scale-gp-beta 0.1.0a8__tar.gz → 0.1.0a9__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- scale_gp_beta-0.1.0a9/.release-please-manifest.json +3 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/CHANGELOG.md +9 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/PKG-INFO +1 -1
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/pyproject.toml +1 -1
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_version.py +1 -1
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/evaluations.py +18 -4
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/__init__.py +1 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/evaluation.py +4 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/evaluation_list_params.py +4 -2
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/evaluation_retrieve_params.py +4 -1
- scale_gp_beta-0.1.0a9/src/scale_gp_beta/types/evaluation_task.py +205 -0
- scale_gp_beta-0.1.0a9/src/scale_gp_beta/types/evaluation_task_param.py +206 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/api_resources/test_evaluations.py +4 -0
- scale_gp_beta-0.1.0a8/.release-please-manifest.json +0 -3
- scale_gp_beta-0.1.0a8/src/scale_gp_beta/types/evaluation_task_param.py +0 -212
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/.gitignore +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/CONTRIBUTING.md +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/LICENSE +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/README.md +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/SECURITY.md +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/api.md +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/bin/check-release-environment +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/bin/publish-pypi +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/examples/.keep +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/mypy.ini +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/noxfile.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/release-please-config.json +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/requirements-dev.lock +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/requirements.lock +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp/lib/.keep +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/__init__.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_base_client.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_client.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_compat.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_constants.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_exceptions.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_files.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_models.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_qs.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_resource.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_response.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_streaming.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_types.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_utils/__init__.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_utils/_logs.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_utils/_proxy.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_utils/_reflection.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_utils/_streams.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_utils/_sync.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_utils/_transform.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_utils/_typing.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_utils/_utils.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/lib/.keep +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/pagination.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/py.typed +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/__init__.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/chat/__init__.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/chat/chat.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/chat/completions.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/completions.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/dataset_items.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/datasets.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/evaluation_items.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/files/__init__.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/files/content.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/files/files.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/inference.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/models.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/chat/__init__.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/chat/chat_completion.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/chat/chat_completion_chunk.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/chat/completion_create_params.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/chat/completion_create_response.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/completion.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/completion_create_params.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset_create_params.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset_delete_response.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset_item.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset_item_batch_create_params.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset_item_batch_create_response.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset_item_delete_response.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset_item_list_params.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset_item_retrieve_params.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset_item_update_params.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset_list_params.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset_retrieve_params.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset_update_params.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/evaluation_archive_response.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/evaluation_create_params.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/evaluation_item.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/evaluation_item_list_params.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/evaluation_item_retrieve_params.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/file.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/file_create_params.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/file_delete_response.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/file_list.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/file_list_params.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/file_update_params.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/files/__init__.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/inference_create_params.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/inference_create_response.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/inference_model.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/inference_model_list.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/inference_response.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/inference_response_chunk.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/model_create_params.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/model_delete_response.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/model_list_params.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/model_update_params.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/sgp_dev/lib/.keep +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/__init__.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/api_resources/__init__.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/api_resources/chat/__init__.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/api_resources/chat/test_completions.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/api_resources/files/__init__.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/api_resources/files/test_content.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/api_resources/test_completions.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/api_resources/test_dataset_items.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/api_resources/test_datasets.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/api_resources/test_evaluation_items.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/api_resources/test_files.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/api_resources/test_inference.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/api_resources/test_models.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/conftest.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/sample_file.txt +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/test_client.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/test_deepcopy.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/test_extract_files.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/test_files.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/test_models.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/test_qs.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/test_required_args.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/test_response.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/test_streaming.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/test_transform.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/test_utils/test_proxy.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/test_utils/test_typing.py +0 -0
- {scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/tests/utils.py +0 -0
|
@@ -1,5 +1,14 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## 0.1.0-alpha.9 (2025-03-27)
|
|
4
|
+
|
|
5
|
+
Full Changelog: [v0.1.0-alpha.8...v0.1.0-alpha.9](https://github.com/scaleapi/sgp-python-beta/compare/v0.1.0-alpha.8...v0.1.0-alpha.9)
|
|
6
|
+
|
|
7
|
+
### Features
|
|
8
|
+
|
|
9
|
+
* **api:** api update ([#87](https://github.com/scaleapi/sgp-python-beta/issues/87)) ([7241799](https://github.com/scaleapi/sgp-python-beta/commit/7241799c9507303b833ca29740bc61b7656c50fe))
|
|
10
|
+
* **api:** manual updates ([#89](https://github.com/scaleapi/sgp-python-beta/issues/89)) ([456e1ff](https://github.com/scaleapi/sgp-python-beta/commit/456e1fff2edb5ce655d5692b10ce7981bd4aca9d))
|
|
11
|
+
|
|
3
12
|
## 0.1.0-alpha.8 (2025-03-26)
|
|
4
13
|
|
|
5
14
|
Full Changelog: [v0.1.0-alpha.7...v0.1.0-alpha.8](https://github.com/scaleapi/sgp-python-beta/compare/v0.1.0-alpha.7...v0.1.0-alpha.8)
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.3
|
|
2
2
|
Name: scale-gp-beta
|
|
3
|
-
Version: 0.1.
