Mintplex-Labs/anything-llm · error · Error

NVIDIA NIM base path must be provided to use agents.

Error message

NVIDIA NIM base path must be provided to use agents.

What it means

Thrown by AgentHandler.checkSetup() (server/utils/agents/index.js:230) when the workspace agent provider is 'nvidia-nim' but NVIDIA_NIM_LLM_BASE_PATH is unset/empty. NVIDIA NIM can be the hosted integrate.api.nvidia.com endpoint or a self-hosted NIM container, so AnythingLLM validates the base URL rather than a key.

Source

Thrown at server/utils/agents/index.js:231

      case "apipie":
        if (!process.env.APIPIE_LLM_API_KEY)
          throw new Error("ApiPie API Key must be provided to use agents.");
        break;
      case "xai":
        if (!process.env.XAI_LLM_API_KEY)
          throw new Error("xAI API Key must be provided to use agents.");
        break;
      case "zai":
        if (!process.env.ZAI_API_KEY)
          throw new Error("Z.AI API Key must be provided to use agents.");
        break;
      case "novita":
        if (!process.env.NOVITA_LLM_API_KEY)
          throw new Error("Novita API Key must be provided to use agents.");
        break;
      case "nvidia-nim":
        if (!process.env.NVIDIA_NIM_LLM_BASE_PATH)
          throw new Error(
            "NVIDIA NIM base path must be provided to use agents."
          );
        break;
      case "ppio":
        if (!process.env.PPIO_API_KEY)
          throw new Error("PPIO API Key must be provided to use agents.");
        break;
      case "gemini":
        if (!process.env.GEMINI_API_KEY)
          throw new Error("Gemini API key must be provided to use agents.");
        break;
      case "moonshotai":
        if (!process.env.MOONSHOT_AI_MODEL_PREF)
          throw new Error("Moonshot AI model must be set to use agents.");
        break;
      case "cometapi":
        if (!process.env.COMETAPI_LLM_API_KEY)
          throw new Error("CometAPI API Key must be provided to use agents.");

View on GitHub (pinned to 526360e320)

Solutions

1. Set NVIDIA_NIM_LLM_BASE_PATH in .env to the NIM endpoint (hosted: https://integrate.api.nvidia.com/v1; self-hosted: http://<host>:8000/v1).
2. For the hosted endpoint, also set NVIDIA_NIM_LLM_API_KEY; the base-path guard does not check it but later calls will 401 without it.
3. Restart AnythingLLM so process.env reloads.
4. Confirm with curl <base path>/models (add Authorization for the hosted endpoint).

Example fix

// before (.env)
// NVIDIA_NIM_LLM_BASE_PATH=
// NVIDIA_NIM_LLM_API_KEY=

// after (.env) - hosted
NVIDIA_NIM_LLM_BASE_PATH=https://integrate.api.nvidia.com/v1
NVIDIA_NIM_LLM_API_KEY=nvapi-...your-key

const base = process.env.NVIDIA_NIM_LLM_BASE_PATH;
if (!base) {
  throw new Error(
    'Cannot start NVIDIA NIM agent: set NVIDIA_NIM_LLM_BASE_PATH (hosted https://integrate.api.nvidia.com/v1 or self-hosted http://<host>:8000/v1) in .env.'
  );
}
try { new URL(base); } catch { throw new Error('NVIDIA_NIM_LLM_BASE_PATH is not a valid URL'); }
// Guard checks only base path; warn if the hosted endpoint lacks a key:
if (base.includes('integrate.api.nvidia.com') && !process.env.NVIDIA_NIM_LLM_API_KEY) {
  console.warn('Hosted NIM endpoint selected but NVIDIA_NIM_LLM_API_KEY is unset - auth will fail later');
}

try {
  await agentHandler.start();
} catch (e) {
  if (/NVIDIA NIM base path must be provided/.test(e.message)) {
    return respondConfigError('nvidia-nim', ['NVIDIA_NIM_LLM_BASE_PATH', 'NVIDIA_NIM_LLM_API_KEY']);
  }
  throw e;
}

When it happens

Trigger: An agent invocation runs with workspace.agentProvider === 'nvidia-nim' while NVIDIA_NIM_LLM_BASE_PATH is absent from process.env. Path: #providerSetupAndCheck() -> checkSetup() at index.js:476.

Common situations: NVIDIA NIM selected in System > LLM Preference without an endpoint URL; pointing at a self-hosted NIM container that is not running; .env edited but the server not restarted; using the hosted URL without also setting the NVIDIA key, which will fail later on auth even though this guard passes.

Related errors

• Azure OpenAI API endpoint and key must be provided to use ag
• KoboldCPP must have a valid base path to use for the api.
• LocalAI must have a valid base path to use for the api.
• OpenRouter API key must be provided to use agents.
• Mistral API key must be provided to use agents.

AI-assisted analysis of Mintplex-Labs/anything-llm@526360e320 (2026-08-13). Data as JSON: /api/errors/babb7b613fe18450. Report an issue: GitHub.