MCPcopy Create free account

hub / github.com/OpenCodeInterpreter/OpenCodeInterpreter / functions

Functions494 in github.com/OpenCodeInterpreter/OpenCodeInterpreter

⨍ Functions 494◇ Types & classes 48↳ Endpoints 13
Methodexecute_code
(self, code)
data_collection/Local-Code-Interpreter/src/jupyter_backend.py:79
Methodextract_code_blocks
(text: str)
demo/code_interpreter/BaseCodeInterpreter.py:21
Functionfix
(data)
evaluation/evalplus/tools/humaneval/fix_v019.py:4
Methodfluctuate_ratio
(self)
evaluation/evalplus/tools/_experimental/type_mut_for_eff.py:54
Methodfluctuate_ratio
(self)
evaluation/evalplus/evalplus/_experimental/type_mut_for_eff.py:54
Methodgenerate
(self, num: int)
evaluation/evalplus/evalplus/gen/type_mut.py:321
Methodgenerate
(self, num: int)
evaluation/evalplus/evalplus/gen/chatgpt_gen.py:67
Methodgenerate
(self, num: int)
evaluation/evalplus/evalplus/gen/mut_gen.py:21
Functionget_instruction_count
( profiler: Callable, func_code: str, entry_point: str, test_inputs: List[Any], timeout_se
evaluation/evalplus/evalplus/perf/profile.py:36
Methodget_tool_data
(self)
data_collection/Local-Code-Interpreter/src/tools.py:125
Methodget_tool_data
(self)
data_collection/Local-Code-Interpreter/src/tools.py:165
Functiongreedy_cover
( task_id: str, tests: Dict[str, List[Any]], exclude_model: str )
evaluation/evalplus/tools/tsr/minimization.py:42
Functionhandler
(signum, frame)
evaluation/evalplus/evalplus/gen/util/openai_request.py:37
Functionhandler
(signum, frame)
evaluation/evalplus/evalplus/gen/util/api_request.py:34
Functionhandler
(signum, frame)
evaluation/evalplus/evalplus/gen/util/anthropic_request.py:8
Functionhas_print_in_non_main_functions
(source)
evaluation/evalplus/tools/collect_valid_solutions.py:85
Functioninitialization
(state_dict: Dict)
data_collection/Local-Code-Interpreter/src/web_ui.py:5
Functioninput_generation
(inputs, signature, contract_code)
evaluation/evalplus/tools/_experimental/generate_big_input.py:26
Functioninput_generation
(inputs, signature, contract_code)
evaluation/evalplus/evalplus/_experimental/generate_big_input.py:26
Functioninquire_image
(work_dir, vision_model, path, prompt)
data_collection/Local-Code-Interpreter/src/tools.py:72
Methodis_direct_completion
(self)
evaluation/evalplus/codegen/model.py:135
Methodis_direct_completion
(self)
evaluation/evalplus/codegen/model.py:194
Methodis_direct_completion
(self)
evaluation/evalplus/codegen/model.py:311
Methodis_direct_completion
(self)
evaluation/evalplus/codegen/model.py:352
Methodis_direct_completion
(self)
evaluation/evalplus/codegen/model.py:361
Functionmain
( output: str, # output file n: int = 16, # sample size and batch size model: Optional[str] = "T
evaluation/evalplus/evalplus/perf/sas.py:101
Functionmain
In the synthesizer file, each line includes a set of input generators for a task. The goal of this script is to use these generators to sample inp
evaluation/evalplus/evalplus/perf/sampling.py:187
Functionmain
( model: str, dataset: str, root: str, bs: int = 1, n_samples: int = 1, temperat
evaluation/evalplus/codegen/generate.py:115
Functionmake_auto_request
(*args, **kwargs)
evaluation/evalplus/evalplus/gen/util/api_request.py:39
Functionmake_auto_request
(client: anthropic.Client, *args, **kwargs)
evaluation/evalplus/evalplus/gen/util/anthropic_request.py:13
Functionnum_instruction_profiler
(function, test_inputs)
evaluation/evalplus/evalplus/perf/profile.py:29
Functionphysical_runtime_profiler
(function, test_inputs)
evaluation/evalplus/evalplus/perf/profile.py:22
Methodrank
(self)
evaluation/evalplus/tools/_experimental/type_mut_for_eff.py:58
Methodrank
(self)
evaluation/evalplus/evalplus/_experimental/type_mut_for_eff.py:58
Methodreadable
Returns True if the IO object can be read.