|
|
3
|
+
Version: 0.1.0a9
|
|
4
4
|
Summary: The official Python library for the Scale GP API
|
|
5
5
|
Project-URL: Homepage, https://github.com/scaleapi/sgp-python-beta
|
|
6
6
|
Project-URL: Repository, https://github.com/scaleapi/sgp-python-beta
|
|
@@ -2,8 +2,8 @@
|
|
|
2
2
|
|
|
3
3
|
from __future__ import annotations
|
|
4
4
|
|
|
5
|
-
from typing import Dict, Iterable, Optional
|
|
6
|
-
from typing_extensions import overload
|
|
5
|
+
from typing import Dict, List, Iterable, Optional
|
|
6
|
+
from typing_extensions import Literal, overload
|
|
7
7
|
|
|
8
8
|
import httpx
|
|
9
9
|
|
|
@@ -199,6 +199,7 @@ class EvaluationsResource(SyncAPIResource):
|
|
|
199
199
|
evaluation_id: str,
|
|
200
200
|
*,
|
|
201
201
|
include_archived: bool | NotGiven = NOT_GIVEN,
|
|
202
|
+
views: List[Literal["tasks"]] | NotGiven = NOT_GIVEN,
|
|
202
203
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
|
203
204
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
|
204
205
|
extra_headers: Headers | None = None,
|
|
@@ -228,7 +229,11 @@ class EvaluationsResource(SyncAPIResource):
|
|
|
228
229
|
extra_body=extra_body,
|
|
229
230
|
timeout=timeout,
|
|
230
231
|
query=maybe_transform(
|
|
231
|
-
{
|
|
232
|
+
{
|
|
233
|
+
"include_archived": include_archived,
|
|
234
|
+
"views": views,
|
|
235
|
+
},
|
|
236
|
+
evaluation_retrieve_params.EvaluationRetrieveParams,
|
|
232
237
|
),
|
|
233
238
|
),
|
|
234
239
|
cast_to=Evaluation,
|
|
@@ -241,6 +246,7 @@ class EvaluationsResource(SyncAPIResource):
|
|
|
241
246
|
include_archived: bool | NotGiven = NOT_GIVEN,
|
|
242
247
|
limit: int | NotGiven = NOT_GIVEN,
|
|
243
248
|
starting_after: Optional[str] | NotGiven = NOT_GIVEN,
|
|
249
|
+
views: List[Literal["tasks"]] | NotGiven = NOT_GIVEN,
|
|
244
250
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
|
245
251
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
|
246
252
|
extra_headers: Headers | None = None,
|
|
@@ -274,6 +280,7 @@ class EvaluationsResource(SyncAPIResource):
|
|
|
274
280
|
"include_archived": include_archived,
|
|
275
281
|
"limit": limit,
|
|
276
282
|
"starting_after": starting_after,
|
|
283
|
+
"views": views,
|
|
277
284
|
},
|
|
278
285
|
evaluation_list_params.EvaluationListParams,
|
|
279
286
|
),
|
|
@@ -483,6 +490,7 @@ class AsyncEvaluationsResource(AsyncAPIResource):
|
|
|
483
490
|
evaluation_id: str,
|
|
484
491
|
*,
|
|
485
492
|
include_archived: bool | NotGiven = NOT_GIVEN,
|
|
493
|
+
views: List[Literal["tasks"]] | NotGiven = NOT_GIVEN,
|
|
486
494
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
|
487
495
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
|
488
496
|
extra_headers: Headers | None = None,
|
|
@@ -512,7 +520,11 @@ class AsyncEvaluationsResource(AsyncAPIResource):
|
|
|
512
520
|
extra_body=extra_body,
|
|
513
521
|
timeout=timeout,
|
|
514
522
|
query=await async_maybe_transform(
|
|
515
|
-
{
|
|
523
|
+
{
|
|
524
|
+
"include_archived": include_archived,
|
|
525
|
+
"views": views,
|
|
526
|
+
},
|
|
527
|
+
evaluation_retrieve_params.EvaluationRetrieveParams,
|
|
516
528
|
),
|
|
517
529
|
),
|
|
518
530
|
cast_to=Evaluation,
|
|
@@ -525,6 +537,7 @@ class AsyncEvaluationsResource(AsyncAPIResource):
|
|
|
525
537
|
