MCPcopy Create free account

hub / github.com/PERSONA-bench/PERSONA / functions

Functions235 in github.com/PERSONA-bench/PERSONA

↓ 31 callersFunctionclean_text
(text)
demo/3.1PromptMaker.py:26
↓ 31 callersFunctionclean_text
(text)
demo/3.2PromptMaker.py:30
↓ 31 callersFunctionclean_text
(text)
PromptMakers/3.1PromptMaker.py:26
↓ 31 callersFunctionclean_text
(text)
PromptMakers/3.2PromptMaker.py:30
↓ 17 callersFunctionclean_text
(text)
PromptMakers/3.2_RandPrompt.py:26
↓ 17 callersFunctionclean_text
(text)
PromptMakers/3.1_RandPrompt.py:20
↓ 16 callersMethodclose
(self)
LLMEvaluators/3.1/LlamaAndDeepSeek_batch_eval.py:668
↓ 15 callersFunctionlog_and_store
(message)
LLMEvaluators/3.2/GPT.py:322
↓ 15 callersFunctionlog_and_store
(message)
demo/GPT3.2.py:310
↓ 14 callersFunctionlog_and_store
(message)
LLMEvaluators/3.1/Claude.py:384
↓ 14 callersFunctionlog_and_store
(message)
LLMEvaluators/3.2/Claude.py:515
↓ 11 callersFunctionclean_text
(text)
PromptMakers/3.3_RandPrompt.py:21
↓ 8 callersFunctiondatetime_to_string
(dt_obj)
demo/3.1PromptMaker.py:62
↓ 8 callersFunctiondatetime_to_string
(dt_obj)
demo/3.2PromptMaker.py:66
↓ 8 callersFunctiondatetime_to_string
(dt_obj)
PromptMakers/3.2_RandPrompt.py:59
↓ 8 callersFunctiondatetime_to_string
(dt_obj)
PromptMakers/3.1PromptMaker.py:62
↓ 8 callersFunctiondatetime_to_string
(dt_obj)
PromptMakers/3.2PromptMaker.py:66
↓ 7 callersMethodclose
(self)
LLMEvaluators/3.2/LlamaAndDeepSeek_batch_eval.py:668
↓ 7 callersFunctiondatetime_to_string
(dt_obj)
PromptMakers/3.1_RandPrompt.py:53
↓ 6 callersFunctionclean_text
(text)
demo/3.3PromptMaker.py:22
↓ 6 callersFunctionclean_text
(text)
PromptMakers/3.3PromptMaker.py:22
↓ 6 callersFunctionis_rate_limit_error
(exception)
LLMEvaluators/3.2/Claude.py:76
↓ 5 callersFunctiondatetime_to_string
(dt_obj)
PromptMakers/3.3_RandPrompt.py:71
↓ 5 callersFunctionget_post_summary_string
(post_obj_from_store, main_author_name_for_summary)
demo/3.1PromptMaker.py:224
↓ 5 callersFunctionget_post_summary_string
(post_obj_from_store, main_author_name_for_summary)
demo/3.2PromptMaker.py:223
↓ 5 callersFunctionget_post_summary_string
(post_obj_from_store, main_author_name_for_summary)
PromptMakers/3.1PromptMaker.py:224
↓ 5 callersFunctionget_post_summary_string
(post_obj_from_store, main_author_name_for_summary)
PromptMakers/3.2PromptMaker.py:223
↓ 4 callersFunctioncalculate_metrics
Calculates accuracy, F1 score, and MCC.
LLMEvaluators/3.1/GPT.py:104
↓ 4 callersFunctioncalculate_metrics
Calculates accuracy, F1 score, and MCC.
demo/GPT3.1.py:100
↓ 4 callersFunctionconvert_datetimes_to_strings_in_obj
(obj)
PromptMakers/3.1_RandPrompt.py:63
↓ 4 callersFunctionparse_timestamp
(ts_str)
PromptMakers/3.3_RandPrompt.py:27
↓ 4 callersFunctionparse_timestamp
(ts_str)
PromptMakers/3.2_RandPrompt.py:32
↓ 4 callersFunctionsetup_logger
Sets up a logger that writes to a file and console.
LLMEvaluators/3.1/Claude.py:53
↓ 3 callersFunctioncalculate_regression_metrics
Calculates MSE, RMSE, MAE.
LLMEvaluators/3.2/GPT.py:84
↓ 3 callersFunctioncalculate_regression_metrics
Calculates MSE, RMSE, MAE.
