Merge main into gatekeeper/fix-4260-1

Preserve the sliced child validity repair against the upstream Lance v14.0.0-beta.7 pin.

python/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.40.0-beta.13"
+version = "0.41.0-beta.0"
 publish = false
 edition.workspace = true
 description = "Python bindings for LanceDB"

python/pyproject.toml

@@ -63,7 +63,7 @@ tests = [
     "polars>=0.19, <=1.32.3",
     "pyarrow<25",
     "pyarrow-stubs>=16.0",
-    "pylance==9.0.0",
+    "pylance==14.0.0b6",
     "requests>=2.31.0",
     "datafusion>=54,<55",
     "opentelemetry-sdk>=1.30.0",

python/python/lancedb/_lancedb.pyi

@@ -155,9 +155,13 @@ class Connection(object):
     async def get_function(
         self, name: str, version: str, namespace_path: Optional[List[str]] = None
     ) -> str: ...
-    async def list_functions(
-        self, namespace_path: Optional[List[str]] = None
-    ) -> List[str]: ...
+    def list_functions(
+        self,
+        namespace_path: Optional[List[str]] = None,
+        *,
+        page_token: Optional[str] = None,
+        page_limit: Optional[int] = None,
+    ) -> FunctionListing: ...
     async def drop_function(
         self, name: str, version: str, namespace_path: Optional[List[str]] = None
     ) -> bool: ...
@@ -170,9 +174,13 @@ class Connection(object):
     async def alter_secret(
         self, name: str, value: str, namespace_path: Optional[List[str]] = None
     ) -> None: ...
-    async def list_secrets(
-        self, namespace_path: Optional[List[str]] = None
-    ) -> List[str]: ...
+    def list_secrets(
+        self,
+        namespace_path: Optional[List[str]] = None,
+        *,
+        page_token: Optional[str] = None,
+        page_limit: Optional[int] = None,
+    ) -> NameListing: ...
     async def drop_secret(
         self, name: str, namespace_path: Optional[List[str]] = None
     ) -> None: ...
@@ -191,10 +199,16 @@ class Connection(object):
     async def drop_view_async(
         self, name: str, namespace_path: Optional[List[str]] = None
     ) -> Job: ...
-    async def list_views(
-        self, namespace_path: Optional[List[str]] = None
-    ) -> List[str]: ...
-    async def list_jobs(self) -> List[JobInfo]: ...
+    def list_views(
+        self,
+        namespace_path: Optional[List[str]] = None,
+        *,
+        page_token: Optional[str] = None,
+        page_limit: Optional[int] = None,
+    ) -> NameListing: ...
+    def list_jobs(
+        self, *, page_token: Optional[str] = None, page_limit: Optional[int] = None
+    ) -> JobListing: ...
     async def cancel_job(self, job_id: str) -> bool: ...
     async def pause_job(self, job_id: str) -> str: ...
     async def resume_job(self, job_id: str) -> str: ...
@@ -265,7 +279,9 @@ class Connection(object):
         limit: Optional[int] = None,
         with_no_data: bool = False,
     ) -> Job: ...
-    async def list_materialized_views(self) -> List[str]: ...
+    def list_materialized_views(
+        self, *, page_token: Optional[str] = None, page_limit: Optional[int] = None
+    ) -> NameListing: ...
     async def drop_materialized_view(
         self, name: str, namespace_path: Optional[List[str]] = None
     ) -> None: ...
@@ -961,3 +977,21 @@ async def connect_catalog(
     read_consistency_interval: Optional[float] = None,
     oauth_config: Optional[Any] = None,
 ) -> Catalog: ...
+
+class NameListing:
+    def num_page_results(self) -> int: ...
+    def page_token(self) -> Optional[str]: ...
+    def __aiter__(self) -> NameListing: ...
+    async def __anext__(self) -> str: ...
+
+class FunctionListing:
+    def num_page_results(self) -> int: ...
+    def page_token(self) -> Optional[str]: ...
+    def __aiter__(self) -> FunctionListing: ...
+    async def __anext__(self) -> str: ...
+
+class JobListing:
+    def num_page_results(self) -> int: ...
+    def page_token(self) -> Optional[str]: ...
+    def __aiter__(self) -> JobListing: ...
+    async def __anext__(self) -> JobInfo: ...

python/python/lancedb/db.py

@@ -31,6 +31,7 @@ if sys.version_info >= (3, 12):
 else:
     from overrides import EnforceOverrides, override  # type: ignore
 
+from lancedb.listing import AsyncListing, Listing
 from lancedb.embeddings.registry import EmbeddingFunctionRegistry
 
 from lancedb.common import data_to_reader, sanitize_uri, validate_schema
@@ -668,11 +669,16 @@ class DBConnection(EnforceOverrides):
             "materialized views are not supported on this connection type"
         )
 
-    def list_materialized_views(self) -> List[str]:
+    def list_materialized_views(
+        self, *, page_token: Optional[str] = None, page_limit: Optional[int] = None
+    ) -> Listing[str]:
         """The names of the materialized views in this database.
 
-        Found by reading every table's schema, so this costs an open per
-        table.
+        Local listings inspect table schemas one page at a time.
+
+        Returns a lazy iterator. ``page_limit`` limits each request, not the total;
+        ``page_token`` resumes from a saved token. Requests and errors occur during
+        iteration. See [pagination state][lancedb.listing.AsyncListing].
         """
         raise NotImplementedError(
             "materialized views are not supported on this connection type"
@@ -885,8 +891,12 @@ class DBConnection(EnforceOverrides):
         )
 
     def list_functions(
-        self, *, namespace_path: Optional[List[str]] = None
-    ) -> List[FunctionVersion]:
+        self,
+        *,
+        namespace_path: Optional[List[str]] = None,
+        page_token: Optional[str] = None,
+        page_limit: Optional[int] = None,
+    ) -> Listing[FunctionVersion]:
         """List every published immutable Function version in a namespace.
 
         Functions in child namespaces are not included. Results are ordered by
@@ -900,6 +910,10 @@ class DBConnection(EnforceOverrides):
         ```python
         [(function.name, function.version) for function in db.list_functions()]
         ```
+
+        Returns a lazy iterator. ``page_limit`` limits each request, not the total;
+        ``page_token`` resumes from a saved token. Requests and errors occur during
+        iteration. See [pagination state][lancedb.listing.AsyncListing].
         """
         raise NotImplementedError(
             "Function catalog operations are not supported for this connection type"
@@ -971,11 +985,21 @@ class DBConnection(EnforceOverrides):
             "Secret operations are not supported for this connection type"
         )
 
-    def list_secrets(self, *, namespace_path: Optional[List[str]] = None) -> List[str]:
+    def list_secrets(
+        self,
+        *,
+        namespace_path: Optional[List[str]] = None,
+        page_token: Optional[str] = None,
+        page_limit: Optional[int] = None,
+    ) -> Listing[str]:
         """The names of every Secret in this database.
 
         Names only. No method returns a stored credential, by construction
         rather than by policy. Local connections raise ``NotImplementedError``.
+
+        Returns a lazy iterator. ``page_limit`` limits each request, not the total;
+        ``page_token`` resumes from a saved token. Requests and errors occur during
+        iteration. See [pagination state][lancedb.listing.AsyncListing].
         """
         raise NotImplementedError(
             "Secret operations are not supported for this connection type"
@@ -1073,12 +1097,22 @@ class DBConnection(EnforceOverrides):
             "View operations are not supported for this connection type"
         )
 
-    def list_views(self, *, namespace_path: Optional[List[str]] = None) -> List[str]:
+    def list_views(
+        self,
+        *,
+        namespace_path: Optional[List[str]] = None,
+        page_token: Optional[str] = None,
+        page_limit: Optional[int] = None,
+    ) -> Listing[str]:
         """The names of the views in one namespace.
 
         Names only; a definition comes from
         [describe_view][lancedb.db.DBConnection.describe_view]. Local
         connections raise ``NotImplementedError``.
+
+        Returns a lazy iterator. ``page_limit`` limits each request, not the total;
+        ``page_token`` resumes from a saved token. Requests and errors occur during
+        iteration. See [pagination state][lancedb.listing.AsyncListing].
         """
         raise NotImplementedError(
             "View operations are not supported for this connection type"
@@ -1097,8 +1131,15 @@ class DBConnection(EnforceOverrides):
         """
         raise NotImplementedError("open_job is not supported for this connection type")
 
-    def list_jobs(self) -> List[JobInfo]:
-        """List server-side jobs across the database's tables."""
+    def list_jobs(
+        self, *, page_token: Optional[str] = None, page_limit: Optional[int] = None
+    ) -> Listing[JobInfo]:
+        """List server-side jobs across the database's tables.
+
+        Returns a lazy iterator. ``page_limit`` limits each request, not the total;
+        ``page_token`` resumes from a saved token. Requests and errors occur during
+        iteration. See [pagination state][lancedb.listing.AsyncListing].
+        """
         raise NotImplementedError("list_jobs is not supported for this connection type")
 
     def cancel_job(self, job_id: str) -> bool:
@@ -1699,9 +1740,20 @@ class LanceDBConnection(DBConnection):
         return view
 
     @override
-    def list_materialized_views(self) -> List[str]:
-        """The names of the materialized views in this database."""
-        return LOOP.run(self._conn.list_materialized_views())
+    def list_materialized_views(
+        self, *, page_token: Optional[str] = None, page_limit: Optional[int] = None
+    ) -> Listing[str]:
+        """The names of the materialized views in this database.
+
+        Returns a lazy iterator. ``page_limit`` limits each request, not the total;
+        ``page_token`` resumes from a saved token. Requests and errors occur during
+        iteration. See [pagination state][lancedb.listing.AsyncListing].
+        """
+        return Listing(
+            self._conn.list_materialized_views(
+                page_token=page_token, page_limit=page_limit
+            )
+        )
 
     @override
     def drop_materialized_view(
@@ -1896,9 +1948,25 @@ class LanceDBConnection(DBConnection):
 
     @override
     def list_functions(
-        self, *, namespace_path: Optional[List[str]] = None
-    ) -> List[FunctionVersion]:
-        return LOOP.run(self._conn.list_functions(namespace_path=namespace_path))
+        self,
+        *,
+        namespace_path: Optional[List[str]] = None,
+        page_token: Optional[str] = None,
+        page_limit: Optional[int] = None,
+    ) -> Listing[FunctionVersion]:
+        """List functions.
+
+        Returns a lazy iterator. ``page_limit`` limits each request, not the total;
+        ``page_token`` resumes from a saved token. Requests and errors occur during
+        iteration. See [pagination state][lancedb.listing.AsyncListing].
+        """
+        return Listing(
+            self._conn.list_functions(
+                namespace_path=namespace_path,
+                page_token=page_token,
+                page_limit=page_limit,
+            )
+        )
 
     @override
     def drop_function(
@@ -1942,8 +2010,26 @@ class LanceDBConnection(DBConnection):
         LOOP.run(self._conn.alter_secret(name, value, namespace_path=namespace_path))
 
