A programming framework for agentic AI
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Agents\n",
"\n",
"AutoGen AgentChat provides a set of preset Agents, each with variations in how an agent might respond to messages.\n",
"All agents share the following attributes and methods:\n",
"\n",
"- {py:attr}`~autogen_agentchat.agents.BaseChatAgent.name`: The unique name of the agent.\n",
"- {py:attr}`~autogen_agentchat.agents.BaseChatAgent.description`: The description of the agent in text.\n",
"- {py:attr}`~autogen_agentchat.agents.BaseChatAgent.run`: The method that runs the agent given a task as a string or a list of messages, and returns a {py:class}`~autogen_agentchat.base.TaskResult`. **Agents are expected to be stateful and this method is expected to be called with new messages, not complete history**.\n",
"- {py:attr}`~autogen_agentchat.agents.BaseChatAgent.run_stream`: Same as {py:meth}`~autogen_agentchat.agents.BaseChatAgent.run` but returns an iterator of messages that subclass {py:class}`~autogen_agentchat.messages.BaseAgentEvent` or {py:class}`~autogen_agentchat.messages.BaseChatMessage` followed by a {py:class}`~autogen_agentchat.base.TaskResult` as the last item.\n",
"\n",
"See {py:mod}`autogen_agentchat.messages` for more information on AgentChat message types."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Assistant Agent\n",
"\n",
"{py:class}`~autogen_agentchat.agents.AssistantAgent` is a built-in agent that\n",
"uses a language model and has the ability to use tools.\n",
"\n",
"```{warning}\n",
"{py:class}`~autogen_agentchat.agents.AssistantAgent` is a \"kitchen sink\" agent\n",
"for prototyping and educational purpose -- it is very general.\n",
"Make sure you read the documentation and implementation to understand the design choices.\n",
"Once you fully understand the design, you may want to implement your own agent.\n",
"See [Custom Agent](../custom-agents.ipynb).\n",
"```"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"from autogen_agentchat.agents import AssistantAgent\n",
"from autogen_agentchat.messages import StructuredMessage\n",
"from autogen_agentchat.ui import Console\n",
"from autogen_ext.models.openai import OpenAIChatCompletionClient"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"# Define a tool that searches the web for information.\n",
"# For simplicity, we will use a mock function here that returns a static string.\n",
"async def web_search(query: str) -> str:\n",
" \"\"\"Find information on the web\"\"\"\n",
" return \"AutoGen is a programming framework for building multi-agent applications.\"\n",
"\n",
"\n",
"# Create an agent that uses the OpenAI GPT-4o model.\n",
"model_client = OpenAIChatCompletionClient(\n",
" model=\"gpt-4.1-nano\",\n",
" # api_key=\"YOUR_API_KEY\",\n",
")\n",
"agent = AssistantAgent(\n",
" name=\"assistant\",\n",
" model_client=model_client,\n",
" tools=[web_search],\n",
" system_message=\"Use tools to solve tasks.\",\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Getting Result\n",
"\n",
"We can use the {py:meth}`~autogen_agentchat.agents.BaseChatAgent.run` method to get the agent run on a given task."
