{"record":{"id":"bc4e742459346df3","repo":"headroomlabs-ai/headroom","slug":"sentence-transformers-required-for-semantic-simila","errorCode":null,"errorMessage":"sentence-transformers required for semantic similarity. Install with: pip install sentence-transformers","messagePattern":"sentence-transformers required for semantic similarity\\. Install with: pip install sentence-transformers","errorType":"exception","errorClass":"ImportError","httpStatus":null,"severity":"error","filePath":"headroom/evals/metrics.py","lineNumber":179,"sourceCode":"    response_b: str,\n    model_name: str | None = None,\n) -> float:\n    \"\"\"Compute semantic similarity using sentence embeddings.\n\n    Requires sentence-transformers package.\n\n    Args:\n        response_a: First response\n        response_b: Second response\n        model_name: Sentence transformer model to use. Uses config default if None.\n\n    Returns:\n        Cosine similarity between embeddings (0.0 to 1.0)\n    \"\"\"\n    try:\n        import numpy as np\n    except ImportError as e:\n        raise ImportError(\n            \"sentence-transformers required for semantic similarity. \"\n            \"Install with: pip install sentence-transformers\"\n        ) from e\n\n    # Use centralized registry for shared model instances\n    from headroom.models.ml_models import MLModelRegistry\n\n    model = MLModelRegistry.get_sentence_transformer(model_name)\n\n    embeddings = model.encode([response_a, response_b])\n    embedding_a, embedding_b = embeddings[0], embeddings[1]\n\n    # Cosine similarity\n    dot_product = np.dot(embedding_a, embedding_b)\n    norm_a = np.linalg.norm(embedding_a)\n    norm_b = np.linalg.norm(embedding_b)\n\n    if norm_a == 0 or norm_b == 0:","sourceCodeStart":161,"sourceCodeEnd":197,"githubUrl":"https://github.com/headroomlabs-ai/headroom/blob/322425c43bffde1ed0b64fecf3cf5951565dd82b/headroom/evals/metrics.py#L161-L197","documentation":"Error \"sentence-transformers required for semantic similarity. Install with: pip install sentence-transformers\" thrown in headroomlabs-ai/headroom.","triggerScenarios":"Raised when a semantic-similarity eval metric is requested but the `sentence-transformers` package is not installed.","commonSituations":"See trigger scenarios.","solutions":["Install sentence-transformers: pip install sentence-transformers","Or install the relevance/evals extra that pulls it in","If install fails on your platform, use a non-semantic similarity metric instead"],"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"}