youngkingdom/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-05-05 01:48:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: Add summary index for knowledge. (#31625)

Browse Source 
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
2026-01-29 13:47:35 +08:00
committed by GitHub
parent 5ce3a04a2c
commit c2473d85dc
51 changed files with 3797 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
api/core/indexing_runner.py
View File

@ -311,14 +311,18 @@ class IndexingRunner:
qa_preview_texts: list[QAPreviewDetail] = []
total_segments = 0
# doc_form represents the segmentation method (general, parent-child, QA)
index_type = doc_form
index_processor = IndexProcessorFactory(index_type).init_index_processor()
# one extract_setting is one source document
for extract_setting in extract_settings:
# extract
processing_rule = DatasetProcessRule(
mode=tmp_processing_rule["mode"], rules=json.dumps(tmp_processing_rule["rules"])
)
# Extract document content
text_docs = index_processor.extract(extract_setting, process_rule_mode=tmp_processing_rule["mode"])
# Cleaning and segmentation
documents = index_processor.transform(
text_docs,
current_user=None,
@ -361,6 +365,12 @@ class IndexingRunner:
if doc_form and doc_form == "qa_model":
return IndexingEstimate(total_segments=total_segments * 20, qa_preview=qa_preview_texts, preview=[])
# Generate summary preview
summary_index_setting = tmp_processing_rule.get("summary_index_setting")
if summary_index_setting and summary_index_setting.get("enable") and preview_texts:
preview_texts = index_processor.generate_summary_preview(tenant_id, preview_texts, summary_index_setting)
return IndexingEstimate(total_segments=total_segments, preview=preview_texts)
def _extract(