Cross-Framework LLM Tool Integration with AG2

In this tutorial, we demonstrate how to integrate LLM tools from various frameworks—including LangChain Tools, CrewAI Tools, and PydanticAI Tools into the AG2 framework. This process enables smooth interoperability between these systems, allowing developers to leverage the unique capabilities of each toolset within AG2’s flexible agent-based architecture. By the end of this guide, you will understand how to configure agents, adapt these tools for use in AG2, and validate the integration through practical examples.

LangChain Tools Integration

LangChain is a popular framework that offers a wide range of tools to work with LLMs. LangChain has already implemented a variety of tools that can be easily integrated into AG2. You can explore the available tools in the LangChain Community Tools folder. These tools, such as those for querying APIs, web scraping, and text generation, can be quickly incorporated into AG2, providing powerful functionality for your agents.

Installation

To integrate LangChain tools into the AG2 framework, install the required dependencies:

pip install ag2[interop-langchain]

Additionally, this notebook uses LangChain’s Wikipedia Tool, which requires the wikipedia package. Install it with:

pip install wikipedia

Imports

Import necessary modules and tools.

WikipediaQueryRun and WikipediaAPIWrapper: Tools for querying Wikipedia.
AssistantAgent and UserProxyAgent: Agents that facilitate communication in the AG2 framework.
Interoperability: This module acts as a bridge, making it easier to integrate LangChain tools with AG2’s architecture.

import os

from langchain_community.tools import WikipediaQueryRun
from langchain_community.utilities import WikipediaAPIWrapper

from autogen import AssistantAgent, UserProxyAgent
from autogen.interop import Interoperability

/usr/local/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
  from .autonotebook import tqdm as notebook_tqdm
/usr/local/lib/python3.11/site-packages/flaml/__init__.py:20: UserWarning: flaml.automl is not available. Please install flaml[automl] to enable AutoML functionalities.
  warnings.warn("flaml.automl is not available. Please install flaml[automl] to enable AutoML functionalities.")

Agent Configuration

Configure the agents for the interaction.

config_list defines the LLM configurations, including the model and API key.
UserProxyAgent simulates user inputs without requiring actual human interaction (set to NEVER).
AssistantAgent represents the AI agent, configured with the LLM settings.

config_list = [{"model": "gpt-4o", "api_key": os.environ["OPENAI_API_KEY"]}]
user_proxy = UserProxyAgent(
    name="User",
    human_input_mode="NEVER",
)

chatbot = AssistantAgent(
    name="chatbot",
    llm_config={"config_list": config_list},
)

Tool Integration

Initialize and register the LangChain tool with AG2.
WikipediaAPIWrapper: Configured to fetch the top 1 result from Wikipedia with a maximum of 1000 characters per document.
WikipediaQueryRun: A LangChain tool that executes Wikipedia queries.
Interoperability: Converts the LangChain tool into a format compatible with the AG2 framework.
ag2_tool.register_for_execution(user_proxy): Registers the tool for use by the user_proxy agent.
ag2_tool.register_for_llm(chatbot): Registers the tool for integration with the chatbot agent.

api_wrapper = WikipediaAPIWrapper(top_k_results=1, doc_content_chars_max=1000)
langchain_tool = WikipediaQueryRun(api_wrapper=api_wrapper)

interop = Interoperability()
ag2_tool = interop.convert_tool(tool=langchain_tool, type="langchain")

ag2_tool.register_for_execution(user_proxy)
ag2_tool.register_for_llm(chatbot)

message = "Tell me about the history of the United States"
user_proxy.initiate_chat(recipient=chatbot, message=message, max_turns=2)

User (to chatbot):

Tell me about the history of the United States

--------------------------------------------------------------------------------
chatbot (to User):

***** Suggested tool call (call_0x3F3lbGj9tth5xxuipsZk3Y): wikipedia *****
Arguments: 
{"tool_input":{"query":"history of the United States"}}
**************************************************************************

--------------------------------------------------------------------------------

>>>>>>>> EXECUTING FUNCTION wikipedia...
User (to chatbot):

