dyff-schema 0.7.2__py3-none-any.whl → 0.9.0__py3-none-any.whl

dyff/schema/errors.py

@@ -0,0 +1,51 @@
+# SPDX-FileCopyrightText: 2024 UL Research Institutes
+# SPDX-License-Identifier: Apache-2.0
+
+
+from typing import NamedTuple, Optional
+
+
+class HTTPResponseStatus(NamedTuple):
+    status_code: int
+    description: str
+
+
+HTTP_400_BAD_REQUEST = HTTPResponseStatus(400, "Bad Request")
+HTTP_500_INTERNAL_SERVER_ERROR = HTTPResponseStatus(500, "Internal Server Error")
+
+
+class DyffError(Exception):
+    """Base class for Errors originating from the Dyff Platform."""
+
+    def __init__(self, message, *, http_status: Optional[HTTPResponseStatus] = None):
+        self.message = message
+        self.http_status = http_status
+
+
+class ClientError(DyffError):
+    """The error was caused by the client using an API incorrectly."""
+
+    def __init__(
+        self, message, *, http_status: HTTPResponseStatus = HTTP_400_BAD_REQUEST
+    ):
+        if not (400 <= http_status.status_code <= 499):
+            raise AssertionError(
+                f"ClientError should map to a 4xx HTTP status; got {http_status}"
+            )
+        super().__init__(message, http_status=http_status)
+
+
+class PlatformError(DyffError):
+    """The error was caused by an internal problem with the platform."""
+
+    def __init__(
+        self,
+        message,
+        *,
+        http_status: HTTPResponseStatus = HTTP_500_INTERNAL_SERVER_ERROR,
+    ):
+        if not (500 <= http_status.status_code <= 599):
+            raise AssertionError(
+                f"PlatformError should map to a 5xx HTTP status; got {http_status}"
+            )
+        super().__init__(message, http_status=http_status)

dyff/schema/v0/r1/base.py

@@ -1,8 +1,11 @@
 # SPDX-FileCopyrightText: 2024 UL Research Institutes
 # SPDX-License-Identifier: Apache-2.0
 
-from datetime import datetime
-from typing import Any, Generic, NamedTuple, Optional, Type, TypeVar
+from __future__ import annotations
+
+import json
+from datetime import datetime, timezone
+from typing import Any, Generic, Literal, NamedTuple, Optional, Type, TypeVar
 
 import pydantic
 
@@ -555,8 +558,12 @@ def list_(
         return pydantic.conlist(item_type, min_items=list_size, max_items=list_size)
 
 
-class DyffSchemaBaseModel(pydantic.BaseModel):
-    """Base class for pydantic models that used for defining data schemas.
+# mypy gets confused because 'dict' is the name of a method in DyffDefaultSerializers
+_ModelAsDict = dict[str, Any]
+
+
+class DyffDefaultSerializers(pydantic.BaseModel):
+    """This must be the base class for *all pydantic models* in the Dyff schema.
 
     Overrides serialization functions to serialize by alias, so that "round-trip"
     serialization is the default for fields with aliases. We prefer aliases because we
@@ -564,24 +571,66 @@ class DyffSchemaBaseModel(pydantic.BaseModel):
     Python reserved words like 'bytes' as field names.
     """
 
