RyanCodrai/turbovec · error · ValueError

embedder returned empty vectors (dim 0) for {n_texts} texts

Error message

embedder returned empty vectors (dim 0) for {n_texts} texts

What it means

Raised in _check_embedded_batch when a 2D embedder output has zero-width vectors (shape (N, 0)) for the given texts. The embedder produced empty vectors — typically a broken model, empty inputs, or a bad wrapper — which would otherwise fail opaquely inside the index kernel.

Source

Thrown at turbovec-python/python/turbovec/langchain.py:203

    def _check_embedded_batch(vectors: np.ndarray, n_texts: int) -> None:
        """Validate the shape of an embedder's document-batch output.

        Only 2D outputs are inspected here — any other ndim falls through
        to ``_store_texts_and_vectors``, whose existing guard names the bad
        dimensionality directly. Without the row-count check, a misbehaving
        embedder that returns fewer vectors than texts surfaces downstream
        as an id-count mismatch (or an IndexError during intra-batch
        dedup) that never names the embedder as the cause.
        """
        if vectors.ndim != 2:
            return
        if vectors.shape[0] != n_texts:
            raise ValueError(
                f"embedder returned {vectors.shape[0]} vectors for "
                f"{n_texts} texts"
            )
        if vectors.shape[1] == 0:
            raise ValueError(
                f"embedder returned empty vectors (dim 0) for {n_texts} texts"
            )

    def _validate_query_embedding(self, embedded: Any) -> np.ndarray:
        """Coerce an embedder's query output to a 1D float32 vector,
        rejecting None and wrong-rank outputs with an error that names
        the embedder (the raw values otherwise surface as opaque errors
        from the index kernel)."""
        if embedded is None:
            raise ValueError("embedder returned None instead of a query embedding")
        qvec = np.asarray(embedded, dtype=np.float32)
        if qvec.ndim != 1:
            raise ValueError(
                f"embedder returned a {qvec.ndim}D query embedding; "
                "expected a single 1D vector"
            )
        return qvec

View on GitHub (pinned to ccab9f325e)

Solutions

1. Inspect the embedder's inputs and configuration; empty vectors usually indicate empty texts or an unloaded model.
2. Validate embedder output shape at embed time before calling add_texts.
3. Catch the ValueError to fail the ingestion step with an embedder-named message.

When it happens

Trigger: Thrown at turbovec-python/python/turbovec/langchain.py:203 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of RyanCodrai/turbovec@ccab9f325e (2026-09-06). Data as JSON: /api/errors/cd77621ffd642aee. Report an issue: GitHub.