BerriAI/litellm · error · ValueError

Expected 'predictions' to be a list, got {type(_predictions)

Error message

Expected 'predictions' to be a list, got {type(_predictions)}

What it means

Type guard on the BGE response: 'predictions' exists but is not a list (e.g. a dict or string), so it cannot be iterated per input text to build embedding rows. The actual type is included in the message.

Source

Thrown at litellm/llms/vertex_ai/vertex_embeddings/bge.py:148

        Args:
            response: The raw response from Vertex AI
            model: The model name
            model_response: The EmbeddingResponse object to populate

        Returns:
            EmbeddingResponse: The transformed response in OpenAI format

        Raises:
            KeyError: If response doesn't contain 'predictions'
            ValueError: If predictions is not a list or contains invalid data
        """
        if "predictions" not in response:
            raise KeyError("Response missing 'predictions' field")

        _predictions: Final = response["predictions"]

        if not isinstance(_predictions, list):
            raise ValueError(f"Expected 'predictions' to be a list, got {type(_predictions)}")

        embedding_response: Final = []
        # BGE models don't return token counts, so we estimate or set to 0
        input_tokens: Final = 0

        for idx, embedding_values in enumerate(_predictions):
            if not isinstance(embedding_values, list):
                raise ValueError(f"Expected embedding at index {idx} to be a list, got {type(embedding_values)}")

            embedding_response.append(
                {
                    "object": "embedding",
                    "index": idx,
                    "embedding": embedding_values,
                }
            )

        model_response.object = "list"

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Check the raw response — 'predictions' should be a list of embeddings; a different type indicates an unexpected endpoint response.
2. Verify you are calling the correct deployed endpoint for the BGE model with the right request schema.

When it happens

Trigger: Thrown at litellm/llms/vertex_ai/vertex_embeddings/bge.py:148 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/3b39f591fe5ad964. Report an issue: GitHub.