Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/Infinity-AILab/DeepResearchEval
/ functions
Functions
851 in github.com/Infinity-AILab/DeepResearchEval
⨍
Functions
851
◇
Types & classes
91
↳
Endpoints
19
Method
evaluate_query
Evaluate a single query (to be implemented by subclasses) Args: query_id: ID of the query to evaluate
point_quality/deepresearcharena/evaluator/base_evaluator.py:247
Method
evaluate_query
Evaluate a single query across all specified models
point_quality/deepresearcharena/evaluator/pointwise_evaluator.py:153
Method
execute_tool_call
(self, *, server_name, tool_name, arguments)
factual_eval/libs/miroflow-tool/src/miroflow/tool/manager_v2.py:89
Method
execute_tool_call
( self, *, server_name: str, tool_name: str, arguments: dict[str, Any] )
factual_eval/libs/miroflow-tool/src/miroflow/tool/manager.py:45
Function
expandAllSteps
()
factual_eval/apps/visualize-trace/static/js/script.js:848
Method
export
(self)
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/spans.py:155
Method
export
(self)
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/spans.py:262
Method
export
Exports a list of traces and spans. Args: items: The items to export.
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/processor_interface.py:69
Method
export
Export the trace as a dictionary.
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/traces.py:69
Method
export
(self)
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/traces.py:116
Method
export
(self)
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/traces.py:194
Method
export
Export the span data as a dictionary.
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/span_data.py:18
Method
export
(self)
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/span_data.py:53
Method
export
(self)
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/span_data.py:87
Method
export
(self)
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/span_data.py:129
Method
export
(self)
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/span_data.py:162
Method
export
(self)
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/span_data.py:185
Method
export
(self)
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/span_data.py:209
Method
export
(self)
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/span_data.py:233
Method
export
(self)
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/span_data.py:272
Method
export
(self)
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/span_data.py:313
Method
export
(self)
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/span_data.py:344
Method
export
(self)
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/span_data.py:370
Method
export
(self, items: list[Trace | Span[Any]])
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/otlp_exporter.py:51
Method
export
(self, items: list[Trace | Span[Any]])
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/otlp_exporter.py:101
Function
expose_sub_agents_as_tools
Expose sub-agents as tools
factual_eval/libs/miroflow/src/miroflow/utils/tool_utils.py:203
Method
extract_tool_calls_info
Extract tool call information from OpenAI LLM response
factual_eval/libs/miroflow/src/miroflow/llm/providers/claude_openrouter_client.py:289
Method
extract_tool_calls_info
Extract tool call information from Anthropic LLM response
factual_eval/libs/miroflow/src/miroflow/llm/providers/claude_anthropic_client.py:193
Method
extract_tool_calls_info
Extract tool call information from OpenAI LLM response
factual_eval/libs/miroflow/src/miroflow/llm/providers/deepseek_newapi_client.py:253
Method
extract_tool_calls_info
Extract tool call information from Qwen LLM response
factual_eval/libs/miroflow/src/miroflow/llm/providers/qwen_sglang_client.py:169
Method
extract_tool_calls_info
Extract tool call information from OpenAI Response API LLM response
factual_eval/libs/miroflow/src/miroflow/llm/providers/gpt_openai_response_client.py:297
Method
extract_tool_calls_info
Extract tool call information from OpenAI LLM response
factual_eval/libs/miroflow/src/miroflow/llm/providers/claude_newapi_client.py:257
Method
extract_tool_calls_info
Extract tool call information from OpenAI LLM response
factual_eval/libs/miroflow/src/miroflow/llm/providers/gpt_openai_client.py:295
Method
find_report_file
Find the report file for a given model and query
point_quality/deepresearcharena/evaluator/base_evaluator.py:134
Method
finish
Finish the trace. Args: reset_current: If true, the trace will be reset as the current trace.
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/traces.py:43
Function
fix_newlines
(match)
factual_eval/libs/miroflow/src/miroflow/utils/parsing_utils.py:378
Method
flow
(self, ctx: Context)
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/pocket/core_v2.py:49
Method
force_flush
Force the processors to flush their buffers.
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/provider.py:85
Method
force_flush
Forces an immediate flush of all queued spans/traces.
