MCPcopy Create free account

hub / github.com/FastMAS/KVCOMM / functions

Functions446 in github.com/FastMAS/KVCOMM

⨍ Functions 446◇ Types & classes 71
Functioncapture_screenshot
(target_url, api_key, device="desktop")
KVCOMM/tools/web/screenshot.py:16
Functionclean_answer
(model_pred)
KVCOMM/utils/utils.py:26
Methodclear_connections
(self)
KVCOMM/graph/node.py:105
Methodcommit
(self)
KVCOMM/llm/kvcomm_engine.py:666
Functioncreate_alt_url_mapping
(code)
KVCOMM/tools/vgen/dalle3.py:50
Functiondelete_extra_zero
(n)
datasets/gsm8k_dataset.py:137
Functiondump_eval_results
(self, dct: Dict[str, Any])
experiments/evaluate_mmlu.py:105
Methodend_header_id
(self)
KVCOMM/llm/gpt_chat.py:317
Methodeot_id
(self)
KVCOMM/llm/gpt_chat.py:321
Methodevaluate
(self, name: str, func: str, test: str, timeout: int = 5)
KVCOMM/tools/coding/executor_types.py:15
Methodevaluate
Evaluates the implementation on Human-Eval Python. probably should be written in a dataset-agnostic way but not now
KVCOMM/tools/coding/python_executor.py:101
Methodexecute
(self, func: str, tests: List[str], timeout: int = 5, verbose: bool = True)
KVCOMM/tools/coding/python_executor.py:76
Functionexecutor_factory
(lang: str)
KVCOMM/tools/coding/executor_factory.py:10
Methodextract_example
Return doctest-style assertions extracted from the task description.
KVCOMM/agents/final_decision.py:31
Methodfinalize_request
Compute and log per-request reuse statistics.
KVCOMM/utils/metrics.py:146
Methodfinalize_request
Stage a request state for commit; flush when last active request ends.
KVCOMM/llm/kvcomm_engine.py:739
Functionfrobenius_norm
(A, S)
KVCOMM/utils/utils.py:60
Methodgen
Synchronous generation not implemented for this adapter.
KVCOMM/llm/gpt_chat.py:169
Methodgen
( self, messages: List[Message], max_tokens: Optional[int] = None, temperature
KVCOMM/llm/gpt_chat.py:1010
Methodgen
(self, task: Optional[str] = None, img: Optional[str] = None)
KVCOMM/llm/visual_llm.py:7
Functiongenerate_images
(code, api_key, image_cache)
KVCOMM/tools/vgen/dalle3.py:63
Methodget
(cls, model_name: Optional[str] = None)
KVCOMM/llm/visual_llm_registry.py:19
Methodget_adversarial_answer_prompt
(question)
KVCOMM/prompt/gsm8k_prompt_set.py:263
Methodget_adversarial_answer_prompt
(question)
KVCOMM/prompt/humaneval_prompt_set.py:147
Methodget_adversarial_answer_prompt
Return an adversarial prompt to elicit intentionally wrong answers.
KVCOMM/prompt/mmlu_prompt_set.py:150
Methodget_analyze_constraint
(role)
KVCOMM/prompt/copy_machine_prompt_set.py:47
Methodget_answer_prompt
Build few-shot answer prompt for a given role and question.
KVCOMM/prompt/gsm8k_prompt_set.py:184
Methodget_answer_prompt
Return the raw question for code generation tasks.
KVCOMM/prompt/humaneval_prompt_set.py:88
Methodget_answer_prompt
(question)
KVCOMM/prompt/copy_machine_prompt_set.py:59
Methodget_answer_prompt
Return the raw question string.
KVCOMM/prompt/mmlu_prompt_set.py:133
Methodget_class
(cls, name: str)
KVCOMM/prompt/prompt_set_registry.py:22
Methodget_class
(cls, name: str)
KVCOMM/agents/agent_registry.py:23
Methodget_combine_materials
TODO
KVCOMM/prompt/prompt_set.py:60
Methodget_combine_materials
Combine multi-source materials into a unified context block.
