yandex-cloud 2025.4.14

/// A pair of text labels and their corresponding confidence values.
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ClassificationLabel {
    /// A class name label.
    #[prost(string, tag = "1")]
    pub label: ::prost::alloc::string::String,
    /// The probability of classifying text into a specific class.
    #[prost(double, tag = "2")]
    pub confidence: f64,
}
/// Description of a sample for the classification task.
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ClassificationSample {
    /// Text sample.
    #[prost(string, tag = "1")]
    pub text: ::prost::alloc::string::String,
    /// Expected label for a given text.
    #[prost(string, tag = "2")]
    pub label: ::prost::alloc::string::String,
}
/// Request for the service to classify text with tuned model.
///
/// The names of the classes between which the model will be distributing requests must be specified during model tuning;
/// therefore, they are not provided in the request.
///
/// For examples of usage, see [step-by-step guides](/docs/foundation-models/operations/classifier/additionally-trained).
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct TextClassificationRequest {
    /// The \[URI\](/docs/foundation-models/concepts/classifier/models) of your tuned classifier model.
    #[prost(string, tag = "1")]
    pub model_uri: ::prost::alloc::string::String,
    /// Text for classification.
    #[prost(string, tag = "2")]
    pub text: ::prost::alloc::string::String,
}
/// Response with classifier predictions.
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct TextClassificationResponse {
    /// The classification results with the `confidence`` values
    /// for the probability of classifying the request text into each class.
    #[prost(message, repeated, tag = "1")]
    pub predictions: ::prost::alloc::vec::Vec<ClassificationLabel>,
    /// The model version changes with each new releases.
    #[prost(string, tag = "2")]
    pub model_version: ::prost::alloc::string::String,
}
/// Request for the service to classify text.
/// For examples of usage, see [step-by-step guides](/docs/operations/classifier/readymade).
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct FewShotTextClassificationRequest {
    /// The \[URI\](/docs/foundation-models/concepts/classifier/models) of the classifier model.
    #[prost(string, tag = "1")]
    pub model_uri: ::prost::alloc::string::String,
    /// Text description of the classification task.
    #[prost(string, tag = "2")]
    pub task_description: ::prost::alloc::string::String,
    /// List of available labels for the classification result.
    /// Give meaningful names to label classes: this is essential for correct classification results.
    /// For example, use ``chemistry`` and ``physics`` rather than ``chm`` and ``phs`` for class names.
    #[prost(string, repeated, tag = "3")]
    pub labels: ::prost::alloc::vec::Vec<::prost::alloc::string::String>,
    /// Text for classification.
    #[prost(string, tag = "4")]
    pub text: ::prost::alloc::string::String,
    /// Optional set of text samples with expected labels that may be used as an additional hint for the classifier.
    #[prost(message, repeated, tag = "5")]
    pub samples: ::prost::alloc::vec::Vec<ClassificationSample>,
}
/// Response containing classifier predictions.
#[allow(clippy::derive_partial_eq_without_eq)]
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct FewShotTextClassificationResponse {
    /// The classification results with the `confidence`` values
    /// for the probability of classifying the request text into each class.
    #[prost(message, repeated, tag = "1")]
    pub predictions: ::prost::alloc::vec::Vec<ClassificationLabel>,
    /// The model version changes with each new releases.
    #[prost(string, tag = "2")]
    pub model_version: ::prost::alloc::string::String,
}
/// Generated client implementations.
pub mod text_classification_service_client {
    #![allow(unused_variables, dead_code, missing_docs, clippy::let_unit_value)]
    use tonic::codegen::*;
    use tonic::codegen::http::Uri;
    /// Service for classifying the text requests provided in prompts.
    #[derive(Debug, Clone)]
    pub struct TextClassificationServiceClient<T> {
        inner: tonic::client::Grpc<T>,
    }
    impl TextClassificationServiceClient<tonic::transport::Channel> {
        /// Attempt to create a new client by connecting to a given endpoint.