     @override
-    def list_secrets(self, *, namespace_path: Optional[List[str]] = None) -> List[str]:
-        return LOOP.run(self._conn.list_secrets(namespace_path=namespace_path))
+    def list_secrets(
+        self,
+        *,
+        namespace_path: Optional[List[str]] = None,
+        page_token: Optional[str] = None,
+        page_limit: Optional[int] = None,
+    ) -> Listing[str]:
+        """List secrets.
+
+        Returns a lazy iterator. ``page_limit`` limits each request, not the total;
+        ``page_token`` resumes from a saved token. Requests and errors occur during
+        iteration. See [pagination state][lancedb.listing.AsyncListing].
+        """
+        return Listing(
+            self._conn.list_secrets(
+                namespace_path=namespace_path,
+                page_token=page_token,
+                page_limit=page_limit,
+            )
+        )
 
     @override
     def drop_secret(
@@ -1986,13 +2072,40 @@ class LanceDBConnection(DBConnection):
         )
 
     @override
-    def list_views(self, *, namespace_path: Optional[List[str]] = None) -> List[str]:
-        return LOOP.run(self._conn.list_views(namespace_path=namespace_path))
+    def list_views(
+        self,
+        *,
+        namespace_path: Optional[List[str]] = None,
+        page_token: Optional[str] = None,
+        page_limit: Optional[int] = None,
+    ) -> Listing[str]:
+        """List views.
+
+        Returns a lazy iterator. ``page_limit`` limits each request, not the total;
+        ``page_token`` resumes from a saved token. Requests and errors occur during
+        iteration. See [pagination state][lancedb.listing.AsyncListing].
+        """
+        return Listing(
+            self._conn.list_views(
+                namespace_path=namespace_path,
+                page_token=page_token,
+                page_limit=page_limit,
+            )
+        )
 
     @override
-    def list_jobs(self) -> List[JobInfo]:
-        """List server-side jobs across the database's tables."""
-        return LOOP.run(self._conn.list_jobs())
+    def list_jobs(
+        self, *, page_token: Optional[str] = None, page_limit: Optional[int] = None
+    ) -> Listing[JobInfo]:
+        """List server-side jobs across the database's tables.
+
+        Returns a lazy iterator. ``page_limit`` limits each request, not the total;
+        ``page_token`` resumes from a saved token. Requests and errors occur during
+        iteration. See [pagination state][lancedb.listing.AsyncListing].
+        """
+        return Listing(
+            self._conn.list_jobs(page_token=page_token, page_limit=page_limit)
+        )
 
     @override
     def cancel_job(self, job_id: str) -> bool:
@@ -2680,13 +2793,22 @@ class AsyncConnection(object):
         await view.definition()
         return view
 
-    async def list_materialized_views(self) -> List[str]:
+    def list_materialized_views(
+        self, *, page_token: Optional[str] = None, page_limit: Optional[int] = None
+    ) -> AsyncListing[str]:
         """The names of the materialized views in this database.
 
-        Found by reading every table's schema, so this costs an open per
-        table.
+        Local listings inspect table schemas one page at a time.
+
+        Returns a lazy iterator. ``page_limit`` limits each request, not the total;
+        ``page_token`` resumes from a saved token. Requests and errors occur during
+        iteration. See [pagination state][lancedb.listing.AsyncListing].
         """
-        return await self._inner.list_materialized_views()
+        return AsyncListing(
+            self._inner.list_materialized_views(
+                page_token=page_token, page_limit=page_limit
+            )
+        )
 
     async def drop_materialized_view(
         self,
@@ -2908,19 +3030,31 @@ class AsyncConnection(object):
             await self._inner.get_function(name, version, namespace_path)
         )
 
-    async def list_functions(
-        self, *, namespace_path: Optional[List[str]] = None
-    ) -> List[FunctionVersion]:
+    def list_functions(
+        self,
+        *,
+        namespace_path: Optional[List[str]] = None,
+        page_token: Optional[str] = None,
+        page_limit: Optional[int] = None,
+    ) -> AsyncListing[FunctionVersion]:
         """List every published immutable Function version in a namespace.
 
         Functions in child namespaces are not included. Results are ordered by
         Function name then version. Local connections raise
         ``NotImplementedError``.
+
+        Returns a lazy iterator. ``page_limit`` limits each request, not the total;
+        ``page_token`` resumes from a saved token. Requests and errors occur during
+        iteration. See [pagination state][lancedb.listing.AsyncListing].
         """
-        return [
-            FunctionVersion.from_json(value)
-            for value in await self._inner.list_functions(namespace_path)
-        ]
+        return AsyncListing(
+            self._inner.list_functions(
+                namespace_path=namespace_path,
+                page_token=page_token,
+                page_limit=page_limit,
+            ),
+            FunctionVersion.from_json,
+        )
 
     async def drop_function(
         self,
@@ -2978,12 +3112,25 @@ class AsyncConnection(object):
             list(validate_namespace_path(namespace_path)),
         )
 
-    async def list_secrets(
-        self, *, namespace_path: Optional[List[str]] = None
-    ) -> List[str]:
-        """The names of every Secret in this database. Names only."""
-        return await self._inner.list_secrets(
-            list(validate_namespace_path(namespace_path))
+    def list_secrets(
+        self,
+        *,
+        namespace_path: Optional[List[str]] = None,
+        page_token: Optional[str] = None,
+        page_limit: Optional[int] = None,
+    ) -> AsyncListing[str]:
+        """The names of every Secret in this database. Names only.
+
+        Returns a lazy iterator. ``page_limit`` limits each request, not the total;
+        ``page_token`` resumes from a saved token. Requests and errors occur during
+        iteration. See [pagination state][lancedb.listing.AsyncListing].
+        """
+        return AsyncListing(
+            self._inner.list_secrets(
+                namespace_path=namespace_path,
+                page_token=page_token,
+                page_limit=page_limit,
+            )
         )
 
     async def drop_secret(
@@ -3055,15 +3202,39 @@ class AsyncConnection(object):
             await self._inner.drop_view_async(name, namespace_path=namespace_path)
         )
 
-    async def list_views(
-        self, *, namespace_path: Optional[List[str]] = None
-    ) -> List[str]:
-        """The names of the views in one namespace."""
-        return await self._inner.list_views(list(namespace_path or []))
+    def list_views(
+        self,
+        *,
+        namespace_path: Optional[List[str]] = None,
+        page_token: Optional[str] = None,
+        page_limit: Optional[int] = None,
+    ) -> AsyncListing[str]:
+        """The names of the views in one namespace.
 
-    async def list_jobs(self) -> List[JobInfo]:
-        """List server-side jobs across the database's tables."""
-        return await self._inner.list_jobs()
+        Returns a lazy iterator. ``page_limit`` limits each request, not the total;
+        ``page_token`` resumes from a saved token. Requests and errors occur during
+        iteration. See [pagination state][lancedb.listing.AsyncListing].
+        """
+        return AsyncListing(
+            self._inner.list_views(
+                namespace_path=namespace_path,
+                page_token=page_token,
+                page_limit=page_limit,
+            )
+        )
+
+    def list_jobs(
+        self, *, page_token: Optional[str] = None, page_limit: Optional[int] = None
+    ) -> AsyncListing[JobInfo]:
+        """List server-side jobs across the database's tables.
+
+        Returns a lazy iterator. ``page_limit`` limits each request, not the total;
+        ``page_token`` resumes from a saved token. Requests and errors occur during
+        iteration. See [pagination state][lancedb.listing.AsyncListing].
+        """
+        return AsyncListing(
+            self._inner.list_jobs(page_token=page_token, page_limit=page_limit)
+        )
 
     async def cancel_job(self, job_id: str) -> bool:
         """Request cancellation of a server-side job by id.

python/python/lancedb/listing.py

@@ -0,0 +1,85 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+"""Lazy, resumable resource listings."""
+
+from __future__ import annotations
+
+from typing import Any, AsyncIterator, Callable, Generic, Iterator, Optional, TypeVar
+
+from .background_loop import LOOP
+
+T = TypeVar("T")
+
+
+class AsyncListing(AsyncIterator[T], Generic[T]):
+    """A lazy async iterator with inspectable pagination state.
+
+    Returned by connection resource-listing methods. For example::
+
+        async for name in connection.list_views(page_limit=20):
+            print(name)
+
+    Requests happen during iteration; request errors terminate the iterator.
+    """
+
+    def __init__(self, inner: Any, convert: Callable[[Any], T] = lambda value: value):
+        self._inner = inner
+        self._convert = convert
+
+    def __aiter__(self) -> AsyncListing[T]:
+        return self
+
+    async def __anext__(self) -> T:
+        return self._convert(await self._inner.__anext__())
+
+    def num_page_results(self) -> int:
+        """Return the number of cached items available without another request."""
+        return self._inner.num_page_results()
+
+    def page_token(self) -> Optional[str]:
+        """Return the token for the next request.
+
+        Initially this is the supplied starting token (``None`` starts at the
+        beginning). After fetching the final page it is ``None``, even if items
+        remain cached. Drain the cache before saving a token to avoid skipping
+        items when resuming. A failed request terminates iteration and retains
+        its token for retrying with a new iterator.
+        """
+        return self._inner.page_token()
+
+
+class Listing(Iterator[T], Generic[T]):
+    """A lazy synchronous iterator with inspectable pagination state.
+
+    For example::
+
+        for name in connection.list_views(page_limit=20):
+            print(name)
+
+    Use ``list(connection.list_views())`` to collect all results.
+    """
+
+    def __init__(self, inner: AsyncListing[T]):
+        self._inner = inner
+
+    def __iter__(self) -> Listing[T]:
+        return self
+
+    def __next__(self) -> T:
+        try:
+            return LOOP.run(self._inner.__anext__())
+        except StopAsyncIteration:
+            raise StopIteration from None
+
+    def num_page_results(self) -> int:
+        """Return the number of cached items available without another request."""
+        return self._inner.num_page_results()
+
+    def page_token(self) -> Optional[str]:
+        """Return the next request's token.
+
+        See [AsyncListing.page_token][lancedb.listing.AsyncListing.page_token]
+        for initial, cached, final-page, and error behavior.
+        """
+        return self._inner.page_token()

python/python/lancedb/namespace.py

@@ -11,7 +11,7 @@ through a namespace abstraction.
 from __future__ import annotations
 
 import sys
-from typing import TYPE_CHECKING, Any, Dict, Iterable, List, Optional, Union
+from typing import Any, Dict, Iterable, List, Optional, Union
 from uuid import UUID
 
 if sys.version_info >= (3, 12):
@@ -19,8 +19,7 @@ if sys.version_info >= (3, 12):
 else:
     from overrides import override
 
-if TYPE_CHECKING:
-    from lancedb.query import Query
+from lancedb.query import Query
 
 from datetime import timedelta
 import pyarrow as pa
@@ -52,6 +51,7 @@ from lancedb.background_loop import LOOP
 from lancedb.arrow import AsyncRecordBatchReader
 from lancedb.db import AsyncConnection, DBConnection
 from lancedb.job import AsyncJob, Job
+from lancedb.listing import AsyncListing, Listing
 from lancedb.sql import AsyncQuery as AsyncSqlQuery
 from lancedb.sql import QueryDescription
 from lance_namespace import (
@@ -698,9 +698,20 @@ class LanceNamespaceDBConnection(DBConnection):
         return view
 
