Struct GenAIEvalResults 

pub struct GenAIEvalResults {
    pub aligned_results: Vec<AlignedEvalResult>,
    pub errored_tasks: Vec<String>,
    pub cluster_data: Option<ClusterData>,
    pub histograms: Option<HashMap<String, Histogram>>,
    pub array_dataset: Option<ArrayDataset>,
    pub results_by_id: HashMap<String, usize>,
}

Fields

aligned_results: Vec<AlignedEvalResult>

Aligned results in original record order

errored_tasks: Vec<String>

cluster_data: Option<ClusterData>

histograms: Option<HashMap<String, Histogram>>

array_dataset: Option<ArrayDataset>

results_by_id: HashMap<String, usize>

Implementations

impl GenAIEvalResults

pub fn __getitem__( &self, key: &str, ) -> Result<AlignedEvalResult, EvaluationError>

pub fn successful_count(&self) -> usize

pub fn failed_count(&self) -> usize

pub fn to_dataframe<'py>( &mut self, py: Python<'py>, polars: bool, ) -> Result<Bound<'py, PyAny>, EvaluationError>

Export to dataframe format

pub fn __str__(&self) -> String

pub fn as_table(&mut self, show_tasks: bool)

Display results as a table in the console

Arguments

• show_tasks - If true, display detailed task results; otherwise, show workflow summary

pub fn model_dump_json(&self) -> String

pub fn model_validate_json(json_string: String) -> Result<Self, EvaluationError>

pub fn compare_to( &self, baseline: &GenAIEvalResults, regression_threshold: f64, ) -> Result<ComparisonResults, EvaluationError>

Compare this evaluation against another baseline evaluation Matches workflows by their task structure and compares task-by-task

impl GenAIEvalResults

pub fn new() -> Self

pub fn add_success( &mut self, record: &GenAIEvalRecord, eval_set: GenAIEvalSet, embeddings: BTreeMap<String, Vec<f32>>, )

Add a successful result

pub fn add_failure(&mut self, record: &GenAIEvalRecord, error: String)

Add a failed result - only reference the record

pub fn finalize( &mut self, config: &Arc<EvaluationConfig>, ) -> Result<(), EvaluationError>

Finalize the results by performing post-processing steps which includes:

• Post-processing embeddings (if any)
• Building the array dataset (if not already built)
• Performing clustering and dimensionality reduction (if enabled) for visualization

Arguments

• config - The evaluation configuration that dictates post-processing behavior

Returns

• Result<(), EvaluationError> - Returns Ok(()) if successful, otherwise returns

Trait Implementations

impl Debug for GenAIEvalResults

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for GenAIEvalResults

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for GenAIEvalResults

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl<'py> IntoPyObject<'py> for GenAIEvalResults

type Target = GenAIEvalResults

The Python output type

type Output = Bound<'py, <GenAIEvalResults as IntoPyObject<'py>>::Target>

The smart pointer type to use.

type Error = PyErr

The type returned in the event of a conversion error.

fn into_pyobject( self, py: Python<'py>, ) -> Result<<Self as IntoPyObject<'_>>::Output, <Self as IntoPyObject<'_>>::Error>

Performs the conversion.

impl PyClass for GenAIEvalResults

type Frozen = False

Whether the pyclass is frozen.

impl PyClassImpl for GenAIEvalResults

const IS_BASETYPE: bool = false

#[pyclass(subclass)]

const IS_SUBCLASS: bool = false

#[pyclass(extends=…)]

const IS_MAPPING: bool = false

#[pyclass(mapping)]

const IS_SEQUENCE: bool = false

#[pyclass(sequence)]

const IS_IMMUTABLE_TYPE: bool = false

#[pyclass(immutable_type)]

const RAW_DOC: &'static CStr = c"\x00"

Docstring for the class provided on the struct or enum.

const DOC: &'static CStr

Fully rendered class doc, including the text_signature if a constructor is defined.

type BaseType = PyAny

Base class

type ThreadChecker = SendablePyClass<GenAIEvalResults>

This handles following two situations:

type PyClassMutability = <<PyAny as PyClassBaseType>::PyClassMutability as PyClassMutability>::MutableChild

Immutable or mutable

type Dict = PyClassDummySlot

Specify this class has #[pyclass(dict)] or not.

type WeakRef = PyClassDummySlot

Specify this class has #[pyclass(weakref)] or not.

type BaseNativeType = PyAny

The closest native ancestor. This is PyAny by default, and when you declare #[pyclass(extends=PyDict)], it’s PyDict.

fn items_iter() -> PyClassItemsIter

fn lazy_type_object() -> &'static LazyTypeObject<Self>

fn dict_offset() -> Option<isize>

fn weaklist_offset() -> Option<isize>

impl PyMethods<GenAIEvalResults> for PyClassImplCollector<GenAIEvalResults>

fn py_methods(self) -> &'static PyClassItems

impl PyTypeInfo for GenAIEvalResults

const NAME: &'static str = "GenAIEvalResults"

Class name.

const MODULE: Option<&'static str> = ::core::option::Option::None

Module name, if any.

fn type_object_raw(py: Python<'_>) -> *mut PyTypeObject

Returns the PyTypeObject instance for this type.

fn type_object(py: Python<'_>) -> Bound<'_, PyType>

Returns the safe abstraction over the type object.

fn is_type_of(object: &Bound<'_, PyAny>) -> bool

Checks if object is an instance of this type or a subclass of this type.

fn is_exact_type_of(object: &Bound<'_, PyAny>) -> bool

Checks if object is an instance of this type.

impl Serialize for GenAIEvalResults

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl DerefToPyAny for GenAIEvalResults

impl ExtractPyClassWithClone for GenAIEvalResults