Merge remote-tracking branch 'refs/remotes/origin/dev' into dev_zdy_1204_neo4j

Author: wustzdy

docker/requirements.txt

@@ -160,4 +160,3 @@ xlrd==2.0.2
 xlsxwriter==3.2.5
 prometheus-client==0.23.1
 pymilvus==2.5.12
-langchain-text-splitters==1.0.0

examples/mem_scheduler/memos_w_scheduler.py

@@ -13,15 +13,15 @@
 from memos.mem_cube.general import GeneralMemCube
 from memos.mem_os.main import MOS
 from memos.mem_scheduler.general_scheduler import GeneralScheduler
-from memos.mem_scheduler.schemas.general_schemas import (
-    ADD_LABEL,
-    ANSWER_LABEL,
-    MEM_ARCHIVE_LABEL,
-    MEM_ORGANIZE_LABEL,
-    MEM_UPDATE_LABEL,
-    QUERY_LABEL,
-)
 from memos.mem_scheduler.schemas.message_schemas import ScheduleLogForWebItem
+from memos.mem_scheduler.schemas.task_schemas import (
+    ADD_TASK_LABEL,
+    ANSWER_TASK_LABEL,
+    MEM_ARCHIVE_TASK_LABEL,
+    MEM_ORGANIZE_TASK_LABEL,
+    MEM_UPDATE_TASK_LABEL,
+    QUERY_TASK_LABEL,
+)
 from memos.mem_scheduler.utils.filter_utils import transform_name_to_key
 
 
@@ -118,24 +118,24 @@ def _first_content() -> str:
             return memcube_content[0].get("content", "") or content
         return content
 
-    if label in ("addMessage", QUERY_LABEL, ANSWER_LABEL):
+    if label in ("addMessage", QUERY_TASK_LABEL, ANSWER_TASK_LABEL):
         target_cube = cube_display.replace("MemCube", "")
         title = _format_title(item.timestamp, f"addMessages to {target_cube} MemCube")
         return title, _truncate_with_rules(_first_content())
 
-    if label in ("addMemory", ADD_LABEL):
+    if label in ("addMemory", ADD_TASK_LABEL):
         title = _format_title(item.timestamp, f"{cube_display} added {memory_len} memories")
         return title, _truncate_with_rules(_first_content())
 
-    if label in ("updateMemory", MEM_UPDATE_LABEL):
+    if label in ("updateMemory", MEM_UPDATE_TASK_LABEL):
         title = _format_title(item.timestamp, f"{cube_display} updated {memory_len} memories")
         return title, _truncate_with_rules(_first_content())
 
-    if label in ("archiveMemory", MEM_ARCHIVE_LABEL):
+    if label in ("archiveMemory", MEM_ARCHIVE_TASK_LABEL):
         title = _format_title(item.timestamp, f"{cube_display} archived {memory_len} memories")
         return title, _truncate_with_rules(_first_content())
 
-    if label in ("mergeMemory", MEM_ORGANIZE_LABEL):
+    if label in ("mergeMemory", MEM_ORGANIZE_TASK_LABEL):
         title = _format_title(item.timestamp, f"{cube_display} merged {memory_len} memories")
         merged = [c for c in memcube_content if c.get("type") == "merged"]
         post = [c for c in memcube_content if c.get("type") == "postMerge"]

examples/mem_scheduler/redis_example.py

@@ -9,8 +9,8 @@
 from memos.configs.mem_scheduler import SchedulerConfigFactory
 from memos.mem_cube.general import GeneralMemCube
 from memos.mem_scheduler.scheduler_factory import SchedulerFactory
-from memos.mem_scheduler.schemas.general_schemas import QUERY_LABEL
 from memos.mem_scheduler.schemas.message_schemas import ScheduleMessageItem
+from memos.mem_scheduler.schemas.task_schemas import QUERY_TASK_LABEL
 
 
 if TYPE_CHECKING:
@@ -55,7 +55,7 @@ def service_run():
         message_item = ScheduleMessageItem(
             user_id=user_id,
             mem_cube_id="mem_cube_2",
-            label=QUERY_LABEL,
+            label=QUERY_TASK_LABEL,
             mem_cube=mem_cube,
             content=query,
             timestamp=datetime.now(),

examples/mem_scheduler/try_schedule_modules.py

@@ -14,7 +14,7 @@
 from memos.mem_cube.general import GeneralMemCube
 from memos.mem_scheduler.analyzer.mos_for_test_scheduler import MOSForTestScheduler
 from memos.mem_scheduler.general_scheduler import GeneralScheduler
-from memos.mem_scheduler.schemas.general_schemas import (
+from memos.mem_scheduler.schemas.task_schemas import (
     NOT_APPLICABLE_TYPE,
 )
 

src/memos/api/handlers/chat_handler.py

@@ -30,11 +30,11 @@
     prepare_reference_data,
     process_streaming_references_complete,
 )
-from memos.mem_scheduler.schemas.general_schemas import (
-    ANSWER_LABEL,
-    QUERY_LABEL,
-)
 from memos.mem_scheduler.schemas.message_schemas import ScheduleMessageItem
+from memos.mem_scheduler.schemas.task_schemas import (
+    ANSWER_TASK_LABEL,
+    QUERY_TASK_LABEL,
+)
 from memos.templates.mos_prompts import (
     FURTHER_SUGGESTION_PROMPT,
     get_memos_prompt,
@@ -244,7 +244,7 @@ def generate_chat_response() -> Generator[str, None, None]:
                         user_id=chat_req.user_id,
                         mem_cube_id=scheduler_cube_id,
                         query=chat_req.query,
-                        label=QUERY_LABEL,
+                        label=QUERY_TASK_LABEL,
                     )
                     # Extract memories from search results
                     memories_list = []
@@ -400,6 +400,7 @@ def generate_chat_response() -> Generator[str, None, None]:
                         include_preference=chat_req.include_preference,
                         pref_top_k=chat_req.pref_top_k,
                         filter=chat_req.filter,
+                        playground_search_goal_parser=True,
                     )
 
