class VoyageEmbeddingsPrompt processing batch size.
The async caller should be used by subclasses to make any async calls, which will thus benefit from the concurrency and retry logic.
The format of the output embeddings. Can be "float", "base64", or "ubinary".
Input type for the embeddings request.
Model name to use. Available options are: qwen-turbo, qwen-plus, qwen-max, or Other compatible models.
Alias for model
The desired dimension of the output embeddings.
The data type of the output embeddings. Can be "float" or "int8".
The truncation strategy to use for the model response.
A class for generating embeddings using the Voyage AI API.