feat(fts): add block size configuration (#3691)

## What changed

- add `block_size` to Python FTS configuration and the deprecated
local/remote helpers
- add `blockSize` to the TypeScript FTS options and propagate it through
the NAPI binding
- serialize the value as `block_size` for remote index creation
- document the existing Rust builder API and generate the TypeScript API
reference
- add local, remote, metadata, search, and invalid-value regression
coverage

## Why

Lance supports configuring the number of documents per compressed FTS
posting block, but LanceDB's Python and TypeScript APIs did not expose
the setting. This made the experimental FTS V3 layout unavailable
through those clients and allowed the value to be dropped before index
creation.

## How it works

The default remains `128`. Supported values are `128` and `256`;
selecting `256` uses the experimental FTS V3 format. Invalid values are
rejected by the Lance builder and surfaced as Python or JavaScript
errors.

## Validation

- `cargo check --quiet --features remote --tests --examples`
- `cargo +1.94.0 clippy --quiet --features remote --tests --examples --
-D warnings`
- targeted Rust local and remote index tests
- Rust doctests: 34 passed
- Python Ruff checks, doctest, and targeted local/remote tests: 5 passed
- TypeScript build, Biome lint, generated docs, and targeted Jest tests:
9 passed
- `git diff --check`

## Limitations

The Java client remains unchanged because its external remote REST model
does not currently expose `block_size`.

