Index

_

__iter__() (unit_tests.UnitTest method) (unit_tests.UnitTests method)

A

Accuracy (class in sources.metrics.accuracy) answer (unit_tests_result.ExecutionResult attribute) app module

app (in module app) AtomicTestCaseExecutionResult (class in unit_tests_result) AtomicUnitTest (class in unit_tests)

B

BaseMetric (class in sources.metrics.base_metric)

BaseTest (class in common_interface) BaseView (class in sources.views.base_view)

C

call_llm_api() (execute_tests.LLMExecutor method) callbacks module callbacks.file_selection module callbacks.graph_updates module callbacks.metrics_updates module callbacks.table_updates module client (in module sources.execute_tests) common_interface module components module components.layout module

components.metrics module components.tables module create_accuracy_gauge() (in module callbacks.metrics_updates) create_file_accuracy_figure() (in module callbacks.graph_updates) create_layout() (in module components) (in module components.layout) create_metadata_table() (in module components) (in module components.tables) create_metrics_section() (in module components) (in module components.metrics) create_question_accuracy_figure() (in module callbacks.graph_updates) create_question_answer_container() (in module components) (in module components.tables) create_results_table() (in module callbacks.table_updates) create_styled_table() (in module callbacks.table_updates) create_test_case_row() (in module callbacks.table_updates)

D

data_loader module

deep_format() (execute_tests.LLMExecutor method) description (metadata.MetaData attribute)

E

evaluate_answer_for_test() (in module sources.helpers.testcase_evaluator) evaluate_responses() (unit_tests.UnitTest method) (unit_tests.UnitTests method) (unit_tests_result.ExecutionResult method) (unit_tests_result.ParaphrasedQuestion method) evaluate_test_case() (in module sources.execute_tests) execute() (unit_tests.UnitTest method) (unit_tests.UnitTests method) (unit_tests_result.ParaphrasedQuestion method)

execute_endpoint() (in module sources.execute_tests) execute_tests module execution_result (unit_tests_result.ParaphrasedQuestion attribute) ExecutionResult (class in unit_tests_result) executor (in module execute_tests) extract_answer() (execute_tests.LLMExecutor method)

F

file (unit_tests.UnitTests attribute)

from_dict() (common_interface.BaseTest class method) from_json() (common_interface.BaseTest class method)

G

GeneralStats (class in sources.metrics.general_stats) generate_tests() (unit_tests.UnitTests method) generate_unit_tests() (unit_tests.UnitTest method) get_default_metric_values() (in module callbacks.metrics_updates) get_evaluation_result_as_numpy() (unit_tests.UnitTest method) (unit_tests.UnitTests method) (unit_tests_result.ExecutionResult method) (unit_tests_result.ParaphrasedQuestion method)

get_metric_value() (sources.metrics.accuracy.Accuracy method) (sources.metrics.general_stats.GeneralStats method) (sources.metrics.hallucination_rate.HallucinationRate method) (sources.metrics.llm_drift_rate.LLMDriftRate method) guideline (unit_tests.UnitTest attribute)

H

HallucinationRate (class in sources.metrics.hallucination_rate)

I

IncorrectResponses (class in sources.views.incorrect_responses)

J

json() (sources.views.incorrect_responses.IncorrectResponses method)

L

LLMDriftRate (class in sources.metrics.llm_drift_rate) LLMExecutor (class in execute_tests)

load_config() (execute_tests.LLMExecutor method) load_metadata() (in module data_loader)

M

metadata module MetaData (class in metadata) metadata (unit_tests.UnitTests attribute) metadata_list (in module app) metric_result (sources.metrics.accuracy.Accuracy attribute) (sources.metrics.base_metric.BaseMetric attribute) (sources.metrics.general_stats.GeneralStats attribute) (sources.metrics.hallucination_rate.HallucinationRate attribute) (sources.metrics.llm_drift_rate.LLMDriftRate attribute) metric_result_question_test_wise (sources.metrics.accuracy.Accuracy attribute) metric_result_question_wise (sources.metrics.accuracy.Accuracy attribute) metrics (unit_tests.UnitTests attribute) MODEL (in module unit_tests) module app callbacks callbacks.file_selection callbacks.graph_updates callbacks.metrics_updates callbacks.table_updates common_interface components components.layout components.metrics components.tables data_loader execute_tests metadata sources sources.execute_tests sources.full_pipeline sources.helpers sources.helpers.openai_client sources.helpers.paraphrase_helper sources.helpers.testcase_evaluator sources.metrics sources.metrics.accuracy sources.metrics.base_metric sources.metrics.general_stats sources.metrics.hallucination_rate sources.metrics.llm_drift_rate sources.views sources.views.base_view sources.views.incorrect_responses unit_tests unit_tests_result utils utils.constants

