Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/alphadl/AdaRubrics
/ functions
Functions
213 in github.com/alphadl/AdaRubrics
⨍
Functions
213
◇
Types & classes
73
Method
generate_text
( self, messages: list[dict[str, str]], *, temperature: float = 0.0, m
adarubric/llm/openai_client.py:166
Method
generate_text
( self, messages: list[dict[str, str]], *, temperature: float = 0.0, m
tests/conftest.py:59
Method
is_reliable
Whether global alpha indicates good reliability (>= 0.80).
adarubric/analysis/reliability.py:117
Method
is_tentative
Whether global alpha is in the tentative range [0.67, 0.80).
adarubric/analysis/reliability.py:122
Method
mean_margin
(self)
adarubric/reward/scalers.py:204
Method
mean_score
(self)
adarubric/pipeline.py:83
Method
mean_score
(self)
adarubric/core/models.py:160
Function
mock_llm_client
(mock_rubric_response: str)
tests/conftest.py:291
Function
mock_rubric_response
(sample_rubric: DynamicRubric)
tests/conftest.py:286
Method
run_sync
Synchronous wrapper for :meth:`run`. Creates a new event loop per call. Prefer :meth:`run` in async code to reuse an existing loop (e
adarubric/pipeline.py:405
Function
sample_evaluation
(sample_rubric: DynamicRubric)
tests/conftest.py:208
Function
sample_rubric
()
tests/conftest.py:95
Function
sample_task
()
tests/conftest.py:77
Function
sample_trajectory
()
tests/conftest.py:171
Method
score_gap
(self)
adarubric/reward/scalers.py:189
Method
summary
(self)
adarubric/analysis/reliability.py:126
Method
survival_rate
(self)
adarubric/pipeline.py:77
Method
test_all_must_pass
(self)
tests/test_filter.py:148
Method
test_all_same
(self)
tests/test_evaluator.py:156
Method
test_basic_assignment
(self)
tests/test_reward.py:127
Method
test_boundary_inclusive
(self)
tests/test_filter.py:55
Method
test_clamping
(self)
tests/test_reward.py:88
Method
test_confidence_weighting
(self)
tests/test_evaluator.py:99
Method
test_custom_dimension_thresholds
(self)
tests/test_filter.py:117
Method
test_custom_range
(self)
tests/test_reward.py:82
Method
test_default_eval_max_tokens_resolution
(self)
tests/test_config.py:66
Method
test_default_range
(self)
tests/test_reward.py:75
Method
test_default_rubric_max_tokens_resolution
(self)
tests/test_config.py:59
Method
test_default_token_helpers_without_config
(self)
tests/test_config.py:73
Method
test_defaults
(self)
tests/test_config.py:52
Method
test_dimension_names
(self, sample_rubric: DynamicRubric)
tests/test_models.py:121
Method
test_duplicate_step_ids_rejected
(self)
tests/test_models.py:73
Method
test_empty
(self)
tests/test_reward.py:122
Method
test_empty_action_rejected
(self)
tests/test_models.py:49
Method
test_empty_dimension_scores_fail
(self)
tests/test_filter.py:126
Method
test_empty_filters_rejected
(self)
tests/test_filter.py:164
Method
test_empty_input
(self)
tests/test_filter.py:82
Method
test_empty_instruction_rejected
(self)
tests/test_models.py:24
Method
test_empty_scores_mean
(self)
tests/test_models.py:149
Method
test_empty_steps
(self)
tests/test_reward.py:147
Method
test_empty_steps
(self)
tests/test_evaluator.py:110
Method
test_empty_steps_rejected
(self)
tests/test_models.py:69
Method
test_env_override
(self, tmp_path, monkeypatch)
tests/test_config.py:77
Method
test_equal_scores
(self)
tests/test_evaluator.py:119
Method
test_export
(self, tmp_dir)
tests/test_io.py:96
Method
test_extra_criteria_key_rejected
(self)
tests/test_models.py:111
Method
test_fails_on_low_dimension
(self)
tests/test_filter.py:106
Function
test_fenced_json_block
()
tests/test_json_extract.py:8
Function
test_few_shot_excluded
(mock_llm_client: MockLLMClient, sample_task: TaskDescription)
tests/test_generator.py:51
Function
test_few_shot_included_in_prompt
( mock_llm_client: MockLLMClient, sample_task: TaskDescription )
tests/test_generator.py:41
Method
test_filters_below_threshold
(self)
tests/test_filter.py:47
Method
test_final_step_bonus
(self)
tests/test_reward.py:134
Method
