MCPcopy Create free account

hub / github.com/JingbiaoMei/ATM-Bench / functions

Functions815 in github.com/JingbiaoMei/ATM-Bench

⨍ Functions 815◇ Types & classes 49
↓ 1 callersMethod_chat_openai
(self, messages: List[Dict[str, Any]])
memqa/utils/evaluator/evaluate_qa.py:469
↓ 1 callersMethod_chat_openai_with_usage
( self, messages: List[Dict[str, Any]] )
memqa/qa_agent_baselines/oracle/oracle_baseline.py:142
↓ 1 callersMethod_chat_openai_with_usage
( self, messages: List[Dict[str, Any]] )
memqa/qa_agent_baselines/MMRag/llm_utils.py:253
↓ 1 callersMethod_chat_vllm_http
(self, messages: List[Dict[str, Any]])
memqa/qa_agent_baselines/oracle/oracle_baseline.py:210
↓ 1 callersMethod_chat_vllm_http
(self, messages: List[Dict[str, Any]])
memqa/qa_agent_baselines/MMRag/llm_utils.py:321
↓ 1 callersMethod_chat_vllm_http
(self, messages: List[Dict[str, Any]])
memqa/utils/evaluator/evaluate_qa.py:518
↓ 1 callersMethod_chat_vllm_http_with_usage
( self, messages: List[Dict[str, Any]] )
memqa/qa_agent_baselines/oracle/oracle_baseline.py:246
↓ 1 callersMethod_chat_vllm_http_with_usage
( self, messages: List[Dict[str, Any]] )
memqa/qa_agent_baselines/MMRag/llm_utils.py:345
↓ 1 callersMethod_chat_vllm_local
(self, messages: List[Dict[str, Any]])
memqa/qa_agent_baselines/oracle/oracle_baseline.py:292
↓ 1 callersMethod_chat_vllm_local
(self, messages: List[Dict[str, Any]])
memqa/qa_agent_baselines/MMRag/llm_utils.py:379
↓ 1 callersMethod_chat_vllm_local_with_usage
( self, messages: List[Dict[str, Any]] )
memqa/qa_agent_baselines/oracle/oracle_baseline.py:312
↓ 1 callersMethod_chat_vllm_local_with_usage
( self, messages: List[Dict[str, Any]] )
memqa/qa_agent_baselines/MMRag/llm_utils.py:398
↓ 1 callersFunction_coerce_accuracy
(value: Any)
memqa/utils/evaluator/evaluate_qa.py:949
↓ 1 callersFunction_compact_whitespace
(text: str)
memqa/utils/evaluator/qtype_utils.py:64
↓ 1 callersMethod_detect_mode
(self, model_name: str)
memqa/retrieve/rerankers.py:93
↓ 1 callersMethod_encode_batch
Encode a batch of texts.
memqa/qa_agent_baselines/HippoRag2/local_embeddings.py:119
↓ 1 callersMethod_encode_images
(self, image_paths: List[Optional[Path]])
memqa/retrieve/retrievers.py:566
↓ 1 callersFunction_ensure_simplemem_config_file
(simplemem_dir: Optional[str])
memqa/qa_agent_baselines/SimpleMem/simplemem_baseline.py:1216
↓ 1 callersFunction_ensure_simplemem_on_path
(simplemem_dir: Optional[str])
memqa/qa_agent_baselines/SimpleMem/simplemem_baseline.py:1206
↓ 1 callersFunction_extract_evidence_ids
(text: str)
memqa/utils/evaluator/qtype_utils.py:68
↓ 1 callersFunction_extract_json_object
(text: str)
memqa/qa_agent_baselines/MMRag/mmrag_utils.py:230
↓ 1 callersFunction_extract_list_ids_from_text
Extract memory item IDs from free-text prose. Applied uniformly to *all* prediction sources during list_jaccard scoring so that agent systems
memqa/utils/evaluator/evaluate_qa.py:56
↓ 1 callersFunction_extract_openai_response_text_and_refusal
(response: Any)
memqa/utils/evaluator/evaluate_qa.py:379
↓ 1 callersMethod_extract_text_from_eml
Extract text content from EML file.