***** Response from calling tool (call_0x3F3lbGj9tth5xxuipsZk3Y) *****
Page: History of the United States
Summary: The history of the lands that became the United States began with the arrival of the first people in the Americas around 15,000 BC. After European colonization of North America began in the late 15th century, wars and epidemics decimated Indigenous societies. By the 1760s, the thirteen British colonies were established. The Southern Colonies built an agricultural system on slave labor, enslaving millions from Africa. After defeating France, the British Parliament imposed a series of taxes; resistance to these taxes, especially the Boston Tea Party in 1773, led to Parliament issuing the Intolerable Acts designed to end self-government.
In 1776, the United States declared its independence. Led by General George Washington, it won the Revolutionary War in 1783. The Constitution was adopted in 1789, and a Bill of Rights was added in 1791 to guarantee inalienable rights. Washington, the first president, and his adviser Alexander Hamilton created a
**********************************************************************

--------------------------------------------------------------------------------
chatbot (to User):

The history of the United States began with the arrival of the first people in the Americas around 15,000 BC. European colonization commenced in the late 15th century, and this led to significant impacts on Indigenous societies, including wars and epidemics that decimated populations. By the 1760s, thirteen British colonies were firmly established. In the Southern Colonies, an agricultural economy heavily reliant on slave labor developed, involving the enslavement of millions of Africans.

Tensions arose in the 18th century between these colonies and Britain, primarily due to taxation without representation, which culminated in events such as the Boston Tea Party in 1773. These events prompted the British Parliament to pass the Intolerable Acts in an attempt to suppress self-governance in the colonies.

In 1776, the colonies declared their independence, forming the United States of America. Under the leadership of General George Washington, the colonies won the Revolutionary War against Britain, achieving victory in 1783. The United States adopted its Constitution in 1789, followed by the Bill of Rights in 1791, which enshrined fundamental rights.

George Washington became the first President, and along with his adviser Alexander Hamilton, began shaping the new nation's governmental and economic structures. This marked the early stages of the United States' journey to becoming an independent and unified country. TERMINATE

--------------------------------------------------------------------------------

ChatResult(chat_id=None, chat_history=[{'content': 'Tell me about the history of the United States', 'role': 'assistant', 'name': 'User'}, {'tool_calls': [{'id': 'call_0x3F3lbGj9tth5xxuipsZk3Y', 'function': {'arguments': '{"tool_input":{"query":"history of the United States"}}', 'name': 'wikipedia'}, 'type': 'function'}], 'content': None, 'role': 'assistant'}, {'content': 'Page: History of the United States\nSummary: The history of the lands that became the United States began with the arrival of the first people in the Americas around 15,000 BC. After European colonization of North America began in the late 15th century, wars and epidemics decimated Indigenous societies. By the 1760s, the thirteen British colonies were established. The Southern Colonies built an agricultural system on slave labor, enslaving millions from Africa. After defeating France, the British Parliament imposed a series of taxes; resistance to these taxes, especially the Boston Tea Party in 1773, led to Parliament issuing the Intolerable Acts designed to end self-government.\nIn 1776, the United States declared its independence. Led by General George Washington, it won the Revolutionary War in 1783. The Constitution was adopted in 1789, and a Bill of Rights was added in 1791 to guarantee inalienable rights. Washington, the first president, and his adviser Alexander Hamilton created a', 'tool_responses': [{'tool_call_id': 'call_0x3F3lbGj9tth5xxuipsZk3Y', 'role': 'tool', 'content': 'Page: History of the United States\nSummary: The history of the lands that became the United States began with the arrival of the first people in the Americas around 15,000 BC. After European colonization of North America began in the late 15th century, wars and epidemics decimated Indigenous societies. By the 1760s, the thirteen British colonies were established. The Southern Colonies built an agricultural system on slave labor, enslaving millions from Africa. After defeating France, the British Parliament imposed a series of taxes; resistance to these taxes, especially the Boston Tea Party in 1773, led to Parliament issuing the Intolerable Acts designed to end self-government.\nIn 1776, the United States declared its independence. Led by General George Washington, it won the Revolutionary War in 1783. The Constitution was adopted in 1789, and a Bill of Rights was added in 1791 to guarantee inalienable rights. Washington, the first president, and his adviser Alexander Hamilton created a'}], 'role': 'tool', 'name': 'User'}, {'content': "The history of the United States began with the arrival of the first people in the Americas around 15,000 BC. European colonization commenced in the late 15th century, and this led to significant impacts on Indigenous societies, including wars and epidemics that decimated populations. By the 1760s, thirteen British colonies were firmly established. In the Southern Colonies, an agricultural economy heavily reliant on slave labor developed, involving the enslavement of millions of Africans.\n\nTensions arose in the 18th century between these colonies and Britain, primarily due to taxation without representation, which culminated in events such as the Boston Tea Party in 1773. These events prompted the British Parliament to pass the Intolerable Acts in an attempt to suppress self-governance in the colonies.\n\nIn 1776, the colonies declared their independence, forming the United States of America. Under the leadership of General George Washington, the colonies won the Revolutionary War against Britain, achieving victory in 1783. The United States adopted its Constitution in 1789, followed by the Bill of Rights in 1791, which enshrined fundamental rights.\n\nGeorge Washington became the first President, and along with his adviser Alexander Hamilton, began shaping the new nation's governmental and economic structures. This marked the early stages of the United States' journey to becoming an independent and unified country. TERMINATE", 'role': 'user', 'name': 'chatbot'}], summary="The history of the United States began with the arrival of the first people in the Americas around 15,000 BC. European colonization commenced in the late 15th century, and this led to significant impacts on Indigenous societies, including wars and epidemics that decimated populations. By the 1760s, thirteen British colonies were firmly established. In the Southern Colonies, an agricultural economy heavily reliant on slave labor developed, involving the enslavement of millions of Africans.\n\nTensions arose in the 18th century between these colonies and Britain, primarily due to taxation without representation, which culminated in events such as the Boston Tea Party in 1773. These events prompted the British Parliament to pass the Intolerable Acts in an attempt to suppress self-governance in the colonies.\n\nIn 1776, the colonies declared their independence, forming the United States of America. Under the leadership of General George Washington, the colonies won the Revolutionary War against Britain, achieving victory in 1783. The United States adopted its Constitution in 1789, followed by the Bill of Rights in 1791, which enshrined fundamental rights.\n\nGeorge Washington became the first President, and along with his adviser Alexander Hamilton, began shaping the new nation's governmental and economic structures. This marked the early stages of the United States' journey to becoming an independent and unified country. ", cost={'usage_including_cached_inference': {'total_cost': 0.00639, 'gpt-4o-2024-08-06': {'cost': 0.00639, 'prompt_tokens': 1356, 'completion_tokens': 300, 'total_tokens': 1656}}, 'usage_excluding_cached_inference': {'total_cost': 0}}, human_input=[])

