memoryscope.scheme.memory_node
- pydantic model memoryscope.scheme.memory_node.MemoryNode[源代码]
基类:
BaseModel
Represents a memory node with comprehensive attributes to store memory information including unique ID, user details, content, metadata, scoring metrics. Automatically handles timestamp conversion to date format during initialization.
Show JSON schema
{ "title": "MemoryNode", "description": "Represents a memory node with comprehensive attributes to store memory information including unique ID,\nuser details, content, metadata, scoring metrics.\nAutomatically handles timestamp conversion to date format during initialization.", "type": "object", "properties": { "memory_id": { "description": "unique id for memory", "title": "Memory Id", "type": "string" }, "user_name": { "default": "", "description": "the user who owns the memory", "title": "User Name", "type": "string" }, "target_name": { "default": "", "description": "target name described by the memory", "title": "Target Name", "type": "string" }, "meta_data": { "additionalProperties": { "type": "string" }, "default": {}, "description": "meta data infos", "title": "Meta Data", "type": "object" }, "content": { "default": "", "description": "memory content", "title": "Content", "type": "string" }, "key": { "default": "", "description": "memory key", "title": "Key", "type": "string" }, "key_vector": { "default": [], "description": "memory key embedding result", "items": { "type": "number" }, "title": "Key Vector", "type": "array" }, "value": { "default": "", "description": "memory value", "title": "Value", "type": "string" }, "score_recall": { "default": 0, "description": "embedding similarity score used in recall stage", "title": "Score Recall", "type": "number" }, "score_rank": { "default": 0, "description": "rank model score used in rank stage", "title": "Score Rank", "type": "number" }, "score_rerank": { "default": 0, "description": "rerank score used in rerank stage", "title": "Score Rerank", "type": "number" }, "memory_type": { "default": "", "description": "conversation / observation / insight...", "title": "Memory Type", "type": "string" }, "action_status": { "default": "none", "description": "new / content_modified / modified / deleted / none", "title": "Action Status", "type": "string" }, "store_status": { "default": "valid", "description": "store_status: valid / expired", "title": "Store Status", "type": "string" }, "vector": { "default": [], "description": "content embedding result", "items": { "type": "number" }, "title": "Vector", "type": "array" }, "timestamp": { "description": "timestamp of the memory node", "title": "Timestamp", "type": "integer" }, "dt": { "default": "", "description": "dt of the memory node", "title": "Dt", "type": "string" }, "obs_reflected": { "default": 0, "description": "if the observation is reflected: 0/1", "title": "Obs Reflected", "type": "integer" }, "obs_updated": { "default": 0, "description": "if the observation has updated user profile or insight: 0/1", "title": "Obs Updated", "type": "integer" } } }
- Fields:
- field memory_id: str [Optional]
unique id for memory
- field user_name: str = ''
the user who owns the memory
- field target_name: str = ''
target name described by the memory
- field meta_data: Dict[str, str] = {}
meta data infos
- field content: str = ''
memory content
- field key: str = ''
memory key
- field key_vector: List[float] = []
memory key embedding result
- field value: str = ''
memory value
- field score_recall: float = 0
embedding similarity score used in recall stage
- field score_rank: float = 0
rank model score used in rank stage
- field score_rerank: float = 0
rerank score used in rerank stage
- field memory_type: str = ''
conversation / observation / insight...
- field action_status: str = 'none'
new / content_modified / modified / deleted / none
- field store_status: str = 'valid'
store_status: valid / expired
- field vector: List[float] = []
content embedding result
- field timestamp: int [Optional]
timestamp of the memory node
- field obs_reflected: int = 0
if the observation is reflected: 0/1
- field obs_updated: int = 0
if the observation has updated user profile or insight: 0/1
- __init__(**kwargs)[源代码]
Create a new model by parsing and validating input data from keyword arguments.
Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.
self is explicitly positional-only to allow self as a field name.
- field dt: str = ''
dt of the memory node
- property node_keys