abacusai.api_class.document_retriever

Attributes

DocumentRetrieverConfig

Classes

ApiClass

Helper class that provides a standard way to create an ABC using

VectorStoreTextEncoder

Generic enumeration.

VectorStoreConfig

Config for indexing options of a document retriever. Default values of optional arguments are heuristically selected by the Abacus.AI platform based on the underlying data.

Module Contents

class abacusai.api_class.document_retriever.ApiClass

Bases: abc.ABC

Helper class that provides a standard way to create an ABC using inheritance.

_upper_snake_case_keys: bool
_support_kwargs: bool
__post_init__()
classmethod _get_builder()
__str__()

Return str(self).

_repr_html_()
__getitem__(item)
Parameters:

item (str)

__setitem__(item, value)
Parameters:

  • item (str)

  • value (Any)

_unset_item(item)
Parameters:

item (str)

get(item, default=None)
Parameters:

  • item (str)

  • default (Any)

pop(item, default=NotImplemented)
Parameters:

  • item (str)

  • default (Any)

to_dict()

Standardizes converting an ApiClass to dictionary. Keys of response dictionary are converted to camel case. This also validates the fields ( type, value, etc ) received in the dictionary.

classmethod from_dict(input_dict)
Parameters:

input_dict (dict)

class abacusai.api_class.document_retriever.VectorStoreTextEncoder

Bases: ApiEnum

Generic enumeration.

Derive from this class to define new enumerations.

E5 = 'E5'
OPENAI = 'OPENAI'
SENTENCE_BERT = 'SENTENCE_BERT'
E5_SMALL = 'E5_SMALL'
class abacusai.api_class.document_retriever.VectorStoreConfig

Bases: abacusai.api_class.abstract.ApiClass

Config for indexing options of a document retriever. Default values of optional arguments are heuristically selected by the Abacus.AI platform based on the underlying data.

Parameters:

  • chunk_size (int) – The size of text chunks in the vector store.

  • chunk_overlap_fraction (float) – The fraction of overlap between chunks.

  • text_encoder (VectorStoreTextEncoder) – Encoder used to index texts from the documents.

  • chunk_size_factors (list) – Chunking data with multiple sizes. The specified list of factors are used to calculate more sizes, in addition to chunk_size.

  • score_multiplier_column (str) – If provided, will use the values in this metadata column to modify the relevance score of returned chunks for all queries.

  • prune_vectors (bool) – Transform vectors using SVD so that the average component of vectors in the corpus are removed.

chunk_size: int
chunk_overlap_fraction: float
text_encoder: abacusai.api_class.enums.VectorStoreTextEncoder
chunk_size_factors: list
score_multiplier_column: str
prune_vectors: bool
abacusai.api_class.document_retriever.DocumentRetrieverConfig