     @override
-    def list_materialized_views(self) -> List[str]:
-        """The names of the materialized views in the root namespace."""
-        return LOOP.run(self._inner.list_materialized_views())
+    def list_materialized_views(
+        self, *, page_token: Optional[str] = None, page_limit: Optional[int] = None
+    ) -> Listing[str]:
+        """The names of the materialized views in the root namespace.
+
+        Returns a lazy iterator. ``page_limit`` limits each request, not the total;
+        ``page_token`` resumes from a saved token. Requests and errors occur during
+        iteration. See [pagination state][lancedb.listing.AsyncListing].
+        """
+        return Listing(
+            self._inner.list_materialized_views(
+                page_token=page_token, page_limit=page_limit
+            )
+        )
 
     @override
     def drop_materialized_view(
@@ -1297,9 +1308,20 @@ class AsyncLanceNamespaceDBConnection:
         await view.definition()
         return view
 
-    async def list_materialized_views(self) -> List[str]:
-        """The names of the materialized views in the root namespace."""
-        return await self._inner.list_materialized_views()
+    def list_materialized_views(
+        self, *, page_token: Optional[str] = None, page_limit: Optional[int] = None
+    ) -> AsyncListing[str]:
+        """The names of the materialized views in the root namespace.
+
+        Returns a lazy iterator. ``page_limit`` limits each request, not the total;
+        ``page_token`` resumes from a saved token. Requests and errors occur during
+        iteration. See [pagination state][lancedb.listing.AsyncListing].
+        """
+        return AsyncListing(
+            self._inner.list_materialized_views(
+                page_token=page_token, page_limit=page_limit
+            )
+        )
 
     async def drop_materialized_view(
         self, name: str, namespace_path: Optional[List[str]] = None

python/python/lancedb/remote/db.py

@@ -2,6 +2,8 @@
 # SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
 
+from __future__ import annotations
+
 from dataclasses import replace
 from datetime import timedelta
 import json
@@ -34,6 +36,7 @@ from lancedb.remote import ClientConfig, RetryConfig, TimeoutConfig, TlsConfig
 import pyarrow as pa
 
 from ..common import DATA
+from lancedb.listing import Listing
 from ..db import DBConnection, LOOP
 from ..functions import FunctionVersion, UdfDefinition
 from ..job import AsyncJob, Job
@@ -608,6 +611,9 @@ class RemoteDBConnection(DBConnection):
             One of "error", "drop", "fill".
         fill_value: float
             The value to use when filling vectors. Only used if on_bad_vectors="fill".
+        embedding_functions: list of EmbeddingFunctionConfig, optional
+            The embedding functions to store in the table schema and use to
+            generate vectors when creating the table or adding data.
 
         Returns
         -------
@@ -682,12 +688,6 @@ class RemoteDBConnection(DBConnection):
         if namespace_path is None:
             namespace_path = []
         validate_table_name(name)
-        if embedding_functions is not None:
-            logging.warning(
-                "embedding_functions is not yet supported on LanceDB Cloud."
-                "Please vote https://github.com/lancedb/lancedb/issues/626 "
-                "for this feature."
-            )
 
         from .table import RemoteTable
 
@@ -700,6 +700,7 @@ class RemoteDBConnection(DBConnection):
                 schema=schema,
                 on_bad_vectors=on_bad_vectors,
                 fill_value=fill_value,
+                embedding_functions=embedding_functions,
             )
         )
         return RemoteTable(
@@ -771,8 +772,20 @@ class RemoteDBConnection(DBConnection):
         return view
 
     @override
-    def list_materialized_views(self) -> List[str]:
-        return LOOP.run(self._conn.list_materialized_views())
+    def list_materialized_views(
+        self, *, page_token: Optional[str] = None, page_limit: Optional[int] = None
+    ) -> Listing[str]:
+        """List materialized views.
+
+        Returns a lazy iterator. ``page_limit`` limits each request, not the total;
+        ``page_token`` resumes from a saved token. Requests and errors occur during
+        iteration. See [pagination state][lancedb.listing.AsyncListing].
+        """
+        return Listing(
+            self._conn.list_materialized_views(
+                page_token=page_token, page_limit=page_limit
+            )
+        )
 
     @override
     def drop_materialized_view(
@@ -887,9 +900,25 @@ class RemoteDBConnection(DBConnection):
 
     @override
     def list_functions(
-        self, *, namespace_path: Optional[List[str]] = None
-    ) -> List[FunctionVersion]:
-        return LOOP.run(self._conn.list_functions(namespace_path=namespace_path))
+        self,
+        *,
+        namespace_path: Optional[List[str]] = None,
+        page_token: Optional[str] = None,
+        page_limit: Optional[int] = None,
+    ) -> Listing[FunctionVersion]:
+        """List functions.
+
+        Returns a lazy iterator. ``page_limit`` limits each request, not the total;
+        ``page_token`` resumes from a saved token. Requests and errors occur during
+        iteration. See [pagination state][lancedb.listing.AsyncListing].
+        """
+        return Listing(
+            self._conn.list_functions(
+                namespace_path=namespace_path,
+                page_token=page_token,
+                page_limit=page_limit,
+            )
+        )
 
     @override
     def drop_function(
@@ -939,8 +968,26 @@ class RemoteDBConnection(DBConnection):
         return LOOP.run(self._conn.describe_secret(name, namespace_path=namespace_path))
 
     @override
-    def list_secrets(self, *, namespace_path: Optional[List[str]] = None) -> List[str]:
-        return LOOP.run(self._conn.list_secrets(namespace_path=namespace_path))
+    def list_secrets(
+        self,
+        *,
+        namespace_path: Optional[List[str]] = None,
+        page_token: Optional[str] = None,
+        page_limit: Optional[int] = None,
+    ) -> Listing[str]:
+        """List secrets.
+
+        Returns a lazy iterator. ``page_limit`` limits each request, not the total;
+        ``page_token`` resumes from a saved token. Requests and errors occur during
+        iteration. See [pagination state][lancedb.listing.AsyncListing].
+        """
+        return Listing(
+            self._conn.list_secrets(
+                namespace_path=namespace_path,
+                page_token=page_token,
+                page_limit=page_limit,
+            )
+        )
 
     @override
     def drop_secret(
@@ -976,13 +1023,40 @@ class RemoteDBConnection(DBConnection):
         return Job(job)
 
     @override
-    def list_views(self, *, namespace_path: Optional[List[str]] = None) -> List[str]:
-        return LOOP.run(self._conn.list_views(namespace_path=namespace_path))
+    def list_views(
+        self,
+        *,
+        namespace_path: Optional[List[str]] = None,
+        page_token: Optional[str] = None,
+        page_limit: Optional[int] = None,
+    ) -> Listing[str]:
+        """List views.
+
+        Returns a lazy iterator. ``page_limit`` limits each request, not the total;
+        ``page_token`` resumes from a saved token. Requests and errors occur during
+        iteration. See [pagination state][lancedb.listing.AsyncListing].
+        """
+        return Listing(
+            self._conn.list_views(
+                namespace_path=namespace_path,
+                page_token=page_token,
+                page_limit=page_limit,
+            )
+        )
 
     @override
-    def list_jobs(self) -> List["JobInfo"]:
-        """List server-side jobs across the database's tables."""
-        return LOOP.run(self._conn.list_jobs())
+    def list_jobs(
+        self, *, page_token: Optional[str] = None, page_limit: Optional[int] = None
+    ) -> Listing[JobInfo]:
+        """List server-side jobs across the database's tables.
+
+        Returns a lazy iterator. ``page_limit`` limits each request, not the total;
+        ``page_token`` resumes from a saved token. Requests and errors occur during
+        iteration. See [pagination state][lancedb.listing.AsyncListing].
+        """
+        return Listing(
+            self._conn.list_jobs(page_token=page_token, page_limit=page_limit)
+        )
 
     @override
     def cancel_job(self, job_id: str) -> bool:

python/python/lancedb/remote/table.py

@@ -63,6 +63,7 @@ from lancedb.table import _normalize_progress
 from ..query import (
     AnalyzePlanDistributedMetrics,
     DocumentGranularity,
+    FullTextQuery,
     LanceQueryBuilder,
     LanceTakeQueryBuilder,
     LanceVectorQueryBuilder,
@@ -77,6 +78,7 @@ from ..table import (
     Tags,
 )
 from ..types import BaseTokenizerType
+from ..util import infer_vector_column_name
 
 
 class RemoteTable(Table):
@@ -734,6 +736,12 @@ class RemoteTable(Table):
             - If the table has multiple vector columns then the *vector_column_name*
             needs to be specified. Otherwise, an error is raised.
 
+        query_type: str, default "auto"
+            The type of search: "auto", "vector", "fts", or "hybrid".
+            With "auto", a string query uses the embedding function for the
+            inferred or specified vector column if available, otherwise it uses
+            full-text search.
+
         fast_search: bool, optional
             Skip a flat search of unindexed data. This may improve
             search performance but search results will not include unindexed data.
@@ -753,6 +761,21 @@ class RemoteTable(Table):
             - and also the "_distance" column which is the distance between the query
             vector and the returned vector.
         """
+        if isinstance(query, FullTextQuery):
+            query_type = "fts"
+        elif (
+            query_type == "auto"
+            and isinstance(query, str)
+            and not self.embedding_functions
+        ):
+            query_type = "fts"
+        vector_column_name = infer_vector_column_name(
+            schema=self.schema,
+            query_type=query_type,
+            query=query,
+            vector_column_name=vector_column_name,
+        )
+
         return LanceQueryBuilder.create(
             self,
             query,

python/python/lancedb/table.py

@@ -5445,11 +5445,16 @@ class AsyncTable:
     async def get_lsm_write_spec(self) -> Optional["LsmWriteSpec"]:
         """Read the LsmWriteSpec currently installed on this table.
 
-        Returns ``None`` when the MemWAL LSM write path is not enabled (no
-        spec has been set, or it was removed with `unset_lsm_write_spec`).
-        The returned spec mirrors what was passed to `set_lsm_write_spec`,
-        except that ``maintained_indexes`` always reports the concrete list
-        resolved when the spec was set — ``None`` never round-trips.
+        Returns ``None`` when the LSM write path is not enabled at all — no
+        spec has been set, or one was removed with `unset_lsm_write_spec`.
+        That is a different answer from a spec whose ``maintained_indexes``
+        is ``None``, which is an installed spec selecting indexes
+        automatically.
+
+        The spec read back is the one that was installed, selection
+        included: ``None`` maintains every supported index the table has now
+        or gains later, ``[]`` maintains none, and a non-empty list maintains
+        exactly those. All three round-trip.
         """
         return await self._inner.get_lsm_write_spec()
 
@@ -7324,6 +7329,13 @@ class TableStatistics:
         and manifests.
     num_rows: int
         The total number of rows in the table.
+    num_deleted_rows: Optional[int]
+        The total number of rows marked as deleted across all fragments of the
+        table. These rows are not counted in ``num_rows``, but still occupy space
+        on disk until the table is compacted, so a large value here indicates
+        that the table should be optimized. Fragments in which every row was
+        deleted are dropped outright, so their rows are not counted here.
+        ``None`` when the backend does not report deletion counts.
     num_indices: int
         The total number of indices in the table.
     fragment_stats: FragmentStatistics
@@ -7332,6 +7344,7 @@ class TableStatistics:
 
     total_bytes: int
     num_rows: int
+    num_deleted_rows: Optional[int]
     num_indices: int
     fragment_stats: FragmentStatistics
 

python/python/tests/test_first_class_function_slice2.py

@@ -1499,7 +1499,7 @@ def test_local_function_catalog_operations_are_not_supported(tmp_path):
     with pytest.raises(NotImplementedError, match=message):
         db.get_function("normalize_score", version=FUNCTION_VERSION)
     with pytest.raises(NotImplementedError, match=message):
-        db.list_functions()
+        list(db.list_functions())
     with pytest.raises(NotImplementedError, match=message):
         db.drop_function("normalize_score", version=FUNCTION_VERSION)
 
