diff --git a/docs/source/conf.py b/docs/source/conf.py index e6fe075..99b69b8 100644 --- a/docs/source/conf.py +++ b/docs/source/conf.py @@ -16,7 +16,7 @@ project = 'RAGoon' copyright = '2024, Louis Brulé Naudet' author = 'Louis Brulé Naudet' -release = '0.0.10' +release = '0.0.11' # -- General configuration --------------------------------------------------- # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration diff --git a/pyproject.toml b/pyproject.toml index 9c777e8..db36ce6 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "ragoon" -version = "0.0.10" +version = "0.0.11" description = "RAGoon : High level library for batched embeddings generation, blazingly-fast web-based RAG and quantitized indexes processing ⚡" readme = "README.md" requires-python = ">=3.9" diff --git a/src/ragoon/embeddings.py b/src/ragoon/embeddings.py index 9c6874f..a1eae12 100644 --- a/src/ragoon/embeddings.py +++ b/src/ragoon/embeddings.py @@ -128,8 +128,8 @@ class EmbeddingsDataLoader: """ def __init__( self, - token: str = None, model_configs: List[Dict[str, str]], + token: str = None, dataset_name: Optional[str] = None, dataset: Optional[Union[Dataset, DatasetDict]] = None, batch_size: Optional[int] = 8, @@ -141,24 +141,24 @@ def __init__( Parameters ---------- - token : str - The token for accessing Hugging Face API. Default is None. - model_configs : list of dict The list of dictionaries with model configurations to use for generating embeddings. - + + token : str + The token for accessing Hugging Face API. Default is None. + dataset_name : str, optional The name of the dataset to load from Hugging Face. Default is None. - + dataset : Dataset or DatasetDict, optional The dataset to process. Default is None. - + batch_size : int, optional The number of samples to process in each batch. Default is 16. - + convert_to_tensor : bool, optional Whether the output should be one large tensor. Default is False. - + device : str, optional The device used for embedding processing if torch.cuda.is_available() is not reliable. Useful when using the Zero GPU on Hugging Face Space. Default is 'cuda'.