BM25Retriever#

class ragger_duck.retrieval.BM25Retriever(*, count_vectorizer=None, top_k=1, b=0.75, k1=1.6)#

Retrieve the k-nearest neighbors using a lexical search based on BM25.

Parameters:

count_vectorizertransformer, default=None: A count vectorizer to compute the count of terms in documents. If None, a sklearn.feature_extraction.text.CountVectorizer is used.
top_kint, default=1: Number of documents to retrieve.

Attributes:

X_fit_list of str or dict: The input data.
X_counts_sparse matrix of shape (n_documents, n_features): The count of terms in documents.
count_vectorizer_transformer: The count vectorizer used to compute the count of terms in documents.
n_terms_by_document_ndarray of shape (n_sentences,): The number of terms by document.
averaged_document_length_float: The average number of terms by document.
idf_ndarray of shape (n_features,): The inverse document frequency.

Methods

`fit`(X[, y])	Compute the vocabulary and the idf.
`get_metadata_routing`()	Get metadata routing of this object.
`get_params`([deep])	Get parameters for this estimator.
`query`(query)	Retrieve the most relevant documents for the query.
`set_params`(**params)	Set the parameters of this estimator.

fit(X, y=None)#

Compute the vocabulary and the idf.

Parameters:

Xlist of str or dict: The input data.
yNone: This parameter is ignored.

Returns:

self: The fitted estimator.

get_metadata_routing()#

Get metadata routing of this object.

Please check User Guide on how the routing mechanism works.

Returns:

routingMetadataRequest: A MetadataRequest encapsulating routing information.

get_params(deep=True)#

Get parameters for this estimator.

Parameters:

deepbool, default=True: If True, will return the parameters for this estimator and contained subobjects that are estimators.

Returns:

paramsdict: Parameter names mapped to their values.

query(query)#

Retrieve the most relevant documents for the query.

Parameters:

querystr: The input data.

Returns:

list of str or dict: The list of the most relevant document from the training set.

set_params(**params)#

Set the parameters of this estimator.

The method works on simple estimators as well as on nested objects (such as Pipeline). The latter have parameters of the form <component>__<parameter> so that it’s possible to update each component of a nested object.

Parameters:

**paramsdict: Estimator parameters.

Returns:

selfestimator instance: Estimator instance.