MCPcopy Create free account

hub / github.com/OpenCodeInterpreter/OpenCodeInterpreter / functions

Functions494 in github.com/OpenCodeInterpreter/OpenCodeInterpreter

⨍ Functions 494◇ Types & classes 48↳ Endpoints 13
↓ 39 callersFunctioncheck_id
(data, n, task_id)
evaluation/evalplus/tools/mbpp/fix_v010.py:1
↓ 34 callersFunctionget_human_eval_plus
Get HumanEvalPlus locally. Args: err_incomplete (bool, optional): Whether to raise error if HumanEvalPlus is not complete. Defaults to Tru
evaluation/evalplus/evalplus/data/humaneval.py:42
↓ 21 callersMethodreadlines
(self, *args, **kwargs)
evaluation/evalplus/evalplus/eval/utils.py:90
↓ 19 callersFunctionget_mbpp_plus
( err_incomplete=True, mini=False, noextreme=False, version="default" )
evaluation/evalplus/evalplus/data/mbpp.py:181
↓ 14 callersFunctionswallow_io
()
evaluation/evalplus/evalplus/eval/utils.py:34
↓ 11 callersFunctionexecute_cmd
(cmd: list)
evaluation/evalplus/tools/tsr/utils.py:33
↓ 11 callersMethodgenerate
(self, num: int)
evaluation/evalplus/evalplus/gen/__init__.py:20
↓ 11 callersMethodread
(self, *args, **kwargs)
evaluation/evalplus/evalplus/eval/utils.py:84
↓ 10 callersFunctionsanitize
(code: str, entrypoint: Optional[str] = None)
evaluation/evalplus/evalplus/sanitize.py:111
↓ 10 callersFunctiontime_limit
(seconds: float)
evaluation/evalplus/evalplus/eval/utils.py:43
↓ 9 callersFunctionget_bot_backend
(state_dict: Dict)
data_collection/Local-Code-Interpreter/src/web_ui.py:14
↓ 8 callersFunctionfunc
(x)
evaluation/evalplus/tools/humaneval/fix_v014.py:19
↓ 8 callersFunctionget_groundtruth
(problems, hashcode, tasks_only_output_not_none)
evaluation/evaluate/utils.py:45
↓ 8 callersFunctionget_groundtruth
(problems, hashcode, tasks_only_output_not_none)
evaluation/evalplus/evalplus/evaluate.py:41
↓ 8 callersFunctionget_human_eval_plus_hash
Get the hash of HumanEvalPlus. Returns: str: The hash of HumanEvalPlus
evaluation/evalplus/evalplus/data/humaneval.py:31
↓ 8 callersFunctionget_mbpp_plus_hash
Get the hash of MbppPlus. Returns: str: The hash of MbppPlus
evaluation/evalplus/evalplus/data/mbpp.py:195
↓ 8 callersFunctionreliability_guard
This disables various destructive functions and prevents the generated code from interfering with the test (e.g. fork bomb, killing other p
evaluation/evalplus/evalplus/eval/utils.py:102
↓ 8 callersFunctionsanitize_solution
(solution,eofs)
evaluation/evaluate/utils.py:116
↓ 8 callersFunctionwrite_jsonl
Writes an iterable of dictionaries to jsonl
evaluation/evalplus/evalplus/data/utils.py:48
↓ 7 callersMethod__init__
( self, name: str, batch_size: int = 1, temperature: float = 0.8,
evaluation/evalplus/codegen/model.py:84
↓ 7 callersFunctionestimate_pass_at_k
Estimates pass@k of each problem and returns them in an array.
evaluation/evalplus/evalplus/eval/__init__.py:55
↓ 6 callersFunctioncheck_id
(data, task_id)
evaluation/evalplus/tools/humaneval/fix_v012.py:1
↓ 6 callersFunctioncheck_id
(data, task_id)
evaluation/evalplus/tools/humaneval/fix_v018.py:4
↓ 6 callersFunctionmbpp_serialize_inputs
(task_id: str, inputs: list)
evaluation/evalplus/evalplus/data/mbpp.py:34
↓ 6 callersFunctiontrusted_exec
Execute trusted code in place.