CrewAI Tools Integration

CrewAI provides a variety of powerful tools designed for tasks such as web scraping, search, code interpretation, and more. These tools are easy to integrate into the AG2 framework, allowing you to enhance your agents with advanced capabilities. You can explore the full list of available tools in the CrewAI Tools repository.

Installation

Install the required packages for integrating CrewAI tools into the AG2 framework. This ensures all dependencies for both frameworks are installed.

pip install ag2[interop-crewai]

Imports

Import necessary modules and tools.

ScrapeWebsiteTool are the CrewAI tools for web scraping
AssistantAgent and UserProxyAgent are core AG2 classes.
Interoperability: This module acts as a bridge, making it easier to integrate CrewAI tools with AG2’s architecture.

import os

from crewai_tools import ScrapeWebsiteTool

from autogen import AssistantAgent, UserProxyAgent
from autogen.interop import Interoperability

Agent Configuration

Configure the agents for the interaction.

config_list defines the LLM configurations, including the model and API key.
UserProxyAgent simulates user inputs without requiring actual human interaction (set to NEVER).
AssistantAgent represents the AI agent, configured with the LLM settings.

config_list = [{"model": "gpt-4o", "api_key": os.environ["OPENAI_API_KEY"]}]
user_proxy = UserProxyAgent(
    name="User",
    human_input_mode="NEVER",
)

chatbot = AssistantAgent(
    name="chatbot",
    llm_config={"config_list": config_list},
)

Tool Integration

Initialize and register the CrewAI tool with AG2.

crewai_tool is an instance of the ScrapeWebsiteTool from CrewAI.
Interoperability converts the CrewAI tool to make it usable in AG2.
register_for_execution and register_for_llm allow the tool to work with the UserProxyAgent and AssistantAgent.

interop = Interoperability()
crewai_tool = ScrapeWebsiteTool()
ag2_tool = interop.convert_tool(tool=crewai_tool, type="crewai")

ag2_tool.register_for_execution(user_proxy)
ag2_tool.register_for_llm(chatbot)

message = "Scrape the website https://ag2.ai/"

chat_result = user_proxy.initiate_chat(recipient=chatbot, message=message, max_turns=2)

User (to chatbot):

Scrape the website https://ag2.ai/

--------------------------------------------------------------------------------
chatbot (to User):

***** Suggested tool call (call_LdavPAKRVqcxteSplbAXedfp): Read_website_content *****
Arguments: 
{"args":{"website_url":"https://ag2.ai/"}}
*************************************************************************************

