Struct TaskSemanticEmbeddingWithInstruction

pub struct TaskSemanticEmbeddingWithInstruction<'a> {
    pub instruction: &'a str,
    pub prompt: Prompt<'a>,
    pub normalize: Option<bool>,
}

Allows you to choose a semantic representation fitting for your use case.

By providing instructions, you can help the model better understand the nuances of your specific data, leading to embeddings that are more useful for your use case.

Fields

instruction: &'a str

To further improve performance by steering the model, you can use instructions.

Instructions can help the model understand nuances of your specific data and ultimately lead to embeddings that are more useful for your use-case. In this case, we aim to further increase the absolute difference between the cosine similarities. Instruction can also be the empty string.

prompt: Prompt<'a>

The prompt (usually text) to be embedded.

normalize: Option<bool>

Return normalized embeddings. This can be used to save on additional compute when applying a cosine similarity metric.

Trait Implementations

impl<'a> Debug for TaskSemanticEmbeddingWithInstruction<'a>

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

Formats the value using the given formatter.

impl Job for TaskSemanticEmbeddingWithInstruction<'_>

type Output = SemanticEmbeddingOutput

Output returned by crate::Client::output_of

type ResponseBody = SemanticEmbeddingOutput

Expected answer of the Aleph Alpha API

fn build_request(&self, client: &Client, base: &str) -> RequestBuilder

Prepare the request for the Aleph Alpha API. Authentication headers can be assumed to be already set.

fn body_to_output(&self, response: Self::ResponseBody) -> Self::Output

Parses the response of the server into higher level structs for the user.

impl<'a> Serialize for TaskSemanticEmbeddingWithInstruction<'a>

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Task for TaskSemanticEmbeddingWithInstruction<'_>

type Output = SemanticEmbeddingOutput

Output returned by crate::Client::output_of

type ResponseBody = SemanticEmbeddingOutput

Expected answer of the Aleph Alpha API

fn build_request( &self, client: &Client, base: &str, model: &str, ) -> RequestBuilder

Prepare the request for the Aleph Alpha API. Authentication headers can be assumed to be already set.

fn body_to_output(&self, response: Self::ResponseBody) -> Self::Output

Parses the response of the server into higher level structs for the user.

fn with_model<'a>(&'a self, model: &'a str) -> MethodJob<'a, Self>

where Self: Sized,

Turn your task into Job by annotating it with a model name.