cherche
Cherche supports creating neural search pipelines that utilize retrievers and pre-trained language models for effective document retrieval and ranking. It excels in constructing end-to-end solutions, suitable for offline semantic searches with batch processing. Cherche integrates with popular retrievers like TfIdf, Flash, Lunr, and uses SentenceTransformers for advanced ranking. Comprehensive documentation and live demos are available to assist users. It is MIT licensed and open for community contributions.