LLMEvaluators/3.2/Claude.py:99
↓ 3 callersFunctioncalculate_regression_metrics
Calculates MSE, RMSE, MAE.
demo/GPT3.2.py:72
↓ 3 callersFunctionconvert_datetimes_to_strings_in_obj
(obj)
demo/3.2PromptMaker.py:76
↓ 3 callersFunctionconvert_datetimes_to_strings_in_obj
(obj, for_history=False)
demo/3.3PromptMaker.py:61
↓ 3 callersFunctionconvert_datetimes_to_strings_in_obj
(obj)
PromptMakers/3.2_RandPrompt.py:69
↓ 3 callersFunctionconvert_datetimes_to_strings_in_obj
(obj)
PromptMakers/3.2PromptMaker.py:76
↓ 3 callersFunctionconvert_datetimes_to_strings_in_obj
(obj, for_history=False)
PromptMakers/3.3PromptMaker.py:61
↓ 3 callersFunctiondatetime_to_string
(dt_obj)
demo/3.3PromptMaker.py:51
↓ 3 callersFunctiondatetime_to_string
(dt_obj)
PromptMakers/3.3PromptMaker.py:51
↓ 3 callersFunctionlog_domain_metrics
(current_domain_stats, logger_instance, meteor_is_available_flag)
LLMEvaluators/3.3/GPT-4o-mini.py:323
↓ 3 callersFunctionlog_domain_metrics
(current_domain_stats, logger_instance, meteor_is_available_flag)
LLMEvaluators/3.3/GPT4.1.py:321
↓ 3 callersFunctionlog_domain_metrics
(current_domain_stats, logger_instance, meteor_is_available_flag)
demo/GPT3.3.py:321
↓ 3 callersFunctionparse_timestamp
(ts_str)
PromptMakers/3.1_RandPrompt.py:26
↓ 3 callersFunctionsetup_logger
Sets up a logger that writes to a file and console.
LLMEvaluators/3.2/Claude.py:55
↓ 2 callersFunctionbuild_dialogue_tree_with_hidden_score
(post_data_with_ids, node_id_to_hide_score_of)
demo/3.1PromptMaker.py:195
↓ 2 callersFunctionbuild_dialogue_tree_with_hidden_score
(post_data_with_ids, node_id_to_hide_score_of)
PromptMakers/3.2_RandPrompt.py:185
↓ 2 callersFunctionbuild_dialogue_tree_with_hidden_score
(post_data_with_ids, node_id_to_hide_score_of)
PromptMakers/3.1PromptMaker.py:195
↓ 2 callersFunctioncalculate_average_metrics
(metrics_summary)
LLMEvaluators/LogEvaluator/LogEval3.3.py:350
↓ 2 callersFunctioncalculate_metrics_sklearn
Calculates accuracy, F1, precision, recall, MCC using sklearn.
LLMEvaluators/3.1/Claude.py:155
↓ 2 callersFunctioncalculate_removed_percentage_in_tree
(tree_nodes_list)
PromptMakers/3.3_RandPrompt.py:261
↓ 2 callersFunctionconvert_datetimes_to_strings_in_obj
(obj)
demo/3.1PromptMaker.py:72
↓ 2 callersFunctionconvert_datetimes_to_strings_in_obj
(obj, for_history=False)
PromptMakers/3.3_RandPrompt.py:81
↓ 2 callersFunctionconvert_datetimes_to_strings_in_obj
(obj)
PromptMakers/3.1PromptMaker.py:72
↓ 2 callersFunctionencode_image
(image_path)
LLMEvaluators/3.1/LlamaAndDeepSeek_batch_eval.py:73
↓ 2 callersFunctionencode_image
(image_path)
LLMEvaluators/3.2/LlamaAndDeepSeek_batch_eval.py:73
↓ 2 callersFunctionfind_author_replies_for_body_prediction
(flat_nodes_list, post_author_name)
PromptMakers/3.3_RandPrompt.py:152
↓ 2 callersFunctionfind_author_replies_in_post_for_score_prediction
(flat_nodes_list, post_author_name)
PromptMakers/3.1_RandPrompt.py:140
↓ 2 callersFunctiongenerate_unique_ids_for_post
(post_data, post_index_prefix)
PromptMakers/3.3_RandPrompt.py:105
↓ 2 callersFunctiongenerate_unique_ids_for_post
(post_data, post_index_prefix)
PromptMakers/3.1_RandPrompt.py:81
↓ 2 callersFunctionget_nodes_in_dialogue_tree
(all_post_nodes_flat, tlc_id_for_tree)
PromptMakers/3.3_RandPrompt.py:236
↓ 2 callersFunctionget_post_summary_string_for_prompt
(post_obj, is_few_shot_unrelated=False)
PromptMakers/3.1_RandPrompt.py:304
↓ 2 callersFunctionget_thread_embedding
(thread_nodes, sbert_model_instance, device_to_use)
LLMEvaluators/3.3/GPT-4o-mini.py:220
↓ 2 callersFunctionget_thread_embedding
(thread_nodes, local_sbert_model, local_device)
LLMEvaluators/3.3/GPT4.1_Random_Task.py:176
↓ 2 callersFunctionget_thread_embedding
(thread_nodes, sbert_model_instance, device_to_use)
LLMEvaluators/3.3/GPT4.1.py:218
↓ 2 callersFunctionget_thread_embedding