@@ -1720,7 +1720,7 @@ def test_remote_secret_verbs_round_trip():
         )
         assert db.create_secret("openai-prod", "sk-live-0001") is None
         assert db.alter_secret("openai-prod", "sk-live-0002") is None
-        assert db.list_secrets() == ["openai-prod", "hf-prod"]
+        assert list(db.list_secrets()) == ["openai-prod", "hf-prod"]
         assert db.drop_secret("openai-prod") is None
 
     routes = [path for path, _ in state["requests"]]
@@ -1781,7 +1781,7 @@ def test_remote_list_functions_paginates_and_returns_typed_versions():
         )
         created = db.create_function(normalize_score)
         state["requests"].clear()
-        functions = db.list_functions()
+        functions = list(db.list_functions())
 
     assert functions == [created]
     assert state["requests"] == [
@@ -1805,7 +1805,7 @@ async def test_async_remote_list_functions_returns_typed_versions():
         registration = await db.create_function_async(normalize_score)
         created = await registration.wait()
         state["requests"].clear()
-        functions = await db.list_functions()
+        functions = [item async for item in db.list_functions()]
 
     assert functions == [created]
     assert [path for path, _ in state["requests"]] == [
@@ -1878,7 +1878,7 @@ def test_remote_function_verbs_address_a_namespace_in_the_path():
         assert reopened(value=lancedb.col("score")).function.namespace_path == tuple(
             namespace
         )
-        db.list_functions(namespace_path=namespace)
+        list(db.list_functions(namespace_path=namespace))
         assert (
             db.drop_function(
                 "normalize_score", version=FUNCTION_VERSION, namespace_path=namespace
@@ -1918,7 +1918,7 @@ async def test_async_remote_function_verbs_address_a_namespace_in_the_path():
         await db.get_function(
             "normalize_score", version=FUNCTION_VERSION, namespace_path=namespace
         )
-        await db.list_functions(namespace_path=namespace)
+        [item async for item in db.list_functions(namespace_path=namespace)]
         assert (
             await db.drop_function(
                 "normalize_score", version=FUNCTION_VERSION, namespace_path=namespace
@@ -1947,6 +1947,6 @@ def test_a_function_namespace_path_must_be_a_list_of_segments():
             client_config={"retry_config": {"retries": 0}},
         )
         with pytest.raises(TypeError):
-            db.list_functions(namespace_path="analytics")
+            list(db.list_functions(namespace_path="analytics"))
 
     assert state["requests"] == []

python/python/tests/test_fts.py

@@ -1267,7 +1267,10 @@ def test_fts_query_to_json():
     json_str = multi_match.to_json()
     expected = (
         '{"multi_match":{"query":"python","columns":["tags","title"],'
-        '"boost":[1.0,1.0]}}'
+        '"boost":[1.0,1.0],"match_queries":[{"column":"tags","terms":"python",'
+        '"boost":1.0,"fuzziness":0,"max_expansions":50,"operator":"Or",'
+        '"prefix_length":0},{"column":"title","terms":"python","boost":1.0,'
+        '"fuzziness":0,"max_expansions":50,"operator":"Or","prefix_length":0}]}}'
     )
     assert json_str == expected
 

python/python/tests/test_listing.py

@@ -0,0 +1,194 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+import asyncio
+from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
+import json
+from pathlib import Path
+from threading import Thread
+from urllib.parse import parse_qs, urlsplit
+
+import lancedb
+from lancedb.remote.errors import HttpError
+import pytest
+
+
+@pytest.fixture
+def listing_server():
+    requests, responses = [], []
+
+    class Handler(BaseHTTPRequestHandler):
+        def handle_request(self):
+            body = self.rfile.read(int(self.headers.get("Content-Length", "0")))
+            requests.append((self.command, self.path, json.loads(body) if body else {}))
+            status, response = responses.pop(0)
+            self.send_response(status)
+            self.send_header("Content-Type", "application/json")
+            self.end_headers()
+            self.wfile.write(json.dumps(response).encode())
+
+        do_GET = handle_request
+        do_POST = handle_request
+
+    with ThreadingHTTPServer(("127.0.0.1", 0), Handler) as server:
+        thread = Thread(target=server.serve_forever, daemon=True)
+        thread.start()
+        try:
+            yield f"http://127.0.0.1:{server.server_port}", requests, responses
+        finally:
+            server.shutdown()
+            thread.join()
+
+
+def response_page(kind, names, token):
+    if kind == "secrets":
+        items = [{"name": name} for name in names]
+    elif kind == "jobs":
+        items = [
+            {
+                "job_id": name,
+                "table": "t",
+                "job_type": "create_index",
+                "state": "in_progress",
+                "created_at_millis": 1,
+            }
+            for name in names
+        ]
+    elif kind == "functions":
+        fixture = (
+            Path(__file__).resolve().parents[3]
+            / "rust/lancedb/tests/fixtures/first_class_functions/v1"
+            / "remote_function_version.canonical.json"
+        )
+        definition = json.loads(fixture.read_text())
+        items = [
+            {"name": "embed", "version": "1", "definition": definition} for _ in names
+        ]
+    else:
+        items = names
+    key = "views" if kind == "materialized_views" else kind
+    return {key: items, "page_token": token}
+
+
+async def connection(endpoint, asynchronous):
+    kwargs = dict(
+        api_key="fake",
+        host_override=endpoint,
+        client_config={"retry_config": {"retries": 0}},
+    )
+    if asynchronous:
+        return await lancedb.connect_async("db://dev", **kwargs)
+    return lancedb.connect("db://dev", **kwargs)
+
+
+async def advance(items, asynchronous):
+    return await items.__anext__() if asynchronous else next(items)
+
+
+KINDS = ["secrets", "views", "jobs", "functions", "materialized_views"]
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize("kind", KINDS)
+@pytest.mark.parametrize("asynchronous", [False, True])
+async def test_listing_lazy_pages_and_resume(listing_server, kind, asynchronous):
+    endpoint, requests, responses = listing_server
+    responses.extend(
+        (200, response_page(kind, names, token))
+        for names, token in [(["a", "b"], "empty"), ([], "last"), (["c", "d"], "")]
+    )
+    db = await connection(endpoint, asynchronous)
+    method = getattr(db, "list_" + kind)
+    kwargs = (
+        {} if kind in ("jobs", "materialized_views") else {"namespace_path": ["team"]}
+    )
+    items = method(page_token="start/token", page_limit=2, **kwargs)
+    assert requests == []
+    assert items.page_token() == "start/token"
+    assert items.num_page_results() == 0
+    first = await advance(items, asynchronous)
+    if kind == "functions":
+        assert first.name == "embed"
+        assert first.version == "1"
+    elif kind == "jobs":
+        assert first.job_id == "a"
+        assert first.state == "running"
+    else:
+        assert first == "a"
+    assert items.num_page_results() == 1
+    assert items.page_token() == "empty"
+    await advance(items, asynchronous)
+    assert items.num_page_results() == 0
+    assert len(requests) == 1
+    resumed = method(page_token=items.page_token(), page_limit=2, **kwargs)
+    await advance(resumed, asynchronous)
+    assert len(requests) == 3
+    assert resumed.page_token() is None
+    assert resumed.num_page_results() == 1
+    remaining = [item async for item in resumed] if asynchronous else list(resumed)
+    assert len(remaining) == 1
+    assert resumed.num_page_results() == 0
+    assert ([item async for item in resumed] if asynchronous else list(resumed)) == []
+    for (verb, url, body), token in zip(requests, ["start/token", "empty", "last"]):
+        path = urlsplit(url)
+        if kind == "jobs":
+            assert verb == "POST"
+            assert path.path == "/v1/jobs/list"
+            assert body == {"page_token": token, "limit": 2}
+        else:
+            namespace = "$" if kind == "materialized_views" else "team"
+            resource = kind.removesuffix("s")
+            assert path.path == f"/v1/namespace/{namespace}/{resource}/list"
+            expected = {"page_token": [token], "limit": ["2"]}
+            if kind == "functions":
+                expected["include_definition"] = ["true"]
+            assert parse_qs(path.query) == expected
+    assert responses == []
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize("kind", KINDS)
+@pytest.mark.parametrize("asynchronous", [False, True])
+async def test_listing_error_retains_token(listing_server, kind, asynchronous):
+    endpoint, requests, responses = listing_server
+    responses.extend([(401, {}), (200, response_page(kind, ["a"], None))])
+    db = await connection(endpoint, asynchronous)
+    method = getattr(db, "list_" + kind)
+    items = method(page_token="retry")
+    with pytest.raises(HttpError):
+        await advance(items, asynchronous)
+    assert items.page_token() == "retry"
+    assert items.num_page_results() == 0
+    assert ([item async for item in items] if asynchronous else list(items)) == []
+    assert len(requests) == 1
+    resumed = method(page_token=items.page_token())
+    assert len([item async for item in resumed] if asynchronous else list(resumed)) == 1
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize("kind", KINDS)
+async def test_listing_serializes_concurrent_advances(listing_server, kind):
+    endpoint, requests, responses = listing_server
+    responses.append((200, response_page(kind, ["a", "b"], None)))
+    db = await connection(endpoint, True)
+    items = getattr(db, "list_" + kind)()
+    results = await asyncio.gather(
+        items.__anext__(), items.__anext__(), items.__anext__(), return_exceptions=True
+    )
+    assert (
+        len([result for result in results if isinstance(result, StopAsyncIteration)])
+        == 1
+    )
+    assert len(requests) == 1
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize("kind", KINDS)
+@pytest.mark.parametrize("page_limit", [0, 2**32 - 1])
+async def test_listing_invalid_limit_does_not_fetch(listing_server, kind, page_limit):
+    endpoint, requests, _ = listing_server
+    db = await connection(endpoint, True)
+    items = getattr(db, "list_" + kind)(page_limit=page_limit)
+    with pytest.raises(ValueError, match="limit"):
+        await items.__anext__()
+    assert requests == []

python/python/tests/test_materialized_views.py

@@ -93,7 +93,7 @@ def test_remote_list_uses_namespace_route():
             host_override=host,
             client_config={"retry_config": {"retries": 0}},
         )
-        assert db.list_materialized_views() == ["daily_sales"]
+        assert list(db.list_materialized_views()) == ["daily_sales"]
     assert requests == ["/v1/namespace/$/materialized_view/list"]
 
 
@@ -190,7 +190,7 @@ def test_create_and_refresh_jobs(tmp_path):
     drop_job = db.drop_materialized_view_async("adults")
     assert drop_job.id is None
     assert drop_job.wait() is None
-    assert "adults" not in db.list_materialized_views()
+    assert "adults" not in list(db.list_materialized_views())
 
 
 def test_definition_round_trips(tmp_path):
@@ -246,18 +246,43 @@ def test_legacy_storage_source_update_rebuilds(tmp_path):
     assert sorted(row["age"] for row in rows) == [8, 36]
 
