always need a way to
configure the storage account name. One way is to use the
storage_options hash map and set azure_storage_account_name. Another way
is to set an environment variable, AZURE_STORAGE_ACCOUNT_NAME.

Prior to this PR, the second way (environment variable) did not work
with remote connections. This is because the existing code that checks
for these environment variables happens inside the Azure object store
implementation itself, which does not run locally when using remote
connections.

This PR addresses that situation by adding a check of the environment
variable. This functions as a default if the relevant storage option is
not set in the storage_options hash map.
2026-01-22 13:36:05 -08:00
Jack Ye 0db8176445 test: fix failing remote doctest reference to aws feature (#2935)
Closes https://github.com/lancedb/lancedb/issues/2933
2026-01-22 13:17:03 -08:00
LanceDB Robot bd84bba14d chore: update lance dependency to v2.0.0-rc.1 (#2936)
## Summary
- bump Lance dependencies to v2.0.0-rc.1 (git tag)
- align Arrow/DataFusion/PyO3 versions for the new Lance release
- update Python bindings for PyO3 0.26 (attach API + Py<PyAny>)

## Verification
- `cargo clippy --workspace --tests --all-features -- -D warnings`
- `cargo fmt --all`

## Reference
- https://github.com/lance-format/lance/releases/tag/v2.0.0-rc.1

---------

Co-authored-by: Jack Ye <yezhaoqin@gmail.com>
Co-authored-by: Will Jones <willjones127@gmail.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: BubbleCal <bubble_cal@outlook.com>
2026-01-22 13:14:38 -08:00
Lance Release ac07f8068c Bump version: 0.24.0-beta.1 → 0.24.0 2026-01-22 01:10:15 +00:00
Lance Release bba362d372 Bump version: 0.24.0-beta.0 → 0.24.0-beta.1 2026-01-22 01:09:53 +00:00
Lance Release 042bc22468 Bump version: 0.27.0-beta.1 → 0.27.0 2026-01-22 01:09:32 +00:00
Lance Release 68569906c6 Bump version: 0.27.0-beta.0 → 0.27.0-beta.1 2026-01-22 01:09:31 +00:00
LanceDB Robot c71c1fc822 feat: update lance dependency to v1.0.3 (#2932)
## Summary
- bump Lance dependency to v1.0.3
- refresh Cargo metadata and lockfile

## Verification
- cargo clippy --workspace --tests --all-features -- -D warnings
- cargo fmt --all

## Release
- https://github.com/lance-format/lance/releases/tag/v1.0.3
2026-01-21 17:08:24 -08:00
Jack Ye 4a6a0c856e ci: fix codex version bump title and summary (#2931)
1. use feat for releases, chore for prereleases
2. do not have literal `\n` in summary
2026-01-21 15:45:28 -08:00
Jack Ye f124c9d8d2 test: string type conversion in pandas 3.0+ (#2928)
Pandas 3.0+ string now converts to Arrow large_utf8. This PR mainly
makes sure our test accounts for the difference across the pandas
versions when constructing schema.
2026-01-21 13:40:48 -08:00
Jack Ye 4e65748abf chore: update lance dependency to v1.0.3-rc.1 (#2927)
Supercedes https://github.com/lancedb/lancedb/pull/2925

We accidentally upgraded lance to 2.0.0-beta.8. This PR reverts that
first and then bump to 1.0.3-rc.1

---------

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-21 11:52:07 -08:00
Colin Patrick McCabe e897f3edab test: assert remote behavior of drop_table (#2926)
Add support for testing remote connections in drop_table in
`rust/lancedb/src/connection.rs`.
2026-01-21 08:42:40 -08:00
Lance Release 790ba7115b Bump version: 0.23.1 → 0.24.0-beta.0 2026-01-21 12:21:53 +00:00
51 changed files with 1167 additions and 783 deletions
+1 -1
View File
@@ -1,5 +1,5 @@
[tool.bumpversion]
current_version = "0.23.1"
current_version = "0.24.1"
parse = """(?x)
(?P<major>0|[1-9]\\d*)\\.
(?P<minor>0|[1-9]\\d*)\\.
@@ -75,6 +75,13 @@ 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 ${VERSION} and prepare a pull request for maintainers to review.
@@ -84,10 +91,10 @@ jobs:
3. After clippy succeeds, run "cargo fmt --all" to format the workspace.
4. Ensure the repository is clean except for intentional changes. Inspect "git status --short" and "git diff" to confirm the dependency update and any required fixes.
5. Create and switch to a new branch named "${BRANCH_NAME}" (replace any duplicated hyphens if necessary).
6. Stage all relevant files with "git add -A". Commit using the message "chore: update lance dependency to v${VERSION}".
6. Stage all relevant files with "git add -A". Commit using the message "${COMMIT_TYPE}: update lance dependency to v${VERSION}".
7. Push the branch to origin. If the branch already exists, force-push your changes.
8. env "GH_TOKEN" is available, use "gh" tools for github related operations like creating pull request.
9. Create a pull request targeting "main" with title "chore: update lance dependency to v${VERSION}". In the body, summarize the dependency bump, clippy/fmt verification, and link the triggering tag (${TAG}).
9. Create a pull request targeting "main" with title "${COMMIT_TYPE}: update lance dependency to v${VERSION}". First, write the PR body to /tmp/pr-body.md using a heredoc (cat <<'EOF' > /tmp/pr-body.md). The body should summarize the dependency bump, clippy/fmt verification, and link the triggering tag (${TAG}). Then run "gh pr create --body-file /tmp/pr-body.md".
10. After creating the PR, display the PR URL, "git status --short", and a concise summary of the commands run and their results.
Constraints:
+5 -1
View File
@@ -48,6 +48,8 @@ jobs:
run: cargo fmt --all -- --check
- name: Run clippy
run: cargo clippy --profile ci --workspace --tests --all-features -- -D warnings
- name: Run clippy (without remote feature)
run: cargo clippy --profile ci --workspace --tests -- -D warnings
build-no-lock:
runs-on: ubuntu-24.04
@@ -181,7 +183,7 @@ jobs:
runs-on: ubuntu-24.04
strategy:
matrix:
msrv: ["1.78.0"] # This should match up with rust-version in Cargo.toml
msrv: ["1.88.0"] # This should match up with rust-version in Cargo.toml
env:
# Need up-to-date compilers for kernels
CC: clang-18
@@ -212,4 +214,6 @@ jobs:
cargo update -p aws-sdk-sts --precise 1.51.0
cargo update -p home --precise 0.5.9
- name: cargo +${{ matrix.msrv }} check
env:
RUSTUP_TOOLCHAIN: ${{ matrix.msrv }}
run: cargo check --profile ci --workspace --tests --benches --all-features
Generated
+485 -352
View File
File diff suppressed because it is too large Load Diff
+31 -31
View File
@@ -12,42 +12,42 @@ repository = "https://github.com/lancedb/lancedb"
description = "Serverless, low-latency vector database for AI applications"
keywords = ["lancedb", "lance", "database", "vector", "search"]
categories = ["database-implementations"]
rust-version = "1.78.0"
rust-version = "1.88.0"
[workspace.dependencies]
lance = { "version" = "=2.0.0-beta.8", default-features = false, "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-core = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-datagen = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-file = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-io = { "version" = "=2.0.0-beta.8", default-features = false, "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-index = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-linalg = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace-impls = { "version" = "=2.0.0-beta.8", default-features = false, "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-table = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-testing = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-datafusion = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-encoding = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-arrow = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance = { "version" = "=1.0.4", default-features = false, "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
lance-core = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
lance-datagen = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
lance-file = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
lance-io = { "version" = "=1.0.4", default-features = false, "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
lance-index = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
lance-linalg = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace-impls = { "version" = "=1.0.4", default-features = false, "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
lance-table = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
lance-testing = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
lance-datafusion = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
lance-encoding = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
lance-arrow = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
ahash = "0.8"
# Note that this one does not include pyarrow
arrow = { version = "57.2", optional = false }
arrow-array = "57.2"
arrow-data = "57.2"
arrow-ipc = "57.2"
arrow-ord = "57.2"
arrow-schema = "57.2"
arrow-select = "57.2"
arrow-cast = "57.2"
arrow = { version = "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"
async-trait = "0"
datafusion = { version = "51.0", default-features = false }
datafusion-catalog = "51.0"
datafusion-common = { version = "51.0", default-features = false }
datafusion-execution = "51.0"
datafusion-expr = "51.0"
datafusion-physical-plan = "51.0"
datafusion = { 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"
env_logger = "0.11"
half = { "version" = "2.7.1", default-features = false, features = [
half = { "version" = "2.6.0", default-features = false, features = [
"num-traits",
] }
futures = "0"
@@ -59,7 +59,7 @@ rand = "0.9"
snafu = "0.8"
url = "2"
num-traits = "0.2"
regex = "1.12"
regex = "1.10"
lazy_static = "1"
semver = "1.0.25"
chrono = "0.4"
+1 -1
View File
@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
<dependency>
<groupId>com.lancedb</groupId>
<artifactId>lancedb-core</artifactId>
<version>0.23.1</version>
<version>0.24.1</version>
</dependency>
```
+1 -1
View File
@@ -8,7 +8,7 @@
<parent>
<groupId>com.lancedb</groupId>
<artifactId>lancedb-parent</artifactId>
<version>0.23.1-final.0</version>
<version>0.24.1-final.0</version>
<relativePath>../pom.xml</relativePath>
</parent>
+1 -1
View File
@@ -6,7 +6,7 @@
<groupId>com.lancedb</groupId>
<artifactId>lancedb-parent</artifactId>
<version>0.23.1-final.0</version>
<version>0.24.1-final.0</version>
<packaging>pom</packaging>
<name>${project.artifactId}</name>
<description>LanceDB Java SDK Parent POM</description>
+1 -1
View File
@@ -1,7 +1,7 @@
[package]
name = "lancedb-nodejs"
edition.workspace = true
version = "0.23.1"
version = "0.24.1"
license.workspace = true
description.workspace = true
repository.workspace = true
+41
View File
@@ -538,6 +538,35 @@ export abstract class Table {
*
*/
abstract stats(): Promise<TableStatistics>;
/**
* Get the initial storage options that were passed in when opening this table.
