Bump version: 0.26.1 → 0.27.0-beta.0

feat: expose table uri (#2922 )
* Expose `table.uri` property for all tables, including remote tables * Fix bug in path calculation on windows file systems
2026-03-28 03:20:39 +00:00 · 2026-01-21 12:21:09 +00:00 · 2026-01-20 19:56:46 -03:30 · 2026-01-16 01:46:52 +08:00 · 2026-01-13 11:23:14 -08:00 · 2026-01-13 20:42:11 +05:30
27 changed files with 797 additions and 673 deletions
--- a/.github/workflows/rust.yml
+++ b/.github/workflows/rust.yml
@@ -167,13 +167,13 @@ jobs:
      - name: Build
        run: |
          $env:VCPKG_ROOT = $env:VCPKG_INSTALLATION_ROOT
-          cargo build --profile ci --features remote --tests --locked --target ${{ matrix.target }}
+          cargo build --profile ci --features aws,remote --tests --locked --target ${{ matrix.target }}
      - name: Run tests
        # Can only run tests when target matches host
        if: ${{ matrix.target == 'x86_64-pc-windows-msvc' }}
        run: |
          $env:VCPKG_ROOT = $env:VCPKG_INSTALLATION_ROOT
-          cargo test --profile ci --features remote --locked
+          cargo test --profile ci --features aws,remote --locked

  msrv:
    # Check the minimum supported Rust version
--- 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" = "=1.0.1", default-features = false }
-lance-core = "=1.0.1"
-lance-datagen = "=1.0.1"
-lance-file = "=1.0.1"
-lance-io = { "version" = "=1.0.1", default-features = false }
-lance-index = "=1.0.1"
-lance-linalg = "=1.0.1"
-lance-namespace = "=1.0.1"
-lance-namespace-impls = { "version" = "=1.0.1", default-features = false }
-lance-table = "=1.0.1"
-lance-testing = "=1.0.1"
-lance-datafusion = "=1.0.1"
-lance-encoding = "=1.0.1"
-lance-arrow = "=1.0.1"
+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" }
 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"
@@ -59,7 +59,7 @@ rand = "0.9"
 snafu = "0.8"
 url = "2"
 num-traits = "0.2"
-regex = "1.10"
+regex = "1.12"
 lazy_static = "1"
 semver = "1.0.25"
 chrono = "0.4"
--- a/nodejs/Cargo.toml
+++ b/nodejs/Cargo.toml
@@ -36,6 +36,6 @@ aws-lc-rs = "=1.13.0"
 napi-build = "2.1"

 [features]
-default = ["remote", "lancedb/default"]
+default = ["remote", "lancedb/aws", "lancedb/gcs", "lancedb/azure", "lancedb/dynamodb", "lancedb/oss", "lancedb/huggingface"]
 fp16kernels = ["lancedb/fp16kernels"]
 remote = ["lancedb/remote"]
--- a/python/.bumpversion.toml
+++ b/python/.bumpversion.toml
@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.26.1"
+current_version = "0.27.0-beta.0"
 parse = """(?x)
    (?P<major>0|[1-9]\\d*)\\.
    (?P<minor>0|[1-9]\\d*)\\.
--- a/python/Cargo.toml
+++ b/python/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.26.1"
+version = "0.27.0-beta.0"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true
@@ -14,15 +14,15 @@ name = "_lancedb"
 crate-type = ["cdylib"]

 [dependencies]
-arrow = { version = "56.2", features = ["pyarrow"] }
+arrow = { 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",
 ] }
@@ -32,12 +32,12 @@ snafu.workspace = true
 tokio = { version = "1.40", features = ["sync"] }

 [build-dependencies]
-pyo3-build-config = { version = "0.25", features = [
+pyo3-build-config = { version = "0.26", features = [
    "extension-module",
    "abi3-py39",
 ] }

 [features]
-default = ["remote", "lancedb/default"]
+default = ["remote",  "lancedb/aws", "lancedb/gcs", "lancedb/azure", "lancedb/dynamodb", "lancedb/oss", "lancedb/huggingface"]
 fp16kernels = ["lancedb/fp16kernels"]
 remote = ["lancedb/remote"]
--- a/python/python/lancedb/_lancedb.pyi
+++ b/python/python/lancedb/_lancedb.pyi
@@ -179,6 +179,7 @@ class Table:
        cleanup_since_ms: Optional[int] = None,
        delete_unverified: Optional[bool] = None,
    ) -> OptimizeStats: ...
+    async def uri(self) -> str: ...
    @property
    def tags(self) -> Tags: ...
    def query(self) -> Query: ...
--- 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/lancedb/remote/table.py
+++ b/python/python/lancedb/remote/table.py
@@ -655,6 +655,14 @@ class RemoteTable(Table):
    def stats(self):
        return LOOP.run(self._table.stats())