 
+def test_direct_writes_to_a_view_are_refused(tmp_path):
+    db = make_db(tmp_path)
+    view = db.create_materialized_view("copy", "people")
+    table = view.table
+    row = [{"name": "eve", "age": 1}]
+    refused = pytest.raises(NotImplementedError, match="is a materialized view")
+
+    with refused:
+        table.add(row)
+    with refused:
+        table.update(where="name = 'kid'", values={"age": 8})
+    with refused:
+        table.delete("age < 18")
+    with refused:
+        table.merge_insert("name").when_not_matched_insert_all().execute(row)
+    with refused:
+        table.add_columns({"older": "age + 1"})
+    with refused:
+        table.drop_columns(["age"])
+    assert table.count_rows() == 3
+
+    db.open_table("people").add(row)
+    assert view.refresh().rows_written == 4
+
+
 def test_list_and_not_a_view(tmp_path):
     db = make_db(tmp_path)
     db.create_materialized_view("adults", "people", where="age >= 18")
 
-    assert db.list_materialized_views() == ["adults"]
+    assert list(db.list_materialized_views()) == ["adults"]
     with pytest.raises(ValueError, match="not a materialized view"):
         db.open_materialized_view("people")
     with pytest.raises(ValueError, match="not a materialized view"):
         db.drop_materialized_view("people")
 
     db.drop_materialized_view("adults")
-    assert db.list_materialized_views() == []
+    assert list(db.list_materialized_views()) == []
 
 
 def test_invalid_expression_fails_at_create(tmp_path):
@@ -285,7 +310,7 @@ async def test_async_create_refresh_and_open(tmp_path):
     reopened = await db.open_materialized_view("shouts")
     definition = await reopened.definition()
     assert definition.query == "SELECT upper(name) AS shout FROM people"
-    assert await db.list_materialized_views() == ["shouts"]
+    assert [item async for item in db.list_materialized_views()] == ["shouts"]
 
 
 @pytest.mark.asyncio
@@ -309,7 +334,7 @@ async def test_async_create_and_refresh_jobs(tmp_path):
     drop_job = await db.drop_materialized_view_async("adults")
     assert drop_job.id is None
     assert await drop_job.wait() is None
-    assert "adults" not in await db.list_materialized_views()
+    assert "adults" not in [item async for item in db.list_materialized_views()]
 
 
 @pytest.mark.asyncio
@@ -399,7 +424,7 @@ def test_namespace_connection_materialized_views(tmp_path):
     view = db.create_materialized_view("adults", "people", where="age >= 18")
     view.refresh()
     assert view.table.count_rows() == 1
-    assert db.list_materialized_views() == ["adults"]
+    assert list(db.list_materialized_views()) == ["adults"]
 
     reopened = db.open_materialized_view("adults")
     assert reopened.definition.query.startswith("SELECT name, age FROM ")
@@ -415,7 +440,7 @@ def test_namespace_connection_materialized_views(tmp_path):
 
     assert db.drop_materialized_view_async("job_view").wait() is None
     db.drop_materialized_view("adults")
-    assert db.list_materialized_views() == []
+    assert list(db.list_materialized_views()) == []
 
 
 @pytest.mark.asyncio
@@ -434,7 +459,7 @@ async def test_async_namespace_connection_materialized_views(tmp_path):
     view = await db.create_materialized_view("adults", "people", where="age >= 18")
     await view.refresh()
     assert await view.table.count_rows() == 1
-    assert await db.list_materialized_views() == ["adults"]
+    assert [item async for item in db.list_materialized_views()] == ["adults"]
 
     reopened = await db.open_materialized_view("adults")
     assert (await reopened.definition()).query.startswith("SELECT name, age FROM ")
@@ -460,7 +485,7 @@ async def test_async_namespace_connection_materialized_views(tmp_path):
     drop_job = await db.drop_materialized_view_async("job_view")
     assert await drop_job.wait() is None
     await db.drop_materialized_view("adults")
-    assert await db.list_materialized_views() == []
+    assert [item async for item in db.list_materialized_views()] == []
 
 
 def test_stored_queries_and_legacy_layouts_are_read():
@@ -509,3 +534,19 @@ def test_stored_queries_and_legacy_layouts_are_read():
     ):
         with pytest.raises(NotImplementedError, match="cannot refresh"):
             read(newer)
+
+
+def test_local_materialized_view_listing_pages_and_resume(tmp_path):
+    db = make_db(tmp_path)
+    db.create_materialized_view("a_view", "people", with_no_data=True)
+    db.create_materialized_view("z_view", "people", with_no_data=True)
+    db.create_table("ordinary", [{"id": 1}])
+    names = db.list_materialized_views(page_limit=1)
+    assert names.num_page_results() == 0
+    first = next(names)
+    assert names.num_page_results() == 0
+    assert names.page_token() is not None
+    resumed = db.list_materialized_views(page_token=names.page_token(), page_limit=1)
+    assert sorted([first, *resumed]) == ["a_view", "z_view"]
+    assert resumed.page_token() is None
+    assert list(resumed) == []

python/python/tests/test_namespace.py

@@ -10,6 +10,7 @@ import pytest
 import pyarrow as pa
 import lancedb
 from lance_namespace.errors import NamespaceNotEmptyError, TableNotFoundError
+from lancedb.listing import AsyncListing, Listing
 from lancedb.namespace import _MAX_QUERY_K
 from lancedb.table import AsyncTable, LanceTable
 
@@ -104,6 +105,18 @@ class TestNamespaceConnection:
         assert isinstance(db, lancedb.LanceNamespaceDBConnection)
         assert len(list(db.table_names())) == 0
 
+    def test_list_materialized_views(self):
+        db = lancedb.connect_namespace("dir", {"root": self.temp_dir})
+        db.create_table("source", [{"id": 1}])
+        db.create_materialized_view("view", "source", with_no_data=True)
+
+        names = db.list_materialized_views(page_limit=1)
+        assert isinstance(names, Listing)
+        assert names.num_page_results() == 0
+        assert list(names) == ["view"]
+        assert names.num_page_results() == 0
+        assert names.page_token() is None
+
     def test_sync_builtin_namespace_uses_rust_without_python_client(self, monkeypatch):
         """Built-in sync namespace connections should not construct or call the
         Python namespace client for normal namespace/table management."""
@@ -605,6 +618,18 @@ class TestAsyncNamespaceConnection:
         table_names = await db.table_names()
         assert len(list(table_names)) == 0
 
+    async def test_list_materialized_views(self):
+        db = lancedb.connect_namespace_async("dir", {"root": self.temp_dir})
+        await db.create_table("source", [{"id": 1}])
+        await db.create_materialized_view("view", "source", with_no_data=True)
+
+        names = db.list_materialized_views(page_limit=1)
+        assert isinstance(names, AsyncListing)
+        assert names.num_page_results() == 0
+        assert [name async for name in names] == ["view"]
+        assert names.num_page_results() == 0
+        assert names.page_token() is None
+
     async def test_async_builtin_namespace_uses_rust_without_python_client(
         self, monkeypatch
     ):

python/python/tests/test_remote_db.py

@@ -17,8 +17,9 @@ from packaging.version import Version
 
 import lancedb
 import numpy as np
-from lancedb.conftest import MockTextEmbeddingFunction
-from lancedb.query import AsyncQuery, ColumnOrdering
+from lancedb.conftest import MockNonNormTextEmbeddingFunction, MockTextEmbeddingFunction
+from lancedb.embeddings import EmbeddingFunctionConfig, EmbeddingFunctionRegistry
+from lancedb.query import AsyncQuery, ColumnOrdering, LanceVectorQueryBuilder
 from lancedb.remote import ClientConfig
 from lancedb.remote.errors import HttpError, RetryError
 import pytest
@@ -596,6 +597,106 @@ def test_remote_permutation_is_picklable():
         ]
 
 
+@pytest.mark.parametrize("with_schema", [True, False])
+def test_create_table_embedding_functions(with_schema):
+    func = MockNonNormTextEmbeddingFunction.create()
+    config = EmbeddingFunctionConfig(
+        source_column="text", vector_column="vector", function=func
+    )
+    schema = pa.schema(
+        [pa.field("text", pa.string()), pa.field("vector", pa.list_(pa.float32(), 10))]
+    )
+    received = {}
+
+    def handler(request):
+        if request.path == "/v1/table/test/describe/":
+            # Echo the metadata actually sent by create_table, as the server does.
+            metadata = received["create"].schema.metadata or {}
+            send_json(
+                request,
+                {
+                    "version": 1,
+                    "schema": {
+                        "fields": [
+                            {
+                                "name": "text",
+                                "type": {"type": "string"},
+                                "nullable": True,
+                            },
+                            {
+                                "name": "vector",
+                                "type": {
+                                    "type": "fixed_size_list",
+                                    "fields": [
+                                        {
+                                            "name": "item",
+                                            "type": {"type": "float"},
+                                            "nullable": True,
+                                        }
+                                    ],
+                                    "length": 10,
+                                },
+                                "nullable": True,
+                            },
+                        ],
+                        "metadata": {
+                            k.decode(): v.decode() for k, v in metadata.items()
+                        },
+                    },
+                },
+            )
+        elif request.path in (
+            "/v1/table/test/create/?mode=create",
+            "/v1/table/test/insert/",
+        ):
+            if request.headers.get("Transfer-Encoding") == "chunked":
+                body = bytearray()
+                while True:
+                    size = int(request.rfile.readline(), 16)
+                    if size == 0:
+                        request.rfile.readline()
+                        break
+                    body.extend(request.rfile.read(size))
+                    request.rfile.read(2)
+            else:
+                body = request.rfile.read(int(request.headers["Content-Length"]))
+            operation = "create" if "/create/" in request.path else "insert"
+            received[operation] = pa.ipc.open_stream(body).read_all()
+            send_json(request, {})
+        else:
+            request.send_response(404)
+            request.end_headers()
+
+    with mock_lancedb_connection(handler) as db:
+        table = db.create_table(
+            "test",
+            schema=schema if with_schema else None,
+            data=None if with_schema else [{"text": "hello world"}],
+            embedding_functions=[config],
+        )
+        metadata = pa.schema(
+            [],
+            metadata=EmbeddingFunctionRegistry.get_instance().get_table_metadata(
+                [config]
+            ),
+        ).metadata
+        assert received["create"].schema.metadata == metadata
+        assert table.schema.metadata == metadata
+        assert table.schema.field("vector").type == pa.list_(pa.float32(), 10)
+        assert table.embedding_functions["vector"].source_column == "text"
+        if with_schema:
+            assert received["create"].num_rows == 0
+        else:
+            assert received["create"]["vector"].to_pylist() == [
+                func.compute_source_embeddings(["hello world"])[0].tolist()
+            ]
+
+        table.add([{"text": "goodbye world"}])
+        assert received["insert"]["vector"].to_pylist() == [
+            func.compute_source_embeddings(["goodbye world"])[0].tolist()
+        ]
+
+
 def test_create_table_exist_ok():
     def handler(request):
         if request.path == "/v1/table/test/create/?mode=exist_ok":
@@ -1373,7 +1474,9 @@ def test_stats():
         table = db.create_table("test", [{"id": 1}])
         res = table.stats()
         print(f"{res=}")
-        assert res == stats
+        # The server does not report num_deleted_rows, and that unsupported
+        # state is preserved as None.
+        assert res == {**stats, "num_deleted_rows": None}
 
