Get Agent State

time	status	user agent
Retrieving recent requests…

time

status

user agent

Retrieving recent requests…

200

Successful Response

Response body

object

description

The description of the agent.

metadata_

The metadata of the agent.

user_id

The user id of the agent.

string

The human-friendly ID of the Agent

name

string

required

The name of the agent.

created_at

date-time

The datetime the agent was created.

message_ids

The ids of the messages in the agent's in-context memory.

memory

object

Represents the in-context memory of the agent. This includes both the Block objects (labelled by sections), as well as tools to edit the blocks.

Attributes:
memory (Dict[str, Block]): Mapping from memory block section to memory block.

memory

object

Mapping from memory block section to memory block.

prompt_template

string

Defaults to {% for block in memory.values() %}<{{ block.label }} characters="{{ block.value|length }}/{{ block.limit }}"> {{ block.value }} </{{ block.label }}>{% if not loop.last %} {% endif %}{% endfor %}

Jinja2 template for compiling memory blocks into a prompt string

tools

array of strings

required

The tools used by the agent.

Tools*

system

string

required

The system prompt used by the agent.

llm_config

object

required

Configuration for a Language Model (LLM) model. This object specifies all the information necessary to access an LLM model to usage with MemGPT, except for secret keys.

Attributes:
model (str): The name of the LLM model.
model_endpoint_type (str): The endpoint type for the model.
model_endpoint (str): The endpoint for the model.
model_wrapper (str): The wrapper for the model.
context_window (int): The context window size for the model.

model

string

required

LLM model name.

model_endpoint_type

string

required

The endpoint type for the model.

model_endpoint

string

required

The endpoint for the model.

model_wrapper

The wrapper for the model.

context_window

integer

required

The context window size for the model.

embedding_config

object

required

Embedding model configuration. This object specifies all the information necessary to access an embedding model to usage with MemGPT, except for secret keys.

Attributes:
embedding_endpoint_type (str): The endpoint type for the model.
embedding_endpoint (str): The endpoint for the model.
embedding_model (str): The model for the embedding.
embedding_dim (int): The dimension of the embedding.
embedding_chunk_size (int): The chunk size of the embedding.
azure_endpoint (:obj:str, optional): The Azure endpoint for the model (Azure only).
azure_version (str): The Azure version for the model (Azure only).
azure_deployment (str): The Azure deployment for the model (Azure only).

embedding_endpoint_type

string

required

The endpoint type for the model.

embedding_endpoint

The endpoint for the model (None if local).

embedding_model

string

required

The model for the embedding.

embedding_dim

integer

required

The dimension of the embedding.

embedding_chunk_size

Defaults to 300

The chunk size of the embedding.

azure_endpoint

The Azure endpoint for the model.

azure_version

The Azure version for the model.

azure_deployment

The Azure deployment for the model.

200Successful Response

422Validation Error