BerriAI/litellm · error · ValueError

Missing required fields in the result={result}

Error message

Missing required fields in the result={result}

What it means

For each item in the Fireworks rerank results array, litellm requires the fields 'index' and 'relevance_score' to construct a RerankResponseResult. An item missing either key raises ValueError echoing that specific result object, pinpointing exactly which entry in the response was malformed.

Source

Thrown at litellm/llms/fireworks_ai/rerank/transformation.py:224

        _billed_units: Final = RerankBilledUnits(search_units=usage.get("total_tokens", 0))
        _tokens: Final = RerankTokens(
            input_tokens=usage.get("prompt_tokens", 0),
            output_tokens=usage.get("completion_tokens", 0),
        )
        rerank_meta: Final = RerankResponseMeta(billed_units=_billed_units, tokens=_tokens)

        # Extract results - Fireworks AI uses "data" instead of "results"
        _results: Final[list[dict] | None] = raw_response_json.get("data") or raw_response_json.get("results")

        if _results is None:
            raise ValueError(f"No results found in the response={raw_response_json}")

        rerank_results: Final[list[RerankResponseResult]] = []

        for result in _results:
            # Validate required fields exist
            if not all(key in result for key in ["index", "relevance_score"]):
                raise ValueError(f"Missing required fields in the result={result}")

            # Get document data - Fireworks AI returns document as a string directly
            document_text = result.get("document")
            document = None
            if document_text:
                # Handle both string and object formats
                if isinstance(document_text, str):
                    document = RerankResponseDocument(text=document_text)
                elif isinstance(document_text, dict):
                    # Handle object format if it exists
                    text = document_text.get("text", "")
                    if text:
                        document = RerankResponseDocument(text=str(text))

            # Create typed result
            rerank_result = RerankResponseResult(
                index=int(result["index"]),
                relevance_score=float(result["relevance_score"]),

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Look at the echoed result object in the message to identify which field is absent or renamed.
2. Upgrade (or pin) litellm to the release matching the Fireworks rerank schema you are targeting.
3. Fix test fixtures/mocks to include both 'index' (int) and 'relevance_score' (float) on every result item.

Example fix

# before (fixture with Cohere-style keys)
{"data": [{"index": 0, "score": 0.9}]}

# after
{"data": [{"index": 0, "relevance_score": 0.9}]}

def validate_rerank_fixture(results: list[dict]) -> bool:
    return all(
        isinstance(r, dict) and "index" in r and "relevance_score" in r
        for r in results
    )

def is_wellformed_rerank_result(result: object) -> bool:
    return (
        isinstance(result, dict)
        and isinstance(result.get("index"), int)
        and isinstance(result.get("relevance_score"), (int, float))
    )

try:
    litellm.rerank(model="fireworks_ai/...", query=q, documents=docs)
except ValueError as e:
    if "Missing required fields" in str(e):
        logging.error("Malformed rerank item from provider: %s", e)
        raise RuntimeError("Fireworks rerank schema drift detected") from e
    raise

When it happens

Trigger: A Fireworks (or mocked) response whose data/results entries omit 'index' or 'relevance_score' — e.g. fields renamed to 'score'/'rank', null entries, or a partially truncated response body.

Common situations: Fireworks ships a schema tweak; a gateway re-serializes and drops fields; test fixtures hand-write results with Cohere-style keys ('relevance_score' vs 'score') so the per-item validation fails.

Related errors

• No results found in the response={response}
• query is required for Fireworks AI rerank
• documents is required for Fireworks AI rerank
• No results found in the response={raw_response_json}
• query is required for DashScope rerank

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/b03f872eb6dd442f. Report an issue: GitHub.