agentscope.message

The message module of AgentScope.

class AudioBlock[source]

Bases: TypedDict

The audio block

type: Required[Literal['audio']]

The type of the block

url: str

The url of the audio

class FileBlock[source]

Bases: TypedDict

The file block

type: Required[Literal['file']]

The type of the block

url: str

The url of the file

class ImageBlock[source]

Bases: TypedDict

The image block

type: Required[Literal['image']]

The type of the block

url: str

The url of the image

class Msg(name: str, content: str | Sequence[ToolUseBlock | ToolResultBlock | TextBlock | ImageBlock | AudioBlock | VideoBlock | FileBlock] | None, role: Literal['system', 'user', 'assistant'], metadata: str | int | float | bool | None | List[Any] | Dict[str, Any] = None, echo: bool = False, url: str | List[str] | None = None)[source]

Bases: BaseModel

The message class in AgentScope.

classmethod from_dict(serialized_dict: dict) → Msg[source]

Deserialize the dictionary to a Msg object.

Parameters:

serialized_dict (dict) – A dictionary that must contain the keys

Returns:

A Msg object.

Return type:

Msg

get_content_blocks(block_type: Literal['text', 'tool_use', 'tool_result', 'image', 'audio', 'video', 'file'] | None = None) → list[ToolUseBlock | ToolResultBlock | TextBlock | ImageBlock | AudioBlock | VideoBlock | FileBlock][source]

Get the content in block format. If the content is a string, it will be converted to a text block.

Parameters:

  • (`Optional[Literal["text" (block_type) –

    ”image”, “audio”, “video”, “file”]]`, defaults to None): The type of the block to be extracted. If None, all blocks will be returned.

  • "tool_use" – “image”, “audio”, “video”, “file”]]`, defaults to None): The type of the block to be extracted. If None, all blocks will be returned.

  • "tool_result" – “image”, “audio”, “video”, “file”]]`, defaults to None): The type of the block to be extracted. If None, all blocks will be returned.

:param“image”, “audio”, “video”, “file”]]`, defaults to None):

The type of the block to be extracted. If None, all blocks will be returned.

Returns:

The content blocks.

Return type:

list[ContentBlock]

get_text_content() → str | None[source]

Get the pure text blocks from the message content.

to_dict() → dict[source]

Serialize the message into a dictionary, which can be deserialized by calling the from_dict function.

Returns:

The serialized dictionary.

Return type:

dict

content: str | list[ToolUseBlock | ToolResultBlock | TextBlock | ImageBlock | AudioBlock | VideoBlock | FileBlock]

The content of the message.

id: str

The unique identity of the message.

metadata: str | int | float | bool | None | List[Any] | Dict[str, Any]

The additional metadata stored in the message.

model_config: ClassVar[ConfigDict] = {}

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

name: str

The name of the message sender.

role: Literal['system', 'user', 'assistant']

The role of the message sender.

timestamp: str

The timestamp of the message.

class TextBlock[source]

Bases: TypedDict

The text block.

text: str

The text content

type: Required[Literal['text']]

The type of the block

class ToolResultBlock[source]

Bases: TypedDict

The tool result block.

id: Required[str]

The identity of the tool call result

name: str | None

The name of the tool function

output: Required[object]

The output of the tool function

type: Required[Literal['tool_result']]

The type of the block

class ToolUseBlock[source]

Bases: TypedDict

The tool use block.

id: Required[str]

The identity of the tool call

input: Required[dict[str, object]]

The input of the tool

name: Required[str]

The name of the tool

type: Required[Literal['tool_use']]

The type of the block, must be tool_use

class VideoBlock[source]

Bases: TypedDict

The video block

type: Required[Literal['video']]

The type of the block

url: str

The url of the video