Feat/merge dev (#374)

fridayL · CaralHsi · CarltonXiang · web-flow · commit e1de4adf3351 · 2025-10-20T17:15:22.000+08:00
* fix: format (#341) * change version to 1.1.0 * change: version to v1.1.1 * feat: add memory size in product api (#348) * feat: add memory size config in product api * fix: memory_size config bug * Fix/remove bug (#356) * fix: nebula search bug * fix: nebula search bug * fix: auto create bug * feat: add single-db-only assertion * feat: make count_nodes support optional memory_type filtering * fix: dim_field when filter non-embedding nodes * feat: add optional whether include embedding when export graph * fix[WIP]: remove oldest memory update * feat: modify nebula search embedding efficiency * fix: modify nebula remove old memory * Fix/api client (#357) * fix: api client get_message models * fix: format error --------- Co-authored-by: chunyu li <78344051+fridayL@users.noreply.github.com> Co-authored-by: harvey_xiang <harvey_xiang22@163.com> Co-authored-by: CaralHsi <caralhsi@gmail.com> * fix: remove old mem (#361) * feat: only single-db mode in nebula now; modify index gql for better efficiency (#363) * feat: only single-db mode in nebula now; modify index gql for better effciency * feat: delete multi-db nebula example * fix:code ci * fix:code ci * fix: nebular bug --------- Co-authored-by: CaralHsi <caralhsi@gmail.com> Co-authored-by: HarveyXiang <harvey_xiang@163.com> Co-authored-by: harvey_xiang <harvey_xiang22@163.com>
diff --git a/examples/basic_modules/nebular_example.py b/examples/basic_modules/nebular_example.py
@@ -52,56 +52,6 @@ def embed_memory_item(memory: str) -> list[float]:
     return embedding_list
 
 
-def example_multi_db(db_name: str = "paper"):
-    # Step 1: Build factory config
-    config = GraphDBConfigFactory(
-        backend="nebular",
-        config={
-            "uri": json.loads(os.getenv("NEBULAR_HOSTS", "localhost")),
-            "user": os.getenv("NEBULAR_USER", "root"),
-            "password": os.getenv("NEBULAR_PASSWORD", "xxxxxx"),
-            "space": db_name,
-            "use_multi_db": True,
-            "auto_create": True,
-            "embedding_dimension": embedder_dimension,
-        },
-    )
-
-    # Step 2: Instantiate the graph store
-    graph = GraphStoreFactory.from_config(config)
-    graph.clear()
-
-    # Step 3: Create topic node
-    topic = TextualMemoryItem(
-        memory="This research addresses long-term multi-UAV navigation for energy-efficient communication coverage.",
-        metadata=TreeNodeTextualMemoryMetadata(
-            memory_type="LongTermMemory",
-            key="Multi-UAV Long-Term Coverage",
-            hierarchy_level="topic",
-            type="fact",
-            memory_time="2024-01-01",
-            source="file",
-            sources=["paper://multi-uav-coverage/intro"],
-            status="activated",
-            confidence=95.0,
-            tags=["UAV", "coverage", "multi-agent"],
-            entities=["UAV", "coverage", "navigation"],
-            visibility="public",
-            updated_at=datetime.now().isoformat(),
-            embedding=embed_memory_item(
-                "This research addresses long-term "
-                "multi-UAV navigation for "
-                "energy-efficient communication "
-                "coverage."
-            ),
-        ),
-    )
-
-    graph.add_node(
-        id=topic.id, memory=topic.memory, metadata=topic.metadata.model_dump(exclude_none=True)
-    )
-
-
 def example_shared_db(db_name: str = "shared-traval-group"):
     """
     Example: Single(Shared)-DB multi-tenant (logical isolation)
@@ -404,9 +354,6 @@ def example_complex_shared_db(db_name: str = "shared-traval-group-complex"):
 
 
 if __name__ == "__main__":
-    print("\n=== Example: Multi-DB ===")
-    example_multi_db(db_name="paper-new")
-
     print("\n=== Example: Single-DB ===")
     example_shared_db(db_name="shared_traval_group-new")
 
diff --git a/pyproject.toml b/pyproject.toml
@@ -4,7 +4,7 @@
 ##############################################################################
 
