Because "Trust me bro" isn't a valid source anymore.
Your AI-powered research assistant that provides scientifically-backed answers by analyzing millions of academic papers in real-time.
Live Demo · Report Bug · Request Feature
ScienceProves.Me revolutionizes research by providing instant, scientifically-backed answers to your questions. Our advanced RAG (Retrieval-Augmented Generation) system analyzes millions of academic papers in real-time, ensuring accurate and verifiable responses.
Feature | Description |
---|---|
🔍 Pure Science | Only peer-reviewed papers and trusted scientific sources |
🚀 Real-time RAG | Advanced retrieval-augmented generation for accurate answers |
📚 Full Transparency | Every answer includes citations and links to original research |
✅ No Hallucinations | Multi-stage verification ensures factual accuracy |
💫 Modern UX | Sleek, responsive interface with real-time streaming responses |
Ready to dive in? Check out our detailed setup guides:
.
├── Frontend/ # Next.js web application
│ ├── src/
│ │ ├── app/
│ │ │ ├── ask/
│ │ │ ├── dashboard/
│ │ │ └── history/
│ │ ├── components/
│ │ │ ├── ui/
│ │ │ ├── nav-bar.tsx
│ │ │ └── footer.tsx
│ │ ├── hooks/
│ │ └── lib/
│ ├── public/
│ ├── next.config.ts
│ └── package.json
│
└── Backend/ # FastAPI + RAG system
├── Data-ingestion/
│ └── data-ingestion.ipynb
├── SQL/
│ ├── create_documents_table.sql
│ ├── create_queries_table.sql
│ └── match_documents.sql
├── app/
│ ├── main.py
│ ├── core/config.py
│ ├── db/manager.py
│ └── services/request_manager.py
├── rag/
│ ├── rag.py
│ ├── rag_embeddings.py
│ ├── rag_llm.py
│ └── rag_retriever.py
├── requirements.txt
└── vercel.json
- Integration with PubMed and Nature databases
- Question Caching for faster responses
- Web Search responses added to DB
- Advanced citation management system
We welcome contributions! Feel free to:
- Open issues for bugs or suggestions
- Submit pull requests
- Share feedback and ideas
Special thanks to our amazing community and partners:
- Cornell University and arXiv for the extensive research papers dataset
- @JasonGoodison for the RAG app concept
- @mckaywrigley for mentorship in RAG development
- @RLanceMartin and @LangChainAI for implementation ideas
- Pixegami for inspiration
This project is licensed under the MIT License - see the LICENSE file for details.