Avoid embedding warnings

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.
2026-03-26 02:20:40 +00:00 · 2026-01-30 12:35:45 -05:00 · 2026-01-22 13:36:05 -08:00 · 2026-01-22 13:17:03 -08:00 · 2026-01-22 13:14:38 -08:00 · 2026-01-22 01:10:15 +00:00
38 changed files with 539 additions and 611 deletions
--- a/.bumpversion.toml
+++ b/.bumpversion.toml
@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.24.0-beta.1"
+current_version = "0.24.0"
 parse = """(?x)
    (?P<major>0|[1-9]\\d*)\\.
    (?P<minor>0|[1-9]\\d*)\\.
--- a/Cargo.lock
+++ b/Cargo.lock
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -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-rc.1", default-features = false, "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=2.0.0-rc.1", default-features = false, "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=2.0.0-rc.1", default-features = false, "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=2.0.0-rc.1", "tag" = "v2.0.0-rc.1", "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 = "57.2", 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"
 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"
--- a/docs/src/java/java.md
+++ b/docs/src/java/java.md
@@ -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.1</version>
+    <version>0.24.0</version>
 </dependency>
 ```

--- a/java/lancedb-core/pom.xml
+++ b/java/lancedb-core/pom.xml
@@ -8,7 +8,7 @@
    <parent>
      <groupId>com.lancedb</groupId>
      <artifactId>lancedb-parent</artifactId>
-      <version>0.24.0-beta.1</version>
+      <version>0.24.0-final.0</version>
      <relativePath>../pom.xml</relativePath>
    </parent>

--- a/java/pom.xml
+++ b/java/pom.xml
@@ -6,7 +6,7 @@

    <groupId>com.lancedb</groupId>
    <artifactId>lancedb-parent</artifactId>
-    <version>0.24.0-beta.1</version>
+    <version>0.24.0-final.0</version>
    <packaging>pom</packaging>
    <name>${project.artifactId}</name>
    <description>LanceDB Java SDK Parent POM</description>
--- a/nodejs/Cargo.toml
+++ b/nodejs/Cargo.toml
@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.24.0-beta.1"
+version = "0.24.0"
 license.workspace = true
 description.workspace = true
 repository.workspace = true
--- a/nodejs/test/table.test.ts
+++ b/nodejs/test/table.test.ts
@@ -1520,9 +1520,9 @@ describe("when optimizing a dataset", () => {

  it("delete unverified", async () => {
    const version = await table.version();
-    const versionFile = `${tmpDir.name}/${table.name}.lance/_versions/${
-      version - 1
-    }.manifest`;
+    const versionFile = `${tmpDir.name}/${table.name}.lance/_versions/${String(
+      18446744073709551615n - (BigInt(version) - 1n),
+    ).padStart(20, "0")}.manifest`;
    fs.rmSync(versionFile);

    let stats = await table.optimize({ deleteUnverified: false });
--- a/nodejs/npm/darwin-arm64/package.json
+++ b/nodejs/npm/darwin-arm64/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.24.0-beta.1",
+	"version": "0.24.0",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",
--- a/nodejs/npm/darwin-x64/package.json
+++ b/nodejs/npm/darwin-x64/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-x64",
-	"version": "0.24.0-beta.1",
+	"version": "0.24.0",
 	"os": ["darwin"],
 	"cpu": ["x64"],
 	"main": "lancedb.darwin-x64.node",
--- a/nodejs/npm/linux-arm64-gnu/package.json
+++ b/nodejs/npm/linux-arm64-gnu/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.24.0-beta.1",
+	"version": "0.24.0",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",
--- a/nodejs/npm/linux-arm64-musl/package.json
+++ b/nodejs/npm/linux-arm64-musl/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-musl",
-	"version": "0.24.0-beta.1",
+	"version": "0.24.0",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-musl.node",
--- a/nodejs/npm/linux-x64-gnu/package.json
+++ b/nodejs/npm/linux-x64-gnu/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.24.0-beta.1",
+	"version": "0.24.0",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",
--- a/nodejs/npm/linux-x64-musl/package.json
+++ b/nodejs/npm/linux-x64-musl/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-musl",
-	"version": "0.24.0-beta.1",
+	"version": "0.24.0",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-musl.node",
--- a/nodejs/npm/win32-arm64-msvc/package.json
+++ b/nodejs/npm/win32-arm64-msvc/package.json
@@ -1,6 +1,6 @@
 {
  "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.24.0-beta.1",
+  "version": "0.24.0",
  "os": [
    "win32"
  ],