evaluation/evalplus/evalplus/eval/utils.py:93
Methodreadline
(self, *args, **kwargs)
evaluation/evalplus/evalplus/eval/utils.py:87
Functionrefresh_file_display
(state_dict: Dict)
data_collection/Local-Code-Interpreter/src/web_ui.py:73
Functionrefresh_token_count
(state_dict: Dict)
data_collection/Local-Code-Interpreter/src/web_ui.py:85
Functionremove_unindented_lines
(code, protect_before, execeptions, trim_tails)
evaluation/evaluate/utils.py:81
Functionreset_textbox
()
demo/chatbot.py:283
Functionrestart_bot_backend
(state_dict: Dict)
data_collection/Local-Code-Interpreter/src/web_ui.py:110
Functionrestart_ui
(history: List)
data_collection/Local-Code-Interpreter/src/web_ui.py:97
Methodrun_code_in_thread
()
demo/code_interpreter/JupyterClient.py:31
Functionsafety_test
(code: str, inputs: List[List[Any]], entry_point: str)
evaluation/evalplus/tools/_experimental/evaluate_coverage.py:83
Functionsafety_test
(code: str, inputs: List[List[Any]], entry_point: str)
evaluation/evalplus/evalplus/_experimental/evaluate_coverage.py:83
Functionsample_one_input
( ref_code_with_contract: str, entry_point: str, generator_code: str, timeout_second: float =
evaluation/evalplus/evalplus/perf/sampling.py:86
Functionscript
(sample_dir: str, dataset: str = "humaneval", debug_task: str = None)
evaluation/evalplus/tools/collect_valid_solutions.py:150
Functionscript
( samples: str, inplace: bool = False, debug_task: str = None, mbpp_version="default" )
evaluation/evalplus/evalplus/sanitize.py:169
Functionscript
( samples: str, dataset: str, output_dir: str, profile_n_correct: int = 10, max_n_samples:
evaluation/evalplus/evalplus/evalperf.py:250
Functionscript
( samples: str, eofs: List[str] = [], inplace: bool = False, rm_prefix_lines: str = None,
evaluation/evalplus/evalplus/lecacy_sanitize.py:119
Functionscript
( samples: str, dataset: str, nsample_check: int = None, verbose: bool = False )
evaluation/evalplus/evalplus/syncheck.py:24
Functionscript
( profiled_solutions: str, output_dataset: str = f"evalperf-{datetime.now():%Y%m%d}.jsonl", debug_
evaluation/evalplus/evalplus/perf/select_pe_tasks.py:127
Functionscript
(solutions: str, output_profiled_solutions: str, pe_inputs: str = None)
evaluation/evalplus/evalplus/perf/select_pe_inputs.py:15
Methodsend_interrupt_signal
(self)
data_collection/Local-Code-Interpreter/src/jupyter_backend.py:101
Functionsignal_handler
(signum, frame)
evaluation/evalplus/evalplus/eval/utils.py:44
Functionstop_generating
(state_dict: Dict)
data_collection/Local-Code-Interpreter/src/web_ui.py:115
Functionstucking_checker
()
evaluation/evalplus/evalplus/evaluate.py:212
Methodsupport
(self)
data_collection/Local-Code-Interpreter/src/tools.py:122
Methodsupport
(self)
data_collection/Local-Code-Interpreter/src/tools.py:162
Methodsupport
(self)
data_collection/Local-Code-Interpreter/src/response_parser.py:20
Methodsupport
(self)
data_collection/Local-Code-Interpreter/src/response_parser.py:29
Methodsupport
(self)
data_collection/Local-Code-Interpreter/src/response_parser.py:48
Methodsupport
(self)
data_collection/Local-Code-Interpreter/src/response_parser.py:71
Methodsupport
(self)
data_collection/Local-Code-Interpreter/src/response_parser.py:111
