mirror of
https://github.com/lancedb/lancedb.git
synced 2026-08-19 04:28:35 +00:00
feat: support FM-Index scalar index for substring search (#3532)
Adds an FM-Index — a scalar index over string and binary columns that
accelerates substring search (`contains(col, 'needle')`), distinct from
the tokenized `FTS` index — across the Rust core and the Python and
TypeScript bindings.
## Rust
- `Index::Fm(FmIndexBuilder)` and `IndexType::Fm`.
- `make_index_params` maps `Index::Fm` to Lance's
`ScalarIndexParams::for_builtin(BuiltinIndexType::Fm)`.
- `supported_fm_data_type` validates
`Utf8`/`LargeUtf8`/`Binary`/`LargeBinary` columns.
- `list_indices` round-trips the type (`"Fm"` → `IndexType::Fm`); the
remote wire type is `"FM"`.
## Python
Adds `lancedb.index.Fm`, accepted by `create_index`:
```python
from lancedb.index import Fm
await tbl.create_index("text", config=Fm())
```
## TypeScript
Adds the `Index.fm()` factory:
```ts
await tbl.createIndex("text", { config: Index.fm() });
```
This commit is contained in:
@@ -20,6 +20,7 @@ from lancedb.index import (
|
||||
IvfRq,
|
||||
Bitmap,
|
||||
LabelList,
|
||||
Fm,
|
||||
HnswPq,
|
||||
HnswSq,
|
||||
HnswFlat,
|
||||
@@ -203,6 +204,16 @@ async def test_create_fixed_size_binary_index(some_table: AsyncTable):
|
||||
assert indices[0].columns == ["fsb"]
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_create_fm_index(some_table: AsyncTable):
|
||||
# FM-Index accelerates substring search on string/binary columns.
|
||||
await some_table.create_index("data", config=Fm())
|
||||
indices = await some_table.list_indices()
|
||||
assert len(indices) == 1
|
||||
assert indices[0].index_type == "Fm"
|
||||
assert indices[0].columns == ["data"]
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_create_bitmap_index(some_table: AsyncTable):
|
||||
await some_table.create_index("id", config=Bitmap())
|
||||
|
||||
Reference in New Issue
Block a user