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[TextMessage(source='user', models_usage=None, metadata={}, content='Find information on AutoGen', type='TextMessage'), ToolCallRequestEvent(source='assistant', models_usage=RequestUsage(prompt_tokens=61, completion_tokens=16), metadata={}, content=[FunctionCall(id='call_703i17OLXfztkuioUbkESnea', arguments='{\"query\":\"AutoGen\"}', name='web_search')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='assistant', models_usage=None, metadata={}, content=[FunctionExecutionResult(content='AutoGen is a programming framework for building multi-agent applications.', name='web_search', call_id='call_703i17OLXfztkuioUbkESnea', is_error=False)], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='assistant', models_usage=None, metadata={}, content='AutoGen is a programming framework for building multi-agent applications.', type='ToolCallSummaryMessage')]\n"
]
}
],
"source": [
"# Use asyncio.run(agent.run(...)) when running in a script.\n",
"result = await agent.run(task=\"Find information on AutoGen\")\n",
"print(result.messages)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The call to the {py:meth}`~autogen_agentchat.agents.BaseChatAgent.run` method\n",
"returns a {py:class}`~autogen_agentchat.base.TaskResult`\n",
"with the list of messages in the {py:attr}`~autogen_agentchat.base.TaskResult.messages` attribute,\n",
"which stores the agent's \"thought process\" as well as the final response.\n",
"\n",
"```{note}\n",
"It is important to note that {py:meth}`~autogen_agentchat.agents.BaseChatAgent.run`\n",
"will update the internal state of the agent -- it will add the messages to the agent's\n",
"message history. You can also call {py:meth}`~autogen_agentchat.agents.BaseChatAgent.run`\n",
"without a task to get the agent to generate responses given its current state.\n",
"```\n",
"\n",
"```{note}\n",
"Unlike in v0.2 AgentChat, the tools are executed by the same agent directly within\n",
"the same call to {py:meth}`~autogen_agentchat.agents.BaseChatAgent.run`.\n",
"By default, the agent will return the result of the tool call as the final response.\n",
"```"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Multi-Modal Input\n",
"\n",
"The {py:class}`~autogen_agentchat.agents.AssistantAgent` can handle multi-modal input\n",
"by providing the input as a {py:class}`~autogen_agentchat.messages.MultiModalMessage`."
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<img src=\"data:image/png;base64,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\"/>"
],
"text/plain": [
"<autogen_core._image.Image at 0x7f7089c83710>"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from io import BytesIO\n",
"\n",
"import PIL\n",
"import requests\n",
"from autogen_agentchat.messages import MultiModalMessage\n",
"from autogen_core import Image\n",
"\n",
"# Create a multi-modal message with random image and text.\n",
"pil_image = PIL.Image.open(BytesIO(requests.get(\"https://picsum.photos/300/200\").content))\n",
"img = Image(pil_image)\n",
"multi_modal_message = MultiModalMessage(content=[\"Can you describe the content of this image?\", img], source=\"user\")\n",
"img"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"The image depicts a scenic mountain landscape under a clear blue sky. There are several rugged mountain peaks in the background, with some clouds scattered across the sky. In the valley below, there is a body of water, possibly a lake or river, surrounded by greenery. The overall scene conveys a sense of natural beauty and tranquility.\n"
]
}
],
"source": [
"# Use asyncio.run(...) when running in a script.\n",
"result = await agent.run(task=multi_modal_message)\n",
"print(result.messages[-1].content) # type: ignore"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Streaming Messages\n",
"\n",
"We can also stream each message as it is generated by the agent by using the\n",
"{py:meth}`~autogen_agentchat.agents.BaseChatAgent.run_stream` method,\n",
"and use {py:class}`~autogen_agentchat.ui.Console` to print the messages\n",
"as they appear to the console."
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"---------- TextMessage (user) ----------\n",
"Find information on AutoGen\n",
"---------- ToolCallRequestEvent (assistant) ----------\n",
"[FunctionCall(id='call_HOTRhOzXCBm0zSqZCFbHD7YP', arguments='{\"query\":\"AutoGen\"}', name='web_search')]\n",
"[Prompt tokens: 61, Completion tokens: 16]\n",
"---------- ToolCallExecutionEvent (assistant) ----------\n",
"[FunctionExecutionResult(content='AutoGen is a programming framework for building multi-agent applications.', name='web_search', call_id='call_HOTRhOzXCBm0zSqZCFbHD7YP', is_error=False)]\n",
"---------- ToolCallSummaryMessage (assistant) ----------\n",
"AutoGen is a programming framework for building multi-agent applications.\n",
