Foglio Informativo del Framework Multi-Agente AutoGen

Panoramica

AutoGen è un innovativo framework open-source sviluppato da Microsoft Research che rivoluziona lo sviluppo di applicazioni con Large Language Model (LLM) abilitando conversazioni multi-agente sofisticate. A differenza dei sistemi tradizionali a singolo agente, AutoGen consente agli sviluppatori di creare applicazioni complesse componendo più agenti AI specializzati che possono conversare tra loro, collaborare su attività e coinvolgere persino esseri umani nel processo in modo fluido.

Ciò che rende AutoGen particolarmente potente è il suo focus sulla conversazione come meccanismo primario di interazione tra agenti. Questo approccio consente una collaborazione naturale, flessibile e dinamica tra agenti, rispecchiando il modo in cui i team umani lavorano insieme per risolvere problemi complessi. AutoGen fornisce un ricco set di strumenti per definire ruoli degli agenti, capacità e protocolli di comunicazione, rendendo possibile costruire sistemi altamente adattabili e intelligenti in grado di affrontare un'ampia gamma di attività, dalla generazione di codice e analisi dei dati alla scrittura creativa e alla pianificazione strategica.

Il framework è progettato per essere sia semplice che estensibile, offrendo astrazioni di alto livello per modelli multi-agente comuni e fornendo al contempo opzioni di personalizzazione approfondita per casi d'uso avanzati. Con la sua architettura basata su eventi e il supporto per diversi LLM e strumenti, AutoGen permette agli sviluppatori di costruire applicazioni AI di nuova generazione più capaci, robuste e allineate con l'umano rispetto al passato.

Would you like me to continue with the rest of the document?```bash

Install AutoGen

pip install pyautogen

Install with specific integrations (e.g., OpenAI)

pip install "pyautogen[openai]"

Install development version

pip install git+https://github.com/microsoft/autogen.git

Install with all optional dependencies

pip install "pyautogen[all]"