include_archived: bool | NotGiven = NOT_GIVEN,
|
|
526
538
|
limit: int | NotGiven = NOT_GIVEN,
|
|
527
539
|
starting_after: Optional[str] | NotGiven = NOT_GIVEN,
|
|
540
|
+
views: List[Literal["tasks"]] | NotGiven = NOT_GIVEN,
|
|
528
541
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
|
529
542
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
|
530
543
|
extra_headers: Headers | None = None,
|
|
@@ -558,6 +571,7 @@ class AsyncEvaluationsResource(AsyncAPIResource):
|
|
|
558
571
|
"include_archived": include_archived,
|
|
559
572
|
"limit": limit,
|
|
560
573
|
"starting_after": starting_after,
|
|
574
|
+
"views": views,
|
|
561
575
|
},
|
|
562
576
|
evaluation_list_params.EvaluationListParams,
|
|
563
577
|
),
|
|
@@ -9,6 +9,7 @@ from .completion import Completion as Completion
|
|
|
9
9
|
from .evaluation import Evaluation as Evaluation
|
|
10
10
|
from .dataset_item import DatasetItem as DatasetItem
|
|
11
11
|
from .evaluation_item import EvaluationItem as EvaluationItem
|
|
12
|
+
from .evaluation_task import EvaluationTask as EvaluationTask
|
|
12
13
|
from .inference_model import InferenceModel as InferenceModel
|
|
13
14
|
from .file_list_params import FileListParams as FileListParams
|
|
14
15
|
from .model_list_params import ModelListParams as ModelListParams
|
|
@@ -6,6 +6,7 @@ from typing_extensions import Literal
|
|
|
6
6
|
|
|
7
7
|
from .dataset import Dataset
|
|
8
8
|
from .._models import BaseModel
|
|
9
|
+
from .evaluation_task import EvaluationTask
|
|
9
10
|
|
|
10
11
|
__all__ = ["Evaluation"]
|
|
11
12
|
|
|
@@ -28,3 +29,6 @@ class Evaluation(BaseModel):
|
|
|
28
29
|
description: Optional[str] = None
|
|
29
30
|
|
|
30
31
|
object: Optional[Literal["evaluation"]] = None
|
|
32
|
+
|
|
33
|
+
tasks: Optional[List[EvaluationTask]] = None
|
|
34
|
+
"""Tasks executed during evaluation. Populated with optional `task` view."""
|
{scale_gp_beta-0.1.0a8 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/evaluation_list_params.py
RENAMED
|
@@ -2,8 +2,8 @@
|
|
|
2
2
|
|
|
3
3
|
from __future__ import annotations
|
|
4
4
|
|
|
5
|
-
from typing import Optional
|
|
6
|
-
from typing_extensions import TypedDict
|
|
5
|
+
from typing import List, Optional
|
|
6
|
+
from typing_extensions import Literal, TypedDict
|
|
7
7
|
|
|
8
8
|
__all__ = ["EvaluationListParams"]
|
|
9
9
|
|
|
@@ -16,3 +16,5 @@ class EvaluationListParams(TypedDict, total=False):
|
|
|
16
16
|
limit: int
|
|
17
17
|
|
|
18
18
|
starting_after: Optional[str]
|
|
19
|
+
|
|
20
|
+
views: List[Literal["tasks"]]
|
|
@@ -2,10 +2,13 @@
|
|
|
2
2
|
|
|
3
3
|
from __future__ import annotations
|
|
4
4
|
|
|
5
|
-
from
|
|
5
|
+
from typing import List
|
|
6
|
+
from typing_extensions import Literal, TypedDict
|
|
6
7
|
|
|
7
8
|
__all__ = ["EvaluationRetrieveParams"]
|
|
8
9
|
|
|
9
10
|
|
|
10
11
|
class EvaluationRetrieveParams(TypedDict, total=False):
|
|
11
12
|
include_archived: bool
|
|
13
|
+
|
|
14
|
+
views: List[Literal["tasks"]]
|
|
@@ -0,0 +1,205 @@
|
|
|
1
|
+
# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
|
|
2
|
+
|
|
3
|
+
from typing import TYPE_CHECKING, Dict, List, Union, Optional
|
|
4
|
+
from typing_extensions import Literal, Annotated, TypeAlias
|
|
5
|
+
|
|
6
|
+
from .._utils import PropertyInfo
