Python API Reference#
The main entrypoint for using bench is the TestSuite which is used to create new test suites, initiate test runs, and manage suite and run data.
- arthur_bench.client
- Subpackages
- arthur_bench.client.auth
- arthur_bench.client.http
- arthur_bench.client.local
- Submodules
LocalBenchClientLocalBenchClient.create_new_test_run()LocalBenchClient.create_test_suite()LocalBenchClient.delete_test_run()LocalBenchClient.delete_test_suite()LocalBenchClient.get_runs_for_test_suite()LocalBenchClient.get_summary_statistics()LocalBenchClient.get_test_run()LocalBenchClient.get_test_suite()LocalBenchClient.get_test_suite_by_name()LocalBenchClient.get_test_suites()
PageInfo
- Submodules
- arthur_bench.client.rest
- Subpackages
- arthur_bench.client.rest.admin
- Submodules
ArthurAdminClientAuthenticationInfoAuthenticationInfo.emailAuthenticationInfo.external_user_idAuthenticationInfo.first_nameAuthenticationInfo.internal_user_idAuthenticationInfo.issuerAuthenticationInfo.last_nameAuthenticationInfo.organization_idsAuthenticationInfo.rolesAuthenticationInfo.service_account_idAuthenticationInfo.username
LoginRequestUserUserContextUserResponseUserResponse.alert_notifications_enabledUserResponse.contextsUserResponse.created_atUserResponse.emailUserResponse.first_nameUserResponse.help_mode_enabledUserResponse.idUserResponse.last_nameUserResponse.organization_idUserResponse.organization_nameUserResponse.planUserResponse.rolesUserResponse.show_intro_sequenceUserResponse.username
- Submodules
- arthur_bench.client.rest.bench
- Submodules
ArthurBenchClientArthurBenchClient.create_new_test_run()ArthurBenchClient.create_test_suite()ArthurBenchClient.delete_test_run()ArthurBenchClient.delete_test_suite()ArthurBenchClient.get_runs_for_test_suite()ArthurBenchClient.get_summary_statistics()ArthurBenchClient.get_test_run()ArthurBenchClient.get_test_suite()ArthurBenchClient.get_test_suites()ArthurBenchClient.score_hallucination()
- Submodules
- arthur_bench.client.rest.admin
- Submodules
- Subpackages
- Submodules
BenchClientBenchClient.check_run_exists()BenchClient.create_new_test_run()BenchClient.create_test_suite()BenchClient.delete_test_run()BenchClient.delete_test_suite()BenchClient.get_runs_for_test_suite()BenchClient.get_suite_if_exists()BenchClient.get_summary_statistics()BenchClient.get_test_run()BenchClient.get_test_suite()BenchClient.get_test_suites()
- Subpackages
- arthur_bench.client.auth
- arthur_bench.client.http
- arthur_bench.client.local
- Submodules
LocalBenchClientLocalBenchClient.create_new_test_run()LocalBenchClient.create_test_suite()LocalBenchClient.delete_test_run()LocalBenchClient.delete_test_suite()LocalBenchClient.get_runs_for_test_suite()LocalBenchClient.get_summary_statistics()LocalBenchClient.get_test_run()LocalBenchClient.get_test_suite()LocalBenchClient.get_test_suite_by_name()LocalBenchClient.get_test_suites()
PageInfo
- Submodules
- arthur_bench.client.rest
- Subpackages
- arthur_bench.client.rest.admin
- Submodules
ArthurAdminClientAuthenticationInfoAuthenticationInfo.emailAuthenticationInfo.external_user_idAuthenticationInfo.first_nameAuthenticationInfo.internal_user_idAuthenticationInfo.issuerAuthenticationInfo.last_nameAuthenticationInfo.organization_idsAuthenticationInfo.rolesAuthenticationInfo.service_account_idAuthenticationInfo.username
LoginRequestUserUserContextUserResponseUserResponse.alert_notifications_enabledUserResponse.contextsUserResponse.created_atUserResponse.emailUserResponse.first_nameUserResponse.help_mode_enabledUserResponse.idUserResponse.last_nameUserResponse.organization_idUserResponse.organization_nameUserResponse.planUserResponse.rolesUserResponse.show_intro_sequenceUserResponse.username
