Mintplex-Labs/anything-llm · critical · Error

No DeepSeek API key was set.

Error message

No DeepSeek API key was set.

What it means

Constructor guard that prevents DeepSeekLLM instantiation when DEEPSEEK_API_KEY is missing from the environment. The key is required to configure the OpenAI-compatible client pointed at https://api.deepseek.com/v1, so the class aborts immediately if it cannot authenticate.

Source

Thrown at server/utils/AiProviders/deepseek/index.js:13

const { NativeEmbedder } = require("../../EmbeddingEngines/native");
const {
  LLMPerformanceMonitor,
} = require("../../helpers/chat/LLMPerformanceMonitor");
const { MODEL_MAP } = require("../modelMap");
const {
  handleDefaultStreamResponseV2,
} = require("../../helpers/chat/responses");

class DeepSeekLLM {
  constructor(embedder = null, modelPreference = null) {
    if (!process.env.DEEPSEEK_API_KEY)
      throw new Error("No DeepSeek API key was set.");
    this.className = "DeepSeekLLM";
    const { OpenAI: OpenAIApi } = require("openai");

    this.openai = new OpenAIApi({
      apiKey: process.env.DEEPSEEK_API_KEY,
      baseURL: "https://api.deepseek.com/v1",
    });
    this.model =
      modelPreference || process.env.DEEPSEEK_MODEL_PREF || "deepseek-chat";
    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(

View on GitHub (pinned to 526360e320)

Solutions

1. Set DEEPSEEK_API_KEY in the .env file to a valid key from platform.deepseek.com.
2. Restart the server so the process picks up the new env var.
3. Re-enter the key in the AnythingLLM UI DeepSeek provider settings and save.

Example fix

# .env
DEEPSEEK_API_KEY=sk-your-deepseek-key-here

const DEEPSEEK_KEY = process.env.DEEPSEEK_API_KEY;
if (!DEEPSEEK_KEY || DEEPSEEK_KEY.trim() === '')
  throw new Error('DEEPSEEK_API_KEY must be set before using the DeepSeek provider');

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

When it happens

Trigger: Instantiating `new DeepSeekLLM()` with DEEPSEEK_API_KEY unset or empty; selecting DeepSeek as the LLM provider without saving an API key; env var name typo (e.g. DEEPSEEKKEY vs DEEPSEEK_API_KEY).

Common situations: New deployment that selected DeepSeek but never entered a key; .env not reloaded after adding the key; key was revoked on the DeepSeek platform; container restart with an env file that omits the variable.

Related errors

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

AI-assisted analysis of Mintplex-Labs/anything-llm@526360e320 (2026-08-13). Data as JSON: /api/errors/ff2e6dab5a876fc7. Report an issue: GitHub.