KVCOMM/prompt/gsm8k_prompt_set.py:332
Methodget_combine_materials
(materials: Dict[str, Any])
KVCOMM/prompt/humaneval_prompt_set.py:214
Methodget_combine_materials
(materials: Dict[str, Any])
KVCOMM/prompt/copy_machine_prompt_set.py:83
Methodget_combine_materials
(materials: Dict[str, Any])
KVCOMM/prompt/mmlu_prompt_set.py:167
Methodget_constraint
Return role-specific instruction/constraint text.
KVCOMM/prompt/gsm8k_prompt_set.py:174
Methodget_constraint
Return role-specific instruction/constraint text.
KVCOMM/prompt/humaneval_prompt_set.py:78
Methodget_constraint
()
KVCOMM/prompt/copy_machine_prompt_set.py:43
Methodget_constraint
Return base task constraints for multiple-choice QA.
KVCOMM/prompt/mmlu_prompt_set.py:93
Methodget_decision_constraint
Return judge/decision constraints for final selection.
KVCOMM/prompt/gsm8k_prompt_set.py:189
Methodget_decision_constraint
()
KVCOMM/prompt/humaneval_prompt_set.py:218
Methodget_decision_constraint
()
KVCOMM/prompt/copy_machine_prompt_set.py:51
Methodget_decision_constraint
Return decision constraints for picking a single option.
KVCOMM/prompt/mmlu_prompt_set.py:120
Methodget_decision_few_shot
Return few-shot exemplars for decision-making (if any).
KVCOMM/prompt/gsm8k_prompt_set.py:204
Methodget_decision_few_shot
()
KVCOMM/prompt/humaneval_prompt_set.py:234
Methodget_decision_few_shot
()
KVCOMM/prompt/copy_machine_prompt_set.py:87
Methodget_decision_few_shot
()
KVCOMM/prompt/mmlu_prompt_set.py:171
Methodget_decision_role
Return the role used for the decision-maker agent.
KVCOMM/prompt/gsm8k_prompt_set.py:198
Methodget_decision_role
()
KVCOMM/prompt/humaneval_prompt_set.py:230
Methodget_decision_role
()
KVCOMM/prompt/copy_machine_prompt_set.py:39
Methodget_decision_role
Return the role used for the decision-maker agent.
KVCOMM/prompt/mmlu_prompt_set.py:88
Methodget_distill_websearch_prompt
TODO
KVCOMM/prompt/prompt_set.py:46
Methodget_distill_websearch_prompt
Build prompt to distill gathered web results into a summary.
KVCOMM/prompt/gsm8k_prompt_set.py:267
Methodget_distill_websearch_prompt
Build prompt to distill gathered web results into a summary.
KVCOMM/prompt/humaneval_prompt_set.py:151
Methodget_distill_websearch_prompt
(query, results)
KVCOMM/prompt/copy_machine_prompt_set.py:75
Methodget_distill_websearch_prompt
(query, results)
KVCOMM/prompt/mmlu_prompt_set.py:159
Methodget_domain
()
datasets/mmlu_dataset.py:19
Methodget_file_analysis_prompt
TODO
KVCOMM/prompt/prompt_set.py:36
Methodget_file_analysis_prompt
Build prompt scaffold for targeted file analysis.
KVCOMM/prompt/gsm8k_prompt_set.py:236
Methodget_file_analysis_prompt
Build prompt scaffold for targeted file analysis.
KVCOMM/prompt/humaneval_prompt_set.py:121
Methodget_file_analysis_prompt
(query, file)
KVCOMM/prompt/copy_machine_prompt_set.py:67
Methodget_file_analysis_prompt
(query, file)
KVCOMM/prompt/mmlu_prompt_set.py:142
Methodget_format
TODO
KVCOMM/prompt/prompt_set.py:21
Methodget_format
Return output format.
KVCOMM/prompt/gsm8k_prompt_set.py:179
Methodget_format
Return output format.