 name = "MemoryOS"
-version = "1.0.1"
+version = "1.1.1"
 description = "Intelligence Begins with Memory"
 license = {text = "Apache-2.0"}
 readme = "README.md"
diff --git a/src/memos/__init__.py b/src/memos/__init__.py
@@ -1,4 +1,4 @@
-__version__ = "1.0.1"
+__version__ = "1.1.1"
 
 from memos.configs.mem_cube import GeneralMemCubeConfig
 from memos.configs.mem_os import MOSConfig
diff --git a/src/memos/api/client.py b/src/memos/api/client.py
@@ -50,6 +50,7 @@ def get_message(
                 )
                 response.raise_for_status()
                 response_data = response.json()
+
                 return MemOSGetMessagesResponse(**response_data)
             except Exception as e:
                 logger.error(f"Failed to get messages (retry {retry + 1}/3): {e}")
@@ -74,6 +75,7 @@ def add_message(
                 )
                 response.raise_for_status()
                 response_data = response.json()
+
                 return MemOSAddResponse(**response_data)
             except Exception as e:
                 logger.error(f"Failed to add memory (retry {retry + 1}/3): {e}")
@@ -102,6 +104,7 @@ def search_memory(
                 )
                 response.raise_for_status()
                 response_data = response.json()
+
                 return MemOSSearchResponse(**response_data)
             except Exception as e:
                 logger.error(f"Failed to search memory (retry {retry + 1}/3): {e}")
diff --git a/src/memos/api/config.py b/src/memos/api/config.py
@@ -530,6 +530,13 @@ def create_user_config(user_name: str, user_id: str) -> tuple[MOSConfig, General
                             "embedder": APIConfig.get_embedder_config(),
                             "internet_retriever": internet_config,
                             "reranker": APIConfig.get_reranker_config(),
+                            "reorganize": os.getenv("MOS_ENABLE_REORGANIZE", "false").lower()
+                            == "true",
+                            "memory_size": {
+                                "WorkingMemory": os.getenv("NEBULAR_WORKING_MEMORY", 20),
+                                "LongTermMemory": os.getenv("NEBULAR_LONGTERM_MEMORY", 1e6),
+                                "UserMemory": os.getenv("NEBULAR_USER_MEMORY", 1e6),
+                            },
                         },
                     },
                     "act_mem": {}
@@ -587,6 +594,11 @@ def get_default_cube_config() -> GeneralMemCubeConfig | None:
                             "reorganize": os.getenv("MOS_ENABLE_REORGANIZE", "false").lower()
                             == "true",
                             "internet_retriever": internet_config,
+                            "memory_size": {
+                                "WorkingMemory": os.getenv("NEBULAR_WORKING_MEMORY", 20),
+                                "LongTermMemory": os.getenv("NEBULAR_LONGTERM_MEMORY", 1e6),
+                                "UserMemory": os.getenv("NEBULAR_USER_MEMORY", 1e6),
+                            },
                         },
                     },
                     "act_mem": {}
diff --git a/src/memos/api/product_models.py b/src/memos/api/product_models.py
@@ -241,7 +241,7 @@ class GetMessagesData(BaseModel):
     """Data model for get messages response based on actual API."""
 
     message_detail_list: list[MessageDetail] = Field(
-        default_factory=list, alias="memory_detail_list", description="List of message details"
+        default_factory=list, alias="message_detail_list", description="List of message details"
     )
 
 
diff --git a/src/memos/graph_dbs/nebular.py b/src/memos/graph_dbs/nebular.py
@@ -187,6 +187,19 @@ def _get_or_create_shared_client(cls, cfg: NebulaGraphDBConfig) -> tuple[str, "N
             client = cls._CLIENT_CACHE.get(key)
             if client is None:
                 # Connection setting
+
+                tmp_client = NebulaClient(
+                    hosts=cfg.uri,
+                    username=cfg.user,
+                    password=cfg.password,
+                    session_config=SessionConfig(graph=None),
+                    session_pool_config=SessionPoolConfig(size=1, wait_timeout=3000),
+                )
+                try:
+                    cls._ensure_space_exists(tmp_client, cfg)
+                finally:
+                    tmp_client.close()
+
                 conn_conf: ConnectionConfig | None = getattr(cfg, "conn_config", None)
                 if conn_conf is None:
                     conn_conf = ConnectionConfig.from_defults(
@@ -317,6 +330,7 @@ def __init__(self, config: NebulaGraphDBConfig):
             }
         """
 