|
|
7
|
+
from .._models import BaseModel
|
|
8
|
+
|
|
9
|
+
__all__ = [
|
|
10
|
+
"EvaluationTask",
|
|
11
|
+
"ChatCompletionEvaluationTask",
|
|
12
|
+
"ChatCompletionEvaluationTaskConfiguration",
|
|
13
|
+
"GenericInferenceEvaluationTask",
|
|
14
|
+
"GenericInferenceEvaluationTaskConfiguration",
|
|
15
|
+
"GenericInferenceEvaluationTaskConfigurationInferenceConfiguration",
|
|
16
|
+
"GenericInferenceEvaluationTaskConfigurationInferenceConfigurationLaunchInferenceConfiguration",
|
|
17
|
+
"ApplicationVariantV1EvaluationTask",
|
|
18
|
+
"ApplicationVariantV1EvaluationTaskConfiguration",
|
|
19
|
+
"ApplicationVariantV1EvaluationTaskConfigurationHistoryUnionMember0",
|
|
20
|
+
"ApplicationVariantV1EvaluationTaskConfigurationOverrides",
|
|
21
|
+
"ApplicationVariantV1EvaluationTaskConfigurationOverridesAgenticApplicationOverrides",
|
|
22
|
+
"ApplicationVariantV1EvaluationTaskConfigurationOverridesAgenticApplicationOverridesInitialState",
|
|
23
|
+
"ApplicationVariantV1EvaluationTaskConfigurationOverridesAgenticApplicationOverridesPartialTrace",
|
|
24
|
+
]
|
|
25
|
+
|
|
26
|
+
|
|
27
|
+
class ChatCompletionEvaluationTaskConfiguration(BaseModel):
|
|
28
|
+
messages: Union[List[Dict[str, object]], str]
|
|
29
|
+
|
|
30
|
+
model: str
|
|
31
|
+
|
|
32
|
+
audio: Union[Dict[str, object], str, None] = None
|
|
33
|
+
|
|
34
|
+
frequency_penalty: Union[float, str, None] = None
|
|
35
|
+
|
|
36
|
+
function_call: Union[Dict[str, object], str, None] = None
|
|
37
|
+
|
|
38
|
+
functions: Union[List[Dict[str, object]], str, None] = None
|
|
39
|
+
|
|
40
|
+
logit_bias: Union[Dict[str, int], str, None] = None
|
|
41
|
+
|
|
42
|
+
logprobs: Union[bool, str, None] = None
|
|
43
|
+
|
|
44
|
+
max_completion_tokens: Union[int, str, None] = None
|
|
45
|
+
|
|
46
|
+
max_tokens: Union[int, str, None] = None
|
|
47
|
+
|
|
48
|
+
metadata: Union[Dict[str, str], str, None] = None
|
|
49
|
+
|
|
50
|
+
modalities: Union[List[str], str, None] = None
|
|
51
|
+
|
|
52
|
+
n: Union[int, str, None] = None
|
|
53
|
+
|
|
54
|
+
parallel_tool_calls: Union[bool, str, None] = None
|
|
55
|
+
|
|
56
|
+
prediction: Union[Dict[str, object], str, None] = None
|
|
57
|
+
|
|
58
|
+
presence_penalty: Union[float, str, None] = None
|
|
59
|
+
|
|
60
|
+
reasoning_effort: Optional[str] = None
|
|
61
|
+
|
|
62
|
+
response_format: Union[Dict[str, object], str, None] = None
|
|
63
|
+
|
|
64
|
+
seed: Union[int, str, None] = None
|
|
65
|
+
|
|
66
|
+
stop: Optional[str] = None
|
|
67
|
+
|
|
68
|
+
store: Union[bool, str, None] = None
|
|
69
|
+
|
|
70
|
+
temperature: Union[float, str, None] = None
|
|
71
|
+
|
|
72
|
+
tool_choice: Optional[str] = None
|
|
73
|
+
|
|
74
|
+
tools: Union[List[Dict[str, object]], str, None] = None
|
|
75
|
+
|
|
76
|
+
top_k: Union[int, str, None] = None
|
|
77
|
+
|
|
78
|
+
top_logprobs: Union[int, str, None] = None
|
|
79
|
+
|
|
80
|
+
top_p: Union[float, str, None] = None
|
|
81
|
+
|
|
82
|
+
if TYPE_CHECKING:
|
|
83
|
+
# Stub to indicate that arbitrary properties are accepted.
|
|
84
|
+
# To access properties that are not valid identifiers you can use `getattr`, e.g.
|
|
85
|
+
# `getattr(obj, '$type')`
|
|
86
|
+
def __getattr__(self, attr: str) -> object: ...
