Refa: fake doc ID. (#10276)

### What problem does this PR solve?
#10273
### Type of change

- [x] Refactoring

api/apps/kb_app.py

@@ -24,7 +24,7 @@ from api.db.services.document_service import DocumentService, queue_raptor_o_gra
 from api.db.services.file2document_service import File2DocumentService
 from api.db.services.file_service import FileService
 from api.db.services.pipeline_operation_log_service import PipelineOperationLogService
-from api.db.services.task_service import TaskService
+from api.db.services.task_service import TaskService, GRAPH_RAPTOR_FAKE_DOC_ID
 from api.db.services.user_service import TenantService, UserTenantService
 from api.utils.api_utils import get_error_data_result, server_error_response, get_data_error_result, validate_request, not_allowed_parameters
 from api.utils import get_uuid
@@ -558,7 +558,7 @@ def run_graphrag():
             if not sample_document:
                 sample_document = document.to_dict()
 
-    task_id = queue_raptor_o_graphrag_tasks(doc=sample_document, ty="graphrag", priority=0, fake_doc_id="x", doc_ids=list(document_ids))
+    task_id = queue_raptor_o_graphrag_tasks(doc=sample_document, ty="graphrag", priority=0, fake_doc_id=GRAPH_RAPTOR_FAKE_DOC_ID, doc_ids=list(document_ids))
 
     if not KnowledgebaseService.update_by_id(kb.id, {"graphrag_task_id": task_id}):
         logging.warning(f"Cannot save graphrag_task_id for kb {kb_id}")

api/db/services/document_service.py

@@ -121,7 +121,7 @@ class DocumentService(CommonService):
                      orderby, desc, keywords, run_status, types, suffix):
         fields = cls.get_cls_model_fields()
         if keywords:
-            docs = cls.model.select(*[*fields, UserCanvas.title])\
+            docs = cls.model.select(*[*fields, UserCanvas.title.alias("pipeline_name")])\
                 .join(File2Document, on=(File2Document.document_id == cls.model.id))\
                 .join(File, on=(File.id == File2Document.file_id))\
                 .join(UserCanvas, on=(cls.model.pipeline_id == UserCanvas.id), join_type=JOIN.LEFT_OUTER)\
@@ -130,7 +130,7 @@ class DocumentService(CommonService):
                     (fn.LOWER(cls.model.name).contains(keywords.lower()))
                 )
         else:
-            docs = cls.model.select(*[*fields, UserCanvas.title])\
+            docs = cls.model.select(*[*fields, UserCanvas.title.alias("pipeline_name")])\
                 .join(File2Document, on=(File2Document.document_id == cls.model.id))\
                 .join(UserCanvas, on=(cls.model.pipeline_id == UserCanvas.id), join_type=JOIN.LEFT_OUTER)\
                 .join(File, on=(File.id == File2Document.file_id))\

api/db/services/pipeline_operation_log_service.py

@@ -25,6 +25,7 @@ from api.db.services.canvas_service import UserCanvasService
 from api.db.services.common_service import CommonService
 from api.db.services.document_service import DocumentService
 from api.db.services.knowledgebase_service import KnowledgebaseService
+from api.db.services.task_service import GRAPH_RAPTOR_FAKE_DOC_ID
 from api.utils import current_timestamp, datetime_format, get_uuid
 
 
@@ -88,7 +89,7 @@ class PipelineOperationLogService(CommonService):
         dsl = ""
         referred_document_id = document_id
 
-        if referred_document_id == "x" and fake_document_ids:
+        if referred_document_id == GRAPH_RAPTOR_FAKE_DOC_ID and fake_document_ids:
             referred_document_id = fake_document_ids[0]
         ok, document = DocumentService.get_by_id(referred_document_id)
         if not ok:
@@ -128,7 +129,7 @@ class PipelineOperationLogService(CommonService):
 
         log = dict(
             id=get_uuid(),
-            document_id=document_id,  # "x" or real document_id
+            document_id=document_id,  # GRAPH_RAPTOR_FAKE_DOC_ID or real document_id
             tenant_id=tenant_id,
             kb_id=document.kb_id,
             pipeline_id=pipeline_id,
@@ -168,7 +169,7 @@ class PipelineOperationLogService(CommonService):
         else:
             logs = cls.model.select(*fields).where(cls.model.kb_id == kb_id)
 
-        logs = logs.where(cls.model.document_id != "x")
+        logs = logs.where(cls.model.document_id != GRAPH_RAPTOR_FAKE_DOC_ID)
 
         if operation_status:
             logs = logs.where(cls.model.operation_status.in_(operation_status))
@@ -206,7 +207,7 @@ class PipelineOperationLogService(CommonService):
     @DB.connection_context()
     def get_dataset_logs_by_kb_id(cls, kb_id, page_number, items_per_page, orderby, desc, operation_status):
         fields = cls.get_dataset_logs_fields()
-        logs = cls.model.select(*fields).where((cls.model.kb_id == kb_id), (cls.model.document_id == "x"))
+        logs = cls.model.select(*fields).where((cls.model.kb_id == kb_id), (cls.model.document_id == GRAPH_RAPTOR_FAKE_DOC_ID))
 
         if operation_status:
             logs = logs.where(cls.model.operation_status.in_(operation_status))

api/db/services/task_service.py

@@ -36,6 +36,7 @@ from api import settings
 from rag.nlp import search
 
 CANVAS_DEBUG_DOC_ID = "dataflow_x"
+GRAPH_RAPTOR_FAKE_DOC_ID = "graph_raptor_x"
 
 def trim_header_by_lines(text: str, max_length) -> str:
     # Trim header text to maximum length while preserving line breaks

api/utils/api_utils.py

@@ -679,7 +679,9 @@ TimeoutException = Union[Type[BaseException], BaseException]
 OnTimeoutCallback = Union[Callable[..., Any], Coroutine[Any, Any, Any]]
 
 
-def timeout(seconds: float | int = None, attempts: int = 2, *, exception: Optional[TimeoutException] = None, on_timeout: Optional[OnTimeoutCallback] = None):
+def timeout(seconds: float | int | str = None, attempts: int = 2, *, exception: Optional[TimeoutException] = None, on_timeout: Optional[OnTimeoutCallback] = None):
+    if isinstance(seconds, str):
+        seconds = float(seconds)
     def decorator(func):
         @wraps(func)
         def wrapper(*args, **kwargs):