*
* For dynamically refreshed options (e.g., credential vending), use
* {@link Table.latestStorageOptions}.
*
* Warning: This is an internal API and the return value is subject to change.
*
* @returns The storage options, or undefined if no storage options were configured.
*/
abstract initialStorageOptions(): Promise<
Record<string, string> | null | undefined
>;
/**
* Get the latest storage options, refreshing from provider if configured.
*
* This method is useful for credential vending scenarios where storage options
* may be refreshed dynamically. If no dynamic provider is configured, this
* returns the initial static options.
*
* Warning: This is an internal API and the return value is subject to change.
*
* @returns The storage options, or undefined if no storage options were configured.
*/
abstract latestStorageOptions(): Promise<
Record<string, string> | null | undefined
>;
}
export class LocalTable extends Table {
@@ -858,6 +887,18 @@ export class LocalTable extends Table {
return await this.inner.stats();
}
async initialStorageOptions(): Promise<
Record<string, string> | null | undefined
> {
return await this.inner.initialStorageOptions();
}
async latestStorageOptions(): Promise<
Record<string, string> | null | undefined
> {
return await this.inner.latestStorageOptions();
}
mergeInsert(on: string | string[]): MergeInsertBuilder {
on = Array.isArray(on) ? on : [on];
return new MergeInsertBuilder(this.inner.mergeInsert(on), this.schema());
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-darwin-arm64",
"version": "0.23.1",
"version": "0.24.1",
"os": ["darwin"],
"cpu": ["arm64"],
"main": "lancedb.darwin-arm64.node",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-darwin-x64",
"version": "0.23.1",
"version": "0.24.1",
"os": ["darwin"],
"cpu": ["x64"],
"main": "lancedb.darwin-x64.node",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-arm64-gnu",
"version": "0.23.1",
"version": "0.24.1",
"os": ["linux"],
"cpu": ["arm64"],
"main": "lancedb.linux-arm64-gnu.node",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-arm64-musl",
"version": "0.23.1",
"version": "0.24.1",
"os": ["linux"],
"cpu": ["arm64"],
"main": "lancedb.linux-arm64-musl.node",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-x64-gnu",
"version": "0.23.1",
"version": "0.24.1",
"os": ["linux"],
"cpu": ["x64"],
"main": "lancedb.linux-x64-gnu.node",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-x64-musl",
"version": "0.23.1",
"version": "0.24.1",
"os": ["linux"],
"cpu": ["x64"],
"main": "lancedb.linux-x64-musl.node",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-win32-arm64-msvc",
"version": "0.23.1",
"version": "0.24.1",
"os": [
"win32"
],
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-win32-x64-msvc",
"version": "0.23.1",
"version": "0.24.1",
"os": ["win32"],
"cpu": ["x64"],
"main": "lancedb.win32-x64-msvc.node",
+2 -2
View File
@@ -1,12 +1,12 @@
{
"name": "@lancedb/lancedb",
"version": "0.23.1",
"version": "0.24.1",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "@lancedb/lancedb",
"version": "0.23.1",
"version": "0.24.1",
"cpu": [
"x64",
"arm64"
+1 -1
View File
@@ -11,7 +11,7 @@
"ann"
],
"private": false,
"version": "0.23.1",
"version": "0.24.1",
"main": "dist/index.js",
"exports": {
".": "./dist/index.js",
+13
View File
@@ -166,6 +166,19 @@ impl Table {
Ok(stats.into())
}
#[napi(catch_unwind)]
pub async fn initial_storage_options(&self) -> napi::Result<Option<HashMap<String, String>>> {
Ok(self.inner_ref()?.initial_storage_options().await)
}
#[napi(catch_unwind)]
pub async fn latest_storage_options(&self) -> napi::Result<Option<HashMap<String, String>>> {
self.inner_ref()?
.latest_storage_options()
.await
.default_error()
}
#[napi(catch_unwind)]
pub async fn update(
&self,
+1 -1
View File
@@ -1,5 +1,5 @@
[tool.bumpversion]
current_version = "0.27.0-beta.0"
current_version = "0.27.1"
parse = """(?x)
(?P<major>0|[1-9]\\d*)\\.
(?P<minor>0|[1-9]\\d*)\\.
+6 -6
View File
@@ -1,28 +1,28 @@
[package]
name = "lancedb-python"
version = "0.27.0-beta.0"
version = "0.27.1"
edition.workspace = true
description = "Python bindings for LanceDB"
license.workspace = true
repository.workspace = true
keywords.workspace = true
categories.workspace = true
rust-version = "1.75.0"
rust-version = "1.88.0"
[lib]
name = "_lancedb"
crate-type = ["cdylib"]
[dependencies]
arrow = { version = "57.2", features = ["pyarrow"] }
arrow = { version = "56.2", 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 = "0.26", features = ["extension-module", "abi3-py39"] }
pyo3-async-runtimes = { version = "0.26", features = [
pyo3 = { version = "0.25", features = ["extension-module", "abi3-py39"] }
pyo3-async-runtimes = { version = "0.25", features = [
"attributes",
"tokio-runtime",
] }
@@ -32,7 +32,7 @@ snafu.workspace = true
tokio = { version = "1.40", features = ["sync"] }
[build-dependencies]
pyo3-build-config = { version = "0.26", features = [
pyo3-build-config = { version = "0.25", features = [
"extension-module",
"abi3-py39",
] }
+2
View File
@@ -180,6 +180,8 @@ class Table:
delete_unverified: Optional[bool] = None,
) -> OptimizeStats: ...
async def uri(self) -> str: ...
async def initial_storage_options(self) -> Optional[Dict[str, str]]: ...
async def latest_storage_options(self) -> Optional[Dict[str, str]]: ...
@property
def tags(self) -> Tags: ...
def query(self) -> Query: ...
+15 -20
View File
@@ -961,27 +961,22 @@ class LanceQueryBuilder(ABC):
>>> query = [100, 100]
>>> plan = table.search(query).analyze_plan()
>>> print(plan) # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
AnalyzeExec verbose=true, elapsed=..., metrics=...
TracedExec, elapsed=..., metrics=...
