{"id":25264323,"url":"https://github.com/samadpls/bestrag","last_synced_at":"2025-10-27T04:30:28.438Z","repository":{"id":261601340,"uuid":"884812802","full_name":"samadpls/BestRAG","owner":"samadpls","description":"BestRAG: A library for hybrid RAG, combining dense, sparse, and late interaction methods for efficient document storage and search.","archived":false,"fork":false,"pushed_at":"2024-12-31T17:16:39.000Z","size":37,"stargazers_count":13,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-01-30T00:33:59.743Z","etag":null,"topics":["best-rag","bm25","embedding-vectors","hybrid-rag","llm","opensource","pypi-package","qdrant","rag","retrival-augmented-generation"],"latest_commit_sha":null,"homepage":"https://pypi.org/project/bestrag/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/samadpls.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-11-07T12:40:58.000Z","updated_at":"2025-01-09T19:00:17.000Z","dependencies_parsed_at":null,"dependency_job_id":"f601fade-4121-4284-9fc9-ffea4435c613","html_url":"https://github.com/samadpls/BestRAG","commit_stats":null,"previous_names":["samadpls/bestrag"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/samadpls%2FBestRAG","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/samadpls%2FBestRAG/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/samadpls%2FBestRAG/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/samadpls%2FBestRAG/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/samadpls","download_url":"https://codeload.github.com/samadpls/BestRAG/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":238431787,"owners_count":19471454,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["best-rag","bm25","embedding-vectors","hybrid-rag","llm","opensource","pypi-package","qdrant","rag","retrival-augmented-generation"],"created_at":"2025-02-12T07:36:29.889Z","updated_at":"2025-10-27T04:30:22.581Z","avatar_url":"https://github.com/samadpls.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cimg src=\"https://github.com/user-attachments/assets/e23d11d5-2d7b-44e2-aa11-59ddcb66bebc\" align=left height=180px\u003e\n\n![Supported python versions](https://img.shields.io/badge/python-3.7%20%7C%203.8%20%7C%203.9%20%7C%203.10%20%7C%203.11-blue)\n[![PEP8](https://img.shields.io/badge/code%20style-pep8-black.svg)](https://www.python.org/dev/peps/pep-0008/)\n[![License](https://img.shields.io/badge/License-MIT%202.0-blue.svg)](LICENSE)\n[![Run Pytest](https://github.com/samadpls/BestRAG/actions/workflows/pytest.yml/badge.svg?branch=main)](https://github.com/samadpls/BestRAG/actions/workflows/pytest.yml)\n![GitHub stars](https://img.shields.io/github/stars/samadpls/BestRAG?color=red\u0026label=stars\u0026logoColor=black\u0026style=social)\n![PyPI - Downloads](https://img.shields.io/pypi/dm/bestrag?style=social)  \n\nIntroducing **BestRAG**! This Python library leverages a hybrid Retrieval-Augmented Generation (RAG) approach to efficiently store and retrieve embeddings. By combining dense, sparse, and late interaction embeddings, **BestRAG** offers a robust solution for managing large datasets.\n\n## ✨ Features\n\n🚀 **Hybrid RAG**: Utilizes dense, sparse, and late interaction embeddings for enhanced performance.  \n🔌 **Easy Integration**: Simple API for storing and searching embeddings.  \n📄 **PDF Support**: Directly store embeddings from PDF documents.  \n\n## 🚀 Installation\n\nTo install **BestRAG**, simply run:\n\n```bash\npip install bestrag\n```\n\n## 📦 Usage\n\nHere’s how you can use **BestRAG** in your projects:\n\n```python\nfrom bestrag import BestRAG\n\nrag = BestRAG(\n    url=\"https://YOUR_QDRANT_URL\", \n    api_key=\"YOUR_API_KEY\", \n    collection_name=\"YOUR_COLLECTION_NAME\"\n)\n\n# Store embeddings from a PDF\nrag.store_pdf_embeddings(\"your_pdf_file.pdf\", \"pdf_name\")\n\n# Search using a query\nresults = rag.search(query=\"your search query\", limit=10)\nprint(results)\n\n# Delete particular pdf embeddings\nrag.delete_pdf_embeddings(\"home/notes.pdf\")\n```\n\n\u003e **Note**: Qdrant offers a free tier with 4GB of storage. To generate your API key and endpoint, visit [Qdrant](https://qdrant.tech/).\n\n##  🤗 Try it on Hugging Face Spaces  \n\nYou can explore and interact with **BestRAG** directly on Hugging Face Spaces: [BestRAG on Hugging Face](https://huggingface.co/spaces/samadpls/BestRAG)  \n\n## 🤝 Contributing  \n\nFeel free to contribute to **BestRAG**! Whether it’s reporting bugs, suggesting features, or submitting pull requests, your contributions are welcome.  \n\n## 📝 License  \n\nThis project is licensed under the [MIT License](LICENSE).  \n\n---\n\nCreated by [samadpls](https://github.com/samadpls) 🎉  \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsamadpls%2Fbestrag","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsamadpls%2Fbestrag","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsamadpls%2Fbestrag/lists"}