EmbeddingsFilter#

class langchain.retrievers.document_compressors.embeddings_filter.EmbeddingsFilter[source]#

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][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

param embeddings: Embeddings [Required]#: Embeddings to use for embedding document contents and queries.

param k: int | None = 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 [Optional]#: 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: float | None = 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: list[BaseCallbackHandler] | BaseCallbackManager | None = None) → Sequence[Document][source]#

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

Parameters:

Return type:

Sequence[Document]

compress_documents(documents: Sequence[Document], query: str, callbacks: list[BaseCallbackHandler] | BaseCallbackManager | None = None) → Sequence[Document][source]#

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

Parameters:

Return type:

Sequence[Document]

classmethod validate_params(values: Dict) → Dict[source]#

Validate similarity parameters.

Examples using EmbeddingsFilter