scale-gp-beta 0.1.0a7__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-0.1.0a7 → scale_gp_beta-0.1.0a9}/CHANGELOG.md +18 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/PKG-INFO +1 -1
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/api.md +1 -1
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/pyproject.toml +1 -1
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_version.py +1 -1
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/evaluations.py +27 -12
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/__init__.py +2 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/evaluation.py +4 -0
- scale_gp_beta-0.1.0a9/src/scale_gp_beta/types/evaluation_create_params.py +85 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/evaluation_list_params.py +4 -2
- {scale_gp_beta-0.1.0a7 → 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-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/api_resources/test_evaluations.py +4 -0
- scale_gp_beta-0.1.0a7/.release-please-manifest.json +0 -3
- scale_gp_beta-0.1.0a7/src/scale_gp_beta/types/evaluation_create_params.py +0 -734
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/.gitignore +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/CONTRIBUTING.md +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/LICENSE +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/README.md +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/SECURITY.md +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/bin/check-release-environment +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/bin/publish-pypi +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/examples/.keep +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/mypy.ini +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/noxfile.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/release-please-config.json +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/requirements-dev.lock +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/requirements.lock +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp/lib/.keep +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/__init__.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_base_client.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_client.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_compat.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_constants.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_exceptions.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_files.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_models.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_qs.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_resource.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_response.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_streaming.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_types.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_utils/__init__.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_utils/_logs.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_utils/_proxy.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_utils/_reflection.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_utils/_streams.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_utils/_sync.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_utils/_transform.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_utils/_typing.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/_utils/_utils.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/lib/.keep +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/pagination.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/py.typed +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/__init__.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/chat/__init__.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/chat/chat.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/chat/completions.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/completions.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/dataset_items.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/datasets.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/evaluation_items.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/files/__init__.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/files/content.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/files/files.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/inference.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/resources/models.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/chat/__init__.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/chat/chat_completion.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/chat/chat_completion_chunk.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/chat/completion_create_params.