Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/RUC-NLPIR/WebThinker
/ functions
Functions
400 in github.com/RUC-NLPIR/WebThinker
⨍
Functions
400
◇
Types & classes
45
↳
Endpoints
1
↓ 1 callers
Method
_load_all
(self)
demo/settings.py:74
↓ 1 callers
Method
_load_client
(self, api_base_url, aux_api_base_url)
demo/settings.py:89
↓ 1 callers
Method
_load_lora
(self, lora_name, lora_path)
demo/settings.py:99
↓ 1 callers
Function
_remove_right_units
(string)
scripts/utils/math_equivalence.py:46
↓ 1 callers
Method
_run_single
(self, prompt: list[dict[str, str]])
scripts/lcb_runner/runner/deepseek_runner.py:32
↓ 1 callers
Method
acquire
获取一个令牌,如果没有可用令牌则等待
scripts/search/bing_search.py:485
↓ 1 callers
Method
acquire
获取一个令牌,如果没有可用令牌则等待
demo/bing_search.py:459
↓ 1 callers
Method
add_child_env
(self)
demo/settings.py:143
↓ 1 callers
Function
app
()
demo/run_demo.py:66
↓ 1 callers
Method
args
Overload a function based on the specified argument types. :param argtypes: The argument types. If None is given, get the argument types f
scripts/lcb_runner/pyext/pyext-0.7/pyext.py:185
↓ 1 callers
Function
bing_web_search
Perform a search using the Bing Web Search API with a set timeout. Args: query (str): Search query. subscription_key (str):
demo/bing_search.py:283
↓ 1 callers
Function
build_runner
(args, model: LanguageModel)
scripts/lcb_runner/runner/runner_utils.py:4
↓ 1 callers
Function
chdir
(root)
scripts/lcb_runner/evaluation/utils_execute.py:175
↓ 1 callers
Function
check_correctness
Evaluates the functional correctness of a completion by running the test suite provided in the problem. :param completion_id: an optiona
scripts/lcb_runner/evaluation/utils_execute.py:64
↓ 1 callers
Function
check_correctness
Check correctness of code generation with a global timeout. The global timeout is to catch some extreme/rare cases not handled by the timeouts
scripts/lcb_runner/evaluation/compute_code_generation_metrics.py:26
↓ 1 callers
Function
check_testcase_output
(testcase_str, expected_output)
scripts/lcb_runner/evaluation/compute_test_output_prediction_metrics.py:39
↓ 1 callers
Function
code_execution_metrics
( samples, generations, )
scripts/lcb_runner/evaluation/compute_code_execution_metrics.py:25
↓ 1 callers
Function
combine_results
( scenario: Scenario, results: list[list[str]], model: LanguageModel, cot_code_execution: bool
scripts/lcb_runner/runner/scenario_router.py:79
↓ 1 callers
Function
compute_scores
(args)
scripts/lcb_runner/evaluation/compute_scores.py:72
↓ 1 callers
Function
create_chat_completion
Generate a chat completion with retry logic
scripts/evaluate/evaluate_report.py:207
↓ 1 callers
Function
create_tempdir
()
scripts/lcb_runner/evaluation/utils_execute.py:143
↓ 1 callers
Function
custom_compare_
(output, ground_truth)
scripts/lcb_runner/evaluation/testing_util.py:629
↓ 1 callers
Function
debug
(idx)
scripts/lcb_runner/evaluation/old_results_check.py:19
↓ 1 callers
Method
default
Executed if quit wasn't called.
scripts/lcb_runner/pyext/pyext-0.7/pyext.py:298
↓ 1 callers
Function
estimator
Calculates 1 - comb(n - c, k) / comb(n, k).
scripts/lcb_runner/evaluation/pass_k_utils.py:7
↓ 1 callers
Function
evaluate_generations
We take the list of code generations and try to compile them and the run their corresponding unit tests which are retrieved from the APPS dataset
scripts/lcb_runner/evaluation/compute_code_generation_metrics.py:105
↓ 1 callers
Function
evaluate_predictions
(output, labeled_answer, mode='math', use_llm=False, question=None, extract_answer=False)
scripts/evaluate/evaluate.py:174
↓ 1 callers
Function
extract_answer_fn
(output, mode='qa', extract_answer=False)
demo/utils.py:14
↓ 1 callers
Function
extract_between
Extracts text between two markers in a string. Parameters: - text (str): The source text to extract from - start_marker (str): The s
scripts/run_search_o1.py:315
↓ 1 callers
Function
extract_execution_code
(model_output: str, lmstyle: LMStyle, cot: bool = False)
scripts/lcb_runner/utils/extraction_utils.py:48
↓ 1 callers
Function
extract_markdown_content
Extract content between ```markdown and ``` tags.
scripts/run_naive_rag_report.py:111
↓ 1 callers
Function
extract_pdf_text
Extract text from a PDF. Args: url (str): URL of the PDF file. Returns: str: Extracted text content or error message.
scripts/search/bing_search.py:363
↓ 1 callers
Function
extract_pdf_text
Extract text from a PDF. Args: url (str): URL of the PDF file. Returns: str: Extracted text content or error message.