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/processor_interface.py:60
Method
force_flush
(self)
factual_eval/libs/miroflow/src/miroflow/logging/tracing_processor.py:43
Method
format_response
(tool)
factual_eval/libs/miroflow-tool/src/miroflow/tool/manager_v2.py:73
Method
format_token_usage_summary
Format token usage statistics and cost estimation, returns summary_lines for format_final_summary and log string - OpenAI implementation
factual_eval/libs/miroflow/src/miroflow/llm/providers/claude_openrouter_client.py:86
Method
format_token_usage_summary
Format token usage statistics and cost estimation, return summary_lines for format_final_summary and log string - Anthropic implementation
factual_eval/libs/miroflow/src/miroflow/llm/providers/claude_anthropic_client.py:233
Method
format_token_usage_summary
Format token usage statistics and cost estimation, returns summary_lines for format_final_summary and log string - OpenAI implementation
factual_eval/libs/miroflow/src/miroflow/llm/providers/deepseek_newapi_client.py:72
Method
format_token_usage_summary
Format token usage statistics and cost estimation, return summary_lines for format_final_summary and log string - Qwen implementation
factual_eval/libs/miroflow/src/miroflow/llm/providers/qwen_sglang_client.py:209
Method
format_token_usage_summary
Format token usage statistics and cost estimation, returns summary_lines for format_final_summary and log string - OpenAI Response API implementation
factual_eval/libs/miroflow/src/miroflow/llm/providers/gpt_openai_response_client.py:70
Method
format_token_usage_summary
Format token usage statistics and cost estimation, returns summary_lines for format_final_summary and log string - OpenAI implementation
factual_eval/libs/miroflow/src/miroflow/llm/providers/claude_newapi_client.py:76
Method
format_token_usage_summary
Format token usage statistics and cost estimation, return summary_lines for format_final_summary and log string - OpenAI implementation
factual_eval/libs/miroflow/src/miroflow/llm/providers/gpt_openai_client.py:68
Function
gen_group_id
Generate a new group ID.
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/util.py:25
Method
gen_group_id
Generate a new group ID.
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/provider.py:210
Function
gen_span_id
Generate a new span ID.
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/util.py:20
Function
gen_trace_id
Generate a new trace ID.
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/util.py:15
Method
generate
Generate experts for all domains. Args: domains: List of domain names Returns: List of expert info,
task_generation/generators/expert_generator.py:40
Method
generate_agent_system_prompt
(self, date, mcp_servers)
factual_eval/libs/miroflow/src/miroflow/llm/providers/claude_openrouter_client.py:360
Method
generate_agent_system_prompt
(self, date, mcp_servers)
factual_eval/libs/miroflow/src/miroflow/llm/providers/claude_anthropic_client.py:218
Method
generate_agent_system_prompt
(self, date, mcp_servers)
factual_eval/libs/miroflow/src/miroflow/llm/providers/deepseek_newapi_client.py:281
Method
generate_agent_system_prompt
(self, date, mcp_servers)
factual_eval/libs/miroflow/src/miroflow/llm/providers/qwen_sglang_client.py:194
Method
generate_agent_system_prompt
(self, date, mcp_servers)
factual_eval/libs/miroflow/src/miroflow/llm/providers/gpt_openai_response_client.py:319
Method
generate_agent_system_prompt
(self, date, mcp_servers)
factual_eval/libs/miroflow/src/miroflow/llm/providers/claude_newapi_client.py:285
Method
generate_agent_system_prompt
(self, date, mcp_servers)
factual_eval/libs/miroflow/src/miroflow/llm/providers/gpt_openai_client.py:323
Method
get_all_tool_definitions
Retrieve all tool definitions from active sessions. Ensures that each session is valid before interacting with it.
factual_eval/libs/miroflow-tool/src/miroflow/tool/manager_v2.py:69
Method
get_all_tool_definitions
(self)
factual_eval/libs/miroflow-tool/src/miroflow/tool/manager.py:44
Function
get_basic_info
Get basic information
factual_eval/apps/visualize-trace/app.py:117
Method
get_cost_summary
Get cost summary information
point_quality/deepresearcharena/utils/llm_call.py:168
Function
get_current_span
Returns the currently active span, if present.
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/create.py:84
Method
get_current_span
Returns the currently active span, if any.
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/provider.py:186
Function
get_current_trace
Returns the currently active trace, if present.
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/create.py:79
Method
get_current_trace
Returns the currently active trace, if any.
