rust/lancedb
1
0
Fork 0
mirror of https://github.com/lancedb/lancedb.git synced 2026-09-04 04:28:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: default create_index to create-only

Browse Source
This commit is contained in:
ChilePiquin
2026-09-03 14:24:27 -07:00
parent 2779b75d0d
commit bd86cc5aa6
10 changed files with 113 additions and 70 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/python/lancedb/remote/table.py
+4 -12
View File
@@ -402,6 +402,7 @@ class RemoteTable(Table):
/,
*,
config: IndexConfigType,
replace: bool = ...,
wait_timeout: Optional[timedelta] = ...,
name: Optional[str] = ...,
train: bool = ...,
@@ -416,7 +417,7 @@ class RemoteTable(Table):
index_cache_size: Optional[int] = ...,
num_partitions: Optional[int] = ...,
num_sub_vectors: Optional[int] = ...,
replace: Optional[bool] = ...,
replace: bool = ...,
accelerator: Optional[str] = ...,
index_type: Literal[
"VECTOR", "IVF_FLAT", "IVF_SQ", "IVF_PQ", "IVF_HNSW_SQ", "IVF_HNSW_PQ"
@@ -435,7 +436,7 @@ class RemoteTable(Table):
index_cache_size: Optional[int] = None,
num_partitions: Optional[int] = None,
num_sub_vectors: Optional[int] = None,
replace: Optional[bool] = None,
replace: bool = False,
accelerator: Optional[str] = None,
index_type="vector",
wait_timeout: Optional[timedelta] = None,
@@ -479,7 +480,6 @@ class RemoteTable(Table):
vector_column_name,
accelerator,
index_cache_size,
replace,
)
if is_legacy:
@@ -503,12 +503,6 @@ class RemoteTable(Table):
"If you have 100M+ vectors to index,"
"please contact us at contact@lancedb.com"
)
if replace is not None:
logging.warning(
"replace is not supported on LanceDB cloud."
"Existing indexes will always be replaced."
)
idx_type = index_type.upper()
if idx_type == "VECTOR" or idx_type == "IVF_PQ":
config = IvfPq(
@@ -561,7 +555,7 @@ class RemoteTable(Table):
column: str,
*,
config: IndexConfigType,
replace: Optional[bool] = None,
replace: bool = False,
wait_timeout: Optional[timedelta] = None,
name: Optional[str] = None,
train: bool = True,
@@ -593,7 +587,6 @@ class RemoteTable(Table):
vector_column_name: str,
accelerator: Optional[str],
index_cache_size: Optional[int],
replace: Optional[bool],
) -> bool:
"""Detect if this is a legacy create_index call."""
if config is not None:
@@ -605,7 +598,6 @@ class RemoteTable(Table):
num_sub_vectors,
accelerator,
index_cache_size,
replace,
)
):
return True
python/python/lancedb/table.py
+13 -13
View File
@@ -1132,7 +1132,7 @@ class Table(ABC):
num_partitions: Optional[int] = None,
num_sub_vectors: Optional[int] = None,
vector_column_name: str = VECTOR_COLUMN_NAME,
replace: bool = True,
replace: bool = False,
accelerator: Optional[str] = None,
index_cache_size: Optional[int] = None,
*,
@@ -1166,7 +1166,7 @@ class Table(ABC):
The index configuration object. If provided, uses the new unified API.
Can be one of: IvfFlat, IvfPq, IvfSq, IvfRq, HnswPq, HnswSq,
BTree, Bitmap, LabelList, Fm, FTS.
replace : bool, default True
replace : bool, default False
Whether to replace an existing index on this column.
wait_timeout : timedelta, optional
Timeout to wait for async indexing to complete.
@@ -1198,7 +1198,7 @@ class Table(ABC):
column: str,
*,
config: IndexConfigType,
replace: Optional[bool] = None,
replace: bool = False,
wait_timeout: Optional[timedelta] = None,
name: Optional[str] = None,
train: bool = True,
@@ -1260,7 +1260,7 @@ class Table(ABC):
self,
column: str,
*,
replace: bool = True,
replace: bool = False,
index_type: ScalarIndexType = "BTREE",
wait_timeout: Optional[timedelta] = None,
name: Optional[str] = None,
@@ -1272,7 +1272,7 @@ class Table(ABC):
column : str
The column to be indexed. Must be a boolean, integer, float,
or string column.
replace : bool, default True
replace : bool, default False
Replace the existing index if it exists.
index_type: Literal["BTREE", "BITMAP", "LABEL_LIST"], default "BTREE"
The type of index to create.
@@ -2988,7 +2988,7 @@ class LanceTable(Table):
num_partitions: Optional[int] = None,
num_sub_vectors: Optional[int] = None,
vector_column_name: str = VECTOR_COLUMN_NAME,
replace: bool = True,
replace: bool = False,
accelerator: Optional[str] = None,
index_cache_size: Optional[int] = None,
num_bits: int = 8,
@@ -3030,7 +3030,7 @@ class LanceTable(Table):
The index configuration object. If provided, uses the new unified API.
Can be one of: IvfFlat, IvfPq, IvfSq, IvfRq, HnswPq, HnswSq,
BTree, Bitmap, LabelList, Fm, FTS.
replace : bool, default True
replace : bool, default False
Whether to replace an existing index on this column.
wait_timeout : timedelta, optional
Timeout to wait for async indexing to complete.
