climate-ref 0.6.5__py3-none-any.whl → 0.7.0__py3-none-any.whl

climate_ref/migrations/versions/2025-07-20T1521_94beace57a9c_cmip6_finalised.py

@@ -22,7 +22,7 @@ depends_on: Union[str, Sequence[str], None] = None
 def upgrade() -> None:
     # ### commands auto generated by Alembic - please adjust! ###
     with op.batch_alter_table("cmip6_dataset", schema=None) as batch_op:
-        batch_op.add_column(sa.Column("finalised", sa.Boolean(), nullable=False))
+        batch_op.add_column(sa.Column("finalised", sa.Boolean(), nullable=True))
         batch_op.alter_column("experiment", existing_type=sa.VARCHAR(), nullable=True)
         batch_op.alter_column("frequency", existing_type=sa.VARCHAR(), nullable=True)
         batch_op.alter_column("grid", existing_type=sa.VARCHAR(), nullable=True)

climate_ref/migrations/versions/2025-08-05T0327_a1b2c3d4e5f6_finalised_on_base_dataset.py

@@ -49,7 +49,7 @@ def downgrade() -> None:
     # Note: Original migration 94beace57a9c added cmip6_dataset.finalised NOT NULL, with no default.
     with op.batch_alter_table("cmip6_dataset", schema=None) as batch_op:
         batch_op.add_column(
-            sa.Column("finalised", sa.Boolean(), nullable=False, server_default=sa.text("false"))
+            sa.Column("finalised", sa.Boolean(), nullable=True, server_default=sa.text("false"))
         )
 
