Mintplex-Labs/anything-llm · critical · Error

OMLX must have a valid model set.

Error message

OMLX must have a valid model set.

What it means

OMLXProvider's constructor (omlx.js:18-24) requires a model id from either config.model or the OMLX_LLM_MODEL_PREF environment variable and throws this if neither is set. OMLX (AMD's Omnissa/OMLX runtime) is reached via an OpenAI-compatible client, so the agent needs the target model id.

Source

Thrown at server/utils/agents/aibitat/providers/omlx.js:24

const { RetryError } = require("../error.js");
const { parseOMLXBasePath } = require("../../../AiProviders/omlx/index.js");

/**
 * The agent provider for OMLX.
 * OMLX is OpenAI-compatible and supports native tool calling, falling back
 * to the UnTooled prompt-based approach when disabled via env.
 */
class OMLXProvider extends InheritMultiple([Provider, UnTooled]) {
  model;

  /**
   * @param {{model?: string}} config
   */
  constructor(config = {}) {
    super();
    this.providerTag = "omlx";
    const model = config?.model || process.env.OMLX_LLM_MODEL_PREF;
    if (!model) throw new Error("OMLX must have a valid model set.");

    const client = new OpenAI({
      baseURL: parseOMLXBasePath(process.env.OMLX_LLM_BASE_PATH),
      apiKey: process.env.OMLX_LLM_API_KEY || null,
    });

    this._client = client;
    this.model = model;
    this.verbose = true;
  }

  get client() {
    return this._client;
  }

  get supportsAgentStreaming() {
    return true;
  }

View on GitHub (pinned to 526360e320)

Solutions

1. Set OMLX_LLM_MODEL_PREF in .env to a model served by the OMLX runtime.
2. Or pass { model: "<id>" } in the provider config.
3. Confirm OMLX_LLM_BASE_PATH points at the running OMLX server and the model is loaded.
4. If a key is required, set OMLX_LLM_API_KEY as well.

Example fix

// before (env missing)
// OMLX_LLM_MODEL_PREF=
const p = new OMLXProvider();

// after (.env)
// OMLX_LLM_MODEL_PREF=Llama-3.1-8B-Instruct
const p = new OMLXProvider();

const model = config?.model || process.env.OMLX_LLM_MODEL_PREF;
if (!model)
  throw new Error(
    "Set OMLX_LLM_MODEL_PREF (or pass config.model) before creating OMLXProvider."
  );

/** @param {unknown} v @returns {v is string} */
function isNonEmptyString(v) {
  return typeof v === "string" && v.trim().length > 0;
}

try {
  return new OMLXProvider(config);
} catch (e) {
  if (/valid model set/.test(e.message)) {
    throw new Error("Please choose an OMLX model before starting the agent.");
  }
  throw e;
}

When it happens

Trigger: Instantiating OMLXProvider with no config.model while OMLX_LLM_MODEL_PREF is unset in the environment.

Common situations: Fresh OMLX setup without setting the model preference, an env var that was renamed, or a deployment that forgot to port OMLX_LLM_MODEL_PREF into the container env.

Related errors

• LMStudio must have a valid model set.
• OMLX base path must be provided to use agents.
• GenericOpenAI must have a valid base path to use for the api
• No Lemonade API Base Path was set.
• LMStudio base path must be provided to use agents.

AI-assisted analysis of Mintplex-Labs/anything-llm@526360e320 (2026-08-13). Data as JSON: /api/errors/c5656baf6e995de2. Report an issue: GitHub.