diff --git a/python/python/lancedb/index.py b/python/python/lancedb/index.py index aa7846892..d2b63baf6 100644 --- a/python/python/lancedb/index.py +++ b/python/python/lancedb/index.py @@ -163,6 +163,15 @@ class FTS: The number of documents per compressed posting block. Supported values are 128 and 256. A value of 256 uses the experimental FTS V3 format and may introduce breaking changes. + memory_limit : int, optional + The total memory limit in MiB for the local FTS build stage. The limit + is divided evenly among indexing workers. This build-only setting is + not persisted with the index and does not apply to remote tables. + num_workers : int, optional + The number of workers for a local FTS build. By default Lance uses + roughly half of the available CPU cores. The effective value is + limited by the available compute capacity. This build-only setting is + not persisted with the index and does not apply to remote tables. Notes ----- @@ -185,6 +194,8 @@ class FTS: prefix_only: bool = False block_size: int = 128 custom_stop_words: Optional[List[str]] = None + memory_limit: Optional[int] = None + num_workers: Optional[int] = None @dataclass diff --git a/python/python/tests/test_fts.py b/python/python/tests/test_fts.py index f791f9886..625198d92 100644 --- a/python/python/tests/test_fts.py +++ b/python/python/tests/test_fts.py @@ -245,6 +245,14 @@ def test_create_inverted_index_rejects_invalid_block_size(table): table.create_index("text", config=FTS(block_size=129)) +def test_create_inverted_index_respects_build_memory_limit(table): + with pytest.raises(ValueError, match="exceeds worker memory limit"): + table.create_index( + "text", + config=FTS(memory_limit=0, num_workers=1), + ) + + def test_custom_stop_words_list(table): table.create_index( "text", diff --git a/python/src/index.rs b/python/src/index.rs index 8c81dcecf..8312e0709 100644 --- a/python/src/index.rs +++ b/python/src/index.rs @@ -42,7 +42,7 @@ pub fn extract_index_params(source: &Option>) -> PyResult Ok(LanceDbIndex::Fm(FmIndexBuilder::default())), "FTS" => { let params = source.extract::()?; - let inner_opts = FtsIndexBuilder::default() + let mut inner_opts = FtsIndexBuilder::default() .base_tokenizer(params.base_tokenizer) .language(¶ms.language) .map_err(|_| { @@ -61,6 +61,12 @@ pub fn extract_index_params(source: &Option>) -> PyResult, + num_workers: Option, } #[derive(FromPyObject)]