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

The Azure AI Search config model forbids unknown keys: any field in the input that is not a declared model field raises ValueError listing the offending names and the allowed set. This catches typos and stale options at config-parse time, before any Azure SDK call. use_compression gets its own more specific message first.

Source

Thrown at mem0/configs/vector_stores/azure_ai_search.py:41

    )

    @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

        # Check for use_compression to provide a helpful error
        if "use_compression" in extra_fields:
            raise ValueError(
                "The parameter 'use_compression' is no longer supported. "
                "Please use 'compression_type=\"scalar\"' instead of 'use_compression=True' "
                "or 'compression_type=None' instead of 'use_compression=False'."
            )

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

        # Validate compression_type values
        if "compression_type" in values and values["compression_type"] is not None:
            valid_types = ["scalar", "binary"]
            if values["compression_type"].lower() not in valid_types:
                raise ValueError(
                    f"Invalid compression_type: {values['compression_type']}. "
                    f"Must be one of: {', '.join(valid_types)}, or None"
                )

        return values

    model_config = ConfigDict(arbitrary_types_allowed=True)

View on GitHub (pinned to 001c235229)

Solutions

1. Read the error message — it enumerates both the bad fields and the exact allowed field list; fix accordingly
2. Compare your config against mem0/configs/vector_stores/azure_ai_search.py model fields for your installed version
3. Remove keys inherited from examples for other providers (qdrant, chroma, etc.)

Example fix

# before
"config": {"service_name": S, "api_key": K, "embedding_dim": 1536}

# after
"config": {"service_name": S, "api_key": K, "embedding_dimensions": 1536}

from mem0.configs.vector_stores.azure_ai_search import AzureAISearchConfig

allowed = set(AzureAISearchConfig.model_fields)
unknown = set(my_config) - allowed
if unknown:
    raise ConfigError(f"unknown azure_ai_search fields: {sorted(unknown)}; allowed: {sorted(allowed)}")

def azure_cfg_keys_valid(cfg: dict) -> bool:
    from mem0.configs.vector_stores.azure_ai_search import AzureAISearchConfig
    return not (set(cfg) - set(AzureAISearchConfig.model_fields))

try:
    Memory.from_config(config)
except ValueError as e:
    if "Extra fields not allowed" in str(e):
        raise ConfigError(f"fix vector store config: {e}") from e
    raise

When it happens

Trigger: Passing misspelled or outdated keys in vector_store.config for provider azure_ai_search, e.g. 'service_name' vs current name, 'index_name' vs 'collection_name', or keys belonging to other providers like 'dim' or 'embedding_dimension'.

Common situations: Copying config snippets between vector store providers; upgrading mem0ai when field names changed; hand-written YAML with typos; LLM-generated configs with hallucinated field names.

Related errors

• Invalid compression_type: {values['compression_type']}. Must
• Baidu vector store requires a non-empty '${name}' config val
• The parameter 'use_compression' is no longer supported. Plea
• Invalid collection_name: {v!r}. Must start with a letter or
• Unsupported VectorStore provider: {provider_name}

AI-assisted analysis of mem0ai/mem0@001c235229 (2026-08-15). Data as JSON: /api/errors/7a15b90ede62faed. Report an issue: GitHub.