ProjectionExec: elapsed=..., expr=[...],
metrics=[output_rows=..., elapsed_compute=..., output_bytes=...]
GlobalLimitExec: elapsed=..., skip=0, fetch=10,
metrics=[output_rows=..., elapsed_compute=..., output_bytes=...]
FilterExec: elapsed=..., _distance@2 IS NOT NULL, metrics=[...]
SortExec: elapsed=..., TopK(fetch=10), expr=[...],
AnalyzeExec verbose=true, metrics=[], cumulative_cpu=...
TracedExec, metrics=[], cumulative_cpu=...
ProjectionExec: expr=[...], metrics=[...], cumulative_cpu=...
GlobalLimitExec: skip=0, fetch=10, metrics=[...], cumulative_cpu=...
FilterExec: _distance@2 IS NOT NULL,
metrics=[output_rows=..., elapsed_compute=...], cumulative_cpu=...
SortExec: TopK(fetch=10), expr=[...],
preserve_partitioning=[...],
metrics=[output_rows=..., elapsed_compute=...,
output_bytes=..., row_replacements=...]
KNNVectorDistance: elapsed=..., metric=l2,
metrics=[output_rows=..., elapsed_compute=...,
output_bytes=..., output_batches=...]
LanceRead: elapsed=..., uri=..., projection=[vector],
num_fragments=..., range_before=None, range_after=None,
row_id=true, row_addr=false,
full_filter=--, refine_filter=--,
metrics=[output_rows=..., elapsed_compute=..., output_bytes=...,
fragments_scanned=..., ranges_scanned=1, rows_scanned=1,
bytes_read=..., iops=..., requests=..., task_wait_time=...]
metrics=[output_rows=..., elapsed_compute=..., row_replacements=...],
cumulative_cpu=...
KNNVectorDistance: metric=l2,
metrics=[output_rows=..., elapsed_compute=..., output_batches=...],
cumulative_cpu=...
LanceRead: uri=..., projection=[vector], ...
metrics=[output_rows=..., elapsed_compute=...,
bytes_read=..., iops=..., requests=...], cumulative_cpu=...
Returns
-------
+62
View File
@@ -2222,6 +2222,37 @@ class LanceTable(Table):
def uri(self) -> str:
return LOOP.run(self._table.uri())
def initial_storage_options(self) -> Optional[Dict[str, str]]:
"""Get the initial storage options that were passed in when opening this table.
For dynamically refreshed options (e.g., credential vending), use
:meth:`latest_storage_options`.
Warning: This is an internal API and the return value is subject to change.
Returns
-------
Optional[Dict[str, str]]
The storage options, or None if no storage options were configured.
"""
return LOOP.run(self._table.initial_storage_options())
def latest_storage_options(self) -> Optional[Dict[str, str]]:
"""Get the latest storage options, refreshing from provider if configured.
This method is useful for credential vending scenarios where storage options
may be refreshed dynamically. If no dynamic provider is configured, this
returns the initial static options.
Warning: This is an internal API and the return value is subject to change.
Returns
-------
Optional[Dict[str, str]]
The storage options, or None if no storage options were configured.
"""
return LOOP.run(self._table.latest_storage_options())
def create_scalar_index(
self,
column: str,
@@ -3624,6 +3655,37 @@ class AsyncTable:
"""
return await self._inner.uri()
async def initial_storage_options(self) -> Optional[Dict[str, str]]:
"""Get the initial storage options that were passed in when opening this table.
For dynamically refreshed options (e.g., credential vending), use
:meth:`latest_storage_options`.
Warning: This is an internal API and the return value is subject to change.
Returns
-------
Optional[Dict[str, str]]
The storage options, or None if no storage options were configured.
"""
return await self._inner.initial_storage_options()
async def latest_storage_options(self) -> Optional[Dict[str, str]]:
"""Get the latest storage options, refreshing from provider if configured.
This method is useful for credential vending scenarios where storage options
may be refreshed dynamically. If no dynamic provider is configured, this
returns the initial static options.
Warning: This is an internal API and the return value is subject to change.
Returns
-------
Optional[Dict[str, str]]
The storage options, or None if no storage options were configured.
"""
return await self._inner.latest_storage_options()
async def add(
self,
data: DATA,
+15
View File
@@ -2,12 +2,27 @@
# 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:
+13 -4
View File
@@ -268,6 +268,8 @@ 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]],
@@ -286,10 +288,11 @@ 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", pa.utf8()),
pa.field("item", pandas_string_type()),
pa.field("price", pa.float64()),
]
)
@@ -299,7 +302,7 @@ 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", pa.utf8()),
pa.field("item", pandas_string_type()),
pa.field("price", pa.float64()),
pa.field("extra", pa.float32()),
]
@@ -365,6 +368,8 @@ 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]],
@@ -382,10 +387,11 @@ 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", pa.utf8()),
pa.field("item", pandas_string_type()),
pa.field("price", pa.float64()),
]
)
@@ -595,6 +601,8 @@ 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(
{
@@ -614,10 +622,11 @@ 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": pa.utf8(),
"item": pandas_string_type(),
"price": pa.float64(),
}
)
@@ -26,6 +26,8 @@ import pytest
from lance_namespace import (
CreateEmptyTableRequest,
CreateEmptyTableResponse,
DeclareTableRequest,
DeclareTableResponse,
DescribeTableRequest,
DescribeTableResponse,
LanceNamespace,
@@ -160,6 +162,19 @@ 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:
+10 -3
View File
@@ -528,12 +528,19 @@ 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": pa.large_utf8()
if isinstance(data, pl.DataFrame)
else pa.string(),
"text": text_type,
"vector": pa.list_(pa.float32(), 10),
}
)
+5 -12
View File
@@ -10,7 +10,8 @@ use arrow::{
use futures::stream::StreamExt;
use lancedb::arrow::SendableRecordBatchStream;
use pyo3::{
exceptions::PyStopAsyncIteration, pyclass, pymethods, Bound, Py, PyAny, PyRef, PyResult, Python,
exceptions::PyStopAsyncIteration, pyclass, pymethods, Bound, PyAny, PyObject, PyRef, PyResult,
Python,
};
use pyo3_async_runtimes::tokio::future_into_py;
@@ -35,11 +36,8 @@ impl RecordBatchStream {
#[pymethods]
impl RecordBatchStream {
#[getter]
pub fn schema(&self, py: Python) -> PyResult<Py<PyAny>> {
(*self.schema)
.clone()
.into_pyarrow(py)
.map(|obj| obj.unbind())
pub fn schema(&self, py: Python) -> PyResult<PyObject> {
(*self.schema).clone().into_pyarrow(py)
}
pub fn __aiter__(self_: PyRef<'_, Self>) -> PyRef<'_, Self> {
@@ -55,12 +53,7 @@ impl RecordBatchStream {
.next()
.await
.ok_or_else(|| PyStopAsyncIteration::new_err(""))?;
#[allow(deprecated)]
let py_obj: Py<PyAny> = Python::with_gil(|py| -> PyResult<Py<PyAny>> {
let bound = inner_next.infer_error()?.to_pyarrow(py)?;
Ok(bound.unbind())
})?;
Ok(py_obj)
Python::with_gil(|py| inner_next.infer_error()?.to_pyarrow(py))
})
}
}
+12 -15
View File
@@ -12,7 +12,7 @@ use pyo3::{
exceptions::{PyRuntimeError, PyValueError},
pyclass, pyfunction, pymethods,
types::{PyDict, PyDictMethods},
Bound, FromPyObject, Py, PyAny, PyRef, PyResult, Python,
Bound, FromPyObject, Py, PyAny, PyObject, 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<Py<PyAny>>,
storage_options_provider: Option<PyObject>,
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<Py<PyAny>>,
storage_options_provider: Option<PyObject>,
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<Py<PyAny>>,
storage_options_provider: Option<PyObject>,
index_cache_size: Option<u32>,
location: Option<String>,
) -> PyResult<Bound<'_, PyAny>> {
@@ -307,7 +307,6 @@ impl Connection {
..Default::default()
};
let response = inner.list_namespaces(request).await.infer_error()?;
#[allow(deprecated)]
Python::with_gil(|py| -> PyResult<Py<PyDict>> {
let dict = PyDict::new(py);
dict.set_item("namespaces", response.namespaces)?;
@@ -328,7 +327,8 @@ impl Connection {
let py = self_.py();
future_into_py(py, async move {
use lance_namespace::models::CreateNamespaceRequest;
let mode_enum = mode.and_then(|m| match m.to_lowercase().as_str() {