"---------- Summary ----------\n",
"Number of messages: 4\n",
"Finish reason: None\n",
"Total prompt tokens: 61\n",
"Total completion tokens: 16\n",
"Duration: 0.52 seconds\n"
]
}
],
"source": [
"async def assistant_run_stream() -> None:\n",
" # Option 1: read each message from the stream (as shown in the previous example).\n",
" # async for message in agent.run_stream(task=\"Find information on AutoGen\"):\n",
" # print(message)\n",
"\n",
" # Option 2: use Console to print all messages as they appear.\n",
" await Console(\n",
" agent.run_stream(task=\"Find information on AutoGen\"),\n",
" output_stats=True, # Enable stats printing.\n",
" )\n",
"\n",
"\n",
"# Use asyncio.run(assistant_run_stream()) when running in a script.\n",
"await assistant_run_stream()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The {py:meth}`~autogen_agentchat.agents.BaseChatAgent.run_stream` method\n",
"returns an asynchronous generator that yields each message generated by the agent,\n",
"followed by a {py:class}`~autogen_agentchat.base.TaskResult` as the last item.\n",
"\n",
"From the messages, you can observe that the assistant agent utilized the `web_search` tool to\n",
"gather information and responded based on the search results."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Using Tools and Workbench\n",
"\n",
"Large Language Models (LLMs) are typically limited to generating text or code responses. \n",
"However, many complex tasks benefit from the ability to use external tools that perform specific actions,\n",
"such as fetching data from APIs or databases.\n",
"\n",
"To address this limitation, modern LLMs can now accept a list of available tool schemas \n",
"(descriptions of tools and their arguments) and generate a tool call message. \n",
"This capability is known as **Tool Calling** or **Function Calling** and \n",
"is becoming a popular pattern in building intelligent agent-based applications.\n",
"Refer to the documentation from [OpenAI](https://platform.openai.com/docs/guides/function-calling) \n",
"and [Anthropic](https://docs.anthropic.com/en/docs/build-with-claude/tool-use) for more information about tool calling in LLMs.\n",
"\n",
"In AgentChat, the {py:class}`~autogen_agentchat.agents.AssistantAgent` can use tools to perform specific actions.\n",
"The `web_search` tool is one such tool that allows the assistant agent to search the web for information.\n",
"A single custom tool can be a Python function or a subclass of the {py:class}`~autogen_core.tools.BaseTool`.\n",
"\n",
"On the other hand, a {py:class}`~autogen_core.tools.Workbench` is a collection of tools that share state and resources.\n",
"\n",
"```{note}\n",
"For how to use model clients directly with tools and workbench, refer to the [Tools](../../core-user-guide/components/tools.ipynb)\n",
"and [Workbench](../../core-user-guide/components/workbench.ipynb) sections\n",
"in the Core User Guide.\n",
"```\n",
"\n",
"By default, when {py:class}`~autogen_agentchat.agents.AssistantAgent` executes a tool,\n",
"it will return the tool's output as a string in {py:class}`~autogen_agentchat.messages.ToolCallSummaryMessage` in its response.\n",
"If your tool does not return a well-formed string in natural language, you\n",
"can add a reflection step to have the model summarize the tool's output,\n",
"by setting the `reflect_on_tool_use=True` parameter in the {py:class}`~autogen_agentchat.agents.AssistantAgent` constructor.\n",
"\n",
"### Built-in Tools and Workbench\n",
"\n",
"AutoGen Extension provides a set of built-in tools that can be used with the Assistant Agent.\n",
"Head over to the [API documentation](../../../reference/index.md) for all the available tools\n",
"under the `autogen_ext.tools` namespace. For example, you can find the following tools:\n",
"\n",
"- {py:mod}`~autogen_ext.tools.graphrag`: Tools for using GraphRAG index.\n",
"- {py:mod}`~autogen_ext.tools.http`: Tools for making HTTP requests.\n",
"- {py:mod}`~autogen_ext.tools.langchain`: Adaptor for using LangChain tools.\n",
"- {py:mod}`~autogen_ext.tools.mcp`: Tools and workbench for using Model Chat Protocol (MCP) servers."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Function Tool\n",
"\n",
"The {py:class}`~autogen_agentchat.agents.AssistantAgent` automatically\n",
"converts a Python function into a {py:class}`~autogen_core.tools.FunctionTool`\n",
"which can be used as a tool by the agent and automatically generates the tool schema\n",
"from the function signature and docstring.\n",
"\n",
"The `web_search_func` tool is an example of a function tool.\n",
"The schema is automatically generated."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'name': 'web_search_func',\n",
" 'description': 'Find information on the web',\n",
" 'parameters': {'type': 'object',\n",
" 'properties': {'query': {'description': 'query',\n",
" 'title': 'Query',\n",