demo/bing_search.py:337
↓ 1 callers
Function
extract_pdf_text_async
Asynchronously extract text from a PDF. Args: url (str): URL of the PDF file. session (aiohttp.ClientSession): Aiohttp clien
scripts/search/bing_search.py:634
↓ 1 callers
Function
extract_pdf_text_async
Asynchronously extract text from a PDF. Args: url (str): URL of the PDF file. session (aiohttp.ClientSession): Aiohttp clien
demo/bing_search.py:602
↓ 1 callers
Function
extract_scores
(response_text)
scripts/evaluate/evaluate_report.py:193
↓ 1 callers
Function
extract_test_output_code
(model_output: str, lmstyle: LMStyle = None)
scripts/lcb_runner/utils/extraction_utils.py:19
↓ 1 callers
Function
extract_text_from_url
Extract text from a URL. If a snippet is provided, extract the context related to it. Args: url (str): URL of a webpage or PDF.
scripts/search/bing_search.py:153
↓ 1 callers
Function
extract_text_from_url
Extract text from a URL. If a snippet is provided, extract the context related to it. Args: url (str): URL of a webpage or PDF.
demo/bing_search.py:149
↓ 1 callers
Function
extract_text_from_url_async
Async version of extract_text_from_url
scripts/search/bing_search.py:505
↓ 1 callers
Function
extract_text_from_url_async
Async version of extract_text_from_url
demo/bing_search.py:482
↓ 1 callers
Function
f1_score
Calculate the F1 score between two sets of words.
scripts/search/bing_search.py:95
↓ 1 callers
Function
f1_score
Calculate the F1 score between two sets of words.
demo/bing_search.py:91
↓ 1 callers
Function
format_prompt_self_repair
( question: str, LanguageModelStyle: LMStyle, code, result, metadata )
scripts/lcb_runner/prompts/self_repair.py:175
↓ 1 callers
Function
format_testcase_func_name_input
use the form of "assert func_name(input) == "
scripts/lcb_runner/prompts/test_output_prediction.py:44
↓ 1 callers
Function
generate_all_responses
Generate all responses concurrently with a limit
scripts/run_naive_rag.py:99
↓ 1 callers
Function
generate_all_responses
Generate all responses concurrently with a limit
scripts/run_direct_gen.py:180
↓ 1 callers
Function
generate_deep_web_explorer
Generate deep web exploration with multiple search and click operations Returns the output, list of interaction records, and initial prompt
scripts/run_web_thinker_report.py:227
↓ 1 callers
Function
generate_deep_web_explorer
Generate deep web exploration with multiple search and click operations Returns the output, list of interaction records, and initial prompt
scripts/run_web_thinker.py:220
↓ 1 callers
Function
generate_deep_web_explorer
( env, search_query: str, search_intent: str, document: str, )
demo/run_logit.py:167
↓ 1 callers
Function
generate_response
Generate a response using the chat API
scripts/run_naive_rag_report.py:131
↓ 1 callers
Function
generate_response
( client: AsyncOpenAI, prompt: str, semaphore: asyncio.Semaphore, temperature: float, top_
scripts/run_direct_gen.py:139
↓ 1 callers
Function
generate_webpage_to_reasonchain
( client: AsyncOpenAI, original_question: str, prev_reasoning: str, search_query: str, doc
scripts/run_search_o1.py:272
↓ 1 callers
Function
get_base_model_question_template_answer
(question: CodeGenerationProblem)
scripts/lcb_runner/prompts/code_generation.py:173
↓ 1 callers
Function
get_cache_path
(model_repr:str, args)
scripts/lcb_runner/utils/path_utils.py:15
↓ 1 callers
Function
get_click_intent_instruction
(prev_reasoning)
scripts/prompts/prompts.py:101
↓ 1 callers
Function
get_click_intent_instruction
(question, prev_reasoning)
scripts/prompts/prompts_report.py:155
↓ 1 callers
Function
get_click_intent_instruction
(prev_reasoning)
demo/prompts.py:78
↓ 1 callers
Function
get_click_web_page_reader_instruction
(click_intent, document)
scripts/prompts/prompts_report.py:132
↓ 1 callers
Function
get_cllama_question_template_answer
(question: CodeGenerationProblem)
scripts/lcb_runner/prompts/code_generation.py:52
↓ 1 callers
Function
get_cllama_question_template_answer
( question: TestOutputPredictionProblem, testcase_input: str )
scripts/lcb_runner/prompts/test_output_prediction.py:84
↓ 1 callers
Function
get_cllama_question_template_answer
(question: str, code, result, metadata)
scripts/lcb_runner/prompts/self_repair.py:74
↓ 1 callers
Function
get_code_search_o1_instruction
(MAX_SEARCH_LIMIT)
scripts/prompts/prompts.py:180
↓ 1 callers
Function
get_deep_web_explorer_instruction
(search_query, search_intent, search_result)
scripts/prompts/prompts.py:30
