youngkingdom/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-05-03 17:08:03 +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

2
api/controllers/service_api/dataset/dataset.py
View File

@ -46,6 +46,7 @@ class DatasetCreatePayload(BaseModel):
retrieval_model: RetrievalModel | None = None
embedding_model: str | None = None
embedding_model_provider: str | None = None
summary_index_setting: dict | None = None
class DatasetUpdatePayload(BaseModel):
@ -217,6 +218,7 @@ class DatasetListApi(DatasetApiResource):
embedding_model_provider=payload.embedding_model_provider,
embedding_model_name=payload.embedding_model,
retrieval_model=payload.retrieval_model,
summary_index_setting=payload.summary_index_setting,
)
except services.errors.dataset.DatasetNameDuplicateError:
raise DatasetNameDuplicateError()

21
api/controllers/service_api/dataset/document.py
View File

@ -45,6 +45,7 @@ from services.entities.knowledge_entities.knowledge_entities import (
Segmentation,
)
from services.file_service import FileService
from services.summary_index_service import SummaryIndexService
class DocumentTextCreatePayload(BaseModel):
@ -508,6 +509,12 @@ class DocumentListApi(DatasetApiResource):
)
documents = paginated_documents.items
DocumentService.enrich_documents_with_summary_index_status(
documents=documents,
dataset=dataset,
tenant_id=tenant_id,
)
response = {
"data": marshal(documents, document_fields),
"has_more": len(documents) == query_params.limit,
@ -612,6 +619,16 @@ class DocumentApi(DatasetApiResource):
if metadata not in self.METADATA_CHOICES:
raise InvalidMetadataError(f"Invalid metadata value: {metadata}")
# Calculate summary_index_status if needed
summary_index_status = None
has_summary_index = dataset.summary_index_setting and dataset.summary_index_setting.get("enable") is True
if has_summary_index and document.need_summary is True:
summary_index_status = SummaryIndexService.get_document_summary_index_status(
document_id=document_id,
dataset_id=dataset_id,
tenant_id=tenant_id,
)
if metadata == "only":
response = {"id": document.id, "doc_type": document.doc_type, "doc_metadata": document.doc_metadata_details}
elif metadata == "without":
@ -646,6 +663,8 @@ class DocumentApi(DatasetApiResource):
"display_status": document.display_status,
"doc_form": document.doc_form,
"doc_language": document.doc_language,
"summary_index_status": summary_index_status,
"need_summary": document.need_summary if document.need_summary is not None else False,
}
else:
dataset_process_rules = DatasetService.get_process_rules(dataset_id)
@ -681,6 +700,8 @@ class DocumentApi(DatasetApiResource):
"display_status": document.display_status,
"doc_form": document.doc_form,
"doc_language": document.doc_language,
"summary_index_status": summary_index_status,
"need_summary": document.need_summary if document.need_summary is not None else False,
}
return response