" 'type': 'string'}},\n",
" 'required': ['query'],\n",
" 'additionalProperties': False},\n",
" 'strict': False}"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from autogen_core.tools import FunctionTool\n",
"\n",
"\n",
"# Define a tool using a Python function.\n",
"async def web_search_func(query: str) -> str:\n",
" \"\"\"Find information on the web\"\"\"\n",
" return \"AutoGen is a programming framework for building multi-agent applications.\"\n",
"\n",
"\n",
"# This step is automatically performed inside the AssistantAgent if the tool is a Python function.\n",
"web_search_function_tool = FunctionTool(web_search_func, description=\"Find information on the web\")\n",
"# The schema is provided to the model during AssistantAgent's on_messages call.\n",
"web_search_function_tool.schema"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Model Context Protocol (MCP) Workbench\n",
"\n",
"The {py:class}`~autogen_agentchat.agents.AssistantAgent` can also use tools that are\n",
"served from a Model Context Protocol (MCP) server\n",
"using {py:func}`~autogen_ext.tools.mcp.McpWorkbench`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Seattle is a major city located in the state of Washington, United States. It was founded on November 13, 1851, and incorporated as a town on January 14, 1865, and later as a city on December 2, 1869. The city is named after Chief Seattle. It covers an area of approximately 142 square miles, with a population of around 737,000 as of the 2020 Census, and an estimated 755,078 residents in 2023. Seattle is known by nicknames such as The Emerald City, Jet City, and Rain City, and has mottos including The City of Flowers and The City of Goodwill. The city operates under a mayor–council government system, with Bruce Harrell serving as mayor. Key landmarks include the Space Needle, Pike Place Market, Amazon Spheres, and the Seattle Great Wheel. It is situated on the U.S. West Coast, with a diverse urban and metropolitan area that extends to a population of over 4 million in the greater metropolitan region.\n"
]
}
],
"source": [
"from autogen_agentchat.agents import AssistantAgent\n",
"from autogen_agentchat.messages import TextMessage\n",
"from autogen_ext.models.openai import OpenAIChatCompletionClient\n",
"from autogen_ext.tools.mcp import McpWorkbench, StdioServerParams\n",
"\n",
"# Get the fetch tool from mcp-server-fetch.\n",
"fetch_mcp_server = StdioServerParams(command=\"uvx\", args=[\"mcp-server-fetch\"])\n",
"\n",
"# Create an MCP workbench which provides a session to the mcp server.\n",
"async with McpWorkbench(fetch_mcp_server) as workbench: # type: ignore\n",
" # Create an agent that can use the fetch tool.\n",
" model_client = OpenAIChatCompletionClient(model=\"gpt-4.1-nano\")\n",
" fetch_agent = AssistantAgent(\n",
" name=\"fetcher\", model_client=model_client, workbench=workbench, reflect_on_tool_use=True\n",
" )\n",
"\n",
" # Let the agent fetch the content of a URL and summarize it.\n",
" result = await fetch_agent.run(task=\"Summarize the content of https://en.wikipedia.org/wiki/Seattle\")\n",
" assert isinstance(result.messages[-1], TextMessage)\n",
" print(result.messages[-1].content)\n",
"\n",
" # Close the connection to the model client.\n",
" await model_client.close()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Agent as a Tool\n",
"\n",
"Any {py:class}`~autogen_agentchat.agents.BaseChatAgent` can be used as a tool\n",
"by wrapping it in a {py:class}`~autogen_agentchat.tools.AgentTool`.\n",
"This allows for a dynamic, model-driven multi-agent workflow where\n",
"the agent can call other agents as tools to solve tasks."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Parallel Tool Calls\n",
"\n",
"Some models support parallel tool calls, which can be useful for tasks that require multiple tools to be called simultaneously.\n",
"By default, if the model client produces multiple tool calls, {py:class}`~autogen_agentchat.agents.AssistantAgent`\n",
"will call the tools in parallel.\n",
"\n",
"You may want to disable parallel tool calls when the tools have side effects that may interfere with each other, or,\n",
"when agent behavior needs to be consistent across different models.\n",
"This should be done at the model client level.\n",
"\n",
"```{important}\n",
"When using {py:class}`~autogen_agentchat.tools.AgentTool` or {py:class}`~autogen_agentchat.tools.TeamTool`,\n",
"you **must** disable parallel tool calls to avoid concurrency issues.\n",
"These tools cannot run concurrently as agents and teams maintain internal state\n",
"that would conflict with parallel execution.\n",
"```\n",
"\n",
"For {py:class}`~autogen_ext.models.openai.OpenAIChatCompletionClient` and {py:class}`~autogen_ext.models.openai.AzureOpenAIChatCompletionClient`,\n",
"set `parallel_tool_calls=False` to disable parallel tool calls."