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/chat/completion_create_response.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/completion.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/completion_create_params.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset_create_params.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset_delete_response.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset_item.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset_item_batch_create_params.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset_item_batch_create_response.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset_item_delete_response.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset_item_list_params.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset_item_retrieve_params.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset_item_update_params.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset_list_params.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset_retrieve_params.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/dataset_update_params.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/evaluation_archive_response.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/evaluation_item.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/evaluation_item_list_params.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/evaluation_item_retrieve_params.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/file.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/file_create_params.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/file_delete_response.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/file_list.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/file_list_params.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/file_update_params.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/files/__init__.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/inference_create_params.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/inference_create_response.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/inference_model.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/inference_model_list.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/inference_response.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/inference_response_chunk.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/model_create_params.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/model_delete_response.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/model_list_params.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/scale_gp_beta/types/model_update_params.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/src/sgp_dev/lib/.keep +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/__init__.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/api_resources/__init__.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/api_resources/chat/__init__.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/api_resources/chat/test_completions.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/api_resources/files/__init__.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/api_resources/files/test_content.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/api_resources/test_completions.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/api_resources/test_dataset_items.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/api_resources/test_datasets.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/api_resources/test_evaluation_items.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/api_resources/test_files.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/api_resources/test_inference.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/api_resources/test_models.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/conftest.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/sample_file.txt +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/test_client.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/test_deepcopy.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/test_extract_files.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/test_files.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/test_models.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/test_qs.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/test_required_args.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/test_response.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/test_streaming.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/test_transform.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/test_utils/test_proxy.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/test_utils/test_typing.py +0 -0
- {scale_gp_beta-0.1.0a7 → scale_gp_beta-0.1.0a9}/tests/utils.py +0 -0