--- a/nodejs/npm/win32-x64-msvc/package.json
+++ b/nodejs/npm/win32-x64-msvc/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.24.0-beta.1",
+	"version": "0.24.0",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",
--- a/nodejs/package-lock.json
+++ b/nodejs/package-lock.json
@@ -1,12 +1,12 @@
 {
  "name": "@lancedb/lancedb",
-  "version": "0.24.0-beta.0",
+  "version": "0.24.0",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "@lancedb/lancedb",
-      "version": "0.24.0-beta.0",
+      "version": "0.24.0",
      "cpu": [
        "x64",
        "arm64"
--- a/nodejs/package.json
+++ b/nodejs/package.json
@@ -11,7 +11,7 @@
    "ann"
  ],
  "private": false,
-  "version": "0.24.0-beta.1",
+  "version": "0.24.0",
  "main": "dist/index.js",
  "exports": {
    ".": "./dist/index.js",
--- a/python/Cargo.toml
+++ b/python/Cargo.toml
@@ -14,15 +14,15 @@ name = "_lancedb"
 crate-type = ["cdylib"]

 [dependencies]
-arrow = { version = "56.2", features = ["pyarrow"] }
+arrow = { version = "57.2", 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 = "0.25", 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",
 ] }
@@ -32,7 +32,7 @@ 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",
 ] }
--- a/python/python/lancedb/embeddings/colpali.py
+++ b/python/python/lancedb/embeddings/colpali.py
@@ -9,6 +9,8 @@ import numpy as np
 import io
 import warnings

+from pydantic import Field
+
 from ..util import attempt_import_or_raise
 from .base import EmbeddingFunction
 from .registry import register
@@ -26,7 +28,7 @@ class ColPaliEmbeddings(EmbeddingFunction):

    Parameters
    ----------
-    model_name : str
+    colpali_model_name : str
        The name of the model to use (e.g., "Metric-AI/ColQwen2.5-3b-multilingual-v1.0")
        Supports models based on these engines:
        - ColPali: "vidore/colpali-v1.3" and others
@@ -57,7 +59,10 @@ class ColPaliEmbeddings(EmbeddingFunction):
        useful for large models that do not fit in memory.
    """

-    model_name: str = "Metric-AI/ColQwen2.5-3b-multilingual-v1.0"
+    colpali_model_name: str = Field(
+        default="Metric-AI/ColQwen2.5-3b-multilingual-v1.0",
+        validation_alias="model_name",
+    )
    device: str = "auto"
    dtype: str = "bfloat16"
    use_token_pooling: bool = True
@@ -107,7 +112,7 @@ class ColPaliEmbeddings(EmbeddingFunction):
            self._processor,
            self._token_pooler,
        ) = self._load_model(
-            self.model_name,
+            self.colpali_model_name,
            dtype,
            device,
            self.pooling_strategy,
--- a/python/python/lancedb/embeddings/siglip.py
+++ b/python/python/lancedb/embeddings/siglip.py
@@ -10,7 +10,7 @@ import urllib.parse as urlparse
 import numpy as np
 import pyarrow as pa
 from tqdm import tqdm
-from pydantic import PrivateAttr
+from pydantic import Field, PrivateAttr

 from ..util import attempt_import_or_raise
 from .base import EmbeddingFunction
@@ -24,7 +24,10 @@ if TYPE_CHECKING:

@register("siglip")
 class SigLipEmbeddings(EmbeddingFunction):
-    model_name: str = "google/siglip-base-patch16-224"
+    siglip_model_name: str = Field(
+        default="google/siglip-base-patch16-224",
+        validation_alias="model_name",
+    )
    device: str = "cpu"
    batch_size: int = 64
    normalize: bool = True
@@ -39,8 +42,10 @@ class SigLipEmbeddings(EmbeddingFunction):
        transformers = attempt_import_or_raise("transformers")
        self._torch = attempt_import_or_raise("torch")

-        self._processor = transformers.AutoProcessor.from_pretrained(self.model_name)
-        self._model = transformers.SiglipModel.from_pretrained(self.model_name)
+        self._processor = transformers.AutoProcessor.from_pretrained(
+            self.siglip_model_name
+        )
+        self._model = transformers.SiglipModel.from_pretrained(self.siglip_model_name)
        self._model.to(self.device)
        self._model.eval()
        self._ndims = None
--- a/python/python/lancedb/query.py
+++ b/python/python/lancedb/query.py
@@ -961,22 +961,27 @@ class LanceQueryBuilder(ABC):
        >>> query = [100, 100]
        >>> plan = table.search(query).analyze_plan()
        >>> print(plan)  # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
-        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=[...],
+        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=[...],
                  preserve_partitioning=[...],
-                  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=...