↓ 1 callers
Function
get_deep_web_explorer_instruction
(search_query, search_intent, search_result)
scripts/prompts/prompts_report.py:93
↓ 1 callers
Function
get_deep_web_explorer_instruction
(search_query, search_intent, search_result)
demo/prompts.py:27
↓ 1 callers
Function
get_deepseekcode_question_template_answer
(question: CodeGenerationProblem)
scripts/lcb_runner/prompts/code_generation.py:64
↓ 1 callers
Function
get_deepseekcode_question_template_answer
( question: TestOutputPredictionProblem, testcase_input: str )
scripts/lcb_runner/prompts/test_output_prediction.py:93
↓ 1 callers
Function
get_deepseekcode_question_template_answer
(question: str, code, result, metadata)
scripts/lcb_runner/prompts/self_repair.py:84
↓ 1 callers
Function
get_detailed_web_page_reader_instruction
(query, search_intent, document)
scripts/prompts/prompts.py:75
↓ 1 callers
Function
get_edit_article_instruction
(edit_instruction, article)
scripts/prompts/prompts_report.py:202
↓ 1 callers
Function
get_eval_all_output_path
(model_repr:str, args)
scripts/lcb_runner/utils/path_utils.py:34
↓ 1 callers
Function
get_final_report_instruction
(question, article)
scripts/prompts/prompts_report.py:262
↓ 1 callers
Function
get_gpqa_search_o1_instruction
(MAX_SEARCH_LIMIT)
scripts/prompts/prompts.py:136
↓ 1 callers
Function
get_magicoder_question_template_answer
(question: CodeGenerationProblem)
scripts/lcb_runner/prompts/code_generation.py:111
↓ 1 callers
Function
get_magicoder_question_template_answer
( question: TestOutputPredictionProblem, testcase_input: str )
scripts/lcb_runner/prompts/test_output_prediction.py:102
↓ 1 callers
Function
get_magicoder_question_template_answer
(question: str, code, result, metadata)
scripts/lcb_runner/prompts/self_repair.py:95
↓ 1 callers
Function
get_math_search_o1_instruction
(MAX_SEARCH_LIMIT)
scripts/prompts/prompts.py:158
↓ 1 callers
Function
get_multiqa_search_o1_instruction
(MAX_SEARCH_LIMIT)
demo/prompts.py:1
↓ 1 callers
Function
get_naive_rag_instruction
(question, documents)
scripts/prompts/prompts.py:314
↓ 1 callers
Function
get_parser
()
scripts/lcb_runner/evaluation/compute_scores.py:15
↓ 1 callers
Function
get_phind_question_template_answer
(question: CodeGenerationProblem)
scripts/lcb_runner/prompts/code_generation.py:141
↓ 1 callers
Function
get_phind_question_template_answer
( question: TestOutputPredictionProblem, testcase_input: str )
scripts/lcb_runner/prompts/test_output_prediction.py:128
↓ 1 callers
Function
get_phind_question_template_answer
(question: str, code, result, metadata)
scripts/lcb_runner/prompts/self_repair.py:133
↓ 1 callers
Function
get_query_plan_instruction
(question)
scripts/prompts/prompts.py:108
↓ 1 callers
Function
get_qwen_question_template_answer
(question: CodeGenerationProblem)
scripts/lcb_runner/prompts/code_generation.py:81
↓ 1 callers
Function
get_qwen_question_template_answer
(question: TestOutputPredictionProblem, testcase_input: str)
scripts/lcb_runner/prompts/test_output_prediction.py:135
↓ 1 callers
Function
get_qwen_question_template_answer
(question: str, code, result, metadata)
scripts/lcb_runner/prompts/self_repair.py:143
↓ 1 callers
Function
get_report_evaluation_instruction
(question, system_a, system_b, system_c, system_d, system_e)
scripts/evaluate/evaluate_report.py:57
↓ 1 callers
Function
get_report_webthinker_instruction
(question, plan)
scripts/prompts/prompts_report.py:2
↓ 1 callers
Function
get_search_intent_instruction
(prev_reasoning)
scripts/prompts/prompts.py:95
↓ 1 callers
Function
get_search_intent_instruction
(question, prev_reasoning)
scripts/prompts/prompts_report.py:148
↓ 1 callers
Function
get_search_intent_instruction
(prev_reasoning)
demo/prompts.py:72
↓ 1 callers
Function
get_search_plan_instruction
(query)
scripts/prompts/prompts_report.py:72
↓ 1 callers
Function
get_search_result
(env, search_query, search_intent)
demo/run_logit.py:97
↓ 1 callers
Function
get_singleqa_search_o1_instruction
(MAX_SEARCH_LIMIT)
scripts/prompts/prompts.py:243
↓ 1 callers
Function
get_standard_rag_report_instruction
(question, documents)
scripts/prompts/prompts_report.py:284
↓ 1 callers
Function
get_task_instruction_openqa
(question)
demo/prompts.py:64
↓ 1 callers
Function
get_title_instruction
(question, article)
scripts/prompts/prompts_report.py:250
↓ 1 callers
Function
get_web_page_reader_instruction
(query, document)
scripts/prompts/prompts.py:70
← previous
next →
101–200 of 400, ranked by callers