### Environment Configuration
```python
import os
import autogen

# Configure LLM provider (OpenAI example)
config_list_openai = [
    \\\\{
        "model": "gpt-4",
        "api_key": os.environ.get("OPENAI_API_KEY")
    \\\\},
    \\\\{
        "model": "gpt-3.5-turbo",
        "api_key": os.environ.get("OPENAI_API_KEY")
    \\\\}
]

# Configure for other LLMs (e.g., Azure OpenAI, local models)
# See AutoGen documentation for specific configurations

# Set up logging
autogen.ChatCompletion.set_cache(seed=42) # For reproducibility

Project Structure

autogen_project/
├── agents/
│   ├── __init__.py
│   ├── researcher_agent.py
│   └── coder_agent.py
├── workflows/
│   ├── __init__.py
│   ├── coding_workflow.py
│   └── research_workflow.py
├── tools/
│   ├── __init__.py
│   └── custom_tools.py
├── skills/
│   ├── __init__.py
│   └── code_execution_skill.py
├── config/
│   ├── __init__.py
│   └── llm_config.py
└── main.py

Core Concepts

Agents

Agents are the fundamental building blocks in AutoGen. They are conversational entities that can send and receive messages, execute code, call functions, and interact with humans.

ConversableAgent

This is the base class for most agents in AutoGen, providing core conversational capabilities.

UserProxyAgent

A specialized agent that acts as a proxy for human users, allowing them to participate in conversations, provide input, and execute code.

AssistantAgent

An agent designed to act as an AI assistant, typically powered by an LLM, capable of writing code, answering questions, and performing tasks.

GroupChat

AutoGen supports multi-agent conversations through GroupChat and GroupChatManager, enabling complex interactions between multiple agents.

Agent Configuration

Basic Agent Creation

import autogen

# Assistant Agent (LLM-powered)
assistant = autogen.AssistantAgent(
    name="Assistant",
    llm_config=\\\\{
        "config_list": config_list_openai,
        "temperature": 0.7,
        "timeout": 600
    \\\\},
    system_message="You are a helpful AI assistant. Provide concise and accurate answers."
)

# User Proxy Agent (Human in the loop)
user_proxy = autogen.UserProxyAgent(
    name="UserProxy",
    human_input_mode="TERMINATE",  # Options: ALWAYS, TERMINATE, NEVER
    max_consecutive_auto_reply=10,
    is_termination_msg=lambda x: x.get("content", "").rstrip().endswith("TERMINATE"),
    code_execution_config=\\\\{
        "work_dir": "coding_output",
        "use_docker": False  # Set to True to use Docker for code execution
    \\\\},
    system_message="A human user. Reply TERMINATE when the task is done or if you want to stop."
)

Advanced Agent Customization

import autogen

# Agent with custom reply function
def custom_reply_func(messages, sender, config):
    last_message = messages[-1]["content"]
    if "hello" in last_message.lower():
        return "Hello there! How can I help you today?"
    return "I received your message."

custom_agent = autogen.ConversableAgent(
    name="CustomAgent",
    llm_config=False,  # No LLM for this agent
    reply_func_list=[custom_reply_func]
)

# Agent with specific skills (function calling)
@autogen.register_function(
    name="get_stock_price",
    description="Get the current stock price for a given symbol.",
    parameters=\\\\{"symbol": \\\\{"type": "string", "description": "Stock symbol"\\\\}\\\\}
)
def get_stock_price(symbol: str) -> str:
    # Implement stock price retrieval logic
    return f"The price of \\\\{symbol\\\\} is $150."

stock_analyst_agent = autogen.AssistantAgent(
    name="StockAnalyst",
    llm_config=\\\\{
        "config_list": config_list_openai,
        "functions": [autogen.AssistantAgent.construct_function_description(get_stock_price)]
    \\\\},
    function_map=\\\\{"get_stock_price": get_stock_price\\\\}
)

Specialized Agent Types

import autogen

# TeachableAgent for learning from feedback
teachable_agent = autogen.TeachableAgent(
    name="TeachableAnalyst",
    llm_config=\\\\{"config_list": config_list_openai\\\\},
    teach_config=\\\\{
        "verbosity": 0,  # 0 for no teaching, 1 for normal, 2 for detailed
        "reset_db": False, # Set to True to clear previous learnings
        "path_to_db_dir": "./teachable_agent_db"
    \\\\}
)

# RetrieveUserProxyAgent for RAG (Retrieval Augmented Generation)
rag_agent = autogen.retrieve_chat.RetrieveUserProxyAgent(
    name="RAGAgent",
    human_input_mode="TERMINATE",
    retrieve_config=\\\\{
        "task": "qa",
        "docs_path": "./documents_for_rag",
        "chunk_token_size": 2000,
        "model": config_list_openai[0]["model"],
        "collection_name": "rag_collection",
        "get_or_create": True
    \\\\}
)

Agent Conversations

Two-Agent Chat

import autogen

# Initiate chat between user_proxy and assistant
user_proxy.initiate_chat(
    assistant,
    message="What is the capital of France?",
    summary_method="reflection_with_llm", # For summarizing conversation history
    max_turns=5
)

# Example with code execution
user_proxy.initiate_chat(
    assistant,
    message="Write a Python script to print numbers from 1 to 5 and run it."
)

Group Chat with Multiple Agents

import autogen

