chore: update lance dependency to v2.0.0-beta.9

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

.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

Cargo.toml

@@ -15,37 +15,37 @@ 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.9", default-features = false, "tag" = "v2.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=2.0.0-beta.9", "tag" = "v2.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=2.0.0-beta.9", "tag" = "v2.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=2.0.0-beta.9", "tag" = "v2.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=2.0.0-beta.9", default-features = false, "tag" = "v2.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=2.0.0-beta.9", "tag" = "v2.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=2.0.0-beta.9", "tag" = "v2.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=2.0.0-beta.9", "tag" = "v2.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=2.0.0-beta.9", default-features = false, "tag" = "v2.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=2.0.0-beta.9", "tag" = "v2.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=2.0.0-beta.9", "tag" = "v2.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=2.0.0-beta.9", "tag" = "v2.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=2.0.0-beta.9", "tag" = "v2.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=2.0.0-beta.9", "tag" = "v2.0.0-beta.9", "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 = [
     "num-traits",

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"]

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",
 ] }
@@ -32,12 +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"]

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())
+            })
         })
     }
 }

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>> {
@@ -297,6 +297,8 @@ impl Connection {
         future_into_py(py, async move {
             use lance_namespace::models::ListNamespacesRequest;
             let request = ListNamespacesRequest {
+                identity: None,
+                context: None,
                 id: if namespace.is_empty() {
                     None
                 } else {
@@ -306,7 +308,7 @@ impl Connection {
                 limit: limit.map(|l| l as i32),
             };
             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)?;
@@ -325,24 +327,26 @@ 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};
-            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),
+            use lance_namespace::models::CreateNamespaceRequest;
+            let mode_value = mode.and_then(|m| match m.to_lowercase().as_str() {
+                "create" => Some("Create".to_string()),
+                "exist_ok" => Some("ExistOk".to_string()),
+                "overwrite" => Some("Overwrite".to_string()),
                 _ => None,
             });
             let request = CreateNamespaceRequest {
+                identity: None,
+                context: None,
                 id: if namespace.is_empty() {
                     None
                 } else {
                     Some(namespace)
                 },
-                mode: mode_enum,
+                mode: mode_value,
                 properties,
             };
             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())
@@ -360,28 +364,30 @@ 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};
-            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),
+            use lance_namespace::models::DropNamespaceRequest;
+            let mode_value = mode.and_then(|m| match m.to_uppercase().as_str() {
+                "SKIP" => Some("Skip".to_string()),
+                "FAIL" => Some("Fail".to_string()),
                 _ => None,
             });
-            let behavior_enum = behavior.and_then(|b| match b.to_uppercase().as_str() {
-                "RESTRICT" => Some(drop_namespace_request::Behavior::Restrict),
-                "CASCADE" => Some(drop_namespace_request::Behavior::Cascade),
+            let behavior_value = behavior.and_then(|b| match b.to_uppercase().as_str() {
+                "RESTRICT" => Some("Restrict".to_string()),
+                "CASCADE" => Some("Cascade".to_string()),
                 _ => None,
             });
             let request = DropNamespaceRequest {
+                identity: None,
+                context: None,
                 id: if namespace.is_empty() {
                     None
                 } else {
                     Some(namespace)
                 },
-                mode: mode_enum,
-                behavior: behavior_enum,
+                mode: mode_value,
+                behavior: behavior_value,
             };
             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)?;
@@ -400,6 +406,8 @@ impl Connection {
         future_into_py(py, async move {
             use lance_namespace::models::DescribeNamespaceRequest;
             let request = DescribeNamespaceRequest {
+                identity: None,
+                context: None,
                 id: if namespace.is_empty() {
                     None
                 } else {
@@ -407,7 +415,7 @@ impl Connection {
                 },
             };
             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())
@@ -427,6 +435,8 @@ impl Connection {
         future_into_py(py, async move {
             use lance_namespace::models::ListTablesRequest;
             let request = ListTablesRequest {
+                identity: None,
+                context: None,
                 id: if namespace.is_empty() {
                     None
                 } else {
@@ -436,7 +446,7 @@ impl Connection {
                 limit: limit.map(|l| l as i32),
             };
             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)?;

