mem0ai/mem0 · error · Error

Unsupported FastEmbed model "${config.model}". Supported mod

Error message

Unsupported FastEmbed model "${config.model}". Supported models: ${SUPPORTED_MODELS.join(", ")}.

What it means

Thrown by the FastEmbedEmbedder constructor when config.model is a non-empty string that is not in the SDK's fixed allowlist. FastEmbed ships only a fixed set of ONNX models, mirrored here as literals so an invalid name is rejected synchronously with a clear list instead of failing later inside FlagEmbedding.init() with a download error. Supported: fast-all-MiniLM-L6-v2, fast-bge-base-en, fast-bge-base-en-v1.5, fast-bge-small-en, fast-bge-small-en-v1.5, fast-bge-small-zh-v1.5, fast-multilingual-e5-large. Omitting model entirely is fine (defaults to fast-bge-small-en-v1.5).

Source

Thrown at mem0-ts/src/oss/src/embeddings/fastembed.ts:31

  "fast-all-MiniLM-L6-v2",
  "fast-bge-base-en",
  "fast-bge-base-en-v1.5",
  "fast-bge-small-en",
  "fast-bge-small-en-v1.5",
  "fast-bge-small-zh-v1.5",
  "fast-multilingual-e5-large",
] as const;
type FastEmbedModel = (typeof SUPPORTED_MODELS)[number];
const DEFAULT_MODEL: FastEmbedModel = "fast-bge-small-en-v1.5";

export class FastEmbedEmbedder implements Embedder {
  private readonly modelName: FastEmbedModel;
  private embeddingModel?: Promise<FlagEmbedding>;

  constructor(config: EmbeddingConfig) {
    if (typeof config.model === "string" && config.model.length > 0) {
      if (!SUPPORTED_MODELS.includes(config.model as FastEmbedModel)) {
        throw new Error(
          `Unsupported FastEmbed model "${config.model}". ` +
            `Supported models: ${SUPPORTED_MODELS.join(", ")}.`,
        );
      }
      this.modelName = config.model as FastEmbedModel;
    } else {
      this.modelName = DEFAULT_MODEL;
    }
  }

  private getEmbeddingModel(): Promise<FlagEmbedding> {
    if (!this.embeddingModel) {
      this.embeddingModel = this.initEmbeddingModel().catch((error) => {
        this.embeddingModel = undefined;
        throw error;
      });
    }

View on GitHub (pinned to 001c235229)

Solutions

1. Use one of the exact names from the error message, e.g. 'fast-bge-small-en-v1.5' or 'fast-multilingual-e5-large'
2. If you need a model outside the list, switch provider to openai/huggingface (TEI) which accepts arbitrary model IDs
3. Omit config.model to accept the default fast-bge-small-en-v1.5

Example fix

// before
embedder: { provider: 'fastembed', config: { model: 'BAAI/bge-small-en-v1.5' } }

// after
embedder: { provider: 'fastembed', config: { model: 'fast-bge-small-en-v1.5' } }

const SUPPORTED = ['fast-all-MiniLM-L6-v2','fast-bge-base-en','fast-bge-base-en-v1.5','fast-bge-small-en','fast-bge-small-en-v1.5','fast-bge-small-zh-v1.5','fast-multilingual-e5-large'];
if (model && !SUPPORTED.includes(model)) {
  throw new Error(`Model ${model} not in FastEmbed allowlist; pick from ${SUPPORTED.join(', ')}`);
}

const isFastEmbedModel = (m: unknown): m is 'fast-all-MiniLM-L6-v2' | 'fast-bge-base-en' | 'fast-bge-base-en-v1.5' | 'fast-bge-small-en' | 'fast-bge-small-en-v1.5' | 'fast-bge-small-zh-v1.5' | 'fast-multilingual-e5-large' =>
  typeof m === 'string' && [
    'fast-all-MiniLM-L6-v2','fast-bge-base-en','fast-bge-base-en-v1.5','fast-bge-small-en','fast-bge-small-en-v1.5','fast-bge-small-zh-v1.5','fast-multilingual-e5-large',
  ].includes(m);

When it happens

Trigger: Passing a HuggingFace-style model ID (e.g. 'BAAI/bge-small-en-v1.5' or 'sentence-transformers/all-MiniLM-L6-v2') instead of the 'fast-' prefixed FastEmbed name; passing 'nomic-embed-text' or other models added in newer fastembed versions but not yet mirrored in this SDK; trailing whitespace/casing differences.

Common situations: Copying a model name from the HuggingFace hub or the Python sentence-transformers docs; upgrading the fastembed package and expecting new models to work before the SDK allowlist catches up.

Related errors

• Unknown embedder provider: ${providerId}
• Azure OpenAI requires both API key and endpoint
• FastEmbed embed() returned no embeddings
• HuggingFace embedder requires an inference endpoint. Set `hu
• Langchain embedder provider requires an initialized Langchai

AI-assisted analysis of mem0ai/mem0@001c235229 (2026-08-15). Data as JSON: /api/errors/4b13d89b6b3a670b. Report an issue: GitHub.