|
@@ -1,5 +1,23 @@
|
|
|
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
|
+
|
|
12
|
+
## 0.1.0-alpha.8 (2025-03-26)
|
|
13
|
+
|
|
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)
|
|
15
|
+
|
|
16
|
+
### Features
|
|
17
|
+
|
|
18
|
+
* **api:** manual updates ([#83](https://github.com/scaleapi/sgp-python-beta/issues/83)) ([a742789](https://github.com/scaleapi/sgp-python-beta/commit/a74278982def1c9ce87d1568cc3e6f65c992ec8b))
|
|
19
|
+
* **api:** manual updates ([#85](https://github.com/scaleapi/sgp-python-beta/issues/85)) ([de471f9](https://github.com/scaleapi/sgp-python-beta/commit/de471f973d6dfd512841ec7af8b762da4c1c9ade))
|
|
20
|
+
|
|
3
21
|
## 0.1.0-alpha.7 (2025-03-26)
|
|
4
22
|
|
|
5
23
|
Full Changelog: [v0.1.0-alpha.6...v0.1.0-alpha.7](https://github.com/scaleapi/sgp-python-beta/compare/v0.1.0-alpha.6...v0.1.0-alpha.7)
|
|
@@ -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
|
|
|
@@ -25,6 +25,7 @@ from .._response import (
|
|
|
25
25
|
from ..pagination import SyncCursorPage, AsyncCursorPage
|
|
26
26
|
from .._base_client import AsyncPaginator, make_request_options
|
|
27
27
|
from ..types.evaluation import Evaluation
|
|
28
|
+
from ..types.evaluation_task_param import EvaluationTaskParam
|
|
28
29
|
from ..types.evaluation_archive_response import EvaluationArchiveResponse
|
|
29
30
|
|
|
30
31
|
__all__ = ["EvaluationsResource", "AsyncEvaluationsResource"]
|
|
@@ -57,7 +58,7 @@ class EvaluationsResource(SyncAPIResource):
|
|
|
57
58
|
data: Iterable[Dict[str, object]],
|
|
58
59
|
name: str,
|
|
59
60
|
description: str | NotGiven = NOT_GIVEN,
|
|
60
|
-
tasks: Iterable[
|
|
61
|
+
tasks: Iterable[EvaluationTaskParam] | NotGiven = NOT_GIVEN,
|
|
61
62
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
|
62
63
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
|
63
64
|
extra_headers: Headers | None = None,
|
|
@@ -91,7 +92,7 @@ class EvaluationsResource(SyncAPIResource):
|
|
|
91
92
|
name: str,
|
|
92
93
|
data: Iterable[evaluation_create_params.EvaluationFromDatasetCreateRequestData] | NotGiven = NOT_GIVEN,
|
|
93
94
|
description: str | NotGiven = NOT_GIVEN,
|
|
94
|
-
tasks: Iterable[
|
|
95
|
+
tasks: Iterable[EvaluationTaskParam] | NotGiven = NOT_GIVEN,
|
|
95
96
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
|
96
97
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
|
97
98
|
extra_headers: Headers | None = None,
|
|
@@ -127,7 +128,7 @@ class EvaluationsResource(SyncAPIResource):
|
|
|
127
128
|
dataset: evaluation_create_params.EvaluationWithDatasetCreateRequestDataset,
|
|
128
129
|
name: str,
|
|
129
130
|
description: str | NotGiven = NOT_GIVEN,
|
|
130
|
-
tasks: Iterable[
|
|
131
|
+
tasks: Iterable[EvaluationTaskParam] | NotGiven = NOT_GIVEN,
|
|
131
132
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
|
132
133
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
|
133
134
|
extra_headers: Headers | None = None,
|
|
@@ -164,7 +165,7 @@ class EvaluationsResource(SyncAPIResource):
|
|
|
164
165
|
| NotGiven = NOT_GIVEN,
|
|
165
166
|
name: str,
|
|
166
167
|
description: str | NotGiven = NOT_GIVEN,
|
|
167
|
-
tasks: Iterable[
|
|
168
|
+
tasks: Iterable[EvaluationTaskParam] | NotGiven = NOT_GIVEN,
|
|
168
169
|
dataset_id: str | NotGiven = NOT_GIVEN,
|
|
169
170
|
dataset: evaluation_create_params.EvaluationWithDatasetCreateRequestDataset | NotGiven = NOT_GIVEN,
|
|
170
171
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
|
@@ -198,6 +199,7 @@ class EvaluationsResource(SyncAPIResource):
|
|
|
198
199
|
evaluation_id: str,
|
|
199
200
|
*,
|
|
200
201
|
include_archived: bool | NotGiven = NOT_GIVEN,
|
|
202
|
+
views: List[Literal["tasks"]] | NotGiven = NOT_GIVEN,
|
|
201
203
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
|
202
204
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
|
203
205
|
extra_headers: Headers | None = None,
|
|
@@ -227,7 +229,11 @@ class EvaluationsResource(SyncAPIResource):
|
|
|
227
229
|
extra_body=extra_body,
|
|
228
230
|
timeout=timeout,
|
|
229
231
|
query=maybe_transform(
|
|
230
|
-
{
|
|
232
|
+
{
|
|
233
|
+
"include_archived": include_archived,
|
|
234
|
+
"views": views,
|
|
235
|
+
},
|
|
236
|
+
evaluation_retrieve_params.EvaluationRetrieveParams,
|
|
231
237
|
),
|
|
232
238
|
),
|
|
233
239
|
cast_to=Evaluation,
|
|
@@ -240,6 +246,7 @@ class EvaluationsResource(SyncAPIResource):
|
|
|
240
246
|
include_archived: bool | NotGiven = NOT_GIVEN,
|
|
241
247
|
limit: int | NotGiven = NOT_GIVEN,
|
|
242
248
|
starting_after: Optional[str] | NotGiven = NOT_GIVEN,
|
|
249
|
+
views: List[Literal["tasks"]] | NotGiven = NOT_GIVEN,
|
|
243
250
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
|
244
251
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
|
245
252
|
extra_headers: Headers | None = None,
|
|
@@ -273,6 +280,7 @@ class EvaluationsResource(SyncAPIResource):
|
|
|
273
280
