feat: list_bases returns registered table storage prefixes

Return the additional storage bases for the current table snapshot
on native, memory, namespace, and Cloud clients.

python/python/lancedb/_lancedb.pyi

@@ -378,6 +378,7 @@ class Table:
     def take_row_ids(self, row_ids: list[int]) -> TakeQuery: ...
     async def blob_columns(self) -> list[str]: ...
     async def add_bases(self, bases: list[Any]) -> None: ...
+    async def list_bases(self) -> list[tuple[str, Optional[str], bool]]: ...
     async def fetch_blobs(
         self, column: str, row_ids: list[int]
     ) -> pa.LargeBinaryArray: ...

python/python/lancedb/remote/table.py

@@ -1089,6 +1089,10 @@ class RemoteTable(Table):
         """Register additional storage bases for this table."""
         LOOP.run(self._table.add_bases(bases))
 
+    def list_bases(self) -> list[TableBase]:
+        """Return the additional storage bases for the current table snapshot."""
+        return LOOP.run(self._table.list_bases())
+
     def fetch_blobs(
         self, column: str, row_ids: Union[list[int], pa.Table]
     ) -> pa.LargeBinaryArray:

python/python/lancedb/table.py

@@ -1596,6 +1596,10 @@ class Table(ABC):
         """
         raise NotImplementedError
 
+    def list_bases(self) -> list[TableBase]:
+        """Return the additional storage bases for the current table snapshot."""
+        raise NotImplementedError
+
     @abstractmethod
     def fetch_blobs(
         self, column: str, row_ids: Union[list[int], pa.Table]
@@ -2448,6 +2452,10 @@ class LanceTable(Table):
     ) -> None:
         LOOP.run(self._table.add_bases(bases))
 
+    def list_bases(self) -> list[TableBase]:
+        """Return the additional storage bases for the current table snapshot."""
+        return LOOP.run(self._table.list_bases())
+
     def fetch_blobs(
         self, column: str, row_ids: Union[list[int], pa.Table]
     ) -> pa.LargeBinaryArray:
@@ -6312,6 +6320,13 @@ class AsyncTable:
         """
         await self._inner.add_bases(_normalize_bases(bases))
 
+    async def list_bases(self) -> list[TableBase]:
+        """Return the additional storage bases for the current table snapshot."""
+        return [
+            TableBase(path=path, name=name, is_dataset_root=is_dataset_root)
+            for path, name, is_dataset_root in await self._inner.list_bases()
+        ]
+
     async def fetch_blobs(
         self, column: str, row_ids: Union[list[int], pa.Table]
     ) -> pa.LargeBinaryArray:

python/python/tests/test_bases.py

@@ -7,7 +7,33 @@ import pytest
 import lancedb
 
 
-def test_add_bases_accepts_named_and_dataset_root(tmp_path):
+def test_list_bases_reflects_added_bases(tmp_path):
+    media = tmp_path / "media"
+    media.mkdir()
+    db = lancedb.connect(tmp_path / "db")
+    schema = pa.schema([pa.field("id", pa.int64())])
+    table = db.create_table("photos", schema=schema)
+    assert table.list_bases() == []
+    table.add_bases(media.as_uri())
+    assert table.list_bases() == [lancedb.TableBase(path=media.as_uri())]
+
+
+def test_add_bases_accepts_two_unnamed_paths(tmp_path):
+    media = tmp_path / "media"
+    other = tmp_path / "other"
+    media.mkdir()
+    other.mkdir()
+    db = lancedb.connect(tmp_path / "db")
+    schema = pa.schema([pa.field("id", pa.int64())])
+    table = db.create_table("photos", schema=schema)
+    table.add_bases([media.as_uri(), other.as_uri()])
+    assert table.list_bases() == [
+        lancedb.TableBase(path=media.as_uri()),
+        lancedb.TableBase(path=other.as_uri()),
+    ]
+
+
+def test_add_bases_records_name_and_dataset_root(tmp_path):
     media = tmp_path / "media"
     parent = tmp_path / "parent"
     media.mkdir()
@@ -23,17 +49,10 @@ def test_add_bases_accepts_named_and_dataset_root(tmp_path):
             ),
         ]
     )
-
-
-def test_add_bases_accepts_two_unnamed_paths(tmp_path):
-    media = tmp_path / "media"
-    other = tmp_path / "other"
-    media.mkdir()
-    other.mkdir()
-    db = lancedb.connect(tmp_path / "db")
-    schema = pa.schema([pa.field("id", pa.int64())])
-    table = db.create_table("photos", schema=schema)
-    table.add_bases([media.as_uri(), other.as_uri()])
+    assert table.list_bases() == [
+        lancedb.TableBase(path=media.as_uri(), name="media", is_dataset_root=False),
+        lancedb.TableBase(path=parent.as_uri(), name="parent", is_dataset_root=True),
+    ]
 
