chore: update lance dependency to v2.0.0-rc.4

Cargo.toml

@@ -15,37 +15,37 @@ categories = ["database-implementations"]
 rust-version = "1.88.0"
 
 [workspace.dependencies]
-lance = { "version" = "=1.0.4", default-features = false, "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=2.0.0-rc.4", default-features = false, "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=2.0.0-rc.4", "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=2.0.0-rc.4", "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=2.0.0-rc.4", "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=1.0.4", default-features = false, "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=2.0.0-rc.4", default-features = false, "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=2.0.0-rc.4", "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=2.0.0-rc.4", "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=2.0.0-rc.4", "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=1.0.4", default-features = false, "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=2.0.0-rc.4", default-features = false, "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=2.0.0-rc.4", "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=2.0.0-rc.4", "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=2.0.0-rc.4", "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=2.0.0-rc.4", "tag" = "v2.0.0-rc.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=2.0.0-rc.4", "tag" = "v2.0.0-rc.4", "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 = { version = "57.2", optional = false }
-arrow-array = "56.2"
+arrow-array = "57.2"
-arrow-data = "56.2"
+arrow-data = "57.2"
-arrow-ipc = "56.2"
+arrow-ipc = "57.2"
-arrow-ord = "56.2"
+arrow-ord = "57.2"
-arrow-schema = "56.2"
+arrow-schema = "57.2"
-arrow-select = "56.2"
+arrow-select = "57.2"
-arrow-cast = "56.2"
+arrow-cast = "57.2"
 async-trait = "0"
-datafusion = { version = "50.1", default-features = false }
+datafusion = { version = "51.0", default-features = false }
-datafusion-catalog = "50.1"
+datafusion-catalog = "51.0"
-datafusion-common = { version = "50.1", default-features = false }
+datafusion-common = { version = "51.0", default-features = false }
-datafusion-execution = "50.1"
+datafusion-execution = "51.0"
-datafusion-expr = "50.1"
+datafusion-expr = "51.0"
-datafusion-physical-plan = "50.1"
+datafusion-physical-plan = "51.0"
 env_logger = "0.11"
 half = { "version" = "2.6.0", default-features = false, features = [
     "num-traits",

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 = { version = "0.26", features = ["extension-module", "abi3-py39"] }
-pyo3-async-runtimes = { version = "0.25", features = [
+pyo3-async-runtimes = { version = "0.26", features = [
     "attributes",
     "tokio-runtime",
 ] }
@@ -32,7 +32,7 @@ snafu.workspace = true
 tokio = { version = "1.40", features = ["sync"] }
 
 [build-dependencies]
-pyo3-build-config = { version = "0.25", features = [
+pyo3-build-config = { version = "0.26", features = [
     "extension-module",
     "abi3-py39",
 ] }

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,
+    exceptions::PyStopAsyncIteration, pyclass, pymethods, Bound, Py, PyAny, PyRef, PyResult, Python,
-    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> {
+    pub fn schema(&self, py: Python) -> PyResult<Py<PyAny>> {
-        (*self.schema).clone().into_pyarrow(py)
+        (*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>> {
@@ -307,7 +307,7 @@ impl Connection {
                 ..Default::default()
             };
             let response = inner.list_namespaces(request).await.infer_error()?;
-            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
+            Python::attach(|py| -> PyResult<Py<PyDict>> {
                 let dict = PyDict::new(py);
                 dict.set_item("namespaces", response.namespaces)?;
                 dict.set_item("page_token", response.page_token)?;
@@ -345,7 +345,7 @@ impl Connection {
                 ..Default::default()
             };
             let response = inner.create_namespace(request).await.infer_error()?;
-            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
+            Python::attach(|py| -> PyResult<Py<PyDict>> {
                 let dict = PyDict::new(py);
                 dict.set_item("properties", response.properties)?;
                 Ok(dict.unbind())
@@ -386,7 +386,7 @@ impl Connection {
                 ..Default::default()
             };
             let response = inner.drop_namespace(request).await.infer_error()?;
-            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
+            Python::attach(|py| -> PyResult<Py<PyDict>> {
                 let dict = PyDict::new(py);
                 dict.set_item("properties", response.properties)?;
                 dict.set_item("transaction_id", response.transaction_id)?;
@@ -413,7 +413,7 @@ impl Connection {
                 ..Default::default()
             };
             let response = inner.describe_namespace(request).await.infer_error()?;
-            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
+            Python::attach(|py| -> PyResult<Py<PyDict>> {
                 let dict = PyDict::new(py);
                 dict.set_item("properties", response.properties)?;
                 Ok(dict.unbind())
@@ -443,7 +443,7 @@ impl Connection {
                 ..Default::default()
             };
             let response = inner.list_tables(request).await.infer_error()?;
-            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
+            Python::attach(|py| -> PyResult<Py<PyDict>> {
                 let dict = PyDict::new(py);
                 dict.set_item("tables", response.tables)?;
                 dict.set_item("page_token", response.page_token)?;

