IRerankingService
Wisej.AI.Services.IRerankingService
Last updated
Wisej.AI.Services.IRerankingService
Last updated
Namespace: Wisej.AI.Services
Assembly: Wisej.AI (3.5.0.0)
Represents a service for reranking documents based on a given query.
: Gets or sets the maximum number of documents to return in the reranked response. If set to 0 it will return all the documents in the input.
Asynchronously reranks the provided chunks based on the specified query.
query
The query used to rerank the chunks.
chunks
The array of text inputs to be reranked.
Returns: . A task that represents the asynchronous operation. The task result contains an array of reranked text inputs.
Represents a service for reranking text inputs using the LocalAI API.
Represents a service for reranking text inputs using the Pinecone API.
Provides a default implementation of the for reranking documents using a specified endpoint to an AI provider. It uses LLM models to rerank and optionally optimize the submitted inputs.