|
|
87
|
+
|
|
88
|
+
|
|
89
|
+
class ChatCompletionEvaluationTask(BaseModel):
|
|
90
|
+
configuration: ChatCompletionEvaluationTaskConfiguration
|
|
91
|
+
|
|
92
|
+
alias: Optional[str] = None
|
|
93
|
+
"""Alias to title the results column. Defaults to the `task_type`"""
|
|
94
|
+
|
|
95
|
+
task_type: Optional[Literal["chat_completion"]] = None
|
|
96
|
+
|
|
97
|
+
|
|
98
|
+
class GenericInferenceEvaluationTaskConfigurationInferenceConfigurationLaunchInferenceConfiguration(BaseModel):
|
|
99
|
+
num_retries: Optional[int] = None
|
|
100
|
+
|
|
101
|
+
timeout_seconds: Optional[int] = None
|
|
102
|
+
|
|
103
|
+
|
|
104
|
+
GenericInferenceEvaluationTaskConfigurationInferenceConfiguration: TypeAlias = Union[
|
|
105
|
+
GenericInferenceEvaluationTaskConfigurationInferenceConfigurationLaunchInferenceConfiguration, str
|
|
106
|
+
]
|
|
107
|
+
|
|
108
|
+
|
|
109
|
+
class GenericInferenceEvaluationTaskConfiguration(BaseModel):
|
|
110
|
+
model: str
|
|
111
|
+
|
|
112
|
+
args: Union[Dict[str, object], str, None] = None
|
|
113
|
+
|
|
114
|
+
inference_configuration: Optional[GenericInferenceEvaluationTaskConfigurationInferenceConfiguration] = None
|
|
115
|
+
|
|
116
|
+
|
|
117
|
+
class GenericInferenceEvaluationTask(BaseModel):
|
|
118
|
+
configuration: GenericInferenceEvaluationTaskConfiguration
|
|
119
|
+
|
|
120
|
+
alias: Optional[str] = None
|
|
121
|
+
"""Alias to title the results column. Defaults to the `task_type`"""
|
|
122
|
+
|
|
123
|
+
task_type: Optional[Literal["inference"]] = None
|
|
124
|
+
|
|
125
|
+
|
|
126
|
+
class ApplicationVariantV1EvaluationTaskConfigurationHistoryUnionMember0(BaseModel):
|
|
127
|
+
request: str
|
|
128
|
+
"""Request inputs"""
|
|
129
|
+
|
|
130
|
+
response: str
|
|
131
|
+
"""Response outputs"""
|
|
132
|
+
|
|
133
|
+
session_data: Optional[Dict[str, object]] = None
|
|
134
|
+
"""Session data corresponding to the request response pair"""
|
|
135
|
+
|
|
136
|
+
|
|
137
|
+
class ApplicationVariantV1EvaluationTaskConfigurationOverridesAgenticApplicationOverridesInitialState(BaseModel):
|
|
138
|
+
current_node: str
|
|
139
|
+
|
|
140
|
+
state: Dict[str, object]
|
|
141
|
+
|
|
142
|
+
|
|
143
|
+
class ApplicationVariantV1EvaluationTaskConfigurationOverridesAgenticApplicationOverridesPartialTrace(BaseModel):
|
|
144
|
+
duration_ms: int
|
|
145
|
+
|
|
146
|
+
node_id: str
|
|
147
|
+
|
|
148
|
+
operation_input: str
|
|
149
|
+
|
|
150
|
+
operation_output: str
|
|
151
|
+
|
|
152
|
+
operation_type: str
|
|
153
|
+
|
|
154
|
+
start_timestamp: str
|
|
155
|
+
|
|
156
|
+
workflow_id: str
|
|
157
|
+
|
|
158
|
+
operation_metadata: Optional[Dict[str, object]] = None
|
|
159
|
+
|
|
160
|
+
|
|
161
|
+
class ApplicationVariantV1EvaluationTaskConfigurationOverridesAgenticApplicationOverrides(BaseModel):
|
|
162
|
+
concurrent: Optional[bool] = None
|
|
163
|
+
|
|
164
|
+
initial_state: Optional[
|
|
165
|
+
ApplicationVariantV1EvaluationTaskConfigurationOverridesAgenticApplicationOverridesInitialState
|
|
166
|
+
] = None
|
|
167
|
+
|
|
168
|
+
partial_trace: Optional[
|
|
169
|
+
List[ApplicationVariantV1EvaluationTaskConfigurationOverridesAgenticApplicationOverridesPartialTrace]
|
|
170
|
+
] = None
|
|
171
|
+
|
|
172
|
+
use_channels: Optional[bool] = None
|
|
173
|
+
|
|
174
|
+
|
|
175
|
+
ApplicationVariantV1EvaluationTaskConfigurationOverrides: TypeAlias = Union[
|
|
176
|
+
ApplicationVariantV1EvaluationTaskConfigurationOverridesAgenticApplicationOverrides, str
