feat!: support multi-level namespace (#2603)

This PR adds support of multi-level namespace in a LanceDB database,
according to the Lance Namespace spec.

This allows users to create namespace inside a database connection,
perform create, drop, list, list_tables in a namespace. (other
operations like update, describe will be in a follow-up PR)

The 3 types of database connections behave like the following:
1 Local database connections will continue to have just a flat list of
tables for backwards compatibility.
2. Remote database connections will make REST API calls according to the
APIs in the Lance Namespace spec.
3. Lance Namespace connections will invoke the corresponding operations
against the specific namespace implementation which could have different
behaviors regarding these APIs.

All the table APIs now take identifier instead of name, for example
`/v1/table/{name}/create` is now `/v1/table/{id}/create`. If a table is
directly in the root namespace, the API call is identical. If the table
is in a namespace, then the full table ID should be used, with `$` as
the default delimiter (`.` is a special character and creates issues
with URL parsing so `$` is used), for example
`/v1/table/ns1$table1/create`. If a different parameter needs to be
passed in, user can configure the `id_delimiter` in client config and
that becomes a query parameter, for example
`/v1/table/ns1__table1/create?delimiter=__`

The Python and Typescript APIs are kept backwards compatible, but the
following Rust APIs are not:
1. `Connection::drop_table(&self, name: impl AsRef<str>) -> Result<()>`
is now `Connection::drop_table(&self, name: impl AsRef<str>, namespace:
&[String]) -> Result<()>`
2. `Connection::drop_all_tables(&self) -> Result<()>` is now
`Connection::drop_all_tables(&self, name: impl AsRef<str>) ->
Result<()>`
This commit is contained in:
Jack Ye
2025-08-27 12:07:55 -07:00
committed by GitHub
parent fabe37274f
commit faf8973624
22 changed files with 2008 additions and 165 deletions

View File

@@ -728,3 +728,93 @@ def test_bypass_vector_index_sync(tmp_db: lancedb.DBConnection):
table.search(sample_key).bypass_vector_index().explain_plan(verbose=True)
)
assert "KNN" in plan_without_index
def test_local_namespace_operations(tmp_path):
"""Test that local mode namespace operations behave as expected."""
# Create a local database connection
db = lancedb.connect(tmp_path)
# Test list_namespaces returns empty list
namespaces = list(db.list_namespaces())
assert namespaces == []
# Test list_namespaces with parameters still returns empty list
namespaces_with_params = list(
db.list_namespaces(namespace=["test"], page_token="token", limit=5)
)
assert namespaces_with_params == []
def test_local_create_namespace_not_supported(tmp_path):
"""Test that create_namespace is not supported in local mode."""
db = lancedb.connect(tmp_path)
with pytest.raises(
NotImplementedError,
match="Namespace operations are not supported for listing database",
):
db.create_namespace(["test_namespace"])
def test_local_drop_namespace_not_supported(tmp_path):
"""Test that drop_namespace is not supported in local mode."""
db = lancedb.connect(tmp_path)
with pytest.raises(
NotImplementedError,
match="Namespace operations are not supported for listing database",
):
db.drop_namespace(["test_namespace"])
def test_local_table_operations_with_namespace_raise_error(tmp_path):
"""
Test that table operations with namespace parameter
raise ValueError in local mode.
"""
db = lancedb.connect(tmp_path)
# Create some test data
data = [{"vector": [1.0, 2.0], "item": "test"}]
schema = pa.schema(
[pa.field("vector", pa.list_(pa.float32(), 2)), pa.field("item", pa.string())]
)
# Test create_table with namespace - should raise ValueError
with pytest.raises(
NotImplementedError,
match="Namespace parameter is not supported for listing database",
):
db.create_table(
"test_table_with_ns", data=data, schema=schema, namespace=["test_ns"]
)
# Create table normally for other tests
db.create_table("test_table", data=data, schema=schema)
assert "test_table" in db.table_names()
# Test open_table with namespace - should raise ValueError
with pytest.raises(
NotImplementedError,
match="Namespace parameter is not supported for listing database",
):
db.open_table("test_table", namespace=["test_ns"])
# Test table_names with namespace - should raise ValueError
with pytest.raises(
NotImplementedError,
match="Namespace parameter is not supported for listing database",
):
list(db.table_names(namespace=["test_ns"]))
# Test drop_table with namespace - should raise ValueError
with pytest.raises(
NotImplementedError,
match="Namespace parameter is not supported for listing database",
):
db.drop_table("test_table", namespace=["test_ns"])
# Test table_names without namespace - should work normally
tables_root = list(db.table_names())
assert "test_table" in tables_root