(thread_nodes, sbert_model_instance, device_to_use)
demo/GPT3.3.py:218
↓ 2 callersFunctionget_tlc_id_for_target_reply
(target_reply_node, nodes_map, root_post_id)
PromptMakers/3.3_RandPrompt.py:218
↓ 2 callersFunctionis_rate_limit_error
(exception)
LLMEvaluators/3.2/GPT.py:74
↓ 2 callersFunctionis_rate_limit_error
(exception)
demo/GPT3.2.py:62
↓ 2 callersFunctionparse_timestamp
(ts_str)
demo/3.1PromptMaker.py:32
↓ 2 callersFunctionparse_timestamp
(ts_str)
demo/3.2PromptMaker.py:36
↓ 2 callersFunctionparse_timestamp
(ts_str)
demo/3.3PromptMaker.py:28
↓ 2 callersFunctionparse_timestamp
(ts_str)
PromptMakers/3.1PromptMaker.py:32
↓ 2 callersFunctionparse_timestamp
(ts_str)
PromptMakers/3.2PromptMaker.py:36
↓ 2 callersFunctionparse_timestamp
(ts_str)
PromptMakers/3.3PromptMaker.py:28
↓ 2 callersMethodprepare_prompt
(self, system_message: str, prompt: str, image: str = None)
LLMEvaluators/3.1/LlamaAndDeepSeek_batch_eval.py:304
↓ 2 callersMethodprepare_prompt
(self, system_message: str, prompt: str, image: str = None)
LLMEvaluators/3.2/LlamaAndDeepSeek_batch_eval.py:304
↓ 2 callersFunctionsetup_logger
Sets up a logger that writes to a file and console.
LLMEvaluators/3.2/GPT.py:53
↓ 2 callersFunctionsetup_logger
Sets up a logger that writes to a file and console.
demo/GPT3.2.py:41
↓ 1 callersMethod_amazon_nova_pro_single_call
( # This should be synchronous if single_call is synchronous self, prompt: str,
LLMEvaluators/3.1/LlamaAndDeepSeek_batch_eval.py:391
↓ 1 callersMethod_amazon_nova_pro_single_call
( # This should be synchronous if single_call is synchronous self, prompt: str,
LLMEvaluators/3.2/LlamaAndDeepSeek_batch_eval.py:391
↓ 1 callersFunction_assign_ids_recursive
(comments_list, parent_id_str_rec)
demo/3.1PromptMaker.py:114
↓ 1 callersFunction_assign_ids_recursive
(comments_list, parent_id_str_rec)
demo/3.2PromptMaker.py:118
↓ 1 callersFunction_assign_ids_recursive
(comments_list, parent_id_str_rec)
demo/3.3PromptMaker.py:102
↓ 1 callersFunction_assign_ids_recursive
(comments_list, parent_id_str_rec)
PromptMakers/3.3_RandPrompt.py:125
↓ 1 callersFunction_assign_ids_recursive
(comments_list, parent_id_str_rec)
PromptMakers/3.2_RandPrompt.py:112
↓ 1 callersFunction_assign_ids_recursive
(comments_list, parent_id_str_rec)
PromptMakers/3.1_RandPrompt.py:108
↓ 1 callersFunction_assign_ids_recursive
(comments_list, parent_id_str_rec)
PromptMakers/3.1PromptMaker.py:114
↓ 1 callersFunction_assign_ids_recursive
(comments_list, parent_id_str_rec)
PromptMakers/3.2PromptMaker.py:118
↓ 1 callersFunction_assign_ids_recursive
(comments_list, parent_id_str_rec)
PromptMakers/3.3PromptMaker.py:102
↓ 1 callersMethod_batch_call_nova_pro_async
( # Renamed to indicate it's async self, query_list: List[str], system_mes
LLMEvaluators/3.1/LlamaAndDeepSeek_batch_eval.py:529
↓ 1 callersMethod_batch_call_nova_pro_async
( # Renamed to indicate it's async self, query_list: List[str], system_mes
LLMEvaluators/3.2/LlamaAndDeepSeek_batch_eval.py:529
↓ 1 callersFunction_recursive_remove
(comments_list)
PromptMakers/3.3_RandPrompt.py:288
↓ 1 callersFunction_throttled_openai_chat_completion_acreate
( client: openai.AsyncOpenAI, limiter: aiolimiter.AsyncLimiter, model: str, qu
LLMEvaluators/3.1/LlamaAndDeepSeek_batch_eval.py:85
↓ 1 callersFunction_throttled_openai_chat_completion_acreate
( client: openai.AsyncOpenAI, limiter: aiolimiter.AsyncLimiter, model: str, qu
LLMEvaluators/3.2/LlamaAndDeepSeek_batch_eval.py:85
↓ 1 callersMethodbatch_call
( self, query_list: List[str], system_message: str, image_list
LLMEvaluators/3.1/LlamaAndDeepSeek_batch_eval.py:452
↓ 1 callersMethodbatch_call
( self, query_list: List[str], system_message: str, image_list
LLMEvaluators/3.2/LlamaAndDeepSeek_batch_eval.py:452
next →1–100 of 235, ranked by callers