                     search_response = self.search_handler.handle_search_memories(search_req)
@@ -422,7 +423,7 @@ def generate_chat_response() -> Generator[str, None, None]:
                         user_id=chat_req.user_id,
                         mem_cube_id=scheduler_cube_id,
                         query=chat_req.query,
-                        label=QUERY_LABEL,
+                        label=QUERY_TASK_LABEL,
                     )
                     # Extract memories from search results
                     memories_list = []
@@ -1033,7 +1034,7 @@ async def _post_chat_processing(
 
             # Send answer to scheduler
             self._send_message_to_scheduler(
-                user_id=user_id, mem_cube_id=cube_id, query=clean_response, label=ANSWER_LABEL
+                user_id=user_id, mem_cube_id=cube_id, query=clean_response, label=ANSWER_TASK_LABEL
             )
 
             self.logger.info(f"Post-chat processing completed for user {user_id}")

src/memos/api/product_models.py

@@ -374,6 +374,9 @@ class APISearchRequest(BaseRequest):
         ),
     )
 
+    # TODO: tmp field for playground search goal parser, will be removed later
+    playground_search_goal_parser: bool = Field(False, description="Playground search goal parser")
+
     # ==== Context ====
     chat_history: MessageList | None = Field(
         None,

src/memos/configs/mem_reader.py

@@ -1,7 +1,7 @@
 from datetime import datetime
 from typing import Any, ClassVar
 
-from pydantic import Field, field_validator, model_validator
+from pydantic import ConfigDict, Field, field_validator, model_validator
 
 from memos.configs.base import BaseConfig
 from memos.configs.chunker import ChunkerConfigFactory
@@ -44,6 +44,9 @@ def parse_datetime(cls, value):
 class SimpleStructMemReaderConfig(BaseMemReaderConfig):
     """SimpleStruct MemReader configuration class."""
 
+    # Allow passing additional fields without raising validation errors
+    model_config = ConfigDict(extra="allow", strict=True)
+
 
 class MultiModalStructMemReaderConfig(BaseMemReaderConfig):
     """MultiModalStruct MemReader configuration class."""

src/memos/embedders/universal_api.py

@@ -4,7 +4,7 @@
 from memos.configs.embedder import UniversalAPIEmbedderConfig
 from memos.embedders.base import BaseEmbedder
 from memos.log import get_logger
-from memos.utils import timed
+from memos.utils import timed_with_status
 
 
 logger = get_logger(__name__)
@@ -30,8 +30,7 @@ def __init__(self, config: UniversalAPIEmbedderConfig):
         else:
             raise ValueError(f"Embeddings unsupported provider: {self.provider}")
 
-    @timed(
-        log=True,
+    @timed_with_status(
         log_prefix="model_timed_embedding",
         log_extra_args={"model_name_or_path": "text-embedding-3-large"},
     )

src/memos/llms/openai.py

@@ -12,7 +12,7 @@
 from memos.llms.utils import remove_thinking_tags
 from memos.log import get_logger
 from memos.types import MessageList
-from memos.utils import timed
+from memos.utils import timed_with_status
 
 
 logger = get_logger(__name__)
@@ -28,7 +28,7 @@ def __init__(self, config: OpenAILLMConfig):
         )
         logger.info("OpenAI LLM instance initialized")
 
-    @timed(log=True, log_prefix="OpenAI LLM", log_args=["model_name_or_path"])
+    @timed_with_status(log_prefix="OpenAI LLM", log_args=["model_name_or_path"])
     def generate(self, messages: MessageList, **kwargs) -> str:
         """Generate a response from OpenAI LLM, optionally overriding generation params."""
         response = self.client.chat.completions.create(
@@ -55,7 +55,7 @@ def generate(self, messages: MessageList, **kwargs) -> str:
             return reasoning_content + response_content
         return response_content
 
-    @timed(log=True, log_prefix="OpenAI LLM", log_args=["model_name_or_path"])
+    @timed_with_status(log_prefix="OpenAI LLM", log_args=["model_name_or_path"])
     def generate_stream(self, messages: MessageList, **kwargs) -> Generator[str, None, None]:
         """Stream response from OpenAI LLM with optional reasoning support."""
         if kwargs.get("tools"):

src/memos/mem_feedback/feedback.py

@@ -17,7 +17,7 @@
 from memos.mem_feedback.base import BaseMemFeedback
 from memos.mem_feedback.utils import should_keep_update, split_into_chunks
 from memos.mem_reader.factory import MemReaderFactory
-from memos.mem_reader.simple_struct import detect_lang
+from memos.mem_reader.read_multi_modal import detect_lang
 from memos.memories.textual.item import TextualMemoryItem, TreeNodeTextualMemoryMetadata
 from memos.memories.textual.tree_text_memory.organize.manager import (
     MemoryManager,