From c18aa84d4c0310b4f37df7c441681fc40b79153d Mon Sep 17 00:00:00 2001
From: Andrei Fajardo <92402603+nerdai@users.noreply.github.com>
Date: Thu, 22 Feb 2024 17:37:09 -0500
Subject: [PATCH] [FIX] - SemanticSplitterNodeParser (#11295)
---
.../llama_index/core/node_parser/text/semantic_splitter.py | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/llama-index-core/llama_index/core/node_parser/text/semantic_splitter.py b/llama-index-core/llama_index/core/node_parser/text/semantic_splitter.py
index e5054ac8cc..6e4760a7b5 100644
--- a/llama-index-core/llama_index/core/node_parser/text/semantic_splitter.py
+++ b/llama-index-core/llama_index/core/node_parser/text/semantic_splitter.py
@@ -227,13 +227,11 @@ class SemanticSplitterNodeParser(NodeParser):
start_index = 0
for index in indices_above_threshold:
- end_index = index - 1
-
- group = sentences[start_index : end_index + 1]
+ group = sentences[start_index : index + 1]
combined_text = "".join([d["sentence"] for d in group])
chunks.append(combined_text)
- start_index = index
+ start_index = index + 1
if start_index < len(sentences):
combined_text = "".join(
--
GitLab