+        assert config.use_multi_db is False, "Multi-DB MODE IS NOT SUPPORTED"
         self.config = config
         self.db_name = config.space
         self.user_name = config.user_name
@@ -349,7 +363,7 @@ def __init__(self, config: NebulaGraphDBConfig):
             if (str(self.embedding_dimension) != str(self.default_memory_dimension))
             else "embedding"
         )
-        self.system_db_name = "system" if config.use_multi_db else config.space
+        self.system_db_name = config.space
 
         # ---- NEW: pool acquisition strategy
         # Get or create a shared pool from the class-level cache
@@ -436,7 +450,7 @@ def remove_oldest_memory(
             WHERE n.memory_type = '{memory_type}'
             {optional_condition}
             ORDER BY n.updated_at DESC
-            OFFSET {keep_latest}
+            OFFSET {int(keep_latest)}
             DETACH DELETE n
         """
         self.execute_query(query)
@@ -481,7 +495,7 @@ def node_not_exist(self, scope: str, user_name: str | None = None) -> int:
         user_name = user_name if user_name else self.config.user_name
         filter_clause = f'n.memory_type = "{scope}" AND n.user_name = "{user_name}"'
         query = f"""
-        MATCH (n@Memory)
+        MATCH (n@Memory /*+ INDEX(idx_memory_user_name) */)
         WHERE {filter_clause}
         RETURN n.id AS id
         LIMIT 1
@@ -838,7 +852,7 @@ def get_neighbors_by_tag(
         query = f"""
             LET tag_list = {tag_list_literal}
 
-            MATCH (n@Memory)
+            MATCH (n@Memory /*+ INDEX(idx_memory_user_name) */)
             WHERE {where_clause}
             RETURN {return_fields},
                size( filter( n.tags, t -> t IN tag_list ) ) AS overlap_count
@@ -1392,6 +1406,17 @@ def get_structure_optimization_candidates(
             logger.error(f"Failed : {e}, traceback: {traceback.format_exc()}")
         return candidates
 
+    @timed
+    def drop_database(self) -> None:
+        """
+        Permanently delete the entire database this instance is using.
+        WARNING: This operation is destructive and cannot be undone.
+        """
+        raise ValueError(
+            f"Refusing to drop protected database: `{self.db_name}` in "
+            f"Shared Database Multi-Tenant mode"
+        )
+
     @timed
     def detect_conflicts(self) -> list[tuple[str, str]]:
         """
@@ -1462,6 +1487,25 @@ def merge_nodes(self, id1: str, id2: str) -> str:
         """
         raise NotImplementedError
 
+    @classmethod
+    def _ensure_space_exists(cls, tmp_client, cfg):
+        """Lightweight check to ensure target graph (space) exists."""
+        db_name = getattr(cfg, "space", None)
+        if not db_name:
+            logger.warning("[NebulaGraphDBSync] No `space` specified in cfg.")
+            return
+
+        try:
+            res = tmp_client.execute("SHOW GRAPHS;")
+            existing = {row.values()[0].as_string() for row in res}
+            if db_name not in existing:
+                tmp_client.execute(f"CREATE GRAPH IF NOT EXISTS `{db_name}` TYPED MemOSBgeM3Type;")
+                logger.info(f"✅ Graph `{db_name}` created before session binding.")
+            else:
+                logger.debug(f"Graph `{db_name}` already exists.")
+        except Exception:
+            logger.exception("[NebulaGraphDBSync] Failed to ensure space exists")
+
     @timed
     def _ensure_database_exists(self):
         graph_type_name = "MemOSBgeM3Type"
diff --git a/src/memos/memories/textual/tree.py b/src/memos/memories/textual/tree.py
@@ -326,10 +326,10 @@ def load(self, dir: str) -> None:
         except Exception as e:
             logger.error(f"An error occurred while loading memories: {e}")
 
