fix document retry

api/services/dataset_service.py

@@ -543,24 +543,24 @@ class DatasetService:
         """
         if dataset.runtime_mode != "rag_pipeline":
             return
-            
+
         pipeline = db.session.query(Pipeline).filter_by(id=dataset.pipeline_id).first()
         if not pipeline:
             return
-            
+
         try:
             rag_pipeline_service = RagPipelineService()
             published_workflow = rag_pipeline_service.get_published_workflow(pipeline)
             draft_workflow = rag_pipeline_service.get_draft_workflow(pipeline)
-            
+
             # update knowledge nodes
             def update_knowledge_nodes(workflow_graph: str) -> str:
                 """Update knowledge-index nodes in workflow graph."""
                 data: dict[str, Any] = json.loads(workflow_graph)
-                    
+
                 nodes = data.get("nodes", [])
                 updated = False
-                
+
                 for node in nodes:
                     if node.get("data", {}).get("type") == "knowledge-index":
                         try:
@@ -576,12 +576,12 @@ class DatasetService:
                         except Exception:
                             logging.exception("Failed to update knowledge node")
                             continue
-                
+
                 if updated:
                     data["nodes"] = nodes
                     return json.dumps(data)
                 return workflow_graph
-            
+
             # Update published workflow
             if published_workflow:
                 updated_graph = update_knowledge_nodes(published_workflow.graph)
@@ -602,17 +602,17 @@ class DatasetService:
                         marked_comment="",
                     )
                     db.session.add(workflow)
-            
+
             # Update draft workflow
             if draft_workflow:
                 updated_graph = update_knowledge_nodes(draft_workflow.graph)
                 if updated_graph != draft_workflow.graph:
                     draft_workflow.graph = updated_graph
                     db.session.add(draft_workflow)
-            
+
             # Commit all changes in one transaction
             db.session.commit()
-            
+
         except Exception:
             logging.exception("Failed to update pipeline knowledge base node data")
             db.session.rollback()
@@ -1360,7 +1360,7 @@ class DocumentService:
             redis_client.setex(retry_indexing_cache_key, 600, 1)
         # trigger async task
         document_ids = [document.id for document in documents]
-        retry_document_indexing_task.delay(dataset_id, document_ids)
+        retry_document_indexing_task.delay(dataset_id, document_ids, current_user.id)
 
     @staticmethod
     def sync_website_document(dataset_id: str, document: Document):

api/services/file_service.py

@@ -120,33 +120,31 @@ class FileService:
 
         return file_size <= file_size_limit
 
-    def upload_text(self, text: str, text_name: str) -> UploadFile:
-        assert isinstance(current_user, Account)
-        assert current_user.current_tenant_id is not None
+    def upload_text(self, text: str, text_name: str, user_id: str, tenant_id: str) -> UploadFile:
 
         if len(text_name) > 200:
             text_name = text_name[:200]
         # user uuid as file name
         file_uuid = str(uuid.uuid4())
-        file_key = "upload_files/" + current_user.current_tenant_id + "/" + file_uuid + ".txt"
+        file_key = "upload_files/" + tenant_id + "/" + file_uuid + ".txt"
 
         # save file to storage
         storage.save(file_key, text.encode("utf-8"))
 
         # save file to db
         upload_file = UploadFile(
-            tenant_id=current_user.current_tenant_id,
+            tenant_id=tenant_id,
             storage_type=dify_config.STORAGE_TYPE,
             key=file_key,
             name=text_name,
             size=len(text),
             extension="txt",
             mime_type="text/plain",
-            created_by=current_user.id,
+            created_by=user_id,
             created_by_role=CreatorUserRole.ACCOUNT,
             created_at=naive_utc_now(),
             used=True,
-            used_by=current_user.id,
+            used_by=user_id,
             used_at=naive_utc_now(),
         )
 

api/services/rag_pipeline/rag_pipeline.py

@@ -5,8 +5,9 @@ import threading
 import time
 from collections.abc import Callable, Generator, Mapping, Sequence
 from datetime import UTC, datetime
-from typing import Any, Optional, cast
+from typing import Any, Optional, Union, cast
 from uuid import uuid4
+import uuid
 
 from flask_login import current_user
 from sqlalchemy import func, or_, select
@@ -14,6 +15,8 @@ from sqlalchemy.orm import Session, sessionmaker
 
 import contexts
 from configs import dify_config
+from core.app.apps.pipeline.pipeline_config_manager import PipelineConfigManager
+from core.app.apps.pipeline.pipeline_generator import PipelineGenerator
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.datasource.entities.datasource_entities import (
     DatasourceMessage,
@@ -54,7 +57,7 @@ from core.workflow.workflow_entry import WorkflowEntry
 from extensions.ext_database import db
 from libs.infinite_scroll_pagination import InfiniteScrollPagination
 from models.account import Account
-from models.dataset import Document, Pipeline, PipelineCustomizedTemplate, PipelineRecommendedPlugin  # type: ignore
+from models.dataset import Dataset, Document, DocumentPipelineExecutionLog, Pipeline, PipelineCustomizedTemplate, PipelineRecommendedPlugin  # type: ignore
 from models.enums import WorkflowRunTriggeredFrom
 from models.model import EndUser
 from models.workflow import (
@@ -1312,3 +1315,35 @@ class RagPipelineService:
             "installed_recommended_plugins": installed_plugin_list,
             "uninstalled_recommended_plugins": uninstalled_plugin_list,
         }
+
+    def retry_error_document(self, dataset: Dataset, document: Document, user: Union[Account, EndUser]):
+        """
+        Retry error document
+        """
+        document_pipeline_excution_log = db.session.query(DocumentPipelineExecutionLog).filter(
+            DocumentPipelineExecutionLog.document_id == document.id).first()
+        if not document_pipeline_excution_log:
+            raise ValueError("Document pipeline execution log not found")
+        pipeline = db.session.query(Pipeline).filter(Pipeline.id == document_pipeline_excution_log.pipeline_id).first()
+        if not pipeline:
+            raise ValueError("Pipeline not found")
+        # convert to app config
+        workflow = self.get_published_workflow(pipeline)
+        if not workflow:
+            raise ValueError("Workflow not found")
+        PipelineGenerator().generate(
+            pipeline=pipeline,
+            workflow=workflow,
+            user=user,
+            args={
+                "inputs": document_pipeline_excution_log.input_data,
+                "start_node_id": document_pipeline_excution_log.datasource_node_id,
+                "datasource_type": document_pipeline_excution_log.datasource_type,
+                "datasource_info_list": [json.loads(document_pipeline_excution_log.datasource_info)],
+            },
+            invoke_from=InvokeFrom.PUBLISHED,
+            streaming=False,
+            call_depth=0,
+            workflow_thread_pool_id=None,
+            is_retry=True,
+        )