microsoft/semantic-kernel · error · VectorStoreOperationException

Field ' ' not in data model (storage property names are…

Error message

Field '{node.id}' not in data model (storage property names are used).

What it means

When the MongoDB filter lambda parser encounters a bare Name node (e.g. using a variable or field reference as `field` instead of `x.field`), it validates that the name exists in the data model's `storage_names`. This VectorStoreOperationException fires when the name does not match any storage property. This guards against referencing undefined fields or variables that are not part of the data model.

Solutions

  1. Ensure every field reference in the lambda uses attribute-access form `x.field_name` with the lambda parameter prefix.
  2. Verify the referenced name matches a storage name in the VectorStoreRecordDefinition.
  3. Use constants via ast.Constant (literal values) rather than bare variable names inside the lambda.

Example fix

// before (bare name 'status' instead of attribute access)
collection.search(filter=lambda x: status == "active")
// after
collection.search(filter=lambda x: x.status == "active")
Defensive patterns

Strategy: validation

Validate before calling

def validate_filter_names(func, storage_names: set[str]):
    import ast, inspect
    tree = ast.parse(inspect.getsource(func))
    for node in ast.walk(tree):
        if isinstance(node, ast.Name) and node.id not in storage_names:
            # bare name not in data model — likely a missing 'x.' prefix
            raise ValueError(f"Name '{node.id}' not in data model; did you forget the lambda parameter prefix?")

Try / catch

try:
    results = await collection.search(filter=my_lambda)
except VectorStoreOperationException as e:
    if "not in data model" in str(e):
        # prefix all field references with the lambda parameter (e.g. x.field)
        ...

Prevention

When it happens

Trigger: The filter lambda references a bare name (not an attribute access) that is not in the data model storage names, for example `lambda x: my_field == 1` where `my_field` is neither a data model field nor prefixed with the lambda parameter.

Common situations: Developer forgets to prefix the field with the lambda parameter (e.g. writes `field` instead of `x.field`). Developer references a local variable or constant by name inside the lambda. Storage name differs from the referenced name.

Related errors

AI-assisted analysis of microsoft/semantic-kernel@c028a0c7dc (2026-08-13). Data as JSON: /api/errors/1b00a1fe0a0dceb4. Report an issue: GitHub.

Appendix: source

Thrown at python/semantic_kernel/connectors/mongodb.py:505

                raise NotImplementedError(f"Unsupported BoolOp: {type(op)}")
            case ast.UnaryOp():
                match node.op:
                    case ast.Not():
                        operand = self._lambda_parser(node.operand)
                        return {"$not": operand}
                    case ast.UAdd() | ast.USub() | ast.Invert():
                        raise NotImplementedError("Unary +, -, ~ are not supported in MongoDB filters.")
            case ast.Attribute():
                # Only allow attributes that are in the data model
                if node.attr not in self.definition.storage_names:
                    raise VectorStoreOperationException(
                        f"Field '{node.attr}' not in data model (storage property names are used)."
                    )
                return node.attr
            case ast.Name():
                # Only allow names that are in the data model
                if node.id not in self.definition.storage_names:
                    raise VectorStoreOperationException(
                        f"Field '{node.id}' not in data model (storage property names are used)."
                    )
                return node.id
            case ast.Constant():
                return node.value
        raise NotImplementedError(f"Unsupported AST node: {type(node)}")

    @override
    def _get_record_from_result(self, result: dict[str, Any]) -> dict[str, Any]:
        return result

    @override
    def _get_score_from_result(self, result: dict[str, Any]) -> float | None:
        return result.get(MONGODB_SCORE_FIELD)

    @override
    async def __aexit__(self, exc_type, exc_value, traceback) -> None:
        """Exit the context manager."""

View on GitHub (pinned to c028a0c7dc)