// 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()),
@@ -340,12 +340,11 @@ impl Connection {
} else {
Some(namespace)
},
mode: mode_enum,
mode: mode_str,
properties,
..Default::default()
};
let response = inner.create_namespace(request).await.infer_error()?;
#[allow(deprecated)]
Python::with_gil(|py| -> PyResult<Py<PyDict>> {
let dict = PyDict::new(py);
dict.set_item("properties", response.properties)?;
@@ -365,12 +364,13 @@ impl Connection {
let py = self_.py();
future_into_py(py, async move {
use lance_namespace::models::DropNamespaceRequest;
let mode_enum = mode.and_then(|m| match m.to_uppercase().as_str() {
// 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 behavior_enum = behavior.and_then(|b| match b.to_uppercase().as_str() {
let behavior_str = behavior.and_then(|b| match b.to_uppercase().as_str() {
"RESTRICT" => Some("Restrict".to_string()),
"CASCADE" => Some("Cascade".to_string()),
_ => None,
@@ -381,12 +381,11 @@ impl Connection {
} else {
Some(namespace)
},
mode: mode_enum,
behavior: behavior_enum,
mode: mode_str,
behavior: behavior_str,
..Default::default()
};
let response = inner.drop_namespace(request).await.infer_error()?;
#[allow(deprecated)]
Python::with_gil(|py| -> PyResult<Py<PyDict>> {
let dict = PyDict::new(py);
dict.set_item("properties", response.properties)?;
@@ -414,7 +413,6 @@ impl Connection {
..Default::default()
};
let response = inner.describe_namespace(request).await.infer_error()?;
#[allow(deprecated)]
Python::with_gil(|py| -> PyResult<Py<PyDict>> {
let dict = PyDict::new(py);
dict.set_item("properties", response.properties)?;
@@ -445,7 +443,6 @@ impl Connection {
..Default::default()
};
let response = inner.list_tables(request).await.infer_error()?;
#[allow(deprecated)]
Python::with_gil(|py| -> PyResult<Py<PyDict>> {
let dict = PyDict::new(py);
dict.set_item("tables", response.tables)?;
+47 -54
View File
@@ -40,34 +40,31 @@ impl<T> PythonErrorExt<T> for std::result::Result<T, LanceError> {
request_id,
source,
status_code,
} => {
#[allow(deprecated)]
Python::with_gil(|py| {
let message = err.to_string();
let http_err_cls = py
.import(intern!(py, "lancedb.remote.errors"))?
.getattr(intern!(py, "HttpError"))?;
let err = http_err_cls.call1((
message,
} => Python::with_gil(|py| {
let message = err.to_string();
let http_err_cls = py
.import(intern!(py, "lancedb.remote.errors"))?
.getattr(intern!(py, "HttpError"))?;
let err = http_err_cls.call1((
message,
request_id,
status_code.map(|s| s.as_u16()),
))?;
if let Some(cause) = source.source() {
// The HTTP error already includes the first cause. But
// we can add the rest of the chain if there is any more.
let cause_err = http_from_rust_error(
py,
cause,
request_id,
status_code.map(|s| s.as_u16()),
))?;
)?;
err.setattr(intern!(py, "__cause__"), cause_err)?;
}
if let Some(cause) = source.source() {
// The HTTP error already includes the first cause. But
// we can add the rest of the chain if there is any more.
let cause_err = http_from_rust_error(
py,
cause,
request_id,
status_code.map(|s| s.as_u16()),
)?;
err.setattr(intern!(py, "__cause__"), cause_err)?;
}
Err(PyErr::from_value(err))
})
}
Err(PyErr::from_value(err))
}),
LanceError::Retry {
request_id,
request_failures,
@@ -78,37 +75,33 @@ impl<T> PythonErrorExt<T> for std::result::Result<T, LanceError> {
max_read_failures,
source,
status_code,
} =>
{
#[allow(deprecated)]
Python::with_gil(|py| {
let cause_err = http_from_rust_error(
py,
source.as_ref(),
request_id,
status_code.map(|s| s.as_u16()),
)?;
} => Python::with_gil(|py| {
let cause_err = http_from_rust_error(
py,
source.as_ref(),
request_id,
status_code.map(|s| s.as_u16()),
)?;
let message = err.to_string();
let retry_error_cls = py
.import(intern!(py, "lancedb.remote.errors"))?
.getattr("RetryError")?;
let err = retry_error_cls.call1((
message,
request_id,
*request_failures,
*connect_failures,
*read_failures,
*max_request_failures,
*max_connect_failures,
*max_read_failures,
status_code.map(|s| s.as_u16()),
))?;
let message = err.to_string();
let retry_error_cls = py
.import(intern!(py, "lancedb.remote.errors"))?
.getattr("RetryError")?;
let err = retry_error_cls.call1((
message,
request_id,
*request_failures,
*connect_failures,
*read_failures,
*max_request_failures,
*max_connect_failures,
*max_read_failures,
status_code.map(|s| s.as_u16()),
))?;
err.setattr(intern!(py, "__cause__"), cause_err)?;
Err(PyErr::from_value(err))
})
}
err.setattr(intern!(py, "__cause__"), cause_err)?;
Err(PyErr::from_value(err))
}),
_ => self.runtime_error(),
},
}
-2
View File
@@ -12,7 +12,6 @@ pub struct PyHeaderProvider {
impl Clone for PyHeaderProvider {
fn clone(&self) -> Self {
#[allow(deprecated)]
Python::with_gil(|py| Self {
provider: self.provider.clone_ref(py),
})
@@ -26,7 +25,6 @@ impl PyHeaderProvider {
/// Get headers from the Python provider (internal implementation)
fn get_headers_internal(&self) -> Result<HashMap<String, String>, String> {
#[allow(deprecated)]
Python::with_gil(|py| {
// Call the get_headers method
let result = self.provider.call_method0(py, "get_headers");
+2 -7
View File
@@ -19,7 +19,7 @@ use pyo3::{
exceptions::PyRuntimeError,
pyclass, pymethods,
types::{PyAnyMethods, PyDict, PyDictMethods, PyType},
Bound, Py, PyAny, PyRef, PyRefMut, PyResult, Python,
Bound, PyAny, PyRef, PyRefMut, PyResult, Python,
};
use pyo3_async_runtimes::tokio::future_into_py;
@@ -281,12 +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()?;
#[allow(deprecated)]
let py_obj: Py<PyAny> = Python::with_gil(|py| -> PyResult<Py<PyAny>> {
let bound = schema.to_pyarrow(py)?;
Ok(bound.unbind())
})?;
Ok(py_obj)
Python::with_gil(|py| schema.to_pyarrow(py))
})
}
+4 -25
View File
@@ -29,7 +29,6 @@ use pyo3::types::PyList;
use pyo3::types::{PyDict, PyString};
use pyo3::Bound;
use pyo3::IntoPyObject;
use pyo3::Py;
use pyo3::PyAny;
use pyo3::PyRef;
use pyo3::PyResult;
@@ -454,12 +453,7 @@ impl Query {
let inner = self_.inner.clone();
future_into_py(self_.py(), async move {
let schema = inner.output_schema().await.infer_error()?;
#[allow(deprecated)]
let py_obj: Py<PyAny> = Python::with_gil(|py| -> PyResult<Py<PyAny>> {
let bound = schema.to_pyarrow(py)?;
Ok(bound.unbind())
})?;
Ok(py_obj)
Python::with_gil(|py| schema.to_pyarrow(py))
})
}
@@ -538,12 +532,7 @@ impl TakeQuery {
let inner = self_.inner.clone();
future_into_py(self_.py(), async move {
let schema = inner.output_schema().await.infer_error()?;
#[allow(deprecated)]
let py_obj: Py<PyAny> = Python::with_gil(|py| -> PyResult<Py<PyAny>> {
let bound = schema.to_pyarrow(py)?;
Ok(bound.unbind())
})?;
Ok(py_obj)
Python::with_gil(|py| schema.to_pyarrow(py))
})
}
@@ -638,12 +627,7 @@ impl FTSQuery {
let inner = self_.inner.clone();
future_into_py(self_.py(), async move {
let schema = inner.output_schema().await.infer_error()?;
#[allow(deprecated)]
let py_obj: Py<PyAny> = Python::with_gil(|py| -> PyResult<Py<PyAny>> {
let bound = schema.to_pyarrow(py)?;
Ok(bound.unbind())
})?;
Ok(py_obj)
Python::with_gil(|py| schema.to_pyarrow(py))
})
}
@@ -822,12 +806,7 @@ impl VectorQuery {
let inner = self_.inner.clone();
future_into_py(self_.py(), async move {
let schema = inner.output_schema().await.infer_error()?;
#[allow(deprecated)]
let py_obj: Py<PyAny> = Python::with_gil(|py| -> PyResult<Py<PyAny>> {
let bound = schema.to_pyarrow(py)?;
Ok(bound.unbind())
})?;
Ok(py_obj)
Python::with_gil(|py| schema.to_pyarrow(py))
})
}
+4 -10
View File
@@ -17,12 +17,11 @@ use pyo3::types::PyDict;
/// Internal wrapper around a Python object implementing StorageOptionsProvider
pub struct PyStorageOptionsProvider {
/// The Python object implementing fetch_storage_options()
inner: Py<PyAny>,
inner: PyObject,
}
impl Clone for PyStorageOptionsProvider {
fn clone(&self) -> Self {
#[allow(deprecated)]
Python::with_gil(|py| Self {
inner: self.inner.clone_ref(py),
})
@@ -30,8 +29,7 @@ impl Clone for PyStorageOptionsProvider {
}
