diff --git a/website/docs/topics/captainagent/configurations.mdx b/website/docs/topics/captainagent/configurations.mdx new file mode 100644 index 0000000000..a834df3bef --- /dev/null +++ b/website/docs/topics/captainagent/configurations.mdx @@ -0,0 +1,79 @@ +# Details of all the available configurations +Captain Agent requires `nested_config` for configuration. Below is an example, we will break it down and provide a detailed explanation. + +``` +nested_config = { + "autobuild_init_config": { + "config_file_or_env": "OAI_CONFIG_LIST", + "builder_model": "gpt-4o", + "agent_model": "gpt-4o", + }, + "autobuild_build_config": { + "default_llm_config": {"temperature": 1, "top_p": 0.95, "max_tokens": 1500, "seed": 52}, + "code_execution_config": {"timeout": 300, "work_dir": "groupchat", "last_n_messages": 1}, + "coding": True, + "library_path_or_json": "captainagent_expert_library.json", + }, + "autobuild_tool_config": { + "tool_root": "default", # this will use the tool library we provide + "retriever": "all-mpnet-base-v2", + }, + "group_chat_config": {"max_round": 15}, + "group_chat_llm_config": llm_config.copy(), +} +``` + + +## `autobuild_init_config` +This section is used to configure the initial setup of autobuild. + +### `config_file_or_env` +Configures the path to API key config. Defaults to `OAI_CONFIG_LIST`. + +### `builder_model` +Configures the backbone of agent builder. The builder is used for agent selection from the library. Defaults to `gpt-4o-mini`. + +### `agent_model` +Configures the backbone of agents in the group chat. Defaults to `gpt-4o-mini`. + +### `kwargs` +`autobuild_init_config` takes in arguments from `AgentBuilder.__init__()`. Check the full list of arguments [here](https://github.com/ag2ai/ag2/blob/main/autogen/agentchat/contrib/agent_builder.py#L181). + +## `autobuild_build_config` +This section is used to configure the building process of autobuild. + +### `default_llm_config` +Configures the default parameters for the builder during the autobuild process. Defaults to `{"temperature": 1, "top_p": 0.95, "max_tokens": 2048}`. `config_list` is **not* needed here. + +### `code_execution_config` +Configures how the user proxy executes code within the nested chat. Defaults to `{"timeout": 300, "work_dir": "groupchat", "last_n_messages": 1, "use_docker": False}`. Full configuration docs [here](https://ag2ai.github.io/ag2/docs/reference/agentchat/user_proxy_agent). + +### `coding` +Enables or disables whether to add the user proxy in the nested chat. Defaults to `True`. + +### `library_path_or_json` +Specifies the path to the agent library file. For details on customizing your own agent library, refer to the [agent library page](https://ag2ai.github.io/ag2/docs/topics/captainagent/agent_library). + +### `kwargs` +`autobuild_build_config` takes in arguments for `AgentBuilder.build()`. Check the full list of arguments [here](https://github.com/ag2ai/ag2/blob/main/autogen/agentchat/contrib/agent_builder.py#L365). + +## `autobuild_tool_config` +This section is used to configure how to retrieve the tool library for the agents in the group chat. For details on customizing your own tool library, refer to the [tool library page](https://ag2ai.github.io/ag2/docs/topics/captainagent/tool_library). + +### `tool_root` +Specifies the root directory of the tool library. When set to `'default'`, it will load the default library we provide. + +### `retriever` +Configures the retriever model used for fetching relevant tools from the library. Defaults to `all-mpnet-base-v2`. The value is valid as long as it is found by [SentenceTransformers library](https://huggingface.co/sentence-transformers). + +## `group_chat_config` +This section is used to configure the group chat settings. + +### `max_round` +Specifies the maximum number of rounds in a group chat session. Defaults to `10`. + +### `kwargs` +`group_chat_config` also takes in arguments for initializing `autogen.GroupChat`. Refer to all the configurables [here](https://ag2ai.github.io/ag2/docs/reference/agentchat/groupchat). + +## `group_chat_llm_config` +Specifies the LLM config of the `GroupChatManager`.