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.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> {
+    pub fn new(obj: Py<PyAny>) -> PyResult<Self> {
-        Python::with_gil(|py| {
+        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)?;
@@ -521,7 +521,7 @@ impl Table {
         let inner = self_.inner_ref()?.clone();
         future_into_py(self_.py(), async move {
             let versions = inner.list_versions().await.infer_error()?;
-            let versions_as_dict = Python::with_gil(|py| {
+            let versions_as_dict = Python::attach(|py| {
                 versions
                     .iter()
                     .map(|v| {
@@ -872,7 +872,7 @@ impl Tags {
             let tags = inner.tags().await.infer_error()?;
             let res = tags.list().await.infer_error()?;
 
-            Python::with_gil(|py| {
+            Python::attach(|py| {
                 let py_dict = PyDict::new(py);
                 for (key, contents) in res {
                     let value_dict = PyDict::new(py);

rust/lancedb/src/dataloader/permutation/builder.rs

@@ -1,14 +1,22 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
-use std::{collections::HashMap, sync::Arc};
+use std::{
+    collections::HashMap,
+    sync::{Arc, Mutex},
+};
 
 use datafusion::prelude::{SessionConfig, SessionContext};
+use datafusion_catalog::streaming::StreamingTable;
+use datafusion_common::DataFusionError;
 use datafusion_execution::{disk_manager::DiskManagerBuilder, runtime_env::RuntimeEnvBuilder};
 use datafusion_expr::col;
+use datafusion_physical_plan::{
+    stream::RecordBatchStreamAdapter, streaming::PartitionStream,
+    SendableRecordBatchStream as DataFusionRecordBatchStream,
+};
 use futures::TryStreamExt;
 use lance_core::ROW_ID;
-use lance_datafusion::exec::SessionContextExt;
 
 use crate::{
     arrow::{SendableRecordBatchStream, SendableRecordBatchStreamExt, SimpleRecordBatchStream},
@@ -29,6 +37,49 @@ pub const SPLIT_NAMES_CONFIG_KEY: &str = "split_names";
 
 pub const DEFAULT_MEMORY_LIMIT: usize = 100 * 1024 * 1024;
 
+struct OneShotPartitionStream {
+    schema: arrow_schema::SchemaRef,
+    stream: Mutex<Option<DataFusionRecordBatchStream>>,
+}
+
+impl OneShotPartitionStream {
+    fn new(schema: arrow_schema::SchemaRef, stream: DataFusionRecordBatchStream) -> Self {
+        Self {
+            schema,
+            stream: Mutex::new(Some(stream)),
+        }
+    }
+}
+
+impl PartitionStream for OneShotPartitionStream {
+    fn schema(&self) -> &arrow_schema::SchemaRef {
+        &self.schema
+    }
+
+    fn execute(&self, _ctx: Arc<datafusion_execution::TaskContext>) -> DataFusionRecordBatchStream {
+        self.stream
+            .lock()
+            .ok()
+            .and_then(|mut stream| stream.take())
+            .unwrap_or_else(|| {
+                Box::pin(RecordBatchStreamAdapter::new(
+                    Arc::clone(&self.schema),
+                    futures::stream::empty::<
+                        std::result::Result<arrow_array::RecordBatch, DataFusionError>,
+                    >(),
+                ))
+            })
+    }
+}
+
+impl std::fmt::Debug for OneShotPartitionStream {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        f.debug_struct("OneShotPartitionStream")
+            .field("schema", &self.schema)
+            .finish()
+    }
+}
+
 /// Where to store the permutation table
 #[derive(Debug, Clone, Default)]
 enum PermutationDestination {
@@ -190,12 +241,17 @@ impl PermutationBuilder {
                 .build_arc()
                 .unwrap(),
         );
-        let df = ctx
+        let df_stream = data.into_df_stream();
-            .read_one_shot(data.into_df_stream())
+        let schema = df_stream.schema();
-            .map_err(|e| Error::Other {
+        let partition = Arc::new(OneShotPartitionStream::new(schema.clone(), df_stream));
-                message: format!("Failed to setup sort by split id: {}", e),
+        let table = StreamingTable::try_new(schema, vec![partition]).map_err(|e| Error::Other {
-                source: Some(e.into()),
+            message: format!("Failed to create streaming table: {}", e),
-            })?;
+            source: Some(e.into()),
+        })?;
+        let df = ctx.read_table(Arc::new(table)).map_err(|e| Error::Other {
+            message: format!("Failed to setup sort by split id: {}", e),
+            source: Some(e.into()),
+        })?;
         let df_stream = df
             .sort_by(vec![col(SPLIT_ID_COLUMN)])
             .map_err(|e| Error::Other {

rust/lancedb/src/table.rs

@@ -1425,7 +1425,10 @@ impl Table {
             })
             .collect::<Vec<_>>();
 
-        let unioned = Arc::new(UnionExec::new(projected_plans));
+        let unioned = UnionExec::try_new(projected_plans).map_err(|e| Error::Other {
+            message: format!("Failed to union query plans: {}", e),
+            source: Some(e.into()),
+        })?;
         // We require 1 partition in the final output
         let repartitioned = RepartitionExec::try_new(
             unioned,

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 {