rust/lancedb
1
0
Fork 0
mirror of https://github.com/lancedb/lancedb.git synced 2025-12-26 06:39:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: add create_fts_index doc in Python API Reference (#1533)

Browse Source 
resolve #1313

---------

Signed-off-by: BubbleCal <bubble-cal@outlook.com>
This commit is contained in:
BubbleCal
2024-08-15 11:35:16 +08:00
committed by GitHub
parent d2caa5e202
commit b624fc59eb
1 changed files with 41 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

69
python/python/lancedb/table.py
View File

@@ -403,6 +403,47 @@ class Table(ABC):
"""
raise NotImplementedError
def create_fts_index(
self,
field_names: Union[str, List[str]],
ordering_field_names: Union[str, List[str]] = None,
*,
replace: bool = False,
writer_heap_size: Optional[int] = 1024 * 1024 * 1024,
tokenizer_name: str = "default",
use_tantivy: bool = True,
):
"""Create a full-text search index on the table.
Warning - this API is highly experimental and is highly likely to change
in the future.
Parameters
----------
field_names: str or list of str
The name(s) of the field to index.
can be only str if use_tantivy=True for now.
replace: bool, default False
If True, replace the existing index if it exists. Note that this is
not yet an atomic operation; the index will be temporarily
unavailable while the new index is being created.
writer_heap_size: int, default 1GB
Only available with use_tantivy=True
ordering_field_names:
A list of unsigned type fields to index to optionally order
results on at search time.
only available with use_tantivy=True
tokenizer_name: str, default "default"
The tokenizer to use for the index. Can be "raw", "default" or the 2 letter
language code followed by "_stem". So for english it would be "en_stem".
For available languages see: https://docs.rs/tantivy/latest/tantivy/tokenizer/enum.Language.html
only available with use_tantivy=True for now
use_tantivy: bool, default True
If True, use the legacy full-text search implementation based on tantivy.
If False, use the new full-text search implementation based on lance-index.
"""
raise NotImplementedError
@abstractmethod
def add(
self,
@@ -1201,34 +1242,6 @@ class LanceTable(Table):
tokenizer_name: str = "default",
use_tantivy: bool = True,
):
"""Create a full-text search index on the table.
Warning - this API is highly experimental and is highly likely to change
in the future.
Parameters
----------
field_names: str or list of str
The name(s) of the field to index.
can be only str if use_tantivy=True for now.
replace: bool, default False
If True, replace the existing index if it exists. Note that this is
not yet an atomic operation; the index will be temporarily
unavailable while the new index is being created.
writer_heap_size: int, default 1GB
ordering_field_names:
A list of unsigned type fields to index to optionally order
results on at search time.
only available with use_tantivy=True
tokenizer_name: str, default "default"
The tokenizer to use for the index. Can be "raw", "default" or the 2 letter
language code followed by "_stem". So for english it would be "en_stem".
For available languages see: https://docs.rs/tantivy/latest/tantivy/tokenizer/enum.Language.html
only available with use_tantivy=True for now
use_tantivy: bool, default False
If True, use the legacy full-text search implementation based on tantivy.
If False, use the new full-text search implementation based on lance-index.
"""
if not use_tantivy:
if not isinstance(field_names, str):
raise ValueError("field_names must be a string when use_tantivy=False")