     # Drop base dataset finalised

climate_ref/migrations/versions/2025-09-05T2019_8d28e5e0f9c3_add_indexes.py

@@ -0,0 +1,108 @@
+"""add indexes
+
+Revision ID: 8d28e5e0f9c3
+Revises: ba5e
+Create Date: 2025-09-05 20:19:18.311472
+
+"""
+
+from collections.abc import Sequence
+from typing import Union
+
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "8d28e5e0f9c3"
+down_revision: Union[str, None] = "ba5e"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table("cmip6_dataset", schema=None) as batch_op:
+        batch_op.create_index(batch_op.f("ix_cmip6_dataset_experiment_id"), ["experiment_id"], unique=False)
+        batch_op.create_index(batch_op.f("ix_cmip6_dataset_instance_id"), ["instance_id"], unique=False)
+        batch_op.create_index(batch_op.f("ix_cmip6_dataset_member_id"), ["member_id"], unique=False)
+        batch_op.create_index(batch_op.f("ix_cmip6_dataset_source_id"), ["source_id"], unique=False)
+
+    with op.batch_alter_table("dataset", schema=None) as batch_op:
+        batch_op.create_index(batch_op.f("ix_dataset_dataset_type"), ["dataset_type"], unique=False)
+
+    with op.batch_alter_table("dataset_file", schema=None) as batch_op:
+        batch_op.create_index(batch_op.f("ix_dataset_file_dataset_id"), ["dataset_id"], unique=False)
+
+    with op.batch_alter_table("diagnostic", schema=None) as batch_op:
+        batch_op.create_index(batch_op.f("ix_diagnostic_updated_at"), ["updated_at"], unique=False)
+
+    with op.batch_alter_table("execution", schema=None) as batch_op:
+        batch_op.create_index(
+            batch_op.f("ix_execution_execution_group_id"), ["execution_group_id"], unique=False
+        )
+        batch_op.create_index(batch_op.f("ix_execution_successful"), ["successful"], unique=False)
+        batch_op.create_index(batch_op.f("ix_execution_updated_at"), ["updated_at"], unique=False)
+
+    with op.batch_alter_table("execution_dataset", schema=None) as batch_op:
+        batch_op.create_index(batch_op.f("ix_execution_dataset_dataset_id"), ["dataset_id"], unique=False)
+        batch_op.create_index(batch_op.f("ix_execution_dataset_execution_id"), ["execution_id"], unique=False)
+
+    with op.batch_alter_table("execution_group", schema=None) as batch_op:
+        batch_op.create_index(batch_op.f("ix_execution_group_diagnostic_id"), ["diagnostic_id"], unique=False)
+        batch_op.create_index(batch_op.f("ix_execution_group_updated_at"), ["updated_at"], unique=False)
+
+    with op.batch_alter_table("execution_output", schema=None) as batch_op:
+        batch_op.create_index(batch_op.f("ix_execution_output_updated_at"), ["updated_at"], unique=False)
+
+    with op.batch_alter_table("metric_value", schema=None) as batch_op:
+        batch_op.create_index(batch_op.f("ix_metric_value_execution_id"), ["execution_id"], unique=False)
+        batch_op.create_index(batch_op.f("ix_metric_value_type"), ["type"], unique=False)
+        batch_op.create_index(batch_op.f("ix_metric_value_updated_at"), ["updated_at"], unique=False)
+
+    with op.batch_alter_table("provider", schema=None) as batch_op:
+        batch_op.create_index(batch_op.f("ix_provider_updated_at"), ["updated_at"], unique=False)
+
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table("provider", schema=None) as batch_op:
+        batch_op.drop_index(batch_op.f("ix_provider_updated_at"))
+
+    with op.batch_alter_table("metric_value", schema=None) as batch_op:
+        batch_op.drop_index(batch_op.f("ix_metric_value_updated_at"))
+        batch_op.drop_index(batch_op.f("ix_metric_value_type"))
+        batch_op.drop_index(batch_op.f("ix_metric_value_execution_id"))
+
+    with op.batch_alter_table("execution_output", schema=None) as batch_op:
+        batch_op.drop_index(batch_op.f("ix_execution_output_updated_at"))
+
+    with op.batch_alter_table("execution_group", schema=None) as batch_op:
+        batch_op.drop_index(batch_op.f("ix_execution_group_updated_at"))
+        batch_op.drop_index(batch_op.f("ix_execution_group_diagnostic_id"))
+
+    with op.batch_alter_table("execution_dataset", schema=None) as batch_op:
+        batch_op.drop_index(batch_op.f("ix_execution_dataset_execution_id"))
+        batch_op.drop_index(batch_op.f("ix_execution_dataset_dataset_id"))
+
+    with op.batch_alter_table("execution", schema=None) as batch_op:
+        batch_op.drop_index(batch_op.f("ix_execution_updated_at"))
+        batch_op.drop_index(batch_op.f("ix_execution_successful"))
+        batch_op.drop_index(batch_op.f("ix_execution_execution_group_id"))
+
+    with op.batch_alter_table("diagnostic", schema=None) as batch_op:
+        batch_op.drop_index(batch_op.f("ix_diagnostic_updated_at"))
+
+    with op.batch_alter_table("dataset_file", schema=None) as batch_op:
+        batch_op.drop_index(batch_op.f("ix_dataset_file_dataset_id"))
+
+    with op.batch_alter_table("dataset", schema=None) as batch_op:
+        batch_op.drop_index(batch_op.f("ix_dataset_dataset_type"))
+
+    with op.batch_alter_table("cmip6_dataset", schema=None) as batch_op:
+        batch_op.drop_index(batch_op.f("ix_cmip6_dataset_source_id"))
+        batch_op.drop_index(batch_op.f("ix_cmip6_dataset_member_id"))
+        batch_op.drop_index(batch_op.f("ix_cmip6_dataset_instance_id"))
+        batch_op.drop_index(batch_op.f("ix_cmip6_dataset_experiment_id"))
+
+    # ### end Alembic commands ###

climate_ref/migrations/versions/2025-09-10T1358_2f6e36738e06_use_version_as_version_facet_for_.py

@@ -0,0 +1,35 @@
+"""use 'version' as version facet for obs4MIPs
+
+Revision ID: 2f6e36738e06
+Revises: 8d28e5e0f9c3
+Create Date: 2025-09-10 13:58:40.660076
+
+"""
+
+from collections.abc import Sequence
+from typing import Union
+
+import sqlalchemy as sa
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "2f6e36738e06"
+down_revision: Union[str, None] = "8d28e5e0f9c3"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table("obs4mips_dataset", schema=None) as batch_op:
+        batch_op.add_column(sa.Column("version", sa.String(), nullable=False))
+
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table("obs4mips_dataset", schema=None) as batch_op:
+        batch_op.drop_column("version")
+
+    # ### end Alembic commands ###

