🎓 Smart Academic Assistant

An AI-powered RAG (Retrieval-Augmented Generation) application that lets students upload academic documents and get instant, structured answers — built with LangChain, Groq, and Streamlit.

🚀 Features

• Document Q&A — Upload PDFs, DOCX, or TXT files and ask questions
• Structured JSON output — Every answer includes question, answer, source, and confidence score
• Agentic Tools — Summarize documents, generate MCQs, and explain topics
• Fast LLM inference — Powered by Llama3 via Groq API
• Semantic search — FAISS vector store with HuggingFace embeddings

🏗️ Architecture

User uploads doc → LangChain Loader → Text Splitter → HuggingFace Embeddings
                                                              ↓
User asks question → FAISS Retriever → Top-K chunks → Groq LLM → Structured JSON Answer

⚙️ Setup

git clone https://github.com/yourusername/smart-academic-assistant
cd smart-academic-assistant
pip install -r requirements.txt

Create a .env file:

GROQ_API_KEY=your_key_here
HUGGINGFACE_TOKEN=your_token_here

Run the app:

streamlit run app.py

🛠️ Tech Stack

Component	Technology
LLM	Llama3-8b via Groq
Embeddings	sentence-transformers/all-MiniLM-L6-v2
Vector Store	FAISS
Framework	LangChain (LCEL)
UI	Streamlit
File Support	PDF, DOCX, TXT

📁 Project Structure

├── app.py              # Streamlit UI
├── rag_pipeline.py     # Core RAG logic
├── tools.py            # Agentic tools
├── agent.py            # LangChain Agent
├── requirements.txt
└── .env                # API keys (not committed)