Agent Engine deployment succeeds but query and stream_query are missing

Google Cloud Build with AI Agents
1

I’m trying to follow the agent engine deployment quickstart, but it doesn’t work as expected.

Here is the code I’m running:

import vertexai

client = vertexai.Client(project="my-project", location="us-central1")

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()

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,
    },
)

remote_agent = client.agent_engines.create(
    agent=agent,
    config={
        "display_name": "test-agent-engine",
        "requirements": ["google-cloud-aiplatform[agent_engines,langchain]"],
        "staging_bucket": "gs://sample",
    },
)

=== result===

아래 로그와 함께 배포는 성공하지만, 배포된 agent engine은 query와 stram_query 함수가 없습니다.

failed to generate schema for query: `query` is not fully defined; you should define `RunnableConfig`, then call `query.model_rebuild()`.

failed to generate schema for stream_query: `stream_query` is not fully defined; you should define `RunnableConfig`, then call `stream_query.model_rebuild()`.

2

Thx for the info, we are working on it now.

1 Like