-    def dump(self, dir: str) -> None:
+    def dump(self, dir: str, include_embedding: bool = False) -> None:
         """Dump memories to os.path.join(dir, self.config.memory_filename)"""
         try:
-            json_memories = self.graph_store.export_graph()
+            json_memories = self.graph_store.export_graph(include_embedding=include_embedding)
 
             os.makedirs(dir, exist_ok=True)
             memory_file = os.path.join(dir, self.config.memory_filename)
diff --git a/src/memos/memories/textual/tree_text_memory/organize/manager.py b/src/memos/memories/textual/tree_text_memory/organize/manager.py
@@ -44,6 +44,7 @@ def __init__(
                 "LongTermMemory": 1500,
                 "UserMemory": 480,
             }
+        logger.info(f"MemorySize is {self.memory_size}")
         self._threshold = threshold
         self.is_reorganize = is_reorganize
         self.reorganizer = GraphStructureReorganizer(
diff --git a/tests/api/test_start_api.py b/tests/api/test_start_api.py
@@ -82,62 +82,6 @@ def mock_mos():
         yield mock_instance
 
 
-def test_configure(mock_mos):
-    """Test configuration endpoint."""
-    with patch("memos.api.start_api.MOS_INSTANCE", None):
-        # Use a valid configuration
-        valid_config = {
-            "user_id": "test_user",
-            "session_id": "test_session",
-            "enable_textual_memory": True,
-            "enable_activation_memory": False,
-            "top_k": 5,
-            "chat_model": {
-                "backend": "openai",
-                "config": {
-                    "model_name_or_path": "gpt-3.5-turbo",
-                    "api_key": "test_key",
-                    "temperature": 0.7,
-                    "api_base": "https://api.openai.com/v1",
-                },
-            },
-            "mem_reader": {
-                "backend": "simple_struct",
-                "config": {
-                    "llm": {
-                        "backend": "openai",
-                        "config": {
-                            "model_name_or_path": "gpt-3.5-turbo",
-                            "api_key": "test_key",
-                            "temperature": 0.7,
-                            "api_base": "https://api.openai.com/v1",
-                        },
-                    },
-                    "embedder": {
-                        "backend": "sentence_transformer",
-                        "config": {"model_name_or_path": "all-MiniLM-L6-v2"},
-                    },
-                    "chunker": {
-                        "backend": "sentence",
-                        "config": {
-                            "tokenizer_or_token_counter": "gpt2",
-                            "chunk_size": 512,
-                            "chunk_overlap": 128,
-                            "min_sentences_per_chunk": 1,
-                        },
-                    },
-                },
-            },
-        }
-        response = client.post("/configure", json=valid_config)
-        assert response.status_code == 200
-        assert response.json() == {
-            "code": 200,
-            "message": "Configuration set successfully",
-            "data": None,
-        }
-
-
 def test_configure_error(mock_mos):
     """Test configuration endpoint with error."""
     with patch("memos.api.start_api.MOS_INSTANCE", None):

Original file line number	Diff line number	Diff line change
`@@ -1,4 +1,4 @@`
`1`		`-__version__ = "1.0.1"`
	`1`	`+__version__ = "1.1.1"`
`2`	`2`
`3`	`3`	`from memos.configs.mem_cube import GeneralMemCubeConfig`
`4`	`4`	`from memos.configs.mem_os import MOSConfig`
Original file line number	Diff line number	Diff line change
`@@ -241,7 +241,7 @@ class GetMessagesData(BaseModel):`
`241`	`241`	`"""Data model for get messages response based on actual API."""`
`242`	`242`
`243`	`243`	`message_detail_list: list[MessageDetail] = Field(`
`244`		`- default_factory=list, alias="memory_detail_list", description="List of message details"`
	`244`	`+ default_factory=list, alias="message_detail_list", description="List of message details"`
`245`	`245`	`)`
`246`	`246`
`247`	`247`
Original file line number	Diff line number	Diff line change
`@@ -44,6 +44,7 @@ def __init__(`
`44`	`44`	`"LongTermMemory": 1500,`
`45`	`45`	`"UserMemory": 480,`
`46`	`46`	`}`
	`47`	`+ logger.info(f"MemorySize is {self.memory_size}")`
`47`	`48`	`self._threshold = threshold`
`48`	`49`	`self.is_reorganize = is_reorganize`
`49`	`50`	`self.reorganizer = GraphStructureReorganizer(`