|
"include_archived": include_archived,
|
|
274
281
|
"limit": limit,
|
|
275
282
|
"starting_after": starting_after,
|
|
283
|
+
"views": views,
|
|
276
284
|
},
|
|
277
285
|
evaluation_list_params.EvaluationListParams,
|
|
278
286
|
),
|
|
@@ -341,7 +349,7 @@ class AsyncEvaluationsResource(AsyncAPIResource):
|
|
|
341
349
|
data: Iterable[Dict[str, object]],
|
|
342
350
|
name: str,
|
|
343
351
|
description: str | NotGiven = NOT_GIVEN,
|
|
344
|
-
tasks: Iterable[
|
|
352
|
+
tasks: Iterable[EvaluationTaskParam] | NotGiven = NOT_GIVEN,
|
|
345
353
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
|
346
354
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
|
347
355
|
extra_headers: Headers | None = None,
|
|
@@ -375,7 +383,7 @@ class AsyncEvaluationsResource(AsyncAPIResource):
|
|
|
375
383
|
name: str,
|
|
376
384
|
data: Iterable[evaluation_create_params.EvaluationFromDatasetCreateRequestData] | NotGiven = NOT_GIVEN,
|
|
377
385
|
description: str | NotGiven = NOT_GIVEN,
|
|
378
|
-
tasks: Iterable[
|
|
386
|
+
tasks: Iterable[EvaluationTaskParam] | NotGiven = NOT_GIVEN,
|
|
379
387
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
|
380
388
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
|
381
389
|
extra_headers: Headers | None = None,
|
|
@@ -411,7 +419,7 @@ class AsyncEvaluationsResource(AsyncAPIResource):
|
|
|
411
419
|
dataset: evaluation_create_params.EvaluationWithDatasetCreateRequestDataset,
|
|
412
420
|
name: str,
|
|
413
421
|
description: str | NotGiven = NOT_GIVEN,
|
|
414
|
-
tasks: Iterable[
|
|
422
|
+
tasks: Iterable[EvaluationTaskParam] | NotGiven = NOT_GIVEN,
|
|
415
423
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
|
416
424
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
|
417
425
|
extra_headers: Headers | None = None,
|
|
@@ -448,7 +456,7 @@ class AsyncEvaluationsResource(AsyncAPIResource):
|
|
|
448
456
|
| NotGiven = NOT_GIVEN,
|
|
449
457
|
name: str,
|
|
450
458
|
description: str | NotGiven = NOT_GIVEN,
|
|
451
|
-
tasks: Iterable[
|
|
459
|
+
tasks: Iterable[EvaluationTaskParam] | NotGiven = NOT_GIVEN,
|
|
452
460
|
dataset_id: str | NotGiven = NOT_GIVEN,
|
|
453
461
|
dataset: evaluation_create_params.EvaluationWithDatasetCreateRequestDataset | NotGiven = NOT_GIVEN,
|
|
454
462
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
|
@@ -482,6 +490,7 @@ class AsyncEvaluationsResource(AsyncAPIResource):
|
|
|
482
490
|
evaluation_id: str,
|
|
483
491
|
*,
|
|
484
492
|
include_archived: bool | NotGiven = NOT_GIVEN,
|
|
493
|
+
views: List[Literal["tasks"]] | NotGiven = NOT_GIVEN,
|
|
485
494
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
|
486
495
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
|
487
496
|
extra_headers: Headers | None = None,
|
|
@@ -511,7 +520,11 @@ class AsyncEvaluationsResource(AsyncAPIResource):
|
|
|
511
520
|
extra_body=extra_body,
|
|
512
521
|
timeout=timeout,
|
|
513
522
|
query=await async_maybe_transform(
|
|
514
|
-
{
|
|
523
|
+
{
|
|
524
|
+
"include_archived": include_archived,
|
|
525
|
+
"views": views,
|
|
526
|
+
},
|
|
527
|
+
evaluation_retrieve_params.EvaluationRetrieveParams,
|
|
515
528
|
),
|
|
516
529
|
),
|
|
517
530
|
cast_to=Evaluation,
|
|
@@ -524,6 +537,7 @@ class AsyncEvaluationsResource(AsyncAPIResource):
|
|
|
524
537
|
include_archived: bool | NotGiven = NOT_GIVEN,
|
|
525
538
|
limit: int | NotGiven = NOT_GIVEN,
|
|
526
539
|
starting_after: Optional[str] | NotGiven = NOT_GIVEN,
|
|
540
|
+
views: List[Literal["tasks"]] | NotGiven = NOT_GIVEN,
|
|
527
541
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
|
528
542
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
|
529
543
|
extra_headers: Headers | None = None,
|
|
@@ -557,6 +571,7 @@ class AsyncEvaluationsResource(AsyncAPIResource):
|
|
|
557
571
|
"include_archived": include_archived,
|
|
558
572
|
"limit": limit,
|
|
559
573
|
"starting_after": starting_after,
|
|
574
|
+
"views": views,
|
|
560
575
|
},
|
|
561
576
|
evaluation_list_params.EvaluationListParams,
|
|
562
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
|
|
@@ -22,6 +23,7 @@ from .file_delete_response import FileDeleteResponse as FileDeleteResponse
|
|
|
22
23
|
from .inference_model_list import InferenceModelList as InferenceModelList
|
|
23
24
|
from .dataset_create_params import DatasetCreateParams as DatasetCreateParams
|
|
24
25
|
from .dataset_update_params import DatasetUpdateParams as DatasetUpdateParams
|
|
26
|
+
from .evaluation_task_param import EvaluationTaskParam as EvaluationTaskParam
|
|
25
27
|
from .model_delete_response import ModelDeleteResponse as ModelDeleteResponse
|
|
26
28
|
from .evaluation_list_params import EvaluationListParams as EvaluationListParams
|
|
27
29
|
from .dataset_delete_response import DatasetDeleteResponse as DatasetDeleteResponse
|
|
@@ -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."""