--------------------------------------------------------------------------------

>>>>>>>> EXECUTING FUNCTION Read_website_content...
Using Tool: Read website content
User (to chatbot):

***** Response from calling tool (call_LdavPAKRVqcxteSplbAXedfp) *****

AgentOS
Join our growing community of over 20,000 agent builders Join our growing community of over 20,000 agent builders The Open-Source AgentOS Build production-ready multi-agent systems in minutes, not months. Github Discord The End-to-End Platform for Multi-Agent Automation The End-to-End Platform for Multi-Agent Automation Flexible Agent Construction and Orchestration Create specialized agents that work together seamlessly. AG2 makes it easy to define roles, configure behaviors, and orchestrate collaboration - all through simple, intuitive code. → Assistant agents for problem-solving → Executor agents for taking action → Critic agents for validation → Group chat managers for coordination Built-in Conversation Patterns Built-in Conversation Patterns Stop wrestling with agent coordination. AG2 handles message routing, state management, and conversation flow automatically. → Two-agent conversations → Group chats with dynamic speaker selection → Sequential chats with context carryover → Nested conversations for modularity Seamless Human-AI collaboration Seamless Human-AI collaboration Seamlessly integrate human oversight and input into your agent workflows. → Configurable human input modes → Flexible intervention points → Optional human approval workflows → Interactive conversation interfaces → Context-aware human handoff Roadmap AG2 STUDIO → Visual agent system design → Real-time testing and debugging → One-click deployment to production → Perfect for prototyping and MVPs AG2 STUDIO → Visual agent system design → Real-time testing and debugging → One-click deployment to production → Perfect for prototyping and MVPs AG2 STUDIO → Visual agent system design → Real-time testing and debugging → One-click deployment to production → Perfect for prototyping and MVPs AG2 MARKETPLACE → Share and monetize your agents → Discover pre-built solution templates → Quick-start your agent development → Connect with other builders AG2 MARKETPLACE → Share and monetize your agents → Discover pre-built solution templates → Quick-start your agent development → Connect with other builders AG2 MARKETPLACE → Share and monetize your agents → Discover pre-built solution templates → Quick-start your agent development → Connect with other builders SCALING TOOLS → Zero to production deployment guides → Usage analytics and cost optimization → Team collaboration features → Enterprise-ready security controls SCALING TOOLS → Zero to production deployment guides → Usage analytics and cost optimization → Team collaboration features → Enterprise-ready security controls SCALING TOOLS → Zero to production deployment guides → Usage analytics and cost optimization → Team collaboration features → Enterprise-ready security controls AG2 STUDIO → Visual agent system design → Real-time testing and debugging → One-click deployment to production → Perfect for prototyping and MVPs AG2 STUDIO → Visual agent system design → Real-time testing and debugging → One-click deployment to production → Perfect for prototyping and MVPs AG2 MARKETPLACE → Share and monetize your agents → Discover pre-built solution templates → Quick-start your agent development → Connect with other builders AG2 MARKETPLACE → Share and monetize your agents → Discover pre-built solution templates → Quick-start your agent development → Connect with other builders SCALING TOOLS → Zero to production deployment guides → Usage analytics and cost optimization → Team collaboration features → Enterprise-ready security controls SCALING TOOLS → Zero to production deployment guides → Usage analytics and cost optimization → Team collaboration features → Enterprise-ready security controls Whether you're a solo founder prototyping the next big AI product, or an enterprise team deploying at scale we're building AG2 for you. This is AgentOS - making multi-agent development accessible to everyone. Github Join Our Growing Community Join Our Growing Community → 20,000+ active agent builders → Daily technical discussions → Weekly community calls → Open RFC process → Regular contributor events (Coming soon) Discord Problem Features Roadmap Community Documentation Problem Features Roadmap Community Documentation Problem Features Roadmap Community Documentation

**********************************************************************

--------------------------------------------------------------------------------
chatbot (to User):

The website https://ag2.ai/ provides the following information:

- **AgentOS Community**: Over 20,000 agent builders are part of the community.
- **Open-Source AgentOS**: It focuses on building production-ready multi-agent systems quickly.
- **Platform for Multi-Agent Automation**: Includes flexible agent construction and orchestration, and built-in conversation patterns.
  - **Agent Types**:
    - Assistant agents for problem-solving.
    - Executor agents for taking action.
    - Critic agents for validation.
    - Group chat managers for coordination.
  - **Conversation Patterns**:
    - Two-agent conversations.
    - Group chats with dynamic speaker selection.
    - Sequential and nested conversations.

