Mintplex-Labs/anything-llm · critical · Error

No embedding model was set.

Error message

No embedding model was set.

What it means

Thrown by the LMStudioEmbedder constructor (line 12) when process.env.EMBEDDING_MODEL_PREF is falsy, immediately after the base-path check. The model identifier is required because it is passed as the `model` field to every /embeddings request; an empty value would make LMStudio reject or misroute the call. This guard fails fast before any network work.

Source

Thrown at server/utils/EmbeddingEngines/lmstudio/index.js:12

const { parseLMStudioBasePath } = require("../../AiProviders/lmStudio");
const {
  maximumChunkLength,
  reportEmbeddingProgress,
} = require("../../helpers");

class LMStudioEmbedder {
  constructor() {
    if (!process.env.EMBEDDING_BASE_PATH)
      throw new Error("No embedding base path was set.");
    if (!process.env.EMBEDDING_MODEL_PREF)
      throw new Error("No embedding model was set.");

    const apiKey = process.env.LMSTUDIO_AUTH_TOKEN ?? null;
    this.className = "LMStudioEmbedder";
    const { OpenAI: OpenAIApi } = require("openai");
    this.lmstudio = new OpenAIApi({
      baseURL: parseLMStudioBasePath(process.env.EMBEDDING_BASE_PATH),
      apiKey,
    });
    this.model = process.env.EMBEDDING_MODEL_PREF;

    // Limit of how many strings we can process in a single pass to stay with resource or network limits
    this.maxConcurrentChunks = 1;
    this.embeddingMaxChunkLength = maximumChunkLength();
  }

  log(text, ...args) {
    console.log(`\x1b[36m[${this.className}]\x1b[0m ${text}`, ...args);
  }

View on GitHub (pinned to 526360e320)

Solutions

1. Set EMBEDDING_MODEL_PREF to the exact model name loaded in LMStudio (visible in its UI), e.g. nomic-ai/nomic-embed-text-v1.5
2. Verify the string matches LMStudio's loaded model identifier exactly (case/hyphens)
3. Reload AnythingLLM env after editing .env

Example fix

// before
EMBEDDING_BASE_PATH=http://localhost:1234/v1
// EMBEDDING_MODEL_PREF unset

// after
EMBEDDING_BASE_PATH=http://localhost:1234/v1
EMBEDDING_MODEL_PREF=nomic-ai/nomic-embed-text-v1.5

function hasEmbeddingModelPref(env = process.env) {
  return typeof env.EMBEDDING_MODEL_PREF === 'string' &&
         env.EMBEDDING_MODEL_PREF.trim().length > 0;
}
if (!hasEmbeddingModelPref()) {
  throw new Error('Missing EMBEDDING_MODEL_PREF for LMStudio.');
}

function isNonEmptyModel(v) {
  return typeof v === 'string' && v.trim().length > 0;
}

When it happens

Trigger: Instantiating `new LMStudioEmbedder()` with EMBEDDING_MODEL_PREF unset/empty. Happens at construction, before #isAlive or any embedding call. Typically when the UI/system settings saved a base path but no model, or .env is partially configured.

Common situations: User loaded a model into LMStudio but did not set the matching EMBEDDING_MODEL_PREF in AnythingLLM; model name copied with a typo; switching engines and the previous model env was cleared; fresh install where only EMBEDDING_BASE_PATH was set.

Related errors

• No embedding base path was set.
• LiteLLM must have a valid base path to use for the api.
• No embedding base path was set.
• No embedding model was set.
• No Mistral API key was set.

AI-assisted analysis of Mintplex-Labs/anything-llm@526360e320 (2026-08-13). Data as JSON: /api/errors/061ba23505da55b4. Report an issue: GitHub.