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"model_client_no_parallel_tool_call = OpenAIChatCompletionClient(\n",
" model=\"gpt-4o\",\n",
" parallel_tool_calls=False, # type: ignore\n",
")\n",
"agent_no_parallel_tool_call = AssistantAgent(\n",
" name=\"assistant\",\n",
" model_client=model_client_no_parallel_tool_call,\n",
" tools=[web_search],\n",
" system_message=\"Use tools to solve tasks.\",\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Tool Iterations\n",
"\n",
"One model call followed by one tool call or parallel tool calls\n",
"is a single tool iteration.\n",
"By default, the {py:class}`~autogen_agentchat.agents.AssistantAgent` will\n",
"execute at most one iteration.\n",
"\n",
"The agent can be configured to execute multiple iterations until the model\n",
"stops generating tool calls or the maximum number of iterations is reached.\n",
"You can control the maximum number of iterations by setting the `max_tool_iterations` parameter\n",
"in the {py:class}`~autogen_agentchat.agents.AssistantAgent` constructor."
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"agent_loop = AssistantAgent(\n",
" name=\"assistant_loop\",\n",
" model_client=model_client_no_parallel_tool_call,\n",
" tools=[web_search],\n",
" system_message=\"Use tools to solve tasks.\",\n",
" max_tool_iterations=10, # At most 10 iterations of tool calls before stopping the loop.\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Structured Output\n",
"\n",
"Structured output allows models to return structured JSON text with pre-defined schema\n",
"provided by the application. Different from JSON-mode, the schema can be provided\n",
"as a [Pydantic BaseModel](https://docs.pydantic.dev/latest/concepts/models/)\n",
"class, which can also be used to validate the output.\n",
"\n",
"Once you specify the base model class in the `output_content_type` parameter\n",
"of the {py:class}`~autogen_agentchat.agents.AssistantAgent` constructor,\n",
"the agent will respond with a {py:class}`~autogen_agentchat.messages.StructuredMessage`\n",
"whose `content`'s type is the type of the base model class.\n",
"\n",
"This way, you can integrate agent's response directly into your application\n",
"and use the model's output as a structured object.\n",
"\n",
"```{note}\n",
"When the `output_content_type` is set, it by default requires the agent to reflect on the tool use\n",
"and return the a structured output message based on the tool call result.\n",
"You can disable this behavior by setting `reflect_on_tool_use=False` explictly.\n",
"```\n",
"\n",
"Structured output is also useful for incorporating Chain-of-Thought\n",
"reasoning in the agent's responses.\n",
"See the example below for how to use structured output with the assistant agent."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"---------- user ----------\n",
"I am happy.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"---------- assistant ----------\n",
"{\n",
" \"thoughts\": \"The user explicitly states they are happy.\",\n",
" \"response\": \"happy\"\n",
"}\n",
"Thought: The user explicitly states they are happy.\n",
"Response: happy\n"
]
}
],
"source": [
"from typing import Literal\n",
"\n",
"from pydantic import BaseModel\n",
"\n",
"\n",
"# The response format for the agent as a Pydantic base model.\n",
"class AgentResponse(BaseModel):\n",
" thoughts: str\n",
" response: Literal[\"happy\", \"sad\", \"neutral\"]\n",
"\n",
"\n",
"# Create an agent that uses the OpenAI GPT-4o model.\n",
"model_client = OpenAIChatCompletionClient(model=\"gpt-4o\")\n",
"agent = AssistantAgent(\n",
" \"assistant\",\n",
" model_client=model_client,\n",
" system_message=\"Categorize the input as happy, sad, or neutral following the JSON format.\",\n",
" # Define the output content type of the agent.\n",
" output_content_type=AgentResponse,\n",
")\n",
"\n",
"result = await Console(agent.run_stream(task=\"I am happy.\"))\n",
"\n",
