OpenBMB/ChatDev · error · ImportError

sentence-transformers is required for LocalEmbedding

Error message

sentence-transformers is required for LocalEmbedding

What it means

LocalEmbedding depends on the sentence-transformers package to load local models. If `from sentence_transformers import SentenceTransformer` fails with ImportError, __init__ converts it into this explicit ImportError telling you to install sentence-transformers.

Source

Thrown at runtime/node/agent/memory/embedding.py:178

            # Default to the first chunk
            return chunk_embeddings[0]

class LocalEmbedding(EmbeddingBase):
    def __init__(self, embedding_config: EmbeddingConfig):
        super().__init__(embedding_config)
        self.model_path = embedding_config.params.get('model_path')
        self.device = embedding_config.params.get('device', 'cpu')
        self._fallback_dim = 768  # Default; updated after first successful call
        
        if not self.model_path:
            raise ValueError("LocalEmbedding requires model_path parameter")
        
        # Load the local embedding model (e.g., sentence-transformers)
        try:
            from sentence_transformers import SentenceTransformer
            self.model = SentenceTransformer(self.model_path, device=self.device)
        except ImportError:
            raise ImportError("sentence-transformers is required for LocalEmbedding")

    def get_embedding(self, text):
        # Preprocess text before encoding
        processed_text = self._preprocess_text(text)
        
        if not processed_text:
            return [0.0] * self._fallback_dim
        
        try:
            embedding = self.model.encode(processed_text, convert_to_tensor=False)
            result = embedding.tolist()
            self._fallback_dim = len(result)
            return result
        except Exception as e:
            logger.error(f"Error getting local embedding: {e}")
            return [0.0] * self._fallback_dim

View on GitHub (pinned to 4fb2db0ea9)

Solutions

1. pip install sentence-transformers
2. Install the package's embedding extras if provided (e.g. pip install 'package[local-embedding]')
3. Confirm you're in the same interpreter/venv the app runs in (pip list | grep sentence)

Example fix

# shell
# before: ImportError at agent construction
pip install sentence-transformers

if embedding_config.provider == 'local':
    import importlib.util
    if importlib.util.find_spec('sentence_transformers') is None:
        raise ConfigError('install sentence-transformers for local embeddings')

When it happens

Trigger: provider='local' with model_path set, but sentence-transformers (and its torch dependency) not installed in the current environment.

Common situations: Fresh environments with only the base runtime installed; missing the extras (e.g. pip install 'pkg[local-embedding]'); wrong virtualenv/conda env activated; torch present but sentence-transformers missing.

Related errors

• mem0ai is required for Mem0Memory. Install it with: pip inst
• Unsupported embedding model: {model}
• LocalEmbedding requires model_path parameter

AI-assisted analysis of OpenBMB/ChatDev@4fb2db0ea9 (2026-08-27). Data as JSON: /api/errors/b413e2e563ec7eb6. Report an issue: GitHub.