feat(bindings): expose new IndexConfig fields in Python and Node.js (#3534)

## Summary

Surfaces the rich per-index metadata added in #3497 to the Python and
Node.js language bindings. Closes #3495.

New optional fields exposed on `IndexConfig` in both bindings:

- `index_uuid` / `indexUuid` — UUID of the first index segment
- `type_url` / `typeUrl` — protobuf type URL for the index
- `created_at` / `createdAt` — creation timestamp (milliseconds since
Unix epoch)
- `num_indexed_rows` / `numIndexedRows` — rows covered by the index
- `num_unindexed_rows` / `numUnindexedRows` — rows not yet indexed
- `size_bytes` / `sizeBytes` — total index file size in bytes
- `num_segments` / `numSegments` — number of index segments
- `index_version` / `indexVersion` — on-disk format version
- `index_details` / `indexDetails` — type-specific JSON details string

All fields are `None`/`undefined` for remote tables (which don't yet
surface this metadata through the server response).

## Changes

- `python/src/index.rs`: extend `IndexConfig` pyclass; update `From`
impl; update `__getitem__`
- `python/python/lancedb/_lancedb.pyi`: add type hints for new fields
- `python/python/tests/test_table.py`: new `test_index_config_fields`
test
- `nodejs/src/table.rs`: extend `IndexConfig` napi struct; update `From`
impl
- `nodejs/__test__/table.test.ts`: new test; update existing `toEqual`
assertions to `expect.objectContaining` to accommodate new fields

## Test plan

- [x] Python: `uv run --extra tests pytest
python/tests/test_table.py::test_index_config_fields`
- [x] Node.js: `pnpm test __test__/table.test.ts`

🤖 Generated with [Claude Code](https://claude.com/claude-code)

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Will Jones
2026-06-11 13:37:39 -07:00
committed by GitHub
parent 40f3e22600
commit f8caef3aca
10 changed files with 359 additions and 45 deletions

View File

@@ -25,8 +25,12 @@ lancedb = { path = "../rust/lancedb", default-features = false }
lance-namespace.workspace = true
napi = { version = "3.8.3", default-features = false, features = [
"napi9",
"async"
"async",
"chrono_date",
"serde-json",
] }
chrono = { version = "0.4", default-features = false, features = ["clock"] }
serde_json = "1"
napi-derive = "3.5.2"
# Prevent dynamic linking of lzma, which comes from datafusion
lzma-sys = { version = "0.1", features = ["static"] }

View File

@@ -845,11 +845,13 @@ describe("When creating an index", () => {
expect(fs.readdirSync(indexDir)).toHaveLength(1);
const indices = await tbl.listIndices();
expect(indices.length).toBe(1);
expect(indices[0]).toEqual({
name: "vec_idx",
indexType: "IvfPq",
columns: ["vec"],
});
expect(indices[0]).toEqual(
expect.objectContaining({
name: "vec_idx",
indexType: "IvfPq",
columns: ["vec"],
}),
);
const stats = await tbl.indexStats("vec_idx");
expect(stats).toBeDefined();
@@ -1011,51 +1013,51 @@ describe("When creating an index", () => {
const indices = await nestedTable.listIndices();
expect(indices).toEqual(
expect.arrayContaining([
{
expect.objectContaining({
name: "row_id_idx",
indexType: "BTree",
columns: ["rowId"],
},
{
}),
expect.objectContaining({
name: "row_dash_id_idx",
indexType: "BTree",
columns: ["`row-id`"],
},
{
}),
expect.objectContaining({
name: "top_user_id_idx",
indexType: "BTree",
columns: ["userId"],
},
{
}),
expect.objectContaining({
name: "nested_user_id_idx",
indexType: "BTree",
columns: ["metadata.user_id"],
},
{
}),
expect.objectContaining({
name: "mixed_case_metadata_user_id_idx",
indexType: "BTree",
columns: ["MetaData.userId"],
},
{
}),
expect.objectContaining({
name: "escaped_names_idx",
indexType: "BTree",
columns: ["`meta-data`.`user-id`"],
},
{
}),
expect.objectContaining({
name: "literal_dot_idx",
indexType: "BTree",
columns: ["literal.`a.b`"],
},
{
}),
expect.objectContaining({
name: "image_embedding_idx",
indexType: "IvfPq",
columns: ["image.embedding"],
},
{
}),
expect.objectContaining({
name: "payload_text_idx",
indexType: "FTS",
columns: ["payload.text"],
},
}),
]),
);
@@ -1109,16 +1111,16 @@ describe("When creating an index", () => {
const indicesAfterOptimize = await nestedTable.listIndices();
expect(indicesAfterOptimize).toEqual(
expect.arrayContaining([
{
expect.objectContaining({
name: "mixed_case_metadata_user_id_idx",
indexType: "BTree",
columns: ["MetaData.userId"],
},
{
}),
expect.objectContaining({
name: "image_embedding_idx",
indexType: "IvfPq",
columns: ["image.embedding"],
},
}),
]),
);
});
@@ -1254,11 +1256,13 @@ describe("When creating an index", () => {
expect(fs.readdirSync(indexDir)).toHaveLength(1);
const indices = await tbl.listIndices();
expect(indices.length).toBe(1);
expect(indices[0]).toEqual({
name: "vec_idx",
indexType: "IvfHnswSq",
columns: ["vec"],
});
expect(indices[0]).toEqual(
expect.objectContaining({
name: "vec_idx",
indexType: "IvfHnswSq",
columns: ["vec"],
}),
);
// Search without specifying the column
let rst = await tbl
@@ -1604,6 +1608,35 @@ describe("When creating an index", () => {
expect(rst64Query.toString()).toEqual(rst64Search.toString());
expect(rst64Query.numRows).toBe(2);
});
it("should expose rich metadata fields on IndexConfig", async () => {
await tbl.createIndex("id", { config: Index.btree() });
await tbl.createIndex("vec");
const indicesByName = Object.fromEntries(
(await tbl.listIndices()).map((idx) => [idx.name, idx]),
);
const scalarIdx = indicesByName["id_idx"];
expect(scalarIdx).toBeDefined();
expect(typeof scalarIdx.indexUuid).toBe("string");
expect(scalarIdx.numIndexedRows).toBe(300);
expect(scalarIdx.numUnindexedRows).toBe(0);
expect(scalarIdx.numSegments).toBeGreaterThanOrEqual(1);
expect(scalarIdx.sizeBytes).toBeGreaterThan(0);
// Use toString check to avoid cross-realm instanceof failures with native Date objects
expect(Object.prototype.toString.call(scalarIdx.createdAt)).toBe(
"[object Date]",
);
expect((scalarIdx.createdAt as Date).getTime()).toBeGreaterThan(0);
expect(typeof scalarIdx.indexDetails).toBe("object");
const vectorIdx = indicesByName["vec_idx"];
expect(vectorIdx).toBeDefined();
expect(typeof vectorIdx.indexUuid).toBe("string");
expect(vectorIdx.numIndexedRows).toBe(300);
expect(typeof vectorIdx.indexDetails).toBe("object");
});
});
describe("When querying a table", () => {