# Define agents for group chat
planner = autogen.AssistantAgent(
    name="Planner",
    llm_config=\\\\{"config_list": config_list_openai\\\\},
    system_message="You are a project planner. Create detailed plans for tasks."
)

engineer = autogen.AssistantAgent(
    name="Engineer",
    llm_config=\\\\{"config_list": config_list_openai\\\\},
    system_message="You are a software engineer. Implement the plans provided."
)

reviewer = autogen.AssistantAgent(
    name="Reviewer",
    llm_config=\\\\{"config_list": config_list_openai\\\\},
    system_message="You are a code reviewer. Review the implemented code for quality."
)

# Create group chat and manager
group_chat = autogen.GroupChat(
    agents=[user_proxy, planner, engineer, reviewer],
    messages=[],
    max_round=12,
    speaker_selection_method="auto" # auto, round_robin, random, manual
)

manager = autogen.GroupChatManager(
    groupchat=group_chat,
    llm_config=\\\\{"config_list": config_list_openai\\\\}
)

# Initiate group chat
user_proxy.initiate_chat(
    manager,
    message="Develop a Python script to calculate Fibonacci numbers up to n."
)

Advanced Conversation Control

import autogen

# Custom speaker selection
def custom_speaker_selector(last_speaker, groupchat):
    if last_speaker is user_proxy:
        return planner
    elif last_speaker is planner:
        return engineer
    elif last_speaker is engineer:
        return reviewer
    else:
        return user_proxy

custom_group_chat = autogen.GroupChat(
    agents=[user_proxy, planner, engineer, reviewer],
    messages=[],
    speaker_selection_method=custom_speaker_selector
)

# Nested chats
def initiate_nested_chat(recipient, message):
    user_proxy.initiate_chat(recipient, message=message, clear_history=False)

# Example of agent calling nested chat
class MainAgent(autogen.AssistantAgent):
    def generate_reply(self, messages, sender, **kwargs):
        # ... logic ...
        if needs_specialized_help:
            initiate_nested_chat(specialist_agent, "Need help with this sub-task.")
            # ... process specialist_agent response ...
        return "Main task processed."

Tool and Function Integration

Using Built-in Tools

AutoGen doesn_t have a large set of pre-built tools like some other frameworks. Instead, it focuses on enabling agents to execute code (Python scripts, shell commands) which can then interact with any library or tool available in the execution environment.

Custom Function Calling (Skills)

import autogen

# Define a function (skill)
@autogen.register_function
def get_weather(location: str) -> str:
    """Get the current weather for a given location."""
    # Replace with actual API call
    if location == "London":
        return "Weather in London is 15°C and cloudy."
    elif location == "Paris":
        return "Weather in Paris is 18°C and sunny."
    else:
        return f"Weather data not available for \\\\{location\\\\}."

# Agent that can use the function
weather_assistant = autogen.AssistantAgent(
    name="WeatherAssistant",
    llm_config=\\\\{
        "config_list": config_list_openai,
        "functions": [autogen.AssistantAgent.construct_function_description(get_weather)]
    \\\\},
    function_map=\\\\{"get_weather": get_weather\\\\}
)

# User proxy to trigger function call
user_proxy.initiate_chat(
    weather_assistant,
    message="What is the weather in London?"
)

Code Execution

import autogen

# UserProxyAgent is configured for code execution by default
# Ensure `code_execution_config` is set appropriately

# Example: Agent asks UserProxyAgent to execute code
coder_agent = autogen.AssistantAgent(
    name="Coder",
    llm_config=\\\\{"config_list": config_list_openai\\\\}
)

user_proxy.initiate_chat(
    coder_agent,
    message="Write a Python script that creates a file named 'test.txt' with content 'Hello AutoGen!' and then execute it."
)
# UserProxyAgent will prompt for confirmation before executing the code.

Human-in-the-Loop (HIL)

Configuring Human Input

import autogen

# UserProxyAgent configured for human input
hil_user_proxy = autogen.UserProxyAgent(
    name="HumanReviewer",
    human_input_mode="ALWAYS",  # ALWAYS: Human input required for every message
                               # TERMINATE: Human input required if no auto-reply, or to terminate
                               # NEVER: No human input (fully autonomous)
    is_termination_msg=lambda x: x.get("content", "").rstrip() == "APPROVE"
)

# Example workflow with human review
planner = autogen.AssistantAgent(name="Planner", llm_config=llm_config)
executor = autogen.AssistantAgent(name="Executor", llm_config=llm_config)

groupchat_with_review = autogen.GroupChat(
    agents=[hil_user_proxy, planner, executor],
    messages=[],
    max_round=10
)
manager_with_review = autogen.GroupChatManager(
    groupchat=groupchat_with_review, llm_config=llm_config
)

hil_user_proxy.initiate_chat(
    manager_with_review,
    message="Plan and execute a task to summarize a long document. I will review the plan and the final summary."
)

Asynchronous Human Input

AutoGen primarily handles HIL synchronously within the conversation flow. For more complex asynchronous HIL, you would typically integrate with external task management or UI systems.

