MCPcopy Create free account

hub / github.com/Codium-ai/AlphaCodium / functions

Functions176 in github.com/Codium-ai/AlphaCodium

⨍ Functions 176◇ Types & classes 108↳ Endpoints 2
↓ 62 callersFunctionget_settings
()
alpha_codium/settings/config_loader.py:24
↓ 28 callersFunctionget_logger
(*args, **kwargs)
alpha_codium/log/__init__.py:44
↓ 12 callersFunctionsend_inference
(f: Callable)
alpha_codium/llm/ai_invoker.py:8
↓ 10 callersFunctionevaluate_solution_on_subset
(evaluation_test_type, problem, solution, silent=False, break_on_timeout=True)
alpha_codium/gen/utils.py:48
↓ 8 callersMethodto_dict
Converts the ProxyException instance to a dictionary.
alpha_codium/litellm/proxy/_types.py:1693
↓ 7 callersFunctionrun_tests
(self, problem, counter, test_inputs, test_outputs)
alpha_codium/gen/stages/run_tests.py:11
↓ 4 callersFunctionload_yaml
(response_text: str, keys_fix_yaml: List[str] = [])
alpha_codium/gen/utils.py:121
↓ 4 callersFunctionsetup_logger
(logger_path: str = "./example.log", level: str = "INFO", fmt: LoggingFormat
alpha_codium/log/__init__.py:18
↓ 3 callersFunctioneval_solution
(evaluation_test_type: str = "private_tests", example: dict = {}, # noqa # the code contest
alpha_codium/code_contests/eval/code_test_runners.py:313
↓ 3 callersFunctionpostprocess_response
(response)
alpha_codium/gen/utils.py:37
↓ 3 callersMethodprint_test_results
(self, result: MultiTestResult, test_inputs: List[str] = None)
alpha_codium/code_contests/eval/code_test_runners.py:79
↓ 3 callersMethodrender
(self, problem_json, prompt: str)
alpha_codium/gen/coding_competitor.py:30
↓ 2 callersMethod__init__
( self, message: str, type: str, param: Optional[str], code: Optional[
alpha_codium/litellm/proxy/_types.py:1666
↓ 2 callersFunctionassert_passed_and_output
(expected, result: MultiTestResult)
tests/alpha_codium/code_contests/eval/test_local_exec.py:160
↓ 2 callersFunctionassert_status_and_error
(result: MultiTestResult, status, err)
tests/alpha_codium/code_contests/eval/test_local_exec.py:203
↓ 2 callersFunctioncalculate_metrics
(ds, k_values=[1, 10, 100])
alpha_codium/code_contests/eval/pass_at_k_evaluator.py:9
↓ 2 callersFunctioncalculate_tests_pass_fail
(multi_tests_results: MultiTestResult, expected_results: List[str])
alpha_codium/code_contests/eval/local_exec.py:219
↓ 2 callersMethodchat_completion
( self, model: str, system: str, user: str, temperature: float
alpha_codium/llm/ai_handler.py:70
↓ 2 callersFunctionclean_trace
(trace_output)
alpha_codium/code_contests/eval/tracer.py:62
↓ 2 callersMethodconnect
(self, ds)
alpha_codium/code_contests/data/provider.py:133
↓ 2 callersMethodcpp_to_python_results
(self, cpp_results)
alpha_codium/code_contests/eval/code_test_runners.py:277
↓ 2 callersMethodexecute_as_str_inner
(self, inputs: List[str], trace=False, sandbox=False)
tests/alpha_codium/code_contests/eval/test_local_exec.py:49
↓ 2 callersMethodexecute_as_string
(self, input: str, sandbox=False)
tests/alpha_codium/code_contests/eval/test_local_exec.py:43
↓ 2 callersMethodexecute_as_string_with_tracing
(self, input: str, sandbox=False)
tests/alpha_codium/code_contests/eval/test_local_exec.py:46
↓ 2 callersMethodfactory
(runner_type, *args, **kwargs)
alpha_codium/code_contests/eval/code_test_runners.py:29
↓ 2 callersMethodfind_problem
(ds, problem_name, split_name=None, evaluation_test_type = None)
alpha_codium/code_contests/data/provider.py:35
↓ 2 callersFunctionhash_token
(token: str)
alpha_codium/litellm/proxy/_types.py:125
↓ 2 callersFunctionis_solved
(s)
