mem0ai/mem0 · error · ValueError

Vector at index {idx} is empty. Expected a vector of dimensi

Error message

Vector at index {idx} is empty. Expected a vector of dimension {self.embedding_model_dims}, got an empty vector.

What it means

insert() rejects vectors whose length is 0. An empty list is structurally a vector of dimension 0, which cannot match the index's configured embedding_model_dims, so the store fails fast with a message naming the expected dimension rather than letting OpenSearch reject the bulk write.

Source

Thrown at mem0/vector_stores/opensearch.py:170

    def insert(
        self, vectors: List[List[float]], payloads: Optional[List[Dict]] = None, ids: Optional[List[str]] = None
    ) -> List[OutputData]:
        """Insert vectors into the index."""
        if not ids:
            ids = [str(i) for i in range(len(vectors))]

        if payloads is None:
            payloads = [{} for _ in range(len(vectors))]

        for idx, vec in enumerate(vectors):
            if vec is None:
                raise ValueError(
                    f"Vector at index {idx} is null. "
                    f"This usually means the embedding model failed to generate an embedding. "
                    f"Check that your embedding model is configured correctly and returning valid vectors."
                )
            if len(vec) == 0:
                raise ValueError(
                    f"Vector at index {idx} is empty. "
                    f"Expected a vector of dimension {self.embedding_model_dims}, got an empty vector."
                )
            if len(vec) != self.embedding_model_dims:
                raise ValueError(
                    f"Vector at index {idx} has dimension {len(vec)}, "
                    f"but the index '{self.collection_name}' expects dimension {self.embedding_model_dims}. "
                    f"Ensure your embedding model's output dimensions match the vector store configuration."
                )

        results = []
        for i, (vec, id_) in enumerate(zip(vectors, ids)):
            body = {
                "vector_field": vec,
                "payload": payloads[i],
                "id": id_,
            }
            try:

View on GitHub (pinned to 001c235229)

Solutions

1. Filter out empty inputs before embedding: skip blank documents
2. Make the embedder raise on empty input instead of returning []
3. Pre-validate vector shapes with the guard below

Example fix

# before
vectors = [embed(t) for t in texts]  # embed(" ") -> []
store.insert(vectors, payloads, ids)

# after
texts = [t for t in texts if t and t.strip()]
vectors = [embed(t) for t in texts]
store.insert(vectors, payloads, ids)

texts = [t for t in texts if t and t.strip()]
vectors = [embedder.embed(t) for t in texts]
assert all(len(v) > 0 for v in vectors), "empty vector produced"
store.insert(vectors=vectors, payloads=payloads[:len(texts)], ids=ids[:len(texts)])

def has_no_empty_vectors(vectors) -> bool:
    return all(v is not None and len(v) > 0 for v in vectors)

try:
    store.insert(vectors, payloads, ids)
except ValueError as e:
    if "is empty" in str(e):
        keep = [i for i, v in enumerate(vectors) if len(v) > 0]
        store.insert([vectors[i] for i in keep], [payloads[i] for i in keep], [ids[i] for i in keep])
    else:
        raise

When it happens

Trigger: Passing vectors=[[]] — an embedder that returned an empty list (some tokenizers do for whitespace-only input), or a slicing bug producing empty rows.

Common situations: Empty/whitespace strings reaching the embedding pipeline; embedding stubs in tests returning []; off-by-one batching that truncates a vector.

Related errors

• Vector at index ${index} is null or undefined.
• Vector at index ${index} is empty. Expected dimension ${this
• Vector at index ${index} has dimension ${vector.length}, but
• Vector at index {idx} is null. This usually means the embedd
• Cannot update with an empty vector.

AI-assisted analysis of mem0ai/mem0@001c235229 (2026-08-15). Data as JSON: /api/errors/6cdccac2ef7307d5. Report an issue: GitHub.