mem0ai/mem0 · error · ValueError

Zero Entropy API key is required. Set ZERO_ENTROPY_API_KEY e

Error message

Zero Entropy API key is required. Set ZERO_ENTROPY_API_KEY environment variable or pass api_key in config.

What it means

ZeroEntropyReranker requires an API key via config.api_key or the ZERO_ENTROPY_API_KEY environment variable; if both are empty it raises ValueError at construction. (Note the dead else-branch in the source: by that point the key is guaranteed non-None, so the key always flows into ZeroEntropy(api_key=...).) The failure is immediate and local — no API call is attempted.

Source

Thrown at mem0/reranker/zero_entropy_reranker.py:32

class ZeroEntropyReranker(BaseReranker):
    """Zero Entropy-based reranker implementation."""
    
    def __init__(self, config):
        """
        Initialize Zero Entropy reranker.
        
        Args:
            config: ZeroEntropyRerankerConfig object with configuration parameters
        """
        if not ZERO_ENTROPY_AVAILABLE:
            raise ImportError("zeroentropy package is required for ZeroEntropyReranker. Install with: pip install zeroentropy")
        
        self.config = config
        self.api_key = config.api_key or os.getenv("ZERO_ENTROPY_API_KEY")
        if not self.api_key:
            raise ValueError("Zero Entropy API key is required. Set ZERO_ENTROPY_API_KEY environment variable or pass api_key in config.")
            
        self.model = config.model or "zerank-1"
        
        # Initialize Zero Entropy client
        if self.api_key:
            self.client = ZeroEntropy(api_key=self.api_key)
        else:
            self.client = ZeroEntropy()  # Will use ZERO_ENTROPY_API_KEY from environment
        
    def rerank(self, query: str, documents: List[Dict[str, Any]], top_k: int = None) -> List[Dict[str, Any]]:
        """
        Rerank documents using Zero Entropy's rerank API.
        
        Args:
            query: The search query
            documents: List of documents to rerank
            top_k: Number of top documents to return
            

View on GitHub (pinned to 001c235229)

Solutions

1. Set ZERO_ENTROPY_API_KEY in the runtime environment or pass api_key in the reranker config
2. Verify inside the process: assert os.getenv('ZERO_ENTROPY_API_KEY') before constructing Memory
3. Store the key in a secret manager and inject at deploy; never hardcode it

Example fix

# before
config = {"reranker": {"provider": "zeroentropy", "config": {"model": "zerank-1"}}}
# ValueError: key required

# after
import os
key = os.environ["ZERO_ENTROPY_API_KEY"]
config = {"reranker": {"provider": "zeroentropy", "config": {"model": "zerank-1", "api_key": key}}}

import os
key = os.getenv("ZERO_ENTROPY_API_KEY")
if not key:
    raise RuntimeError("ZERO_ENTROPY_API_KEY not set; refusing to build zeroentropy reranker")

When it happens

Trigger: Configuring the zeroentropy reranker with no api_key and no ZERO_ENTROPY_API_KEY in the process environment; the env var set in a local .env but not loaded in Docker/systemd; api_key passed as empty string while the env var is also absent.

Common situations: Deploying with secret managers where the env var name changed; local-to-prod config drift; CI lacking secrets for optional integrations.

Related errors

• Zero Entropy API key is required. Set ZERO_ENTROPY_API_KEY e
• Cohere API key is required. Set COHERE_API_KEY environment v
• Cohere API key is required. Set COHERE_API_KEY environment v
• Pinecone API key required: pass apiKey or set PINECONE_API_K
• Mem0 API key is required

AI-assisted analysis of mem0ai/mem0@001c235229 (2026-08-15). Data as JSON: /api/errors/9f84bd2b12d5174b. Report an issue: GitHub.