Personal-RAG-Assistant in short

🧠 Personal RAG Knowledge Assistant

A local-first AI assistant that lets you upload PDFs/notes, ask questions about them, and get grounded answers with source citations.

✨ Features

• 📄 Upload PDF and notes
• 🔍 Semantic search using embeddings
• 🗄️ Vector storage with ChromaDB
• 🤖 RAG-powered question answering
• 📑 Document and page citations
• 💬 Conversation history
• 🔒 Local-first document storage
• 🖥️ Streamlit interface

🏗️ RAG Pipeline

Document
   ↓
Text Extraction
   ↓
Chunking
   ↓
Embeddings
   ↓
ChromaDB
   ↓
Semantic Retrieval
   ↓
LLM
   ↓
Answer + Citations

🛠️ Tech Stack

Python • FastAPI • Streamlit • PyMuPDF • Sentence Transformers • ChromaDB • SQLite • LLM API

🚀 Run

pip install -r requirements.txt
streamlit run streamlit_app/app.py

Configure your LLM/API credentials in .env.

🎯 Goal

Built to explore and understand embeddings, vector databases, semantic retrieval, and Retrieval-Augmented Generation (RAG) through a practical end-to-end project.

📌 Status

under work but functional for testing

🚧 Partially Active development