rust/lancedb
1
0
Fork 0
mirror of https://github.com/lancedb/lancedb.git synced 2026-01-05 03:12:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: support FTS options on RemoteTable (#1807)

Browse Source
This commit is contained in:
BubbleCal
2024-12-06 21:49:03 +08:00
committed by GitHub
parent 8b628854d5
commit c663085203
2 changed files with 31 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
python/python/lancedb/index.py
View File

@@ -110,7 +110,16 @@ class FTS:
remove_stop_words: bool = False,
ascii_folding: bool = False,
):
self._inner = LanceDbIndex.fts(with_position=with_position)
self._inner = LanceDbIndex.fts(
with_position=with_position,
base_tokenizer=base_tokenizer,
language=language,
max_token_length=max_token_length,
lower_case=lower_case,
stem=stem,
remove_stop_words=remove_stop_words,
ascii_folding=ascii_folding,
)
class HnswPq:

23
python/python/lancedb/remote/table.py
View File

@@ -138,9 +138,28 @@ class RemoteTable(Table):
*,
replace: bool = False,
with_position: bool = True,
# tokenizer configs:
base_tokenizer: str = "simple",
language: str = "English",
max_token_length: Optional[int] = 40,
lower_case: bool = True,
stem: bool = False,
remove_stop_words: bool = False,
ascii_folding: bool = False,
):
config = FTS(with_position=with_position)
LOOP.run(self._table.create_index(column, config=config, replace=replace))
config = FTS(
with_position=with_position,
base_tokenizer=base_tokenizer,
language=language,
max_token_length=max_token_length,
lower_case=lower_case,
stem=stem,
remove_stop_words=remove_stop_words,
ascii_folding=ascii_folding,
)
self._loop.run_until_complete(
self._table.create_index(column, config=config, replace=replace)
)
def create_index(
self,