Mintplex-Labs/anything-llm · error · Error

GenericOpenAI must have a valid model set.

Error message

GenericOpenAI must have a valid model set.

What it means

Thrown after the constructor resolves this.model from modelPreference ?? process.env.GENERIC_OPEN_AI_MODEL_PREF ?? null. If all three are nullish, this.model is null and the constructor aborts. Unlike the base path, a default cannot be invented because Generic OpenAI has no idea what models the arbitrary endpoint serves.

Source

Thrown at server/utils/AiProviders/genericOpenAi/index.js:41

      );

    this.className = "GenericOpenAiLLM";
    this.basePath = process.env.GENERIC_OPEN_AI_BASE_PATH;
    this.openai = new OpenAIApi({
      baseURL: this.basePath,
      apiKey: process.env.GENERIC_OPEN_AI_API_KEY ?? null,
      defaultHeaders: {
        "User-Agent": getAnythingLLMUserAgent(),
        ...GenericOpenAiLLM.parseCustomHeaders(),
      },
    });
    this.model =
      modelPreference ?? process.env.GENERIC_OPEN_AI_MODEL_PREF ?? null;
    this.maxTokens = process.env.GENERIC_OPEN_AI_MAX_TOKENS
      ? toValidNumber(process.env.GENERIC_OPEN_AI_MAX_TOKENS, 1024)
      : 1024;
    if (!this.model)
      throw new Error("GenericOpenAI must have a valid model set.");
    this.limits = {
      history: this.promptWindowLimit() * 0.15,
      system: this.promptWindowLimit() * 0.15,
      user: this.promptWindowLimit() * 0.7,
    };

    this.embedder = embedder ?? new NativeEmbedder();
    this.defaultTemp = 0.7;
    this.log(`Inference API: ${this.basePath} Model: ${this.model}`);
  }

  log(text, ...args) {
    console.log(`\x1b[36m[${this.className}]\x1b[0m ${text}`, ...args);
  }

  /**
   * Parses custom headers from a CSV-formatted environment variable.
   * Format: "Header-Name:value,Another-Header:value2"

View on GitHub (pinned to 526360e320)

Solutions

1. Query the endpoint's model list (curl $BASE_PATH/models) and set GENERIC_OPEN_AI_MODEL_PREF to a returned id
2. Pass modelPreference explicitly when constructing from code
3. Fill the model field in the Generic OpenAI provider UI
4. Restart the server after updating .env

Example fix

// before
// .env: GENERIC_OPEN_AI_BASE_PATH=http://localhost:1234/v1  // no model

// after
// .env:
//   GENERIC_OPEN_AI_BASE_PATH=http://localhost:1234/v1
//   GENERIC_OPEN_AI_MODEL_PREF=llama-3.1-8b-instruct

const model = modelPreference ?? process.env.GENERIC_OPEN_AI_MODEL_PREF;
if (!model) {
  throw new ConfigError('GenericOpenAI needs GENERIC_OPEN_AI_MODEL_PREF.');
}
// optionally cross-check against GET $BASE_PATH/models

When it happens

Trigger: Constructing GenericOpenAiLLM with no modelPreference while GENERIC_OPEN_AI_MODEL_PREF is also unset. The provider must be told which model id the target endpoint expects.

Common situations: User set the base path but forgot the model id; the endpoint serves models under different names than expected; copying a config template that omitted the model pref line.

Related errors

• GenericOpenAI must have a valid base path to use for the api
• KoboldCPP must have a valid model set.
• No Lemonade Model Pref was set.
• LiteLLM must have a valid model set.
• LMStudio must have a valid model set.

AI-assisted analysis of Mintplex-Labs/anything-llm@526360e320 (2026-08-13). Data as JSON: /api/errors/8ab6312ac794389b. Report an issue: GitHub.