alpha_codium/gen/dataset_solver.py:120
↓ 2 callersFunctionmy_func
(val)
tests/alpha_codium/code_contests/eval/test_local_exec.py:79
↓ 2 callersMethodprepare_for_evaluation
( predictions, source_of_truth, evaluation_test_type )
alpha_codium/code_contests/data/provider.py:59
↓ 2 callersMethodremove_if_main
(script: str)
alpha_codium/code_contests/eval/code_test_runners.py:54
↓ 2 callersFunctionrender_trace
(trace_data)
alpha_codium/gen/utils.py:28
↓ 2 callersMethodrun
(self, user_prompt)
alpha_codium/gen/generators.py:25
↓ 2 callersMethodrun
(self, problem, iteration=0, logger_ext=None)
alpha_codium/gen/coding_competitor.py:58
↓ 2 callersFunctionrun_analyze_and_fix_test_failure
(self, problem, error_str)
alpha_codium/gen/stages/indirect/run_analyze_and_fix_test_failure.py:13
↓ 2 callersFunctionrun_initial_solve
(self, problem)
alpha_codium/gen/stages/run_initial_solve.py:10
↓ 2 callersMethodrun_tests
(self, test_id, candidate_id, candidate, test_inputs, tests_outputs, snoop=False)
alpha_codium/code_contests/eval/code_test_runners.py:42
↓ 2 callersFunctionsolve_my_problem
(problem)
alpha_codium/gen/coding_competitor.py:161
↓ 2 callersMethodsolve_problem_in_dataset
(self, example, iteration=0, logger_ext=None)
alpha_codium/gen/coding_competitor.py:98
↓ 2 callersFunctionswallow_io
(input_stream=None, binary=False)
alpha_codium/code_contests/eval/local_exec.py:259
↓ 2 callersFunctiontime_limit
(seconds)
alpha_codium/code_contests/eval/local_exec.py:237
↓ 2 callersFunctiontrace_code
(check_program, tracing)
alpha_codium/code_contests/eval/tracer.py:52
↓ 1 callersFunction_get_all_deployments
(all_models: List[str])
alpha_codium/llm/ai_invoker.py:35
↓ 1 callersFunction_get_all_models
()
alpha_codium/llm/ai_invoker.py:26
↓ 1 callersMethod_get_system_user_tokens
Calculates the number of tokens in the system and user strings. Args: - message: The pull request object. - encoder:
alpha_codium/llm/token_handler.py:44
↓ 1 callersFunctionadd_is_valid_field
(data_provider)
alpha_codium/code_contests/data/prepare_and_clean_dataset.py:143
↓ 1 callersFunctionadd_multiple_solutions_field
(data_provider)
alpha_codium/code_contests/data/prepare_and_clean_dataset.py:111
↓ 1 callersMethodbulk_test
(self, num_workers, predictions, references)
alpha_codium/code_contests/eval/code_test_runners.py:118
↓ 1 callersFunctioncalc_distance_between_results
(non_empty_output, tests_timeout, test_outputs, results)
alpha_codium/gen/stages/run_tests.py:81
↓ 1 callersFunctioncalc_is_valid_problem
(data_provider)
alpha_codium/code_contests/data/prepare_and_clean_dataset.py:47
↓ 1 callersFunctionchdir
(root)
alpha_codium/code_contests/eval/local_exec.py:287
↓ 1 callersFunctionchoose_prompt
()
alpha_codium/gen/stages/run_initial_solve.py:36
↓ 1 callersFunctionchoose_prompt
()
alpha_codium/gen/stages/run_choose_best_solution.py:41
↓ 1 callersFunctionchoose_prompt
()
alpha_codium/gen/stages/indirect/run_analyze_and_fix_test_failure.py:62
↓ 1 callersFunctionclip_string
(s: str, max_lines: int = None)
alpha_codium/gen/utils.py:13
↓ 1 callersFunctioncompare_func
(a, b)
alpha_codium/code_contests/eval/local_exec.py:179
↓ 1 callersMethodcreate_executor
(self)
alpha_codium/code_contests/eval/code_test_runners.py:50
↓ 1 callersFunctioncreate_tempdir
()
alpha_codium/code_contests/eval/local_exec.py:277
↓ 1 callersFunctionestimate_pass_at_k
Estimates pass@k of each problem and returns them in an array.
alpha_codium/code_contests/eval/code_contests_metric.py:195
↓ 1 callersFunctionestimator
Calculates 1 - comb(n - c, k) / comb(n, k).
