InsightPDF is a high-performance RAG (Retrieval-Augmented Generation) application that allows users to upload complex documents and query them in real-time. Powered by Groq's LPL (Language Processing Unit) and LLaMA 3, it delivers near-instant AI responses with deep contextual understanding.
- ⚡ Lightning Fast Inference: Leverages Groq's API for sub-second response times using LLaMA 3.
- 🧠 Intelligent RAG Pipeline: Uses LangChain and FAISS for efficient vector similarity search.
- 🎨 Modern UX/UI: A sleek, responsive interface built with Next.js 14, Tailwind CSS, and Framer Motion.
- 📂 Multi-Page Context: Extracts and processes text from large PDFs while maintaining structural context.
- 🔒 Privacy First: Documents are processed securely and stored in-memory for session-based privacy.
| Layer | Technologies |
|---|---|
| Frontend | Next.js 14 (App Router), TypeScript, Tailwind CSS, Framer Motion, Zustand |
| Backend | FastAPI (Python), Uvicorn, Pydantic |
| AI / ML | Groq API (LLaMA 3.1 8B), LangChain, HuggingFace Embeddings |
| Vector DB | FAISS (Facebook AI Similarity Search) |
| PDF Engine | PyMuPDF (fitz) |
- Python 3.9+
- Node.js 18+
- Groq API Key (Get one here)
cd backend
python -m venv venv
source venv/bin/scripts/activate # Windows: venv\Scripts\activate
pip install -r requirements.txtcd frontend
npm installCreate a .env file in the root directory:
GROQ_API_KEY=your_api_key_here- Start Backend:
cd backend python main.py - Start Frontend:
cd frontend npm run dev - Access the App: Open
http://localhost:3000in your browser.
- Support for multiple file uploads (Batch Processing).
- OCR integration for scanned/image-based PDFs.
- Export chat history to PDF/Markdown.
- Deployment via Docker & AWS/Vercel.
Rahul Raj Jaiswal
- GitHub: @Rahul130405
- LinkedIn: Rahul Raj Jaiswal
- Portfolio: [Your Portfolio Link]
Distributed under the MIT License. See LICENSE for more information.