CohereRerank

class langchain.retrievers.document_compressors.cohere_rerank.CohereRerank

Bases: BaseDocumentCompressor

Deprecated since version 0.0.30: Use langchain_cohere.CohereRerank instead.

Document compressor that uses Cohere Rerank API.

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

Cohere client to use for compressing documents.

param cohere_api_key: str | None = None

Cohere API key. Must be specified directly or via environment variable COHERE_API_KEY.

param model: str = 'rerank-english-v2.0'

Model to use for reranking.

param top_n: int | None = 3

Number of documents to return.

param user_agent: str = 'langchain'

Identifier for the application making the request.

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:

• documents (Sequence[Document]) – The retrieved documents.

• query (str) – The query context.

• callbacks (List[BaseCallbackHandler] | BaseCallbackManager | None) – Optional callbacks to run during compression.

Returns:

The compressed documents.

Return type:

Sequence[Document]

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

Compress documents using Cohere’s rerank API.

Parameters:

• documents (Sequence[Document]) – A sequence of documents to compress.

• query (str) – The query to use for compressing the documents.

• callbacks (List[BaseCallbackHandler] | BaseCallbackManager | None) – Callbacks to run during the compression process.

Returns:

A sequence of compressed documents.

Return type:

Sequence[Document]

rerank(documents: Sequence[str | Document | dict], query: str, *, model: str | None = None, top_n: int | None = -1, max_chunks_per_doc: int | None = None) → List[Dict[str, Any]]

Returns an ordered list of documents ordered by their relevance to the provided query.

Parameters:

• query (str) – The query to use for reranking.

• documents (Sequence[str | Document | dict]) – A sequence of documents to rerank.

• model (str | None) – The model to use for re-ranking. Default to self.model.

• top_n (int | None) – The number of results to return. If None returns all results. Defaults to self.top_n.

• max_chunks_per_doc (int | None) – The maximum number of chunks derived from a document.

Return type:

List[Dict[str, Any]]