Enum EmbeddingProviderEnum 

pub enum EmbeddingProviderEnum {
    Gemini(GeminiClient),
    OpenAI(OpenAIClient),
}

Unified embedding provider that wraps concrete implementations.

This enum allows runtime selection of embedding providers while implementing the EmbeddingProvider trait.

Variants

Gemini(GeminiClient)

Google Gemini embedding provider (768 dimensions).

OpenAI(OpenAIClient)

OpenAI embedding provider (1536 or 3072 dimensions).

Implementations

impl EmbeddingProviderEnum

pub fn gemini(api_key: &str) -> Result<Self, AppError>

Creates a Gemini embedding provider.

Arguments

• api_key - Google Gemini API key

pub fn openai(api_key: &str) -> Result<Self, AppError>

Creates an OpenAI embedding provider with the default model.

Uses text-embedding-3-small (1536 dimensions).

Arguments

• api_key - OpenAI API key (starts with sk-)

pub fn openai_with_model(api_key: &str, model: &str) -> Result<Self, AppError>

Creates an OpenAI embedding provider with a specific model.

Arguments

• api_key - OpenAI API key
• model - Model name (e.g., text-embedding-3-large)

Trait Implementations

impl Clone for EmbeddingProviderEnum

fn clone(&self) -> EmbeddingProviderEnum

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl EmbeddingProvider for EmbeddingProviderEnum

fn name(&self) -> &'static str

Returns the provider identifier for logging and configuration.

fn dimension(&self) -> usize

Returns the embedding dimension this provider generates.

async fn generate(&self, text: &str) -> Result<Vec<f32>, AppError>

Generates an embedding vector for the given text.

async fn generate_batch( &self, texts: &[String], ) -> Result<Vec<Vec<f32>>, AppError>

Generates embeddings for multiple texts in a batch.