{"library":"flashrank","type":"library","category":null,"description":"FlashRank is an ultra-lite and super-fast Python library designed to add re-ranking capabilities to existing search and retrieval pipelines. Leveraging state-of-the-art LLMs and cross-encoders, it provides both pairwise (cross-encoder based) and listwise (LLM-based) re-ranking. As of version 0.2.10, FlashRank is known for its speed and efficiency, particularly on CPU, making it suitable for cost-effective serverless deployments. The library maintains an active development pace with frequent updates and bug fixes.","language":"python","status":"active","version":"0.2.10","tags":["re-ranking","nlp","search","retrieval-augmented-generation","RAG","cross-encoder","LLM"],"last_verified":"Mon May 25","install":[{"cmd":"pip install flashrank","imports":["from flashrank.Ranker import Ranker","from flashrank.RerankRequest import RerankRequest"]},{"cmd":"pip install flashrank[llm]","imports":[]}],"homepage":null,"github":"https://github.com/PrithivirajDamodaran/FlashRank","docs":null,"changelog":null,"pypi":"https://pypi.org/project/flashrank/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":50,"avg_install_s":10.9,"avg_import_s":0.91,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/flashrank/compatibility"}}