https://github.com/samadpls/bestrag

BestRAG: A library for hybrid RAG, combining dense, sparse, and late interaction methods for efficient document storage and search.
https://github.com/samadpls/bestrag

best-rag bm25 embedding-vectors hybrid-rag llm opensource pypi-package qdrant rag retrival-augmented-generation

Last synced: 8 months ago
JSON representation

BestRAG: A library for hybrid RAG, combining dense, sparse, and late interaction methods for efficient document storage and search.

• Host: GitHub
• URL: https://github.com/samadpls/bestrag
• Owner: samadpls
• License: mit
• Created: 2024-11-07T12:40:58.000Z (11 months ago)
• Default Branch: main
• Last Pushed: 2024-12-31T17:16:39.000Z (9 months ago)
• Last Synced: 2025-01-30T00:33:59.743Z (8 months ago)
• Topics: best-rag, bm25, embedding-vectors, hybrid-rag, llm, opensource, pypi-package, qdrant, rag, retrival-augmented-generation
• Language: Python
• Homepage: https://pypi.org/project/bestrag/
• Size: 36.1 KB
• Stars: 13
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE

Awesome Lists containing this project

README

          


![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)

[![PEP8](https://img.shields.io/badge/code%20style-pep8-black.svg)](https://www.python.org/dev/peps/pep-0008/)

[![License](https://img.shields.io/badge/License-MIT%202.0-blue.svg)](LICENSE)

[![Run Pytest](https://github.com/samadpls/BestRAG/actions/workflows/pytest.yml/badge.svg?branch=main)](https://github.com/samadpls/BestRAG/actions/workflows/pytest.yml)

![GitHub stars](https://img.shields.io/github/stars/samadpls/BestRAG?color=red&label=stars&logoColor=black&style=social)

![PyPI - Downloads](https://img.shields.io/pypi/dm/bestrag?style=social)  

Introducing **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.

## ✨ Features

🚀 **Hybrid RAG**: Utilizes dense, sparse, and late interaction embeddings for enhanced performance.  

🔌 **Easy Integration**: Simple API for storing and searching embeddings.  

📄 **PDF Support**: Directly store embeddings from PDF documents.  

## 🚀 Installation

To install **BestRAG**, simply run:

```bash

pip install bestrag

```

## 📦 Usage

Here’s how you can use **BestRAG** in your projects:

```python

from bestrag import BestRAG

rag = BestRAG(

    url="https://YOUR_QDRANT_URL", 

    api_key="YOUR_API_KEY", 

    collection_name="YOUR_COLLECTION_NAME"

)

# Store embeddings from a PDF

rag.store_pdf_embeddings("your_pdf_file.pdf", "pdf_name")

# Search using a query

results = rag.search(query="your search query", limit=10)

print(results)

# Delete particular pdf embeddings

rag.delete_pdf_embeddings("home/notes.pdf")

```

> **Note**: Qdrant offers a free tier with 4GB of storage. To generate your API key and endpoint, visit [Qdrant](https://qdrant.tech/).

##  🤗 Try it on Hugging Face Spaces  

You can explore and interact with **BestRAG** directly on Hugging Face Spaces: [BestRAG on Hugging Face](https://huggingface.co/spaces/samadpls/BestRAG)  

## 🤝 Contributing  

Feel free to contribute to **BestRAG**! Whether it’s reporting bugs, suggesting features, or submitting pull requests, your contributions are welcome.  

## 📝 License  

This project is licensed under the [MIT License](LICENSE).  

---

Created by [samadpls](https://github.com/samadpls) 🎉