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 when EMBEDDING_MODEL_PREF is unset. There is no default because LM Studio only serves the models you explicitly loaded; the embedder needs the exact id of a loaded embedding model. This check runs after the base-path check, so seeing it means EMBEDDING_BASE_PATH is already set.

Solutions

1. Load an embedding model in LM Studio (not a chat model), e.g. nomic-embed-text-v1.5
2. Copy its exact model id from LM Studio's server/UI
3. Set EMBEDDING_MODEL_PREF to that id and restart

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=text-embedding-nomic-embed-text-v1.5

function assertLMStudioModelSelected() {
  if (!process.env.EMBEDDING_MODEL_PREF) {
    throw new Error("LMStudio embedder needs EMBEDDING_MODEL_PREF set to a loaded embedding model id");
  }
}
assertLMStudioModelSelected();

try {
  const embedder = new LMStudioEmbedder();
} catch (e) {
  if (e.message === "No embedding model was set.") {
    // load an embedding model in LM Studio, then set its exact id here
  }
  throw e;
}

When it happens

Trigger: Configuring the LMStudio embedding engine with a URL but empty model field; deleting EMBEDDING_MODEL_PREF from .env; settings saved before a model was chosen.

Common situations: Assuming LM Studio embeds with 'whatever model is in the chat tab' — embeddings require a dedicated embedding model to be loaded (e.g. nomic-embed-text) and its id recorded here.

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

• No embedding base path was set.
• LMStudio Failed to embed
• LMStudio must have a valid model set.
• No embedding base path was set.
• No Embedding Model Pref was set.

AI-assisted analysis of Mintplex-Labs/anything-llm@3aec848f28 (2026-08-18). Data as JSON: /api/errors/061ba23505da55b4. Report an issue: GitHub.

Appendix: 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 3aec848f28)