langchain.retrievers.document_compressors.embeddings_filter.EmbeddingsFilter

class langchain.retrievers.document_compressors.embeddings_filter.EmbeddingsFilter(*, embeddings: ~langchain.embeddings.base.Embeddings, similarity_fn: ~typing.Callable = <function cosine_similarity>, k: ~typing.Optional[int] = 20, similarity_threshold: ~typing.Optional[float] = None)

Bases: BaseDocumentCompressor

Document compressor that uses embeddings to drop documents unrelated to the query.

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

param embeddings: langchain.embeddings.base.Embeddings [Required]

Embeddings to use for embedding document contents and queries.

param k: Optional[int] = 20

The number of relevant documents to return. Can be set to None, in which case similarity_threshold must be specified. Defaults to 20.

param similarity_fn: Callable = <function cosine_similarity>

Similarity function for comparing documents. Function expected to take as input two matrices (List[List[float]]) and return a matrix of scores where higher values indicate greater similarity.

param similarity_threshold: Optional[float] = None

Threshold for determining when two documents are similar enough to be considered redundant. Defaults to None, must be specified if k is set to None.

async acompress_documents(documents: Sequence[Document], query: str, callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None) → Sequence[Document]

Filter down documents.

compress_documents(documents: Sequence[Document], query: str, callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None) → Sequence[Document]

Filter documents based on similarity of their embeddings to the query.

validator validate_params  »  all fields

Validate similarity parameters.

model Config

Bases: object

Configuration for this pydantic object.

arbitrary_types_allowed = True