autogen_core.model_context#

class BufferedChatCompletionContext(buffer_size: int, initial_messages: List[Annotated[SystemMessage | UserMessage | AssistantMessage | FunctionExecutionResultMessage, FieldInfo(annotation=NoneType, required=True, discriminator='type')]] | None = None)[source]#

Bases: ChatCompletionContext

A buffered chat completion context that keeps a view of the last n messages, where n is the buffer size. The buffer size is set at initialization.

Parameters:: buffer_size (int) – The size of the buffer.

async add_message(message: Annotated[SystemMessage | UserMessage | AssistantMessage | FunctionExecutionResultMessage, FieldInfo(annotation=NoneType, required=True, discriminator='type')]) → None[source]#: Add a message to the memory.

async clear() → None[source]#: Clear the message memory.

async get_messages() → List[Annotated[SystemMessage | UserMessage | AssistantMessage | FunctionExecutionResultMessage, FieldInfo(annotation=NoneType, required=True, discriminator='type')]][source]#: Get at most buffer_size recent messages.

load_state(state: Mapping[str, Any]) → None[source]#

save_state() → Mapping[str, Any][source]#

class ChatCompletionContext(*args, **kwargs)[source]#

Bases: Protocol

A protocol for defining the interface of a chat completion context. A chat completion context lets agents store and retrieve LLM messages. It can be implemented with different recall strategies.

async add_message(message: Annotated[SystemMessage | UserMessage | AssistantMessage | FunctionExecutionResultMessage, FieldInfo(annotation=NoneType, required=True, discriminator='type')]) → None[source]#

async clear() → None[source]#

async get_messages() → List[Annotated[SystemMessage | UserMessage | AssistantMessage | FunctionExecutionResultMessage, FieldInfo(annotation=NoneType, required=True, discriminator='type')]][source]#

load_state(state: Mapping[str, Annotated[SystemMessage | UserMessage | AssistantMessage | FunctionExecutionResultMessage, FieldInfo(annotation=NoneType, required=True, discriminator='type')]]) → None[source]#

save_state() → Mapping[str, Annotated[SystemMessage | UserMessage | AssistantMessage | FunctionExecutionResultMessage, FieldInfo(annotation=NoneType, required=True, discriminator='type')]][source]#

class HeadAndTailChatCompletionContext(head_size: int, tail_size: int)[source]#

Bases: ChatCompletionContext

A chat completion context that keeps a view of the first n and last m messages, where n is the head size and m is the tail size. The head and tail sizes are set at initialization.

Parameters:

head_size (int) – The size of the head.
tail_size (int) – The size of the tail.

async add_message(message: Annotated[SystemMessage | UserMessage | AssistantMessage | FunctionExecutionResultMessage, FieldInfo(annotation=NoneType, required=True, discriminator='type')]) → None[source]#: Add a message to the memory.

async clear() → None[source]#: Clear the message memory.

async get_messages() → List[Annotated[SystemMessage | UserMessage | AssistantMessage | FunctionExecutionResultMessage, FieldInfo(annotation=NoneType, required=True, discriminator='type')]][source]#: Get at most head_size recent messages and tail_size oldest messages.

load_state(state: Mapping[str, Any]) → None[source]#

save_state() → Mapping[str, Any][source]#