climate_ref/migrations/versions/2025-09-22T2359_20cd136a5b04_add_pmp_version.py

@@ -0,0 +1,35 @@
+"""add pmp version
+
+Revision ID: 20cd136a5b04
+Revises: 2f6e36738e06
+Create Date: 2025-09-22 23:59:42.724007
+
+"""
+
+from collections.abc import Sequence
+from typing import Union
+
+import sqlalchemy as sa
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "20cd136a5b04"
+down_revision: Union[str, None] = "2f6e36738e06"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table("pmp_climatology_dataset", schema=None) as batch_op:
+        batch_op.add_column(sa.Column("version", sa.String(), nullable=False))
+
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table("pmp_climatology_dataset", schema=None) as batch_op:
+        batch_op.drop_column("version")
+
+    # ### end Alembic commands ###

climate_ref/models/__init__.py

@@ -4,9 +4,7 @@ Declaration of the models used by the REF.
 These models are used to represent the data that is stored in the database.
 """
 
-from typing import TypeVar
-
-from climate_ref.models.base import Base
+from climate_ref.models.base import Base, Table
 from climate_ref.models.dataset import Dataset
 from climate_ref.models.diagnostic import Diagnostic
 from climate_ref.models.execution import (
@@ -17,9 +15,6 @@ from climate_ref.models.execution import (
 from climate_ref.models.metric_value import MetricValue, ScalarMetricValue, SeriesMetricValue
 from climate_ref.models.provider import Provider
 
-Table = TypeVar("Table", bound=Base)
-
-
 __all__ = [
     "Base",
     "Dataset",

climate_ref/models/base.py

@@ -1,8 +1,7 @@
-import datetime
-from typing import Any
+from typing import Any, TypeVar
 
-from sqlalchemy import JSON, MetaData, func
-from sqlalchemy.orm import DeclarativeBase, Mapped, mapped_column
+from sqlalchemy import JSON, MetaData
+from sqlalchemy.orm import DeclarativeBase
 
 
 class Base(DeclarativeBase):
@@ -28,17 +27,4 @@ class Base(DeclarativeBase):
     )
 
 
-class CreatedUpdatedMixin:
-    """
-    Mixin for models that have a created_at and updated_at fields
-    """
-
-    created_at: Mapped[datetime.datetime] = mapped_column(server_default=func.now())
-    """
-    When the dataset was added to the database
-    """
-
-    updated_at: Mapped[datetime.datetime] = mapped_column(server_default=func.now(), onupdate=func.now())
-    """
-    When the dataset was updated.
-    """
+Table = TypeVar("Table", bound=Base)

climate_ref/models/dataset.py

@@ -30,7 +30,7 @@ class Dataset(Base):
 
     In the case of CMIP6 datasets, this is the instance_id.
     """
-    dataset_type: Mapped[SourceDatasetType] = mapped_column(nullable=False)
+    dataset_type: Mapped[SourceDatasetType] = mapped_column(nullable=False, index=True)
     """
     Type of dataset
     """
@@ -73,7 +73,9 @@ class DatasetFile(Base):
     __tablename__ = "dataset_file"
 
     id: Mapped[int] = mapped_column(primary_key=True)
-    dataset_id: Mapped[int] = mapped_column(ForeignKey("dataset.id", ondelete="CASCADE"), nullable=False)
+    dataset_id: Mapped[int] = mapped_column(
+        ForeignKey("dataset.id", ondelete="CASCADE"), nullable=False, index=True
+    )
     """
     Foreign key to the dataset table
     """
@@ -111,13 +113,13 @@ class CMIP6Dataset(Dataset):
     branch_time_in_child: Mapped[float] = mapped_column(nullable=True)
     branch_time_in_parent: Mapped[float] = mapped_column(nullable=True)
     experiment: Mapped[str] = mapped_column(nullable=True)
-    experiment_id: Mapped[str] = mapped_column()
+    experiment_id: Mapped[str] = mapped_column(index=True)
     frequency: Mapped[str] = mapped_column(nullable=True)
     grid: Mapped[str] = mapped_column(nullable=True)
     grid_label: Mapped[str] = mapped_column()
     institution_id: Mapped[str] = mapped_column()
     long_name: Mapped[str] = mapped_column(nullable=True)
-    member_id: Mapped[str] = mapped_column()
+    member_id: Mapped[str] = mapped_column(index=True)
     nominal_resolution: Mapped[str] = mapped_column(nullable=True)
     parent_activity_id: Mapped[str] = mapped_column(nullable=True)
     parent_experiment_id: Mapped[str] = mapped_column(nullable=True)
@@ -126,7 +128,7 @@ class CMIP6Dataset(Dataset):
     parent_variant_label: Mapped[str] = mapped_column(nullable=True)
     realm: Mapped[str] = mapped_column(nullable=True)
     product: Mapped[str] = mapped_column(nullable=True)
-    source_id: Mapped[str] = mapped_column()
+    source_id: Mapped[str] = mapped_column(index=True)
     standard_name: Mapped[str] = mapped_column(nullable=True)
     source_type: Mapped[str] = mapped_column(nullable=True)
     sub_experiment: Mapped[str] = mapped_column(nullable=True)
@@ -138,7 +140,7 @@ class CMIP6Dataset(Dataset):
     vertical_levels: Mapped[int] = mapped_column(nullable=True)
     version: Mapped[str] = mapped_column()
 
