Enum Embedding 

pub enum Embedding {
    OneDim(Vec<f32>),
    TwoDim(Vec<Vec<f32>>),
    ThreeDim(Vec<Vec<Vec<f32>>>),
}

Embedding vector that supports multiple dimensionalities.

The OpenAI API typically returns 1D vectors, but this enum provides flexibility for future API changes or custom use cases. The #[serde(untagged)] attribute allows automatic deserialization based on the JSON structure.

Variants

• OneDim - Standard 1D embedding vector (e.g., [0.1, 0.2, 0.3])
• TwoDim - 2D embedding matrix (e.g., [[0.1, 0.2], [0.3, 0.4]])
• ThreeDim - 3D embedding tensor

Examples

use openai_tools::embedding::response::Embedding;

// Parse a 1D embedding
let json = r#"[0.1, 0.2, 0.3]"#;
let embedding: Embedding = serde_json::from_str(json).unwrap();

assert!(embedding.is_1d());
let vector = embedding.as_1d().unwrap();
assert_eq!(vector.len(), 3);

Variants

OneDim(Vec<f32>)

1D embedding: Vec

TwoDim(Vec<Vec<f32>>)

2D embedding: Vec<Vec>

ThreeDim(Vec<Vec<Vec<f32>>>)

3D embedding: Vec<Vec<Vec>>

Implementations

impl Embedding

pub fn as_1d(&self) -> Option<&Vec<f32>>

Returns the embedding as a 1D vector if it is 1D, otherwise returns None.

Returns

• Some(&Vec<f32>) - Reference to the 1D vector if the embedding is 1D
• None - If the embedding is 2D or 3D

Example

use openai_tools::embedding::response::Embedding;

let embedding: Embedding = serde_json::from_str("[0.1, 0.2, 0.3]").unwrap();
if let Some(vec) = embedding.as_1d() {
    println!("Dimension: {}", vec.len());
}

pub fn as_2d(&self) -> Option<&Vec<Vec<f32>>>

Returns the embedding as a 2D vector if it is 2D, otherwise returns None.

Returns

• Some(&Vec<Vec<f32>>) - Reference to the 2D vector if the embedding is 2D
• None - If the embedding is 1D or 3D

pub fn as_3d(&self) -> Option<&Vec<Vec<Vec<f32>>>>

Returns the embedding as a 3D vector if it is 3D, otherwise returns None.

Returns

• Some(&Vec<Vec<Vec<f32>>>) - Reference to the 3D vector if the embedding is 3D
• None - If the embedding is 1D or 2D

pub fn is_1d(&self) -> bool

Returns true if the embedding is 1D.

Example

use openai_tools::embedding::response::Embedding;

let embedding: Embedding = serde_json::from_str("[0.1, 0.2]").unwrap();
assert!(embedding.is_1d());

pub fn is_2d(&self) -> bool

Returns true if the embedding is 2D.

pub fn is_3d(&self) -> bool

Returns true if the embedding is 3D.

Trait Implementations

impl Clone for Embedding

fn clone(&self) -> Embedding

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for Embedding

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for Embedding

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.