|
|
@@ -0,0 +1,85 @@
|
|
|
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 Required, TypeAlias, TypedDict
|
|
7
|
+
|
|
8
|
+
from .evaluation_task_param import EvaluationTaskParam
|
|
9
|
+
|
|
10
|
+
__all__ = [
|
|
11
|
+
"EvaluationCreateParams",
|
|
12
|
+
"EvaluationStandaloneCreateRequest",
|
|
13
|
+
"EvaluationFromDatasetCreateRequest",
|
|
14
|
+
"EvaluationFromDatasetCreateRequestData",
|
|
15
|
+
"EvaluationWithDatasetCreateRequest",
|
|
16
|
+
"EvaluationWithDatasetCreateRequestDataset",
|
|
17
|
+
]
|
|
18
|
+
|
|
19
|
+
|
|
20
|
+
class EvaluationStandaloneCreateRequest(TypedDict, total=False):
|
|
21
|
+
data: Required[Iterable[Dict[str, object]]]
|
|
22
|
+
"""Items to be evaluated"""
|
|
23
|
+
|
|
24
|
+
name: Required[str]
|
|
25
|
+
|
|
26
|
+
description: str
|
|
27
|
+
|
|
28
|
+
tasks: Iterable[EvaluationTaskParam]
|
|
29
|
+
"""Tasks allow you to augment and evaluate your data"""
|
|
30
|
+
|
|
31
|
+
|
|
32
|
+
class EvaluationFromDatasetCreateRequest(TypedDict, total=False):
|
|
33
|
+
dataset_id: Required[str]
|
|
34
|
+
"""The ID of the dataset containing the items referenced by the `data` field"""
|
|
35
|
+
|
|
36
|
+
name: Required[str]
|
|
37
|
+
|
|
38
|
+
data: Iterable[EvaluationFromDatasetCreateRequestData]
|
|
39
|
+
"""Items to be evaluated, including references to the input dataset items"""
|
|
40
|
+
|
|
41
|
+
description: str
|
|
42
|
+
|
|
43
|
+
tasks: Iterable[EvaluationTaskParam]
|
|
44
|
+
"""Tasks allow you to augment and evaluate your data"""
|
|
45
|
+
|
|
46
|
+
|
|
47
|
+
class EvaluationFromDatasetCreateRequestDataTyped(TypedDict, total=False):
|
|
48
|
+
dataset_item_id: Required[str]
|
|
49
|
+
|
|
50
|
+
|
|
51
|
+
EvaluationFromDatasetCreateRequestData: TypeAlias = Union[
|
|
52
|
+
EvaluationFromDatasetCreateRequestDataTyped, Dict[str, object]
|
|
53
|
+
]
|
|
54
|
+
|
|
55
|
+
|
|
56
|
+
class EvaluationWithDatasetCreateRequest(TypedDict, total=False):
|
|
57
|
+
data: Required[Iterable[Dict[str, object]]]
|
|
58
|
+
"""Items to be evaluated"""
|
|
59
|
+
|
|
60
|
+
dataset: Required[EvaluationWithDatasetCreateRequestDataset]
|
|
61
|
+
"""Create a reusable dataset from items in the `data` field"""
|
|
62
|
+
|
|
63
|
+
name: Required[str]
|
|
64
|
+
|
|
65
|
+
description: str
|
|
66
|
+
|
|
67
|
+
tasks: Iterable[EvaluationTaskParam]
|
|
68
|
+
"""Tasks allow you to augment and evaluate your data"""
|
|
69
|
+
|
|
70
|
+
|
|
71
|
+
class EvaluationWithDatasetCreateRequestDataset(TypedDict, total=False):
|
|
72
|
+
name: Required[str]
|
|
73
|
+
|
|
74
|
+
description: str
|
|
75
|
+
|
|
76
|
+
keys: List[str]
|
|
77
|
+
"""Keys from items in the `data` field that should be included in the dataset.
|
|
78
|
+
|
|
79
|
+
If not provided, all keys will be included.
|
|
80
|
+
"""
|
|
81
|
+
|
|
82
|
+
|
|
83
|
+
EvaluationCreateParams: TypeAlias = Union[
|
|
84
|
+
EvaluationStandaloneCreateRequest, EvaluationFromDatasetCreateRequest, EvaluationWithDatasetCreateRequest
|
|
85
|
+
]
|
{scale_gp_beta-0.1.0a7 → 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
|
+
]
|