Mintplex-Labs/anything-llm · critical · Error

No FireworksAI API key was set.

Error message

No FireworksAI API key was set.

What it means

Constructor guard that prevents FireworksAiLLM instantiation when FIREWORKS_AI_LLM_API_KEY is missing. The key authenticates the OpenAI-compatible client at https://api.fireworks.ai/inference/v1. Without it the client cannot make inference calls, so the class aborts at construction.

Source

Thrown at server/utils/AiProviders/fireworksAi/index.js:23

const {
  LLMPerformanceMonitor,
} = require("../../helpers/chat/LLMPerformanceMonitor");
const {
  handleDefaultStreamResponseV2,
} = require("../../helpers/chat/responses");

const cacheFolder = path.resolve(
  process.env.STORAGE_DIR
    ? path.resolve(process.env.STORAGE_DIR, "models", "fireworks")
    : path.resolve(__dirname, `../../../storage/models/fireworks`)
);

class FireworksAiLLM {
  constructor(embedder = null, modelPreference = null) {
    this.className = "FireworksAiLLM";

    if (!process.env.FIREWORKS_AI_LLM_API_KEY)
      throw new Error("No FireworksAI API key was set.");
    const { OpenAI: OpenAIApi } = require("openai");
    this.openai = new OpenAIApi({
      baseURL: "https://api.fireworks.ai/inference/v1",
      apiKey: process.env.FIREWORKS_AI_LLM_API_KEY ?? null,
    });
    this.model = modelPreference || process.env.FIREWORKS_AI_LLM_MODEL_PREF;
    this.limits = {
      history: this.promptWindowLimit() * 0.15,
      system: this.promptWindowLimit() * 0.15,
      user: this.promptWindowLimit() * 0.7,
    };

    this.embedder = !embedder ? new NativeEmbedder() : embedder;
    this.defaultTemp = 0.7;

    if (!fs.existsSync(cacheFolder))
      fs.mkdirSync(cacheFolder, { recursive: true });
    this.cacheModelPath = path.resolve(cacheFolder, "models.json");

View on GitHub (pinned to 526360e320)

Solutions

1. Set FIREWORKS_AI_LLM_API_KEY in .env to a valid key from fireworks.ai/account/api-keys.
2. Restart the server to load the new env var.
3. Re-enter the key in the AnythingLLM FireworksAI provider settings and save.

Example fix

# .env
FIREWORKS_AI_LLM_API_KEY=fw-your-fireworks-key-here

const FW_KEY = process.env.FIREWORKS_AI_LLM_API_KEY;
if (!FW_KEY || FW_KEY.trim() === '')
  throw new Error('FIREWORKS_AI_LLM_API_KEY must be set before using the FireworksAI provider');

try {
  provider = new FireworksAiLLM(embedder, modelPref);
} catch (e) {
  if (/No FireworksAI API key/i.test(e.message))
    return respondConfigError('Set FIREWORKS_AI_LLM_API_KEY in the FireworksAI provider settings.');
  throw e;
}

When it happens

Trigger: Instantiating `new FireworksAiLLM()` with FIREWORKS_AI_LLM_API_KEY unset or empty; selecting FireworksAI as the provider without saving a key; env var name typo.

Common situations: Fresh deployment selecting FireworksAI without entering a key; .env missing the key after migration; key revoked on the Fireworks AI dashboard; CI environment without the key injected.

Related errors

• No CometAPI API key was set.
• No DeepSeek API key was set.
• No Docker Model Runner API Base Path was set.
• No Docker Model Runner Model Pref was set.
• FireworksAI chat: ${this.model} is not valid for chat comple

AI-assisted analysis of Mintplex-Labs/anything-llm@526360e320 (2026-08-13). Data as JSON: /api/errors/ff039c7a675ce518. Report an issue: GitHub.