BerriAI/litellm · error · PredibaseError

'completion_response' is not a dictionary - {completion_resp

Error message

'completion_response' is not a dictionary - {completion_response}

What it means

Shape guard in the Predibase response transformation: the parsed completion_response is not a dict (e.g. a list or string), so the code cannot look up 'generated_text', and the whole payload is included in the error for inspection.

Source

Thrown at litellm/llms/predibase/chat/transformation.py:157

    ) -> ModelResponse:
        logging_obj.post_call(
            input=messages,
            api_key=api_key or "",
            original_response=raw_response.text,
            additional_args={"complete_input_dict": request_data},
        )
        try:
            completion_response: Final = raw_response.json()
        except Exception:
            raise PredibaseError(message=raw_response.text, status_code=422)

        if "error" in completion_response:
            raise PredibaseError(
                message=str(completion_response["error"]),
                status_code=raw_response.status_code,
            )
        elif not isinstance(completion_response, dict):
            raise PredibaseError(
                status_code=422,
                message=f"'completion_response' is not a dictionary - {completion_response}",
            )
        elif "generated_text" not in completion_response:
            raise PredibaseError(
                status_code=422,
                message=f"'generated_text' is not a key response dictionary - {completion_response}",
            )

        if len(completion_response["generated_text"]) > 0:
            model_response.choices[0].message.content = self.output_parser(completion_response["generated_text"])

        if "details" in completion_response and "tokens" in completion_response["details"]:
            model_response.choices[0].finish_reason = map_finish_reason(completion_response["details"]["finish_reason"])
            sum_logprob = 0
            for token in completion_response["details"]["tokens"]:
                if token["logprob"] is not None:
                    sum_logprob += token["logprob"]

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Ensure the Predibase endpoint returns a JSON object; a non-dict response indicates a proxy or endpoint misconfiguration.
2. Verify api_base points to the correct Predibase deployment URL.

Example fix

# confirm api_base returns JSON: curl the endpoint and check the payload type.

When it happens

Trigger: Triggered when the Predibase completion response is not a dictionary, e.g. the API returned an unexpected payload shape.

Common situations: See trigger scenarios.

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/b0faaedf2f88b276. Report an issue: GitHub.