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

--- a/python/python/lancedb/table.py
+++ b/python/python/lancedb/table.py
@@ -2218,6 +2218,10 @@ class LanceTable(Table):
    def stats(self) -> TableStatistics:
        return LOOP.run(self._table.stats())

+    @property
+    def uri(self) -> str:
+        return LOOP.run(self._table.uri())
+
    def create_scalar_index(
        self,
        column: str,
@@ -3606,6 +3610,20 @@ class AsyncTable:
        """
        return await self._inner.stats()

+    async def uri(self) -> str:
+        """
+        Get the table URI (storage location).
+
+        For remote tables, this fetches the location from the server via describe.
+        For local tables, this returns the dataset URI.
+
+        Returns
+        -------
+        str
+            The full storage location of the table (e.g., S3/GCS path).
+        """
+        return await self._inner.uri()
+
    async def add(
        self,
        data: DATA,
--- a/python/python/tests/test_table.py
+++ b/python/python/tests/test_table.py
@@ -1967,3 +1967,9 @@ def test_add_table_with_empty_embeddings(tmp_path):
        on_bad_vectors="drop",
    )
    assert table.count_rows() == 1
+
+
+def test_table_uri(tmp_path):
+    db = lancedb.connect(tmp_path)
+    table = db.create_table("my_table", data=[{"x": 0}])
+    assert table.uri == str(tmp_path / "my_table.lance")
--- 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))
+            #[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)
        })
    }
 }
--- 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>> {
@@ -304,8 +304,10 @@ impl Connection {
                },
                page_token,
                limit: limit.map(|l| l as i32),
+                ..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)?;
@@ -325,11 +327,11 @@ impl Connection {
        let inner = self_.get_inner()?.clone();
        let py = self_.py();
        future_into_py(py, async move {
-            use lance_namespace::models::{create_namespace_request, CreateNamespaceRequest};
+            use lance_namespace::models::CreateNamespaceRequest;
            let mode_enum = mode.and_then(|m| match m.to_lowercase().as_str() {
-                "create" => Some(create_namespace_request::Mode::Create),
-                "exist_ok" => Some(create_namespace_request::Mode::ExistOk),
-                "overwrite" => Some(create_namespace_request::Mode::Overwrite),
+                "create" => Some("Create".to_string()),
+                "exist_ok" => Some("ExistOk".to_string()),
+                "overwrite" => Some("Overwrite".to_string()),
                _ => None,
            });
            let request = CreateNamespaceRequest {
@@ -340,8 +342,10 @@ impl Connection {
                },
                mode: mode_enum,
                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)?;
@@ -360,15 +364,15 @@ impl Connection {
        let inner = self_.get_inner()?.clone();
        let py = self_.py();
        future_into_py(py, async move {
-            use lance_namespace::models::{drop_namespace_request, DropNamespaceRequest};
+            use lance_namespace::models::DropNamespaceRequest;
            let mode_enum = mode.and_then(|m| match m.to_uppercase().as_str() {
-                "SKIP" => Some(drop_namespace_request::Mode::Skip),
-                "FAIL" => Some(drop_namespace_request::Mode::Fail),
+                "SKIP" => Some("Skip".to_string()),
+                "FAIL" => Some("Fail".to_string()),
                _ => None,
            });
            let behavior_enum = behavior.and_then(|b| match b.to_uppercase().as_str() {
-                "RESTRICT" => Some(drop_namespace_request::Behavior::Restrict),
-                "CASCADE" => Some(drop_namespace_request::Behavior::Cascade),
+                "RESTRICT" => Some("Restrict".to_string()),
+                "CASCADE" => Some("Cascade".to_string()),
                _ => None,
            });
            let request = DropNamespaceRequest {
@@ -379,8 +383,10 @@ impl Connection {
                },
                mode: mode_enum,
                behavior: behavior_enum,
+                ..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)?;
@@ -405,8 +411,10 @@ impl Connection {
                } else {
                    Some(namespace)
                },
+                ..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)?;
@@ -434,8 +442,10 @@ impl Connection {
                },
                page_token,
                limit: limit.map(|l| l as i32),
+                ..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)?;
--- a/python/src/error.rs
+++ b/python/src/error.rs
@@ -40,31 +40,34 @@ impl<T> PythonErrorExt<T> for std::result::Result<T, LanceError> {
                    request_id,
                    source,
                    status_code,
-                } => 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,
+                } => {
+                    #[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,
                            request_id,
                            status_code.map(|s| s.as_u16()),
-                        )?;
-                        err.setattr(intern!(py, "__cause__"), cause_err)?;
-                    }
+                        ))?;