impl PyStorageOptionsProvider {
pub fn new(obj: Py<PyAny>) -> PyResult<Self> {
#[allow(deprecated)]
pub fn new(obj: PyObject) -> PyResult<Self> {
Python::with_gil(|py| {
// Verify the object has a fetch_storage_options method
if !obj.bind(py).hasattr("fetch_storage_options")? {
@@ -39,9 +37,7 @@ impl PyStorageOptionsProvider {
"StorageOptionsProvider must implement fetch_storage_options() method",
));
}
Ok(Self {
inner: obj.clone_ref(py),
})
Ok(Self { inner: obj })
})
}
}
@@ -64,7 +60,6 @@ impl StorageOptionsProvider for PyStorageOptionsProviderWrapper {
let py_provider = self.py_provider.clone();
tokio::task::spawn_blocking(move || {
#[allow(deprecated)]
Python::with_gil(|py| {
// Call the Python fetch_storage_options method
let result = py_provider
@@ -124,7 +119,6 @@ impl StorageOptionsProvider for PyStorageOptionsProviderWrapper {
}
fn provider_id(&self) -> String {
#[allow(deprecated)]
Python::with_gil(|py| {
// Call provider_id() method on the Python object
let obj = self.py_provider.inner.bind(py);
@@ -149,7 +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: Py<PyAny>,
py_obj: PyObject,
) -> PyResult<Arc<dyn StorageOptionsProvider>> {
let py_provider = PyStorageOptionsProvider::new(py_obj)?;
Ok(Arc::new(PyStorageOptionsProviderWrapper::new(py_provider)))
+16 -11
View File
@@ -21,7 +21,7 @@ use pyo3::{
exceptions::{PyKeyError, PyRuntimeError, PyValueError},
pyclass, pymethods,
types::{IntoPyDict, PyAnyMethods, PyDict, PyDictMethods},
Bound, FromPyObject, Py, PyAny, PyRef, PyResult, Python,
Bound, FromPyObject, PyAny, PyRef, PyResult, Python,
};
use pyo3_async_runtimes::tokio::future_into_py;
@@ -287,12 +287,7 @@ impl Table {
let inner = self_.inner_ref()?.clone();
future_into_py(self_.py(), async move {
let schema = inner.schema().await.infer_error()?;
#[allow(deprecated)]
let py_obj: Py<PyAny> = Python::with_gil(|py| -> PyResult<Py<PyAny>> {
let bound = schema.to_pyarrow(py)?;
Ok(bound.unbind())
})?;
Ok(py_obj)
Python::with_gil(|py| schema.to_pyarrow(py))
})
}
@@ -442,7 +437,6 @@ impl Table {
future_into_py(self_.py(), async move {
let stats = inner.index_stats(&index_name).await.infer_error()?;
if let Some(stats) = stats {
#[allow(deprecated)]
Python::with_gil(|py| {
let dict = PyDict::new(py);
dict.set_item("num_indexed_rows", stats.num_indexed_rows)?;
@@ -473,7 +467,6 @@ impl Table {
let inner = self_.inner_ref()?.clone();
future_into_py(self_.py(), async move {
let stats = inner.stats().await.infer_error()?;
#[allow(deprecated)]
Python::with_gil(|py| {
let dict = PyDict::new(py);
dict.set_item("total_bytes", stats.total_bytes)?;
@@ -509,6 +502,20 @@ impl Table {
future_into_py(self_.py(), async move { inner.uri().await.infer_error() })
}
pub fn initial_storage_options(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
let inner = self_.inner_ref()?.clone();
future_into_py(self_.py(), async move {
Ok(inner.initial_storage_options().await)
})
}
pub fn latest_storage_options(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
let inner = self_.inner_ref()?.clone();
future_into_py(self_.py(), async move {
inner.latest_storage_options().await.infer_error()
})
}
pub fn __repr__(&self) -> String {
match &self.inner {
None => format!("ClosedTable({})", self.name),
@@ -528,7 +535,6 @@ impl Table {
let inner = self_.inner_ref()?.clone();
future_into_py(self_.py(), async move {
let versions = inner.list_versions().await.infer_error()?;
#[allow(deprecated)]
let versions_as_dict = Python::with_gil(|py| {
versions
.iter()
@@ -880,7 +886,6 @@ impl Tags {
let tags = inner.tags().await.infer_error()?;
let res = tags.list().await.infer_error()?;
#[allow(deprecated)]
Python::with_gil(|py| {
let py_dict = PyDict::new(py);
for (key, contents) in res {
+1 -1
View File
@@ -1,6 +1,6 @@
[package]
name = "lancedb"
version = "0.23.1"
version = "0.24.1"
edition.workspace = true
description = "LanceDB: A serverless, low-latency vector database for AI applications"
license.workspace = true
+128 -60
View File
@@ -36,10 +36,42 @@ 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::StorageOptionsProvider;
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));
}
/// A builder for configuring a [`Connection::table_names`] operation
pub struct TableNamesBuilder {
@@ -246,16 +278,14 @@ 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_options = self
let store_params = 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());
store_options.insert(key.into(), value.into());
merge_storage_options(store_params, [(key.into(), value.into())]);
self
}
@@ -269,19 +299,17 @@ impl<const HAS_DATA: bool> CreateTableBuilder<HAS_DATA> {
mut self,
pairs: impl IntoIterator<Item = (impl Into<String>, impl Into<String>)>,
) -> Self {
let store_options = self
let store_params = 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());
for (key, value) in pairs {
store_options.insert(key.into(), value.into());
}
let updates = pairs
.into_iter()
.map(|(key, value)| (key.into(), value.into()));
merge_storage_options(store_params, updates);
self
}
@@ -318,23 +346,21 @@ 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 storage_options = self
let store_params = 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);
storage_options.insert(
OPT_NEW_TABLE_V2_MANIFEST_PATHS.to_string(),
if use_v2_manifest_paths {
"true".to_string()
} else {
"false".to_string()
},
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)],
);
self
}
@@ -344,19 +370,19 @@ 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 storage_options = self
let store_params = 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);
storage_options.insert(
OPT_NEW_TABLE_STORAGE_VERSION.to_string(),
data_storage_version.to_string(),
merge_storage_options(
store_params,
[(
OPT_NEW_TABLE_STORAGE_VERSION.to_string(),
data_storage_version.to_string(),
)],
);
self
}
@@ -381,13 +407,14 @@ 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 {
self.request
let store_params = self
.request
.write_options
.lance_write_params
.get_or_insert(Default::default())
.store_params
.get_or_insert(Default::default())
.storage_options_provider = Some(provider);
.get_or_insert(Default::default());
set_storage_options_provider(store_params, provider);
self
}
}
@@ -450,15 +477,13 @@ 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 storage_options = self
let store_params = self
.request
.lance_read_params
.get_or_insert(Default::default())
.store_options
.get_or_insert(Default::default())
.storage_options
.get_or_insert(Default::default());
storage_options.insert(key.into(), value.into());
merge_storage_options(store_params, [(key.into(), value.into())]);
self
}
@@ -472,18 +497,16 @@ impl OpenTableBuilder {
mut self,
pairs: impl IntoIterator<Item = (impl Into<String>, impl Into<String>)>,
) -> Self {
let storage_options = self
let store_params = self
.request
.lance_read_params
.get_or_insert(Default::default())
.store_options
.get_or_insert(Default::default())
.storage_options
.get_or_insert(Default::default());
for (key, value) in pairs {
storage_options.insert(key.into(), value.into());
}
let updates = pairs
.into_iter()
.map(|(key, value)| (key.into(), value.into()));
merge_storage_options(store_params, updates);
self
}
@@ -507,12 +530,13 @@ 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 {
self.request
let store_params = self
.request
.lance_read_params
.get_or_insert(Default::default())
.store_options
.get_or_insert(Default::default())
.storage_options_provider = Some(provider);
.get_or_insert(Default::default());
set_storage_options_provider(store_params, provider);
self
}
@@ -868,6 +892,10 @@ pub struct ConnectBuilder {
embedding_registry: Option<Arc<dyn EmbeddingRegistry>>,
}
#[cfg(feature = "remote")]
const ENV_VARS_TO_STORAGE_OPTS: [(&str, &str); 1] =
[("AZURE_STORAGE_ACCOUNT_NAME", "azure_storage_account_name")];
impl ConnectBuilder {
/// Create a new [`ConnectOptions`] with the given database URI.