test_fixed_baseline
(self)
tests/test_reward.py:106
Method
test_from_json
(self, tmp_path)
tests/test_config.py:12
Method
test_full_creation
(self)
tests/test_models.py:28
Function
test_full_pipeline
( mock_llm_client: MockLLMClient, sample_task: TaskDescription, sample_trajectory: Trajectory, )
tests/test_pipeline.py:18
Function
test_generate_respects_max_tokens
( mock_llm_client: MockLLMClient, sample_task: TaskDescription, )
tests/test_generator.py:59
Function
test_generate_rubric
(mock_llm_client: MockLLMClient, sample_task: TaskDescription)
tests/test_generator.py:15
Function
test_generate_rubric_fixes_task_id
(mock_llm_client: MockLLMClient)
tests/test_generator.py:24
Function
test_generate_rubric_llm_failure
()
tests/test_generator.py:32
Method
test_generates_pairs
(self)
tests/test_reward.py:153
Method
test_get_dimension
(self, sample_rubric: DynamicRubric)
tests/test_models.py:129
Method
test_get_nonexistent_dimension
(self, sample_rubric: DynamicRubric)
tests/test_models.py:134
Method
test_invalid_margin
(self)
tests/test_reward.py:186
Method
test_invalid_range
(self)
tests/test_reward.py:93
Method
test_invalid_threshold_rejected
(self)
tests/test_filter.py:60
Function
test_llm_evaluator_max_tokens
( mock_llm_client: MockLLMClient, sample_trajectory, sample_rubric, )
tests/test_evaluator.py:169
Method
test_margin_filtering
(self)
tests/test_reward.py:166
Method
test_max_pairs_per_chosen
(self)
tests/test_reward.py:172
Method
test_mean_baseline
(self)
tests/test_reward.py:99
Method
test_mean_score
(self)
tests/test_models.py:139
Method
test_median_baseline
(self)
tests/test_reward.py:112
Method
test_min_survivors
(self)
tests/test_filter.py:77
Method
test_minimal_creation
(self)
tests/test_models.py:19
Method
test_missing_criteria_key_rejected
(self)
tests/test_models.py:103
Method
test_multi_step_averaging
(self)
tests/test_evaluator.py:74
Function
test_nested_braces
()
tests/test_json_extract.py:17
Method
test_no_agreement
(self)
tests/test_analysis.py:23
Method
test_non_monotonic_step_ids_rejected
(self)
tests/test_models.py:83
Method
test_non_uniform_weights
(self)
tests/test_evaluator.py:63
Method
test_normalize
(self)
tests/test_reward.py:140
Method
test_partial_agreement
(self)
tests/test_analysis.py:29
Method
test_penalizes_low_outlier
(self)
tests/test_evaluator.py:130
Method
test_perfect_agreement
(self)
tests/test_analysis.py:12
Function
test_pipeline_filtering
( mock_llm_client: MockLLMClient, sample_task: TaskDescription, sample_trajectory: Trajectory, )
tests/test_pipeline.py:54
Function
test_pipeline_generate_rubric_uses_config_max_tokens
( mock_llm_client: MockLLMClient, sample_task: TaskDescription, )
tests/test_pipeline.py:85
Function
test_pipeline_run_passes_eval_max_tokens
( mock_llm_client: MockLLMClient, sample_task: TaskDescription, sample_trajectory: Trajectory,
tests/test_pipeline.py:103
Function
test_pipeline_with_prebuilt_rubric
( mock_llm_client: MockLLMClient, sample_task: TaskDescription, sample_trajectory: Trajectory,
tests/test_pipeline.py:36
Function
test_plain_object
()
tests/test_json_extract.py:13
Method
test_recency_decay
(self)
tests/test_evaluator.py:87
Method
test_rejects_missing_rubric_dimension_score
(self)
tests/test_filter.py:137
Method
test_reliability_thresholds
(self)
tests/test_analysis.py:63
Method
test_roundtrip
(self, tmp_dir)
tests/test_io.py:65
Method
test_roundtrip
(self, tmp_dir)
tests/test_io.py:86
Function
test_run_requires_non_empty_trajectories
( mock_llm_client: MockLLMClient, sample_task: TaskDescription, )
tests/test_pipeline.py:71
Method
test_score_for
(self)
tests/test_models.py:153
Method
test_single_item_returns_nan
(self)
tests/test_analysis.py:40
Method
test_single_rater_returns_nan
(self)
tests/test_analysis.py:45
Method
test_skips_malformed_lines
(self, tmp_dir)
tests/test_io.py:74
Method
test_takes_minimum
(self)
tests/test_evaluator.py:145
← previous
next →
101–200 of 213, ranked by callers