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
Fix: get memory size cache rightly (#18370)
Lynn238b1aee7d50
diff --git a/api/db/joint_services/memory_message_service.py b/api/db/joint_services/memory_message_service.pyindex e1abfc7cfa..eed0b06d11 100644--- a/api/db/joint_services/memory_message_service.py+++ b/api/db/joint_services/memory_message_service.py@@ -229,7 +229,7 @@ async def embed_and_save(memory, message_list: list[dict], task_id: str = None):return False, error_msgnew_msg_size = sum([MessageService.calculate_message_size(m) for m in message_list])- current_memory_size = get_memory_size_cache(memory.tenant_id, memory.id)+ current_memory_size = get_memory_size_cache(memory.id, memory.tenant_id)if new_msg_size + current_memory_size > memory.memory_size:size_to_delete = current_memory_size + new_msg_size - memory.memory_sizeif memory.forgetting_policy == "FIFO":