youngkingdom/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-05-04 17:38:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix re-chunk document

Browse Source
This commit is contained in:
jyong
2025-09-16 16:05:01 +08:00
parent 610f0414db
commit 05aec66424
7 changed files with 50 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
api/core/app/apps/pipeline/pipeline_generator.py
View File

@ -72,7 +72,6 @@ class PipelineGenerator(BaseAppGenerator):
call_depth: int,
workflow_thread_pool_id: Optional[str],
is_retry: bool = False,
document_id: Optional[str] = None,
) -> Mapping[str, Any] | Generator[Mapping | str, None, None] | None: ...
@overload
@ -88,7 +87,6 @@ class PipelineGenerator(BaseAppGenerator):
call_depth: int,
workflow_thread_pool_id: Optional[str],
is_retry: bool = False,
document_id: Optional[str] = None,
) -> Mapping[str, Any]: ...
@overload
@ -104,7 +102,6 @@ class PipelineGenerator(BaseAppGenerator):
call_depth: int,
workflow_thread_pool_id: Optional[str],
is_retry: bool = False,
document_id: Optional[str] = None,
) -> Union[Mapping[str, Any], Generator[Mapping | str, None, None]]: ...
def generate(
@ -119,7 +116,6 @@ class PipelineGenerator(BaseAppGenerator):
call_depth: int = 0,
workflow_thread_pool_id: Optional[str] = None,
is_retry: bool = False,
documents: list[Document] = [],
) -> Union[Mapping[str, Any], Generator[Mapping | str, None, None], None]:
# Add null check for dataset
@ -138,7 +134,8 @@ class PipelineGenerator(BaseAppGenerator):
pipeline_config = PipelineConfigManager.get_pipeline_config(
pipeline=pipeline, workflow=workflow, start_node_id=start_node_id
)
if invoke_from == InvokeFrom.PUBLISHED and not is_retry:
documents: list[Document] = []
if invoke_from == InvokeFrom.PUBLISHED and not is_retry and not args.get("original_document_id"):
from services.dataset_service import DocumentService
for datasource_info in datasource_info_list:
position = DocumentService.get_documents_position(dataset.id)
@ -162,10 +159,9 @@ class PipelineGenerator(BaseAppGenerator):
rag_pipeline_invoke_entities = []
for i, datasource_info in enumerate(datasource_info_list):
workflow_run_id = str(uuid.uuid4())
document_id = None
if documents:
document_id = documents[i].id
document_id = args.get("original_document_id") or None
if invoke_from == InvokeFrom.PUBLISHED and not is_retry:
document_id = document_id or documents[i].id
document_pipeline_execution_log = DocumentPipelineExecutionLog(
document_id=document_id,
datasource_type=datasource_type,
@ -184,6 +180,7 @@ class PipelineGenerator(BaseAppGenerator):
datasource_type=datasource_type,
datasource_info=datasource_info,
dataset_id=dataset.id,
original_document_id=args.get("original_document_id"),
start_node_id=start_node_id,
batch=batch,
document_id=document_id,

1
api/core/app/apps/pipeline/pipeline_runner.py
View File

@ -122,6 +122,7 @@ class PipelineRunner(WorkflowBasedAppRunner):
workflow_id=app_config.workflow_id,
workflow_execution_id=self.application_generate_entity.workflow_execution_id,
document_id=self.application_generate_entity.document_id,
original_document_id=self.application_generate_entity.original_document_id,
batch=self.application_generate_entity.batch,
dataset_id=self.application_generate_entity.dataset_id,
datasource_type=self.application_generate_entity.datasource_type,