hsliuping/TradingAgents-CN · critical · ValueError

使用Google需要设置GOOGLE_API_KEY环境变量或在数据库中配置API Key

Error message

使用Google需要设置GOOGLE_API_KEY环境变量或在数据库中配置API Key

What it means

create_llm_by_provider raises this when provider is 'google' and no API key is available: neither the api_key argument nor the GOOGLE_API_KEY environment variable is set. The Google provider requires a key for every ChatGoogle-style client instantiation. This is a fail-fast check before any network call is attempted.

Source

Thrown at tradingagents/graph/trading_graph.py:90

        factory_provider = "openai" if normalized_provider == "siliconflow" else normalized_provider
        client = create_llm_client(
            provider=factory_provider,
            model=model,
            base_url=backend_url,
            api_key=api_key,
            temperature=temperature,
            max_tokens=max_tokens,
            timeout=timeout,
            **extra_kwargs,
        )
        return client.get_llm()

    if normalized_provider == "google":
        # 优先使用传入的 API Key，否则从环境变量读取
        google_api_key = api_key or os.getenv('GOOGLE_API_KEY')
        if not google_api_key:
            raise ValueError("使用Google需要设置GOOGLE_API_KEY环境变量或在数据库中配置API Key")

        client = create_llm_client(
            provider="google",
            model=model,
            base_url=backend_url if backend_url else None,
            api_key=google_api_key,
            temperature=temperature,
            max_tokens=max_tokens,
            timeout=timeout,
            **extra_kwargs,
        )
        return client.get_llm()

    elif normalized_provider == "anthropic":
        from langchain_anthropic import ChatAnthropic

        return ChatAnthropic(
            model=model,

View on GitHub (pinned to 74783e8817)

Solutions

1. Export GOOGLE_API_KEY or pass api_key="..." explicitly to create_llm_by_provider
2. If using dotenv, ensure load_dotenv() runs before LLM creation and .env contains GOOGLE_API_KEY=...
3. If the key lives in the app database, fetch it first and pass it via the api_key parameter

Example fix

# before
llm = create_llm_by_provider(provider="google", model="gemini-2.0-flash")

# after
llm = create_llm_by_provider(provider="google", model="gemini-2.0-flash", api_key=os.environ["GOOGLE_API_KEY"])

from dotenv import load_dotenv; load_dotenv()
import os
if os.getenv("GOOGLE_API_KEY") is None and api_key is None:
    raise SystemExit("Missing GOOGLE_API_KEY — set it before creating the LLM")

def has_google_key(api_key: str | None) -> bool:
    return bool(api_key or os.getenv("GOOGLE_API_KEY"))

try:
    llm = create_llm_by_provider(provider="google", model=m, api_key=k)
except ValueError as e:
    if "GOOGLE_API_KEY" in str(e):
        raise SystemExit("Configure GOOGLE_API_KEY (Settings -> LLM Providers or env)") from e
    raise

When it happens

Trigger: Calling create_llm_by_provider(provider="google", model=...) with api_key=None while GOOGLE_API_KEY is unset; common in fresh deployments or CI where .env was not loaded.

Common situations: Forgot to export GOOGLE_API_KEY; .env file not loaded (python-dotenv not called); key stored only in the web UI database but calling create_llm_by_provider directly bypasses DB lookup; typo in env var name.

Understand the failure class

Background: "API key is required" / "API key not found" / "No API key was set": the missing-api-key error family across 16 libraries — this error's family across 16 libraries.

Related errors

• 使用Google AI需要在数据库中配置API Key或设置GOOGLE_API_KEY环境变量
• 使用SiliconFlow需要设置SILICONFLOW_API_KEY环境变量
• 使用OpenRouter需要设置OPENROUTER_API_KEY或OPENAI_API_KEY环境变量
• 使用AiHubMix需要设置AIHUBMIX_API_KEY环境变量
• 使用DeepSeek需要设置DEEPSEEK_API_KEY环境变量

AI-assisted analysis of hsliuping/TradingAgents-CN@74783e8817 (2026-08-28). Data as JSON: /api/errors/638897a65112e7fd. Report an issue: GitHub.