docs: fix typos, spelling and docstring formatting in vectorisers

src/classifai/vectorisers/__init__.py

@@ -1,5 +1,6 @@
 # pylint: disable=C0301
-"""This module provides classes for creating and utilizing embedding models.
+"""This module provides classes for creating and utilising embedding models from different services.
+
 The Vectoriser module offers a unified interface to interact with various other ClassifAI Package Modules.
 Generally Vectorisers are used to convert text data into numerical embeddings that can be used for
 machine learning tasks.
@@ -8,11 +9,11 @@
 ###########################
 # Vectoriser Overview
 
-In our Package, Vectoriser have a simple role:
+In our Package, Vectorisers have a simple role:
 
-  * Take in text data (as a string or list of strings)
-  * Output numerical embeddings (as a numpy array)
-  * Each Vectortiser should provide a `transform` method to perform this conversion.
+  - Take in text data (as a string or list of strings)
+  - Output numerical embeddings (as a numpy array)
+  - Each Vectoriser should provide a `transform` method to perform this conversion.
 
 It is possible for users to implement their own Vectoriser classes by inheriting from the
 `VectoriserBase` abstract base class and implementing the `transform` method.
@@ -22,15 +23,14 @@
 ###########################
 # Implemented Vectorisers
 
-We provide several robust implementations of Vectorisers that interface with popular services and libraries.
-
-The module contains the following 'ready-made' classes:
+We provide several quick implementations of Vectorisers that interface with popular services and libraries.
 
-  * `GcpVectoriser`: A class for embedding text using Google Cloud Platform's GenAI API.
-  * `HuggingFaceVectoriser`: A general wrapper class for Huggingface Transformers
-    models to generate text embeddings.
-  * `OllamaVectoriser`: A general wrapper class for using a locally running ollama
-    server to generate text embeddings.
+This module contains the following 'ready-made' classes:
+- `GcpVectoriser`: A class for embedding text using Google Cloud Platform's GenAI API.
+- `HuggingFaceVectoriser`: A general wrapper class for Huggingface Transformers
+models to generate text embeddings.
+- `OllamaVectoriser`: A general wrapper class for using a locally running Ollama
+server to generate text embeddings.
 
 Each class is designed to interface with a specific service that provides embedding model
 functionality.
@@ -39,7 +39,7 @@
 
 The `HuggingFaceVectoriser` class utilizes models from the Huggingface Transformers library.
 
-The `OllamaVectoriser` class can use any local/downloaded model which can be served by ollama.
+The `OllamaVectoriser` class can use any local/downloaded model which can be served by Ollama.
 
 These classes abstract the underlying implementation details, providing a simple and consistent
 interface for embedding text using different services.

src/classifai/vectorisers/base.py

@@ -1,4 +1,5 @@
-"""This module provides classes for creating and utilizing embedding models from different services.
+"""This module provides classes for creating and utilising embedding models from different services.
+
 The Vectoriser module offers a unified interface to interact with various other ClassifAI Package Modules.
 Generally Vectorisers are used to convert text data into numerical embeddings that can be used for
 machine learning tasks.
@@ -7,11 +8,11 @@
 ###########################
 # Vectoriser Overview
 
-In our Package, Vectoriser have a simple role:
-    - Take in text data (as a string or list of strings)
-    - Output numerical embeddings (as a numpy array)
-    - Each Vectortiser should provide a `transform` method to perform this conversion.
+In our Package, Vectorisers have a simple role:
 
+  - Take in text data (as a string or list of strings)
+  - Output numerical embeddings (as a numpy array)
+  - Each Vectoriser should provide a `transform` method to perform this conversion.
 It is possible for users to implement their own Vectoriser classes by inheriting from the
 `VectoriserBase` abstract base class and implementing the `transform` method.
 
@@ -22,11 +23,11 @@
 
 We provide several quick implementations of Vectorisers that interface with popular services and libraries.
 
-The module contains the following 'ready-made' classes:
+This module contains the following 'ready-made' classes:
 - `GcpVectoriser`: A class for embedding text using Google Cloud Platform's GenAI API.
 - `HuggingFaceVectoriser`: A general wrapper class for Huggingface Transformers
 models to generate text embeddings.
-- `OllamaVectoriser`: A general wrapper class for using a locally running ollama
+- `OllamaVectoriser`: A general wrapper class for using a locally running Ollama
 server to generate text embeddings.
 
 Each class is designed to interface with a specific service that provides embedding model
@@ -36,7 +37,7 @@
 
 The `HuggingFaceVectoriser` class utilizes models from the Huggingface Transformers library.
 
-The `OllamaVectoriser` class can use any local/downloaded model which can be served by ollama.
+The `OllamaVectoriser` class can use any local/downloaded model which can be served by Ollama.
 
 These classes abstract the underlying implementation details, providing a simple and consistent
 interface for embedding text using different services.

src/classifai/vectorisers/gcp.py

@@ -48,20 +48,20 @@ def __init__(
         task_type="CLASSIFICATION",
         **client_kwargs,
     ):
-        """Initializes the GcpVectoriser with the specified project ID, location, and model name.
+        """Initialises the GcpVectoriser with the specified project ID, location, and model name.
 
