Struct aleph_alpha_client::TaskSemanticEmbedding

pub struct TaskSemanticEmbedding<'a> {
    pub prompt: Prompt<'a>,
    pub representation: SemanticRepresentation,
    pub compress_to_size: Option<u32>,
}

Create embeddings for prompts which can be used for downstream tasks. E.g. search, classifiers

Fields

prompt: Prompt<'a>

The prompt (usually text) to be embedded.

representation: SemanticRepresentation

Semantic representation to embed the prompt with. This parameter is governed by the specific usecase in mind.

compress_to_size: Option<u32>

Default behaviour is to return the full embedding, but you can optionally request an embedding compressed to a smaller set of dimensions. A size of 128 is supported for every model.

The 128 size is expected to have a small drop in accuracy performance (4-6%), with the benefit of being much smaller, which makes comparing these embeddings much faster for use cases where speed is critical.

The 128 size can also perform better if you are embedding short texts or documents.

Trait Implementations

impl<'a> Debug for TaskSemanticEmbedding<'a>

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

Formats the value using the given formatter.

impl<'a> Serialize for TaskSemanticEmbedding<'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 TaskSemanticEmbedding<'_>

type Output = SemanticEmbeddingOutput

Output returned by Client::execute

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.