From cc9473a94aeefb04ec48a0ab01aac73b10b421cc Mon Sep 17 00:00:00 2001
From: Weston Pace <weston.pace@gmail.com>
Date: Thu, 1 Feb 2024 15:06:00 -0800
Subject: [PATCH] docs: add cleanup_old_versions and compact_files to `Table`
 for documentation purposes (#900)

Closes #819
---
 python/lancedb/remote/table.py | 12 ++++++++
 python/lancedb/table.py        | 51 ++++++++++++++++++++++++++++++++--
 2 files changed, 61 insertions(+), 2 deletions(-)

diff --git a/python/lancedb/remote/table.py b/python/lancedb/remote/table.py
index a313d2c9..e751bcbb 100644
--- a/python/lancedb/remote/table.py
+++ b/python/lancedb/remote/table.py
@@ -359,6 +359,18 @@ class RemoteTable(Table):
         payload = {"predicate": where, "updates": updates}
         self._conn._client.post(f"/v1/table/{self._name}/update/", data=payload)
 
+    def cleanup_old_versions(self, *_):
+        """cleanup_old_versions() is not supported on the LanceDB cloud"""
+        raise NotImplementedError(
+            "cleanup_old_versions() is not supported on the LanceDB cloud"
+        )
+
+    def compact_files(self, *_):
+        """compact_files() is not supported on the LanceDB cloud"""
+        raise NotImplementedError(
+            "compact_files() is not supported on the LanceDB cloud"
+        )
+
 
 def add_index(tbl: pa.Table, i: int) -> pa.Table:
     return tbl.add_column(
diff --git a/python/lancedb/table.py b/python/lancedb/table.py
index 6e433425..56638d81 100644
--- a/python/lancedb/table.py
+++ b/python/lancedb/table.py
@@ -590,6 +590,52 @@ class Table(ABC):
         """
         raise NotImplementedError
 
+    @abstractmethod
+    def cleanup_old_versions(
+        self,
+        older_than: Optional[timedelta] = None,
+        *,
+        delete_unverified: bool = False,
+    ) -> CleanupStats:
+        """
+        Clean up old versions of the table, freeing disk space.
+
+        Note: This function is not available in LanceDb Cloud (since LanceDb
+        Cloud manages cleanup for you automatically)
+
+        Parameters
+        ----------
+        older_than: timedelta, default None
+            The minimum age of the version to delete. If None, then this defaults
+            to two weeks.
+        delete_unverified: bool, default False
+            Because they may be part of an in-progress transaction, files newer
+            than 7 days old are not deleted by default. If you are sure that
+            there are no in-progress transactions, then you can set this to True
+            to delete all files older than `older_than`.
+
+        Returns
+        -------
+        CleanupStats
+            The stats of the cleanup operation, including how many bytes were
+            freed.
+        """
+
+    @abstractmethod
+    def compact_files(self, *args, **kwargs):
+        """
+        Run the compaction process on the table.
+
+        Note: This function is not available in LanceDb Cloud (since LanceDb
+        Cloud manages compaction for you automatically)
+
+        This can be run after making several small appends to optimize the table
+        for faster reads.
+
+        Arguments are passed onto :meth:`lance.dataset.DatasetOptimizer.compact_files`.
+        For most cases, the default should be fine.
+        """
+
 
 class LanceTable(Table):
     """
@@ -1314,8 +1360,9 @@ class LanceTable(Table):
         This can be run after making several small appends to optimize the table
         for faster reads.
 
-        Arguments are passed onto :meth:`lance.dataset.DatasetOptimizer.compact_files`.
-        For most cases, the default should be fine.
+        Arguments are passed onto `lance.dataset.DatasetOptimizer.compact_files`.
+         (see Lance documentation for more details) For most cases, the default
+        should be fine.
         """
         return self.to_lance().optimize.compact_files(*args, **kwargs)