Functionswitch_to_gpt4
(state_dict: Dict, whether_switch: bool)
data_collection/Local-Code-Interpreter/src/web_ui.py:18
Functionsynthesize_test_code
(task_id, entry_point, inputs, results, ref_func, atol)
evaluation/evalplus/tools/humaneval/to_original_fmt.py:59
Functionsynthesize_test_code
(task_id, entry_point, inputs, results, ref_func, atol)
evaluation/evalplus/tools/mbpp/to_original_fmt.py:64
Functiontest
()
evaluation/evalplus/tools/mbpp/to_original_fmt.py:216
Functiontest_code_extract
()
evaluation/evalplus/tests/test_treesitter_sanitizer.py:4
Functiontest_entrypoint_basic
()
evaluation/evalplus/tests/test_treesitter_sanitizer.py:98
Functiontest_entrypoint_chain
()
evaluation/evalplus/tests/test_treesitter_sanitizer.py:130
Functiontest_entrypoint_no_chain
()
evaluation/evalplus/tests/test_treesitter_sanitizer.py:176
Functiontest_entrypoint_variable
()
evaluation/evalplus/tests/test_treesitter_sanitizer.py:211
Functiontest_inline_fn
()
evaluation/evalplus/tests/test_legacy_sanitizer.py:6
Functiontest_inline_fn
()
evaluation/evalplus/tests/test_sanitizer.py:6
Functiontest_sanitize_class
()
evaluation/evalplus/tests/test_treesitter_sanitizer.py:71
Functiontest_sanitize_simple
()
evaluation/evalplus/tests/test_treesitter_sanitizer.py:39
Functiontest_solution_runtime
( dataset: str = "humaneval", task_id: str = "HumanEval/0", impl: str = "canonical", inputs: U
evaluation/evalplus/tools/_experimental/evaluate_runtime.py:70
Functiontest_solution_runtime
( dataset: str = "humaneval", task_id: str = "HumanEval/0", impl: str = "canonical", inputs: U
evaluation/evalplus/evalplus/_experimental/evaluate_runtime.py:70
Functionto_four_space_indents
(old_code)
evaluation/evaluate/utils.py:106
Functionundo_upload_file
(state_dict: Dict, history: List)
data_collection/Local-Code-Interpreter/src/web_ui.py:57
Functionunsafe_execute
( dataset: str, entry_point: str, code: str, inputs, expected: List, time_limits,
evaluation/evaluate/utils.py:154
Functionunsafe_execute
()
evaluation/evalplus/tools/_experimental/evaluate_runtime.py:22
Functionunsafe_execute
( dataset: str, entry_point: str, code: str, inputs, expected: List, time_limits
evaluation/evalplus/evalplus/eval/__init__.py:106
Functionunsafe_execute
()
evaluation/evalplus/evalplus/_experimental/evaluate_runtime.py:22
Methodvisit_Call
(self, node)
demo/chatbot.py:115
Methodvisit_Call
(self, node)
evaluation/evalplus/tools/collect_valid_solutions.py:46
Methodvisit_Call
(self, node)
evaluation/evalplus/tools/collect_valid_solutions.py:72
Methodvisit_FunctionDef
(self, node)
evaluation/evalplus/tools/collect_valid_solutions.py:32
Methodvisit_FunctionDef
(self, node: ast.FunctionDef)
evaluation/evalplus/tools/collect_valid_solutions.py:66
Functionworker_on_one_task
( task_id: str, task_ref: Dict, samples: list, task: Dict, expected_output: Dict, prof
evaluation/evalplus/evalplus/evalperf.py:73
Methodwrapper
(self, seed_input)
evaluation/evalplus/tools/_experimental/type_mut_for_eff.py:33
Methodwrapper
(self, seed_input)
evaluation/evalplus/evalplus/gen/type_mut.py:25
Methodwrapper
(self, seed_input)
evaluation/evalplus/evalplus/_experimental/type_mut_for_eff.py:33
← previous401–494 of 494, ranked by callers