From 0ea72245358171478726aaa95a1fcde69707e115 Mon Sep 17 00:00:00 2001
From: Jona Sassenhagen <jona.sassenhagen@datarobot.com>
Date: Tue, 11 Jul 2023 22:43:46 +0200
Subject: [PATCH] [Minor] Remove tagger from spacy sentencizer (#7534)

@svlandeg gave me a tip for how to improve a bit on
https://github.com/hwchase17/langchain/pull/7442 for some extra speed
and memory gains. The tagger isn't needed for sentencization, so can be
disabled too.
---
 langchain/text_splitter.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/langchain/text_splitter.py b/langchain/text_splitter.py
index 37de47f0fc..932d252a48 100644
--- a/langchain/text_splitter.py
+++ b/langchain/text_splitter.py
@@ -47,7 +47,7 @@ def _make_spacy_pipeline_for_splitting(pipeline: str) -> Any:  # avoid importing
         sentencizer = English()
         sentencizer.add_pipe("sentencizer")
     else:
-        sentencizer = spacy.load(pipeline, disable=["ner"])
+        sentencizer = spacy.load(pipeline, exclude=["ner", "tagger"])
     return sentencizer