N

name (metadata.MetaData attribute)

O

openai_client (in module sources.helpers.openai_client)

P

paraphrase() (unit_tests.UnitTest method) (unit_tests.UnitTests method) paraphrase_question() (in module sources.execute_tests) (in module sources.helpers.paraphrase_helper) paraphrased_question (unit_tests.UnitTest attribute) ParaphrasedQuestion (class in unit_tests_result) parse_response_path() (execute_tests.LLMExecutor method) passed (unit_tests_result.AtomicTestCaseExecutionResult attribute)

passed() (sources.metrics.accuracy.Accuracy method) (sources.metrics.base_metric.BaseMetric method) (sources.metrics.general_stats.GeneralStats method) (sources.metrics.hallucination_rate.HallucinationRate method) (sources.metrics.llm_drift_rate.LLMDriftRate method) process_file_accuracies() (in module callbacks.graph_updates) process_metadata() (in module data_loader) process_metrics() (in module callbacks.metrics_updates) process_question_accuracies() (in module callbacks.graph_updates)

Q

question (unit_tests.UnitTest attribute) (unit_tests_result.ParaphrasedQuestion attribute)

R

read_file() (unit_tests.UnitTests method) reason (unit_tests_result.AtomicTestCaseExecutionResult attribute) register_callbacks() (in module callbacks) register_file_selection_callbacks() (in module callbacks) (in module callbacks.file_selection) register_graph_callbacks() (in module callbacks) (in module callbacks.graph_updates) register_metrics_callbacks() (in module callbacks) (in module callbacks.metrics_updates)

register_table_callbacks() (in module callbacks) (in module callbacks.table_updates) results (sources.views.incorrect_responses.IncorrectResponses attribute) run_by (metadata.MetaData attribute) run_date (metadata.MetaData attribute) run_duration (metadata.MetaData attribute) run_pipeline() (in module sources.full_pipeline) run_time (metadata.MetaData attribute)

S

sources module sources.execute_tests module sources.full_pipeline module sources.helpers module sources.helpers.openai_client module sources.helpers.paraphrase_helper module sources.helpers.testcase_evaluator module sources.metrics module

sources.metrics.accuracy module sources.metrics.base_metric module sources.metrics.general_stats module sources.metrics.hallucination_rate module sources.metrics.llm_drift_rate module sources.views module sources.views.base_view module sources.views.incorrect_responses module

T

TABLE_CELL_CONDITIONAL_STYLE (in module utils) (in module utils.constants) TABLE_CELL_STYLE (in module utils) (in module utils.constants) TABLE_DATA_CONDITIONAL_STYLE (in module utils) (in module utils.constants) TABLE_HEADER_CONDITIONAL_STYLE (in module utils) (in module utils.constants) TABLE_HEADER_STYLE (in module utils) (in module utils.constants) TABLE_STYLE (in module utils) (in module utils.constants)

test_case (unit_tests.AtomicUnitTest attribute) (unit_tests_result.AtomicTestCaseExecutionResult attribute) test_cases (unit_tests.UnitTest attribute) (unit_tests_result.ExecutionResult attribute) tests() (unit_tests.UnitTests method) threshold (sources.metrics.accuracy.Accuracy attribute) (sources.metrics.base_metric.BaseMetric attribute) (sources.metrics.general_stats.GeneralStats attribute) (sources.metrics.hallucination_rate.HallucinationRate attribute) (sources.metrics.llm_drift_rate.LLMDriftRate attribute) to_dict() (common_interface.BaseTest method) to_json() (common_interface.BaseTest method)

U

unit_tests module unit_tests (unit_tests.UnitTests attribute) unit_tests_result module UnitTest (class in unit_tests)

UnitTests (class in unit_tests) utils module utils.constants module uuid (metadata.MetaData attribute)