{"data":{"slug":"prithivirajdamodaran-flashrank","name":"FlashRank","tagline":"Lite & Super-fast re-ranking for search & retrieval pipelines","github_url":"https://github.com/PrithivirajDamodaran/FlashRank","owner":"PrithivirajDamodaran","repo":"FlashRank","owner_avatar_url":"https://avatars.githubusercontent.com/u/7071019?v=4","primary_language":"Python","stars":1002,"forks":72,"topics":["cross-encoder","full-text-search","hybrid-search","lexical-search","rag","ranking","reranking","retrieval-augmented-generation","semantic-search","vector-database","vector-search"],"archived":false,"github_pushed_at":"2026-07-11T08:06:27+00:00","maintenance_label":"Steady","stars_delta_30d":7,"url":"https://www.graphcanon.com/tools/prithivirajdamodaran-flashrank","markdown_url":"https://www.graphcanon.com/tools/prithivirajdamodaran-flashrank.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/prithivirajdamodaran-flashrank","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=prithivirajdamodaran-flashrank","description":"Lite & Super-fast re-ranking for your search & retrieval pipelines.  Supports SoTA Listwise and Pairwise reranking based on LLMs and  cross-encoders and more.  Created by Prithivi Da, open for PRs & Collaborations.","homepage_url":null,"license":"Apache-2.0","open_issues":10,"watchers":6,"ai_summary":"FlashRank supports state-of-the-art listwise and pairwise reranking based on Large Language Models (LLMs) and cross-encoders, enhancing the functionality of hybrid, lexical, and semantic search systems.","readme_excerpt":"## Installation:\n#### If you need lightweight pairwise rerankers [default] \n```python \npip install flashrank\n```\n\n#### If you need LLM based listwise rerankers\n```python \npip install flashrank[listwise]\n```\n\n---\n\n## Getting started:\n```python\nfrom flashrank import Ranker, RerankRequest\n\n---\n\n## Deployment patterns\n#### How to use it in a AWS Lambda function ?\nIn AWS or other serverless environments the entire VM is read-only you might have to create your \nown custom dir. You can do so in your Dockerfile and use it for loading the models (and eventually as a cache between warm calls). You can do it during init with cache_dir parameter. \n\n```python\nranker = Ranker(model_name=\"ms-marco-MiniLM-L-12-v2\", cache_dir=\"/opt\")\n```","github_created_at":"2023-12-04T14:23:44+00:00","created_at":"2026-07-07T17:44:46.436515+00:00","updated_at":"2026-08-21T18:02:03.909115+00:00","categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"}],"tags":[{"slug":"cross-encoder","name":"cross-encoder"},{"slug":"full-text-search","name":"full-text-search"},{"slug":"hybrid-search","name":"hybrid-search"},{"slug":"lexical-search","name":"lexical-search"},{"slug":"rag","name":"rag"},{"slug":"ranking","name":"ranking"},{"slug":"reranking","name":"reranking"},{"slug":"retrieval-augmented-generation","name":"retrieval-augmented-generation"}],"trust":{"provenance":{"is_fork":false,"github_id":727268148,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-21T18:02:03.077Z","maintenance":{"label":"Steady","score":60,"methodology":"github_public_v1","releases_90d":0,"days_since_push":41,"last_release_at":"2024-11-29T09:46:10Z","stars_delta_30d":7,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:26:38.518Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-21T18:02:03.554Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-08-21T18:02:03.554Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-21T18:02:03.554Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["Need fast re-ranking solutions for hybrid or semantic searches","Want to integrate state-of-the-art LLM-based techniques into existing pipelines"],"when_not_to_use":["Prioritize lightweight tools over comprehensive feature sets in simpler search applications","Seeking traditional relevance feedback mechanisms over modern reranking methods"],"source":"enrich:decision_facts","observed_at":"2026-07-12T14:08:16.513Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"FlashRank enhances search and retrieval efficiency with rapid listwise and pairwise reranking using LLMs and cross-encoders."}]}}