mirror of
https://github.com/lancedb/lancedb.git
synced 2026-06-06 22:00:40 +00:00
refactor!: drop unused loss field from IndexStatistics (#3496)
BREAKING CHANGE: direct Rust users lose the `IndexStatistics::loss` field. Python and Node.js consumers are unaffected in practice for remote tables (the value was always `None`/absent), but the attribute is gone for local tables too. `IndexStatistics::loss` was local-only — LanceDB Cloud never returned it, so `RemoteTable::index_stats` always set `loss: None`. It's vestigial; this removes it. - Remove `loss` from `IndexStatistics` and the internal `IndexMetadata` in `rust/lancedb/src/index.rs`, plus the summing logic in `NativeTable::index_stats`. - Drop `loss` from the Python and Node.js bindings (and their tests/docs). Fixes #3493 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -30,17 +30,6 @@ The type of the index
|
||||
|
||||
***
|
||||
|
||||
### loss?
|
||||
|
||||
```ts
|
||||
optional loss: number;
|
||||
```
|
||||
|
||||
The KMeans loss value of the index,
|
||||
it is only present for vector indices.
|
||||
|
||||
***
|
||||
|
||||
### numIndexedRows
|
||||
|
||||
```ts
|
||||
|
||||
@@ -721,7 +721,7 @@ describe("When creating an index", () => {
|
||||
columns: ["vec"],
|
||||
});
|
||||
const stats = await tbl.indexStats("vec_idx");
|
||||
expect(stats?.loss).toBeDefined();
|
||||
expect(stats).toBeDefined();
|
||||
|
||||
// Search without specifying the column
|
||||
let rst = await tbl
|
||||
@@ -1150,7 +1150,6 @@ describe("When creating an index", () => {
|
||||
expect(stats?.distanceType).toBeUndefined();
|
||||
expect(stats?.indexType).toEqual("BTREE");
|
||||
expect(stats?.numIndices).toEqual(1);
|
||||
expect(stats?.loss).toBeUndefined();
|
||||
});
|
||||
|
||||
test("when getting stats on non-existent index", async () => {
|
||||
|
||||
@@ -838,9 +838,6 @@ pub struct IndexStatistics {
|
||||
pub distance_type: Option<String>,
|
||||
/// The number of parts this index is split into.
|
||||
pub num_indices: Option<u32>,
|
||||
/// The KMeans loss value of the index,
|
||||
/// it is only present for vector indices.
|
||||
pub loss: Option<f64>,
|
||||
}
|
||||
impl From<lancedb::index::IndexStatistics> for IndexStatistics {
|
||||
fn from(value: lancedb::index::IndexStatistics) -> Self {
|
||||
@@ -850,7 +847,6 @@ impl From<lancedb::index::IndexStatistics> for IndexStatistics {
|
||||
index_type: value.index_type.to_string(),
|
||||
distance_type: value.distance_type.map(|d| d.to_string()),
|
||||
num_indices: value.num_indices,
|
||||
loss: value.loss,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -5637,8 +5637,6 @@ class IndexStatistics:
|
||||
The distance type used by the index.
|
||||
num_indices: Optional[int]
|
||||
The number of parts the index is split into.
|
||||
loss: Optional[float]
|
||||
The KMeans loss for the index, for only vector indices.
|
||||
"""
|
||||
|
||||
num_indexed_rows: int
|
||||
@@ -5658,7 +5656,6 @@ class IndexStatistics:
|
||||
]
|
||||
distance_type: Optional[Literal["l2", "cosine", "dot"]] = None
|
||||
num_indices: Optional[int] = None
|
||||
loss: Optional[float] = None
|
||||
|
||||
# This exists for backwards compatibility with an older API, which returned
|
||||
# a dictionary instead of a class.
|
||||
|
||||
@@ -226,7 +226,6 @@ async def test_create_vector_index(some_table: AsyncTable):
|
||||
assert stats.num_indexed_rows == await some_table.count_rows()
|
||||
assert stats.num_unindexed_rows == 0
|
||||
assert stats.num_indices == 1
|
||||
assert stats.loss >= 0.0
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@@ -250,7 +249,6 @@ async def test_create_4bit_ivfpq_index(some_table: AsyncTable):
|
||||
assert stats.num_indexed_rows == await some_table.count_rows()
|
||||
assert stats.num_unindexed_rows == 0
|
||||
assert stats.num_indices == 1
|
||||
assert stats.loss >= 0.0
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
|
||||
@@ -711,10 +711,6 @@ impl Table {
|
||||
dict.set_item("num_indices", num_indices)?;
|
||||
}
|
||||
|
||||
if let Some(loss) = stats.loss {
|
||||
dict.set_item("loss", loss)?;
|
||||
}
|
||||
|
||||
Ok(Some(dict.unbind()))
|
||||
})
|
||||
} else {
|
||||
|
||||
@@ -372,7 +372,6 @@ pub(crate) struct IndexMetadata {
|
||||
pub metric_type: Option<DistanceType>,
|
||||
// Sometimes the index type is provided at this level.
|
||||
pub index_type: Option<IndexType>,
|
||||
pub loss: Option<f64>,
|
||||
}
|
||||
|
||||
// This struct is used to deserialize the JSON data returned from the Lance API
|
||||
@@ -404,6 +403,4 @@ pub struct IndexStatistics {
|
||||
pub distance_type: Option<DistanceType>,
|
||||
/// The number of parts this index is split into.
|
||||
pub num_indices: Option<u32>,
|
||||
/// The loss value used by the index.
|
||||
pub loss: Option<f64>,
|
||||
}
|
||||
|
||||
@@ -4121,7 +4121,6 @@ mod tests {
|
||||
index_type: IndexType::IvfPq,
|
||||
distance_type: Some(DistanceType::L2),
|
||||
num_indices: None,
|
||||
loss: None,
|
||||
};
|
||||
assert_eq!(indices, expected);
|
||||
|
||||
|
||||
@@ -3019,20 +3019,12 @@ impl BaseTable for NativeTable {
|
||||
.ok_or_else(|| Error::InvalidInput {
|
||||
message: "index statistics was missing index type".to_string(),
|
||||
})?;
|
||||
let loss = stats
|
||||
.indices
|
||||
.iter()
|
||||
.map(|index| index.loss.unwrap_or_default())
|
||||
.sum::<f64>();
|
||||
|
||||
let loss = first_index.loss.map(|first_loss| first_loss + loss);
|
||||
Ok(Some(IndexStatistics {
|
||||
num_indexed_rows: stats.num_indexed_rows,
|
||||
num_unindexed_rows: stats.num_unindexed_rows,
|
||||
index_type,
|
||||
distance_type: first_index.metric_type,
|
||||
num_indices: stats.num_indices,
|
||||
loss,
|
||||
}))
|
||||
}
|
||||
|
||||
@@ -3435,7 +3427,6 @@ mod tests {
|
||||
assert_eq!(stats.num_unindexed_rows, 0);
|
||||
assert_eq!(stats.index_type, crate::index::IndexType::IvfPq);
|
||||
assert_eq!(stats.distance_type, Some(crate::DistanceType::L2));
|
||||
assert!(stats.loss.is_some());
|
||||
|
||||
table.drop_index(index_name).await.unwrap();
|
||||
assert_eq!(table.list_indices().await.unwrap().len(), 0);
|
||||
|
||||
Reference in New Issue
Block a user