-                    Err(PyErr::from_value(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))
+                    })
+                }
                LanceError::Retry {
                    request_id,
                    request_failures,
@@ -75,33 +78,37 @@ impl<T> PythonErrorExt<T> for std::result::Result<T, LanceError> {
                    max_read_failures,
                    source,
                    status_code,
-                } => Python::with_gil(|py| {
-                    let cause_err = http_from_rust_error(
-                        py,
-                        source.as_ref(),
-                        request_id,
-                        status_code.map(|s| s.as_u16()),
-                    )?;
+                } =>
+                {
+                    #[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()),
+                        )?;

-                    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(),
            },
        }
--- a/python/src/header.rs
+++ b/python/src/header.rs
@@ -12,6 +12,7 @@ pub struct PyHeaderProvider {

 impl Clone for PyHeaderProvider {
    fn clone(&self) -> Self {
+        #[allow(deprecated)]
        Python::with_gil(|py| Self {
            provider: self.provider.clone_ref(py),
        })
@@ -25,6 +26,7 @@ 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");
--- a/python/src/permutation.rs
+++ b/python/src/permutation.rs
@@ -19,7 +19,7 @@ use pyo3::{
    exceptions::PyRuntimeError,
    pyclass, pymethods,
    types::{PyAnyMethods, PyDict, PyDictMethods, PyType},
-    Bound, PyAny, PyRef, PyRefMut, PyResult, Python,
+    Bound, Py, PyAny, PyRef, PyRefMut, PyResult, Python,
 };
 use pyo3_async_runtimes::tokio::future_into_py;

@@ -281,7 +281,12 @@ 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))
+            #[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)
        })
    }

--- a/python/src/query.rs
+++ b/python/src/query.rs
@@ -29,6 +29,7 @@ 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;
@@ -453,7 +454,12 @@ 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))
+            #[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)
        })
    }

@@ -532,7 +538,12 @@ 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))
+            #[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)
        })
    }

@@ -627,7 +638,12 @@ 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))
+            #[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)
        })
    }

@@ -806,7 +822,12 @@ 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))
+            #[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)
        })
    }

--- a/python/src/storage_options.rs
+++ b/python/src/storage_options.rs
@@ -17,11 +17,12 @@ 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 {
+        #[allow(deprecated)]
        Python::with_gil(|py| Self {
            inner: self.inner.clone_ref(py),
        })
@@ -29,7 +30,8 @@ impl Clone for PyStorageOptionsProvider {
 }

 impl PyStorageOptionsProvider {
-    pub fn new(obj: PyObject) -> PyResult<Self> {
+    pub fn new(obj: Py<PyAny>) -> PyResult<Self> {
+        #[allow(deprecated)]
        Python::with_gil(|py| {
            // Verify the object has a fetch_storage_options method
            if !obj.bind(py).hasattr("fetch_storage_options")? {
@@ -37,7 +39,9 @@ impl PyStorageOptionsProvider {
                    "StorageOptionsProvider must implement fetch_storage_options() method",
                ));
            }
-            Ok(Self { inner: obj })
+            Ok(Self {
+                inner: obj.clone_ref(py),
+            })
        })
    }
 }
@@ -60,6 +64,7 @@ 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
@@ -119,6 +124,7 @@ 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);
@@ -143,7 +149,7 @@ 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
@@ -21,7 +21,7 @@ use pyo3::{
    exceptions::{PyKeyError, PyRuntimeError, PyValueError},
    pyclass, pymethods,
    types::{IntoPyDict, PyAnyMethods, PyDict, PyDictMethods},
-    Bound, FromPyObject, PyAny, PyRef, PyResult, Python,
+    Bound, FromPyObject, Py, PyAny, PyRef, PyResult, Python,
 };
 use pyo3_async_runtimes::tokio::future_into_py;

@@ -287,7 +287,12 @@ 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))
+            #[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)
        })
    }

@@ -437,6 +442,7 @@ impl Table {
        future_into_py(self_.py(), async move {
            let stats = inner.index_stats(&index_name).await.infer_error()?;
            if let Some(stats) = stats {
+                #[allow(deprecated)]
                Python::with_gil(|py| {
                    let dict = PyDict::new(py);
                    dict.set_item("num_indexed_rows", stats.num_indexed_rows)?;
@@ -467,6 +473,7 @@ 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)?;
@@ -497,6 +504,11 @@ impl Table {
        })
    }

