xinference.client.handlers.EmbeddingModelHandle.create_embedding

EmbeddingModelHandle.create_embedding(input: str | List[str] | List[int] | List[List[int]] | Dict[str, Any] | List[Dict[str, Any]] | List[str | Dict[str, Any]], **kwargs) → Embedding

Create an Embedding from user input via RESTful APIs.

Parameters:

input (Union[str, List[str], List[int], List[List[int]], Dict[str, Any],) – List[Dict[str, Any]], List[Union[str, Dict[str, Any]]]] Text, token IDs, or multimodal input. Multimodal dictionaries may contain text, image, video, or interleaved role/content messages.

Returns:

The resulted Embedding vector that can be easily consumed by machine learning models and algorithms.

Return type:

Embedding

Raises:

RuntimeError – Report the failure of embeddings and provide the error message.