memqa/mem_processor/email/email_processor.py:251
↓ 1 callersFunction_find_first_json_object
(text: str)
agent_systems/extract_usage.py:45
↓ 1 callersFunction_find_opencode_write_answer
opencode traces may include a tool call that writes `output/answer.json`. Prefer the written JSON content if present, since some agents write
agent_systems/extract_answer.py:387
↓ 1 callersMethod_format_eta
Format ETA in a human-readable format.
memqa/mem_processor/image/batch_processor.py:190
↓ 1 callersMethod_format_eta
Format ETA in a human-readable format.
memqa/mem_processor/video/batch_processor.py:162
↓ 1 callersMethod_format_neighbor_text
(self, neighbor_indices: List[int])
memqa/qa_agent_baselines/A-Mem/memory_layer.py:641
↓ 1 callersFunction_format_range
(year: Optional[int], month: int, start_day: int, end_day: int)
memqa/utils/evaluator/normalizer.py:359
↓ 1 callersMethod_get_cache_key
Get a stable cache key from the filename (stem without extension).
memqa/mem_processor/image/image_processor.py:99
↓ 1 callersMethod_get_cache_path
Get cache file path for a given email and cache type.
memqa/mem_processor/email/email_processor.py:105
↓ 1 callersFunction_has_alpha
(tokens: Iterable[str])
memqa/utils/evaluator/qtype_utils.py:81
↓ 1 callersFunction_has_list_conjunction
(text: str)
memqa/utils/evaluator/qtype_utils.py:104
↓ 1 callersFunction_is_evidence_id_list
(answer: str)
memqa/utils/evaluator/qtype_utils.py:155
↓ 1 callersFunction_is_usage_like
(d: Dict[str, Any])
agent_systems/extract_usage.py:188
↓ 1 callersFunction_load_build_checkpoint
(db_path: Path)
memqa/qa_agent_baselines/SimpleMem/simplemem_baseline.py:1710
↓ 1 callersMethod_load_checkpoint
Load previous checkpoint if exists.
memqa/mem_processor/image/batch_processor.py:139
↓ 1 callersMethod_load_checkpoint
Load previous checkpoint if exists.
memqa/mem_processor/email/batch_processor.py:155
↓ 1 callersMethod_load_checkpoint
Load previous checkpoint if exists.
memqa/mem_processor/video/batch_processor.py:111
↓ 1 callersMethod_load_emails
Load emails from merged_emails.json.
memqa/qa_agent_baselines/HippoRag2/data_adapter.py:274
↓ 1 callersMethod_load_from_cache
Load data from cache if it exists.
memqa/mem_processor/email/email_processor.py:110
↓ 1 callersMethod_load_image
(self, path: Path)
memqa/retrieve/retrievers.py:553
↓ 1 callersMethod_load_image_batch_results
Load image batch results.
memqa/qa_agent_baselines/HippoRag2/data_adapter.py:284
↓ 1 callersMethod_load_previous_results
Load previous results if they exist.
memqa/mem_processor/email/batch_processor.py:161
↓ 1 callersMethod_load_video_batch_results
Load video batch results.
memqa/qa_agent_baselines/HippoRag2/data_adapter.py:299
↓ 1 callersMethod_memory_doc
(self, note: MemoryNote)
memqa/qa_agent_baselines/A-Mem/memory_layer.py:428
↓ 1 callersFunction_normalize_pi_usage
Pi exposes usage on each `message_end` event as {"input": N, "output": N, "cacheRead": N, "cacheWrite": N, "totalTokens": N, "co
agent_systems/extract_usage.py:494
↓ 1 callersFunction_normalize_support
(value: Any)
memqa/qa_agent_baselines/MMRag/mmrag_utils.py:245
↓ 1 callersFunction_openclaw_model
(obj: Any)
agent_systems/extract_usage.py:222
↓ 1 callersMethod_parse_eml_headers
Basic EML header parsing.
