openai/openai-python · error · ValueError

Expected a non-empty value for `output_item_id` but received

Error message

Expected a non-empty value for `output_item_id` but received {output_item_id!r}

What it means

The sync EvalRunOutputItem.retrieve() method requires output_item_id to be non-empty since it forms the final path segment of /evals/{eval_id}/runs/{run_id}/output_items/{output_item_id}. The SDK raises ValueError client-side to avoid issuing a request with a malformed identifier.

Source

Thrown at src/openai/resources/evals/runs/output_items.py:76

    ) -> OutputItemRetrieveResponse:
        """
        Get an evaluation run output item by ID.

        Args:
          extra_headers: Send extra headers

          extra_query: Add additional query parameters to the request

          extra_body: Add additional JSON properties to the request

          timeout: Override the client-level default timeout for this request, in seconds
        """
        if not eval_id:
            raise ValueError(f"Expected a non-empty value for `eval_id` but received {eval_id!r}")
        if not run_id:
            raise ValueError(f"Expected a non-empty value for `run_id` but received {run_id!r}")
        if not output_item_id:
            raise ValueError(f"Expected a non-empty value for `output_item_id` but received {output_item_id!r}")
        return self._get(
            path_template(
                "/evals/{eval_id}/runs/{run_id}/output_items/{output_item_id}",
                eval_id=eval_id,
                run_id=run_id,
                output_item_id=output_item_id,
            ),
            options=make_request_options(
                extra_headers=extra_headers,
                extra_query=extra_query,
                extra_body=extra_body,
                timeout=timeout,
                security={"bearer_auth": True},
            ),
            cast_to=OutputItemRetrieveResponse,
        )

    def list(

View on GitHub (pinned to 9917c6e28e)

Solutions

  1. Confirm you are reading the id field from the output item object you obtained from output_items.list().
  2. If iterating, skip entries whose id is falsy.
  3. Add a pre-call guard for output_item_id.
  4. Check for attribute typos on the item object (use the documented field name).

Example fix

# before
item = client.evals.runs.output_items.retrieve(eval_id, run_id, output_item_id)

# after
if not output_item_id:
    continue  # or raise with context
item = client.evals.runs.output_items.retrieve(eval_id, run_id, output_item_id)
Defensive patterns

Strategy: validation

Validate before calling

if not isinstance(output_item_id, str) or not output_item_id.strip():
    raise ValueError(f"output_item_id must be a non-empty string, got {output_item_id!r}")

Type guard

def is_valid_output_item_id(output_item_id: object) -> bool:
    return isinstance(output_item_id, str) and bool(output_item_id.strip())

Try / catch

try:
    item = client.evals.runs.output_items.retrieve(eval_id=eval_id, run_id=run_id, output_item_id=output_item_id)
except ValueError as e:
    if 'output_item_id' in str(e):
        continue  # in a loop over items
    raise

Prevention

When it happens

Trigger: Calling client.evals.runs.output_items.retrieve() with output_item_id='' or None. Typically happens when looping over output items from a listing and one entry has an empty/missing id.

Common situations: Iterating results where some records lack ids, referencing the wrong attribute name (e.g. item.ref instead of item.id), or passing an index/None by mistake.

Related errors

AI-assisted analysis of openai/openai-python@9917c6e28e (2026-08-28). Data as JSON: /api/errors/2bf9dbc5fca5ac61. Report an issue: GitHub.