mem0ai/mem0 · error · ValueError

Extra fields not allowed: {', '.join(extra_fields)}. Please

Error message

Extra fields not allowed: {', '.join(extra_fields)}. Please input only the following fields: {', '.join(allowed_fields)}

What it means

S3VectorsConfig's `before` model_validator rejects any configuration key that is not a declared field (the S3 Vectors options: bucket name/arn, vector store name/arn, region_name, distance metric, embedding_model_dims, etc.). The message enumerates both the rejected keys and the full allowed set, so the fix is mechanical.

Source

Thrown at mem0/configs/vector_stores/s3_vectors.py:23

class S3VectorsConfig(BaseModel):
    vector_bucket_name: str = Field(description="Name of the S3 Vector bucket")
    collection_name: str = Field("mem0", description="Name of the vector index")
    embedding_model_dims: int = Field(1536, description="Dimension of the embedding vector")
    distance_metric: str = Field(
        "cosine",
        description="Distance metric for similarity search. Options: 'cosine', 'euclidean'",
    )
    region_name: Optional[str] = Field(None, description="AWS region for the S3 Vectors client")

    @model_validator(mode="before")
    @classmethod
    def validate_extra_fields(cls, values: Dict[str, Any]) -> Dict[str, Any]:
        allowed_fields = set(cls.model_fields.keys())
        input_fields = set(values.keys())
        extra_fields = input_fields - allowed_fields
        if extra_fields:
            raise ValueError(
                f"Extra fields not allowed: {', '.join(extra_fields)}. Please input only the following fields: {', '.join(allowed_fields)}"
            )
        return values

    model_config = ConfigDict(arbitrary_types_allowed=True)

View on GitHub (pinned to 001c235229)

Solutions

Delete the extra keys named in the error so the dict only uses fields from the allowed list in the message
Supply AWS credentials via environment variables (AWS_ACCESS_KEY_ID etc.), an IAM role, or ~/.aws/credentials instead of the config dict
Check the S3VectorsConfig field declarations for the exact accepted names (e.g. region_name for the AWS region)

Example fix

# before
config = {"bucket_name": "my-bucket", "aws_access_key_id": "...", "aws_secret_access_key": "..."}

# after
config = {"bucket_name": "my-bucket", "region_name": "us-east-1"}  # credentials from env/IAM

Defensive patterns

Strategy: validation

Validate before calling

from mem0.configs.vector_stores.s3_vectors import S3VectorsConfig
extra = set(cfg) - set(S3VectorsConfig.model_fields)
assert not extra, f"extra keys: {extra}"

Prevention

Never put AWS credentials in the vector store config; use env vars or IAM roles
Validate config dicts against the Pydantic model before passing them to Memory

When it happens

Trigger: Calling Memory with vector_store={'provider': 's3_vectors', 'config': {...}} where the config dict contains keys not declared on S3VectorsConfig — typical offenders are AWS credential keys (aws_access_key_id, aws_secret_access_key), profile, or keys copied from other vector store configs.

Common situations: Assuming AWS credentials belong in the vector store config (they belong in the environment, IAM roles, or the boto3 client passed separately); copying an example config for another provider; using a field name from an older mem0 release.

Related errors

AI-assisted analysis of mem0ai/mem0@001c235229 (2026-08-15). Data as JSON: /api/errors/cfefacaf61756734. Report an issue: GitHub.