From 5c87f132de541c0c43a5b2d5f878d3b0d67a1a5c Mon Sep 17 00:00:00 2001
From: Kumar Saurabh Arora <kuarora@meta.com>
Date: Thu, 22 Aug 2024 10:44:55 -0700
Subject: [PATCH] Add sampling fields to dataset descriptor (#3782)

Summary:
Pull Request resolved: https://github.com/facebookresearch/faiss/pull/3782

Fields sampling_column and sampling_rate are added to dataset descriptor for supporting sampling in dataset readers.

Reviewed By: satymish

Differential Revision: D61569067

fbshipit-source-id: e5db9957538b033bbef4b7662154411b9044d1f8
---
 benchs/bench_fw/descriptors.py | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/benchs/bench_fw/descriptors.py b/benchs/bench_fw/descriptors.py
index a553da5896..a9bae2a1ba 100644
--- a/benchs/bench_fw/descriptors.py
+++ b/benchs/bench_fw/descriptors.py
@@ -80,6 +80,11 @@ class DatasetDescriptor:
 
     embedding_column: Optional[str] = None
 
+    sampling_rate: Optional[float] = None
+
+    # sampling column for xdb
+    sampling_column: Optional[str] = None
+
     def __hash__(self):
         return hash(self.get_filename())