pub fn new(uri: &str) -> Self {
@@ -1051,11 +1079,27 @@ impl ConnectBuilder {
self
}
#[cfg(feature = "remote")]
fn apply_env_defaults(
env_var_to_remote_storage_option: &[(&str, &str)],
options: &mut HashMap<String, String>,
) {
for (env_key, opt_key) in env_var_to_remote_storage_option {
if let Ok(env_value) = std::env::var(env_key) {
if !options.contains_key(*opt_key) {
options.insert((*opt_key).to_string(), env_value);
}
}
}
}
#[cfg(feature = "remote")]
fn execute_remote(self) -> Result<Connection> {
use crate::remote::db::RemoteDatabaseOptions;
let options = RemoteDatabaseOptions::parse_from_map(&self.request.options)?;
let mut merged_options = self.request.options.clone();
Self::apply_env_defaults(&ENV_VARS_TO_STORAGE_OPTS, &mut merged_options);
let options = RemoteDatabaseOptions::parse_from_map(&merged_options)?;
let region = options.region.ok_or_else(|| Error::InvalidInput {
message: "A region is required when connecting to LanceDb Cloud".to_string(),
@@ -1277,8 +1321,6 @@ 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};
@@ -1302,6 +1344,23 @@ mod tests {
assert_eq!(tc.connection.uri(), tc.uri);
}
#[cfg(feature = "remote")]
#[test]
fn test_apply_env_defaults() {
let env_key = "TEST_APPLY_ENV_DEFAULTS_ENVIRONMENT_VARIABLE_ENV_KEY";
let env_val = "TEST_APPLY_ENV_DEFAULTS_ENVIRONMENT_VARIABLE_ENV_VAL";
let opts_key = "test_apply_env_defaults_environment_variable_opts_key";
std::env::set_var(env_key, env_val);
let mut options = HashMap::new();
ConnectBuilder::apply_env_defaults(&[(env_key, opts_key)], &mut options);
assert_eq!(Some(&env_val.to_string()), options.get(opts_key));
options.insert(opts_key.to_string(), "EXPLICIT-VALUE".to_string());
ConnectBuilder::apply_env_defaults(&[(env_key, opts_key)], &mut options);
assert_eq!(Some(&"EXPLICIT-VALUE".to_string()), options.get(opts_key));
}
#[cfg(not(windows))]
#[tokio::test]
async fn test_connect_relative() {
@@ -1526,18 +1585,27 @@ mod tests {
#[tokio::test]
async fn drop_table() {
let tmp_dir = tempdir().unwrap();
let tc = new_test_connection().await.unwrap();
let db = tc.connection;
let uri = tmp_dir.path().to_str().unwrap();
let db = connect(uri).execute().await.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 { .. }),
));
}
// 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();
let schema = Arc::new(Schema::new(vec![Field::new("x", DataType::Int32, false)]));
db.create_empty_table("table1", schema.clone())
.execute()
.await
.unwrap();
db.drop_table("table1", &[]).await.unwrap();
let tables = db.table_names().execute().await.unwrap();
+59 -35
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::StorageOptionsProvider;
use lance_io::object_store::{StorageOptionsAccessor, StorageOptionsProvider};
use lance_table::io::commit::commit_handler_from_url;
use object_store::local::LocalFileSystem;
use snafu::ResultExt;
@@ -356,7 +356,13 @@ impl ListingDatabase {
.clone()
.unwrap_or_else(|| Arc::new(lance::session::Session::default()));
let os_params = ObjectStoreParams {
storage_options: Some(options.storage_options.clone()),
storage_options_accessor: if options.storage_options.is_empty() {
None
} else {
Some(Arc::new(StorageOptionsAccessor::with_static_options(
options.storage_options.clone(),
)))
},
..Default::default()
};
let (object_store, base_path) = ObjectStore::from_uri_and_params(
@@ -492,7 +498,13 @@ impl ListingDatabase {
async fn drop_tables(&self, names: Vec<String>) -> Result<()> {
let object_store_params = ObjectStoreParams {
storage_options: Some(self.storage_options.clone()),
storage_options_accessor: if self.storage_options.is_empty() {
None
} else {
Some(Arc::new(StorageOptionsAccessor::with_static_options(
self.storage_options.clone(),
)))
},
..Default::default()
};
let mut uri = self.uri.clone();
@@ -541,7 +553,7 @@ impl ListingDatabase {
.lance_write_params
.as_ref()
.and_then(|p| p.store_params.as_ref())
.and_then(|sp| sp.storage_options.as_ref());
.and_then(|sp| sp.storage_options());
let storage_version_override = storage_options
.and_then(|opts| opts.get(OPT_NEW_TABLE_STORAGE_VERSION))
@@ -592,21 +604,20 @@ 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() {
let storage_options = write_params
if !self.storage_options.is_empty() || self.storage_options_provider.is_some() {
let store_params = write_params
.store_params
.get_or_insert_with(Default::default)
.storage_options
.get_or_insert_with(Default::default);
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();
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));
}
write_params.data_storage_version = self
@@ -892,7 +903,13 @@ impl Database for ListingDatabase {
validate_table_name(&request.target_table_name)?;
let storage_params = ObjectStoreParams {
storage_options: Some(self.storage_options.clone()),
storage_options_accessor: if self.storage_options.is_empty() {
None
} else {
Some(Arc::new(StorageOptionsAccessor::with_static_options(
self.storage_options.clone(),
)))
},
..Default::default()
};
let read_params = ReadParams {
@@ -956,25 +973,28 @@ 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() {
let storage_options = request
if !self.storage_options.is_empty() || self.storage_options_provider.is_some() {
let store_params = 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);
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();
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));
}
// Some ReadParams are exposed in the OpenTableBuilder, but we also
@@ -1881,7 +1901,9 @@ mod tests {
let write_options = WriteOptions {
lance_write_params: Some(lance::dataset::WriteParams {
store_params: Some(lance::io::ObjectStoreParams {
storage_options: Some(storage_options),
storage_options_accessor: Some(Arc::new(
StorageOptionsAccessor::with_static_options(storage_options),
)),
..Default::default()
}),
..Default::default()
@@ -1955,7 +1977,9 @@ mod tests {
let write_options = WriteOptions {
lance_write_params: Some(lance::dataset::WriteParams {
store_params: Some(lance::io::ObjectStoreParams {
storage_options: Some(storage_options),
storage_options_accessor: Some(Arc::new(
StorageOptionsAccessor::with_static_options(storage_options),
)),
..Default::default()
}),
..Default::default()
+47 -34
View File
@@ -9,14 +9,15 @@ use std::sync::Arc;
use async_trait::async_trait;
use lance_namespace::{
models::{
CreateNamespaceRequest, CreateNamespaceResponse, DeclareTableRequest,
DescribeNamespaceRequest, DescribeNamespaceResponse, DescribeTableRequest,
DropNamespaceRequest, DropNamespaceResponse, DropTableRequest, ListNamespacesRequest,
ListNamespacesResponse, ListTablesRequest, ListTablesResponse,
CreateEmptyTableRequest, 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};
@@ -154,7 +155,6 @@ impl Database for LanceNamespaceDatabase {
table_id.push(request.name.clone());
let describe_request = DescribeTableRequest {
id: Some(table_id.clone()),
version: None,
..Default::default()
};
