Merge branch 'main' into changhiskhan/improve-index-docs

python/lancedb/query.py

@@ -24,6 +24,7 @@ class LanceQueryBuilder:
     """
 
     def __init__(self, table: "lancedb.table.LanceTable", query: np.ndarray):
+        self._metric = "L2"
         self._nprobes = 20
         self._refine_factor = None
         self._table = table
@@ -77,6 +78,21 @@ class LanceQueryBuilder:
         self._where = where
         return self
 
+    def metric(self, metric: str) -> LanceQueryBuilder:
+        """Set the distance metric to use.
+
+        Parameters
+        ----------
+        metric: str
+            The distance metric to use. By default "l2" is used.
+
+        Returns
+        -------
+        The LanceQueryBuilder object.
+        """
+        self._metric = metric
+        return self
+
     def nprobes(self, nprobes: int) -> LanceQueryBuilder:
         """Set the number of probes to use.
 
@@ -123,6 +139,7 @@ class LanceQueryBuilder:
                 "column": VECTOR_COLUMN_NAME,
                 "q": self._query,
                 "k": self._limit,
+                "metric": self._metric,
                 "nprobes": self._nprobes,
                 "refine_factor": self._refine_factor,
             },

python/lancedb/table.py

@@ -106,11 +106,14 @@ class LanceTable:
     def _dataset_uri(self) -> str:
         return os.path.join(self._conn.uri, f"{self.name}.lance")
 
-    def create_index(self, num_partitions=256, num_sub_vectors=96):
+    def create_index(self, metric="L2", num_partitions=256, num_sub_vectors=96):
         """Create an index on the table.
 
         Parameters
         ----------
+        metric: str, default "L2"
+            The distance metric to use when creating the index. Valid values are "L2" or "cosine".
+            L2 is euclidean distance.
         num_partitions: int
             The number of IVF partitions to use when creating the index.
             Default is 256.
@@ -121,6 +124,7 @@ class LanceTable:
         self._dataset.create_index(
             column=VECTOR_COLUMN_NAME,
             index_type="IVF_PQ",
+            metric=metric,
             num_partitions=num_partitions,
             num_sub_vectors=num_sub_vectors,
         )