Skip to content

A programming framework for agentic AI

SelectorGroupChat Docs Update (#3876)

Gerardo Morenob7509b3659e1
diff --git a/python/packages/autogen-core/docs/src/user-guide/agentchat-user-guide/tutorial/selector-group-chat.ipynb b/python/packages/autogen-core/docs/src/user-guide/agentchat-user-guide/tutorial/selector-group-chat.ipynb
index ed2a4bf8e..6db803b7d 100644
--- a/python/packages/autogen-core/docs/src/user-guide/agentchat-user-guide/tutorial/selector-group-chat.ipynb
+++ b/python/packages/autogen-core/docs/src/user-guide/agentchat-user-guide/tutorial/selector-group-chat.ipynb
@@ -7,6 +7,30 @@
"# Selector Group Chat"
]
},
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "The `SelectorGroupChat` implements a team coordination pattern where participants take turns publishing messages, with the next speaker selected by a generative model (LLM) based on the conversation context. This enables dynamic and context-aware multi-agent conversations.\n",
+ "\n",
+ "\n",
+ "`SelectorGroupChat` provides several key features:\n",
+ "- Dynamic speaker selection using an LLM to analyze conversation context\n",
+ "- Configurable participant roles and descriptions\n",
+ "- Optional prevention of consecutive turns by the same speaker\n",
+ "- Customizable selection prompting\n",
+ "\n",
+ "\n",
+ "### Speaker Selection Process\n",
+ "\n",
+ "The chat uses an LLM to select the next speaker by:\n",
+ "1. Analyzing the conversation history\n",
+ "2. Evaluating participant roles and descriptions\n",
+ "3. Using a configurable prompt template to make the selection\n",
+ "4. Validating that exactly one participant is selected\n",
+ "\n"
+ ]
+ },
{
"cell_type": "code",
"execution_count": 1,
@@ -30,6 +54,14 @@
"from autogen_core.components.tools import FunctionTool"
]
},
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Defining Agents\n",
+ "The `UserProxyAgent` allows the user to input messages directly. This agent waits for user input and returns a text message or a stop message if the user decides to terminate the conversation."
+ ]
+ },
{
"cell_type": "code",
"execution_count": 2,
@@ -67,6 +99,15 @@
" return f\"Booked flight {flight} on {date}\""
]
},
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "The `ToolUseAssistantAgent` is responsible for calling external tools. In this example, two tools are defined: `flight_search` and `flight_booking`.\n",
+ "\n",
+ "Additionally, the `CodingAssistantAgent` serves as a general travel assistant with predefined behavior specified in the `system_message`."
+ ]
+ },
{
"cell_type": "code",
"execution_count": 4,
diff --git a/python/packages/autogen-core/docs/src/user-guide/agentchat-user-guide/tutorial/teams.ipynb b/python/packages/autogen-core/docs/src/user-guide/agentchat-user-guide/tutorial/teams.ipynb
index 2d414d180..ce30aee61 100644
--- a/python/packages/autogen-core/docs/src/user-guide/agentchat-user-guide/tutorial/teams.ipynb
+++ b/python/packages/autogen-core/docs/src/user-guide/agentchat-user-guide/tutorial/teams.ipynb
@@ -127,7 +127,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "### SelctorGroupChat\n",
+ "### SelectorGroupChat\n",
"\n",
"A team where a generative model (LLM) is used to select the next agent to send a message based on the current conversation history.\n"
]