+    pub fn uri(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.inner_ref()?.clone();
+        future_into_py(self_.py(), async move { inner.uri().await.infer_error() })
+    }
+
    pub fn __repr__(&self) -> String {
        match &self.inner {
            None => format!("ClosedTable({})", self.name),
@@ -516,6 +528,7 @@ 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()
@@ -867,6 +880,7 @@ 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 {
--- a/rust/lancedb/Cargo.toml
+++ b/rust/lancedb/Cargo.toml
@@ -104,11 +104,16 @@ test-log = "0.2"


 [features]
-default = ["aws", "gcs", "azure", "dynamodb", "oss"]
+default = []
 aws = ["lance/aws", "lance-io/aws", "lance-namespace-impls/dir-aws"]
 oss = ["lance/oss", "lance-io/oss", "lance-namespace-impls/dir-oss"]
 gcs = ["lance/gcp", "lance-io/gcp", "lance-namespace-impls/dir-gcp"]
 azure = ["lance/azure", "lance-io/azure", "lance-namespace-impls/dir-azure"]
+huggingface = [
+    "lance/huggingface",
+    "lance-io/huggingface",
+    "lance-namespace-impls/dir-huggingface",
+]
 dynamodb = ["lance/dynamodb", "aws"]
 remote = ["dep:reqwest", "dep:http", "lance-namespace-impls/rest", "lance-namespace-impls/rest-adapter"]
 fp16kernels = ["lance-linalg/fp16kernels"]
@@ -148,3 +153,6 @@ name = "ivf_pq"
 [[example]]
 name = "hybrid_search"
 required-features = ["sentence-transformers"]
+
+[package.metadata.docs.rs]
+all-features = true
--- a/rust/lancedb/src/database/listing.rs
+++ b/rust/lancedb/src/database/listing.rs
@@ -463,9 +463,20 @@ impl ListingDatabase {
        validate_table_name(name)?;

        let mut uri = self.uri.clone();
-        // If the URI does not end with a slash, add one
-        if !uri.ends_with('/') {
-            uri.push('/');
+        // If the URI does not end with a path separator, add one
+        // Use forward slash for URIs (http://, s3://, gs://, file://, etc.)
+        // Use platform-specific separator for local paths without scheme
+        let has_scheme = uri.contains("://");
+        let ends_with_separator = uri.ends_with('/') || uri.ends_with('\\');
+
+        if !ends_with_separator {
+            if has_scheme {
+                // URIs always use forward slash
+                uri.push('/');
+            } else {
+                // Local path without scheme - use platform separator
+                uri.push(std::path::MAIN_SEPARATOR);
+            }
        }
        // Append the table name with the lance file extension
        uri.push_str(&format!("{}.{}", name, LANCE_FILE_EXTENSION));
@@ -1071,6 +1082,7 @@ mod tests {
    use crate::table::{Table, TableDefinition};
    use arrow_array::{Int32Array, RecordBatch, StringArray};
    use arrow_schema::{DataType, Field, Schema};
+    use std::path::PathBuf;
    use tempfile::tempdir;

    async fn setup_database() -> (tempfile::TempDir, ListingDatabase) {
@@ -2046,6 +2058,19 @@ mod tests {
        assert_eq!(db_options.new_table_config.enable_stable_row_ids, None);
    }

+    #[tokio::test]
+    async fn test_table_uri() {
+        let (_tempdir, db) = setup_database().await;
+
+        let mut pb = PathBuf::new();
+        pb.push(db.uri.clone());
+        pb.push("test.lance");
+
+        let expected = pb.to_str().unwrap();
+        let uri = db.table_uri("test").ok().unwrap();
+        assert_eq!(uri, expected);
+    }
+
    #[tokio::test]
    async fn test_namespace_client() {
        let (_tempdir, db) = setup_database().await;
--- a/rust/lancedb/src/database/namespace.rs
+++ b/rust/lancedb/src/database/namespace.rs
@@ -9,7 +9,7 @@ use std::sync::Arc;
 use async_trait::async_trait;
 use lance_namespace::{
    models::{
-        CreateEmptyTableRequest, CreateNamespaceRequest, CreateNamespaceResponse,
+        CreateNamespaceRequest, CreateNamespaceResponse, DeclareTableRequest,
        DescribeNamespaceRequest, DescribeNamespaceResponse, DescribeTableRequest,
        DropNamespaceRequest, DropNamespaceResponse, DropTableRequest, ListNamespacesRequest,
        ListNamespacesResponse, ListTablesRequest, ListTablesResponse,
@@ -137,6 +137,7 @@ impl Database for LanceNamespaceDatabase {
            id: Some(request.namespace),
            page_token: request.start_after,
            limit: request.limit.map(|l| l as i32),
+            ..Default::default()
        };