@@ -205,26 +205,53 @@ impl Database for LanceNamespaceDatabase {
let mut table_id = request.namespace.clone();
table_id.push(request.name.clone());
let create_empty_request = DeclareTableRequest {
// 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 create_empty_response = self
.namespace
.declare_table(create_empty_request)
.await
.map_err(|e| Error::Runtime {
message: format!("Failed to declare table: {}", e),
})?;
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 location = create_empty_response
.location
.ok_or_else(|| Error::Runtime {
message: "Table location is missing from create_empty_table response".to_string(),
})?;
#[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 native_table = NativeTable::create_from_namespace(
self.namespace.clone(),
@@ -439,8 +466,6 @@ mod tests {
// Create a child namespace first
conn.create_namespace(CreateNamespaceRequest {
id: Some(vec!["test_ns".into()]),
mode: None,
properties: None,
..Default::default()
})
.await
@@ -501,8 +526,6 @@ mod tests {
// Create a child namespace first
conn.create_namespace(CreateNamespaceRequest {
id: Some(vec!["test_ns".into()]),
mode: None,
properties: None,
..Default::default()
})
.await
@@ -566,8 +589,6 @@ mod tests {
// Create a child namespace first
conn.create_namespace(CreateNamespaceRequest {
id: Some(vec!["test_ns".into()]),
mode: None,
properties: None,
..Default::default()
})
.await
@@ -651,8 +672,6 @@ mod tests {
// Create a child namespace first
conn.create_namespace(CreateNamespaceRequest {
id: Some(vec!["test_ns".into()]),
mode: None,
properties: None,
..Default::default()
})
.await
@@ -708,8 +727,6 @@ mod tests {
// Create a child namespace first
conn.create_namespace(CreateNamespaceRequest {
id: Some(vec!["test_ns".into()]),
mode: None,
properties: None,
..Default::default()
})
.await
@@ -790,8 +807,6 @@ mod tests {
// Create a child namespace first
conn.create_namespace(CreateNamespaceRequest {
id: Some(vec!["test_ns".into()]),
mode: None,
properties: None,
..Default::default()
})
.await
@@ -825,8 +840,6 @@ mod tests {
// Create a child namespace first
conn.create_namespace(CreateNamespaceRequest {
id: Some(vec!["test_ns".into()]),
mode: None,
properties: None,
..Default::default()
})
.await
@@ -171,7 +171,7 @@ impl Shuffler {
// This is kind of an annoying limitation but if we allow runt clumps from batches then
// clumps will get unaligned and we will mess up the clumps when we do the in-memory
// shuffle step. If this is a problem we can probably figure out a better way to do this.
if !is_last && batch.num_rows() as u64 % clump_size != 0 {
if !is_last && !(batch.num_rows() as u64).is_multiple_of(clump_size) {
return Err(Error::Runtime {
message: format!(
"Expected batch size ({}) to be divisible by clump size ({})",
@@ -1,12 +1,9 @@
// SPDX-License-Identifier: Apache-2.0
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
use std::{
iter,
sync::{
atomic::{AtomicBool, AtomicU64, AtomicUsize, Ordering},
Arc,
},
use std::sync::{
atomic::{AtomicBool, AtomicU64, AtomicUsize, Ordering},
Arc,
};
use arrow_array::{Array, BooleanArray, RecordBatch, UInt64Array};
@@ -158,7 +155,7 @@ impl Splitter {
remaining_in_split
};
split_ids.extend(iter::repeat(split_id as u64).take(rows_to_add as usize));
split_ids.extend(std::iter::repeat_n(split_id as u64, rows_to_add as usize));
if done {
// Quit early if we've run out of splits
break;
@@ -662,7 +659,7 @@ mod tests {
assert_eq!(split_batch.num_rows(), total_split_sizes as usize);
let mut expected = Vec::with_capacity(total_split_sizes as usize);
for (i, size) in expected_split_sizes.iter().enumerate() {
expected.extend(iter::repeat(i as u64).take(*size as usize));
expected.extend(std::iter::repeat_n(i as u64, *size as usize));
}
let expected = Arc::new(UInt64Array::from(expected)) as Arc<dyn Array>;
+2 -2
View File
@@ -297,10 +297,10 @@ impl IvfPqIndexBuilder {
}
pub(crate) fn suggested_num_sub_vectors(dim: u32) -> u32 {
if dim % 16 == 0 {
if dim.is_multiple_of(16) {
// Should be more aggressive than this default.
dim / 16
} else if dim % 8 == 0 {
} else if dim.is_multiple_of(8) {
dim / 8
} else {
log::warn!(
+5 -10
View File
@@ -51,24 +51,19 @@
//! - `s3://bucket/path/to/database` or `gs://bucket/path/to/database` - database on cloud object store
//! - `db://dbname` - Lance Cloud
//!
//! You can also use [`ConnectOptions`] to configure the connection to the database.
//! You can also use [`ConnectBuilder`] to configure the connection to the database.
//!
//! ```rust
//! # #[cfg(feature = "aws")]
//! # {
//! use object_store::aws::AwsCredential;
//! # tokio::runtime::Runtime::new().unwrap().block_on(async {
//! let db = lancedb::connect("data/sample-lancedb")
//! .aws_creds(AwsCredential {
//! key_id: "some_key".to_string(),
//! secret_key: "some_secret".to_string(),
//! token: None,
//! })
//! .storage_options([
//! ("aws_access_key_id", "some_key"),
//! ("aws_secret_access_key", "some_secret"),
//! ])
//! .execute()
//! .await
//! .unwrap();
//! # });
//! # }
//! ```
//!
//! LanceDB uses [arrow-rs](https://github.com/apache/arrow-rs) to define schema, data types and array itself.
-10
View File
@@ -1718,8 +1718,6 @@ mod tests {
let namespace = vec!["test_ns".to_string()];
conn.create_namespace(CreateNamespaceRequest {
id: Some(namespace.clone()),
mode: None,
properties: None,
..Default::default()
})
.await
@@ -1745,8 +1743,6 @@ mod tests {
let list_response = conn
.list_tables(ListTablesRequest {
id: Some(namespace.clone()),
page_token: None,
limit: None,
..Default::default()
})
.await
@@ -1758,8 +1754,6 @@ mod tests {
let list_response = namespace_client
.list_tables(ListTablesRequest {
id: Some(namespace.clone()),
page_token: None,
limit: None,
..Default::default()
})
.await
@@ -1800,8 +1794,6 @@ 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
@@ -1827,8 +1819,6 @@ mod tests {
let list_response = conn
.list_tables(ListTablesRequest {
id: Some(namespace.clone()),
page_token: None,
limit: None,
..Default::default()
})
.await
+8
View File
@@ -1493,6 +1493,14 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
None
}
async fn initial_storage_options(&self) -> Option<HashMap<String, String>> {
None
}
async fn latest_storage_options(&self) -> Result<Option<HashMap<String, String>>> {
Ok(None)
}
async fn stats(&self) -> Result<TableStatistics> {
let request = self
.client
+77 -44
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;
use lance_io::object_store::{LanceNamespaceStorageOptionsProvider, StorageOptionsAccessor};
use lance_namespace::models::{
QueryTableRequest as NsQueryTableRequest, QueryTableRequestColumns,
QueryTableRequestFullTextQuery, QueryTableRequestVector, StringFtsQuery,
@@ -611,7 +611,17 @@ pub trait BaseTable: std::fmt::Display + std::fmt::Debug + Send + Sync {
/// Get the table URI (storage location)
async fn uri(&self) -> Result<String>;
/// Get the storage options used when opening this table, if any.
