Deploying to gh-pages from @ a1d3631 🚀

.buildinfo

@@ -0,0 +1,4 @@
+# Sphinx build info version 1
+# This file records the configuration used when building these files. When it is not found, a full rebuild will be done.
+config: 5bff8e112615726b22bbc2c1a7f4563b
+tags: 645f666f9bcd5a90fca523b33c5a78b7

_sources/autoapi/autointent/Context.rst.txt

@@ -0,0 +1,158 @@
+autointent.Context
+==================
+
+.. py:class:: autointent.Context(seed = 42)
+
+   Context manager for configuring and managing data handling, vector indexing, and optimization.
+
+   This class provides methods to set up logging, configure data and vector index components,
+   manage datasets, and retrieve various configurations for inference and optimization.
+
+
+   .. py:attribute:: data_handler
+      :type:  autointent.context.data_handler.DataHandler
+
+
+   .. py:attribute:: vector_index_client
+      :type:  autointent.context.vector_index_client.VectorIndexClient
+
+
+   .. py:attribute:: optimization_info
+      :type:  autointent.context.optimization_info.OptimizationInfo
+
+
+   .. py:attribute:: seed
+      :value: 42
+
+
+
+   .. py:method:: configure_logging(config)
+
+      Configure logging settings.
+
+      :param config: Logging configuration settings.
+
+
+
+   .. py:method:: configure_vector_index(config, embedder_config = None)
+
+      Configure the vector index client and embedder.
+
+      :param config: Configuration for the vector index.
+      :param embedder_config: Configuration for the embedder. If None, a default EmbedderConfig is used.
+
+
+
+   .. py:method:: configure_data(config)
+
+      Configure data handling.
+
+      :param config: Configuration for the data handling process.
+
+
+
+   .. py:method:: set_dataset(dataset, force_multilabel = False)
+
+      Set the datasets for training, validation and testing.
+
+      :param dataset: Dataset.
+      :param force_multilabel: Whether to force multilabel classification.
+
+
+
+   .. py:method:: get_inference_config()
+
+      Generate configuration settings for inference.
+
+      :return: Dictionary containing inference configuration.
+
+
+
+   .. py:method:: dump()
+
+      Save logs, configurations, and datasets to disk.
+
+      Dumps evaluation results, training/test data splits, and inference configurations
+      to the specified logging directory.
+
+
+
+   .. py:method:: get_db_dir()
+
+      Get the database directory of the vector index.
+
+      :return: Path to the database directory.
+
+
+
+   .. py:method:: get_device()
+
+      Get the embedder device used by the vector index client.
+
+      :return: Device name.
+
+
+
+   .. py:method:: get_batch_size()
+
+      Get the batch size used by the embedder.
+
+      :return: Batch size.
+
+
+
+   .. py:method:: get_max_length()
+
+      Get the maximum sequence length for embeddings.
+
+      :return: Maximum length or None if not set.
+
+
+
+   .. py:method:: get_use_cache()
+
+      Check if caching is enabled for the embedder.
+
+      :return: True if caching is enabled, False otherwise.
+
+
+
+   .. py:method:: get_dump_dir()
+
+      Get the directory for saving dumped modules.
+
+      :return: Path to the dump directory or None if dumping is disabled.
+
+
+
+   .. py:method:: is_multilabel()
+
+      Check if the dataset is configured for multilabel classification.
+
+      :return: True if multilabel classification is enabled, False otherwise.
+
+
+
+   .. py:method:: get_n_classes()
+
+      Get the number of classes in the dataset.
+
+      :return: Number of classes.
+
+
+
+   .. py:method:: is_ram_to_clear()
+
+      Check if RAM clearing is enabled in the logging configuration.
+
+      :return: True if RAM clearing is enabled, False otherwise.
+
+
+
+   .. py:method:: has_saved_modules()
+
+      Check if any modules have been saved.
+
+      :return: True if there are saved modules, False otherwise.
+
+

