Add further installation guidance and files for CaptainAgent

notebook/agentchat_captainagent.ipynb

@@ -11,9 +11,9 @@
     "\n",
     "````{=mdx}\n",
     ":::info Requirements\n",
-    "Install `ag2`:\n",
+    "Install `ag2` with CaptainAgent:\n",
     "```bash\n",
-    "pip install ag2[autobuild]\n",
+    "pip install ag2[captainagent]\n",
     "```\n",
     "\n",
     "For more information, please refer to the [installation guide](/docs/installation/).\n",
@@ -522,7 +522,7 @@
     "\n",
     "For agent library, refer to [`captainagent_expert_library.json`](https://github.com/ag2ai/ag2/blob/main/notebook/captainagent_expert_library.json) for samples. You can refer to [docs](https://ag2ai.github.io/ag2/docs/topics/captainagent/agent_library) on how to customize your own expert library.\n",
     "\n",
-    "For tool library, we provide a set of tools [here](https://github.com/ag2ai/ag2/tree/main/autogen/agentchat/contrib/captainagent/tools/README.md), the tools are categorized into three types: data analysis, information_retrieval, math."
+    "For tool library, we provide a set of tools [here](https://github.com/ag2ai/ag2/tree/main/autogen/agentchat/contrib/captainagent/tools/README.md), the tools are categorized into three types: data analysis, information_retrieval, math. If you are using the tools, you should [install the requirements](https://github.com/ag2ai/ag2/tree/main/autogen/agentchat/contrib/captainagent/tools/README.md#how-to-use) for them."
    ]
   },
   {

setup.py

@@ -131,6 +131,14 @@
     long_description_content_type="text/markdown",
     url="https://github.com/ag2ai/ag2",
     packages=setuptools.find_packages(include=["autogen*"], exclude=["test"]),
+    package_data={
+        "autogen.agentchat.contrib.captainagent": [
+            "tools/**/*.py",  # CaptainAgent tools
+            "tools/tool_description.tsv",
+            "tools/requirements.txt",
+        ]
+    },
+    include_package_data=True,
     install_requires=install_requires,
     extras_require=extra_require,
     classifiers=[

website/.gitignore

@@ -14,6 +14,7 @@ docs/reference
 docs/tutorial/*.mdx
 docs/tutorial/**/*.png
 !docs/tutorial/assets/*.png
+docs/topics/swarm.mdx
 docs/topics/llm_configuration.mdx
 docs/topics/code-execution/*.mdx
 docs/topics/task_decomposition.mdx
@@ -23,6 +24,9 @@ docs/topics/non-openai-models/**/*.py
 docs/topics/non-openai-models/**/*.svg
 docs/topics/code-execution/*.mdx
 docs/topics/groupchat/customized_speaker_selection.mdx
+docs/topics/groupchat/resuming_groupchat.mdx
+docs/topics/groupchat/transform_messages_speaker_selection.mdx
+docs/topics/groupchat/using_custom_model_client_classes.mdx
 cell-*-output-*.png
 
 # Misc

website/blog/2024-11-15-CaptainAgent/index.mdx

@@ -24,12 +24,18 @@ CaptainAgent iterates over the following two steps until the problem is successf
 
 The design of CaptainAgent allows it to leverage agents and tools from a pre-specified agent library and tool library. In the following section, we demonstrate how to use CaptainAgent with or without the provided library.
 
+To install AG2 with CaptainAgent:
+
+```bash
+pip install ag2[captainagent]
+```
+
 # Using CaptainAgent without pre-specified agent/tool libraries
-CaptainAgent can serve as a drop-in replacement for the general `AssistantAgent` class in AG2. To do that we just need to add a few lines of configurations for the group chat involved.
-Without the agent library and tool library, CaptainAgent will automatically generate a set of agents into a group chat.
+CaptainAgent can serve as a drop-in replacement for the general `AssistantAgent` class in AG2. It also allows customization such as agent/tool libraries. When the libraries are provided, CaptainAgent will try to leverage them when solving a task.
+Without them, CaptainAgent will automatically generate new agents.
 
 ```python
-from autogen.agentchat.contrib.captain_agent import CaptainAgent
+from autogen.agentchat.contrib.captainagent import CaptainAgent
 from autogen import UserProxyAgent
 
 llm_config = {
@@ -58,7 +64,7 @@ The tool library we provide requires subscribing to specific APIs, please refer
 To use agents from an agent library, you just need to specify a `library_path` sub-field or a `autobuild_tool_config` field in CaptainAgent's configuration.
 
 ```python
-from autogen.agentchat.contrib.captain_agent import CaptainAgent
+from autogen.agentchat.contrib.captainagent import CaptainAgent
 from autogen import UserProxyAgent
 
 llm_config = {
@@ -70,7 +76,7 @@ llm_config = {
 captain_agent = CaptainAgent(
     name="captain_agent",
     llm_config=llm_config,
-    nested_mode_config=nested_mode_config,
+    nested_config=nested_mode_config,
     agent_lib="captainagent_expert_library.json",
     tool_lib="default",
     code_execution_config={"use_docker": False, "work_dir": "groupchat"},

website/docs/topics/captainagent/_category_.json

@@ -1,4 +1,4 @@
 {
-    "label": "Captain Agent",
+    "label": "CaptainAgent",
     "collapsible": true
 }

website/docs/topics/captainagent/configurations.mdx

@@ -1,5 +1,5 @@
 # Configurations in `nested_config`
-Captain Agent requires `nested_config` for configuration. Below is an example, we will break it down and provide a detailed explanation.
+CaptainAgent requires `nested_config` for configuration. Below is an example, we will break it down and provide a detailed explanation.
 
 ```
 nested_config = {
@@ -23,6 +23,15 @@ nested_config = {
 }
 ```
 
+:::info Requirements
+If you run CaptainAgent without specifying a `nested_config`, a default is used and this **requires an OAI_CONFIG_LIST**.
+
+**The default model used is OpenAI's GPT-4o**.
+
+To see the default configuration and the OpenAI model used, see the [captainagent.py](https://github.com/ag2ai/ag2/blob/ceb75d865d0a7eb2b7c0bc51776e093681e0970e/autogen/agentchat/contrib/captainagent.py) file.
+
+For advice on using OAI_CONFIG_LIST, [see the documentation](https://ag2ai.github.io/ag2/docs/topics/llm_configuration#oai_config_list-pattern).
+:::
 
 ## `autobuild_init_config`
 This section is used to configure the initial setup of autobuild. `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).
@@ -31,10 +40,10 @@ This section is used to configure the initial setup of autobuild. `autobuild_ini
 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`.
+Configures the backbone of agent builder. The builder is used for agent selection from the library. Defaults to `gpt-4o`.
 
 ### `agent_model`
-Configures the backbone of agents in the group chat. Defaults to `gpt-4o-mini`.
+Configures the backbone of agents in the group chat. Defaults to `gpt-4o`.
 
 ### Other `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).

website/docs/topics/llm_configuration.ipynb

@@ -126,7 +126,7 @@
     "\n",
     "### `OAI_CONFIG_LIST` pattern\n",
     "\n",
-    "A common, useful pattern used is to define this `config_list` is via JSON (specified as a file or an environment variable set to a JSON-formatted string) and then use the [`config_list_from_json`](/docs/reference/oai/openai_utils#config_list_from_json) helper function to load it:"
+    "A common, useful pattern used is to define this `config_list` via JSON (specified as a file or an environment variable set to a JSON-formatted string) and then use the [`config_list_from_json`](/docs/reference/oai/openai_utils#config_list_from_json) helper function to load it:"
    ]
   },
   {