+    def dict(self, *, by_alias: bool = True, **kwargs) -> _ModelAsDict:
+        return super().dict(by_alias=by_alias, **kwargs)
+
+    def json(self, *, by_alias: bool = True, **kwargs) -> str:
+        return super().json(by_alias=by_alias, **kwargs)
+
+    def model_dump(
+        self,
+        *,
+        mode: Literal["python", "json"] = "python",
+        by_alias: bool = True,
+        **kwargs,
+    ) -> _ModelAsDict:
+        """Encode the object as a dict containing only JSON datatypes.
+
+        .. deprecated::
+
+            FIXME: This emulates a Pydantic 2 feature, but the mode="json"
+            option can only be implemented in an inefficient way. Remove when
+            we convert to Pydantic 2. See: DYFF-223
+        """
+        if mode == "python":
+            return self.dict(by_alias=by_alias, **kwargs)
+        else:
+            return json.loads(self.json(by_alias=by_alias, **kwargs))
+
+
+# Note: I *really* wanted to require datetimes to have timezones, like in
+# DyffRequestDefaultValidators, but some existing objects in the Auth database
+# don't have timezones set currently for historical reasons. It's actually
+# better if all datetimes in the system are UTC, so that their JSON
+# representations (i.e., isoformat strings) are well-ordered.
+class DyffSchemaBaseModel(DyffDefaultSerializers):
+    """This should be the base class for *almost all* non-request models in the Dyff
+    schema. Models that do not inherit from this class *must* still inherit from
+    DyffDefaultSerializers.
+
+    Adds a root validator to ensure that all datetime fields are represented in the UTC
+    timezone. This is necessary to avoid errors when comparing "naive" and "aware"
+    datetimes. Using the UTC timezone everywhere ensures that JSON representations of
+    datetimes are well-ordered.
+    """
+
     @pydantic.root_validator
-    def _require_datetime_timezone_aware(cls, values):
+    def _ensure_datetime_timezone_utc(cls, values):
+        update = {}
         for k, v in values.items():
             if isinstance(v, datetime):
                 if v.tzinfo is None:
-                    raise ValueError(f"{cls.__qualname__}.{k}: timezone not set")
+                    update[k] = v.replace(tzinfo=timezone.utc)
+                elif v.tzinfo != timezone.utc:
+                    update[k] = v.astimezone(timezone.utc)
+        values.update(update)
         return values
 
-    def dict(self, *, by_alias: bool = True, **kwargs) -> dict[str, Any]:
-        return super().dict(by_alias=by_alias, **kwargs)
-
-    def json(self, *, by_alias: bool = True, **kwargs) -> str:
-        return super().json(by_alias=by_alias, **kwargs)
-
 
 __all__ = [
     "DTYPE",
     "DType",
+    "DyffDefaultSerializers",
     "DyffSchemaBaseModel",
     "FixedWidthFloat",
     "FixedWidthInt",

dyff/schema/v0/r1/platform.py

@@ -18,7 +18,7 @@ We use the following naming convention:
 # mypy: disable-error-code="import-untyped"
 import abc
 import enum
-from datetime import datetime, timezone
+from datetime import datetime
 from enum import Enum
 from typing import Any, Literal, NamedTuple, Optional, Type, Union
 
@@ -67,7 +67,7 @@ def _dns_domain_regex():
     Note that its maximum length is 253 characters, but we can't enforce this in the
     regex.
     """
-    return f"{_dns_label_regex()}(\.{_dns_label_regex()})*"
+    return rf"{_dns_label_regex()}(\.{_dns_label_regex()})*"
 
 
 def _k8s_domain_maxlen():
@@ -96,7 +96,7 @@ def _k8s_label_key_regex():
         * my-multi_segment.key
         * dyff.io/reserved-key
     """
-    return f"^({_dns_domain_regex()}/)?{_dns_label_regex()}$"
+    return rf"^({_dns_domain_regex()}/)?{_dns_label_regex()}$"
 
 
 def _k8s_label_key_maxlen():
@@ -126,7 +126,7 @@ def _k8s_label_value_regex():
 
     See: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/
     """
-    return f"^({_k8s_label_regex()})?$"
+    return rf"^({_k8s_label_regex()})?$"
 
 
 def _k8s_label_value_maxlen():
@@ -532,10 +532,7 @@ class AccessGrant(DyffSchemaBaseModel):
     )
 
 
-# FIXME: We can't derive from DyffSchemaBaseModel right now because existing
-# APIKeys don't have a timezone set for their datetime members.
-# See: DYFF-406
-class APIKey(pydantic.BaseModel):
+class APIKey(DyffSchemaBaseModel):
     """A description of a set of permissions granted to a single subject (either an
     account or a workload).
 
@@ -564,21 +561,26 @@ class APIKey(pydantic.BaseModel):
         default_factory=list, description="AccessGrants associated with the APIKey"
     )
 
-    @pydantic.root_validator
-    def _ensure_datetime_timezone_aware(cls, values):
-        update = {}
-        for k, v in values.items():
-            if isinstance(v, datetime):
-                if v.tzinfo is None:
-                    update[k] = v.replace(tzinfo=timezone.utc)
-        values.update(update)
-        return values
 
-    def dict(self, *, by_alias: bool = True, **kwargs) -> dict[str, Any]:
-        return super().dict(by_alias=by_alias, **kwargs)
+class Identity(DyffSchemaBaseModel):
+    """The identity of an Account according to one or more external identity
+    providers."""
 