        let response = self.namespace.list_tables(ns_request).await?;
@@ -154,6 +155,7 @@ impl Database for LanceNamespaceDatabase {
        let describe_request = DescribeTableRequest {
            id: Some(table_id.clone()),
            version: None,
+            ..Default::default()
        };

        let describe_result = self.namespace.describe_table(describe_request).await;
@@ -171,6 +173,7 @@ impl Database for LanceNamespaceDatabase {
                    // Drop the existing table - must succeed
                    let drop_request = DropTableRequest {
                        id: Some(table_id.clone()),
+                        ..Default::default()
                    };
                    self.namespace
                        .drop_table(drop_request)
@@ -202,22 +205,19 @@ impl Database for LanceNamespaceDatabase {
        let mut table_id = request.namespace.clone();
        table_id.push(request.name.clone());

-        let create_empty_request = CreateEmptyTableRequest {
+        let create_empty_request = DeclareTableRequest {
            id: Some(table_id.clone()),
            location: None,
-            properties: if self.storage_options.is_empty() {
-                None
-            } else {
-                Some(self.storage_options.clone())
-            },
+            vend_credentials: None,
+            ..Default::default()
        };

        let create_empty_response = self
            .namespace
-            .create_empty_table(create_empty_request)
+            .declare_table(create_empty_request)
            .await
            .map_err(|e| Error::Runtime {
-                message: format!("Failed to create empty table: {}", e),
+                message: format!("Failed to declare table: {}", e),
            })?;

        let location = create_empty_response
@@ -281,7 +281,10 @@ impl Database for LanceNamespaceDatabase {
        let mut table_id = namespace.to_vec();
        table_id.push(name.to_string());

-        let drop_request = DropTableRequest { id: Some(table_id) };
+        let drop_request = DropTableRequest {
+            id: Some(table_id),
+            ..Default::default()
+        };
        self.namespace
            .drop_table(drop_request)
            .await
@@ -438,6 +441,7 @@ mod tests {
            id: Some(vec!["test_ns".into()]),
            mode: None,
            properties: None,
+            ..Default::default()
        })
        .await
        .expect("Failed to create namespace");
@@ -499,6 +503,7 @@ mod tests {
            id: Some(vec!["test_ns".into()]),
            mode: None,
            properties: None,
+            ..Default::default()
        })
        .await
        .expect("Failed to create namespace");
@@ -563,6 +568,7 @@ mod tests {
            id: Some(vec!["test_ns".into()]),
            mode: None,
            properties: None,
+            ..Default::default()
        })
        .await
        .expect("Failed to create namespace");
@@ -647,6 +653,7 @@ mod tests {
            id: Some(vec!["test_ns".into()]),
            mode: None,
            properties: None,
+            ..Default::default()
        })
        .await
        .expect("Failed to create namespace");
@@ -703,6 +710,7 @@ mod tests {
            id: Some(vec!["test_ns".into()]),
            mode: None,
            properties: None,
+            ..Default::default()
        })
        .await
        .expect("Failed to create namespace");
@@ -784,6 +792,7 @@ mod tests {
            id: Some(vec!["test_ns".into()]),
            mode: None,
            properties: None,
+            ..Default::default()
        })
        .await
        .expect("Failed to create namespace");
@@ -818,6 +827,7 @@ mod tests {
            id: Some(vec!["test_ns".into()]),
            mode: None,
            properties: None,
+            ..Default::default()
        })
        .await
        .expect("Failed to create namespace");
--- a/rust/lancedb/src/lib.rs
+++ b/rust/lancedb/src/lib.rs
@@ -25,13 +25,14 @@
 //!
 //! ## Crate Features
 //!
-//! ### Experimental Features
-//!
-//! These features are not enabled by default.  They are experimental or in-development features that
-//! are not yet ready to be released.
-//!
-//! - `remote` - Enable remote client to connect to LanceDB cloud.  This is not yet fully implemented
-//!   and should not be enabled.
+//! - `aws` - Enable AWS S3 object store support.
+//! - `dynamodb` - Enable DynamoDB manifest store support.
+//! - `azure` - Enable Azure Blob Storage object store support.
+//! - `gcs` - Enable Google Cloud Storage object store support.
+//! - `oss` - Enable Alibaba Cloud OSS object store support.
+//! - `remote` - Enable remote client to connect to LanceDB cloud.
+//! - `huggingface` - Enable HuggingFace Hub integration for loading datasets from the Hub.
+//! - `fp16kernels` - Enable FP16 kernels for faster vector search on CPU.
 //!
 //! ### Quick Start
 //!
@@ -53,6 +54,8 @@
 //! You can also use [`ConnectOptions`] 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")
@@ -65,6 +68,7 @@
 //!     .await
 //!     .unwrap();
 //! # });
+//! # }
 //! ```
 //!
 //! LanceDB uses [arrow-rs](https://github.com/apache/arrow-rs) to define schema, data types and array itself.
--- a/rust/lancedb/src/remote/db.rs
+++ b/rust/lancedb/src/remote/db.rs
@@ -1720,6 +1720,7 @@ mod tests {
                id: Some(namespace.clone()),
                mode: None,
                properties: None,
+                ..Default::default()
            })
            .await
            .expect("Failed to create namespace");
@@ -1746,6 +1747,7 @@ mod tests {
                    id: Some(namespace.clone()),
                    page_token: None,
                    limit: None,
+                    ..Default::default()
                })
                .await
                .expect("Failed to list tables");
@@ -1758,6 +1760,7 @@ mod tests {
                    id: Some(namespace.clone()),
                    page_token: None,
                    limit: None,
+                    ..Default::default()
                })
                .await
                .unwrap();
@@ -1799,6 +1802,7 @@ mod tests {
                id: Some(namespace.clone()),
                mode: None,
                properties: None,
+                ..Default::default()
            })
            .await
            .expect("Failed to create namespace");
@@ -1825,6 +1829,7 @@ mod tests {
                    id: Some(namespace.clone()),
                    page_token: None,
                    limit: None,
+                    ..Default::default()
                })
                .await
                .unwrap();
--- a/rust/lancedb/src/remote/table.rs
+++ b/rust/lancedb/src/remote/table.rs
@@ -204,6 +204,7 @@ pub struct RemoteTable<S: HttpSend = Sender> {
    server_version: ServerVersion,