evaluation/evalplus/evalplus/gen/util/__init__.py:7
↓ 5 callersFunctioncreate_tempdir
()
evaluation/evalplus/evalplus/eval/utils.py:56
↓ 5 callersFunctionget_task_ids
(dataset: str)
evaluation/evalplus/tools/tsr/utils.py:19
↓ 5 callersFunctionstream_jsonl
Parses each jsonl line and yields it as a dictionary
evaluation/evalplus/evalplus/data/utils.py:74
↓ 5 callersFunctionto_path
(task_id: str)
evaluation/evalplus/tools/tsr/utils.py:24
↓ 5 callersFunctionwrite_to_notebook
()
data_collection/Local-Code-Interpreter/src/notebook_serializer.py:30
↓ 4 callersMethod_fetch_list_like
(self, seed_input)
evaluation/evalplus/tools/_experimental/type_mut_for_eff.py:392
↓ 4 callersMethod_fetch_list_like
(self, seed_input)
evaluation/evalplus/evalplus/gen/type_mut.py:297
↓ 4 callersMethod_fetch_list_like
(self, seed_input)
evaluation/evalplus/evalplus/_experimental/type_mut_for_eff.py:392
↓ 4 callersFunctionare_profiles_broken
(profiles)
evaluation/evalplus/evalplus/perf/profile.py:18
↓ 4 callersFunctioncheck_correctness
( dataset: str, completion_id: int, problem: Dict[str, Any], solution: str, expected_outpu
evaluation/evaluate/utils.py:337
↓ 4 callersFunctioncheck_id
(data: dict, task_id: str)
evaluation/evalplus/tools/humaneval/fix_utils.py:5
↓ 4 callersFunctioncheck_id
(data, task_id)
evaluation/evalplus/tools/humaneval/fix_v017.py:4
↓ 4 callersFunctiongen_report
(set_cover_info: Dict[str, List[str]], sample_eval_dir: str, model: str)
evaluation/evalplus/tools/tsr/minimization.py:140
↓ 4 callersFunctionget_definition_name
(node: Node)
evaluation/evalplus/evalplus/sanitize.py:78
↓ 4 callersFunctiongpt_predict
(messages, model="gpt3.5")
evaluation/evaluate/multi_turn/chat_with_gpt.py:9
↓ 4 callersFunctionload_solutions
We accept two formats of inputs. + `sample.jsonl` which is the format from HumanEval, i.e., {task_id, completion or solution}. + A folder whic
evaluation/evalplus/evalplus/data/utils.py:91
↓ 4 callersFunctionmbpp_deserialize_inputs
(task_id: str, inputs: list)
evaluation/evalplus/evalplus/data/mbpp.py:47
↓ 4 callersFunctionprofile
Profile the func_code against certain input tests. The function code is assumed to be correct and if a string is returned, it is an error message.
