mem0ai/mem0 · error · ImportError

sentence-transformers package is required for SentenceTransf

Error message

sentence-transformers package is required for SentenceTransformerReranker. Install with: pip install sentence-transformers

What it means

SentenceTransformerReranker raises ImportError when sentence-transformers is missing (guarded by SENTENCE_TRANSFORMERS_AVAILABLE). Like the HuggingFace reranker it runs models locally and needs its own optional package, distinct from plain transformers. Construction fails at Memory.from_config() time with the exact pip command in the message.

Source

Thrown at mem0/reranker/sentence_transformer_reranker.py:32

    SENTENCE_TRANSFORMERS_AVAILABLE = True
except ImportError:
    SENTENCE_TRANSFORMERS_AVAILABLE = False

logger = logging.getLogger(__name__)


class SentenceTransformerReranker(BaseReranker):
    """Sentence Transformer based reranker implementation."""

    def __init__(self, config: Union[BaseRerankerConfig, SentenceTransformerRerankerConfig, Dict]):
        """
        Initialize Sentence Transformer reranker.

        Args:
            config: Configuration object with reranker parameters
        """
        if not SENTENCE_TRANSFORMERS_AVAILABLE:
            raise ImportError("sentence-transformers package is required for SentenceTransformerReranker. Install with: pip install sentence-transformers")

        # Convert to SentenceTransformerRerankerConfig if needed
        if isinstance(config, dict):
            config = SentenceTransformerRerankerConfig(**config)
        elif isinstance(config, BaseRerankerConfig) and not isinstance(config, SentenceTransformerRerankerConfig):
            # Convert BaseRerankerConfig to SentenceTransformerRerankerConfig with defaults
            config = SentenceTransformerRerankerConfig(
                provider=getattr(config, 'provider', 'sentence_transformer'),
                model=getattr(config, 'model', 'cross-encoder/ms-marco-MiniLM-L-6-v2'),
                api_key=getattr(config, 'api_key', None),
                top_k=getattr(config, 'top_k', None),
                device=None,  # Will auto-detect
                batch_size=32,  # Default
                show_progress_bar=False,  # Default
            )

        self.config = config
        self.model = CrossEncoder(self.config.model, device=self.config.device)

View on GitHub (pinned to 001c235229)

Solutions

1. pip install sentence-transformers (it will pull torch if missing)
2. Or use a lighter/hosted reranker provider if the dependency is too heavy
3. Verify in the runtime interpreter: python -c "import sentence_transformers"

Example fix

# before
config = {"reranker": {"provider": "sentence_transformer", "config": {"model": "cross-encoder/ms-marco-MiniLM-L-6-v2"}}}
# ImportError

# after
# pip install sentence-transformers
config = {"reranker": {"provider": "sentence_transformer", "config": {"model": "cross-encoder/ms-marco-MiniLM-L-6-v2", "device": "cpu"}}}

import importlib.util
if importlib.util.find_spec("sentence_transformers") is None:
    raise RuntimeError("install sentence-transformers before enabling this reranker")

try:
    reranker = SentenceTransformerReranker(cfg)
except ImportError:
    reranker = None  # or fall back to another provider

When it happens

Trigger: Configuring reranker={'provider':'sentence_transformer', ...} without `pip install sentence-transformers`; environments that installed transformers+torch but not the sentence-transformers package (they are separate); minimal deployment images.

Common situations: Assuming transformers covers sentence-transformers (it does not — it is an extra package); moving from API-based rerankers to local cross-encoders to cut costs; dependency pruning scripts removing 'unused' packages.

Related errors

• cohere package is required for CohereReranker. Install with:
• transformers package is required for HuggingFaceReranker. In
• zeroentropy package is required for ZeroEntropyReranker. Ins
• The 'chromadb' library is required. Please install it using
• langchain-core is required to pass a custom LLM to procedura

AI-assisted analysis of mem0ai/mem0@001c235229 (2026-08-15). Data as JSON: /api/errors/f56026b0d5ee9be7. Report an issue: GitHub.