 
 @contextlib.contextmanager
@@ -1502,14 +1605,51 @@ def test_checkpoint_lsm_sync():
 
 
 @contextlib.contextmanager
-def query_test_table(query_handler, *, server_version=Version("0.1.0")):
+def query_test_table(
+    query_handler,
+    *,
+    server_version=Version("0.1.0"),
+    vector_columns=None,
+    embedding_functions=None,
+):
+    if vector_columns is None:
+        vector_columns = {"vector": 3}
+    schema = {
+        "fields": [
+            {"name": "text", "type": {"type": "string"}, "nullable": False},
+            *[
+                {
+                    "name": name,
+                    "type": {
+                        "type": "fixed_size_list",
+                        "fields": [
+                            {
+                                "name": "item",
+                                "type": {"type": "float"},
+                                "nullable": True,
+                            }
+                        ],
+                        "length": dim,
+                    },
+                    "nullable": False,
+                }
+                for name, dim in vector_columns.items()
+            ],
+        ]
+    }
+    if embedding_functions:
+        metadata = EmbeddingFunctionRegistry.get_instance().get_table_metadata(
+            embedding_functions
+        )
+        schema["metadata"] = {key: value.decode() for key, value in metadata.items()}
+
     def handler(request):
         if request.path == "/v1/table/test/describe/":
             request.send_response(200)
             request.send_header("Content-Type", "application/json")
             request.send_header("phalanx-version", str(server_version))
             request.end_headers()
-            request.wfile.write(b'{"version": 1, "schema": {"fields": []}}')
+            request.wfile.write(json.dumps({"version": 1, "schema": schema}).encode())
         elif request.path == "/v1/table/test/query/":
             content_len = int(request.headers.get("Content-Length"))
             body = request.rfile.read(content_len)
@@ -1560,6 +1700,7 @@ def test_query_sync_minimal():
             "upper_bound": None,
             "ef": None,
             "vector": [1.0, 2.0, 3.0],
+            "vector_column": "vector",
             "nprobes": 20,
             "minimum_nprobes": 20,
             "maximum_nprobes": 20,
@@ -1574,7 +1715,84 @@ def test_query_sync_minimal():
         assert data == expected
 
 
-def test_query_sync_empty_query():
+@pytest.mark.parametrize("query_type", ["auto", "vector", "hybrid"])
+@pytest.mark.parametrize("vector_column_name", [None, "embedding"])
+def test_query_sync_text_embedding(query_type, vector_column_name):
+    embedding_func = MockTextEmbeddingFunction.create()
+    config = EmbeddingFunctionConfig(
+        source_column="text", vector_column="embedding", function=embedding_func
+    )
+    query = "quick brown fox"
+    expected_vector = embedding_func.compute_query_embeddings(query)[0]
+    queries = []
+
+    def handler(body):
+        queries.append(body)
+        if "full_text_query" in body:
+            assert query_type == "hybrid"
+            assert body["full_text_query"]["query"] == query
+            return pa.table({"id": [1], "_rowid": [1], "_score": [1.0]})
+        assert body["vector_column"] == "embedding"
+        assert body["vector"] == pytest.approx(expected_vector)
+        return pa.table({"id": [1], "_rowid": [1], "_distance": [0.0]})
+
+    with query_test_table(
+        handler,
+        vector_columns={
+            "embedding": embedding_func.ndims(),
+            **({"other": embedding_func.ndims()} if vector_column_name else {}),
+        },
+        embedding_functions=[config],
+    ) as table:
+        assert list(table.embedding_functions) == ["embedding"]
+        builder = table.search(
+            query, query_type=query_type, vector_column_name=vector_column_name
+        )
+        if query_type != "hybrid":
+            assert isinstance(builder, LanceVectorQueryBuilder)
+        results = builder.to_list()
+        assert results[0]["id"] == 1
+        if query_type != "hybrid":
+            assert results[0]["_distance"] == 0.0
+    assert len(queries) == (2 if query_type == "hybrid" else 1)
+
+
+@pytest.mark.parametrize("query_type", ["auto", "vector", "hybrid"])
+def test_query_sync_ambiguous_vector_columns(query_type):
+    config = EmbeddingFunctionConfig(
+        source_column="text",
+        vector_column="v1",
+        function=MockTextEmbeddingFunction.create(),
+    )
+    queries = []
+
+    def handler(body):
+        queries.append(body)
+        return pa.table({"id": [1]})
+
+    with query_test_table(
+        handler,
+        vector_columns={"v1": 10, "v2": 10},
+        embedding_functions=[config],
+    ) as table:
+        with pytest.raises(ValueError, match=r"Candidates: \['v1', 'v2'\]"):
+            table.search("puppy", query_type=query_type).to_list()
+    assert queries == []
+
+
+@pytest.mark.parametrize("vector_column, dim", [("v1", 3), ("v2", 4)])
+def test_query_sync_infers_vector_column_by_dimension(vector_column, dim):
+    def handler(body):
+        assert body["vector_column"] == vector_column
+        assert body["vector"] == [1.0] * dim
+        return pa.table({"id": [1]})
+
+    with query_test_table(handler, vector_columns={"v1": 3, "v2": 4}) as table:
+        assert table.search([1.0] * dim).to_list() == [{"id": 1}]
+
+
+@pytest.mark.parametrize("vector_columns", [{}, {"v1": 3, "v2": 3}])
+def test_query_sync_empty_query(vector_columns):
     def handler(body):
         assert body == {
             "k": 10,
@@ -1587,7 +1805,7 @@ def test_query_sync_empty_query():
 
         return pa.table({"id": [1, 2, 3]})
 
-    with query_test_table(handler) as table:
+    with query_test_table(handler, vector_columns=vector_columns) as table:
         data = table.search(None).where("true").select(["id"]).limit(10).to_list()
         expected = [{"id": 1}, {"id": 2}, {"id": 3}]
         assert data == expected
@@ -1837,7 +2055,9 @@ def test_query_sync_batch_queries(server_version):
         assert results == [{"id": 1, "query_index": 0}, {"id": 1, "query_index": 1}]
 
 
-def test_query_sync_fts():
+@pytest.mark.parametrize("vector_columns", [{}, {"vector": 3}, {"v1": 3, "v2": 3}])
+@pytest.mark.parametrize("query_type", ["auto", "fts"])
+def test_query_sync_fts(vector_columns, query_type):
     def handler(body):
         assert body == {
             "full_text_query": {
@@ -1852,8 +2072,8 @@ def test_query_sync_fts():
 
         return pa.table({"id": [1, 2, 3]})
 
-    with query_test_table(handler) as table:
-        (table.search("puppy", query_type="fts").to_list())
+    with query_test_table(handler, vector_columns=vector_columns) as table:
+        (table.search("puppy", query_type=query_type).to_list())
 
     def handler(body):
         assert body == {
@@ -1880,9 +2100,11 @@ def test_query_sync_fts():
 
         return pa.table({"id": [1, 2, 3]})
 
-    with query_test_table(handler) as table:
+    with query_test_table(handler, vector_columns=vector_columns) as table:
         (
-            table.search("puppy", query_type="fts", fts_columns=["name", "description"])
+            table.search(
+                "puppy", query_type=query_type, fts_columns=["name", "description"]
+            )
             .with_row_id(True)
             .limit(42)
             .to_list()
@@ -1920,7 +2142,9 @@ def test_query_sync_fts_document_granularity():
             }
         )
 
-    with query_test_table(handler, server_version=Version("0.6.0")) as table:
+    with query_test_table(
+        handler, server_version=Version("0.6.0"), vector_columns={}
+    ) as table:
         result = table.search(
             MatchQuery(
                 "alpha",
@@ -1955,6 +2179,7 @@ def test_query_sync_hybrid():
                 "prefilter": True,
                 "refine_factor": None,
                 "vector": [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+                "vector_column": "vector",
                 "nprobes": 20,
                 "minimum_nprobes": 20,
                 "maximum_nprobes": 20,
@@ -1966,15 +2191,14 @@ def test_query_sync_hybrid():
             }
             return pa.table({"_rowid": [1, 2, 3], "_distance": [0.1, 0.2, 0.3]})
 
-    with query_test_table(handler) as table:
-        embedding_func = MockTextEmbeddingFunction()
-        embedding_config = MagicMock()
-        embedding_config.function = embedding_func
-
-        embedding_funcs = MagicMock()
-        embedding_funcs.get = MagicMock(return_value=embedding_config)
-        table.embedding_functions = embedding_funcs
-
+    config = EmbeddingFunctionConfig(
+        source_column="text",
+        vector_column="vector",
+        function=MockTextEmbeddingFunction.create(),
+    )
+    with query_test_table(
+        handler, vector_columns={"vector": 10}, embedding_functions=[config]
+    ) as table:
         (table.search("puppy", query_type="hybrid").limit(42).to_list())
 
 
@@ -2901,7 +3125,7 @@ def test_remote_connection_jobs_surface():
             request.end_headers()
 
     with mock_lancedb_connection(handler) as db:
-        jobs = db.list_jobs()
+        jobs = list(db.list_jobs())
         assert [job.job_id for job in jobs] == ["job-1", "job-2"]
         assert jobs[0].state == "running"
         assert jobs[0].table == "t1"
@@ -3061,7 +3285,7 @@ def test_view_crud_addresses_its_own_routes():
         described = db.describe_view("adults", namespace_path=["analytics"])
         assert described.schema == view.schema
 
-        assert db.list_views(namespace_path=["analytics"]) == ["adults"]
+        assert list(db.list_views(namespace_path=["analytics"])) == ["adults"]
         db.drop_view("adults", namespace_path=["analytics"])
 
     assert paths == [

python/python/tests/test_table.py

@@ -4541,22 +4541,25 @@ def test_stats(mem_db: DBConnection):
         "my_table",
         data=[{"text": "foo", "id": 0}, {"text": "bar", "id": 1}],
     )
-    assert len(table) == 2
+    table.add([{"text": "baz", "id": 1}])
+    assert len(table) == 3
     stats = table.stats()
     print(f"{stats=}")
     assert stats == {
-        # Full on-disk size of the data file, footer and metadata included.
-        "total_bytes": 637,
-        "num_rows": 2,
+        # Full on-disk size of the data files, footer and metadata included:
+        # 637 bytes for the two-row fragment plus 415 for the one-row fragment.
+        "total_bytes": 1052,
+        "num_rows": 3,
+        "num_deleted_rows": 0,
         "num_indices": 0,
         "fragment_stats": {
-            "num_fragments": 1,
-            "num_small_fragments": 1,
+            "num_fragments": 2,
+            "num_small_fragments": 2,
             "lengths": {
-                "min": 2,
+                "min": 1,
                 "max": 2,
-                "mean": 2,
-                "p25": 2,
+                "mean": 1,
+                "p25": 1,
                 "p50": 2,
                 "p75": 2,
                 "p99": 2,
@@ -4564,12 +4567,19 @@ def test_stats(mem_db: DBConnection):
         },
     }
 