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(),

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");
 

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.as_ref().to_pyarrow(py).map(|obj| obj.unbind()))
         })
     }
 

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()))
         })
     }
 

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)))

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)?;
@@ -516,7 +516,7 @@ 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| {
@@ -867,7 +867,7 @@ 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);

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

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,
@@ -134,6 +134,8 @@ impl Database for LanceNamespaceDatabase {
 
     async fn table_names(&self, request: TableNamesRequest) -> Result<Vec<String>> {
         let ns_request = ListTablesRequest {
+            identity: None,
+            context: None,
             id: Some(request.namespace),
             page_token: request.start_after,
             limit: request.limit.map(|l| l as i32),
@@ -152,8 +154,13 @@ impl Database for LanceNamespaceDatabase {
         let mut table_id = request.namespace.clone();
         table_id.push(request.name.clone());
         let describe_request = DescribeTableRequest {
+            identity: None,
+            context: None,
             id: Some(table_id.clone()),
             version: None,
+            with_table_uri: None,
+            load_detailed_metadata: None,
+            vend_credentials: None,
         };
 
         let describe_result = self.namespace.describe_table(describe_request).await;
@@ -170,6 +177,8 @@ impl Database for LanceNamespaceDatabase {
                 if describe_result.is_ok() {
                     // Drop the existing table - must succeed
                     let drop_request = DropTableRequest {
+                        identity: None,
+                        context: None,
                         id: Some(table_id.clone()),
                     };
                     self.namespace
@@ -202,22 +211,24 @@ 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 {
+            identity: None,
+            context: None,
             id: Some(table_id.clone()),
             location: None,
-            properties: if self.storage_options.is_empty() {
+            vend_credentials: if self.storage_options.is_empty() {
                 None
             } else {
-                Some(self.storage_options.clone())
+                Some(true)
             },
         };
 
         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 +292,11 @@ 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 {
+            identity: None,
+            context: None,
+            id: Some(table_id),
+        };
         self.namespace
             .drop_table(drop_request)
             .await
@@ -435,6 +450,8 @@ mod tests {
 
         // Create a child namespace first
         conn.create_namespace(CreateNamespaceRequest {
+            identity: None,
+            context: None,
             id: Some(vec!["test_ns".into()]),
             mode: None,
             properties: None,
@@ -496,6 +513,8 @@ mod tests {
 
         // Create a child namespace first
         conn.create_namespace(CreateNamespaceRequest {
+            identity: None,
+            context: None,
             id: Some(vec!["test_ns".into()]),
             mode: None,
             properties: None,
@@ -560,6 +579,8 @@ mod tests {
 
         // Create a child namespace first
         conn.create_namespace(CreateNamespaceRequest {
+            identity: None,
+            context: None,
             id: Some(vec!["test_ns".into()]),
             mode: None,
             properties: None,
@@ -644,6 +665,8 @@ mod tests {
 
         // Create a child namespace first
         conn.create_namespace(CreateNamespaceRequest {
+            identity: None,
+            context: None,
             id: Some(vec!["test_ns".into()]),
             mode: None,
             properties: None,
@@ -700,6 +723,8 @@ mod tests {
 
         // Create a child namespace first
         conn.create_namespace(CreateNamespaceRequest {
+            identity: None,
+            context: None,
             id: Some(vec!["test_ns".into()]),
             mode: None,
             properties: None,
@@ -781,6 +806,8 @@ mod tests {
 
         // Create a child namespace first
         conn.create_namespace(CreateNamespaceRequest {
+            identity: None,
+            context: None,
             id: Some(vec!["test_ns".into()]),
             mode: None,
             properties: None,
@@ -815,6 +842,8 @@ mod tests {
 