+                  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=...]

        Returns
        -------
--- a/python/python/tests/test_remote_db.py
+++ b/python/python/tests/test_remote_db.py
@@ -601,7 +601,6 @@ def test_head():
 def test_query_sync_minimal():
    def handler(body):
        assert body == {
-            "distance_type": "l2",
            "k": 10,
            "prefilter": True,
            "refine_factor": None,
@@ -685,7 +684,6 @@ def test_query_sync_maximal():
 def test_query_sync_nprobes():
    def handler(body):
        assert body == {
-            "distance_type": "l2",
            "k": 10,
            "prefilter": True,
            "fast_search": True,
@@ -715,7 +713,6 @@ def test_query_sync_nprobes():
 def test_query_sync_no_max_nprobes():
    def handler(body):
        assert body == {
-            "distance_type": "l2",
            "k": 10,
            "prefilter": True,
            "fast_search": True,
@@ -838,7 +835,6 @@ def test_query_sync_hybrid():
        else:
            # Vector query
            assert body == {
-                "distance_type": "l2",
                "k": 42,
                "prefilter": True,
                "refine_factor": None,
--- a/python/python/tests/test_table.py
+++ b/python/python/tests/test_table.py
@@ -1880,8 +1880,13 @@ async def test_optimize_delete_unverified(tmp_db_async: AsyncConnection, tmp_pat
        ],
    )
    version = await table.version()
-    path = tmp_path / "test.lance" / "_versions" / f"{version - 1}.manifest"
+    assert version == 2
+
+    # By removing a manifest file, we make the data files we just inserted unverified
+    version_name = 18446744073709551615 - (version - 1)
+    path = tmp_path / "test.lance" / "_versions" / f"{version_name:020}.manifest"
    os.remove(path)
+
    stats = await table.optimize(delete_unverified=False)
    assert stats.prune.old_versions_removed == 0
    stats = await table.optimize(
--- a/python/src/arrow.rs
+++ b/python/src/arrow.rs
@@ -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(|obj| obj.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(|obj| obj.unbind())
+            })
        })
    }
 }
--- a/python/src/connection.rs
+++ b/python/src/connection.rs
@@ -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>> {
@@ -307,7 +307,7 @@ impl Connection {
                ..Default::default()
            };
            let response = inner.list_namespaces(request).await.infer_error()?;
-            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
+            Python::attach(|py| -> PyResult<Py<PyDict>> {
                let dict = PyDict::new(py);
                dict.set_item("namespaces", response.namespaces)?;
                dict.set_item("page_token", response.page_token)?;
@@ -345,7 +345,7 @@ impl Connection {
                ..Default::default()
            };
            let response = inner.create_namespace(request).await.infer_error()?;
-            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
+            Python::attach(|py| -> PyResult<Py<PyDict>> {
                let dict = PyDict::new(py);
                dict.set_item("properties", response.properties)?;
                Ok(dict.unbind())
@@ -386,7 +386,7 @@ impl Connection {
                ..Default::default()
            };
            let response = inner.drop_namespace(request).await.infer_error()?;
-            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
+            Python::attach(|py| -> PyResult<Py<PyDict>> {
                let dict = PyDict::new(py);
                dict.set_item("properties", response.properties)?;
                dict.set_item("transaction_id", response.transaction_id)?;
@@ -413,7 +413,7 @@ impl Connection {
                ..Default::default()
            };
            let response = inner.describe_namespace(request).await.infer_error()?;
-            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
+            Python::attach(|py| -> PyResult<Py<PyDict>> {
                let dict = PyDict::new(py);
                dict.set_item("properties", response.properties)?;
                Ok(dict.unbind())
@@ -443,7 +443,7 @@ impl Connection {
                ..Default::default()
            };
            let response = inner.list_tables(request).await.infer_error()?;
-            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
+            Python::attach(|py| -> PyResult<Py<PyDict>> {
                let dict = PyDict::new(py);
                dict.set_item("tables", response.tables)?;
                dict.set_item("page_token", response.page_token)?;
--- a/python/src/error.rs
+++ b/python/src/error.rs
@@ -40,7 +40,7 @@ impl<T> PythonErrorExt<T> for std::result::Result<T, LanceError> {
                    request_id,
                    source,
                    status_code,
-                } => Python::with_gil(|py| {
+                } => Python::attach(|py| {
                    let message = err.to_string();
                    let http_err_cls = py
                        .import(intern!(py, "lancedb.remote.errors"))?
