RankLLMRerank#

class langchain_community.document_compressors.rankllm_rerank.RankLLMRerank[source]#

Bases: BaseDocumentCompressor

Document compressor using Flashrank interface.

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 client: Any = None#

RankLLM client to use for compressing documents

param gpt_model: str = 'gpt-3.5-turbo'#

OpenAI model name.

param model: str = 'zephyr'#

Name of model to use for reranking.

param step_size: int = 10#

Step size for moving sliding window.

param top_n: int = 3#

Top N documents to return.

async acompress_documents(documents: Sequence[Document], query: str, callbacks: List[BaseCallbackHandler] | BaseCallbackManager | None = None) Sequence[Document]#

Async compress retrieved documents given the query context.

Parameters:
Returns:

The compressed documents.

Return type:

Sequence[Document]

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

Compress retrieved documents given the query context.

Parameters:
Returns:

The compressed documents.

Return type:

Sequence[Document]

Examples using RankLLMRerank