HFEmbeddingDeployModelParameters Configuration

HFEmbeddingDeployModelParameters(name: str, provider: str = 'hf', verbose: Optional[bool] = False, concurrency: Optional[int] = 100, path: Optional[str] = None, device: Optional[str] = None, cache_folder: Optional[str] = None, normalize_embeddings: bool = False, multi_process: bool = False, model_kwargs: Dict[str, Any] = <factory>, encode_kwargs: Dict[str, Any] = <factory>, embed_instruction: Optional[str] = None, query_instruction: Optional[str] = None)

Parameters

Name	Type	Required	Description
name	string	✅	The name of the model.
path	string	❌	The path of the model, if you want to deploy a local model.
device	string	❌	Device to run model. If None, the device is automatically determined
provider	string	❌	The provider of the model. If model is deployed in local, this is the inference type. If model is deployed in third-party service, this is platform name('proxy/<platform>') Defaults：hf
verbose	boolean	❌	Show verbose output. Defaults：False
concurrency	integer	❌	Model concurrency limit Defaults：100
cache_folder	string	❌	Path of the cache folder.
normalize_embeddings	boolean	❌	Normalize embeddings. Defaults：False
multi_process	boolean	❌	Run encode() on multiple GPUs. Defaults：False
model_kwargs	object	❌	Keyword arguments to pass to the model. Defaults：{}
encode_kwargs	object	❌	Keyword arguments to pass when calling the `encode` method. Defaults：{}
embed_instruction	string	❌	Instruction to use for embedding documents. Just for Instructor model.
query_instruction	string	❌	Instruction to use for embedding query. Just for Instructor model.