Advanced Features

Teachable Agents

import autogen

# Setup TeachableAgent
teachable_coder = autogen.TeachableAgent(
    name="TeachableCoder",
    llm_config=\\\\{"config_list": config_list_openai\\\\},
    teach_config=\\\\{
        "verbosity": 1,
        "reset_db": False,
        "path_to_db_dir": "./teachable_coder_db",
        "recall_threshold": 1.5,  # Higher value means less recall
    \\\\}
)

# User teaches the agent
user_proxy.initiate_chat(
    teachable_coder,
    message="When I ask for a quick sort algorithm, always implement it in Python using a recursive approach."
)

# Later, the agent uses the learned information
user_proxy.initiate_chat(
    teachable_coder,
    message="Implement a quick sort algorithm."
)

# To clear learnings:
# teachable_coder.clear_mem L() # For in-memory (if not using DB)
# Or set teach_config["reset_db"] = True and re-initialize

Retrieval Augmented Generation (RAG)

import autogen
from autogen.agentchat.contrib.retrieve_assistant_agent import RetrieveAssistantAgent

# Ensure you have a directory with documents (e.g., ./my_documents)
# Supported formats: .txt, .md, .pdf, .html, .htm, .json, .jsonl, .csv, .tsv, .xls, .xlsx, .doc, .docx, .ppt, .pptx, .odt, .rtf, .epub

# Create a RetrieveAssistantAgent (combines LLM with retrieval)
retrieval_assistant = RetrieveAssistantAgent(
    name="RetrievalAssistant",
    system_message="You are a helpful assistant that answers questions based on provided documents.",
    llm_config=\\\\{"config_list": config_list_openai\\\\}
)

# Create a RetrieveUserProxyAgent to handle document processing and querying
rag_user_proxy = autogen.retrieve_chat.RetrieveUserProxyAgent(
    name="RAGUserProxy",
    human_input_mode="TERMINATE",
    max_consecutive_auto_reply=5,
    retrieve_config=\\\\{
        "task": "qa",  # Can be "qa", "code", "chat"
        "docs_path": "./my_documents", # Path to your documents
        "chunk_token_size": 2000,
        "model": config_list_openai[0]["model"],
        "collection_name": "my_rag_collection",
        "get_or_create": True, # Creates collection if it doesn_t exist
        "embedding_model": "all-mpnet-base-v2" # Example sentence transformer model
    \\\\},
    code_execution_config=False
)

# Initiate RAG chat
# The RAGUserProxy will first try to answer from documents, then pass to RetrievalAssistant if needed.
rag_user_proxy.initiate_chat(
    retrieval_assistant,
    problem="What are the main features of AutoGen according to the documents?"
)

# To update or add new documents, you might need to re-index or manage the collection.
# rag_user_proxy.retrieve_config["update_context"] = True (for some RAG setups)

Multi-Modal Conversations

AutoGen supports multi-modal inputs (e.g., images) if the underlying LLM supports it (like GPT-4V).

import autogen

# Ensure your config_list points to a multimodal LLM (e.g., gpt-4-vision-preview)
multimodal_config_list = [
    \\\\{
        "model": "gpt-4-vision-preview",
        "api_key": os.environ.get("OPENAI_API_KEY")
    \\\\}
]

multimodal_agent = autogen.AssistantAgent(
    name="MultimodalAgent",
    llm_config=\\\\{"config_list": multimodal_config_list\\\\}
)

# Example message with an image URL
user_proxy.initiate_chat(
    multimodal_agent,
    message=[
        \\\\{"type": "text", "text": "What is in this image?"\\\\},
        \\\\{"type": "image_url", "image_url": \\\\{"url": "https://example.com/image.jpg"\\\\}\\\\}
    ]
)

# Example with local image (requires proper handling to make it accessible to the LLM)
# This might involve uploading the image or using a local multimodal LLM setup.
# For local images with OpenAI, you typically need to base64 encode them.
import base64

def image_to_base64(image_path):
    with open(image_path, "rb") as img_file:
        return base64.b64encode(img_file.read()).decode("utf-8")

local_image_path = "./path_to_your_image.png"
base64_image = image_to_base64(local_image_path)

user_proxy.initiate_chat(
    multimodal_agent,
    message=[
        \\\\{"type": "text", "text": "Describe this local image:"\\\\},
        \\\\{"type": "image_url", "image_url": \\\\{"url": f"data:image/png;base64,\\\\{base64_image\\\\}"\\\\}\\\\}
    ]
)

Agent Workflow Patterns

Reflection and Self-Correction

import autogen

# Agent that reflects on its own output
self_reflecting_agent = autogen.AssistantAgent(
    name="Reflector",
    llm_config=\\\\{"config_list": config_list_openai\\\\},
    system_message="You are an AI that writes code. After writing code, reflect on its quality and correctness. If you find issues, try to correct them."
)

# User proxy to facilitate reflection
reflection_user_proxy = autogen.UserProxyAgent(
    name="ReflectionProxy",
    human_input_mode="NEVER",
    max_consecutive_auto_reply=3, # Allow a few turns for reflection
    # Custom message to trigger reflection or provide feedback
    # This often involves a more complex setup where the proxy or another agent critiques the output.
)

# This pattern is often implemented with a sequence of chats or a GroupChat
# where one agent produces work and another critiques it, then the first agent revises.

# Simplified example:
user_proxy.initiate_chat(
