OpenAICompatibleEmbedding

class OpenAICompatibleEmbedding:

Provides text embedding functionalities supporting OpenAI compatibility.

Parameters:

  • model_type (str): The model type to be used for text embeddings.
  • api_key (str): The API key for authenticating with the model service.
  • url (str): The url to the model service.
  • output_dim (Optional[int]): The dimensionality of the embedding vectors. If None, it will be determined during the first embedding call.

init

def __init__(
    self,
    model_type: str,
    api_key: Optional[str] = None,
    url: Optional[str] = None,
    output_dim: Optional[int] = None
):

embed_list

def embed_list(self, objs: list[str], **kwargs: Any):

Generates embeddings for the given texts.

Parameters:

  • objs (list[str]): The texts for which to generate the embeddings. **kwargs (Any): Extra kwargs passed to the embedding API.

Returns:

list[list[float]]: A list that represents the generated embedding as a list of floating-point numbers.

get_output_dim

def get_output_dim(self):

Returns:

int: The dimensionality of the embedding for the current model.