- **Human-AI Collaboration**: Allows integration of human oversight and input with agents.
- **AG2 Studio**: A tool for visual agent system design, real-time testing, debugging, and deployment.
- **AG2 Marketplace**: Platform for sharing, monetizing agents, and discovering templates.
- **Scaling Tools**: Guides for deployment, usage analytics, cost optimization, and team collaboration features.
  
The tagline suggests that AgentOS is designed to make multi-agent development accessible, catering to both solo founders and enterprise teams.

TERMINATE

--------------------------------------------------------------------------------

print(chat_result.summary)

The website https://ag2.ai/ provides the following information:

- **AgentOS Community**: Over 20,000 agent builders are part of the community.
- **Open-Source AgentOS**: It focuses on building production-ready multi-agent systems quickly.
- **Platform for Multi-Agent Automation**: Includes flexible agent construction and orchestration, and built-in conversation patterns.
  - **Agent Types**:
    - Assistant agents for problem-solving.
    - Executor agents for taking action.
    - Critic agents for validation.
    - Group chat managers for coordination.
  - **Conversation Patterns**:
    - Two-agent conversations.
    - Group chats with dynamic speaker selection.
    - Sequential and nested conversations.

- **Human-AI Collaboration**: Allows integration of human oversight and input with agents.
- **AG2 Studio**: A tool for visual agent system design, real-time testing, debugging, and deployment.
- **AG2 Marketplace**: Platform for sharing, monetizing agents, and discovering templates.
- **Scaling Tools**: Guides for deployment, usage analytics, cost optimization, and team collaboration features.
  
The tagline suggests that AgentOS is designed to make multi-agent development accessible, catering to both solo founders and enterprise teams.

PydanticAI Tools Integration

PydanticAI is a newer framework that offers powerful capabilities for working with LLMs. Although it currently does not have a repository with pre-built tools, it provides features like dependency injection, allowing you to inject a “Context” into a tool for better execution without relying on LLMs. This context can be used for passing parameters or managing state during the execution of a tool. While the framework is still growing, you can integrate its tools into AG2 to enhance agent capabilities, especially for tasks that involve structured data and context-driven logic.

Installation

To integrate LangChain tools into the AG2 framework, install the required dependencies:

pip install ag2[interop-pydantic-ai]

Imports

Import necessary modules and tools.

BaseModel: Used to define data structures for tool inputs and outputs.
RunContext: Provides context during the execution of tools.
PydanticAITool: Represents a tool in the PydanticAI framework.
AssistantAgent and UserProxyAgent: Agents that facilitate communication in the AG2 framework.
Interoperability: This module acts as a bridge, making it easier to integrate PydanticAI tools with AG2’s architecture.

import os
from typing import Optional

from pydantic import BaseModel
from pydantic_ai import RunContext
from pydantic_ai.tools import Tool as PydanticAITool

from autogen import AssistantAgent, UserProxyAgent
from autogen.interop import Interoperability

Agent Configuration

Configure the agents for the interaction.

config_list defines the LLM configurations, including the model and API key.
UserProxyAgent simulates user inputs without requiring actual human interaction (set to NEVER).
AssistantAgent represents the AI agent, configured with the LLM settings.

config_list = [{"model": "gpt-4o", "api_key": os.environ["OPENAI_API_KEY"]}]
user_proxy = UserProxyAgent(
    name="User",
    human_input_mode="NEVER",
)

chatbot = AssistantAgent(
    name="chatbot",
    llm_config={"config_list": config_list},
)

Tool Integration

Integrate the PydanticAI tool with AG2.

Define a Player model using BaseModel to structure the input data.
Use RunContext to securely inject dependencies (like the Player instance) into the tool function without exposing them to the LLM.
Implement get_player to define the tool’s functionality, accessing ctx.deps for injected data.
Convert the tool to an AG2-compatible format with Interoperability and register it for execution and LLM communication.
Convert the PydanticAI tool into an AG2-compatible format using convert_tool.
Register the tool for both execution and communication with the LLM by associating it with the user_proxy and chatbot.

class Player(BaseModel):
    name: str
    age: int


def get_player(ctx: RunContext[Player], additional_info: Optional[str] = None) -> str:  # type: ignore[valid-type]
    """Get the player's name.