    version: RwLock<Option<u64>>,
+    location: RwLock<Option<String>>,
 }

 impl<S: HttpSend> RemoteTable<S> {
@@ -221,6 +222,7 @@ impl<S: HttpSend> RemoteTable<S> {
            identifier,
            server_version,
            version: RwLock::new(None),
+            location: RwLock::new(None),
        }
    }

@@ -639,6 +641,7 @@ impl<S: HttpSend> RemoteTable<S> {
 struct TableDescription {
    version: u64,
    schema: JsonSchema,
+    location: Option<String>,
 }

 impl<S: HttpSend> std::fmt::Display for RemoteTable<S> {
@@ -667,6 +670,7 @@ mod test_utils {
                identifier: name,
                server_version: version.map(ServerVersion).unwrap_or_default(),
                version: RwLock::new(None),
+                location: RwLock::new(None),
            }
        }
    }
@@ -1461,8 +1465,28 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
            message: "table_definition is not supported on LanceDB cloud.".into(),
        })
    }
-    fn dataset_uri(&self) -> &str {
-        "NOT_SUPPORTED"
+    async fn uri(&self) -> Result<String> {
+        // Check if we already have the location cached
+        {
+            let location = self.location.read().await;
+            if let Some(ref loc) = *location {
+                return Ok(loc.clone());
+            }
+        }
+
+        // Fetch from server via describe
+        let description = self.describe().await?;
+        let location = description.location.ok_or_else(|| Error::NotSupported {
+            message: "Table URI not supported by the server".into(),
+        })?;
+
+        // Cache the location for future use
+        {
+            let mut cached_location = self.location.write().await;
+            *cached_location = Some(location.clone());
+        }
+
+        Ok(location)
    }