KVCOMM/prompt/humaneval_prompt_set.py:83
Methodget_format
()
KVCOMM/prompt/copy_machine_prompt_set.py:55
Methodget_format
()
KVCOMM/prompt/mmlu_prompt_set.py:129
Methodget_query_prompt
TODO
KVCOMM/prompt/prompt_set.py:31
Methodget_query_prompt
Build prompt scaffold for planning information gathering.
KVCOMM/prompt/gsm8k_prompt_set.py:221
Methodget_query_prompt
Build prompt scaffold for planning information gathering.
KVCOMM/prompt/humaneval_prompt_set.py:106
Methodget_query_prompt
(question)
KVCOMM/prompt/copy_machine_prompt_set.py:63
Methodget_query_prompt
(question)
KVCOMM/prompt/mmlu_prompt_set.py:138
Methodget_react_prompt
TODO
KVCOMM/prompt/prompt_set.py:55
Methodget_react_prompt
Build prompt to revise a solution using provided feedback.
KVCOMM/prompt/gsm8k_prompt_set.py:209
Methodget_react_prompt
Build prompt to revise a solution using provided feedback.
KVCOMM/prompt/humaneval_prompt_set.py:94
Methodget_reflect_prompt
TODO
KVCOMM/prompt/prompt_set.py:51
Methodget_reflect_prompt
Build prompt that encourages reflection on a prior answer.
KVCOMM/prompt/gsm8k_prompt_set.py:284
Methodget_reflect_prompt
Build prompt that encourages reflection on a prior answer.
KVCOMM/prompt/humaneval_prompt_set.py:167
Methodget_reflect_prompt
(question, answer)
KVCOMM/prompt/copy_machine_prompt_set.py:79
Methodget_reflect_prompt
(question, answer)
KVCOMM/prompt/mmlu_prompt_set.py:163
Methodget_request_state
Return the request state; identical to resolve_request_state.
KVCOMM/llm/kvcomm_engine.py:765
Methodget_role
Return the next cyclic role for multi-agent setups.
KVCOMM/prompt/gsm8k_prompt_set.py:169
Methodget_role
Return the next cyclic role for multi-agent setups.
KVCOMM/prompt/humaneval_prompt_set.py:73
Methodget_role
()
KVCOMM/prompt/copy_machine_prompt_set.py:35
Methodget_role
Return the next cyclic role for multi-agent setups.
KVCOMM/prompt/mmlu_prompt_set.py:83
Methodget_select_best
Build a best-answer evaluation prompt over candidates.
KVCOMM/prompt/gsm8k_prompt_set.py:314
Methodget_select_best
Build a best-answer evaluation prompt over candidates.
KVCOMM/prompt/humaneval_prompt_set.py:196
Methodget_self_consistency
Build a self-consistency selection prompt over candidate answers.
KVCOMM/prompt/gsm8k_prompt_set.py:296
Methodget_self_consistency
Build a self-consistency selection prompt over candidate answers.
KVCOMM/prompt/humaneval_prompt_set.py:178
Methodget_websearch_prompt
TODO
KVCOMM/prompt/prompt_set.py:41
Methodget_websearch_prompt
Build prompt scaffold for targeted web search queries.
KVCOMM/prompt/gsm8k_prompt_set.py:250
Methodget_websearch_prompt
(question, query)
KVCOMM/prompt/humaneval_prompt_set.py:135
Methodget_websearch_prompt
(query)
KVCOMM/prompt/copy_machine_prompt_set.py:71
Methodget_websearch_prompt
(query)
KVCOMM/prompt/mmlu_prompt_set.py:146
Functiongsm_get_predict
(pred_str)
datasets/gsm8k_dataset.py:50
Functioninitialize_log_file
Initialize the log file with a start message and return its path. Args: mode (str): The mode of operation, used in the file path.
KVCOMM/utils/log.py:28
Functionis_correct
(model_answer, answer)
KVCOMM/utils/utils.py:21
Methodkeys
(cls)
KVCOMM/llm/visual_llm_registry.py:15
← previousnext →301–400 of 446, ranked by callers