Skip to content

Replace objective run with evaluator judge run #36

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
May 19, 2025
Merged

Replace objective run with evaluator judge run #36

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 0 additions & 20 deletions examples/objective.py
View file
Open in desktop

This file was deleted.

160 changes: 0 additions & 160 deletions src/root/objectives.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,13 +8,7 @@

from .generated.openapi_aclient import ApiClient as AApiClient
from .generated.openapi_aclient.api.v1_api import V1Api as AObjectivesApi
from .generated.openapi_aclient.models.evaluator_execution_functions_request import (
EvaluatorExecutionFunctionsRequest as AEvaluatorExecutionFunctionsRequest,
)
from .generated.openapi_aclient.models.objective import Objective as AOpenApiObjective
from .generated.openapi_aclient.models.objective_execution_request import (
ObjectiveExecutionRequest as AObjectiveExecutionRequest,
)
from .generated.openapi_aclient.models.objective_list import ObjectiveList as AObjectiveList
from .generated.openapi_aclient.models.objective_request import ObjectiveRequest as AObjectiveRequest
from .generated.openapi_aclient.models.paginated_objective_list import (
Expand All @@ -26,21 +20,13 @@
from .generated.openapi_aclient.models.patched_objective_request import (
PatchedObjectiveRequest as APatchedObjectiveRequest,
)
from .generated.openapi_aclient.models.validator_execution_result import (
ValidatorExecutionResult as AValidatorExecutionResult,
)
from .generated.openapi_client import ApiClient
from .generated.openapi_client.api.v1_api import V1Api as ObjectivesApi
from .generated.openapi_client.models.evaluator_execution_functions_request import (
EvaluatorExecutionFunctionsRequest,
)
from .generated.openapi_client.models.objective import Objective as OpenApiObjective
from .generated.openapi_client.models.objective_execution_request import ObjectiveExecutionRequest
from .generated.openapi_client.models.objective_list import ObjectiveList
from .generated.openapi_client.models.objective_request import ObjectiveRequest
from .generated.openapi_client.models.paginated_objective_list import PaginatedObjectiveList
from .generated.openapi_client.models.patched_objective_request import PatchedObjectiveRequest
from .generated.openapi_client.models.validator_execution_result import ValidatorExecutionResult
from .skills import Skills
from .utils import ClientContextCallable, iterate_cursor_list, with_async_client, with_sync_client
from .validators import AValidator
Expand Down Expand Up @@ -101,43 +87,6 @@ def _wrap(cls, apiobj: OpenApiObjective, client_context: ClientContextCallable)
obj.client_context = client_context
return obj

@with_sync_client
def run(
self,
*,
response: str,
request: Optional[str] = None,
contexts: Optional[List[str]] = None,
functions: Optional[List[EvaluatorExecutionFunctionsRequest]] = None,
expected_output: Optional[str] = None,
_request_timeout: Optional[int] = None,
_client: ApiClient,
) -> ValidatorExecutionResult:
"""
Run all validators associated with the objective.

Args:
response: LLM output.
request: The prompt sent to the LLM. Optional.
contexts: Optional documents passed to RAG evaluators
functions: Optional function definitions to LLM tool call validation
expected_output: Optional expected output for the evaluators
"""

api_instance = ObjectivesApi(_client)
skill_execution_request = ObjectiveExecutionRequest(
request=request,
response=response,
contexts=contexts,
functions=functions,
expected_output=expected_output,
)
return api_instance.v1_objectives_objectives_execute_create(
objective_id=self.id,
objective_execution_request=skill_execution_request,
_request_timeout=_request_timeout,
)


class AObjective(AOpenApiObjective):
"""
Expand All @@ -158,43 +107,6 @@ async def _awrap(cls, apiobj: AOpenApiObjective, client_context: ClientContextCa
obj.client_context = client_context
return obj

@with_async_client
async def arun(
self,
*,
response: str,
request: Optional[str] = None,
contexts: Optional[List[str]] = None,
functions: Optional[List[AEvaluatorExecutionFunctionsRequest]] = None,
expected_output: Optional[str] = None,
_request_timeout: Optional[int] = None,
_client: AApiClient,
) -> AValidatorExecutionResult:
"""
Asynchronously run all validators associated with the objective.

Args:
response: LLM output.
request: The prompt sent to the LLM. Optional.
contexts: Optional documents passed to RAG evaluators
functions: Optional function definitions to LLM tool call validation
expected_output: Optional expected output for the evaluators
"""

api_instance = AObjectivesApi(_client)
skill_execution_request = AObjectiveExecutionRequest(
request=request,
response=response,
contexts=contexts,
functions=functions,
expected_output=expected_output,
)
return await api_instance.v1_objectives_objectives_execute_create(
objective_id=self.id,
objective_execution_request=skill_execution_request,
_request_timeout=_request_timeout,
)


class Objectives:
"""
Expand Down Expand Up @@ -378,78 +290,6 @@ async def alist(self, *, intent: Optional[str] = None, limit: int = 100) -> Asyn
if not (cursor := result.next):
return

@with_sync_client
def run(
self,
objective_id: str,
*,
response: str,
request: Optional[str] = None,
contexts: Optional[List[str]] = None,
functions: Optional[List[EvaluatorExecutionFunctionsRequest]] = None,
expected_output: Optional[str] = None,
_request_timeout: Optional[int] = None,
_client: ApiClient,
) -> ValidatorExecutionResult:
"""
Run all validators associated with an objective.

Args:
response: LLM output.
request: The prompt sent to the LLM. Optional.
contexts: Optional documents passed to RAG evaluators
"""

api_instance = ObjectivesApi(_client)
skill_execution_request = ObjectiveExecutionRequest(
request=request,
response=response,
contexts=contexts,
functions=functions,
expected_output=expected_output,
)
return api_instance.v1_objectives_objectives_execute_create(
objective_id=objective_id,
objective_execution_request=skill_execution_request,
_request_timeout=_request_timeout,
)

@with_async_client
async def arun(
self,
objective_id: str,
*,
_client: AApiClient,
response: str,
request: Optional[str] = None,
contexts: Optional[List[str]] = None,
functions: Optional[List[AEvaluatorExecutionFunctionsRequest]] = None,
expected_output: Optional[str] = None,
_request_timeout: Optional[int] = None,
) -> AValidatorExecutionResult:
"""
Asynchronously run all validators associated with an objective.

Args:
response: LLM output.
request: The prompt sent to the LLM. Optional.
contexts: Optional documents passed to RAG evaluators
"""

api_instance = AObjectivesApi(_client)
skill_execution_request = AObjectiveExecutionRequest(
request=request,
response=response,
contexts=contexts,
functions=functions,
expected_output=expected_output,
)
return await api_instance.v1_objectives_objectives_execute_create(
objective_id=objective_id,
objective_execution_request=skill_execution_request,
_request_timeout=_request_timeout,
)

@with_sync_client
def update(
self,
Expand Down