    async fn storage_options(&self) -> Option<HashMap<String, String>> {
@@ -3332,4 +3356,69 @@ mod tests {
        let result = table.drop_columns(&["old_col1", "old_col2"]).await.unwrap();
        assert_eq!(result.version, 5);
    }
+
+    #[tokio::test]
+    async fn test_uri() {
+        let table = Table::new_with_handler("my_table", |request| {
+            assert_eq!(request.method(), "POST");
+            assert_eq!(request.url().path(), "/v1/table/my_table/describe/");
+
+            http::Response::builder()
+                .status(200)
+                .body(r#"{"version": 1, "schema": {"fields": []}, "location": "s3://bucket/path/to/table"}"#)
+                .unwrap()
+        });
+
+        let uri = table.uri().await.unwrap();
+        assert_eq!(uri, "s3://bucket/path/to/table");
+    }
+
+    #[tokio::test]
+    async fn test_uri_missing_location() {
+        let table = Table::new_with_handler("my_table", |request| {
+            assert_eq!(request.method(), "POST");
+            assert_eq!(request.url().path(), "/v1/table/my_table/describe/");
+
+            // Server returns response without location field
+            http::Response::builder()
+                .status(200)
+                .body(r#"{"version": 1, "schema": {"fields": []}}"#)
+                .unwrap()
+        });
+
+        let result = table.uri().await;
+        assert!(result.is_err());
+        assert!(matches!(&result, Err(Error::NotSupported { .. })));
+    }
+
+    #[tokio::test]
+    async fn test_uri_caching() {
+        use std::sync::atomic::{AtomicUsize, Ordering};
+        use std::sync::Arc;
+
+        let call_count = Arc::new(AtomicUsize::new(0));
+        let call_count_clone = call_count.clone();
+
+        let table = Table::new_with_handler("my_table", move |request| {
+            assert_eq!(request.url().path(), "/v1/table/my_table/describe/");
+            call_count_clone.fetch_add(1, Ordering::SeqCst);
+
+            http::Response::builder()
+                .status(200)
+                .body(
+                    r#"{"version": 1, "schema": {"fields": []}, "location": "gs://bucket/table"}"#,
+                )
+                .unwrap()
+        });
+
+        // First call should fetch from server
+        let uri1 = table.uri().await.unwrap();
+        assert_eq!(uri1, "gs://bucket/table");
+        assert_eq!(call_count.load(Ordering::SeqCst), 1);
+
+        // Second call should use cached value
+        let uri2 = table.uri().await.unwrap();
+        assert_eq!(uri2, "gs://bucket/table");
+        assert_eq!(call_count.load(Ordering::SeqCst), 1); // Still 1, no new call
+    }
 }
--- a/rust/lancedb/src/table.rs
+++ b/rust/lancedb/src/table.rs
@@ -42,8 +42,8 @@ use lance_index::DatasetIndexExt;
 use lance_index::IndexType;
 use lance_io::object_store::LanceNamespaceStorageOptionsProvider;
 use lance_namespace::models::{
-    QueryTableRequest as NsQueryTableRequest, QueryTableRequestFullTextQuery,
-    QueryTableRequestVector, StringFtsQuery,
+    QueryTableRequest as NsQueryTableRequest, QueryTableRequestColumns,
+    QueryTableRequestFullTextQuery, QueryTableRequestVector, StringFtsQuery,
 };
 use lance_namespace::LanceNamespace;
 use lance_table::format::Manifest;
@@ -608,8 +608,8 @@ pub trait BaseTable: std::fmt::Display + std::fmt::Debug + Send + Sync {
    async fn list_versions(&self) -> Result<Vec<Version>>;
    /// Get the table definition.
    async fn table_definition(&self) -> Result<TableDefinition>;
-    /// Get the table URI
-    fn dataset_uri(&self) -> &str;
+    /// Get the table URI (storage location)
+    async fn uri(&self) -> Result<String>;
    /// Get the storage options used when opening this table, if any.
    async fn storage_options(&self) -> Option<HashMap<String, String>>;
    /// Poll until the columns are fully indexed. Will return Error::Timeout if the columns
@@ -1317,11 +1317,12 @@ impl Table {
        self.inner.list_indices().await
    }

-    /// Get the underlying dataset URI
+    /// Get the table URI (storage location)
    ///
-    /// Warning: This is an internal API and the return value is subject to change.
-    pub fn dataset_uri(&self) -> &str {
-        self.inner.dataset_uri()
+    /// Returns the full storage location of the table (e.g., S3/GCS path).
+    /// For remote tables, this fetches the location from the server via describe.
+    pub async fn uri(&self) -> Result<String> {
+        self.inner.uri().await
    }

    /// Get the storage options used when opening this table, if any.
@@ -1424,7 +1425,9 @@ impl Table {
            })
            .collect::<Vec<_>>();

-        let unioned = Arc::new(UnionExec::new(projected_plans));
+        let unioned = UnionExec::try_new(projected_plans).map_err(|e| Error::Runtime {
+            message: format!("Failed to build union plan: {e}"),
+        })?;
        // We require 1 partition in the final output
        let repartitioned = RepartitionExec::try_new(
            unioned,
@@ -2346,9 +2349,12 @@ impl NativeTable {
                };

