Cherche allows the creation of efficient neural search pipelines using retrievers and pre-trained language models as rankers. Cherche's main strength is its ability to build diverse and end-to-end pipelines from lexical matching, semantic matching, and collaborative filtering-based models. Cherche provides modules dedicated to summarization and question answering. These modules are compatible with Hugging Face's pre-trained models and fully integrated into neural search pipelines. Search is fully compatible with the collaborative filtering library Implicit. It is advantageous if you have a history associated with users and you want to retrieve / re-rank documents based on user preferences.
Features
- Cherche allows creating a neural search pipeline
- Use retrievers and pre-trained language models as rankers
- Cherche's main strength is its ability to build diverse and end-to-end pipelines
- Cherche allows to find the right document within a list of JSON
- Retriever ranker
- Map the index to documents
License
MIT LicenseFollow Cherche
You Might Also Like
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of Cherche!