From b32b69c993839bd56995bf98704aafa919899c12 Mon Sep 17 00:00:00 2001
From: QianZhu <qian@lancedb.com>
Date: Thu, 29 Feb 2024 13:32:01 -0800
Subject: [PATCH] Add create scalar index to sdk (#1033)

---
 node/src/index.ts                     |  8 +++++--
 node/src/remote/index.ts              | 23 ++++++++++++++++---
 python/python/lancedb/remote/table.py | 32 +++++++++++++++++++++++----
 3 files changed, 54 insertions(+), 9 deletions(-)

diff --git a/node/src/index.ts b/node/src/index.ts
index 8dd48788..69aea280 100644
--- a/node/src/index.ts
+++ b/node/src/index.ts
@@ -341,6 +341,7 @@ export interface Table<T = number[]> {
    *
    * @param column The column to index
    * @param replace If false, fail if an index already exists on the column
+   * it is always set to true for remote connections
    *
    * Scalar indices, like vector indices, can be used to speed up scans.  A scalar
    * index can speed up scans that contain filter expressions on the indexed column.
@@ -384,7 +385,7 @@ export interface Table<T = number[]> {
    * await table.createScalarIndex('my_col')
    * ```
    */
-  createScalarIndex: (column: string, replace: boolean) => Promise<void>
+  createScalarIndex: (column: string, replace?: boolean) => Promise<void>
 
   /**
    * Returns the number of rows in this table.
@@ -914,7 +915,10 @@ export class LocalTable<T = number[]> implements Table<T> {
       })
   }
 
-  async createScalarIndex (column: string, replace: boolean): Promise<void> {
+  async createScalarIndex (column: string, replace?: boolean): Promise<void> {
+    if (replace === undefined) {
+      replace = true
+    }
     return tableCreateScalarIndex.call(this._tbl, column, replace)
   }
 
diff --git a/node/src/remote/index.ts b/node/src/remote/index.ts
index 56c3181d..6e6e590a 100644
--- a/node/src/remote/index.ts
+++ b/node/src/remote/index.ts
@@ -397,7 +397,7 @@ export class RemoteTable<T = number[]> implements Table<T> {
     }
 
     const column = indexParams.column ?? 'vector'
-    const indexType = 'vector' // only vector index is supported for remote connections
+    const indexType = 'vector'
     const metricType = indexParams.metric_type ?? 'L2'
     const indexCacheSize = indexParams.index_cache_size ?? null
 
@@ -420,8 +420,25 @@ export class RemoteTable<T = number[]> implements Table<T> {
     }
   }
 
-  async createScalarIndex (column: string, replace: boolean): Promise<void> {
-    throw new Error('Not implemented')
+  async createScalarIndex (column: string): Promise<void> {
+    const indexType = 'scalar'
+
+    const data = {
+      column,
+      index_type: indexType,
+      replace: true
+    }
+    const res = await this._client.post(
+      `/v1/table/${this._name}/create_scalar_index/`,
+      data
+    )
+    if (res.status !== 200) {
+      throw new Error(
+        `Server Error, status: ${res.status}, ` +
+          // eslint-disable-next-line @typescript-eslint/restrict-template-expressions
+          `message: ${res.statusText}: ${res.data}`
+      )
+    }
   }
 
   async countRows (): Promise<number> {
diff --git a/python/python/lancedb/remote/table.py b/python/python/lancedb/remote/table.py
index dafa2e2c..bbae9921 100644
--- a/python/python/lancedb/remote/table.py
+++ b/python/python/lancedb/remote/table.py
@@ -66,12 +66,36 @@ class RemoteTable(Table):
         """to_pandas() is not yet supported on LanceDB cloud."""
         return NotImplementedError("to_pandas() is not yet supported on LanceDB cloud.")
 
-    def create_scalar_index(self, *args, **kwargs):
-        """Creates a scalar index"""
-        return NotImplementedError(
-            "create_scalar_index() is not yet supported on LanceDB cloud."
+    def list_indices(self):
+        """List all the indices on the table"""
+        print(self._name)
+        resp = self._conn._client.post(f"/v1/table/{self._name}/index/list/")
+        return resp
+
+    def create_scalar_index(
+        self,
+        column: str,
+    ):
+        """Creates a scalar index
+        Parameters
+        ----------
+        column : str
+            The column to be indexed.  Must be a boolean, integer, float,
+            or string column.
+        """
+        index_type = "scalar"
+
+        data = {
+            "column": column,
+            "index_type": index_type,
+            "replace": True,
+        }
+        resp = self._conn._client.post(
+            f"/v1/table/{self._name}/create_scalar_index/", data=data
         )
 
+        return resp
+
     def create_index(
         self,
         metric="L2",