BerriAI/litellm · error · ValueError

embedContent response missing 'embedding' field: {response_j

Error message

embedContent response missing 'embedding' field: {response_json}

What it means

Gemini embedContent response guard: the parsed response JSON lacks the required 'embedding' field, so no vector can be extracted; the full response JSON is echoed to diagnose the unexpected provider payload.

Source

Thrown at litellm/llms/vertex_ai/gemini_embeddings/batch_embed_content_transformation.py:425

    response_json: dict,
    resolved_files: Mapping[str, Mapping[str, str]] | None = None,
) -> EmbeddingResponse:
    """
    Process Gemini embedContent response (single embedding for multimodal input).

    Args:
        input: Original input
        model_response: EmbeddingResponse to populate
        model: Model name
        response_json: Raw JSON response from embedContent endpoint
        resolved_files: Mapping of file references (files/abc) to {mime_type, uri},
            used to bill resolved image references at the per-image rate

    Returns:
        EmbeddingResponse with single embedding
    """
    if "embedding" not in response_json:
        raise ValueError(f"embedContent response missing 'embedding' field: {response_json}")

    embedding_data: Final = response_json["embedding"]

    openai_embedding: Final = Embedding(
        embedding=embedding_data["values"],
        index=0,
        object="embedding",
    )

    model_response.data = [openai_embedding]
    model_response.model = model
    model_response.usage = _usage_from_embed_content_response(
        input=input,
        model=model,
        raw_usage_metadata=response_json.get("usageMetadata"),
        resolved_files=resolved_files or {},
    )

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Inspect the raw response_json in the error for an upstream error message or a changed response schema.
2. Retry the request; if it persists, verify the model name and that the embedContent endpoint returned a successful status.

When it happens

Trigger: Thrown at litellm/llms/vertex_ai/gemini_embeddings/batch_embed_content_transformation.py:425 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/7547ec979161289c. Report an issue: GitHub.