evaluation/evalplus/evalplus/perf/profile.py:98
↓ 4 callersFunctionreplay_contract
(data: dict, tid: int)
evaluation/evalplus/tools/humaneval/fix_utils.py:19
↓ 4 callersMethodreset_gpt_response_log_values
(self, exclude=None)
data_collection/Local-Code-Interpreter/src/bot_backend.py:74
↓ 4 callersFunctionsyntax_check
(code, verbose=False)
evaluation/evalplus/evalplus/syncheck.py:14
↓ 4 callersMethodtyped_gen
(self, _)
evaluation/evalplus/tools/_experimental/type_mut_for_eff.py:162
↓ 4 callersMethodtyped_gen
(self, _)
evaluation/evalplus/evalplus/gen/type_mut.py:65
↓ 4 callersMethodtyped_gen
(self, _)
evaluation/evalplus/evalplus/_experimental/type_mut_for_eff.py:162
↓ 4 callersFunctionuntrusted_check
( dataset: str, code: str, inputs: List[Any], entry_point: str, expected, atol,
evaluation/evalplus/evalplus/eval/__init__.py:197
↓ 4 callersMethodupdate_display_code_block
(self, display_code_block)
data_collection/Local-Code-Interpreter/src/bot_backend.py:113
↓ 4 callersMethodupdate_gpt_model_choice
(self, model_choice)
data_collection/Local-Code-Interpreter/src/bot_backend.py:305
↓ 3 callersFunction_ready_mbpp_plus_path
(mini=False, noextreme=False, version="default")
evaluation/evalplus/evalplus/data/mbpp.py:20
↓ 3 callersMethodadd_and_run
(self, code_string)
demo/code_interpreter/JupyterClient.py:29
↓ 3 callersMethodadd_function_call_response_message
(self, function_response: Union[str, None], save_tokens=True)
data_collection/Local-Code-Interpreter/src/bot_backend.py:258
↓ 3 callersFunctioncode_extract
(text: str)
evaluation/evalplus/evalplus/sanitize.py:30
↓ 3 callersMethodcodegen
( self, prompt: str, do_sample: bool = True, num_samples: int = 200 )
evaluation/evalplus/codegen/model.py:104
↓ 3 callersMethodexecute
(self, bot_backend: BotBackend, history: List, whether_exit: bool)
data_collection/Local-Code-Interpreter/src/response_parser.py:14
↓ 3 callersFunctionfix
(data)
evaluation/evalplus/tools/humaneval/fix_v011.py:1
↓ 3 callersFunctionget_bot_backend
(state_dict: Dict)
data_collection/Local-Code-Interpreter/src/cli.py:17
↓ 3 callersFunctionget_mbpp
Get sanitized MBPP from Google's Github repo.
evaluation/evalplus/evalplus/data/mbpp.py:161
↓ 3 callersFunctionget_problems
(dataset: str)
evaluation/evalplus/tools/tsr/utils.py:15
↓ 3 callersFunctionmain
()
evaluation/evalplus/evalplus/sanitize.py:240
↓ 3 callersFunctionmake_cache
(gzip_url, cache_path)
evaluation/evalplus/evalplus/data/utils.py:27
↓ 3 callersFunctionparallel_greedy_cover
( info_dict: Optional[Dict[str, Dict[str, List[Any]]]], exclude_model: str, type: str, **kwarg
evaluation/evalplus/tools/tsr/minimization.py:72
↓ 3 callersFunctionpoly
(xs, x)
evaluation/evalplus/tools/humaneval/fix_v014.py:8
↓ 3 callersMethodseed_selection
(self)
evaluation/evalplus/evalplus/gen/mut_gen.py:13
↓ 3 callersFunctionswitch_to_gpt4
(state_dict: Dict, whether_switch: bool)
data_collection/Local-Code-Interpreter/src/cli.py:20
↓ 3 callersFunctionto_raw
(string)
evaluation/evalplus/evalplus/data/utils.py:165
↓ 3 callersFunctiontrusted_check_exec
Check trusted_exec success.
