nat.tool.memory_tools.common

Attributes

UserIdResolver

Classes

MemoryToolConfigBase	Shared configuration for memory tools.
AddMemoryInput	LLM-controlled input for adding a memory.
GetMemoryInput	LLM-controlled input for retrieving memories.
DeleteMemoryInput	LLM-controlled input for deleting a user's memories.

Functions

resolve_memory_user_id(→ str)

Resolve a memory identity from trusted configuration or application code.

Module Contents

UserIdResolver

class MemoryToolConfigBase

Bases: nat.data_models.function.FunctionBaseConfig

Shared configuration for memory tools.

memory: nat.data_models.component_ref.MemoryRef = None

user_id: str | None = None

user_id_resolver: pydantic.ImportString[UserIdResolver] | None = None

classmethod validate_user_id(value: str | None) → str | None

validate_user_id_source() → Self

async resolve_memory_user_id(config: MemoryToolConfigBase) → str

Resolve a memory identity from trusted configuration or application code.

class AddMemoryInput(/, **data: Any)

Bases: pydantic.BaseModel

LLM-controlled input for adding a memory.

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.

model_config

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

conversation: list[dict[str, str]] | None = None

tags: list[str] = None

metadata: dict[str, Any] = None

memory: str | None = None

class GetMemoryInput(/, **data: Any)

Bases: pydantic.BaseModel

LLM-controlled input for retrieving memories.

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.

model_config

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

query: str = None

top_k: int = None

class DeleteMemoryInput(/, **data: Any)

Bases: pydantic.BaseModel

LLM-controlled input for deleting a user’s memories.

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.

model_config

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].