@@ -75,7 +75,7 @@ impl<T> PythonErrorExt<T> for std::result::Result<T, LanceError> {
                    max_read_failures,
                    source,
                    status_code,
-                } => Python::with_gil(|py| {
+                } => Python::attach(|py| {
                    let cause_err = http_from_rust_error(
                        py,
                        source.as_ref(),
--- a/python/src/header.rs
+++ b/python/src/header.rs
@@ -12,7 +12,7 @@ pub struct PyHeaderProvider {

 impl Clone for PyHeaderProvider {
    fn clone(&self) -> Self {
-        Python::with_gil(|py| Self {
+        Python::attach(|py| Self {
            provider: self.provider.clone_ref(py),
        })
    }
@@ -25,7 +25,7 @@ impl PyHeaderProvider {

    /// Get headers from the Python provider (internal implementation)
    fn get_headers_internal(&self) -> Result<HashMap<String, String>, String> {
-        Python::with_gil(|py| {
+        Python::attach(|py| {
            // Call the get_headers method
            let result = self.provider.call_method0(py, "get_headers");

--- a/python/src/permutation.rs
+++ b/python/src/permutation.rs
@@ -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::attach(|py| schema.to_pyarrow(py).map(|obj| obj.unbind()))
        })
    }

--- a/python/src/query.rs
+++ b/python/src/query.rs
@@ -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::attach(|py| schema.to_pyarrow(py).map(|obj| obj.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::attach(|py| schema.to_pyarrow(py).map(|obj| obj.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::attach(|py| schema.to_pyarrow(py).map(|obj| obj.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::attach(|py| schema.to_pyarrow(py).map(|obj| obj.unbind()))
        })
    }

--- a/python/src/storage_options.rs
+++ b/python/src/storage_options.rs
@@ -17,20 +17,20 @@ 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 {
    fn clone(&self) -> Self {
-        Python::with_gil(|py| Self {
+        Python::attach(|py| Self {
            inner: self.inner.clone_ref(py),
        })
    }
 }

 impl PyStorageOptionsProvider {
-    pub fn new(obj: PyObject) -> PyResult<Self> {
-        Python::with_gil(|py| {
+    pub fn new(obj: Py<PyAny>) -> PyResult<Self> {
+        Python::attach(|py| {
            // Verify the object has a fetch_storage_options method
            if !obj.bind(py).hasattr("fetch_storage_options")? {
                return Err(pyo3::exceptions::PyTypeError::new_err(
@@ -60,7 +60,7 @@ impl StorageOptionsProvider for PyStorageOptionsProviderWrapper {
        let py_provider = self.py_provider.clone();

        tokio::task::spawn_blocking(move || {
-            Python::with_gil(|py| {
+            Python::attach(|py| {
                // Call the Python fetch_storage_options method
                let result = py_provider
                    .inner
@@ -119,7 +119,7 @@ impl StorageOptionsProvider for PyStorageOptionsProviderWrapper {
    }

    fn provider_id(&self) -> String {
-        Python::with_gil(|py| {
+        Python::attach(|py| {
            // Call provider_id() method on the Python object
            let obj = self.py_provider.inner.bind(py);
            obj.call_method0("provider_id")
@@ -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)))
--- a/python/src/table.rs
+++ b/python/src/table.rs
@@ -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::attach(|py| schema.to_pyarrow(py).map(|obj| obj.unbind()))
        })
    }

@@ -437,7 +437,7 @@ impl Table {
        future_into_py(self_.py(), async move {
            let stats = inner.index_stats(&index_name).await.infer_error()?;
            if let Some(stats) = stats {
-                Python::with_gil(|py| {
+                Python::attach(|py| {
                    let dict = PyDict::new(py);
                    dict.set_item("num_indexed_rows", stats.num_indexed_rows)?;
                    dict.set_item("num_unindexed_rows", stats.num_unindexed_rows)?;