|
|
177
|
+
]
|
|
178
|
+
|
|
179
|
+
|
|
180
|
+
class ApplicationVariantV1EvaluationTaskConfiguration(BaseModel):
|
|
181
|
+
application_variant_id: str
|
|
182
|
+
|
|
183
|
+
inputs: Union[Dict[str, object], str]
|
|
184
|
+
|
|
185
|
+
history: Union[List[ApplicationVariantV1EvaluationTaskConfigurationHistoryUnionMember0], str, None] = None
|
|
186
|
+
|
|
187
|
+
operation_metadata: Union[Dict[str, object], str, None] = None
|
|
188
|
+
|
|
189
|
+
overrides: Optional[ApplicationVariantV1EvaluationTaskConfigurationOverrides] = None
|
|
190
|
+
"""Execution override options for agentic applications"""
|
|
191
|
+
|
|
192
|
+
|
|
193
|
+
class ApplicationVariantV1EvaluationTask(BaseModel):
|
|
194
|
+
configuration: ApplicationVariantV1EvaluationTaskConfiguration
|
|
195
|
+
|
|
196
|
+
alias: Optional[str] = None
|
|
197
|
+
"""Alias to title the results column. Defaults to the `task_type`"""
|
|
198
|
+
|
|
199
|
+
task_type: Optional[Literal["application_variant"]] = None
|
|
200
|
+
|
|
201
|
+
|
|
202
|
+
EvaluationTask: TypeAlias = Annotated[
|
|
203
|
+
Union[ChatCompletionEvaluationTask, GenericInferenceEvaluationTask, ApplicationVariantV1EvaluationTask],
|
|
204
|
+
PropertyInfo(discriminator="task_type"),
|
|
205
|
+
]
|
|
@@ -0,0 +1,206 @@
|
|
|
1
|
+
# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
|
|
2
|
+
|
|
3
|
+
from __future__ import annotations
|
|
4
|
+
|
|
5
|
+
from typing import Dict, List, Union, Iterable
|
|
6
|
+
from typing_extensions import Literal, Required, TypeAlias, TypedDict
|
|
7
|
+
|
|
8
|
+
__all__ = [
|
|
9
|
+
"EvaluationTaskParam",
|
|
10
|
+
"ChatCompletionEvaluationTask",
|
|
11
|
+
"ChatCompletionEvaluationTaskConfiguration",
|
|
12
|
+
"GenericInferenceEvaluationTask",
|
|
13
|
+
"GenericInferenceEvaluationTaskConfiguration",
|
|
14
|
+
"GenericInferenceEvaluationTaskConfigurationInferenceConfiguration",
|
|
15
|
+
"GenericInferenceEvaluationTaskConfigurationInferenceConfigurationLaunchInferenceConfiguration",
|
|
16
|
+
"ApplicationVariantV1EvaluationTask",
|
|
17
|
+
"ApplicationVariantV1EvaluationTaskConfiguration",
|
|
18
|
+
"ApplicationVariantV1EvaluationTaskConfigurationHistoryUnionMember0",
|
|
19
|
+
"ApplicationVariantV1EvaluationTaskConfigurationOverrides",
|
|
20
|
+
"ApplicationVariantV1EvaluationTaskConfigurationOverridesAgenticApplicationOverrides",
|
|
21
|
+
"ApplicationVariantV1EvaluationTaskConfigurationOverridesAgenticApplicationOverridesInitialState",
|
|
22
|
+
"ApplicationVariantV1EvaluationTaskConfigurationOverridesAgenticApplicationOverridesPartialTrace",
|
|
23
|
+
]
|
|
24
|
+
|
|
25
|
+
|
|
26
|
+
class ChatCompletionEvaluationTaskConfigurationTyped(TypedDict, total=False):
|
|
27
|
+
messages: Required[Union[Iterable[Dict[str, object]], str]]
|
|
28
|
+
|
|
29
|
+
model: Required[str]
|
|
30
|
+
|
|
31
|
+
audio: Union[Dict[str, object], str]
|
|
32
|
+
|
|
33
|
+
frequency_penalty: Union[float, str]
|
|
34
|
+
|
|
35
|
+
function_call: Union[Dict[str, object], str]
|
|
36
|
+
|
|
37
|
+
functions: Union[Iterable[Dict[str, object]], str]
|
|
38
|
+
|
|
39
|
+
logit_bias: Union[Dict[str, int], str]
|
|
40
|
+
|
|
41
|
+
logprobs: Union[bool, str]
|
|
42
|
+
|
|
43
|
+
max_completion_tokens: Union[int, str]
|
|
44
|
+
|
|
45
|
+
max_tokens: Union[int, str]
|
|
46
|
+
|
|
47
|
+
metadata: Union[Dict[str, str], str]
|
|
48
|
+
|
|
49
|
+
modalities: Union[List[str], str]
|
|
50
|
+
|
|
51
|
+