-    instance_id: Mapped[str] = mapped_column()
+    instance_id: Mapped[str] = mapped_column(index=True)
     """
     Unique identifier for the dataset (including the version).
     """
@@ -170,6 +172,7 @@ class Obs4MIPsDataset(Dataset):
     units: Mapped[str] = mapped_column()
     variable_id: Mapped[str] = mapped_column()
     variant_label: Mapped[str] = mapped_column()
+    version: Mapped[str] = mapped_column()
     vertical_levels: Mapped[int] = mapped_column()
     source_version_number: Mapped[str] = mapped_column()
 
@@ -204,6 +207,7 @@ class PMPClimatologyDataset(Dataset):
     units: Mapped[str] = mapped_column()
     variable_id: Mapped[str] = mapped_column()
     variant_label: Mapped[str] = mapped_column()
+    version: Mapped[str] = mapped_column()
     vertical_levels: Mapped[int] = mapped_column()
     source_version_number: Mapped[str] = mapped_column()
 

climate_ref/models/diagnostic.py

@@ -3,7 +3,8 @@ from typing import TYPE_CHECKING
 from sqlalchemy import ForeignKey, UniqueConstraint
 from sqlalchemy.orm import Mapped, mapped_column, relationship
 
-from climate_ref.models.base import Base, CreatedUpdatedMixin
+from climate_ref.models.base import Base
+from climate_ref.models.mixins import CreatedUpdatedMixin
 
 if TYPE_CHECKING:
     from climate_ref.models.execution import ExecutionGroup

climate_ref/models/execution.py

@@ -1,19 +1,22 @@
 import enum
 import pathlib
-from typing import TYPE_CHECKING, Any
+from collections.abc import Sequence
+from typing import TYPE_CHECKING, Any, ClassVar
 
 from loguru import logger
-from sqlalchemy import Column, ForeignKey, Table, UniqueConstraint, func
+from sqlalchemy import Column, ForeignKey, Table, UniqueConstraint, func, or_
 from sqlalchemy.orm import Mapped, Session, mapped_column, relationship
 from sqlalchemy.orm.query import RowReturningQuery
 
-from climate_ref.models import Dataset
-from climate_ref.models.base import Base, CreatedUpdatedMixin
+from climate_ref.models.base import Base
+from climate_ref.models.dataset import Dataset
+from climate_ref.models.diagnostic import Diagnostic
+from climate_ref.models.mixins import CreatedUpdatedMixin, DimensionMixin
+from climate_ref.models.provider import Provider
 from climate_ref_core.datasets import ExecutionDatasetCollection
 
 if TYPE_CHECKING:
     from climate_ref.database import Database
-    from climate_ref.models.diagnostic import Diagnostic
     from climate_ref.models.metric_value import MetricValue
 
 
@@ -40,7 +43,7 @@ class ExecutionGroup(CreatedUpdatedMixin, Base):
 
     id: Mapped[int] = mapped_column(primary_key=True)
 
-    diagnostic_id: Mapped[int] = mapped_column(ForeignKey("diagnostic.id"))
+    diagnostic_id: Mapped[int] = mapped_column(ForeignKey("diagnostic.id"), index=True)
     """
     The diagnostic that this execution group belongs to
     """
@@ -103,8 +106,8 @@ class ExecutionGroup(CreatedUpdatedMixin, Base):
 execution_datasets = Table(
     "execution_dataset",
     Base.metadata,
-    Column("execution_id", ForeignKey("execution.id")),
-    Column("dataset_id", ForeignKey("dataset.id")),
+    Column("execution_id", ForeignKey("execution.id"), index=True),
+    Column("dataset_id", ForeignKey("dataset.id"), index=True),
 )
 
