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

Raised by the Baidu vector store config's strict extra-fields validator. Only keys matching declared model fields are accepted; anything else aborts validation with a message listing both the offending keys and the full allowed set. This is a closed-schema guard against typo'd or unsupported options.

Source

Thrown at mem0/configs/vector_stores/baidu.py:22


class BaiduDBConfig(BaseModel):
    endpoint: str = Field("http://localhost:8287", description="Endpoint URL for Baidu VectorDB")
    account: str = Field("root", description="Account for Baidu VectorDB")
    api_key: str = Field(None, description="API Key for Baidu VectorDB")
    database_name: str = Field("mem0", description="Name of the database")
    table_name: str = Field("mem0", description="Name of the table")
    embedding_model_dims: int = Field(1536, description="Dimensions of the embedding model")
    metric_type: str = Field("L2", description="Metric type for similarity search")

    @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 key(s) named in the error
Cross-check remaining keys against the allowed-fields list included in the error text
Keep provider configs in separate dicts per provider rather than one shared dict passed everywhere
After upgrading mem0, re-validate all vector store configs in a smoke test

Example fix

# before
BaiduConfig(api_key="k", database_name="mem0", table_name="mem0", replica_count=3)

# after
BaiduConfig(api_key="k", database_name="mem0", table_name="mem0")

Defensive patterns

Strategy: validation

Validate before calling

from mem0.configs.vector_stores.baidu import BaiduConfig
def prune_baidu_extra(cfg: dict) -> dict:
    extra = set(cfg) - set(BaiduConfig.model_fields)
    if extra:
        raise RuntimeError(f"Unexpected baidu keys: {sorted(extra)}")
    return cfg

Type guard

def baidu_keys_valid(cfg: dict) -> bool:
    return not (set(cfg) - set(BaiduConfig.model_fields))

Try / catch

from pydantic import ValidationError
try:
    BaiduConfig(**cfg)
except ValidationError as e:
    if "Extra fields not allowed" in str(e):
        # fix keys per the allowed list in the message
        ...

Prevention

Write provider-specific config dicts, never reuse another provider's
Check the allowed-fields list printed in the error before retrying
Pin mem0 version and store configs alongside the pin

When it happens

Trigger: Instantiating BaiduConfig with any key not in its declared fields (e.g. an unexpected 'region', 'timeout', or a field belonging to another vector store provider).

Common situations: Porting a config from another provider (qdrant, milvus) into the baidu section; using an option that was renamed or removed in a mem0 upgrade; hand-writing config dicts from memory instead of docs.

Related errors

AI-assisted analysis of mem0ai/mem0@001c235229 (2026-08-15). Data as JSON: /api/errors/7f6ed5d309ab2677. Report an issue: GitHub.