-    def json(self, *, by_alias: bool = True, **kwargs) -> str:
-        return super().json(by_alias=by_alias, **kwargs)
+    google: Optional[str] = pydantic.Field(default=None)
+
+
+class Account(DyffSchemaBaseModel):
+    """An Account in the system.
+
+    All entities are owned by an Account.
+    """
+
+    name: str
+    identity: Identity = pydantic.Field(default_factory=Identity)
+    apiKeys: list[APIKey] = pydantic.Field(default_factory=list)
+    # --- Added by system
+    id: Optional[str] = None
+    creationTime: Optional[datetime] = None
 
 
 # ----------------------------------------------------------------------------
@@ -1860,6 +1862,7 @@ __all__ = [
     "Accelerator",
     "AcceleratorGPU",
     "AccessGrant",
+    "Account",
     "Analysis",
     "AnalysisArgument",
     "AnalysisBase",
@@ -1900,6 +1903,7 @@ __all__ = [
     "ForeignMethod",
     "ForeignModel",
     "Frameworks",
+    "Identity",
     "InferenceInterface",
     "InferenceService",
     "InferenceServiceBase",

dyff/schema/v0/r1/requests.py

@@ -12,13 +12,14 @@ resource will include the full dependency object as a sub-resource. The
 in response.
 """
 
+from __future__ import annotations
 
 from datetime import datetime
-from typing import Any, Optional, Union
+from typing import Optional, Union
 
 import pydantic
 
-from .base import DyffSchemaBaseModel
+from .base import DyffDefaultSerializers
 from .platform import (
     AnalysisBase,
     DatasetBase,
@@ -37,7 +38,28 @@ from .platform import (
 from .version import SchemaVersion
 
 
-class DyffEntityCreateRequest(SchemaVersion, DyffSchemaBaseModel):
+class DyffRequestDefaultValidators(DyffDefaultSerializers):
+    """This must be the base class for *all* request models in the Dyff schema.
+
+    Adds a root validator to ensure that all user-provided datetime fields have a
+    timezone set. Timezones will be converted to UTC once the data enters the platform,
+    but we allow requests to have non-UTC timezones for user convenience.
+    """
+
+    @pydantic.root_validator
+    def _require_datetime_timezone_aware(cls, values):
+        for k, v in values.items():
+            if isinstance(v, datetime):
+                if v.tzinfo is None:
+                    raise ValueError(f"{cls.__qualname__}.{k}: timezone not set")
+        return values
+
+
+class DyffRequestBase(SchemaVersion, DyffRequestDefaultValidators):
+    pass
+
+
+class DyffEntityCreateRequest(DyffRequestBase):
     account: str = pydantic.Field(description="Account that owns the entity")
 
 
@@ -52,7 +74,7 @@ class DatasetCreateRequest(DyffEntityCreateRequest, DatasetBase):
     pass
 
 
-class DocumentationEditRequest(SchemaVersion, DocumentationBase):
+class DocumentationEditRequest(DyffRequestBase, DocumentationBase):
     pass
 
 
@@ -66,7 +88,7 @@ class InferenceSessionCreateRequest(DyffEntityCreateRequest, InferenceSessionBas
     inferenceService: str = pydantic.Field(description="InferenceService ID")
 
 
-class InferenceSessionTokenCreateRequest(SchemaVersion, DyffSchemaBaseModel):
+class InferenceSessionTokenCreateRequest(DyffRequestBase):
     expires: Optional[datetime] = pydantic.Field(
         default=None,
         description="Expiration time of the token. Must be <= expiration time"
@@ -137,11 +159,11 @@ class ReportCreateRequest(DyffEntityCreateRequest, ReportBase):
     )
 
 
-class TagCreateRequest(SchemaVersion, TagBase):
+class TagCreateRequest(DyffRequestBase, TagBase):
     pass
 