 
@@ -136,7 +139,8 @@ class Execution(CreatedUpdatedMixin, Base):
         ForeignKey(
             "execution_group.id",
             name="fk_execution_id",
-        )
+        ),
+        index=True,
     )
     """
     The execution group that this execution belongs to
@@ -149,7 +153,7 @@ class Execution(CreatedUpdatedMixin, Base):
     This is used to verify if an existing diagnostic execution has been run with the same datasets.
     """
 
-    successful: Mapped[bool] = mapped_column(nullable=True)
+    successful: Mapped[bool] = mapped_column(nullable=True, index=True)
     """
     Was the run successful
     """
@@ -216,16 +220,21 @@ class ResultOutputType(enum.Enum):
     HTML = "html"
 
 
-class ExecutionOutput(CreatedUpdatedMixin, Base):
+class ExecutionOutput(DimensionMixin, CreatedUpdatedMixin, Base):
     """
     An output generated as part of an execution.
 
     This output may be a plot, data file or HTML file.
-    These outputs are defined in the CMEC output bundle
+    These outputs are defined in the CMEC output bundle.
+
+    Outputs can be tagged with dimensions from the controlled vocabulary
+    to enable filtering and organization.
     """
 
     __tablename__ = "execution_output"
 
+    _cv_dimensions: ClassVar[list[str]] = []
+
     id: Mapped[int] = mapped_column(primary_key=True)
 
     execution_id: Mapped[int] = mapped_column(ForeignKey("execution.id"), index=True)
@@ -263,6 +272,65 @@ class ExecutionOutput(CreatedUpdatedMixin, Base):
 
     execution: Mapped["Execution"] = relationship(back_populates="outputs")
 
+    @classmethod
+    def build(  # noqa: PLR0913
+        cls,
+        *,
+        execution_id: int,
+        output_type: ResultOutputType,
+        dimensions: dict[str, str],
+        filename: str | None = None,
+        short_name: str | None = None,
+        long_name: str | None = None,
+        description: str | None = None,
+    ) -> "ExecutionOutput":
+        """
+        Build an ExecutionOutput from dimensions and metadata
+
+        This is a helper method that validates the dimensions supplied.
+
+        Parameters
+        ----------
+        execution_id
+            Execution that created the output
+        output_type
+            Type of the output
+        dimensions
+            Dimensions that describe the output
+        filename
+            Path to the output
+        short_name
+            Short key of the output
+        long_name
+            Human readable name
+        description
+            Long description
+
+        Raises
+        ------
+        KeyError
+            If an unknown dimension was supplied.
+
+            Dimensions must exist in the controlled vocabulary.
+
+        Returns
+        -------
+            Newly created ExecutionOutput
+        """
+        for k in dimensions:
+            if k not in cls._cv_dimensions:
+                raise KeyError(f"Unknown dimension column '{k}'")
+
+        return ExecutionOutput(
+            execution_id=execution_id,
+            output_type=output_type,
+            filename=filename,
+            short_name=short_name,
+            long_name=long_name,
+            description=description,
+            **dimensions,
+        )
+
 
 def get_execution_group_and_latest(
     session: Session,
@@ -304,3 +372,148 @@ def get_execution_group_and_latest(
     )
 