Co-authored-by: Yang Cen <yangcen@Yangs-Mac-mini.local>
This commit is contained in:
Yang Cen
2026-07-25 06:02:38 +08:00
committed by GitHub
parent 18760f74cd
commit 9dc5ec03aa
14 changed files with 198 additions and 12 deletions
+13
View File
@@ -43,6 +43,19 @@ The following tokenizers are available:
***
### blockSize?
```ts
optional blockSize: 128 | 256;
```
Number of documents per compressed posting block.
The default is 128. Supported values are 128 and 256. A value of 256 uses
the experimental FTS V3 format and may introduce breaking changes.
***
### language?
```ts
+49
View File
@@ -15,6 +15,7 @@ import {
OAuthHeaderProvider,
StaticHeaderProvider,
} from "../lancedb/header";
import { Index } from "../lancedb/indices";
// Test-only header providers
class CustomProvider extends HeaderProvider {
@@ -225,6 +226,54 @@ describe("remote connection", () => {
);
});
it("sends the FTS posting block size to remote tables", async () => {
let createIndexBody: Record<string, unknown> | undefined;
await withMockDatabase(
(req, res) => {
const path = req.url ?? "";
if (path.endsWith("/describe/")) {
res.writeHead(200, { "Content-Type": "application/json" }).end(
JSON.stringify({
name: "t",
version: 1,
schema: {
fields: [
{ name: "text", type: { type: "string" }, nullable: false },
],
},
}),
);
return;
}
if (path.endsWith("/create_index/")) {
let raw = "";
req.on("data", (chunk) => {
raw += chunk;
});
req.on("end", () => {
createIndexBody = JSON.parse(raw);
res.writeHead(200).end();
});
return;
}
res.writeHead(404).end();
},
async (db) => {
const table = await db.openTable("t");
await table.createIndex("text", {
config: Index.fts({ blockSize: 256 }),
});
},
);
expect(createIndexBody?.["column"]).toBe("text");
expect(createIndexBody?.["index_type"]).toBe("FTS");
expect(createIndexBody?.["block_size"]).toBe(256);
});
it("diffs and merges remote branches", async () => {
const sampleDiff = {
fromBranch: "exp",
+29
View File
@@ -2527,6 +2527,35 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
expect(results3.length).toBe(1);
});
test("full text search with custom posting block size", async () => {
const db = await connect(tmpDir.name);
const data = [
{ text: "hello world", vector: [0.1, 0.2, 0.3] },
{ text: "goodbye world", vector: [0.4, 0.5, 0.6] },
];
const table = await db.createTable("test", data);
await table.createIndex("text", {
config: Index.fts({ blockSize: 256 }),
});
const index = (await table.listIndices()).find(
(index) => index.indexType === "FTS",
);
expect(index?.indexVersion).toBe(3);
expect(
(index?.indexDetails as Record<string, unknown>)["block_size"],
).toBe(256);
const results = await table.search("hello").toArray();
expect(results[0].text).toBe(data[0].text);
});
test("rejects invalid full text posting block size", () => {
expect(() => Index.fts({ blockSize: 129 as 128 | 256 })).toThrow(
"128 or 256",
);
});
test("full text search without lowercase", async () => {
const db = await connect(tmpDir.name);
const data = [
+9
View File
@@ -572,6 +572,14 @@ export interface FtsOptions {
* whether to only index the prefix of the token for ngram tokenizer
*/
prefixOnly?: boolean;
/**
* Number of documents per compressed posting block.
*
* The default is 128. Supported values are 128 and 256. A value of 256 uses
* the experimental FTS V3 format and may introduce breaking changes.
*/
blockSize?: 128 | 256;
}
export class Index {
@@ -751,6 +759,7 @@ export class Index {
options?.ngramMinLength,
options?.ngramMaxLength,
options?.prefixOnly,
options?.blockSize,
),
);
}
+10 -4
View File
@@ -226,7 +226,8 @@ impl Index {
ngram_min_length: Option<u32>,
ngram_max_length: Option<u32>,
prefix_only: Option<bool>,
) -> Self {
block_size: Option<u32>,
) -> napi::Result<Self> {
let mut opts = FtsIndexBuilder::default();
if let Some(with_position) = with_position {
opts = opts.with_position(with_position);
@@ -261,10 +262,15 @@ impl Index {
if let Some(prefix_only) = prefix_only {
opts = opts.ngram_prefix_only(prefix_only);
}
Self {
inner: Mutex::new(Some(LanceDbIndex::FTS(opts))),
if let Some(block_size) = block_size {
opts = opts
.block_size(block_size as usize)
.map_err(|err| napi::Error::from_reason(err.to_string()))?;
}
Ok(Self {
inner: Mutex::new(Some(LanceDbIndex::FTS(opts))),
})
}
#[napi(factory)]
+11
View File
@@ -115,6 +115,12 @@ class FTS:
For example, it works with `title`, `description`, `content`, etc.
Examples
--------
Create an index configuration that uses 256-document posting blocks:
>>> config = FTS(block_size=256)
Attributes
----------
with_position : bool, default False
@@ -148,6 +154,10 @@ class FTS:
ascii_folding : bool, default True
Whether to fold ASCII characters. This converts accented characters to
their ASCII equivalent. For example, "café" would be converted to "cafe".
block_size : int, default 128
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.
Notes
-----
@@ -168,6 +178,7 @@ class FTS:
ngram_min_length: int = 3
ngram_max_length: int = 3
prefix_only: bool = False
block_size: int = 128
@dataclass
+2
View File
@@ -344,6 +344,7 @@ class RemoteTable(Table):
ngram_min_length: int = 3,
ngram_max_length: int = 3,
prefix_only: bool = False,
block_size: int = 128,
name: Optional[str] = None,
):
"""Create a full-text search index on a column.
@@ -364,6 +365,7 @@ class RemoteTable(Table):
ngram_min_length=ngram_min_length,
ngram_max_length=ngram_max_length,
prefix_only=prefix_only,
block_size=block_size,
)
LOOP.run(
self._table.create_index(
+7 -3
View File
@@ -1106,6 +1106,7 @@ class Table(ABC):
ngram_min_length: int = 3,
ngram_max_length: int = 3,
prefix_only: bool = False,
block_size: int = 128,
wait_timeout: Optional[timedelta] = None,
name: Optional[str] = None,
):
@@ -1177,6 +1178,10 @@ class Table(ABC):
The maximum length of an n-gram.
prefix_only: bool, default False
Whether to only index the prefix of the token for ngram tokenizer.