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/provider.py:180
Method
get_evaluation_result
Get cached evaluation result
point_quality/deepresearcharena/cache/cache_manager.py:116
Function
get_execution_flow
Get execution flow
factual_eval/apps/visualize-trace/app.py:141
Function
get_execution_summary
Get execution summary
factual_eval/apps/visualize-trace/app.py:153
Method
get_instance_cost
Get total cost of current instance
point_quality/deepresearcharena/utils/llm_call.py:159
Method
get_model_results
Get cached model results
point_quality/deepresearcharena/cache/cache_manager.py:108
Function
get_performance_summary
Get performance summary
factual_eval/apps/visualize-trace/app.py:129
Method
get_query_criteria
Get cached query criteria
point_quality/deepresearcharena/cache/cache_manager.py:100
Method
get_query_dimensions
Get cached query dimensions
point_quality/deepresearcharena/cache/cache_manager.py:84
Method
get_query_weights
Get cached query weights
point_quality/deepresearcharena/cache/cache_manager.py:92
Function
get_raw_messages
Get raw message data for debugging
factual_eval/apps/visualize-trace/app.py:189
Function
get_spans_summary
Get spans summary
factual_eval/apps/visualize-trace/app.py:165
Function
get_step_logs_summary
Get step logs summary
factual_eval/apps/visualize-trace/app.py:177
Method
get_token_usage
Get current cumulative token usage - implemented by specific implementation class
factual_eval/libs/miroflow/src/miroflow/llm/provider_client_base.py:153
Method
get_total_cost
Get total cost of all API calls
point_quality/deepresearcharena/utils/llm_call.py:149
Function
google_search
Perform google searches via Serper API and retrieve rich results. It is able to retrieve organic search results, people also ask, related searches
factual_eval/libs/miroflow-tool/src/miroflow/tool/mcp_servers/searching_mcp_server.py:21
Function
guardrail_function
( context: RunContextWrapper[Any], agent: Agent[Any], input: str | list[TResponseInputItem], )
factual_eval/libs/miroflow-contrib/tests/tracing/deprecated_tracing_errors.py:544
Function
guardrail_span
Create a new guardrail span. The span will not be started automatically, you should either do `with guardrail_span() ...` or call `span.start()` +
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/tracing/create.py:296
Method
handle
(self: Flowable, action: str)
factual_eval/libs/miroflow-contrib/src/miroflow/contrib/pocket/core_v2.py:33
Function
handleKeyboardShortcuts
(event)
factual_eval/apps/visualize-trace/static/js/script.js:428
Function
handleScroll
()
factual_eval/apps/visualize-trace/static/js/script.js:1140
Method
handle_max_turns_reached_summary_prompt
Handle max turns reached summary prompt
factual_eval/libs/miroflow/src/miroflow/llm/providers/claude_openrouter_client.py:440
Method
handle_max_turns_reached_summary_prompt
Handle max turns reached summary prompt
factual_eval/libs/miroflow/src/miroflow/llm/providers/claude_anthropic_client.py:221
Method
handle_max_turns_reached_summary_prompt
Handle max turns reached summary prompt
factual_eval/libs/miroflow/src/miroflow/llm/providers/deepseek_newapi_client.py:290
Method
handle_max_turns_reached_summary_prompt
Handle max turns reached summary prompt
factual_eval/libs/miroflow/src/miroflow/llm/providers/qwen_sglang_client.py:197
Method
handle_max_turns_reached_summary_prompt
Handle max turns reached summary prompt
factual_eval/libs/miroflow/src/miroflow/llm/providers/gpt_openai_response_client.py:322
Method
handle_max_turns_reached_summary_prompt
Handle max turns reached summary prompt
factual_eval/libs/miroflow/src/miroflow/llm/providers/claude_newapi_client.py:294
Method
handle_max_turns_reached_summary_prompt
Handle max turns reached summary prompt
factual_eval/libs/miroflow/src/miroflow/llm/providers/gpt_openai_client.py:326
Method
has
Check if key exists in cache Args: key: Cache key Returns: True if key exists,
point_quality/deepresearcharena/cache/file_cache.py:81
Function
index
Main page
factual_eval/apps/visualize-trace/app.py:16
Function
input_guardrail_function
( context: RunContextWrapper[Any], agent: Agent[Any], input: str | list[TResponseInputItem], )
factual_eval/libs/miroflow-contrib/tests/tracing/deprecated_tracing_errors_streamed.py:567
Method
list_caches
List all cache names Returns: List of cache names
point_quality/deepresearcharena/cache/cache_manager.py:74
Function
list_files
List available JSON files
factual_eval/apps/visualize-trace/app.py:22
← previous
next →
501–600 of 851, ranked by callers