Mintplex-Labs/anything-llm · critical · Error

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

Error message

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

What it means

Thrown by the GenericOpenAiLLM constructor when process.env.GENERIC_OPEN_AI_BASE_PATH is unset. This provider targets any OpenAI-compatible endpoint (LiteLLM, vLLM, Ollama's OpenAI shim, etc.), and the base path is the one piece of configuration it cannot guess — without it the OpenAI client has no baseURL.

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 526360e320)

Solutions

1. Set GENERIC_OPEN_AI_BASE_PATH to the OpenAI-compatible base URL including the version, e.g. http://localhost:1234/v1
2. Confirm the endpoint is up and answers /models
3. Restart AnythingLLM after editing .env
4. If using a proxy (LiteLLM/vLLM), start it first and verify the path

Example fix

// before
// .env: GENERIC_OPEN_AI_MODEL_PREF=local-model   // but no base path

// after
// .env:
//   GENERIC_OPEN_AI_BASE_PATH=http://localhost:1234/v1
//   GENERIC_OPEN_AI_MODEL_PREF=local-model

function hasGenericBasePath() {
  try {
    const u = new URL(process.env.GENERIC_OPEN_AI_BASE_PATH);
    return u.protocol.startsWith('http');
  } catch { return false; }
}
if (!hasGenericBasePath()) {
  throw new ConfigError('Set GENERIC_OPEN_AI_BASE_PATH (include /v1).');
}

When it happens

Trigger: Constructing `new GenericOpenAiLLM(embedder, modelPreference)` while GENERIC_OPEN_AI_BASE_PATH is absent. Fires when the user selected the 'Generic OpenAI' provider but did not fill in the endpoint URL.

Common situations: Misunderstanding that Generic OpenAI needs the full base URL (e.g. http://host:8000/v1) not just a host; .env line missing; pointing to an endpoint that omits the /v1 suffix; proxy/LiteLLM not started.

Related errors

• No Foundry Base Path was set.
• No Gemini API key was set.
• GenericOpenAI must have a valid model set.
• No Gitee AI API key was set.
• No Groq API key was set.

AI-assisted analysis of Mintplex-Labs/anything-llm@526360e320 (2026-08-13). Data as JSON: /api/errors/f73c48ae47b4b127. Report an issue: GitHub.