langchain.retrievers.document_compressors.base.DocumentCompressorPipeline¶

class langchain.retrievers.document_compressors.base.DocumentCompressorPipeline(*, transformers: List[Union[BaseDocumentTransformer, BaseDocumentCompressor]])[source]¶

Bases: BaseDocumentCompressor

Document compressor that uses a pipeline of transformers.

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 transformers: List[Union[langchain.schema.document.BaseDocumentTransformer, langchain.retrievers.document_compressors.base.BaseDocumentCompressor]] [Required]¶

List of document filters that are chained together and run in sequence.

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

Compress retrieved documents given the query context.

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

Transform a list of documents.

model Config[source]¶

Bases: object

Configuration for this pydantic object.

arbitrary_types_allowed = True¶

Examples using DocumentCompressorPipeline¶