langchain_experimental.generative_agents.generative_agent.GenerativeAgent

class langchain_experimental.generative_agents.generative_agent.GenerativeAgent(*, name: str, age: Optional[int] = None, traits: str = 'N/A', status: str, memory: GenerativeAgentMemory, llm: BaseLanguageModel, verbose: bool = False, summary: str = '', summary_refresh_seconds: int = 3600, last_refreshed: datetime = None, daily_summaries: List[str] = None)

Bases: BaseModel

An Agent as a character with memory and innate characteristics.

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

param age: Optional[int] = None

The optional age of the character.

param daily_summaries: List[str] [Optional]

Summary of the events in the plan that the agent took.

param last_refreshed: datetime.datetime [Optional]

The last time the character’s summary was regenerated.

param llm: langchain.schema.language_model.BaseLanguageModel [Required]

The underlying language model.

param memory: langchain_experimental.generative_agents.memory.GenerativeAgentMemory [Required]

The memory object that combines relevance, recency, and ‘importance’.

param name: str [Required]

The character’s name.

param status: str [Required]

The traits of the character you wish not to change.

param summary: str = ''

Stateful self-summary generated via reflection on the character’s memory.

param summary_refresh_seconds: int = 3600

How frequently to re-generate the summary.

param traits: str = 'N/A'

Permanent traits to ascribe to the character.

param verbose: bool = False

chain(prompt: PromptTemplate) → LLMChain

generate_dialogue_response(observation: str, now: Optional[datetime] = None) → Tuple[bool, str]

React to a given observation.

generate_reaction(observation: str, now: Optional[datetime] = None) → Tuple[bool, str]

React to a given observation.

get_full_header(force_refresh: bool = False, now: Optional[datetime] = None) → str

Return a full header of the agent’s status, summary, and current time.

get_summary(force_refresh: bool = False, now: Optional[datetime] = None) → str

Return a descriptive summary of the agent.

summarize_related_memories(observation: str) → str

Summarize memories that are most relevant to an observation.

model Config

Bases: object

Configuration for this pydantic object.

arbitrary_types_allowed = True