From 25b45d7ba05c7df127d51d1124656633e999fd0b Mon Sep 17 00:00:00 2001 From: CaptainB Date: Thu, 11 Dec 2025 16:21:50 +0800 Subject: [PATCH] chore: limit paragraph list to first 5 segments in get_details method --- .../impl/base_document_split_node.py | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/apps/application/flow/step_node/document_split_node/impl/base_document_split_node.py b/apps/application/flow/step_node/document_split_node/impl/base_document_split_node.py index 80b32f80b..9d32bb045 100644 --- a/apps/application/flow/step_node/document_split_node/impl/base_document_split_node.py +++ b/apps/application/flow/step_node/document_split_node/impl/base_document_split_node.py @@ -161,6 +161,18 @@ class BaseDocumentSplitNode(IDocumentSplitNode): return list(set(problem_list)) def get_details(self, index: int, **kwargs): + paragraph_list = self.context.get('paragraph_list', []) + # 每个文档保留前5个分段 + limited_paragraph_list = [] + for doc in paragraph_list: + if doc.get('paragraphs'): + doc_copy = doc.copy() + doc_copy['paragraphs'] = doc['paragraphs'][:5] + limited_paragraph_list.append(doc_copy) + else: + limited_paragraph_list.append(doc) + paragraph_list = limited_paragraph_list + return { 'name': self.node.properties.get('stepName'), "index": index, @@ -168,11 +180,11 @@ class BaseDocumentSplitNode(IDocumentSplitNode): 'type': self.node.type, 'status': self.status, 'err_message': self.err_message, - 'paragraph_list': self.context.get('paragraph_list', []), + 'paragraph_list': paragraph_list, 'limit': self.context.get('limit'), 'chunk_size': self.context.get('chunk_size'), 'with_filter': self.context.get('with_filter'), 'patterns': self.context.get('patterns'), 'split_strategy': self.context.get('split_strategy'), - 'document_list': self.context.get('document_list', []), + # 'document_list': self.context.get('document_list', []), }