alpha_codium/code_contests/eval/code_contests_metric.py:198
↓ 1 callersFunctionevaluate_code_contest_dataset
( dataset_name, split_name='valid', k_values=[1, 10, 10], # noqa: B006 evalua
alpha_codium/code_contests/eval/pass_at_k_evaluator.py:21
↓ 1 callersFunctionevaluate_dataset_solution
Evaluate the performance of dataset solutions. Args: dataset_name (str, optional): The name of the dataset. Defaults to 'valid_and_t
alpha_codium/evaluate_dataset.py:10
↓ 1 callersFunctionexcepter
(n)
tests/alpha_codium/code_contests/eval/test_local_exec.py:128
↓ 1 callersFunctionexecute_candidate_code
(candidate, inputs, test_id, timeout=1, sandbox=True, snoop=False, break_on_timeout=False)
alpha_codium/code_contests/eval/local_exec.py:61
↓ 1 callersFunctionexecute_inner
(check_program, single_input, snoop, timeout, input_stream, globals, tracing=None)
alpha_codium/code_contests/eval/local_exec.py:158
↓ 1 callersFunctionfibonacci
(n)
tests/alpha_codium/code_contests/eval/test_local_exec.py:104
↓ 1 callersMethodflatten_result_list_by_index
(results_list)
alpha_codium/code_contests/eval/code_test_runners.py:69
↓ 1 callersMethodget_body
(self)
tests/alpha_codium/code_contests/eval/test_local_exec.py:62
↓ 1 callersFunctionget_token_encoder
()
alpha_codium/llm/token_handler.py:7
↓ 1 callersMethodload_dataset
(self)
alpha_codium/code_contests/data/provider.py:125
↓ 1 callersFunctionmock_input_output
(mock_input_value)
tests/alpha_codium/code_contests/eval/test_local_exec.py:22
↓ 1 callersMethodparse_location
(self, dataset_location)
alpha_codium/code_contests/data/provider.py:83
↓ 1 callersMethodpass_fail_ratio
(self, results)
alpha_codium/code_contests/eval/code_contests_metric.py:174
↓ 1 callersFunctionpreapare_and_clean_dataset
(dataset_name='valid_and_test')
alpha_codium/code_contests/data/prepare_and_clean_dataset.py:19
↓ 1 callersMethodprepare_code_contest_split_for_eval
( ds, evaluation_test_type="public_tests", task_name_column="name", path_to_solutions_colu
alpha_codium/code_contests/data/provider.py:95
↓ 1 callersFunctionprinter
(val)
tests/alpha_codium/code_contests/eval/test_local_exec.py:91
↓ 1 callersFunctionprinter_inner
(val)
tests/alpha_codium/code_contests/eval/test_local_exec.py:88
↓ 1 callersFunctionproblem_29_test_fix
(data_provider)
alpha_codium/code_contests/data/prepare_and_clean_dataset.py:177
↓ 1 callersFunctionproblem_3_validation_fix
(data_provider)
alpha_codium/code_contests/data/prepare_and_clean_dataset.py:152
↓ 1 callersFunctionproblem_92_test_fix
(data_provider)
alpha_codium/code_contests/data/prepare_and_clean_dataset.py:205
↓ 1 callersFunctionreliability_guard
This disables various destructive functions and prevents the generated code from interfering with the test (e.g. fork bomb, killing other pro
alpha_codium/code_contests/eval/local_exec.py:302
↓ 1 callersFunctionrun_analyze_test_failure
(self, problem,error_str)
alpha_codium/gen/stages/indirect/run_analyze_tests_failure.py:13
↓ 1 callersFunctionrun_baseline
(self, problem)
alpha_codium/gen/stages/run_baseline.py:10
↓ 1 callersFunctionrun_choose_best_solution
(self, problem)
alpha_codium/gen/stages/run_choose_best_solution.py:11
↓ 1 callersFunctionrun_evaluate_all_ai_tests
(self, problem)
alpha_codium/gen/stages/run_evaluate_all_ai_tests.py:12
↓ 1 callersFunctionrun_evaluate_public_tests
(self, problem)
alpha_codium/gen/stages/run_evaluate_public_tests.py:14
↓ 1 callersFunctionrun_fix_code_from_tests_failure
(self, problem,error_str)
alpha_codium/gen/stages/indirect/run_fix_code_from_tests_failure.py:11
↓ 1 callersFunctionrun_generate_ai_tests
(self, problem)
alpha_codium/gen/stages/run_generate_ai_test.py:13
↓ 1 callersFunctionrun_generate_possible_solutions
(self, problem)
alpha_codium/gen/stages/run_generate_possible_solutions.py:14
↓ 1 callersFunctionrun_initial_code_generation
(self, problem)
alpha_codium/gen/stages/run_initial_code_generation.py:12
↓ 1 callersFunctionrun_self_reflect
(self, problem)
alpha_codium/gen/stages/run_self_reflect.py:14
↓ 1 callersMethodrun_tests
(self, test_id, candidate_id, candidate, test_inputs, tests_outputs, timeout=10, snoop=None, break_on_timeout=
alpha_codium/code_contests/eval/code_test_runners.py:219
↓ 1 callersFunctionrun_validate_ai_tests
(self, problem)
alpha_codium/gen/stages/indirect/run_validate_ai_test.py:11
↓ 1 callersFunctionrun_validate_self_reflect
(self, problem)
alpha_codium/gen/stages/indirect/run_fix_self_reflect.py:14
↓ 1 callersMethodsample
(ds, fraction=0.1)
alpha_codium/code_contests/data/provider.py:146
↓ 1 callersFunctionset_all_seeds
(seed)
alpha_codium/__init__.py:7
↓ 1 callersFunctionset_configurations
(problem, iteration=0)
alpha_codium/gen/stages/utils.py:6
↓ 1 callersFunctionsleeper
(timeout)
tests/alpha_codium/code_contests/eval/test_local_exec.py:118
↓ 1 callersFunctionsolve_dataset
(dataset_name='valid_and_test_processed', split_name='valid', database_sol
alpha_codium/gen/dataset_solver.py:13
↓ 1 callersFunctionsolve_problem
(dataset_name, split_name="valid", problem_name="", prob
alpha_codium/gen/coding_competitor.py:104
next →1–100 of 176, ranked by callers