memqa/mem_processor/email/email_processor.py:210
↓ 1 callersFunction_pi_model
(events: List[Dict[str, Any]])
agent_systems/extract_usage.py:570
↓ 1 callersMethod_process_email_chunk_concurrent
Process a chunk of emails concurrently using ThreadPoolExecutor.
memqa/mem_processor/email/batch_processor.py:168
↓ 1 callersMethod_process_image_chunk_concurrent
Process a chunk of images concurrently using ThreadPoolExecutor.
memqa/mem_processor/image/batch_processor.py:150
↓ 1 callersMethod_process_memory
(self, note: MemoryNote)
memqa/qa_agent_baselines/A-Mem/memory_layer.py:483
↓ 1 callersMethod_process_video_chunk_concurrent
Process a chunk of videos concurrently using ThreadPoolExecutor.
memqa/mem_processor/video/batch_processor.py:122
↓ 1 callersMethod_query_openai
Query OpenAI vision model with image and prompt.
memqa/mem_processor/image/image_processor.py:269
↓ 1 callersMethod_query_openai_multi
Query OpenAI vision model with multiple images.
memqa/mem_processor/video/video_processor.py:282
↓ 1 callersMethod_query_openai_text
Query OpenAI text model with text-only prompt.
memqa/mem_processor/image/image_processor.py:350
↓ 1 callersMethod_query_openai_text
Query OpenAI text model with text-only prompt.
memqa/mem_processor/video/video_processor.py:348
↓ 1 callersMethod_query_vllm
Query VLLM model with image and prompt.
memqa/mem_processor/image/image_processor.py:311
↓ 1 callersMethod_query_vllm_multi
Query VLLM model with multiple images.
memqa/mem_processor/video/video_processor.py:315
↓ 1 callersMethod_query_vllm_text
Query VLLM model with text-only prompt.
memqa/mem_processor/image/image_processor.py:383
↓ 1 callersMethod_query_vllm_text
Query VLLM model with text-only prompt.
memqa/mem_processor/video/video_processor.py:372
↓ 1 callersFunction_records_from_claude_jsonl
(events: List[Dict[str, Any]])
agent_systems/extract_usage.py:457
↓ 1 callersFunction_records_from_openclaw_json
(obj: Any)
agent_systems/extract_usage.py:588
↓ 1 callersFunction_records_from_opencode_jsonl
(events: Iterable[Dict[str, Any]])
agent_systems/extract_usage.py:422
↓ 1 callersFunction_records_from_pi_jsonl
Iterate pi JSONL events and build one usage record per assistant `message_end`. Each assistant turn produces a single `message_end` whose `me
agent_systems/extract_usage.py:533
↓ 1 callersMethod_resolve_image_path
(self, item: RetrievalItem)
memqa/retrieve/retrievers.py:606
↓ 1 callersMethod_resolve_link_index
(self, link_id: Union[int, str])
memqa/qa_agent_baselines/A-Mem/memory_layer.py:631
↓ 1 callersMethod_resolve_positive_label_index
(self, num_labels: int)
memqa/retrieve/rerankers.py:138
↓ 1 callersMethod_resolve_yes_no_token_ids
(self)
memqa/retrieve/rerankers.py:105
↓ 1 callersFunction_save_item_id_mapping
( system: Any, items: List[RetrievalItem], db_path: str, )
memqa/qa_agent_baselines/SimpleMem/simplemem_baseline.py:1284
↓ 1 callersMethod_save_to_cache
Save data to cache.
memqa/mem_processor/email/email_processor.py:119
↓ 1 callersMethod_score_causal_lm
(self, inputs: Dict[str, torch.Tensor])
memqa/retrieve/rerankers.py:149
↓ 1 callersMethod_score_sequence_cls
(self, inputs: Dict[str, torch.Tensor])
memqa/retrieve/rerankers.py:124
↓ 1 callersMethod_setup_logging
Setup logging configuration.
