feat: support a bunch or FTS features in JS SDK (#2431)

- operator for match query
- slop for phrase query
- boolean query

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

- **New Features**
- Introduced support for boolean full-text search queries with AND/OR
logic and occurrence conditions.
- Added operator options for match and multi-match queries to control
term combination logic.
- Enabled phrase queries to specify proximity (slop) for flexible phrase
matching.
- Added new enumerations (`Operator`, `Occur`) and the `BooleanQuery`
class for enhanced query expressiveness.

- **Bug Fixes**
- Improved validation and error handling for invalid operator and
occurrence inputs in full-text queries.

- **Tests**
- Expanded test coverage with new cases for boolean queries and
operator-based full-text searches.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Signed-off-by: BubbleCal <bubble-cal@outlook.com>
This commit is contained in:
BubbleCal
2025-06-12 17:04:19 +08:00
committed by GitHub
parent 84ded9d678
commit fec8d58f06
14 changed files with 291 additions and 8 deletions

View File

@@ -33,7 +33,12 @@ import {
register,
} from "../lancedb/embedding";
import { Index } from "../lancedb/indices";
import { instanceOfFullTextQuery } from "../lancedb/query";
import {
BooleanQuery,
Occur,
Operator,
instanceOfFullTextQuery,
} from "../lancedb/query";
import exp = require("constants");
describe.each([arrow15, arrow16, arrow17, arrow18])(
@@ -1531,6 +1536,18 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
const results = await table.search("hello").toArray();
expect(results[0].text).toBe(data[0].text);
const results2 = await table
.search(new MatchQuery("hello world", "text"))
.toArray();
expect(results2.length).toBe(2);
const results3 = await table
.search(
new MatchQuery("hello world", "text", { operator: Operator.And }),
)
.toArray();
expect(results3.length).toBe(1);
});
test("full text search without lowercase", async () => {
@@ -1609,6 +1626,38 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
expect(resultSet.has("food")).toBe(true);
});
test("full text search boolean query", 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({ withPosition: false }),
});
const shouldResults = await table
.search(
new BooleanQuery([
[Occur.Should, new MatchQuery("hello", "text")],
[Occur.Should, new MatchQuery("goodbye", "text")],
]),
)
.toArray();
expect(shouldResults.length).toBe(2);
const mustResults = await table
.search(
new BooleanQuery([
[Occur.Must, new MatchQuery("hello", "text")],
[Occur.Must, new MatchQuery("world", "text")],
]),
)
.toArray();
expect(mustResults.length).toBe(1);
});
test.each([
[0.4, 0.5, 0.599], // number[]
Float32Array.of(0.4, 0.5, 0.599), // Float32Array