langchain_community.vectorstores.vectara
.VectaraQueryConfig¶
- class langchain_community.vectorstores.vectara.VectaraQueryConfig(k: int = 10, lambda_val: float = 0.0, filter: str = '', score_threshold: ~typing.Optional[float] = None, n_sentence_context: int = 2, mmr_config: ~langchain_community.vectorstores.vectara.MMRConfig = <factory>, summary_config: ~langchain_community.vectorstores.vectara.SummaryConfig = <factory>)[source]¶
k: Number of Documents to return. Defaults to 10. lambda_val: lexical match parameter for hybrid search. filter Dictionary of argument(s) to filter on metadata. For example a
filter can be “doc.rating > 3.0 and part.lang = ‘deu’”} see https://docs.vectara.com/docs/search-apis/sql/filter-overview for more details.
- score_threshold: minimal score threshold for the result.
If defined, results with score less than this value will be filtered out.
- n_sentence_context: number of sentences before/after the matching segment
to add, defaults to 2
mmr_config: MMRConfig configuration dataclass summary_config: SummaryConfig configuration dataclass
Attributes
filter
k
lambda_val
n_sentence_context
score_threshold
mmr_config
summary_config
Methods
__init__
([k, lambda_val, filter, ...])- __init__(k: int = 10, lambda_val: float = 0.0, filter: str = '', score_threshold: ~typing.Optional[float] = None, n_sentence_context: int = 2, mmr_config: ~langchain_community.vectorstores.vectara.MMRConfig = <factory>, summary_config: ~langchain_community.vectorstores.vectara.SummaryConfig = <factory>) None ¶