    self_reflecting_agent,
    message="Write a Python function to calculate factorial. Then, review your code for potential bugs or improvements and provide a revised version if necessary."
)

Hierarchical Agent Teams

This is typically achieved using GroupChatManager where one agent (e.g., a manager or planner) coordinates other specialized agents.

import autogen

# Manager Agent
manager_agent = autogen.AssistantAgent(
    name="Manager",
    llm_config=\\\\{"config_list": config_list_openai\\\\},
    system_message="You are a project manager. Delegate tasks to your team (Engineer, Researcher) and synthesize their results."
)

# Specialist Agents
engineer_agent = autogen.AssistantAgent(name="Engineer", llm_config=llm_config)
researcher_agent = autogen.AssistantAgent(name="Researcher", llm_config=llm_config)

# Group Chat for the team
team_groupchat = autogen.GroupChat(
    agents=[user_proxy, manager_agent, engineer_agent, researcher_agent],
    messages=[],
    max_round=15,
    # Manager agent can be set to speak or select next speaker
    speaker_selection_method=lambda last_speaker, groupchat: manager_agent if last_speaker != manager_agent else user_proxy # Simplified example
)

team_manager = autogen.GroupChatManager(
    groupchat=team_groupchat, llm_config=llm_config
)

user_proxy.initiate_chat(
    team_manager,
    message="Develop a new feature for our app that requires research on user needs and then engineering implementation."
)

Best Practices

Agent Design

• Clear Roles: Define specific, unambiguous roles and responsibilities for each agent.
• System Messages: Use detailed system messages to guide agent behavior and persona.
• Tool Access: Provide agents only with the tools they need for their role.
• LLM Configuration: Tailor LLM temperature, model, and other settings per agent for optimal performance.

Conversation Management

• Termination Conditions: Clearly define when a conversation or task is complete.
• Max Turns/Rounds: Set limits to prevent infinite loops or excessive costs.
• Speaker Selection: Choose appropriate speaker selection methods for group chats (auto, round_robin, custom).
• Summarization: Use conversation summarization for long-running chats to manage context window.

Code Execution Security

• Sandboxing: Use Docker (use_docker=True in code_execution_config) for safer code execution, especially with untrusted code.
• Human Review: Implement human review (human_input_mode="ALWAYS"o"TERMINATE") prima di eseguire codice potenzialmente rischioso.
• Ambienti Ristretti: Se non si utilizza Docker, assicurarsi che l'ambiente di esecuzione abbia autorizzazioni limitate.

Gestione dei Costi

• Selezione del Modello: Utilizzare modelli meno costosi (es. GPT-3.5-turbo) per attività più semplici o agenti.
• Max Token/Turni: Limitare la lunghezza delle conversazioni e degli output LLM.
• Caching: Utilizzare autogen.ChatCompletion.set_cache()per memorizzare le risposte LLM e ridurre chiamate ridondanti.
• Monitoraggio: Tracciare attentamente l'utilizzo dei token e i costi API.

Debug

• Registrazione Dettagliata: AutoGen fornisce logging; aumentare la verbosità per il debug.
• Esecuzione Passo-Passo: Per chat di gruppo complesse, considerare la selezione manuale del parlante o punti di interruzione per comprendere il flusso.
• Isolamento Agente: Testare gli agenti individualmente prima di integrarli in gruppi più ampi.

Risoluzione dei Problemi

Problemi Comuni

Agenti Bloccati in Loop

• Causa: Condizioni di terminazione vaghe, obiettivi degli agenti in conflitto o interazioni troppo complesse.
• Soluzione: Raffinare is_termination_msglambda, semplificare le istruzioni degli agenti, impostare max_consecutive_auto_replyo max_roundlimiti.

Comportamento Inatteso dell'Agente

• Causa: Messaggi di sistema ambigui, fraintendimenti LLM o configurazioni LLM non corrette.
• Soluzione: Rendere i messaggi di sistema più specifici, sperimentare con temperature LLM diverse, assicurare descrizioni corrette di funzioni/strumenti.

Errori di Esecuzione del Codice

• Causa: Dipendenze mancanti nell'ambiente di esecuzione, codice generato in modo errato da LLM, problemi di autorizzazione.
• Soluzione: Assicurare l'installazione di tutti i pacchetti necessari (o utilizzare Docker), migliorare i prompt per la generazione di codice, verificare i permessi di file/rete.

Problemi di Chiamata di Funzioni

• Causa: Descrizioni di funzioni non corrette fornite a LLM, bug nel codice di funzioni personalizzate, LLM che non genera JSON valido per gli argomenti.
• Soluzione: Assicurare che le descrizioni delle funzioni siano chiare e corrispondano ai parametri, testare accuratamente le funzioni personalizzate, raffinare i prompt per guidare LLM verso il formato JSON corretto.

---

Questo cheat sheet di AutoGen fornisce una guida completa per costruire applicazioni AI multi-agente sofisticate. Sfruttando il framework conversazionale di AutoGen, gli sviluppatori possono creare sistemi AI altamente capaci e collaborativi. Ricordarsi di consultare la documentazione ufficiale di AutoGen per le ultime funzionalità e riferimenti API dettagliati.