View File

@@ -3,6 +3,8 @@
use std::collections::HashMap;
use chrono::{DateTime, Utc};
use lancedb::ipc::{ipc_file_to_batches, ipc_file_to_schema};
use lancedb::table::{
AddDataMode, ColumnAlteration as LanceColumnAlteration, Duration,
@@ -602,6 +604,43 @@ pub struct IndexConfig {
/// Currently this is always an array of size 1. In the future there may
/// be more columns to represent composite indices.
pub columns: Vec<String>,
/// The UUID of the first segment of the index.
///
/// `undefined` for remote tables, which do not yet surface this.
pub index_uuid: Option<String>,
/// The protobuf type URL, a precise type identifier for the index.
///
/// `undefined` for remote tables.
pub type_url: Option<String>,
/// When the index was created.
///
/// `undefined` for remote tables or indices created before timestamps were tracked.
pub created_at: Option<DateTime<Utc>>,
/// The number of rows indexed, across all segments.
///
/// `undefined` for remote tables.
pub num_indexed_rows: Option<i64>,
/// The number of rows not yet covered by this index.
///
/// `undefined` for remote tables.
pub num_unindexed_rows: Option<i64>,
/// The total size in bytes of all index files across all segments.
///
/// `undefined` for remote tables or indices without size tracking.
pub size_bytes: Option<i64>,
/// The number of segments that make up the index.
///
/// `undefined` for remote tables.
pub num_segments: Option<i32>,
/// The on-disk index format version.
///
/// `undefined` for remote tables.
pub index_version: Option<i32>,
/// Index-type-specific details parsed as a JavaScript object.
///
/// Falls back to a raw string if JSON parsing fails. `undefined` for
/// remote tables or when details are unavailable.
pub index_details: Option<serde_json::Value>,
}
impl From<lancedb::index::IndexConfig> for IndexConfig {
@@ -611,6 +650,17 @@ impl From<lancedb::index::IndexConfig> for IndexConfig {
index_type,
columns: value.columns,
name: value.name,
index_uuid: value.index_uuid,
type_url: value.type_url,
created_at: value.created_at,
num_indexed_rows: value.num_indexed_rows.map(|n| n as i64),
num_unindexed_rows: value.num_unindexed_rows.map(|n| n as i64),
size_bytes: value.size_bytes.map(|n| n as i64),
num_segments: value.num_segments.map(|n| n as i32),
index_version: value.index_version,
index_details: value
.index_details
.and_then(|s| serde_json::from_str(&s).ok()),
}
}
}