Learn how to configure reranking in Quivr.
Quivr uses its own reranking service to improve the quality of search results. This guide will show you how to configure the reranking service in Quivr.
We are using FlashrankRerank from Flashrank to improve the quality of search results. It is a reranking open-source library that uses deep learning models to rerank search results.
To use the Cohere ReRanker, you need to configure the following environment variables in your .env file:
By default, the COHERE_API_KEY variable is not set. If you want to use the Cohere ReRanker, you need to set it to your Cohere API key.
By default the Ranker outputs the best 5 results.
We only use the Cohere ReRanker to improve the quality of search results. We do not collect any personal data or sensitive information.