Skip to content

Latest commit

 

History

History
59 lines (40 loc) · 1.72 KB

README.md

File metadata and controls

59 lines (40 loc) · 1.72 KB

study-buddy

A personalized AI-powered study tool that helps you learn from PDF documents through goal-based learning, assessments, and interactive practice.

Features

  • PDF Processing: Upload and process PDF documents with text and image extraction
  • Goal-Based Learning: Set your study goals and get a personalized study plan
  • Knowledge Assessment: Initial assessment to gauge your current understanding
  • RAG-Powered Chat: Ask questions about your documents with context-aware responses
  • Knowledge Graph: Visual representation of concepts and their relationships
  • Practice Quizzes: Topic-focused quizzes with adaptive difficulty
  • Performance Tracking: Monitor your progress across different topics

Installation

This project requires Python 3.13+. Install dependencies using uv:

uv sync

Usage

Run the Streamlit app:

uv run run_app.py

Then:

  1. Upload a PDF document
  2. Configure your model settings (OpenAI, Anthropic, or Ollama)
  3. Set your study goals
  4. Complete a quick assessment
  5. Start studying with your personalized plan

Configuration

You'll need API keys for the models you want to use:

  • OpenAI: Set OPENAI_API_KEY environment variable
  • Anthropic: Set ANTHROPIC_API_KEY environment variable
  • Ollama: Install and run Ollama locally

How It Works

The app uses:

  • Vector embeddings to store and retrieve document content
  • LLMs for chat, question generation, and assessments
  • Knowledge graphs to map relationships between concepts
  • ChromaDB for persistent vector storage
  • Docling or PyMuPDF for PDF extraction

Project Purpose

This is a learning project built to explore LLM application development and RAG systems.