Neurelic is a Retrieval-Augmented Generation (RAG) system designed to provide smart, context-aware responses by combining document retrieval with advanced language generation. Built using a modular architecture, Neurelic enables querying large document sets using semantic search and delivers AI-generated answers powered by transformer models.
Ask questions. Search documents. Get intelligent answers.
- Semantic Document Search – Uses embeddings for accurate information retrieval.
- Language Generation – Integrates large language models for natural language responses.
- Multi-format Document Support – Easily index and query JSON or raw text docs.
- Modular Architecture – Pluggable components for embeddings, retrieval, and generation.
- Streamlit UI – Simple, responsive interface for user-friendly querying.
- Clone the repository
git clone https://github.com/sedegah/Neurelic--RAG.git
cd Neurelic--RAG- Create a virtual environment
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate- Install dependencies
pip install -r requirements.txtstreamlit run app.pyThen open http://localhost:8501 in your browser.
- Indexing:
RAGSystemloads and indexes documents using sentence embeddings (viaSentenceTransformers). - Querying: On user input, the system retrieves the top relevant passages using FAISS similarity.
- Generation: The selected context is passed to a language model to generate a final answer.
- Internal knowledge base assistant
- Research paper Q&A system
- Educational tools
- Legal and compliance document querying
This project is licensed under the MIT License. See the LICENSE file for more info.
Kimathi Elikplim Sedegah Portfolio · GitHub
Contributions, issues, and feature requests are welcome! Feel free to open an issue or submit a pull request.
---
Let me know if you’d like a version with setup screenshots, hosted demo link, or deployment guide (e.g., on Vercel or Hugging Face Spaces).