Mintplex-Labs/anything-llm · error · Error

GenericOpenAI must have a valid base path to use for the…

Error message

GenericOpenAI must have a valid base path to use for the api.

What it means

The GenericOpenAiLLM constructor throws when GENERIC_OPEN_AI_BASE_PATH is unset. This provider is the 'OpenAI-compatible' connector for arbitrary endpoints (LM Studio, Ollama's compat layer, vLLM, OpenRouter, etc.), and the base path is the one mandatory setting — the API key (GENERIC_OPEN_AI_API_KEY) is optional and defaults to null. The constructor also attaches a custom User-Agent and parsed custom headers to every request.

Solutions

1. Set GENERIC_OPEN_AI_BASE_PATH to your endpoint including the version segment, e.g. http://localhost:1234/v1, and restart
2. If the endpoint needs auth, also set GENERIC_OPEN_AI_API_KEY
3. Verify the target service is up: curl http://localhost:1234/v1/models
4. For the real OpenAI API, use the native OpenAI provider instead of the generic one

Example fix

# before (.env)
# GENERIC_OPEN_AI_BASE_PATH unset

# after (.env)
GENERIC_OPEN_AI_BASE_PATH=http://localhost:1234/v1
GENERIC_OPEN_AI_API_KEY=sk-...   # optional

if (!process.env.GENERIC_OPEN_AI_BASE_PATH) {
  return setupError("Generic OpenAI needs GENERIC_OPEN_AI_BASE_PATH (e.g. http://localhost:1234/v1).");
}
const llm = new GenericOpenAiLLM(embedder, modelPref);

try {
  const llm = new GenericOpenAiLLM(embedder, modelPref);
} catch (err) {
  if (/must have a valid base path/.test(err.message)) {
    return respond("Set GENERIC_OPEN_AI_BASE_PATH in settings first.");
  }
  throw err;
}

When it happens

Trigger: Selecting the 'Generic OpenAI' provider without setting GENERIC_OPEN_AI_BASE_PATH, e.g. intending http://localhost:1234/v1 (LM Studio), http://localhost:11434/v1 (Ollama), or a hosted compat URL. Any chat request instantiates the class and fails here.

Common situations: User assumed the provider defaults to api.openai.com (it does not — use the dedicated OpenAI provider for that); forgot /v1 suffix so later requests 404; base path set under a misspelled var name; local service not running when the path was configured.

Understand the failure class

Background: "environment variable is not set" and "Missing keys in environment" errors: what missing required env var messages mean and how to fix them — this error's family across 28 libraries.

Related errors

• e.message
• GenericOpenAI must have a valid base path to use for the…
• No FireworksAI API key was set.
• No Foundry Base Path was set.
• No Gemini API key was set.

AI-assisted analysis of Mintplex-Labs/anything-llm@3aec848f28 (2026-08-18). Data as JSON: /api/errors/f73c48ae47b4b127. Report an issue: GitHub.

Appendix: source

Thrown at server/utils/AiProviders/genericOpenAi/index.js:21

const {
  LLMPerformanceMonitor,
} = require("../../helpers/chat/LLMPerformanceMonitor");
const {
  formatChatHistory,
  writeResponseChunk,
  clientAbortedHandler,
  extractReasoningContent,
} = require("../../helpers/chat/responses");
const { v4: uuidv4 } = require("uuid");
const { toValidNumber } = require("../../http");
const { getAnythingLLMUserAgent } = require("../../../endpoints/utils");
const { attachmentToContentBlock } = require("../../helpers/attachments");

class GenericOpenAiLLM {
  constructor(embedder = null, modelPreference = null) {
    const { OpenAI: OpenAIApi } = require("openai");
    if (!process.env.GENERIC_OPEN_AI_BASE_PATH)
      throw new Error(
        "GenericOpenAI must have a valid base path to use for the api."
      );

    this.className = "GenericOpenAiLLM";
    this.basePath = process.env.GENERIC_OPEN_AI_BASE_PATH;
    this.openai = new OpenAIApi({
      baseURL: this.basePath,
      apiKey: process.env.GENERIC_OPEN_AI_API_KEY ?? null,
      defaultHeaders: {
        "User-Agent": getAnythingLLMUserAgent(),
        ...GenericOpenAiLLM.parseCustomHeaders(),
      },
    });
    this.model =
      modelPreference ?? process.env.GENERIC_OPEN_AI_MODEL_PREF ?? null;
    this.maxTokens = process.env.GENERIC_OPEN_AI_MAX_TOKENS
      ? toValidNumber(process.env.GENERIC_OPEN_AI_MAX_TOKENS, 1024)
      : 1024;

View on GitHub (pinned to 3aec848f28)