         // Create a child namespace first
         conn.create_namespace(CreateNamespaceRequest {
+            identity: None,
+            context: None,
             id: Some(vec!["test_ns".into()]),
             mode: None,
             properties: None,

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
 //!

rust/lancedb/src/remote/db.rs

@@ -1717,6 +1717,8 @@ mod tests {
             // Create a child namespace first
             let namespace = vec!["test_ns".to_string()];
             conn.create_namespace(CreateNamespaceRequest {
+                identity: None,
+                context: None,
                 id: Some(namespace.clone()),
                 mode: None,
                 properties: None,
@@ -1743,6 +1745,8 @@ mod tests {
             // List tables in the child namespace
             let list_response = conn
                 .list_tables(ListTablesRequest {
+                    identity: None,
+                    context: None,
                     id: Some(namespace.clone()),
                     page_token: None,
                     limit: None,
@@ -1755,6 +1759,8 @@ mod tests {
             let namespace_client = conn.namespace_client().await.unwrap();
             let list_response = namespace_client
                 .list_tables(ListTablesRequest {
+                    identity: None,
+                    context: None,
                     id: Some(namespace.clone()),
                     page_token: None,
                     limit: None,
@@ -1796,6 +1802,8 @@ mod tests {
             // Create a child namespace first
             let namespace = vec!["multi_table_ns".to_string()];
             conn.create_namespace(CreateNamespaceRequest {
+                identity: None,
+                context: None,
                 id: Some(namespace.clone()),
                 mode: None,
                 properties: None,
@@ -1822,6 +1830,8 @@ mod tests {
             // List tables in the child namespace
             let list_response = conn
                 .list_tables(ListTablesRequest {
+                    identity: None,
+                    context: None,
                     id: Some(namespace.clone()),
                     page_token: None,
                     limit: None,

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;
@@ -1424,7 +1424,9 @@ 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 union query plans: {}", e),
+        })?;
         // We require 1 partition in the final output
         let repartitioned = RepartitionExec::try_new(
             unioned,
@@ -2348,7 +2350,10 @@ impl NativeTable {
                 // Convert select to columns list
                 let columns = 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:
@@ -2383,6 +2388,8 @@ impl NativeTable {
                 });
 
                 Ok(NsQueryTableRequest {
+                    identity: None,
+                    context: None,
                     id: None, // Will be set in namespace_query
                     k: vq.base.limit.unwrap_or(10) as i32,
                     vector: Box::new(vector),
@@ -2421,7 +2428,10 @@ impl NativeTable {
 
                 let columns = 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"
@@ -2453,6 +2463,8 @@ impl NativeTable {
                 });
 
                 Ok(NsQueryTableRequest {
+                    identity: None,
+                    context: None,
                     id: None, // Will be set by caller
                     vector,
                     k: q.limit.unwrap_or(10) as i32,
@@ -5146,7 +5158,13 @@ mod tests {
         assert_eq!(ns_request.k, 10);
         assert_eq!(ns_request.offset, Some(5));
         assert_eq!(ns_request.filter, Some("id > 0".to_string()));
-        assert_eq!(ns_request.columns, Some(vec!["id".to_string()]));
+        assert_eq!(
+            ns_request
+                .columns
+                .as_ref()
+                .and_then(|columns| columns.column_names.clone()),
+            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());
@@ -5187,7 +5205,13 @@ mod tests {
         assert_eq!(ns_request.k, 20);
         assert_eq!(ns_request.offset, Some(5));
         assert_eq!(ns_request.filter, Some("id > 5".to_string()));
-        assert_eq!(ns_request.columns, Some(vec!["id".to_string()]));
+        assert_eq!(
+            ns_request
+                .columns
+                .as_ref()
+                .and_then(|columns| columns.column_names.clone()),
+            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

rust/lancedb/src/table/dataset.rs

@@ -101,6 +101,7 @@ impl DatasetRef {
                     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,
                 };
 
                 if should_checkout {