Struct Evals 

pub struct Evals<'c, C: Config> { /* private fields */ }

Create, manage, and run evals in the OpenAI platform. Related guide: Evals

Implementations

impl<'c, C: Config> Evals<'c, C>

pub fn new(client: &'c Client<C>) -> Self

Available on crate feature evals only.

pub fn runs(&self, eval_id: &str) -> EvalRuns<'_, C>

Available on crate feature evals only.

EvalRuns API group

pub async fn list(&self) -> Result<EvalList, OpenAIError>

Available on crate feature evals only.

List evaluations for a project. List evaluations for a project.

pub async fn list_byot<R: DeserializeOwned>(&self) -> Result<R, OpenAIError>

Available on crate feature evals only.

List evaluations for a project.

pub async fn create( &self, request: CreateEvalRequest, ) -> Result<Eval, OpenAIError>

Available on crate feature evals only.

Create the structure of an evaluation that can be used to test a model’s performance. An evaluation is a set of testing criteria and the config for a data source, which dictates the schema of the data used in the evaluation. After creating an evaluation, you can run it on different models and model parameters. We support several types of graders and datasources. For more information, see the Evals guide. Create the structure of an evaluation that can be used to test a model’s performance. An evaluation is a set of testing criteria and the config for a data source, which dictates the schema of the data used in the evaluation. After creating an evaluation, you can run it on different models and model parameters. We support several types of graders and datasources. For more information, see the Evals guide.

pub async fn create_byot<T0: Serialize, R: DeserializeOwned>( &self, request: T0, ) -> Result<R, OpenAIError>

Available on crate feature evals only.

Create the structure of an evaluation that can be used to test a model’s performance. An evaluation is a set of testing criteria and the config for a data source, which dictates the schema of the data used in the evaluation. After creating an evaluation, you can run it on different models and model parameters. We support several types of graders and datasources. For more information, see the Evals guide.

pub async fn retrieve(&self, eval_id: &str) -> Result<Eval, OpenAIError>

Available on crate feature evals only.

Get an evaluation by ID. Get an evaluation by ID.

pub async fn retrieve_byot<T0: Display, R: DeserializeOwned>( &self, eval_id: T0, ) -> Result<R, OpenAIError>

Available on crate feature evals only.

Get an evaluation by ID.

pub async fn update( &self, eval_id: &str, request: UpdateEvalRequest, ) -> Result<Eval, OpenAIError>

Available on crate feature evals only.

Update certain properties of an evaluation. Update certain properties of an evaluation.

pub async fn update_byot<T0: Display, T1: Serialize, R: DeserializeOwned>( &self, eval_id: T0, request: T1, ) -> Result<R, OpenAIError>

Available on crate feature evals only.

Update certain properties of an evaluation.

pub async fn delete( &self, eval_id: &str, ) -> Result<DeleteEvalResponse, OpenAIError>

Available on crate feature evals only.

Delete an evaluation. Delete an evaluation.

pub async fn delete_byot<T0: Display, R: DeserializeOwned>( &self, eval_id: T0, ) -> Result<R, OpenAIError>

Available on crate feature evals only.

Delete an evaluation.

Trait Implementations

impl<'c, C: Config> RequestOptionsBuilder for Evals<'c, C>

Available on crate feature _api only.

fn options_mut(&mut self) -> &mut RequestOptions

Get mutable reference to RequestOptions (for building)

fn options(&self) -> &RequestOptions

Get reference to RequestOptions

fn headers(self, headers: HeaderMap) -> Self

Add headers to RequestOptions

fn header<K, V>(self, key: K, value: V) -> Result<Self, OpenAIError>

where K: IntoHeaderName, V: TryInto<HeaderValue>, V::Error: Into<InvalidHeaderValue>,

Add a single header to RequestOptions

fn query<Q: Serialize + ?Sized>(self, query: &Q) -> Result<Self, OpenAIError>

Add query parameters to RequestOptions

fn path<P: Into<String>>(self, path: P) -> Result<Self, OpenAIError>

Add a path to RequestOptions