        pub async fn connect<D>(dst: D) -> Result<Self, tonic::transport::Error>
        where
            D: TryInto<tonic::transport::Endpoint>,
            D::Error: Into<StdError>,
        {
            let conn = tonic::transport::Endpoint::new(dst)?.connect().await?;
            Ok(Self::new(conn))
        }
    }
    impl<T> TextClassificationServiceClient<T>
    where
        T: tonic::client::GrpcService<tonic::body::BoxBody>,
        T::Error: Into<StdError>,
        T::ResponseBody: Body<Data = Bytes> + Send + 'static,
        <T::ResponseBody as Body>::Error: Into<StdError> + Send,
    {
        pub fn new(inner: T) -> Self {
            let inner = tonic::client::Grpc::new(inner);
            Self { inner }
        }
        pub fn with_origin(inner: T, origin: Uri) -> Self {
            let inner = tonic::client::Grpc::with_origin(inner, origin);
            Self { inner }
        }
        pub fn with_interceptor<F>(
            inner: T,
            interceptor: F,
        ) -> TextClassificationServiceClient<InterceptedService<T, F>>
        where
            F: tonic::service::Interceptor,
            T::ResponseBody: Default,
            T: tonic::codegen::Service<
                http::Request<tonic::body::BoxBody>,
                Response = http::Response<
                    <T as tonic::client::GrpcService<tonic::body::BoxBody>>::ResponseBody,
                >,
            >,
            <T as tonic::codegen::Service<
                http::Request<tonic::body::BoxBody>,
            >>::Error: Into<StdError> + Send + Sync,
        {
            TextClassificationServiceClient::new(
                InterceptedService::new(inner, interceptor),
            )
        }
        /// Compress requests with the given encoding.
        ///
        /// This requires the server to support it otherwise it might respond with an
        /// error.
        #[must_use]
        pub fn send_compressed(mut self, encoding: CompressionEncoding) -> Self {
            self.inner = self.inner.send_compressed(encoding);
            self
        }
        /// Enable decompressing responses.
        #[must_use]
        pub fn accept_compressed(mut self, encoding: CompressionEncoding) -> Self {
            self.inner = self.inner.accept_compressed(encoding);
            self
        }
        /// Limits the maximum size of a decoded message.
        ///
        /// Default: `4MB`
        #[must_use]
        pub fn max_decoding_message_size(mut self, limit: usize) -> Self {
            self.inner = self.inner.max_decoding_message_size(limit);
            self
        }
        /// Limits the maximum size of an encoded message.
        ///
        /// Default: `usize::MAX`
        #[must_use]
        pub fn max_encoding_message_size(mut self, limit: usize) -> Self {
            self.inner = self.inner.max_encoding_message_size(limit);
            self
        }
        /// RPC method to classify text with tuned model.
        ///
        /// The names of the classes between which the model will be distributing requests
        /// must be specified during model tuning and are not provided in the request.
        pub async fn classify(
            &mut self,
            request: impl tonic::IntoRequest<super::TextClassificationRequest>,
        ) -> std::result::Result<
            tonic::Response<super::TextClassificationResponse>,
            tonic::Status,
        > {
            self.inner
                .ready()
                .await
                .map_err(|e| {
                    tonic::Status::new(
                        tonic::Code::Unknown,
                        format!("Service was not ready: {}", e.into()),
                    )
                })?;
            let codec = tonic::codec::ProstCodec::default();
            let path = http::uri::PathAndQuery::from_static(
                "/yandex.cloud.ai.foundation_models.v1.text_classification.TextClassificationService/Classify",
            );
            let mut req = request.into_request();
            req.extensions_mut()
                .insert(
                    GrpcMethod::new(
                        "yandex.cloud.ai.foundation_models.v1.text_classification.TextClassificationService",
                        "Classify",
                    ),
                );
            self.inner.unary(req, path, codec).await
        }
        /// RPC method for binary and multi-class classification.
        ///
        /// You can provide up to 20 classes for few-shot text classification
        /// with optional examples.
        pub async fn few_shot_classify(
            &mut self,
            request: impl tonic::IntoRequest<super::FewShotTextClassificationRequest>,
        ) -> std::result::Result<
            tonic::Response<super::FewShotTextClassificationResponse>,
            tonic::Status,
        > {
            self.inner
                .ready()
                .await
                .map_err(|e| {
                    tonic::Status::new(
                        tonic::Code::Unknown,
                        format!("Service was not ready: {}", e.into()),
                    )
                })?;
            let codec = tonic::codec::ProstCodec::default();
            let path = http::uri::PathAndQuery::from_static(
                "/yandex.cloud.ai.foundation_models.v1.text_classification.TextClassificationService/FewShotClassify",
            );
            let mut req = request.into_request();
            req.extensions_mut()
                .insert(
                    GrpcMethod::new(
                        "yandex.cloud.ai.foundation_models.v1.text_classification.TextClassificationService",
                        "FewShotClassify",
                    ),
                );
            self.inner.unary(req, path, codec).await
        }
    }
}