 
-class LabelUpdateRequest(SchemaVersion, Labeled):
+class LabelUpdateRequest(DyffRequestBase, Labeled):
     pass
 
 
@@ -150,7 +172,15 @@ class LabelUpdateRequest(SchemaVersion, Labeled):
 # specify. I think it's not that important, because all of the query parameters
 # will always be optional. There could be a problem if the semantics of a
 # name change, but let's just not do that!
-class DyffEntityQueryRequest(DyffSchemaBaseModel):
+class DyffEntityQueryRequest(DyffRequestDefaultValidators):
+    query: Optional[str] = pydantic.Field(
+        default=None,
+        description="A JSON structure describing a query, encoded as a string."
+        " Valid keys are the same as the valid query keys for the corresponding"
+        " endpoint. Values can be scalars or lists. Lists are treated as"
+        " disjunctive queries (i.e., 'value $in list').",
+    )
+
     id: Optional[str] = pydantic.Field(default=None)
     account: Optional[str] = pydantic.Field(default=None)
     status: Optional[str] = pydantic.Field(default=None)
@@ -159,12 +189,6 @@ class DyffEntityQueryRequest(DyffSchemaBaseModel):
         default=None, description="Labels dict represented as a JSON string."
     )
 
-    def dict(self, exclude_unset=True, **kwargs) -> dict[str, Any]:
-        return super().dict(exclude_unset=exclude_unset, **kwargs)
-
-    def json(self, exclude_unset=True, **kwargs) -> Any:
-        return super().json(exclude_unset=exclude_unset, **kwargs)
-
 
 class _AnalysisProductQueryRequest(DyffEntityQueryRequest):
     method: Optional[str] = pydantic.Field(default=None)
@@ -173,7 +197,7 @@ class _AnalysisProductQueryRequest(DyffEntityQueryRequest):
     evaluation: Optional[str] = pydantic.Field(default=None)
     inferenceService: Optional[str] = pydantic.Field(default=None)
     model: Optional[str] = pydantic.Field(default=None)
-    inputsAnyOf: Optional[str] = pydantic.Field(default=None)
+    inputs: Optional[str] = pydantic.Field(default=None)
 
 
 class AuditQueryRequest(DyffEntityQueryRequest):
@@ -240,6 +264,8 @@ __all__ = [
     "AuditQueryRequest",
     "DyffEntityCreateRequest",
     "DyffEntityQueryRequest",
+    "DyffRequestBase",
+    "DyffRequestDefaultValidators",
     "DatasetCreateRequest",
     "DatasetQueryRequest",
     "DocumentationEditRequest",

{dyff_schema-0.7.2.dist-info → dyff_schema-0.9.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dyff-schema
-Version: 0.7.2
+Version: 0.9.0
 Summary: Data models for the Dyff AI auditing platform.
 Author-email: Digital Safety Research Institute <contact@dsri.org>
 License: Apache-2.0

