Mintplex-Labs/anything-llm · error · Error

e.message

Error message

e.message

What it means

Not a distinct error — the message is whatever the OpenAI SDK raised against the generic endpoint. The `.catch((e) => { throw new Error(e.message); })` wrapper keeps only the text, dropping the SDK error subclass and stack. Anything the arbitrary OpenAI-compatible server returns as a failure surfaces here.

Source

Thrown at server/utils/AiProviders/genericOpenAi/index.js:234

    if (process.env.GENERIC_OPEN_AI_REPORT_USAGE !== "true") return {};
    return {
      stream_options: {
        include_usage: true,
      },
    };
  }

  async getChatCompletion(messages = null, { temperature = 0.7 }) {
    const result = await LLMPerformanceMonitor.measureAsyncFunction(
      this.openai.chat.completions
        .create({
          model: this.model,
          messages,
          temperature,
          max_tokens: this.maxTokens,
        })
        .catch((e) => {
          throw new Error(e.message);
        })
    );

    if (
      !result.output.hasOwnProperty("choices") ||
      result.output.choices.length === 0
    )
      return null;

    const usage = {
      prompt_tokens: result.output?.usage?.prompt_tokens || 0,
      completion_tokens: result.output?.usage?.completion_tokens || 0,
      total_tokens: result.output?.usage?.total_tokens || 0,
      duration: result.duration,
    };
    this.#extractLlamaCppTimings(result.output, usage);

    return {

View on GitHub (pinned to 526360e320)

Solutions

1. Read e.message for the server's actual error text
2. Confirm the model id matches one from GET $BASE_PATH/models
3. Lower GENERIC_OPEN_AI_MAX_TOKENS if the message mentions token limits
4. Set GENERIC_OPEN_AI_API_KEY if the endpoint requires auth

Example fix

// before
.catch((e) => { throw new Error(e.message); })

// after
.catch((e) => { throw e; })

try {
  return await llm.getChatCompletion(messages, { temperature });
} catch (e) {
  const msg = e.message;
  if (/401|unauthor/i.test(msg)) throw new AuthError(msg);
  if (/model_not_found|404/i.test(msg)) throw new UnknownModelError(msg);
  if (/maximum context|too long/i.test(msg)) throw new ContextTooLongError(msg);
  throw e;
}

When it happens

Trigger: this.openai.chat.completions.create({ model, messages, temperature, max_tokens }) rejecting: server returned 4xx/5xx, model id unknown to that server, max_tokens exceeds the server's limit, auth header rejected, or the server is not actually OpenAI-compatible.

Common situations: Model id in GENERIC_OPEN_AI_MODEL_PREF not served by the endpoint; max_tokens too large for the local model; endpoint requires an API key but GENERIC_OPEN_AI_API_KEY is unset/wrong; server speaks a slightly different schema.

Related errors

• e.message
• e.message
• e.message
• e.message
• ${e.message}

AI-assisted analysis of Mintplex-Labs/anything-llm@526360e320 (2026-08-13). Data as JSON: /api/errors/41ccbb313fb5987f. Report an issue: GitHub.