mem0ai/mem0 · error · Error

Vector at index ${index} is empty. Expected dimension ${this

Error message

Vector at index ${index} is empty. Expected dimension ${this.embeddingModelDims}.

What it means

Before inserting into OpenSearch, each vector is checked for a non-zero length. An empty array means the embedding call returned no components (for example an empty-string input or a broken provider response), and OpenSearch would reject the document with a less clear mapping error, so the store raises this explicit message naming the index position and expected dimension.

Source

Thrown at mem0-ts/src/oss/src/vector_stores/opensearch.ts:216

    await this.client.indices.create({
      index: "memory_migrations",
      body: {
        mappings: {
          properties: {
            user_id: { type: "keyword" },
          },
        },
      },
    });
  }

  private validateVector(vector: number[], index: number): void {
    if (!vector) {
      throw new Error(`Vector at index ${index} is null or undefined.`);
    }
    if (vector.length === 0) {
      throw new Error(
        `Vector at index ${index} is empty. Expected dimension ${this.embeddingModelDims}.`,
      );
    }
    if (vector.length !== this.embeddingModelDims) {
      throw new Error(
        `Vector at index ${index} has dimension ${vector.length}, but index ` +
          `'${this.collectionName}' expects dimension ${this.embeddingModelDims}.`,
      );
    }
  }

  async insert(
    vectors: number[][],
    ids: string[],
    payloads: Record<string, any>[],
  ): Promise<void> {
    await this.initialize();
    vectors.forEach((vector, index) => this.validateVector(vector, index));

View on GitHub (pinned to 001c235229)

Solutions

1. Skip or reject empty documents before embedding so providers never receive them.
2. Validate embedding responses: if emb.length === 0 throw or retry at the embedding layer.
3. Log the failing index from the message and inspect that input document.

Example fix

// before
const embs = docs.map(d => embed(d)); // some empty string -> []
await store.insert(embs, ids, payloads);

// after
const embs = docs.map(d => d.trim() ? embed(d) : null);
if (embs.some(e => !e || e.length === 0)) throw new Error('empty embedding');

if (vectors.some((v) => Array.isArray(v) && v.length === 0)) {
  throw new Error('Empty embedding vector produced; check embedding inputs');
}

const isNonEmptyVector = (v: unknown): v is number[] => Array.isArray(v) && v.length > 0;

When it happens

Trigger: Passing vectors[i] === [] — e.g. an embedding provider returned an empty vector for an empty/whitespace document, or a placeholder was never filled.

Common situations: Embedding empty strings or skipped documents; test fixtures with empty arrays; providers that return [] on rate-limit or content-filter instead of throwing.

Related errors

• Vector at index ${index} is null or undefined.
• Unknown embedder provider: ${providerId}
• Langchain embedder provider requires an initialized Langchai
• Provided Langchain 'instance' in the 'model' field does not
• Invalid memory action: ${memoryAction}

AI-assisted analysis of mem0ai/mem0@001c235229 (2026-08-15). Data as JSON: /api/errors/fa2bb4d691f8950e. Report an issue: GitHub.