fix: summary index bug (#31810)

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Jyong <76649700+JohnJyong@users.noreply.github.com>
Co-authored-by: zxhlyh <jasonapring2015@outlook.com>
Co-authored-by: Yansong Zhang <916125788@qq.com>
Co-authored-by: hj24 <mambahj24@gmail.com>
Co-authored-by: CodingOnStar <hanxujiang@dify.ai>
Co-authored-by: CodingOnStar <hanxujiang@dify.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
FFXN
2026-02-02 09:45:17 +08:00
committed by GitHub
parent 4f826b4641
commit 41177757e6
11 changed files with 137 additions and 9 deletions

View File

@ -49,11 +49,18 @@ class SummaryIndexService:
# Use lazy import to avoid circular import
from core.rag.index_processor.processor.paragraph_index_processor import ParagraphIndexProcessor
# Get document language to ensure summary is generated in the correct language
# This is especially important for image-only chunks where text is empty or minimal
document_language = None
if segment.document and segment.document.doc_language:
document_language = segment.document.doc_language
summary_content, usage = ParagraphIndexProcessor.generate_summary(
tenant_id=dataset.tenant_id,
text=segment.content,
summary_index_setting=summary_index_setting,
segment_id=segment.id,
document_language=document_language,
)
if not summary_content:
@ -558,6 +565,9 @@ class SummaryIndexService:
)
session.add(summary_record)
# Commit the batch created records
session.commit()
@staticmethod
def update_summary_record_error(
segment: DocumentSegment,
@ -762,7 +772,6 @@ class SummaryIndexService:
dataset=dataset,
status="not_started",
)
session.commit() # Commit initial records
summary_records = []