Introduction to ScholaRAG

Learn how ScholaRAG transforms the traditional literature review process from weeks of manual work into hours of AI-powered efficiency.

What is ScholaRAG?

ScholaRAG is an open-source, conversational AI-guided system that helps researchers build custom RAG (Retrieval-Augmented Generation) systems for academic literature review. Built on top of VS Code and Claude Code, it guides you through every step of creating a systematic review pipeline.

The Problem It Solves

Traditional Literature Review (6-8 weeks)

If you've ever conducted a systematic review, you know the pain:

1. Database Search: Spend days crafting queries for PubMed, ERIC, Web of Science
2. Export & Screen: Download 500+ papers, export to Excel, read abstracts one by one
3. Full-Text Review: Manually review 200+ PDFs for inclusion criteria
4. Data Extraction: Copy-paste findings, methods, and statistics into spreadsheets
5. Citation Hell: Constantly re-read papers to verify citations and quotes

The result? 67-75% of your time spent on mechanical tasks instead of analysis.

With ScholaRAG (2-3 weeks)

1. 30-minute Setup: Build your RAG system with step-by-step Claude Code guidance
2. 2-hour Screening: PRISMA pipeline screens thousands of papers automatically
3. Instant Queries: Ask questions and get answers with specific paper citations
4. Never Forget: Your RAG system remembers every relevant detail across all papers

What You'll Build

In approximately 30 minutes of active setup (plus 3-4 hours of automated processing), you'll create:

Database Strategy

ScholaRAG supports comprehensive multi-database coverage with both free open-access sources and institutional databases for broader reach:

Open Access Databases (Free, No Setup Required)

Institutional Databases (Optional, Requires Access)

You'll set up access to these databases in Step 6 of Getting Started, and learn to query them effectively in Stage 2 of the workflow.

Core Concepts

1. AI-Powered PRISMA Screening

PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) is the gold standard for systematic reviews. ScholaRAG implements PRISMA 2020 with AI-enhanced multi-dimensional evaluation:

• Identification: Comprehensive database search with complete retrieval (no limits)
• Screening: AI-powered multi-dimensional evaluation using large language models
• Eligibility: Confidence-based routing (auto-include/exclude/human-review)
• Inclusion: Validated final set with optional human agreement metrics (Cohen's Kappa)

2. RAG (Retrieval-Augmented Generation)

RAG combines two powerful capabilities:

1. Retrieval: Semantic search finds the most relevant papers and sections
2. Generation: LLM synthesizes answers grounded in retrieved content

This architecture prevents hallucinations by ensuring every statement is backed by actual research. Learn more about RAG in our Implementation Guide.

3. 7-Stage Workflow

ScholaRAG breaks down the complex process into 7 conversational stages with Claude Code:

Who Should Use ScholaRAG?

Prerequisites

Before starting, ensure you have:

• VS Code with Claude Code extension installed
• Python 3.9+ on your system
• Anthropic API key (free tier available)
• 30 minutes for initial setup + 3-4 hours for automated processing
• Basic familiarity with your research domain

Next Steps

Ready to start building? Head to Chapter 2: Getting Started to set up your environment and run your first ScholaRAG workflow.

# Clone the repository
git clone https://github.com/HosungYou/ScholaRAG.git
cd ScholaRAG

# Install dependencies
pip install -r requirements.txt

# Open in VS Code with Claude Code
code .

Further Reading: PRISMA Guidelines · Contextual Retrieval (Anthropic) · Templates & Examples