feat: upgrade to Lance v0.20.0 (#1908)

Upstream change log:
https://github.com/lancedb/lance/releases/tag/v0.20.0

python/src/arrow.rs

@@ -10,7 +10,7 @@ use arrow::{
 use futures::stream::StreamExt;
 use lancedb::arrow::SendableRecordBatchStream;
 use pyo3::{pyclass, pymethods, Bound, PyAny, PyObject, PyRef, PyResult, Python};
-use pyo3_asyncio_0_21::tokio::future_into_py;
+use pyo3_async_runtimes::tokio::future_into_py;
 
 use crate::error::PythonErrorExt;
 

python/src/connection.rs

@@ -9,7 +9,7 @@ use pyo3::{
     exceptions::{PyRuntimeError, PyValueError},
     pyclass, pyfunction, pymethods, Bound, FromPyObject, PyAny, PyRef, PyResult, Python,
 };
-use pyo3_asyncio_0_21::tokio::future_into_py;
+use pyo3_async_runtimes::tokio::future_into_py;
 
 use crate::{error::PythonErrorExt, table::Table};
 
@@ -58,6 +58,7 @@ impl Connection {
         self.inner.take();
     }
 
+    #[pyo3(signature = (start_after=None, limit=None))]
     pub fn table_names(
         self_: PyRef<'_, Self>,
         start_after: Option<String>,
@@ -74,6 +75,7 @@ impl Connection {
         future_into_py(self_.py(), async move { op.execute().await.infer_error() })
     }
 
+    #[pyo3(signature = (name, mode, data, storage_options=None, data_storage_version=None, enable_v2_manifest_paths=None))]
     pub fn create_table<'a>(
         self_: PyRef<'a, Self>,
         name: String,
@@ -111,6 +113,7 @@ impl Connection {
         })
     }
 
+    #[pyo3(signature = (name, mode, schema, storage_options=None, data_storage_version=None, enable_v2_manifest_paths=None))]
     pub fn create_empty_table<'a>(
         self_: PyRef<'a, Self>,
         name: String,
@@ -198,6 +201,7 @@ impl Connection {
 }
 
 #[pyfunction]
+#[pyo3(signature = (uri, api_key=None, region=None, host_override=None, read_consistency_interval=None, client_config=None, storage_options=None))]
 #[allow(clippy::too_many_arguments)]
 pub fn connect(
     py: Python,

python/src/error.rs

@@ -138,7 +138,9 @@ fn http_from_rust_error(
     status_code: Option<u16>,
 ) -> PyResult<PyErr> {
     let message = err.to_string();
-    let http_err_cls = py.import("lancedb.remote.errors")?.getattr("HttpError")?;
+    let http_err_cls = py
+        .import_bound("lancedb.remote.errors")?
+        .getattr("HttpError")?;
     let py_err = http_err_cls.call1((message, request_id, status_code))?;
 
     // Reset the traceback since it doesn't provide additional information.
@@ -149,5 +151,5 @@ fn http_from_rust_error(
         py_err.setattr(intern!(py, "__cause__"), cause_err)?;
     }
 
-    Ok(PyErr::from_value(py_err))
+    Ok(PyErr::from_value_bound(py_err))
 }

python/src/index.rs

@@ -47,6 +47,7 @@ impl Index {
 
 #[pymethods]
 impl Index {
+    #[pyo3(signature = (distance_type=None, num_partitions=None, num_sub_vectors=None, max_iterations=None, sample_rate=None))]
     #[staticmethod]
     pub fn ivf_pq(
         distance_type: Option<String>,
@@ -106,6 +107,7 @@ impl Index {
         })
     }
 
+    #[pyo3(signature = (with_position=None, base_tokenizer=None, language=None, max_token_length=None, lower_case=None, stem=None, remove_stop_words=None, ascii_folding=None))]
     #[allow(clippy::too_many_arguments)]
     #[staticmethod]
     pub fn fts(
@@ -146,6 +148,7 @@ impl Index {
         }
     }
 
+    #[pyo3(signature = (distance_type=None, num_partitions=None, num_sub_vectors=None, max_iterations=None, sample_rate=None, m=None, ef_construction=None))]
     #[staticmethod]
     pub fn hnsw_pq(
         distance_type: Option<String>,
@@ -184,6 +187,7 @@ impl Index {
         })
     }
 