_sources/autoapi/autointent/Dataset.rst.txt

@@ -0,0 +1,129 @@
+autointent.Dataset
+==================
+
+.. py:class:: autointent.Dataset(*args, intents, **kwargs)
+
+   Bases: :py:obj:`dict`\ [\ :py:obj:`str`\ , :py:obj:`datasets.Dataset`\ ]
+
+
+   Represents a dataset with associated metadata and utilities for processing.
+
+   :param args: Positional arguments to initialize the dataset.
+   :param intents: List of intents associated with the dataset.
+   :param kwargs: Additional keyword arguments to initialize the dataset.
+
+
+   .. py:attribute:: label_feature
+      :value: 'label'
+
+
+
+   .. py:attribute:: utterance_feature
+      :value: 'utterance'
+
+
+
+   .. py:attribute:: intents
+
+
+   .. py:property:: multilabel
+      :type: bool
+
+
+      Check if the dataset is multilabel.
+
+      :return: True if the dataset is multilabel, False otherwise.
+
+
+
+   .. py:property:: n_classes
+      :type: int
+
+
+      Get the number of classes in the training split.
+
+      :return: Number of classes.
+
+
+
+   .. py:method:: from_dict(mapping)
+      :classmethod:
+
+
+      Load a dataset from a dictionary mapping.
+
+      :param mapping: Dictionary representing the dataset.
+      :return: Initialized Dataset object.
+
+
+
+   .. py:method:: from_json(filepath)
+      :classmethod:
+
+
+      Load a dataset from a JSON file.
+
+      :param filepath: Path to the JSON file.
+      :return: Initialized Dataset object.
+
+
+
+   .. py:method:: from_hub(repo_id)
+      :classmethod:
+
+
+      Load a dataset from a Hugging Face repository.
+
+      :param repo_id: ID of the Hugging Face repository.
+      :return: Initialized Dataset object.
+
+
+
+   .. py:method:: to_multilabel()
+
+      Convert dataset labels to multilabel format.
+
+      :return: Self, with labels converted to multilabel.
+
+
+
+   .. py:method:: to_dict()
+
+      Convert the dataset splits and intents to a dictionary of lists.
+
+      :return: A dictionary containing dataset splits and intents as lists of dictionaries.
+
+
+
+   .. py:method:: to_json(filepath)
+
+      Save the dataset splits and intents to a JSON file.
+
+      :param filepath: The path to the file where the JSON data will be saved.
+
+
+
+   .. py:method:: push_to_hub(repo_id, private = False)
+
+      Push dataset splits to a Hugging Face repository.
+
+      :param repo_id: ID of the Hugging Face repository.
+
+
+
+   .. py:method:: get_tags()
+
+      Extract unique tags from the dataset's intents.
+
+      :return: List of tags with their associated intent IDs.
+
+
+
+   .. py:method:: get_n_classes(split)
+
+      Calculate the number of unique classes in a given split.
+
+      :param split: The split to analyze.
+      :return: Number of unique classes.
+
+

_sources/autoapi/autointent/Embedder.rst.txt

@@ -0,0 +1,93 @@
+autointent.Embedder
+===================
+
+.. py:class:: autointent.Embedder(model_name, device = 'cpu', batch_size = 32, max_length = None, use_cache = False)
+
+   A wrapper for managing embedding models using Sentence Transformers.
+
+   This class handles initialization, saving, loading, and clearing of
+   embedding models, as well as calculating embeddings for input texts.
+
+
+   .. py:attribute:: embedder_subdir
+      :type:  str
+      :value: 'sentence_transformers'
+
+
+
+   .. py:attribute:: metadata_dict_name
+      :type:  str
+      :value: 'metadata.json'
+
+
+
+   .. py:attribute:: model_name
+
+
+   .. py:attribute:: device
+      :value: 'cpu'
+
+
+
+   .. py:attribute:: batch_size
+      :value: 32
+
+
+
+   .. py:attribute:: max_length
+      :value: None
+
+
+
+   .. py:attribute:: use_cache
+      :value: False
+
+
+
+   .. py:attribute:: logger
+
+
+   .. py:method:: __hash__()
+
+      Compute a hash value for the Embedder.
+
+      :returns: The hash value of the Embedder.
+
+
+
+   .. py:method:: clear_ram()
+
+      Move the embedding model to CPU and delete it from memory.
+
+
+
+   .. py:method:: delete()
+
+      Delete the embedding model and its associated directory.
+
+
+
+   .. py:method:: dump(path)
+
+      Save the embedding model and metadata to disk.
+
+      :param path: Path to the directory where the model will be saved.
+
+
+
+   .. py:method:: load(path)
+
+      Load the embedding model and metadata from disk.
+
+      :param path: Path to the directory where the model is stored.
+
+
+
+   .. py:method:: embed(utterances)
+
+      Calculate embeddings for a list of utterances.
+
+      :param utterances: List of input texts to calculate embeddings for.
+      :return: A numpy array of embeddings.
+
+