Mintplex-Labs/anything-llm · critical · Error

No LMStudio API Base Path was set.

Error message

No LMStudio API Base Path was set.

What it means

Thrown by the LMStudioLLM constructor when LMSTUDIO_BASE_PATH is not set. The base path is the URL of the local LMStudio server. It is parsed through parseLMStudioBasePath to normalize the URL format. There is no constructor-parameter fallback for the base path — it must come from the environment.

Source

Thrown at server/utils/AiProviders/lmStudio/index.js:18

const { NativeEmbedder } = require("../../EmbeddingEngines/native");
const {
  handleDefaultStreamResponseV2,
  formatChatHistory,
} = require("../../helpers/chat/responses");
const {
  LLMPerformanceMonitor,
} = require("../../helpers/chat/LLMPerformanceMonitor");
const { OpenAI: OpenAIApi } = require("openai");

//  hybrid of openAi LLM chat completion for LMStudio
class LMStudioLLM {
  /** @see LMStudioLLM.cacheContextWindows */
  static modelContextWindows = {};

  constructor(embedder = null, modelPreference = null) {
    if (!process.env.LMSTUDIO_BASE_PATH)
      throw new Error("No LMStudio API Base Path was set.");

    this.className = "LMStudioLLM";
    const apiKey = process.env.LMSTUDIO_AUTH_TOKEN ?? null;
    this.lmstudio = new OpenAIApi({
      baseURL: parseLMStudioBasePath(process.env.LMSTUDIO_BASE_PATH), // here is the URL to your LMStudio instance
      apiKey,
    });

    // Prior to LMStudio 0.2.17 the `model` param was not required and you could pass anything
    // into that field and it would work. On 0.2.17 LMStudio introduced multi-model chat
    // which now has a bug that reports the server model id as "Loaded from Chat UI"
    // and any other value will crash inferencing. So until this is patched we will
    // try to fetch the `/models` and have the user set it, or just fallback to "Loaded from Chat UI"
    // which will not impact users with <v0.2.17 and should work as well once the bug is fixed.
    this.model = modelPreference || process.env.LMSTUDIO_MODEL_PREF;
    if (!this.model) throw new Error("LMStudio must have a valid model set.");

    this.embedder = embedder ?? new NativeEmbedder();

View on GitHub (pinned to 526360e320)

Solutions

1. Set LMSTUDIO_BASE_PATH in .env to your LMStudio server URL (e.g. 'http://localhost:1234/v1') and restart.
2. Ensure the LMStudio local server is started and listening (LMStudio > Local Server tab > Start Server).
3. If running AnythingLLM in Docker, use host.docker.internal instead of localhost.

Example fix

// before: .env
# LMSTUDIO_BASE_PATH='http://your-server:1234/v1'

// after (local)
LMSTUDIO_BASE_PATH='http://localhost:1234/v1'

// after (docker)
LMSTUDIO_BASE_PATH='http://host.docker.internal:1234/v1'

function validateLMStudioConfig() {
  if (!process.env.LMSTUDIO_BASE_PATH) {
    throw new Error(
      'LMSTUDIO_BASE_PATH is not set. Configure it in .env (e.g. http://localhost:1234/v1).'
    );
  }
  return process.env.LMSTUDIO_BASE_PATH;
}

validateLMStudioConfig();

try {
  const llm = new LMStudioLLM(embedder, model);
} catch (e) {
  if (e.message.includes('Base Path')) {
    console.error('Set LMSTUDIO_BASE_PATH in .env and ensure LMStudio local server is running.');
    return null;
  }
  throw e;
}

When it happens

Trigger: Instantiating `new LMStudioLLM(embedder, model)` (via getLLMProvider('lmstudio')) when process.env.LMSTUDIO_BASE_PATH is undefined or empty. The check `if (!process.env.LMSTUDIO_BASE_PATH)` fires immediately.

Common situations: LMStudio was selected as the provider but the .env was never configured. A new deployment where .env.example was copied but LMSTUDIO_BASE_PATH remained commented out. The user assumed selecting the provider in the UI was sufficient without editing .env.

Related errors

• No Lemonade API Base Path was set.
• LiteLLM must have a valid base path to use for the api.
• LMStudio must have a valid model set.
• No LocalAI Base Path was set.
• KoboldCPP must have a valid model set.

AI-assisted analysis of Mintplex-Labs/anything-llm@526360e320 (2026-08-13). Data as JSON: /api/errors/530720b796d79656. Report an issue: GitHub.