                // Convert select to columns list
-                let columns = match &vq.base.select {
+                let columns: Option<Box<QueryTableRequestColumns>> = match &vq.base.select {
                    Select::All => None,
-                    Select::Columns(cols) => Some(cols.clone()),
+                    Select::Columns(cols) => Some(Box::new(QueryTableRequestColumns {
+                        column_names: Some(cols.clone()),
+                        column_aliases: None,
+                    })),
                    Select::Dynamic(_) => {
                        return Err(Error::NotSupported {
                            message:
@@ -2402,6 +2408,7 @@ impl NativeTable {
                    bypass_vector_index: Some(!vq.use_index),
                    full_text_query,
                    version: None,
+                    ..Default::default()
                })
            }
            AnyQuery::Query(q) => {
@@ -2419,9 +2426,12 @@ impl NativeTable {
                    .map(|f| self.filter_to_sql(f))
                    .transpose()?;

-                let columns = match &q.select {
+                let columns: Option<Box<QueryTableRequestColumns>> = match &q.select {
                    Select::All => None,
-                    Select::Columns(cols) => Some(cols.clone()),
+                    Select::Columns(cols) => Some(Box::new(QueryTableRequestColumns {
+                        column_names: Some(cols.clone()),
+                        column_aliases: None,
+                    })),
                    Select::Dynamic(_) => {
                        return Err(Error::NotSupported {
                            message: "Dynamic columns are not supported for server-side query"
@@ -2472,6 +2482,7 @@ impl NativeTable {
                    fast_search: None,
                    lower_bound: None,
                    upper_bound: None,
+                    ..Default::default()
                })
            }
        }
@@ -3224,8 +3235,8 @@ impl BaseTable for NativeTable {
        Ok(results.into_iter().flatten().collect())
    }

-    fn dataset_uri(&self) -> &str {
-        self.uri.as_str()
+    async fn uri(&self) -> Result<String> {
+        Ok(self.uri.clone())
    }

    async fn storage_options(&self) -> Option<HashMap<String, String>> {
@@ -5143,10 +5154,15 @@ 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!(ns_request.columns, Some(vec!["id".to_string()]));
+        assert_eq!(column_names, 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());
@@ -5183,11 +5199,16 @@ 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!(ns_request.columns, Some(vec!["id".to_string()]));
+        assert_eq!(column_names, 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
--- 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
Lance Release	446a69b51b	Bump version: 0.26.1 → 0.27.0-beta.0	2026-01-21 12:21:09 +00:00
Ryan Green	cd5f91bb7d	feat: expose table uri (#2922 ) * Expose `table.uri` property for all tables, including remote tables * Fix bug in path calculation on windows file systems	2026-01-20 19:56:46 -03:30
LanceDB Robot	4da01a0e65	chore: update lance dependency to v2.0.0-beta.8 (#2907 ) ## Summary - bump Lance crates to v2.0.0-beta.8 and align arrow/datafusion/regex/half and PyO3 dependencies - update Rust/Python bindings for upstream API changes (namespace/table requests, query select columns, storage option providers) - verified with cargo clippy --workspace --tests --all-features -D warnings and cargo fmt --all Triggered by refs/tags/v2.0.0-beta.8. --------- Signed-off-by: BubbleCal <bubble-cal@outlook.com> Co-authored-by: BubbleCal <bubble-cal@outlook.com>	2026-01-16 01:46:52 +08:00
Will Jones	1840aa7edc	feat(rust)!: remove default features (#2912 ) BREAKING CHANGE: removes `aws`, `dynamodb`, `azure`, `gcs`, `oss`, `huggingface` from default Rust features. They can be enabled by users as needed. They are still enabled for Python and NodeJS, since those users don't control the compilation of artifacts. Closes #2911	2026-01-13 11:23:14 -08:00
Xuanwo	489c91c5d6	feat: enable huggingface feature by default (#2910 )	2026-01-13 20:42:11 +05:30
LanceDB Robot	f0c3fe5c6d	chore: update lance dependency to v1.0.2-rc.2 (#2908 ) ## Summary - bump Lance dependencies to v1.0.2-rc.2 using ci/set_lance_version.py - verified cargo clippy --workspace --tests --all-features -D warnings - ran cargo fmt --all Tag: https://github.com/lance-format/lance/releases/tag/v1.0.2-rc.2	2026-01-12 12:28:07 -08:00