Skip to main content

gemini_batch_to_openai

gproxy_protocol::adapt::embeddings

Function gemini_batch_to_openai 

Source 
pub async fn gemini_batch_to_openai<U: Upstream>(
    upstream: &U,
    target: &U::Target,
    template: WireRequest<()>,
    input: BatchEmbedContentsRequestBody,
    target_model: &str,
    options: EmbeddingBatchOptions,
) -> Result<EmbeddingBatchResult<BatchEmbedContentsResponseBody>, EmbeddingBatchError>
Expand description

Execute a Gemini embedding batch through the selected OpenAI model. Varying output dimensions are split into separate calls and returned in input order.