memqa/mem_processor/image/image_processor.py:86
↓ 1 callersMethod_setup_logging
Setup logging for batch processing.
memqa/mem_processor/image/batch_processor.py:103
↓ 1 callersMethod_setup_logging
Setup logging configuration.
memqa/mem_processor/email/email_processor.py:92
↓ 1 callersMethod_setup_logging
Setup logging for batch processing.
memqa/mem_processor/email/batch_processor.py:101
↓ 1 callersMethod_setup_logging
Setup logging configuration.
memqa/mem_processor/video/video_processor.py:97
↓ 1 callersMethod_setup_logging
Setup logging for batch processing.
memqa/mem_processor/video/batch_processor.py:75
↓ 1 callersFunction_shell_export
(key: str, value: str)
agent_systems/config.py:45
↓ 1 callersMethod_split_into_chunks
Split a list into chunks of specified size.
memqa/mem_processor/image/batch_processor.py:186
↓ 1 callersMethod_split_into_chunks
Split a list into chunks of specified size.
memqa/mem_processor/email/batch_processor.py:204
↓ 1 callersMethod_split_into_chunks
Split a list into chunks of specified size.
memqa/mem_processor/video/batch_processor.py:158
↓ 1 callersFunction_strip_code_fences
(text: str)
memqa/qa_agent_baselines/MMRag/mmrag_utils.py:218
↓ 1 callersFunction_strip_item
(item: str)
memqa/utils/evaluator/qtype_utils.py:75
↓ 1 callersMethodadd_documents
(self, documents: List[str])
memqa/qa_agent_baselines/A-Mem/memory_layer.py:311
↓ 1 callersMethodanalyze_content
( content: str, llm: LLMController, image_path: Optional[str] = None )
memqa/qa_agent_baselines/A-Mem/memory_layer.py:184
↓ 1 callersMethodanalyze_email_content
Analyze email content using LLM.
memqa/mem_processor/email/email_processor.py:333
↓ 1 callersFunctionanswer_atm_with_simplemem_llm
Run the answer LLM through SimpleMem's OpenAI client but capture usage. SimpleMem's wrapper drops the ``usage`` block on the response. We bypass
memqa/qa_agent_baselines/SimpleMem/simplemem_baseline.py:1629
↓ 1 callersFunctionanswer_external_llm
( question: str, contexts: List[Any], llm: LLMClient, args: argparse.Namespace, )
memqa/qa_agent_baselines/SimpleMem/simplemem_baseline.py:1675
↓ 1 callersFunctionanswer_native_simplemem
( system: Any, question: str, contexts: List[Any], args: argparse.Namespace, )
memqa/qa_agent_baselines/SimpleMem/simplemem_baseline.py:1664
↓ 1 callersFunctionanswer_no_evidence
( hipporag: Any, questions: List[str], max_workers: int, )
memqa/qa_agent_baselines/HippoRag2/hipporag2_baseline.py:727
↓ 1 callersFunctionanswer_question
( qa: Dict[str, Any], args: argparse.Namespace, mem0_instance, llm_getter, )
memqa/qa_agent_baselines/mem0/mem0_baseline.py:1056
↓ 1 callersFunctionanswer_question
( llm: LLMClient, question: str, context: str, )
memqa/qa_agent_baselines/A-Mem/amem_baseline.py:703
↓ 1 callersFunctionanswer_question
( llm: LLMClient, question: str, context: str, )
memqa/qa_agent_baselines/Mempalace/mempalace_baseline.py:313
↓ 1 callersFunctionanswer_question_chat_api
Answer question using mem0-style agentic answering with automatic memory retrieval. Implements the same logic as mem0's Chat API but without
memqa/qa_agent_baselines/mem0/mem0_baseline.py:970
↓ 1 callersFunctionanswer_questions
( args: argparse.Namespace, hipporag: Any, qa_items: List[Dict[str, Any]], corpus: Any, ou
memqa/qa_agent_baselines/HippoRag2/hipporag2_baseline.py:776
← previousnext →301–400 of 815, ranked by callers