{"record":{"id":"cb7e4cf2c1050a9a","repo":"headroomlabs-ai/headroom","slug":"huggingface-datasets-required","errorCode":null,"errorMessage":"HuggingFace datasets required","messagePattern":"HuggingFace datasets required","errorType":"exception","errorClass":"ImportError","httpStatus":null,"severity":"error","filePath":"headroom/evals/html_oss_benchmarks.py","lineNumber":279,"sourceCode":") -> QAAccuracyResult:\n    \"\"\"Evaluate whether HTML extraction preserves QA accuracy.\n\n    This test verifies that LLMs can answer questions equally well\n    (or better) from extracted content vs original HTML.\n\n    Args:\n        answer_fn: Function(context, question) -> answer string\n        extractor: HTMLExtractor instance\n        max_questions: Number of questions to evaluate\n        dataset_name: Which dataset to use (\"squad\" or \"hotpotqa\")\n\n    Returns:\n        QAAccuracyResult showing whether accuracy is preserved\n    \"\"\"\n    try:\n        from datasets import load_dataset\n    except ImportError:\n        raise ImportError(\"HuggingFace datasets required\") from None\n\n    if extractor is None:\n        from headroom.transforms.html_extractor import HTMLExtractor\n\n        extractor = HTMLExtractor()\n\n    # Load QA dataset\n    logger.info(f\"Loading {dataset_name} dataset...\")\n\n    if dataset_name == \"squad\":\n        dataset = load_dataset(\"rajpurkar/squad_v2\", split=\"validation\")\n    elif dataset_name == \"hotpotqa\":\n        dataset = load_dataset(\"hotpotqa/hotpot_qa\", \"fullwiki\", split=\"validation\")\n    else:\n        raise ValueError(f\"Unknown dataset: {dataset_name}\")\n\n    # Select subset\n    samples = dataset.select(range(min(max_questions, len(dataset))))","sourceCodeStart":261,"sourceCodeEnd":297,"githubUrl":"https://github.com/headroomlabs-ai/headroom/blob/322425c43bffde1ed0b64fecf3cf5951565dd82b/headroom/evals/html_oss_benchmarks.py#L261-L297","documentation":"Error \"HuggingFace datasets required\" thrown in headroomlabs-ai/headroom.","triggerScenarios":"Raised when an HTML OSS benchmark requires the HuggingFace `datasets` library and it is missing from the environment.","commonSituations":"See trigger scenarios.","solutions":["Install the datasets package: pip install datasets","Or install the evals extra: pip install headroom-ai[evals]"],"exampleFix":null,"handlingStrategy":null,"validationCode":null,"typeGuard":null,"tryCatchPattern":null,"preventionTips":[],"tags":[],"backgroundTag":null,"analyzedSha":"322425c43bffde1ed0b64fecf3cf5951565dd82b","analyzedAt":"2026-08-15T01:03:05.481Z","schemaVersion":2},"datasetVersion":"2026-08-15T22:17:37.221Z"}