+    # Both rows with id = 1 are deleted, but that empties the second fragment,
+    # which is dropped outright rather than kept with a deletion file, so only
+    # the row marked in the surviving fragment is counted.
+    table.delete("id = 1")
     # Index files count toward total_bytes too (only deletion files and
     # manifests are excluded).
     table.create_index("id", config=BTree())
     stats_with_index = table.stats()
     assert stats_with_index["num_indices"] == 1
     assert stats_with_index["total_bytes"] > stats["total_bytes"]
+    assert stats_with_index["num_rows"] == 1
+    assert stats_with_index["num_deleted_rows"] == 1
+    assert stats_with_index["fragment_stats"]["num_fragments"] == 1
 
 
 def test_create_table_empty_list_with_schema(mem_db: DBConnection):

python/src/connection.rs

@@ -464,12 +464,16 @@ impl Connection {
         })
     }
 
-    pub fn list_materialized_views(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
-        let inner = self_.get_inner()?.clone();
-        future_into_py(self_.py(), async move {
-            let views = inner.list_materialized_views().await.infer_error()?;
-            Ok(views)
-        })
+    #[pyo3(signature = (*, page_token=None, page_limit=None))]
+    pub fn list_materialized_views(
+        &self,
+        page_token: Option<String>,
+        page_limit: Option<u32>,
+    ) -> PyResult<crate::listing::NameListing> {
+        Ok(crate::listing::NameListing::new(
+            self.get_inner()?
+                .list_materialized_views(crate::listing::options(page_token, page_limit)),
+        ))
     }
 
     #[pyo3(signature = (name, namespace_path=None))]
@@ -776,22 +780,19 @@ impl Connection {
         })
     }
 
-    #[pyo3(signature = (namespace_path=None))]
+    #[pyo3(signature = (namespace_path=None, *, page_token=None, page_limit=None))]
     pub fn list_functions(
-        self_: PyRef<'_, Self>,
+        &self,
         namespace_path: Option<Vec<String>>,
-    ) -> PyResult<Bound<'_, PyAny>> {
-        let inner = self_.get_inner()?.clone();
-        let namespace_path = namespace_path.unwrap_or_default();
-        future_into_py(self_.py(), async move {
-            inner
-                .list_functions(&namespace_path)
-                .await
-                .infer_error()?
-                .into_iter()
-                .map(|function| function.to_canonical_json().infer_error())
-                .collect::<PyResult<Vec<_>>>()
-        })
+        page_token: Option<String>,
+        page_limit: Option<u32>,
+    ) -> PyResult<crate::listing::FunctionListing> {
+        Ok(crate::listing::FunctionListing::new(
+            self.get_inner()?.list_functions(
+                &namespace_path.unwrap_or_default(),
+                crate::listing::options(page_token, page_limit),
+            ),
+        ))
     }
 
     #[pyo3(signature = (name, version, namespace_path=None))]
@@ -863,16 +864,19 @@ impl Connection {
         })
     }
 
-    #[pyo3(signature = (namespace_path=None))]
+    #[pyo3(signature = (namespace_path=None, *, page_token=None, page_limit=None))]
     pub fn list_secrets(
-        self_: PyRef<'_, Self>,
+        &self,
         namespace_path: Option<Vec<String>>,
-    ) -> PyResult<Bound<'_, PyAny>> {
-        let inner = self_.get_inner()?.clone();
-        let namespace_path = namespace_path.unwrap_or_default();
-        future_into_py(self_.py(), async move {
-            inner.list_secrets(&namespace_path).await.infer_error()
-        })
+        page_token: Option<String>,
+        page_limit: Option<u32>,
+    ) -> PyResult<crate::listing::NameListing> {
+        Ok(crate::listing::NameListing::new(
+            self.get_inner()?.list_secrets(
+                &namespace_path.unwrap_or_default(),
+                crate::listing::options(page_token, page_limit),
+            ),
+        ))
     }
 
     #[pyo3(signature = (name, namespace_path=None))]
@@ -973,27 +977,31 @@ impl Connection {
         })
     }
 
-    #[pyo3(signature = (namespace_path=None))]
+    #[pyo3(signature = (namespace_path=None, *, page_token=None, page_limit=None))]
     pub fn list_views(
-        self_: PyRef<'_, Self>,
+        &self,
         namespace_path: Option<Vec<String>>,
-    ) -> PyResult<Bound<'_, PyAny>> {
-        let inner = self_.get_inner()?.clone();
-        let namespace_path = namespace_path.unwrap_or_default();
-        future_into_py(self_.py(), async move {
-            inner.list_views(&namespace_path).await.infer_error()
-        })
+        page_token: Option<String>,
+        page_limit: Option<u32>,
+    ) -> PyResult<crate::listing::NameListing> {
+        Ok(crate::listing::NameListing::new(
+            self.get_inner()?.list_views(
+                &namespace_path.unwrap_or_default(),
+                crate::listing::options(page_token, page_limit),
+            ),
+        ))
     }
 
-    pub fn list_jobs(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
-        let inner = self_.get_inner()?.clone();
-        future_into_py(self_.py(), async move {
-            let jobs = inner.list_jobs().await.infer_error()?;
-            Ok(jobs
-                .into_iter()
-                .map(crate::job::JobInfo::from)
-                .collect::<Vec<_>>())
-        })
+    #[pyo3(signature = (*, page_token=None, page_limit=None))]
+    pub fn list_jobs(
+        &self,
+        page_token: Option<String>,
+        page_limit: Option<u32>,
+    ) -> PyResult<crate::listing::JobListing> {
+        Ok(crate::listing::JobListing::new(
+            self.get_inner()?
+                .list_jobs(crate::listing::options(page_token, page_limit)),
+        ))
     }
 
     pub fn cancel_job(self_: PyRef<'_, Self>, job_id: String) -> PyResult<Bound<'_, PyAny>> {

python/src/lib.rs

@@ -29,6 +29,7 @@ pub mod expr;
 pub mod header;
 pub mod index;
 pub mod job;
+mod listing;
 pub mod namespace;
 pub mod oauth;
 pub mod otel;
@@ -65,6 +66,10 @@ pub fn _lancedb(py: Python, m: &Bound<'_, PyModule>) -> PyResult<()> {
     m.add_class::<Connection>()?;
     m.add_class::<catalog::Catalog>()?;
     m.add_class::<catalog::DatabaseNames>()?;
+    m.add_class::<listing::NameListing>()?;
+    m.add_class::<listing::FunctionListing>()?;
+    m.add_class::<listing::JobListing>()?;
+
     m.add_function(wrap_pyfunction!(catalog::connect_catalog, m)?)?;
     m.add_class::<Session>()?;
     m.add_class::<Table>()?;

python/src/listing.rs

@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+use crate::error::PythonErrorExt;
+use crate::runtime::future_into_py;
+use futures::{StreamExt, future::poll_fn};
+use lancedb::listing::{Listing, ListingOptions};
+use pyo3::exceptions::PyStopAsyncIteration;
+use pyo3::{Bound, PyAny, PyRef, PyResult, Python, pyclass, pymethods};
+use std::sync::{Arc, Mutex};
+
+pub fn options(page_token: Option<String>, page_limit: Option<u32>) -> ListingOptions {
+    let mut options = ListingOptions::default();
+    options.page_token = page_token;
+    options.page_limit = page_limit;
+    options
+}
+
+#[pyclass]
+pub struct NameListing {
+    inner: Arc<Mutex<Listing<String>>>,
+    next_lock: Arc<tokio::sync::Mutex<()>>,
+}
+impl NameListing {
+    pub fn new(inner: Listing<String>) -> Self {
+        Self {
+            inner: Arc::new(Mutex::new(inner)),
+            next_lock: Arc::new(tokio::sync::Mutex::new(())),
+        }
+    }
+}
+#[pymethods]
+impl NameListing {
+    fn num_page_results(&self, py: Python<'_>) -> usize {
+        py.detach(|| self.inner.lock().unwrap().num_page_results())
+    }
+    fn page_token(&self, py: Python<'_>) -> Option<String> {
+        py.detach(|| self.inner.lock().unwrap().page_token().map(str::to_owned))
+    }
+    fn __aiter__(self_: PyRef<'_, Self>) -> PyRef<'_, Self> {
+        self_
+    }
+    fn __anext__(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.inner.clone();
+        let next_lock = self_.next_lock.clone();
+        future_into_py(self_.py(), async move {
+            let _guard = next_lock.lock().await;
+            let value = poll_fn(|cx| inner.lock().unwrap().poll_next_unpin(cx))
+                .await
+                .ok_or_else(|| PyStopAsyncIteration::new_err(""))?
+                .infer_error()?;
+            Ok(value)
+        })
+    }
+}
+
+#[pyclass]
+pub struct FunctionListing {
+    inner: Arc<Mutex<Listing<lancedb::function::FunctionVersion>>>,
+    next_lock: Arc<tokio::sync::Mutex<()>>,
+}
+impl FunctionListing {
+    pub fn new(inner: Listing<lancedb::function::FunctionVersion>) -> Self {
+        Self {
+            inner: Arc::new(Mutex::new(inner)),
+            next_lock: Arc::new(tokio::sync::Mutex::new(())),
+        }
+    }
+}
+#[pymethods]
+impl FunctionListing {
+    fn num_page_results(&self, py: Python<'_>) -> usize {
+        py.detach(|| self.inner.lock().unwrap().num_page_results())
+    }
+    fn page_token(&self, py: Python<'_>) -> Option<String> {
+        py.detach(|| self.inner.lock().unwrap().page_token().map(str::to_owned))
+    }
+    fn __aiter__(self_: PyRef<'_, Self>) -> PyRef<'_, Self> {
+        self_
+    }
+    fn __anext__(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.inner.clone();
+        let next_lock = self_.next_lock.clone();
+        future_into_py(self_.py(), async move {
+            let _guard = next_lock.lock().await;
+            let value = poll_fn(|cx| inner.lock().unwrap().poll_next_unpin(cx))
+                .await
+                .ok_or_else(|| PyStopAsyncIteration::new_err(""))?
+                .infer_error()?;
+            value.to_canonical_json().infer_error()
+        })
+    }
+}
+
+#[pyclass]
+pub struct JobListing {
+    inner: Arc<Mutex<Listing<lancedb::database::JobInfo>>>,
+    next_lock: Arc<tokio::sync::Mutex<()>>,
+}
+impl JobListing {
+    pub fn new(inner: Listing<lancedb::database::JobInfo>) -> Self {
+        Self {
+            inner: Arc::new(Mutex::new(inner)),
+            next_lock: Arc::new(tokio::sync::Mutex::new(())),
+        }
+    }
+}
+#[pymethods]
+impl JobListing {
+    fn num_page_results(&self, py: Python<'_>) -> usize {
+        py.detach(|| self.inner.lock().unwrap().num_page_results())
+    }
+    fn page_token(&self, py: Python<'_>) -> Option<String> {
+        py.detach(|| self.inner.lock().unwrap().page_token().map(str::to_owned))
+    }
+    fn __aiter__(self_: PyRef<'_, Self>) -> PyRef<'_, Self> {
+        self_
+    }
+    fn __anext__(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.inner.clone();
+        let next_lock = self_.next_lock.clone();
+        future_into_py(self_.py(), async move {
+            let _guard = next_lock.lock().await;
+            let value = poll_fn(|cx| inner.lock().unwrap().poll_next_unpin(cx))
+                .await
+                .ok_or_else(|| PyStopAsyncIteration::new_err(""))?
+                .infer_error()?;
+            Ok(crate::job::JobInfo::from(value))
+        })
+    }
+}

python/src/table.rs

@@ -267,7 +267,7 @@ fn fmt_maintained(maintained: &Option<Vec<String>>) -> String {
 /// Constructed via the `bucket(...)`, `identity(...)`, or `unsharded()`
 /// classmethods, then optionally chain `with_maintained_indexes(...)` and
 /// `with_writer_config_defaults(...)`. A fresh spec maintains every index the
-/// MemWAL supports, resolved on install.
+/// table has, including ones created later.
 #[pyclass(module = "lancedb._lancedb", from_py_object)]
 #[derive(Clone, Debug)]
 pub struct LsmWriteSpec {
@@ -307,9 +307,9 @@ impl LsmWriteSpec {
         }
     }
 