block_size: int, default 128
The number of documents per compressed posting block. Must be 128
or 256. A value of 256 uses the experimental FTS V3 format and
may introduce breaking changes.
wait_timeout: timedelta, optional
The timeout to wait if indexing is asynchronous.
name: str, optional
@@ -3026,6 +3031,7 @@ class LanceTable(Table):
ngram_min_length: int = 3,
ngram_max_length: int = 3,
prefix_only: bool = False,
block_size: int = 128,
name: Optional[str] = None,
):
"""Create a full-text search index on a column.
@@ -3075,9 +3081,7 @@ class LanceTable(Table):
else:
tokenizer_configs = self.infer_tokenizer_configs(tokenizer_name)
config = FTS(
**tokenizer_configs,
)
config = FTS(block_size=block_size, **tokenizer_configs)
try:
LOOP.run(
+17
View File
@@ -226,6 +226,23 @@ def test_create_inverted_index(table, with_position):
assert any(i.name == "custom_fts_index" for i in fts_indices)
@pytest.mark.parametrize("block_size", [128, 256])
def test_create_inverted_index_block_size(table, block_size):
table.create_index("text", config=FTS(block_size=block_size))
index = next(index for index in table.list_indices() if index.index_type == "FTS")
assert index.index_details["block_size"] == block_size
assert index.index_version == (2 if block_size == 128 else 3)
results = table.search("puppy").limit(5).to_list()
assert len(results) == 5
def test_create_inverted_index_rejects_invalid_block_size(table):
with pytest.raises(ValueError, match="128 or 256"):
table.create_index("text", config=FTS(block_size=129))
def test_search_fts(table):
table.create_fts_index("text")
results = table.search("puppy").select(["id", "text"]).limit(5).to_list()
+7 -2
View File
@@ -768,7 +768,10 @@ def test_table_create_indices():
# Test create_fts_index with custom name (legacy method)
with pytest.warns(DeprecationWarning, match="create_fts_index"):
table.create_fts_index(
"text", wait_timeout=timedelta(seconds=2), name="custom_fts_idx"
"text",
wait_timeout=timedelta(seconds=2),
block_size=256,
name="custom_fts_idx",
)
# Test create_index with custom name (legacy form: vector_column_name kwarg)
@@ -791,6 +794,7 @@ def test_table_create_indices():
fts_req = received_requests[1]
assert "name" in fts_req
assert fts_req["name"] == "custom_fts_idx"
assert fts_req["block_size"] == 256
# Check vector index request has custom name
vector_req = received_requests[2]
@@ -876,7 +880,7 @@ def test_remote_create_index_new_api():
_warnings.simplefilter("error", DeprecationWarning)
table.create_index("vector", config=IvfPq(distance_type="l2"))
table.create_index("category", config=BTree())
table.create_index("text", config=FTS())
table.create_index("text", config=FTS(block_size=256))
# IvfRq via new API
table.create_index("vector", config=IvfRq(distance_type="l2"))
@@ -896,6 +900,7 @@ def test_remote_create_index_new_api():
"vector",
"vector",
]
assert received_requests[2]["block_size"] == 256
def test_table_wait_for_index_timeout():
+4
View File
@@ -60,6 +60,9 @@ pub fn extract_index_params(source: &Option<Bound<'_, PyAny>>) -> PyResult<Lance
.ngram_min_length(params.ngram_min_length)
.ngram_max_length(params.ngram_max_length)
.ngram_prefix_only(params.prefix_only);
let inner_opts = inner_opts
.block_size(params.block_size)
.map_err(|err| PyValueError::new_err(err.to_string()))?;
Ok(LanceDbIndex::FTS(inner_opts))
}
"IvfFlat" => {
@@ -207,6 +210,7 @@ struct FtsParams {
ngram_min_length: u32,
ngram_max_length: u32,
prefix_only: bool,
block_size: usize,
}
#[derive(FromPyObject)]
+20 -1
View File
@@ -54,7 +54,26 @@ pub enum Index {
/// substrings of the raw bytes, unlike the tokenized [`Index::FTS`] index.
Fm(FmIndexBuilder),
/// Full text search index using bm25.
/// Full text search index using BM25.
///
/// The posting block size defaults to 128. Supported values are 128 and 256;
/// a value of 256 uses the experimental FTS V3 format and may introduce
/// breaking changes.
///
/// ```
/// use lancedb::index::{Index, scalar::FtsIndexBuilder};
///
/// # async fn create_fts_index(
/// # table: &lancedb::Table,
/// # ) -> Result<(), Box<dyn std::error::Error>> {
/// let params = FtsIndexBuilder::default().block_size(256)?;
/// table
/// .create_index(&["text"], Index::FTS(params))
/// .execute()
/// .await?;
/// # Ok(())
/// # }
/// ```
FTS(FtsIndexBuilder),
/// IVF index
+9
View File
@@ -4496,6 +4496,15 @@ mod tests {
serde_json::to_value(InvertedIndexParams::default()).unwrap(),
Index::FTS(Default::default()),
),
(
"FTS",
{
let mut body = serde_json::to_value(InvertedIndexParams::default()).unwrap();
body["block_size"] = 256.into();
body
},
Index::FTS(InvertedIndexParams::default().block_size(256).unwrap()),
),
];
for (index_type, expected_body, index) in cases {
+11 -2
View File
@@ -382,7 +382,9 @@ mod tests {
use crate::connect;
use crate::connection::ConnectBuilder;
use crate::index::Index;
use crate::index::scalar::{BTreeIndexBuilder, BitmapIndexBuilder, FmIndexBuilder};
use crate::index::scalar::{
BTreeIndexBuilder, BitmapIndexBuilder, FmIndexBuilder, FtsIndexBuilder,
};
use crate::index::vector::{
IvfHnswFlatIndexBuilder, IvfHnswPqIndexBuilder, IvfHnswSqIndexBuilder,
};
@@ -1362,7 +1364,10 @@ mod tests {
.unwrap();
table
.create_index(&["text"], Index::FTS(Default::default()))
.create_index(
&["text"],
Index::FTS(FtsIndexBuilder::default().block_size(256).unwrap()),
)
.execute()
.await
.unwrap();
@@ -1372,6 +1377,10 @@ mod tests {
assert_eq!(index.index_type, crate::index::IndexType::FTS);
assert_eq!(index.columns, vec!["text".to_string()]);
assert_eq!(index.name, "text_idx");
assert_eq!(index.index_version, Some(3));
let index_params: FtsIndexBuilder =
serde_json::from_str(index.index_details.as_deref().unwrap()).unwrap();
assert_eq!(index_params.posting_block_size(), 256);
let num_rows = 120;
let stats = table.index_stats("text_idx").await.unwrap().unwrap();