     return query  # type: ignore
+
+
+def _filter_executions_by_facets(
+    results: Sequence[tuple[ExecutionGroup, Execution | None]],
+    facet_filters: dict[str, str],
+) -> list[tuple[ExecutionGroup, Execution | None]]:
+    """
+    Filter execution groups and their latest executions based on facet key-value pairs.
+
+    This is a relatively expensive operation as it requires iterating over all results.
+    This should be replaced once we have normalised the selectors into a separate table.
+
+
+    Parameters
+    ----------
+    results
+        List of tuples containing ExecutionGroup and its latest Execution (or None)
+    facet_filters
+        Dictionary of facet key-value pairs to filter by (AND logic, exact match)
+
+    Returns
+    -------
+        Filtered list of tuples containing ExecutionGroup and its latest Execution (or None)
+
+    Notes
+    -----
+    - Facet filters can either be key=value (searches all dataset types)
+      or dataset_type.key=value (searches specific dataset type)
+    - Key=value filters search across all dataset types
+    - dataset_type.key=value filters only search within the specified dataset type
+    - Multiple values within same filter type use OR logic
+    - All specified facets must match for an execution group to be included (AND logic)
+    """
+    filtered_results = []
+    for eg, execution in results:
+        all_filters_match = True
+        for facet_key, facet_value in facet_filters.items():
+            filter_match = False
+            if "." in facet_key:
+                # Handle dataset_type.key=value format
+                dataset_type, key = facet_key.split(".", 1)
+                if dataset_type in eg.selectors:
+                    if [key, facet_value] in eg.selectors[dataset_type]:
+                        filter_match = True
+                        break
+            else:
+                # Handle key=value format (search across all dataset types)
+                for ds_type_selectors in eg.selectors.values():
+                    if [facet_key, facet_value] in ds_type_selectors:
+                        filter_match = True
+                        break
+
+            if not filter_match:
+                all_filters_match = False
+                break
+        if all_filters_match:
+            filtered_results.append((eg, execution))
+    return filtered_results
+
+
+def get_execution_group_and_latest_filtered(  # noqa: PLR0913
+    session: Session,
+    diagnostic_filters: list[str] | None = None,
+    provider_filters: list[str] | None = None,
+    facet_filters: dict[str, str] | None = None,
+    dirty: bool | None = None,
+    successful: bool | None = None,
+) -> list[tuple[ExecutionGroup, Execution | None]]:
+    """
+    Query execution groups with filtering capabilities.
+
+    Parameters
+    ----------
+    session
+        Database session
+    diagnostic_filters
+        List of diagnostic slug substrings (OR logic, case-insensitive)
+    provider_filters
+        List of provider slug substrings (OR logic, case-insensitive)
+    facet_filters
+        Dictionary of facet key-value pairs (AND logic, exact match)
+    dirty
+        If True, only return dirty execution groups.
+        If False, only return clean execution groups.
+        If None, do not filter by dirty status.
+    successful
+        If True, only return execution groups whose latest execution was successful.
+        If False, only return execution groups whose latest execution was unsuccessful or has no executions.
+        If None, do not filter by execution success.
+
+    Returns
+    -------
+        Query returning tuples of (ExecutionGroup, latest Execution or None)
+
+    Notes
+    -----
+    - Diagnostic and provider filters use substring matching (case-insensitive)
+    - Multiple values within same filter type use OR logic
+    - Different filter types use AND logic
+    - Facet filters can either be key=value (searches all dataset types)
+      or dataset_type.key=value (searches specific dataset type)
+    """
+    # Start with base query
+    query = get_execution_group_and_latest(session)
+
+    if diagnostic_filters or provider_filters:
+        # Join through to the Diagnostic table
+        query = query.join(Diagnostic, ExecutionGroup.diagnostic_id == Diagnostic.id)
+
+    # Apply diagnostic filter (OR logic for multiple values)
+    if diagnostic_filters:
+        diagnostic_conditions = [
+            Diagnostic.slug.ilike(f"%{filter_value.lower()}%") for filter_value in diagnostic_filters
+        ]
+        query = query.filter(or_(*diagnostic_conditions))
+
+    # Apply provider filter (OR logic for multiple values)
+    if provider_filters:
+        # Need to join through Diagnostic to Provider
+        query = query.join(Provider, Diagnostic.provider_id == Provider.id)
+
+        provider_conditions = [
+            Provider.slug.ilike(f"%{filter_value.lower()}%") for filter_value in provider_filters
+        ]
+        query = query.filter(or_(*provider_conditions))
+
+    if successful is not None:
+        if successful:
+            query = query.filter(Execution.successful.is_(True))
+        else:
+            query = query.filter(or_(Execution.successful.is_(False), Execution.successful.is_(None)))
+
+    if dirty is not None:
+        if dirty:
+            query = query.filter(ExecutionGroup.dirty.is_(True))
+        else:
+            query = query.filter(or_(ExecutionGroup.dirty.is_(False), ExecutionGroup.dirty.is_(None)))
+
+    if facet_filters:
+        # Load all results into memory for Python-based filtering
+        # TODO: Update once we have normalised the selector
+        results = [r._tuple() for r in query.all()]
+        return _filter_executions_by_facets(results, facet_filters)
+    else:
+        return [r._tuple() for r in query.all()]