RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
Go agent-harnessagent-native-databaseagentic-aiagentic-retrievalagentic-searchaiai-agentscontext-enginecontext-engineeringcontext-managementharness-engineeringknowledge-compilationragretrieval-augmented-generationretrieval-harnesssearch-harness
Refactor: get rid of graphrag and raptor during task creation (#19194)
Wang Qi51da97784b65
diff --git a/api/db/services/task_service.py b/api/db/services/task_service.pyindex 7c14e3e652..f723d9c719 100644--- a/api/db/services/task_service.py+++ b/api/db/services/task_service.py@@ -218,6 +218,9 @@ class TaskService(CommonService):if not docs:return Nonedoc = docs[0]+ for config_key in ("parser_config", "kb_parser_config"):+ if isinstance(doc.get(config_key), dict):+ doc[config_key] = {key: value for key, value in doc[config_key].items() if key not in ("graphrag", "raptor")}msg = f"\n{datetime.now().strftime('%H:%M:%S')} Task has been received."prog = random.random() / 10.0diff --git a/rag/svr/task_executor.py b/rag/svr/task_executor.pyindex aada32fc38..ae5d3fa0f2 100644--- a/rag/svr/task_executor.py+++ b/rag/svr/task_executor.py@@ -1753,6 +1753,8 @@ async def handle_task():await asyncio.sleep(5)return+ logging.info(f"handle_task begin for task {json.dumps(task)}")+task_type = task["task_type"]pipeline_task_type = TASK_TYPE_TO_PIPELINE_TASK_TYPE.get(task_type, PipelineTaskType.PARSE) or PipelineTaskType.PARSEtask_id = task["id"]