{dyff_schema-0.7.2.dist-info → dyff_schema-0.9.0.dist-info}/RECORD

@@ -2,6 +2,7 @@ dyff/schema/__init__.py,sha256=JcpxaRHNYgLjJWLjVayLlqacb2GX49Pazpwb8m-BctM,1031
 dyff/schema/adapters.py,sha256=YMTHv_2VlLGFp-Kqwa6H51hjffHmk8gXjZilHysIF5Q,123
 dyff/schema/base.py,sha256=jvaNtsSZyFfsdUZTcY_U-yfLY5_GyrMxSXhON2R9XR0,119
 dyff/schema/copydoc.py,sha256=B4ZRpQmbFxi-3l9LCHvaJiVKb9VxADgC5vey804Febc,1075
+dyff/schema/errors.py,sha256=4FwatI-0RUYYqVR0hHoifXPgANk89QgSq9PTS9FzfwU,1568
 dyff/schema/ids.py,sha256=Z3JQzlAJQC2Pam7ehxb4TXA4MIuFQN5SyzL5Ql0RukA,1422
 dyff/schema/platform.py,sha256=peHzGGSd5dQ-EFXrWDjBqMUtoOL3iCHxcV3XzW6Rjag,123
 dyff/schema/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -20,9 +21,9 @@ dyff/schema/io/vllm.py,sha256=2q05M_-lTzq9oywKXHPPpCFCSDVCSsRQqtmERzWTtio,123
 dyff/schema/v0/__init__.py,sha256=L5y8UhRnojerPYHumsxQJRcHCNz8Hj9NM8b47mewMNs,92
 dyff/schema/v0/r1/__init__.py,sha256=L5y8UhRnojerPYHumsxQJRcHCNz8Hj9NM8b47mewMNs,92
 dyff/schema/v0/r1/adapters.py,sha256=2t2oxsnGfSEDKKDIEYw4qqLXMH7qlFIwPVuLyUmbsHs,23552
-dyff/schema/v0/r1/base.py,sha256=X4QVwOzNw5xPCF_f14w2JhARj1CHmGMjUmTcNzb-X0c,17471
-dyff/schema/v0/r1/platform.py,sha256=ocEofM51a4bC0wlHB5zJO6jZUwJVUkYwv7RadTawhVA,61574
-dyff/schema/v0/r1/requests.py,sha256=bTLtQUK80_fFeEWRG6QUJoLwy1_PyXf8ua9Ei4av0ug,8913
+dyff/schema/v0/r1/base.py,sha256=QX1TfqX3jBafxpBnf2bUTcgP0sMyqZFFNJZQHhM48BI,19385
+dyff/schema/v0/r1/platform.py,sha256=t7XKNBXByrkleLhcRZn1Et0Dtb36CtmghWeezThz_UI,61416
+dyff/schema/v0/r1/requests.py,sha256=I2K3thOsga0X9-6oRsAO1Hqgkr8qV_8haw-7ALIf_yc,9857
 dyff/schema/v0/r1/test.py,sha256=X6dUyVd5svcPCI-PBMOAqEfK9jv3bRDvkQTJzwS96c0,10720
 dyff/schema/v0/r1/version.py,sha256=isKAGuGxsdru8vDaYmI4YiZdJOu_wNxXK7u6QzD6FE4,392
 dyff/schema/v0/r1/dataset/__init__.py,sha256=LbVlkO2asyGYBKk2z49xjJYTM-pu9y9e4eQDXgTDLnM,2553
@@ -33,9 +34,9 @@ dyff/schema/v0/r1/dataset/text.py,sha256=nLIn91Zlt0tNdXUklSgjJ-kEDxoPX32ISLkiv2D
 dyff/schema/v0/r1/dataset/vision.py,sha256=aIe0fbfM_g3DsrDTdg2K803YKLjZBpurM_VJcJFuZLc,369
 dyff/schema/v0/r1/io/__init__.py,sha256=L5y8UhRnojerPYHumsxQJRcHCNz8Hj9NM8b47mewMNs,92
 dyff/schema/v0/r1/io/vllm.py,sha256=CUE9y8KthtUI7sD49S875rDmPvKotSXVIRaBS79aBZs,5320
-dyff_schema-0.7.2.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-dyff_schema-0.7.2.dist-info/METADATA,sha256=zEELaVi3ZL67mNV3031i02KZH7DeuXqEwSkXR_C6LhI,3459
-dyff_schema-0.7.2.dist-info/NOTICE,sha256=YONACu0s_Ui6jNi-wtEsVQbTU1JIkh8wvLH6d1-Ni_w,43
-dyff_schema-0.7.2.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-dyff_schema-0.7.2.dist-info/top_level.txt,sha256=9e3VVdeX73t_sUJOPQPCcGtYO1JhoErhHIi3WoWGcFI,5
-dyff_schema-0.7.2.dist-info/RECORD,,
+dyff_schema-0.9.0.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+dyff_schema-0.9.0.dist-info/METADATA,sha256=y8iwfPwD_j6hEaMZXg7wTYwt319cWdKjB2eDNRiyc14,3459
+dyff_schema-0.9.0.dist-info/NOTICE,sha256=YONACu0s_Ui6jNi-wtEsVQbTU1JIkh8wvLH6d1-Ni_w,43
+dyff_schema-0.9.0.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+dyff_schema-0.9.0.dist-info/top_level.txt,sha256=9e3VVdeX73t_sUJOPQPCcGtYO1JhoErhHIi3WoWGcFI,5
+dyff_schema-0.9.0.dist-info/RECORD,,