#[deprecated(since = "0.25.0", note = "Use initial_storage_options() instead")]
async fn storage_options(&self) -> Option<HashMap<String, String>>;
/// Get the initial storage options that were passed in when opening this table.
///
/// For dynamically refreshed options (e.g., credential vending), use [`Self::latest_storage_options`].
async fn initial_storage_options(&self) -> Option<HashMap<String, String>>;
/// Get the latest storage options, refreshing from provider if configured.
///
/// Returns `Ok(Some(options))` if storage options are available (static or refreshed),
/// `Ok(None)` if no storage options were configured, or `Err(...)` if refresh failed.
async fn latest_storage_options(&self) -> Result<Option<HashMap<String, String>>>;
/// Poll until the columns are fully indexed. Will return Error::Timeout if the columns
/// are not fully indexed within the timeout.
async fn wait_for_index(
@@ -1328,10 +1338,32 @@ impl Table {
/// Get the storage options used when opening this table, if any.
///
/// Warning: This is an internal API and the return value is subject to change.
#[deprecated(since = "0.25.0", note = "Use initial_storage_options() instead")]
pub async fn storage_options(&self) -> Option<HashMap<String, String>> {
#[allow(deprecated)]
self.inner.storage_options().await
}
/// Get the initial storage options that were passed in when opening this table.
///
/// For dynamically refreshed options (e.g., credential vending), use [`Self::latest_storage_options`].
///
/// Warning: This is an internal API and the return value is subject to change.
pub async fn initial_storage_options(&self) -> Option<HashMap<String, String>> {
self.inner.initial_storage_options().await
}
/// Get the latest storage options, refreshing from provider if configured.
///
/// This method is useful for credential vending scenarios where storage options
/// may be refreshed dynamically. If no dynamic provider is configured, this
/// returns the initial static options.
///
/// Warning: This is an internal API and the return value is subject to change.
pub async fn latest_storage_options(&self) -> Result<Option<HashMap<String, String>>> {
self.inner.latest_storage_options().await
}
/// Get statistics about an index.
/// Returns None if the index does not exist.
pub async fn index_stats(
@@ -1425,9 +1457,7 @@ impl Table {
})
.collect::<Vec<_>>();
let unioned = UnionExec::try_new(projected_plans).map_err(|e| Error::Runtime {
message: format!("Failed to build union plan: {e}"),
})?;
let unioned = Arc::new(UnionExec::new(projected_plans));
// We require 1 partition in the final output
let repartitioned = RepartitionExec::try_new(
unioned,
@@ -1668,18 +1698,14 @@ 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,
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 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 dataset = builder
.with_read_params(params)
@@ -1883,7 +1909,13 @@ impl NativeTable {
let store_params = params
.store_params
.get_or_insert_with(ObjectStoreParams::default);
store_params.storage_options_provider = Some(storage_options_provider);
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));
// Patch the params if we have a write store wrapper
let params = match write_store_wrapper.clone() {
@@ -2059,7 +2091,7 @@ impl NativeTable {
return provided;
}
let suggested = suggested_num_sub_vectors(dim);
if num_bits.is_some_and(|num_bits| num_bits == 4) && suggested % 2 != 0 {
if num_bits.is_some_and(|num_bits| num_bits == 4) && !suggested.is_multiple_of(2) {
// num_sub_vectors must be even when 4 bits are used
suggested + 1
} else {
@@ -2349,7 +2381,7 @@ impl NativeTable {
};
// Convert select to columns list
let columns: Option<Box<QueryTableRequestColumns>> = match &vq.base.select {
let columns = match &vq.base.select {
Select::All => None,
Select::Columns(cols) => Some(Box::new(QueryTableRequestColumns {
column_names: Some(cols.clone()),
@@ -2407,7 +2439,6 @@ impl NativeTable {
with_row_id: Some(vq.base.with_row_id),
bypass_vector_index: Some(!vq.use_index),
full_text_query,
version: None,
..Default::default()
})
}
@@ -2426,7 +2457,7 @@ impl NativeTable {
.map(|f| self.filter_to_sql(f))
.transpose()?;
let columns: Option<Box<QueryTableRequestColumns>> = match &q.select {
let columns = match &q.select {
Select::All => None,
Select::Columns(cols) => Some(Box::new(QueryTableRequestColumns {
column_names: Some(cols.clone()),
@@ -2470,18 +2501,10 @@ 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,
version: None,
fast_search: None,
lower_bound: None,
upper_bound: None,
..Default::default()
})
}
@@ -3240,11 +3263,20 @@ impl BaseTable for NativeTable {
}
async fn storage_options(&self) -> Option<HashMap<String, String>> {
self.initial_storage_options().await
}
async fn initial_storage_options(&self) -> Option<HashMap<String, String>> {
self.dataset
.get()
.await
.ok()
.and_then(|dataset| dataset.storage_options().cloned())
.and_then(|dataset| dataset.initial_storage_options().cloned())
}
async fn latest_storage_options(&self) -> Result<Option<HashMap<String, String>>> {
let dataset = self.dataset.get().await?;
Ok(dataset.latest_storage_options().await?.map(|o| o.0))
}
async fn index_stats(&self, index_name: &str) -> Result<Option<IndexStatistics>> {
@@ -3409,7 +3441,6 @@ pub struct FragmentSummaryStats {
#[cfg(test)]
#[allow(deprecated)]
mod tests {
use std::iter;
use std::sync::atomic::{AtomicBool, Ordering};
use std::sync::Arc;
use std::time::Duration;
@@ -4026,7 +4057,7 @@ mod tests {
schema.clone(),
vec![
Arc::new(Int32Array::from_iter_values(offset..(offset + 10))),
Arc::new(Int32Array::from_iter_values(iter::repeat(age).take(10))),
Arc::new(Int32Array::from_iter_values(std::iter::repeat_n(age, 10))),
],
)],
schema,
@@ -5154,15 +5185,16 @@ mod tests {
let any_query = AnyQuery::VectorQuery(vq);
let ns_request = table.convert_to_namespace_query(&any_query).unwrap();
let column_names = ns_request
.columns
.as_ref()
.and_then(|cols| cols.column_names.clone());
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!(column_names, Some(vec!["id".to_string()]));
assert_eq!(
ns_request
.columns
.as_ref()
.and_then(|c| c.column_names.as_ref()),
Some(&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());
@@ -5199,16 +5231,17 @@ mod tests {
let any_query = AnyQuery::Query(q);
let ns_request = table.convert_to_namespace_query(&any_query).unwrap();
let column_names = ns_request
.columns
.as_ref()
.and_then(|cols| cols.column_names.clone());
// Plain queries should pass an empty vector
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!(column_names, Some(vec!["id".to_string()]));
assert_eq!(
ns_request
.columns
.as_ref()
.and_then(|c| c.column_names.as_ref()),
Some(&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
+1 -2
View File
@@ -100,8 +100,7 @@ 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::VersionNumber(target_ver) => version != target_ver,
refs::Ref::Tag(_) => true, // Always checkout for tags
refs::Ref::Tag(_) => true, // Always checkout for tags
};
if should_checkout {
@@ -4,7 +4,6 @@
use std::{
borrow::Cow,
collections::{HashMap, HashSet},
iter::repeat,
sync::Arc,
};
@@ -268,9 +267,10 @@ fn create_some_records() -> Result<impl IntoArrow> {
schema.clone(),
vec![
Arc::new(Int32Array::from_iter_values(0..TOTAL as i32)),
Arc::new(StringArray::from_iter(
repeat(Some("hello world".to_string())).take(TOTAL),
)),
Arc::new(StringArray::from_iter(std::iter::repeat_n(
Some("hello world".to_string()),
TOTAL,
))),
],
)
.unwrap()]