@@ -467,7 +467,7 @@ impl Table {
        let inner = self_.inner_ref()?.clone();
        future_into_py(self_.py(), async move {
            let stats = inner.stats().await.infer_error()?;
-            Python::with_gil(|py| {
+            Python::attach(|py| {
                let dict = PyDict::new(py);
                dict.set_item("total_bytes", stats.total_bytes)?;
                dict.set_item("num_rows", stats.num_rows)?;
@@ -521,7 +521,7 @@ impl Table {
        let inner = self_.inner_ref()?.clone();
        future_into_py(self_.py(), async move {
            let versions = inner.list_versions().await.infer_error()?;
-            let versions_as_dict = Python::with_gil(|py| {
+            let versions_as_dict = Python::attach(|py| {
                versions
                    .iter()
                    .map(|v| {
@@ -872,7 +872,7 @@ impl Tags {
            let tags = inner.tags().await.infer_error()?;
            let res = tags.list().await.infer_error()?;

-            Python::with_gil(|py| {
+            Python::attach(|py| {
                let py_dict = PyDict::new(py);
                for (key, contents) in res {
                    let value_dict = PyDict::new(py);
--- a/rust/lancedb/Cargo.toml
+++ b/rust/lancedb/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.24.0-beta.1"
+version = "0.24.0"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true
--- a/rust/lancedb/src/connection.rs
+++ b/rust/lancedb/src/connection.rs
@@ -892,6 +892,9 @@ pub struct ConnectBuilder {
    embedding_registry: Option<Arc<dyn EmbeddingRegistry>>,
 }

+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 {
@@ -1075,11 +1078,27 @@ 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(),
@@ -1324,6 +1343,23 @@ 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() {
--- a/rust/lancedb/src/lib.rs
+++ b/rust/lancedb/src/lib.rs
@@ -51,17 +51,15 @@
 //! - `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
-//! 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();
--- a/rust/lancedb/src/remote/table.rs
+++ b/rust/lancedb/src/remote/table.rs
@@ -468,7 +468,9 @@ impl<S: HttpSend> RemoteTable<S> {
        self.apply_query_params(&mut body, &query.base)?;

        // Apply general parameters, before we dispatch based on number of query vectors.
-        body["distance_type"] = serde_json::json!(query.distance_type.unwrap_or_default());
+        if let Some(distance_type) = query.distance_type {
+            body["distance_type"] = serde_json::json!(distance_type);
+        }
        // In 0.23.1 we migrated from `nprobes` to `minimum_nprobes` and `maximum_nprobes`.
        // Old client / new server: since minimum_nprobes is missing, fallback to nprobes
        // New client / old server: old server will only see nprobes, make sure to set both
@@ -2230,7 +2232,6 @@ mod tests {
            let body: serde_json::Value = serde_json::from_slice(body).unwrap();
            let mut expected_body = serde_json::json!({
                "prefilter": true,
-                "distance_type": "l2",
                "nprobes": 20,
                "minimum_nprobes": 20,
                "maximum_nprobes": 20,
--- a/rust/lancedb/src/table.rs
+++ b/rust/lancedb/src/table.rs
@@ -1425,7 +1425,9 @@ impl Table {
            })
            .collect::<Vec<_>>();

-        let unioned = Arc::new(UnionExec::new(projected_plans));
+        let unioned = UnionExec::try_new(projected_plans).map_err(|err| Error::Runtime {
+            message: err.to_string(),
+        })?;
        // We require 1 partition in the final output
        let repartitioned = RepartitionExec::try_new(
            unioned,
--- a/rust/lancedb/src/table/dataset.rs
+++ b/rust/lancedb/src/table/dataset.rs
@@ -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 {
Author	SHA1	Message	Date
Dan Tasse	65c14f6b40	Avoid embedding warnings	2026-01-30 12:35:45 -05:00
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