Mintplex-Labs/anything-llm · error · Error

${e.message}

Error message

${e.message}

What it means

Re-thrown from the OpenAI SDK rejection inside PPIOLLM.getChatCompletion via `.catch((e) => { throw new Error(e.message); })`. The wrapper discards the SDK error class and HTTP status, leaving only the message string, so a 401, 429, and a 500 look identical to the caller except for wording.

Source

Thrown at server/utils/AiProviders/ppio/index.js:162

    };
    return [prompt, ...chatHistory, { role: "user", content: userPrompt }];
  }

  async getChatCompletion(messages = null, { temperature = 0.7 }) {
    if (!(await this.isValidChatCompletionModel(this.model)))
      throw new Error(
        `PPIO chat: ${this.model} is not valid for chat completion!`
      );

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

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

    return {
      textResponse: result.output.choices[0].message.content,
      metrics: {
        prompt_tokens: result.output.usage.prompt_tokens || 0,
        completion_tokens: result.output.usage.completion_tokens || 0,
        total_tokens: result.output.usage.total_tokens || 0,
        outputTps: result.output.usage.completion_tokens / result.duration,
        duration: result.duration,
        model: this.model,

View on GitHub (pinned to 526360e320)

Solutions

1. Match the message: '401'/'Unauthorized' -> key issue; '429'/'rate' -> throttle; 'model'/'not found' -> model id issue; 'timeout'/'ECONN' -> network.
2. curl the same payload to https://api.ppintra.com/v3/openai/chat/completions to isolate auth vs model vs quota.
3. Check the PPIO console for quota/usage.
4. For transient errors, wrap the call in bounded exponential-backoff retry.

Example fix

// before
const out = await llm.getChatCompletion(messages, { temperature: 0.7 });

// after
try {
  const out = await llm.getChatCompletion(messages, { temperature: 0.7 });
} catch (err) {
  if (/401|unauthorized/i.test(err.message)) throw new Error("PPIO key invalid — reconfigure", { cause: err });
  if (/429|rate/i.test(err.message)) throw new Error("PPIO rate limited — back off", { cause: err });
  throw err;
}

function classifyPpioError(message) {
  if (/401|unauthorized|invalid api key/i.test(message)) return "auth";
  if (/429|rate limit|quota/i.test(message)) return "rate";
  if (/5\d{2}|timeout|ECONN/i.test(message)) return "transient";
  return "fatal";
}

function isTransientPpioError(message) {
  return typeof message === "string" && /429|5\d{2}|timeout|ECONNRESET|fetch failed/i.test(message);
}

async function ppioCall(llm, messages, opts, retries = 3) {
  for (let i = 0; i <= retries; i++) {
    try {
      return await llm.getChatCompletion(messages, opts);
    } catch (e) {
      if (/401|not valid for chat/i.test(e.message) || i === retries) throw e;
      await new Promise((r) => setTimeout(r, 2 ** i * 500));
    }
  }
}

When it happens

Trigger: PPIO's endpoint returns non-2xx or the client throws pre-response: 401 invalid key, 403 forbidden, 404 model not found server-side, 429 rate/quota, 5xx, or a transport error (DNS, TLS, abort).

Common situations: PPIO_API_KEY was correct at startup but later deactivated; burst traffic tripped the per-minute rate limit; requesting a model the key's plan excludes; cold-start timeout against ppinfra.com; client aborted the request while streaming.

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/f8727e0e5df1c74e. Report an issue: GitHub.