 
 def test_add_bases_rejects_dict_input(tmp_path):
@@ -51,7 +70,9 @@ async def test_async_add_bases_accepts_file_uri(tmp_path):
     db = await lancedb.connect_async(tmp_path / "db")
     schema = pa.schema([pa.field("id", pa.int64())])
     table = await db.create_table("photos", schema=schema)
+    assert await table.list_bases() == []
     await table.add_bases(media.as_uri())
+    assert await table.list_bases() == [lancedb.TableBase(path=media.as_uri())]
 
 
 def test_memory_add_bases_accepts_file_uri(tmp_path):
@@ -60,7 +81,9 @@ def test_memory_add_bases_accepts_file_uri(tmp_path):
     db = lancedb.connect("memory:///")
     schema = pa.schema([pa.field("id", pa.int64())])
     table = db.create_table("photos", schema=schema)
+    assert table.list_bases() == []
     table.add_bases(media.as_uri())
+    assert table.list_bases() == [lancedb.TableBase(path=media.as_uri())]
 
 
 def test_namespace_add_bases_accepts_file_uri(tmp_path):
@@ -69,4 +92,6 @@ def test_namespace_add_bases_accepts_file_uri(tmp_path):
     db = lancedb.connect_namespace("dir", {"root": str(tmp_path / "ns")})
     schema = pa.schema([pa.field("id", pa.int64())])
     table = db.create_table("photos", schema=schema)
+    assert table.list_bases() == []
     table.add_bases(media.as_uri())
+    assert table.list_bases() == [lancedb.TableBase(path=media.as_uri())]

python/python/tests/test_remote_db.py

@@ -2308,7 +2308,7 @@ def test_remote_connection_jobs_surface():
             job.wait(timeout=timedelta(seconds=5))
 
 
-def test_remote_add_bases_posts_the_bases_array():
+def test_remote_add_and_list_bases():
     captured_body = {}
 
     def handler(request):
@@ -2324,6 +2324,13 @@ def test_remote_add_bases_posts_the_bases_array():
             request.send_header("Content-Type", "application/json")
             request.end_headers()
             request.wfile.write(b'{"version": 2}')
+        elif request.path == "/v1/table/test/bases/list/":
+            request.send_response(200)
+            request.send_header("Content-Type", "application/json")
+            request.end_headers()
+            request.wfile.write(
+                b'{"bases":[{"path":"s3://bucket/media/","isDatasetRoot":false}]}'
+            )
         else:
             request.send_response(404)
             request.end_headers()
@@ -2331,6 +2338,13 @@ def test_remote_add_bases_posts_the_bases_array():
     with mock_lancedb_connection(handler) as db:
         table = db.open_table("test")
         table.add_bases(lancedb.TableBase(path="s3://bucket/media/"))
+        assert table.list_bases() == [
+            lancedb.TableBase(
+                path="s3://bucket/media/",
+                name=None,
+                is_dataset_root=False,
+            )
+        ]
 
     assert captured_body["bases"] == [
         {
@@ -2339,3 +2353,32 @@ def test_remote_add_bases_posts_the_bases_array():
         }
     ]
 
+
+def test_remote_list_bases_returns_named_dataset_root():
+    def handler(request):
+        if request.path == "/v1/table/test/describe/":
+            request.send_response(200)
+            request.send_header("Content-Type", "application/json")
+            request.end_headers()
+            request.wfile.write(json.dumps(BLOB_DESCRIBE_RESPONSE).encode())
+        elif request.path == "/v1/table/test/bases/list/":
+            request.send_response(200)
+            request.send_header("Content-Type", "application/json")
+            request.end_headers()
+            request.wfile.write(
+                b'{"bases":[{"path":"s3://bucket/archive/","name":"archive","isDatasetRoot":true}]}'
+            )
+        else:
+            request.send_response(404)
+            request.end_headers()
+
+    with mock_lancedb_connection(handler) as db:
+        table = db.open_table("test")
+        assert table.list_bases() == [
+            lancedb.TableBase(
+                path="s3://bucket/archive/",
+                name="archive",
+                is_dataset_root=True,
+            )
+        ]
+

python/src/table.rs

@@ -1265,6 +1265,17 @@ impl Table {
         })
     }
 
+    pub fn list_bases(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.inner_ref()?.clone();
+        future_into_py(self_.py(), async move {
+            let bases = inner.list_bases().await.infer_error()?;
+            Ok(bases
+                .into_iter()
+                .map(|base| (base.path, base.name, base.is_dataset_root))
+                .collect::<Vec<_>>())
+        })
+    }
+
     /// Read blob bytes for `row_ids` from blob v2 column `column`.
     #[pyo3(signature = (column, row_ids))]
     pub fn fetch_blobs(