GenRAG-UI

Improved and better version of the Terminal GenRAG tool designed to set up a Retrieval-Augmented Generation Pipeline locally from scratch, without utilizing any high-level frameworks like LangChain or vector databases. It includes features such as recursive text splitting, chunking, and building embeddings. The embeddings are stored in a CSV file,without using any Vector Databases and searching is based on cosine similarity.

Features

• Recursive text splitting
• Text chunking
• Building embeddings
• Storing embeddings in a CSV file
• Searching based on cosine similarity
• Inference from local LLM/API
• UI for easier interaction and evaluation metrics (React-based)

Installation

1. Clone the repository:

   git clone https://github.com/adityaghai07/GenRAG.git
   cd GenRAG

2. Create and activate a virtual environment:

   python -m venv env
   source env/bin/activate  # On Windows use `env\Scripts\activate`

3. Install the required dependencies:

   pip install -r requirements.txt

Usage

1. Navigate to the backend folder:

   cd backend
   npm i
   npm run dev

2. Open a new terminal and navigate to the frontend folder:

   cd frontend
   python main.py

LLM Response

You can use both a local LLM or an LLM from an API like Gemini for generating responses.

• Local LLM: If you have the capability to run a local LLM, you can use it for generating responses. Cause mine is too slow :(

• LLM from API: If your system is not powerful enough for local inference, you can use an API like Gemini. To do this, create a .env file and pass the Gemini API key.

Using Gemini API

1. Create a .env file in the root directory of the project.
2. Add your Gemini API key to the .env file:

   GEMINI_API_KEY=your_api_key_here

3. The system will use the API key for generating responses through the Gemini API.

Credits

Special thanks to Pratik Solanki for his amazing React UI work , without him this project was not possible. Special thanks to the following YouTube channels and research papers for their invaluable resources and insights:

YouTube Channels

• AI Anytime
• Daniel Brouke
• Krish Naik
• Codebasics
• CampusX

Research Papers

• Patrick Lewis ., "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks" arXiv:2005.11401
• Vaswani et al., "Attention is All You Need" arXiv:1706.03762
• Reimers et al., "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks" arXiv:1908.10084

License

This project is licensed under the MIT License - see the LICENSE file for details.