VoyageAIRerank#
- class langchain_voyageai.rerank.VoyageAIRerank[source]#
Bases:
BaseDocumentCompressor
Document compressor that uses VoyageAI 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 aclient: AsyncClient = None#
VoyageAI clients to use for compressing documents.
- param client: Client = None#
- param model: str [Required]#
Model to use for reranking.
- param top_k: int | None = None#
Number of documents to return.
- param truncation: bool = True#
- param voyage_api_key: SecretStr | None = None#
VoyageAI API key. Must be specified directly or via environment variable VOYAGE_API_KEY.
- Constraints:
type = string
writeOnly = True
format = password
- async acompress_documents(documents: Sequence[Document], query: str, callbacks: List[BaseCallbackHandler] | BaseCallbackManager | None = None) Sequence[Document] [source]#
Compress documents using VoyageAI’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 in relevance_score order.
- Return type:
Sequence[Document]
- compress_documents(documents: Sequence[Document], query: str, callbacks: List[BaseCallbackHandler] | BaseCallbackManager | None = None) Sequence[Document] [source]#
Compress documents using VoyageAI’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 in relevance_score order.
- Return type:
Sequence[Document]