    Args:
        additional_info: Additional information which can be used.
    """
    return f"Name: {ctx.deps.name}, Age: {ctx.deps.age}, Additional info: {additional_info}"  # type: ignore[attr-defined]


interop = Interoperability()
pydantic_ai_tool = PydanticAITool(get_player, takes_ctx=True)

# player will be injected as a dependency
player = Player(name="Luka", age=25)
ag2_tool = interop.convert_tool(tool=pydantic_ai_tool, type="pydanticai", deps=player)

ag2_tool.register_for_execution(user_proxy)
ag2_tool.register_for_llm(chatbot)

Initiate a conversation between the UserProxyAgent and the AssistantAgent.

Use the initiate_chat method to send a message from the user_proxy to the chatbot.
In this example, the user requests the chatbot to retrieve player information, providing “goal keeper” as additional context.
The Player instance is securely injected into the tool using RunContext, ensuring the chatbot can retrieve and use this data during the interaction.

user_proxy.initiate_chat(
    recipient=chatbot, message="Get player, for additional information use 'goal keeper'", max_turns=3
)

User (to chatbot):

Get player, for additional information use 'goal keeper'

--------------------------------------------------------------------------------
chatbot (to User):

***** Suggested tool call (call_6zAckrEDxxbffyNc4XtX5rIM): get_player *****
Arguments: 
{"additional_info":"goal keeper"}
***************************************************************************

--------------------------------------------------------------------------------

>>>>>>>> EXECUTING FUNCTION get_player...
User (to chatbot):

***** Response from calling tool (call_6zAckrEDxxbffyNc4XtX5rIM) *****
Name: Luka, Age: 25, Additional info: goal keeper
**********************************************************************

--------------------------------------------------------------------------------
chatbot (to User):

The player's name is Luka, aged 25, and he is a goal keeper. TERMINATE

--------------------------------------------------------------------------------
User (to chatbot):



--------------------------------------------------------------------------------
chatbot (to User):

It looks like there isn't any additional input from your side. If you need further assistance, feel free to ask! TERMINATE

--------------------------------------------------------------------------------

ChatResult(chat_id=None, chat_history=[{'content': "Get player, for additional information use 'goal keeper'", 'role': 'assistant', 'name': 'User'}, {'tool_calls': [{'id': 'call_6zAckrEDxxbffyNc4XtX5rIM', 'function': {'arguments': '{"additional_info":"goal keeper"}', 'name': 'get_player'}, 'type': 'function'}], 'content': None, 'role': 'assistant'}, {'content': 'Name: Luka, Age: 25, Additional info: goal keeper', 'tool_responses': [{'tool_call_id': 'call_6zAckrEDxxbffyNc4XtX5rIM', 'role': 'tool', 'content': 'Name: Luka, Age: 25, Additional info: goal keeper'}], 'role': 'tool', 'name': 'User'}, {'content': "The player's name is Luka, aged 25, and he is a goal keeper. TERMINATE", 'role': 'user', 'name': 'chatbot'}, {'content': '', 'role': 'assistant', 'name': 'User'}, {'content': "It looks like there isn't any additional input from your side. If you need further assistance, feel free to ask! TERMINATE", 'role': 'user', 'name': 'chatbot'}], summary="It looks like there isn't any additional input from your side. If you need further assistance, feel free to ask! ", cost={'usage_including_cached_inference': {'total_cost': 0.0048325, 'gpt-4o-2024-08-06': {'cost': 0.0048325, 'prompt_tokens': 1677, 'completion_tokens': 64, 'total_tokens': 1741}}, 'usage_excluding_cached_inference': {'total_cost': 0}}, human_input=[])

Enhanced Swarm Orchestration with AG2 RealtimeAgent in a Swarm Orchestration

On this page

LangChain Tools Integration
Installation
Imports
Agent Configuration
Tool Integration
CrewAI Tools Integration
Installation
Imports
Agent Configuration
Tool Integration
PydanticAI Tools Integration
Installation
Imports
Agent Configuration
Tool Integration

Examples

​LangChain Tools Integration

​Installation

​Imports

​Agent Configuration

​Tool Integration

​CrewAI Tools Integration

​Installation

​Imports

​Agent Configuration

​Tool Integration

​PydanticAI Tools Integration

​Installation

​Imports

​Agent Configuration

​Tool Integration

LangChain Tools Integration

Installation

Imports

Agent Configuration

Tool Integration

CrewAI Tools Integration

Installation

Imports

Agent Configuration

Tool Integration

PydanticAI Tools Integration

Installation

Imports

Agent Configuration

Tool Integration