feat: remote index stats (#1702)

BREAKING CHANGE: the return value of `index_stats` method has changed
and all `index_stats` APIs now take index name instead of UUID. Also
several deprecated index statistics methods were removed.

* Removes deprecated methods for individual index statistics
* Aligns public `IndexStatistics` struct with API response from LanceDB
Cloud.
* Implements `index_stats` for remote Rust SDK and Python async API.

python/python/lancedb/table.py

@@ -2683,6 +2683,26 @@ class AsyncTable:
         """
         return await self._inner.list_indices()
 
+    async def index_stats(self, index_name: str) -> Optional[IndexStatistics]:
+        """
+        Retrieve statistics about an index
+
+        Parameters
+        ----------
+        index_name: str
+            The name of the index to retrieve statistics for
+
+        Returns
+        -------
+        IndexStatistics or None
+            The statistics about the index. Returns None if the index does not exist.
+        """
+        stats = await self._inner.index_stats(index_name)
+        if stats is None:
+            return None
+        else:
+            return IndexStatistics(**stats)
+
     async def uses_v2_manifest_paths(self) -> bool:
         """
         Check if the table is using the new v2 manifest paths.
@@ -2713,3 +2733,31 @@ class AsyncTable:
         to check if the table is already using the new path style.
         """
         await self._inner.migrate_manifest_paths_v2()
+
+
+@dataclass
+class IndexStatistics:
+    """
+    Statistics about an index.
+
+    Attributes
+    ----------
+    num_indexed_rows: int
+        The number of rows that are covered by this index.
+    num_unindexed_rows: int
+        The number of rows that are not covered by this index.
+    index_type: str
+        The type of index that was created.
+    distance_type: Optional[str]
+        The distance type used by the index.
+    num_indices: Optional[int]
+        The number of parts the index is split into.
+    """
+
+    num_indexed_rows: int
+    num_unindexed_rows: int
+    index_type: Literal[
+        "IVF_PQ", "IVF_HNSW_PQ", "IVF_HNSW_SQ", "FTS", "BTREE", "BITMAP", "LABEL_LIST"
+    ]
+    distance_type: Optional[Literal["l2", "cosine", "dot"]] = None
+    num_indices: Optional[int] = None

python/python/tests/test_index.py

@@ -66,6 +66,15 @@ async def test_create_bitmap_index(some_table: AsyncTable):
     # TODO: Fix via https://github.com/lancedb/lance/issues/2039
     # indices = await some_table.list_indices()
     # assert str(indices) == '[Index(Bitmap, columns=["id"])]'
+    indices = await some_table.list_indices()
+    assert len(indices) == 1
+    index_name = indices[0].name
+    stats = await some_table.index_stats(index_name)
+    assert stats.index_type == "BITMAP"
+    assert stats.distance_type is None
+    assert stats.num_indexed_rows == await some_table.count_rows()
+    assert stats.num_unindexed_rows == 0
+    assert stats.num_indices == 1
 
 
 @pytest.mark.asyncio
@@ -91,6 +100,14 @@ async def test_create_vector_index(some_table: AsyncTable):
     assert len(indices) == 1
     assert indices[0].index_type == "IvfPq"
     assert indices[0].columns == ["vector"]
+    assert indices[0].name == "vector_idx"
+
+    stats = await some_table.index_stats("vector_idx")
+    assert stats.index_type == "IVF_PQ"
+    assert stats.distance_type == "l2"
+    assert stats.num_indexed_rows == await some_table.count_rows()
+    assert stats.num_unindexed_rows == 0
+    assert stats.num_indices == 1
 
 
 @pytest.mark.asyncio