         Args:
             project_id (str): [optional] The Google Cloud project ID. Defaults to None.
             api_key (str): [optional] The API key for authenticating with the GenAI API. Defaults to None.
-            location (str): [optional] The location of the GenAI API. Defaults to None.
+            location (str): [optional] The location of the GenAI API. Defaults to "europe-west2".
             model_name (str): [optional] The name of the embedding model. Defaults to "text-embedding-004".
             task_type (str): [optional] The embedding task. Defaults to "CLASSIFICATION".
                                        See https://cloud.google.com/vertex-ai/generative-ai/docs/embeddings/task-types
                                        for other options.
             **client_kwargs: [optional] Additional keyword arguments to pass to the GenAI client.
 
         Raises:
-            `ConfigurationError`: If the GenAI client fails to initialize.
+            `ConfigurationError`: If the authentication arguments are invalid, or if the GenAI client fails to initialise.
         """
         check_deps(["google-genai"], extra="gcp")
         from google import genai  # type: ignore
@@ -86,7 +86,7 @@ def __init__(
             )
         except Exception as e:
             raise ConfigurationError(
-                "Failed to initialize GCP GenAI client.",
+                "Failed to initialise GCP GenAI client.",
                 context={"vectoriser": "gcp", "cause": str(e), "cause_type": type(e).__name__},
             ) from e
 

src/classifai/vectorisers/huggingface.py

@@ -13,16 +13,14 @@ class HuggingFaceVectoriser(VectoriserBase):
 
     The `HuggingFaceVectoriser` accepts most encoder-based models from the Huggingface Transformers library,
     and provides a simple interface to generate embeddings from text data. Additional configuration options,
-    such as `trust_remote` or a HuggingFaceAPI token can be passed via the `tokenizer_kwargs` and `model_kwargs`
+    such as `trust_remote_code` or a HuggingFaceAPI token can be passed via the `tokenizer_kwargs` and `model_kwargs`
     parameters.
 
     Attributes:
         model_name (str): The name of the Huggingface model to use.
         tokenizer (transformers.PreTrainedTokenizer): The tokenizer for the specified model.
         model (transformers.PreTrainedModel): The Huggingface model instance.
         device (torch.device): The device (CPU or GPU) on which the model is loaded.
-        tokenizer_kwargs (dict): Additional keyword arguments passed to the tokenizer.
-        model_kwargs (dict): Additional keyword arguments passed to the model.
     """
 
     def __init__(
@@ -33,7 +31,7 @@ def __init__(
         tokenizer_kwargs: dict | None = None,
         model_kwargs: dict | None = None,
     ):
-        """Initializes the HuggingfaceVectoriser with the specified model name and device.
+        """Initialises the HuggingfaceVectoriser with the specified model name and device.
 
         Args:
             model_name (str): The name of the Huggingface model to use.
@@ -44,7 +42,7 @@ def __init__(
 
         Raises:
             `ExternalServiceError`: If the model or tokenizer cannot be loaded.
-            `ConfigurationError`: If the model cannot be initialized on the specified device.
+            `ConfigurationError`: If the model cannot be initialised on the specified device.
         """
         check_deps(["transformers", "torch"], extra="huggingface")
         import torch  # type: ignore
@@ -85,7 +83,7 @@ def __init__(
             self.model.eval()
         except Exception as e:
             raise ConfigurationError(
-                "Failed to initialize model on device.",
+                "Failed to initialise model on device.",
                 context={
                     "vectoriser": "huggingface",
                     "model": model_name,

src/classifai/vectorisers/ollama.py

@@ -9,7 +9,7 @@
 
 
 class OllamaVectoriser(VectoriserBase):
-    """A wrapper class allowing a locally-running ollama server to generate text embeddings.
+    """A wrapper class allowing a locally-running Ollama server to generate text embeddings.
 
     The `OllamaVectoriser` interacts with a locally-running Ollama server, which must be set
     up by the user separately.
@@ -22,23 +22,23 @@ class OllamaVectoriser(VectoriserBase):
     """
 
     def __init__(self, model_name: str):
-        """Initializes the OllamaVectoriser with the specified model name and device.
+        """Initialises the OllamaVectoriser with the specified model name and device.
 
         Args:
             model_name (str): The name of the local model to use.
 
         Notes:
-            requires an ollama server to be running locally (`ollama serve`)
+            requires an Ollama server to be running locally (`ollama serve`)
         """
         check_deps(["ollama"], extra="ollama")
 
         self.model_name = model_name
 
     def transform(self, texts: str | list[str]) -> np.ndarray:
-        """Transforms input text(s) into embeddings using the Huggingface model.
+        """Transforms input text(s) into embeddings using the Ollama model.
 
         Args:
-            texts (str ,list [str]): The input text(s) to embed. Can be a single string or a list of strings.
+            texts (str, list [str]): The input text(s) to embed. Can be a single string or a list of strings.
 
         Returns:
             numpy.ndarray: A 2D array of embeddings, where each row corresponds to an input text.