-    /// Set which indexes the MemWAL maintains. `None` (the default)
-    /// resolves every supported index on install; a list is verbatim,
-    /// and an empty list maintains nothing.
+    /// Set which indexes the MemWAL maintains. `None` (the default) is
+    /// every index the table has, including ones created later; a list is
+    /// verbatim, and an empty list maintains nothing.
     #[pyo3(signature = (indexes))]
     pub fn with_maintained_indexes(&self, indexes: Option<Vec<String>>) -> Self {
         Self {
@@ -1266,6 +1266,7 @@ impl Table {
                 let dict = PyDict::new(py);
                 dict.set_item("total_bytes", stats.total_bytes)?;
                 dict.set_item("num_rows", stats.num_rows)?;
+                dict.set_item("num_deleted_rows", stats.num_deleted_rows)?;
                 dict.set_item("num_indices", stats.num_indices)?;
 
                 let fragment_stats = PyDict::new(py);

python/uv.lock

@@ -1849,19 +1849,19 @@ wheels = [
 
 [[package]]
 name = "lance-namespace"
-version = "0.8.6"
+version = "0.11.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "lance-namespace-urllib3-client" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/af/12/f7ab93b29be3edbf5fc3610714bf2d06088e7f4524bfb38dfd6852458b08/lance_namespace-0.8.6.tar.gz", hash = "sha256:18232e721c8188145f4ec9389cc2dfbeeabf54a619d94885ea1b3375bee9f4af", size = 11529, upload-time = "2026-06-12T17:36:41.651Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/bf/93/da5f7fcac690db9b282a3439ed9e34960c147619a0d6e1f4eb8cd240e7a5/lance_namespace-0.11.1.tar.gz", hash = "sha256:f67cfbbe0647b7cb42f23b673e7edf8a75b7d8a047265a916492f8d247ee1bc2", size = 11631, upload-time = "2026-08-18T17:40:06.294Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/a0/1b/5b1668ee2dc8910965f390640359112a31157092fcf8e000b89c79b58708/lance_namespace-0.8.6-py3-none-any.whl", hash = "sha256:571eae34f9aad70e5b05020416c2860889b9ec82993ccd0eb015e7b39c3ea309", size = 13383, upload-time = "2026-06-12T17:36:43.456Z" },
+    { url = "https://files.pythonhosted.org/packages/fa/bc/601f2b3cc4cfa0070d858a33223bc823fffdd7981a25c45984a5216ca952/lance_namespace-0.11.1-py3-none-any.whl", hash = "sha256:07643fce9a42ad4d58cc8bf91e3f592bc7f4cbd8d0ad5233223506debf67551c", size = 13507, upload-time = "2026-08-18T17:40:03.561Z" },
 ]
 
 [[package]]
 name = "lance-namespace-urllib3-client"
-version = "0.8.6"
+version = "0.11.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "pydantic" },
@@ -1869,9 +1869,9 @@ dependencies = [
     { name = "typing-extensions" },
     { name = "urllib3" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/c7/80/fb224b4a89c1c1638cde949cb6cce6c3aca7759effbfea46a3d9c3960b21/lance_namespace_urllib3_client-0.8.6.tar.gz", hash = "sha256:b6fb1d306e74a7576e5309919020be744527de484a63dbf5eed10f8b368548df", size = 228772, upload-time = "2026-06-12T17:36:42.609Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/e4/c5/2bdd0ff98b469894c8a73be809d26ffdad5402517b0e5f9e758026cba29e/lance_namespace_urllib3_client-0.11.1.tar.gz", hash = "sha256:145a9e9424d7597487249b5b95ee274423bf2910e1a9160b6a07b676b61ea46a", size = 237345, upload-time = "2026-08-18T17:40:07.308Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/c5/90/1e27de15cd1b16785a1c7312beb0a59e75c8344a815f600f58173a565bd1/lance_namespace_urllib3_client-0.8.6-py3-none-any.whl", hash = "sha256:9d78249c3fb15aa3d15d668f78f04a275af3d08d800a7027492f37996ac4968b", size = 369950, upload-time = "2026-06-12T17:36:40.438Z" },
+    { url = "https://files.pythonhosted.org/packages/2a/2a/eaaefd55d1190291207049fedc6b3eb22b506e57d6de91bae46bbaaa9c60/lance_namespace_urllib3_client-0.11.1-py3-none-any.whl", hash = "sha256:36537f529294da6d884ba0fe783704483f0a75463497c7705fd083a4d0257990", size = 406311, upload-time = "2026-08-18T17:40:04.842Z" },
 ]
 
 [[package]]
@@ -2005,7 +2005,7 @@ requires-dist = [
     { name = "pyarrow-stubs", marker = "extra == 'tests'", specifier = ">=16.0" },
     { name = "pydantic", specifier = ">=2.7.4,<3" },
     { name = "pylance", marker = "extra == 'pylance'", specifier = ">=5.0.0b5" },
-    { name = "pylance", marker = "extra == 'tests'", specifier = "==9.0.0" },
+    { name = "pylance", marker = "extra == 'tests'", specifier = "==14.0.0b6" },
     { name = "pyright", marker = "extra == 'dev'", specifier = ">=1.1.350" },
     { name = "pytest", marker = "extra == 'tests'", specifier = ">=7.0" },
     { name = "pytest-asyncio", marker = "extra == 'tests'", specifier = ">=0.21" },
@@ -3912,8 +3912,8 @@ crypto = [
 
 [[package]]
 name = "pylance"
-version = "9.0.0"
-source = { registry = "https://pypi.org/simple" }
+version = "14.0.0b6"
+source = { registry = "https://pypi.fury.io/lance-format/" }
 dependencies = [
     { name = "lance-namespace" },
     { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" },
@@ -3922,12 +3922,12 @@ dependencies = [
     { name = "pyarrow" },
 ]
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/e9/be/45733acd64801991852aac8e658601fd8fc12f76ceb81e57fca690896b90/pylance-9.0.0-cp310-abi3-macosx_11_0_arm64.whl", hash = "sha256:8257213501d3298c5b6a344d60938e4bbe4de9f00cd3265371a56d1dc3dd15ca", size = 68377982, upload-time = "2026-07-24T16:53:45.247Z" },
-    { url = "https://files.pythonhosted.org/packages/d0/3e/1ef707cb215cc7268c63ad84a91344ad6313d3984b343eeb19a9b708698e/pylance-9.0.0-cp310-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:804eedfa1fda2e703cca8580c76f0b44a1b849b725a8908c06f8acfca811732f", size = 71844362, upload-time = "2026-07-24T16:56:07.6Z" },
-    { url = "https://files.pythonhosted.org/packages/c8/fb/a499e5c53ddb75c7de44100fd2bb1f7cc735966200d20292eed7af9ef552/pylance-9.0.0-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0a0b75595e3766c1d5f4c90abdc52337b4de60f1a52d123a4f8c4e5bcbbbfa8f", size = 75663088, upload-time = "2026-07-24T17:10:31.283Z" },
-    { url = "https://files.pythonhosted.org/packages/e9/80/0714e09f64a68dbdf62558955e737a7436df763b9834a6aba506861b5352/pylance-9.0.0-cp310-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:d2f69c5c390ae3710c35a429905fe15f769951777fafb1b72a359e035ec121f7", size = 71866858, upload-time = "2026-07-24T16:56:35.937Z" },
-    { url = "https://files.pythonhosted.org/packages/4b/3c/78d3a6d6ca0d843b7c3ac0c30d9cd2cf4635b0c2cabe6ec66583d5bfc1a1/pylance-9.0.0-cp310-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:836268a7832d62f3d5ccbe1c3fca239621971d90297bcfff14a70b3cb6842aa8", size = 75642656, upload-time = "2026-07-24T17:13:11.879Z" },
-    { url = "https://files.pythonhosted.org/packages/cf/c1/dc9c9a31e171530ec0add024d922488c046437d32a7087c29e254a7eacc7/pylance-9.0.0-cp310-abi3-win_amd64.whl", hash = "sha256:96441d27a5ed3805300388ccf8f31835cd280c98751f80b6a1a11dcd6808fc43", size = 81668288, upload-time = "2026-07-24T17:05:38.707Z" },
+    { url = "https://pypi.fury.io/lance-format/-/ver_DuQEn/pylance-14.0.0b6-cp310-abi3-macosx_11_0_arm64.whl", hash = "sha256:3eade86fa30d9ff3248ee7ffb0b27ce29495394d12327da4d22b5c54bc2b59fe" },
+    { url = "https://pypi.fury.io/lance-format/-/ver_K5sqj/pylance-14.0.0b6-cp310-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:10e291974ee738a1d5d7e9dad17a634394a91cb60080b5ceac209077fbaec43c" },
+    { url = "https://pypi.fury.io/lance-format/-/ver_EnbkT/pylance-14.0.0b6-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:61bac10f5081c1210edd017f81c8c784d800b89446bd0ed05d4a24e7001965bc" },
+    { url = "https://pypi.fury.io/lance-format/-/ver_19ffYg/pylance-14.0.0b6-cp310-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:3c627ad4a9870611becf84409d8e5ecddc6be64e1dd53bee4bd5fb10ab561e5c" },
+    { url = "https://pypi.fury.io/lance-format/-/ver_2eLLY5/pylance-14.0.0b6-cp310-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:bc603a7dd690233f1fe000600171e1c092f153bc9060cdf198825c4bbe1418aa" },
+    { url = "https://pypi.fury.io/lance-format/-/ver_t8ggc/pylance-14.0.0b6-cp310-abi3-win_amd64.whl", hash = "sha256:1d32df32a3d157611450def07eae8ace3a7401286eac68cad9a24e0d5deed2db" },
 ]
 
 [[package]]

python/vendor/lance-arrow/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lance-arrow"
-version = "14.0.0-beta.1"
+version = "14.0.0-beta.7"
 edition = "2024"
 authors = ["Lance Devs <dev@lance.org>"]
 license = "Apache-2.0"

python/vendor/lance-arrow/README.lancedb.md

@@ -1,5 +1,5 @@
-This directory contains `rust/lance-arrow` from Lance tag `v14.0.0-beta.1`
-(commit `ae2903729f02ec8e519a4e53797a052393f25ee3`), licensed under Apache-2.0.
+This directory contains `rust/lance-arrow` from Lance tag `v14.0.0-beta.7`
+(commit `0fd26effc79c62c244a5baf92cdda06e301baf21`), licensed under Apache-2.0.
 
 LanceDB carries a local fix in `src/lib.rs` for sliced child validity bitmaps
 until a Lance release includes the fix. The patch is selected in the root