"# Check the last message in the result, validate its type, and print the thoughts and response.\n",
"assert isinstance(result.messages[-1], StructuredMessage)\n",
"assert isinstance(result.messages[-1].content, AgentResponse)\n",
"print(\"Thought: \", result.messages[-1].content.thoughts)\n",
"print(\"Response: \", result.messages[-1].content.response)\n",
"await model_client.close()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Streaming Tokens\n",
"\n",
"You can stream the tokens generated by the model client by setting `model_client_stream=True`.\n",
"This will cause the agent to yield {py:class}`~autogen_agentchat.messages.ModelClientStreamingChunkEvent` messages\n",
"in {py:meth}`~autogen_agentchat.agents.BaseChatAgent.run_stream`.\n",
"\n",
"The underlying model API must support streaming tokens for this to work.\n",
"Please check with your model provider to see if this is supported."
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"source='user' models_usage=None metadata={} content='Name two cities in South America' type='TextMessage'\n",
"source='assistant' models_usage=None metadata={} content='Two' type='ModelClientStreamingChunkEvent'\n",
"source='assistant' models_usage=None metadata={} content=' cities' type='ModelClientStreamingChunkEvent'\n",
"source='assistant' models_usage=None metadata={} content=' in' type='ModelClientStreamingChunkEvent'\n",
"source='assistant' models_usage=None metadata={} content=' South' type='ModelClientStreamingChunkEvent'\n",
"source='assistant' models_usage=None metadata={} content=' America' type='ModelClientStreamingChunkEvent'\n",
"source='assistant' models_usage=None metadata={} content=' are' type='ModelClientStreamingChunkEvent'\n",
"source='assistant' models_usage=None metadata={} content=' Buenos' type='ModelClientStreamingChunkEvent'\n",
"source='assistant' models_usage=None metadata={} content=' Aires' type='ModelClientStreamingChunkEvent'\n",
"source='assistant' models_usage=None metadata={} content=' in' type='ModelClientStreamingChunkEvent'\n",
"source='assistant' models_usage=None metadata={} content=' Argentina' type='ModelClientStreamingChunkEvent'\n",
"source='assistant' models_usage=None metadata={} content=' and' type='ModelClientStreamingChunkEvent'\n",
"source='assistant' models_usage=None metadata={} content=' São' type='ModelClientStreamingChunkEvent'\n",
"source='assistant' models_usage=None metadata={} content=' Paulo' type='ModelClientStreamingChunkEvent'\n",
"source='assistant' models_usage=None metadata={} content=' in' type='ModelClientStreamingChunkEvent'\n",
"source='assistant' models_usage=None metadata={} content=' Brazil' type='ModelClientStreamingChunkEvent'\n",
"source='assistant' models_usage=None metadata={} content='.' type='ModelClientStreamingChunkEvent'\n",
"source='assistant' models_usage=RequestUsage(prompt_tokens=0, completion_tokens=0) metadata={} content='Two cities in South America are Buenos Aires in Argentina and São Paulo in Brazil.' type='TextMessage'\n",
"messages=[TextMessage(source='user', models_usage=None, metadata={}, content='Name two cities in South America', type='TextMessage'), TextMessage(source='assistant', models_usage=RequestUsage(prompt_tokens=0, completion_tokens=0), metadata={}, content='Two cities in South America are Buenos Aires in Argentina and São Paulo in Brazil.', type='TextMessage')] stop_reason=None\n"
]
}
],
"source": [
"model_client = OpenAIChatCompletionClient(model=\"gpt-4o\")\n",
"\n",
"streaming_assistant = AssistantAgent(\n",
" name=\"assistant\",\n",
" model_client=model_client,\n",
" system_message=\"You are a helpful assistant.\",\n",
" model_client_stream=True, # Enable streaming tokens.\n",
")\n",
"\n",
"# Use an async function and asyncio.run() in a script.\n",
"async for message in streaming_assistant.run_stream(task=\"Name two cities in South America\"): # type: ignore\n",
" print(message)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"You can see the streaming chunks in the output above.\n",