n: Union[int, str]
|
|
52
|
+
|
|
53
|
+
parallel_tool_calls: Union[bool, str]
|
|
54
|
+
|
|
55
|
+
prediction: Union[Dict[str, object], str]
|
|
56
|
+
|
|
57
|
+
presence_penalty: Union[float, str]
|
|
58
|
+
|
|
59
|
+
reasoning_effort: str
|
|
60
|
+
|
|
61
|
+
response_format: Union[Dict[str, object], str]
|
|
62
|
+
|
|
63
|
+
seed: Union[int, str]
|
|
64
|
+
|
|
65
|
+
stop: str
|
|
66
|
+
|
|
67
|
+
store: Union[bool, str]
|
|
68
|
+
|
|
69
|
+
temperature: Union[float, str]
|
|
70
|
+
|
|
71
|
+
tool_choice: str
|
|
72
|
+
|
|
73
|
+
tools: Union[Iterable[Dict[str, object]], str]
|
|
74
|
+
|
|
75
|
+
top_k: Union[int, str]
|
|
76
|
+
|
|
77
|
+
top_logprobs: Union[int, str]
|
|
78
|
+
|
|
79
|
+
top_p: Union[float, str]
|
|
80
|
+
|
|
81
|
+
|
|
82
|
+
ChatCompletionEvaluationTaskConfiguration: TypeAlias = Union[
|
|
83
|
+
ChatCompletionEvaluationTaskConfigurationTyped, Dict[str, object]
|
|
84
|
+
]
|
|
85
|
+
|
|
86
|
+
|
|
87
|
+
class ChatCompletionEvaluationTask(TypedDict, total=False):
|
|
88
|
+
configuration: Required[ChatCompletionEvaluationTaskConfiguration]
|
|
89
|
+
|
|
90
|
+
alias: str
|
|
91
|
+
"""Alias to title the results column. Defaults to the `task_type`"""
|
|
92
|
+
|
|
93
|
+
task_type: Literal["chat_completion"]
|
|
94
|
+
|
|
95
|
+
|
|
96
|
+
class GenericInferenceEvaluationTaskConfigurationInferenceConfigurationLaunchInferenceConfiguration(
|
|
97
|
+
TypedDict, total=False
|
|
98
|
+
):
|
|
99
|
+
num_retries: int
|
|
100
|
+
|
|
101
|
+
timeout_seconds: int
|
|
102
|
+
|
|
103
|
+
|
|
104
|
+
GenericInferenceEvaluationTaskConfigurationInferenceConfiguration: TypeAlias = Union[
|
|
105
|
+
GenericInferenceEvaluationTaskConfigurationInferenceConfigurationLaunchInferenceConfiguration, str
|
|
106
|
+
]
|
|
107
|
+
|
|
108
|
+
|
|
109
|
+
class GenericInferenceEvaluationTaskConfiguration(TypedDict, total=False):
|
|
110
|
+
model: Required[str]
|
|
111
|
+
|
|
112
|
+
args: Union[Dict[str, object], str]
|
|
113
|
+
|
|
114
|
+
inference_configuration: GenericInferenceEvaluationTaskConfigurationInferenceConfiguration
|
|
115
|
+
|
|
116
|
+
|
|
117
|
+
class GenericInferenceEvaluationTask(TypedDict, total=False):
|
|
118
|
+
configuration: Required[GenericInferenceEvaluationTaskConfiguration]
|
|
119
|
+
|
|
120
|
+
alias: str
|
|
121
|
+
"""Alias to title the results column. Defaults to the `task_type`"""
|
|
122
|
+
|
|
123
|
+
task_type: Literal["inference"]
|
|
124
|
+
|
|
125
|
+
|
|
126
|
+
class ApplicationVariantV1EvaluationTaskConfigurationHistoryUnionMember0(TypedDict, total=False):
|
|
127
|
+
request: Required[str]
|
|
128
|
+
"""Request inputs"""
|
|
129
|
+
|
|
130
|
+
response: Required[str]
|
|
131
|
+
"""Response outputs"""
|
|
132
|
+
|
|
133
|
+
session_data: Dict[str, object]
|
|
134
|
+
"""Session data corresponding to the request response pair"""
|
|
135
|
+
|
|
136
|
+
|
|
137
|
+
class ApplicationVariantV1EvaluationTaskConfigurationOverridesAgenticApplicationOverridesInitialState(
|
|
138
|
+
TypedDict, total=False
|
|
139
|
+
):
|
|
140
|
+
current_node: Required[str]
|
|
141
|
+
|
|
142
|
+
state: Required[Dict[str, object]]
|
|
143
|
+
|
|
144
|
+
|
|
145
|
+
class ApplicationVariantV1EvaluationTaskConfigurationOverridesAgenticApplicationOverridesPartialTrace(
|
|
146
|
+
TypedDict, total=False
|
|
147
|
+
):
|
|
148
|
+
duration_ms: Required[int]
|
|
149
|
+
|
|
150
|
+
node_id: Required[str]
|
|
151
|
+
|
|
152
|
+
operation_input: Required[str]
|
|
153