- Submodules
- arthur_bench.client.rest.bench
- Submodules
ArthurBenchClientArthurBenchClient.create_new_test_run()ArthurBenchClient.create_test_suite()ArthurBenchClient.delete_test_run()ArthurBenchClient.delete_test_suite()ArthurBenchClient.get_runs_for_test_suite()ArthurBenchClient.get_summary_statistics()ArthurBenchClient.get_test_run()ArthurBenchClient.get_test_suite()ArthurBenchClient.get_test_suites()ArthurBenchClient.score_hallucination()
- Submodules
- arthur_bench.client.rest.admin
- Submodules
- Subpackages
- arthur_bench.client.rest.admin
- Submodules
ArthurAdminClientAuthenticationInfoAuthenticationInfo.emailAuthenticationInfo.external_user_idAuthenticationInfo.first_nameAuthenticationInfo.internal_user_idAuthenticationInfo.issuerAuthenticationInfo.last_nameAuthenticationInfo.organization_idsAuthenticationInfo.rolesAuthenticationInfo.service_account_idAuthenticationInfo.username
LoginRequestUserUserContextUserResponseUserResponse.alert_notifications_enabledUserResponse.contextsUserResponse.created_atUserResponse.emailUserResponse.first_nameUserResponse.help_mode_enabledUserResponse.idUserResponse.last_nameUserResponse.organization_idUserResponse.organization_nameUserResponse.planUserResponse.rolesUserResponse.show_intro_sequenceUserResponse.username
- Submodules
- arthur_bench.client.rest.bench
- Submodules
ArthurBenchClientArthurBenchClient.create_new_test_run()ArthurBenchClient.create_test_suite()ArthurBenchClient.delete_test_run()ArthurBenchClient.delete_test_suite()ArthurBenchClient.get_runs_for_test_suite()ArthurBenchClient.get_summary_statistics()ArthurBenchClient.get_test_run()ArthurBenchClient.get_test_suite()ArthurBenchClient.get_test_suites()ArthurBenchClient.score_hallucination()
- Submodules
- arthur_bench.exceptions
- Submodules
ArthurErrorArthurInternalErrorArthurUserErrorExpectedParameterNotFoundErrorForbiddenErrorInternalTypeErrorInternalValueErrorMethodNotApplicableErrorMissingParameterErrorNotFoundErrorPaymentRequiredErrorResponseClientErrorResponseRedirectErrorResponseServerErrorUnauthorizedErrorUserTypeErrorUserValueErrorarthur_excepted()
- Submodules
- arthur_bench.models
- Submodules
CategoricalHistogramItemCategoryCommonSortEnumCreateRunRequestCreateRunResponseHistogramItemPaginatedRunPaginatedRunsPaginatedTestSuitePaginatedTestSuite.created_atPaginatedTestSuite.descriptionPaginatedTestSuite.idPaginatedTestSuite.last_run_timePaginatedTestSuite.namePaginatedTestSuite.num_runsPaginatedTestSuite.pagePaginatedTestSuite.page_sizePaginatedTestSuite.scoring_methodPaginatedTestSuite.test_casesPaginatedTestSuite.total_countPaginatedTestSuite.total_pagesPaginatedTestSuite.updated_at
PaginatedTestSuitesRunResultScoreResultScorerOutputTypeScoringMethodScoringMethodTypeSummaryItemTestCaseOutputTestCaseRequestTestCaseResponseTestCaseSortEnumTestRunMetadataTestRunSortEnumTestSuiteMetadataTestSuiteRequestTestSuiteSortEnumTestSuiteSummaryHallucinationScoreRequestHallucinationScoreResponse
- Submodules
- arthur_bench.run
- arthur_bench.scoring
ScoringMethodNameScoringMethodName.BERTScoreScoringMethodName.ExactMatchScoringMethodName.HallucinationScoringMethodName.HedgingLanguageScoringMethodName.PythonUnitTestingScoringMethodName.QACorrectnessScoringMethodName.ReadabilityScoringMethodName.SpecificityScoringMethodName.SummaryQualityScoringMethodName.WordCountMatch
scorer_from_string()- Submodules
- arthur_bench.server
- arthur_bench.telemetry
- arthur_bench.utils