From ceede4667312e7e295c7dfaf8a9e6570b45bd143 Mon Sep 17 00:00:00 2001 From: Marco Vinciguerra Date: Tue, 24 Sep 2024 15:27:20 +0200 Subject: [PATCH] fix: parse_node --- scrapegraphai/nodes/parse_node.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scrapegraphai/nodes/parse_node.py b/scrapegraphai/nodes/parse_node.py index adc9d1b1..46e9c1d1 100644 --- a/scrapegraphai/nodes/parse_node.py +++ b/scrapegraphai/nodes/parse_node.py @@ -88,7 +88,7 @@ class ParseNode(BaseNode): link_urls, img_urls = self._extract_urls(docs_transformed.page_content, source) chunk_size = self.chunk_size - chunk_size = min(chunk_size - 500, int(chunk_size * 0.9)) + chunk_size = min(chunk_size - 500, int(chunk_size * 0.75)) if isinstance(docs_transformed, Document): chunks = split_text_into_chunks(text=docs_transformed.page_content,