+    #[pyo3(signature = (distance_type=None, num_partitions=None, max_iterations=None, sample_rate=None, m=None, ef_construction=None))]
     #[staticmethod]
     pub fn hnsw_sq(
         distance_type: Option<String>,

python/src/lib.rs

@@ -16,7 +16,11 @@ use arrow::RecordBatchStream;
 use connection::{connect, Connection};
 use env_logger::Env;
 use index::{Index, IndexConfig};
-use pyo3::{pymodule, types::PyModule, wrap_pyfunction, PyResult, Python};
+use pyo3::{
+    pymodule,
+    types::{PyModule, PyModuleMethods},
+    wrap_pyfunction, Bound, PyResult, Python,
+};
 use query::{Query, VectorQuery};
 use table::Table;
 
@@ -29,7 +33,7 @@ pub mod table;
 pub mod util;
 
 #[pymodule]
-pub fn _lancedb(_py: Python, m: &PyModule) -> PyResult<()> {
+pub fn _lancedb(_py: Python, m: &Bound<'_, PyModule>) -> PyResult<()> {
     let env = Env::new()
         .filter_or("LANCEDB_LOG", "warn")
         .write_style("LANCEDB_LOG_STYLE");

python/src/query.rs

@@ -29,7 +29,7 @@ use pyo3::PyAny;
 use pyo3::PyRef;
 use pyo3::PyResult;
 use pyo3::{pyclass, PyErr};
-use pyo3_asyncio_0_21::tokio::future_into_py;
+use pyo3_async_runtimes::tokio::future_into_py;
 
 use crate::arrow::RecordBatchStream;
 use crate::error::PythonErrorExt;
@@ -105,6 +105,7 @@ impl Query {
         Ok(())
     }
 
+    #[pyo3(signature = (max_batch_length=None))]
     pub fn execute(
         self_: PyRef<'_, Self>,
         max_batch_length: Option<u32>,
@@ -203,6 +204,7 @@ impl VectorQuery {
         self.inner = self.inner.clone().bypass_vector_index()
     }
 
+    #[pyo3(signature = (max_batch_length=None))]
     pub fn execute(
         self_: PyRef<'_, Self>,
         max_batch_length: Option<u32>,

python/src/table.rs

@@ -12,10 +12,10 @@ use lancedb::table::{
 use pyo3::{
     exceptions::{PyRuntimeError, PyValueError},
     pyclass, pymethods,
-    types::{IntoPyDict, PyAnyMethods, PyDict, PyDictMethods, PyString},
+    types::{IntoPyDict, PyAnyMethods, PyDict, PyDictMethods},
     Bound, FromPyObject, PyAny, PyRef, PyResult, Python, ToPyObject,
 };
-use pyo3_asyncio_0_21::tokio::future_into_py;
+use pyo3_async_runtimes::tokio::future_into_py;
 
 use crate::{
     error::PythonErrorExt,
@@ -141,9 +141,10 @@ impl Table {
         })
     }
 
+    #[pyo3(signature = (updates, r#where=None))]
     pub fn update<'a>(
         self_: PyRef<'a, Self>,
-        updates: &PyDict,
+        updates: &Bound<'_, PyDict>,
         r#where: Option<String>,
     ) -> PyResult<Bound<'a, PyAny>> {
         let mut op = self_.inner_ref()?.update();
@@ -151,10 +152,8 @@ impl Table {
             op = op.only_if(only_if);
         }
         for (column_name, value) in updates.into_iter() {
-            let column_name: &PyString = column_name.downcast()?;
-            let column_name = column_name.to_str()?.to_string();
-            let value: &PyString = value.downcast()?;
-            let value = value.to_str()?.to_string();
+            let column_name: String = column_name.extract()?;
+            let value: String = value.extract()?;
             op = op.column(column_name, value);
         }
         future_into_py(self_.py(), async move {
@@ -163,6 +162,7 @@ impl Table {
         })
     }
 
+    #[pyo3(signature = (filter=None))]
     pub fn count_rows(
         self_: PyRef<'_, Self>,
         filter: Option<String>,
@@ -173,6 +173,7 @@ impl Table {
         })
     }
 
+    #[pyo3(signature = (column, index=None, replace=None))]
     pub fn create_index<'a>(
         self_: PyRef<'a, Self>,
         column: String,
@@ -267,7 +268,8 @@ impl Table {
                         .unwrap();
 
                         let tup: Vec<(&String, &String)> = v.metadata.iter().collect();
-                        dict.set_item("metadata", tup.into_py_dict(py)).unwrap();
+                        dict.set_item("metadata", tup.into_py_dict_bound(py))
+                            .unwrap();
                         dict.to_object(py)
                     })
                     .collect::<Vec<_>>()
@@ -303,6 +305,7 @@ impl Table {
         Query::new(self.inner_ref().unwrap().query())
     }
 
+    #[pyo3(signature = (cleanup_since_ms=None, delete_unverified=None))]
     pub fn optimize(
         self_: PyRef<'_, Self>,
         cleanup_since_ms: Option<u64>,