evaluation/evalplus/evalplus/gen/util/__init__.py:33
↓ 3 callersMethodupdate_code_str
(self, code_str: str)
data_collection/Local-Code-Interpreter/src/bot_backend.py:110
↓ 2 callersMethod_create_work_dir
(self)
data_collection/Local-Code-Interpreter/src/jupyter_backend.py:92
↓ 2 callersMethod_init_conversation
(self)
data_collection/Local-Code-Interpreter/src/bot_backend.py:145
↓ 2 callersMethod_init_kwargs_for_chat_completion
(self)
data_collection/Local-Code-Interpreter/src/bot_backend.py:186
↓ 2 callersFunction_poly
Evaluates polynomial with coefficients xs at point x. return xs[0] + xs[1] * x + xs[1] * x^2 + .... xs[n] * x^n
evaluation/evalplus/evalplus/eval/_special_oracle.py:23
↓ 2 callersFunction_ready_human_eval_plus_path
(mini=False, noextreme=False, version="default")
evaluation/evalplus/evalplus/data/humaneval.py:18
↓ 2 callersFunctionadaptive_seg1d
(arr1d, base_thresh=0.10)
evaluation/evalplus/evalplus/perf/select_pe_tasks.py:86
↓ 2 callersMethodadd_gpt_response_content_message
(self)
data_collection/Local-Code-Interpreter/src/bot_backend.py:228
↓ 2 callersFunctionadd_image_to_notebook
(image, mime_type)
data_collection/Local-Code-Interpreter/src/notebook_serializer.py:60
↓ 2 callersFunctionadd_markdown_to_notebook
(content, title=None)
data_collection/Local-Code-Interpreter/src/notebook_serializer.py:66
↓ 2 callersMethodadd_text_message
(self, user_text)
data_collection/Local-Code-Interpreter/src/bot_backend.py:234
↓ 2 callersFunctionanalyze_resfile
(resfile)
evaluation/evalplus/tools/render.py:16
↓ 2 callersFunctionaplus
(s)
evaluation/evalplus/tools/render.py:88
↓ 2 callersFunctionchat_completion
(bot_backend: BotBackend)
data_collection/Local-Code-Interpreter/src/functional.py:33
↓ 2 callersFunctioncheck_id
(data, task_id)
evaluation/evalplus/tools/humaneval/fix_v015.py:4
↓ 2 callersFunctioncheck_unique
(grid)
evaluation/evalplus/tools/humaneval/fix_v011.py:30
↓ 2 callersFunctionclean
(file_path: str)
evaluation/evalplus/tools/tsr/utils.py:28
↓ 2 callersMethodclose
Shutdown the kernel.
demo/code_interpreter/JupyterClient.py:76
↓ 2 callersFunctioncollect_coverage_info
(coverage_dir: str, dataset: str)
evaluation/evalplus/tools/tsr/coverage_init.py:76
↓ 2 callersFunctioncollect_mutation_info
( eval_path: str, dataset: str )
evaluation/evalplus/tools/tsr/mutation_init.py:82
↓ 2 callersFunctioncollect_sample_info
(sample_dir: str, sample_eval_dir: str, dataset: str)
evaluation/evalplus/tools/tsr/sample_init.py:10
↓ 2 callersFunctioncompleteness_check
(name, plus)
evaluation/evalplus/evalplus/data/utils.py:152
↓ 2 callersFunctioncv
We use Coefficient of Variation (CV) to as the variance of PE. CV = 100 * standard deviation / mean
evaluation/evalplus/evalplus/perf/select_pe_tasks.py:18
↓ 2 callersFunctiondeduplicate
Deduplicate solutions
evaluation/evalplus/tools/collect_valid_solutions.py:108
↓ 2 callersFunctiondelete_color_control_char
(string)
data_collection/Local-Code-Interpreter/src/jupyter_backend.py:5
↓ 2 callersMethoddialog_to_prompt
(self, dialog: List[Dict])
demo/code_interpreter/OpenCodeInterpreter.py:57
↓ 2 callersFunctionevaluate
(flags)
evaluation/evalplus/evalplus/evaluate.py:126
↓ 2 callersFunctionevolve
(src_file: str, tgt_file: str, fix: Callable)
evaluation/evalplus/tools/humaneval/fix_utils.py:9
↓ 2 callersFunctionevolve
(src_file, tgt_file)
evaluation/evalplus/tools/humaneval/fix_v017.py:39
↓ 2 callersFunctionevolve
(src_file, tgt_file)
evaluation/evalplus/tools/humaneval/fix_v018.py:57
next →1–100 of 494, ranked by callers