@@ -3169,7 +3169,7 @@ class LanceTable(Table):
column: str,
*,
config: IndexConfigType,
replace: Optional[bool] = None,
replace: bool = False,
wait_timeout: Optional[timedelta] = None,
name: Optional[str] = None,
train: bool = True,
@@ -3424,7 +3424,7 @@ class LanceTable(Table):
self,
column: str,
*,
replace: bool = True,
replace: bool = False,
index_type: ScalarIndexType = "BTREE",
name: Optional[str] = None,
):
@@ -5313,7 +5313,7 @@ class AsyncTable:
self,
column: str,
*,
replace: Optional[bool] = None,
replace: bool = False,
config: Optional[
Union[
IvfFlat,
@@ -5344,14 +5344,14 @@ class AsyncTable:
----------
column: str
The column to index.
replace: bool, default True
replace: bool, default False
Whether to replace the existing index
If this is false, and another index already exists on the same columns
and the same name, then an error will be returned. This is true even if
that index is out of date.
The default is True
The default is False
config: default None
For advanced configuration you can specify the type of index you would
like to create. You can also specify index-specific parameters when
@@ -5409,7 +5409,7 @@ class AsyncTable:
self,
column: str,
*,
replace: Optional[bool] = None,
replace: bool = False,
config: Optional[
Union[
IvfFlat,
python/python/tests/test_index.py
+10 -2
View File
@@ -97,6 +97,9 @@ async def test_create_index_async_returns_done_job(some_table: AsyncTable):
async def test_create_scalar_index(some_table: AsyncTable):
# Can create
await some_table.create_index("id")
# Can't recreate by default
with pytest.raises(RuntimeError, match="already exists"):
await some_table.create_index("id")
# Can recreate if replace=True
await some_table.create_index("id", replace=True)
indices = await some_table.list_indices()
@@ -110,7 +113,7 @@ async def test_create_scalar_index(some_table: AsyncTable):
with pytest.raises(RuntimeError, match="already exists"):
await some_table.create_index("id", replace=False)
# can also specify index type
await some_table.create_index("id", config=BTree())
await some_table.create_index("id", config=BTree(), replace=True)
await some_table.drop_index("id_idx")
indices = await some_table.list_indices()
@@ -351,13 +354,18 @@ async def test_full_text_search_index(some_table: AsyncTable):
async def test_create_vector_index(some_table: AsyncTable):
# Can create
await some_table.create_index("vector")
# Can't recreate by default
with pytest.raises(RuntimeError, match="already exists"):
await some_table.create_index("vector")
# Can recreate if replace=True
await some_table.create_index("vector", replace=True)
# Can't recreate if replace=False
with pytest.raises(RuntimeError, match="already exists"):
await some_table.create_index("vector", replace=False)
# Can also specify index type
await some_table.create_index("vector", config=IvfPq(num_partitions=100))
await some_table.create_index(
"vector", config=IvfPq(num_partitions=100), replace=True
)
indices = await some_table.list_indices()
assert len(indices) == 1
assert indices[0].index_type == "IvfPq"
python/python/tests/test_table.py
+8 -8
View File
@@ -1600,7 +1600,7 @@ def test_create_index_method(mock_create_index, mem_db: DBConnection):
)
mock_create_index.assert_called_with(
"my_vector",
replace=True,
replace=False,
config=expected_config,
wait_timeout=None,
name=None,
@@ -1620,7 +1620,7 @@ def test_create_index_method(mock_create_index, mem_db: DBConnection):
)
mock_create_index.assert_called_with(
"my_vector",
replace=True,
replace=False,
config=expected_config,
wait_timeout=None,
name=None,
@@ -1646,7 +1646,7 @@ def test_create_index_name_and_train_parameters(
expected_config = IvfPq() # Default config
mock_create_index.assert_called_with(
"vector",
replace=True,
replace=False,
config=expected_config,
wait_timeout=None,
name="my_custom_index",
@@ -1657,7 +1657,7 @@ def test_create_index_name_and_train_parameters(
table.create_index(vector_column_name="vector", train=False)
mock_create_index.assert_called_with(
"vector",
replace=True,
replace=False,
config=expected_config,
wait_timeout=None,
name=None,
@@ -1668,7 +1668,7 @@ def test_create_index_name_and_train_parameters(
table.create_index(vector_column_name="vector", name="my_index_name", train=True)
mock_create_index.assert_called_with(
"vector",
replace=True,
replace=False,
config=expected_config,
wait_timeout=None,
name="my_index_name",
@@ -1705,7 +1705,7 @@ def test_create_index_new_api(mock_create_index, mem_db: DBConnection):
table.create_index("vector", config=IvfPq(distance_type="l2"))
mock_create_index.assert_called_with(
"vector",
replace=True,
replace=False,
config=IvfPq(distance_type="l2"),
wait_timeout=None,
name=None,
@@ -1716,7 +1716,7 @@ def test_create_index_new_api(mock_create_index, mem_db: DBConnection):
table.create_index("category", config=BTree())
mock_create_index.assert_called_with(
"category",
replace=True,
replace=False,
config=BTree(),
wait_timeout=None,
name=None,
@@ -1727,7 +1727,7 @@ def test_create_index_new_api(mock_create_index, mem_db: DBConnection):
table.create_index("text", config=FTS(with_position=True))
mock_create_index.assert_called_with(
"text",
replace=True,
replace=False,
config=FTS(with_position=True),
wait_timeout=None,
name=None,