|
+
|
|
154
|
+
operation_output: Required[str]
|
|
155
|
+
|
|
156
|
+
operation_type: Required[str]
|
|
157
|
+
|
|
158
|
+
start_timestamp: Required[str]
|
|
159
|
+
|
|
160
|
+
workflow_id: Required[str]
|
|
161
|
+
|
|
162
|
+
operation_metadata: Dict[str, object]
|
|
163
|
+
|
|
164
|
+
|
|
165
|
+
class ApplicationVariantV1EvaluationTaskConfigurationOverridesAgenticApplicationOverrides(TypedDict, total=False):
|
|
166
|
+
concurrent: bool
|
|
167
|
+
|
|
168
|
+
initial_state: ApplicationVariantV1EvaluationTaskConfigurationOverridesAgenticApplicationOverridesInitialState
|
|
169
|
+
|
|
170
|
+
partial_trace: Iterable[
|
|
171
|
+
ApplicationVariantV1EvaluationTaskConfigurationOverridesAgenticApplicationOverridesPartialTrace
|
|
172
|
+
]
|
|
173
|
+
|
|
174
|
+
use_channels: bool
|
|
175
|
+
|
|
176
|
+
|
|
177
|
+
ApplicationVariantV1EvaluationTaskConfigurationOverrides: TypeAlias = Union[
|
|
178
|
+
ApplicationVariantV1EvaluationTaskConfigurationOverridesAgenticApplicationOverrides, str
|
|
179
|
+
]
|
|
180
|
+
|
|
181
|
+
|
|
182
|
+
class ApplicationVariantV1EvaluationTaskConfiguration(TypedDict, total=False):
|
|
183
|
+
application_variant_id: Required[str]
|
|
184
|
+
|
|
185
|
+
inputs: Required[Union[Dict[str, object], str]]
|
|
186
|
+
|
|
187
|
+
history: Union[Iterable[ApplicationVariantV1EvaluationTaskConfigurationHistoryUnionMember0], str]
|
|
188
|
+
|
|
189
|
+
operation_metadata: Union[Dict[str, object], str]
|
|
190
|
+
|
|
191
|
+
overrides: ApplicationVariantV1EvaluationTaskConfigurationOverrides
|
|
192
|
+
"""Execution override options for agentic applications"""
|
|
193
|
+
|
|
194
|
+
|
|
195
|
+
class ApplicationVariantV1EvaluationTask(TypedDict, total=False):
|
|
196
|
+
configuration: Required[ApplicationVariantV1EvaluationTaskConfiguration]
|
|
197
|
+
|
|
198
|
+
alias: str
|
|
199
|
+
"""Alias to title the results column. Defaults to the `task_type`"""
|
|
200
|
+
|
|
201
|
+
task_type: Literal["application_variant"]
|
|
202
|
+
|
|
203
|
+
|
|
204
|
+
EvaluationTaskParam: TypeAlias = Union[
|
|
205
|
+
ChatCompletionEvaluationTask, GenericInferenceEvaluationTask, ApplicationVariantV1EvaluationTask
|
|
206
|
+
]
|
|
@@ -276,6 +276,7 @@ class TestEvaluations:
|
|
|
276
276
|
evaluation = client.evaluations.retrieve(
|
|
277
277
|
evaluation_id="evaluation_id",
|
|
278
278
|
include_archived=True,
|
|
279
|
+
views=["tasks"],
|
|
279
280
|
)
|
|
280
281
|
assert_matches_type(Evaluation, evaluation, path=["response"])
|
|
281
282
|
|
|
@@ -322,6 +323,7 @@ class TestEvaluations:
|
|
|
322
323
|
include_archived=True,
|
|
323
324
|
limit=1,
|
|
324
325
|
starting_after="starting_after",
|
|
326
|
+
views=["tasks"],
|
|
325
327
|
)
|
|
326
328
|
assert_matches_type(SyncCursorPage[Evaluation], evaluation, path=["response"])
|
|
327
329
|
|
|
@@ -642,6 +644,7 @@ class TestAsyncEvaluations:
|
|
|
642
644
|
evaluation = await async_client.evaluations.retrieve(
|
|
643
645
|
evaluation_id="evaluation_id",
|
|
644
646
|
include_archived=True,
|
|
647
|
+
views=["tasks"],
|
|
645
648
|
)
|
|
646
649
|
assert_matches_type(Evaluation, evaluation, path=["response"])
|
|
647
650
|
|
|
@@ -688,6 +691,7 @@ class TestAsyncEvaluations:
|
|
|
688
691
|
include_archived=True,
|
|
689
692
|
limit=1,
|
|
690
693
|
starting_after="starting_after",
|
|
694
|
+
views=["tasks"],
|
|
691
695
|
)
|
|
692
696
|
assert_matches_type(AsyncCursorPage[Evaluation], evaluation, path=["response"])
|
|
693
697
|
|