Mintplex-Labs/anything-llm · error · Error

Perplexity chat: is not valid for chat completion!

Error message

Perplexity chat: ${this.model} is not valid for chat completion!

What it means

Pre-flight guard in PerplexityLLM.getChatCompletion: the configured model is not a key in the bundled Perplexity MODELS list, so a completion would target an unsupported Sonar model and is rejected before the API call.

Solutions

1. Select a Perplexity model valid for chat completion.

When it happens

Trigger: Thrown when the configured Perplexity model is not a chat model.

Common situations: Model preference set to an invalid model.

AI-assisted analysis of Mintplex-Labs/anything-llm@20f6d3546c (2026-08-18). Data as JSON: /api/errors/ec1b3b44935268b9. Report an issue: GitHub.

Appendix: source

Thrown at server/utils/AiProviders/perplexity/index.js:96

    return availableModels.hasOwnProperty(model);
  }

  constructPrompt({
    systemPrompt = "",
    contextTexts = [],
    chatHistory = [],
    userPrompt = "",
  }) {
    const prompt = {
      role: "system",
      content: `${systemPrompt}${this.#appendContext(contextTexts)}`,
    };
    return [prompt, ...chatHistory, { role: "user", content: userPrompt }];
  }

  async getChatCompletion(messages = null, { temperature = 0.7 }) {
    if (!(await this.isValidChatCompletionModel(this.model)))
      throw new Error(
        `Perplexity 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 (
      !result.output.hasOwnProperty("choices") ||
      result.output.choices.length === 0

View on GitHub (pinned to 20f6d3546c)