Sviluppare ed eseguire il deployment di agenti su Vertex AI Agent Engine
Questa pagina mostra come creare ed eseguire il deployment di un agente che restituisce il tasso di cambio tra due valute in una data specifica utilizzando i seguenti framework dell'agente:
Agent Development Kit (ADK) (anteprima)
Pipeline di query LlamaIndex (anteprima)
Prima di iniziare
- Sign in to your Google Cloud account. If you're new to Google Cloud, create an account to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.
-
In the Google Cloud console, on the project selector page, select or create a Google Cloud project.
-
Verify that billing is enabled for your Google Cloud project.
-
Enable the Vertex AI and Cloud Storage APIs.
-
In the Google Cloud console, on the project selector page, select or create a Google Cloud project.
-
Verify that billing is enabled for your Google Cloud project.
-
Enable the Vertex AI and Cloud Storage APIs.
-
Utente Vertex AI (
roles/aiplatform.user) -
Amministratore spazio di archiviazione (
roles/storage.admin) Esegui il seguente comando per installare l'SDK Vertex AI Python e altri pacchetti richiesti:
ADK
pip install --upgrade --quiet google-cloud-aiplatform[agent_engines,adk]LangGraph
pip install --upgrade --quiet google-cloud-aiplatform[agent_engines,langchain]LangChain
pip install --upgrade --quiet google-cloud-aiplatform[agent_engines,langchain]AG2
pip install --upgrade --quiet google-cloud-aiplatform[agent_engines,ag2]LlamaIndex
pip install --upgrade --quiet google-cloud-aiplatform[agent_engines,llama_index]Autenticarsi come utente
Colab
Esegui questo codice:
from google.colab import auth auth.authenticate_user(project_id="PROJECT_ID")Cloud Shell
Non occorre alcun intervento.
Local Shell
Esegui questo comando:
gcloud auth application-default loginEsegui il seguente codice per importare Vertex AI Agent Engine e inizializzare l'SDK:
import vertexai from vertexai import agent_engines vertexai.init( project="PROJECT_ID", # Your project ID. location="LOCATION", # Your cloud region. staging_bucket="gs://BUCKET_NAME", # Your staging bucket. )
Per ottenere le autorizzazioni necessarie per utilizzare Vertex AI Agent Engine, chiedi all'amministratore di concederti i seguenti ruoli IAM sul progetto:
Per ulteriori informazioni sulla concessione dei ruoli, consulta Gestisci l'accesso a progetti, cartelle e organizzazioni.
Potresti anche riuscire a ottenere le autorizzazioni richieste tramite i ruoli personalizzati o altri ruoli predefiniti.
Installare e inizializzare l'SDK Vertex AI Python
Sviluppare un agente
Innanzitutto, sviluppa uno strumento:
def get_exchange_rate(
currency_from: str = "USD",
currency_to: str = "EUR",
currency_date: str = "latest",
):
"""Retrieves the exchange rate between two currencies on a specified date."""
import requests
response = requests.get(
f"https://api.frankfurter.app/{currency_date}",
params={"from": currency_from, "to": currency_to},
)
return response.json()
Successivamente, crea un'istanza di un agente:
ADK
from google.adk.agents import Agent
from vertexai.preview.reasoning_engines import AdkApp
agent = Agent(
model="gemini-2.0-flash",
name='currency_exchange_agent',
tools=[get_exchange_rate],
)
app = AdkApp(agent=agent)
LangGraph
from vertexai import agent_engines
agent = agent_engines.LanggraphAgent(
model="gemini-2.0-flash",
tools=[get_exchange_rate],
model_kwargs={
"temperature": 0.28,
"max_output_tokens": 1000,
"top_p": 0.95,
},
)
LangChain
from vertexai import agent_engines
agent = agent_engines.LangchainAgent(
model="gemini-2.0-flash",
tools=[get_exchange_rate],
model_kwargs={
"temperature": 0.28,
"max_output_tokens": 1000,
"top_p": 0.95,
},
)
AG2
from vertexai import agent_engines
agent = agent_engines.AG2Agent(
model="gemini-2.0-flash",
runnable_name="Get Exchange Rate Agent",
tools=[get_exchange_rate],
)
LlamaIndex
from vertexai.preview import reasoning_engines
def runnable_with_tools_builder(model, runnable_kwargs=None, **kwargs):
from llama_index.core.query_pipeline import QueryPipeline
from llama_index.core.tools import FunctionTool
from llama_index.core.agent import ReActAgent
llama_index_tools = []
for tool in runnable_kwargs.get("tools"):
llama_index_tools.append(FunctionTool.from_defaults(tool))
agent = ReActAgent.from_tools(llama_index_tools, llm=model, verbose=True)
return QueryPipeline(modules = {"agent": agent})
agent = reasoning_engines.LlamaIndexQueryPipelineAgent(
model="gemini-2.0-flash",
runnable_kwargs={"tools": [get_exchange_rate]},
runnable_builder=runnable_with_tools_builder,
)
Infine, testa l'agente localmente:
ADK
for event in app.stream_query(
user_id="USER_ID",
message="What is the exchange rate from US dollars to SEK today?",
):
print(event)
dove USER_ID è un ID definito dall'utente con un limite di 128 caratteri.
LangGraph
agent.query(input={"messages": [
("user", "What is the exchange rate from US dollars to SEK today?"),
]})
LangChain
agent.query(
input="What is the exchange rate from US dollars to SEK today?"
)
AG2
agent.query(
input="What is the exchange rate from US dollars to SEK today?"
)
LlamaIndex
agent.query(
input="What is the exchange rate from US dollars to SEK today?"
)
Esegui il deployment di un agente
Per eseguire il deployment dell'agente:
ADK
from vertexai import agent_engines
remote_agent = agent_engines.create(
app,
requirements=["google-cloud-aiplatform[agent_engines,adk]"],
)
LangGraph
from vertexai import agent_engines
remote_agent = agent_engines.create(
agent,
requirements=["google-cloud-aiplatform[agent_engines,langchain]"],
)
LangChain
from vertexai import agent_engines
remote_agent = agent_engines.create(
agent,
requirements=["google-cloud-aiplatform[agent_engines,langchain]"],
)
AG2
from vertexai import agent_engines
remote_agent = agent_engines.create(
agent,
requirements=["google-cloud-aiplatform[agent_engines,ag2]"],
)
LlamaIndex
from vertexai import agent_engines
remote_agent = agent_engines.create(
agent,
requirements=["google-cloud-aiplatform[agent_engines,llama_index]"],
)
Viene creata una risorsa reasoningEngine in Vertex AI.
Utilizzare un agente
Prova l'agente di cui è stato eseguito il deployment inviando una query:
ADK
for event in remote_agent.stream_query(
user_id="USER_ID",
message="What is the exchange rate from US dollars to SEK today?",
):
print(event)
LangGraph
remote_agent.query(input={"messages": [
("user", "What is the exchange rate from US dollars to SEK today?"),
]})
LangChain
remote_agent.query(
input="What is the exchange rate from US dollars to SEK today?"
)
AG2
remote_agent.query(
input="What is the exchange rate from US dollars to SEK today?"
)
LlamaIndex
remote_agent.query(
input="What is the exchange rate from US dollars to SEK today?"
)
Esegui la pulizia
Per evitare che al tuo account Google Cloud vengano addebitati costi relativi alle risorse utilizzate in questa pagina, segui questi passaggi.
remote_agent.delete(force=True)