autogen

Tree: 025490a1bd

History

Eric Zhu 025490a1bd Use class hierarchy to organize AgentChat message types and introduce StructuredMessage type (#5998 ) This PR refactored `AgentEvent` and `ChatMessage` union types to abstract base classes. This allows for user-defined message types that subclass one of the base classes to be used in AgentChat. To support a unified interface for working with the messages, the base classes added abstract methods for: - Convert content to string - Convert content to a `UserMessage` for model client - Convert content for rendering in console. - Dump into a dictionary - Load and create a new instance from a dictionary This way, all agents such as `AssistantAgent` and `SocietyOfMindAgent` can utilize the unified interface to work with any built-in and user-defined message type. This PR also introduces a new message type, `StructuredMessage` for AgentChat (Resolves #5131), which is a generic type that requires a user-specified content type. You can create a `StructuredMessage` as follow: ```python class MessageType(BaseModel): data: str references: List[str] message = StructuredMessage[MessageType](content=MessageType(data="data", references=["a", "b"]), source="user") # message.content is of type `MessageType`. ``` This PR addresses the receving side of this message type. To produce this message type from `AssistantAgent`, the work continue in #5934. Added unit tests to verify this message type works with agents and teams.		1 year ago
..
agentchat_chainlit	Add author name before their message in Chainlit team sample (#5878)	1 year ago

agentchat_chess_game	Use class hierarchy to organize AgentChat message types and introduce StructuredMessage type (#5998)	1 year ago

agentchat_fastapi	Add sample chat application with FastAPI (#5433)	1 year ago

agentchat_graphrag	Properly close model clients in documentation and samples (#5898)	1 year ago

agentchat_streamlit	Use class hierarchy to organize AgentChat message types and introduce StructuredMessage type (#5998)	1 year ago

core_async_human_in_the_loop	Properly close model clients in documentation and samples (#5898)	1 year ago

core_chess_game	Properly close model clients in documentation and samples (#5898)	1 year ago

core_distributed-group-chat	Properly close model clients in documentation and samples (#5898)	1 year ago

core_grpc_worker_runtime	fix: Make race condition between channel open and RPC less likely to occur (#5514)	1 year ago

core_semantic_router	fix: Make race condition between channel open and RPC less likely to occur (#5514)	1 year ago

core_xlang_hello_python_agent	Improve e2e integration tests and isolate tests from other things; includes patch to Serializer (#5497)	1 year ago

gitty	Add new sample: Gitty (#5842)	1 year ago

task_centric_memory	Properly close model clients in documentation and samples (#5898)	1 year ago

This is a mirror of AutoGen from GitHub. AutoGen is a framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks.

Python SVG Jupyter Notebook C# TSX other

jackgerrits@users.noreply.github.com ekzhu@users.noreply.github.com wang.chi@microsoft.com rysweet@microsoft.com bigmiao.zhang@gmail.com adamfo@microsoft.com victordibia@microsoft.com gagb@users.noreply.github.com bnujli@gmail.com qingyun.wu@psu.edu liususan091219@users.noreply.github.com kostapetan@gmail.com jack@jackgerrits.com jaalber@microsoft.com davor@airt.ai 49209570+peterychang@users.noreply.github.com shaokunzhang529@gmail.com griffinbassman@gmail.com 32823396+kevin666aa@users.noreply.github.com adam.fourney@gmail.com leosantospinheiro@gmail.com qw2ky@virginia.edu 49699333+dependabot[bot]@users.noreply.github.com 66362098+marklysze@users.noreply.github.com hahahah2021@163.com

Contributors (25+) All

Contributors (25+)
All