Mintplex-Labs/anything-llm · critical · Error

No embedding model was set.

Error message

No embedding model was set.

What it means

Thrown by the LocalAiEmbedder constructor when EMBEDDING_MODEL_PREF is unset. LocalAI models must be installed explicitly (via its model gallery or config), so there is no safe default model id; the constructor demands the exact name of an installed embedding model. It runs after the base-path check, so this error implies the URL is already configured.

Solutions

1. Install an embedding model in LocalAI (gallery: e.g. 'localai' provides bert-embeddings / sentence-transformers backends)
2. Copy the exact installed model name into EMBEDDING_MODEL_PREF
3. Restart the backend and re-embed the failed documents

Example fix

# before
EMBEDDING_BASE_PATH=http://localhost:8080/v1
# EMBEDDING_MODEL_PREF unset

# after
EMBEDDING_BASE_PATH=http://localhost:8080/v1
EMBEDDING_MODEL_PREF=bert-embeddings

function assertLocalAiModelSelected() {
  if (!process.env.EMBEDDING_MODEL_PREF) {
    throw new Error("LocalAI embedder needs EMBEDDING_MODEL_PREF set to an installed embedding model");
  }
}
assertLocalAiModelSelected();

try {
  const embedder = new LocalAiEmbedder();
} catch (e) {
  if (e.message === "No embedding model was set.") {
    // install an embedding model from the LocalAI gallery, then set its exact name
  }
  throw e;
}

When it happens

Trigger: Configuring LocalAI embeddings with a URL but empty model field; the model was uninstalled from LocalAI but the preference left blank; settings saved mid-configuration.

Common situations: Fresh LocalAI installs where no embedding backend (e.g. bert-embeddings) has been pulled from the gallery yet; model name mismatch between the gallery id and what the user typed.

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.
• No Embedding Model Pref was set.
• No embedding model was set.
• ${error.message}
• GenericOpenAI must have a valid base path to use for the…

AI-assisted analysis of Mintplex-Labs/anything-llm@3aec848f28 (2026-08-18). Data as JSON: /api/errors/8141341434a9b824. Report an issue: GitHub.

Appendix: source

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

const {
  toChunks,
  maximumChunkLength,
  reportEmbeddingProgress,
} = require("../../helpers");

class LocalAiEmbedder {
  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.");

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

    // Limit of how many strings we can process in a single pass to stay with resource or network limits
    this.maxConcurrentChunks = 50;
    this.embeddingMaxChunkLength = maximumChunkLength();

    this.log(
      `Initialized with ${this.model} - Max Size: ${this.embeddingMaxChunkLength}` +
        (this.outputDimensions
          ? ` - Output Dimensions: ${this.outputDimensions}`
          : " Assuming default output dimensions")

View on GitHub (pinned to 3aec848f28)