"The chunks are generated by the model client and are yielded by the agent as they are received.\n",
"The final response, the concatenation of all the chunks, is yielded right after the last chunk."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Using Model Context\n",
"\n",
"{py:class}`~autogen_agentchat.agents.AssistantAgent` has a `model_context`\n",
"parameter that can be used to pass in a {py:class}`~autogen_core.model_context.ChatCompletionContext`\n",
"object. This allows the agent to use different model contexts, such as\n",
"{py:class}`~autogen_core.model_context.BufferedChatCompletionContext` to\n",
"limit the context sent to the model.\n",
"\n",
"By default, {py:class}`~autogen_agentchat.agents.AssistantAgent` uses\n",
"the {py:class}`~autogen_core.model_context.UnboundedChatCompletionContext`\n",
"which sends the full conversation history to the model. To limit the context\n",
"to the last `n` messages, you can use the {py:class}`~autogen_core.model_context.BufferedChatCompletionContext`.\n",
"To limit the context by token count, you can use the\n",
"{py:class}`~autogen_core.model_context.TokenLimitedChatCompletionContext`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from autogen_core.model_context import BufferedChatCompletionContext\n",
"\n",
"# Create an agent that uses only the last 5 messages in the context to generate responses.\n",
"agent = AssistantAgent(\n",
" name=\"assistant\",\n",
" model_client=model_client,\n",
" tools=[web_search],\n",
" system_message=\"Use tools to solve tasks.\",\n",
" model_context=BufferedChatCompletionContext(buffer_size=5), # Only use the last 5 messages in the context.\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Other Preset Agents\n",
"\n",
"The following preset agents are available:\n",
"\n",
"- {py:class}`~autogen_agentchat.agents.UserProxyAgent`: An agent that takes user input returns it as responses.\n",
"- {py:class}`~autogen_agentchat.agents.CodeExecutorAgent`: An agent that can execute code.\n",
"- {py:class}`~autogen_ext.agents.openai.OpenAIAssistantAgent`: An agent that is backed by an OpenAI Assistant, with ability to use custom tools.\n",
"- {py:class}`~autogen_ext.agents.web_surfer.MultimodalWebSurfer`: A multi-modal agent that can search the web and visit web pages for information.\n",
"- {py:class}`~autogen_ext.agents.file_surfer.FileSurfer`: An agent that can search and browse local files for information.\n",
"- {py:class}`~autogen_ext.agents.video_surfer.VideoSurfer`: An agent that can watch videos for information."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Next Step\n",
"\n",
"Having explored the usage of the {py:class}`~autogen_agentchat.agents.AssistantAgent`, we can now proceed to the next section to learn about the teams feature in AgentChat.\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<!-- ## CodingAssistantAgent\n",
"\n",
"Generates responses (text and code) using an LLM upon receipt of a message. It takes a `system_message` argument that defines or sets the tone for how the agent's LLM should respond. \n",
"\n",
"```python\n",
"\n",
"writing_assistant_agent = CodingAssistantAgent(\n",
" name=\"writing_assistant_agent\",\n",
" system_message=\"You are a helpful assistant that solve tasks by generating text responses and code.\",\n",
" model_client=model_client,\n",
")\n",
"`\n",
"\n",
"We can explore or test the behavior of the agent by sending a message to it using the {py:meth}`~autogen_agentchat.agents.BaseChatAgent.on_messages` method. \n",
"\n",
"```python\n",
"result = await writing_assistant_agent.on_messages(\n",
" messages=[\n",
" TextMessage(content=\"What is the weather right now in France?\", source=\"user\"),\n",
" ],\n",
" cancellation_token=CancellationToken(),\n",
")\n",
"print(result) -->"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "python",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.11"
}
},
"nbformat": 4,
"nbformat_minor": 2
}