[docs] Add development setup guide and contribution guidelines

.env.example

@@ -0,0 +1,14 @@
+# OpenAI Configuration
+OPENAI_API_KEY=your_openai_api_key_here
+
+# Optional: LLM Model
+LLM_MODEL=gpt-3.5-turbo
+
+# Optional: Logging Level
+LOG_LEVEL=INFO
+
+# Optional: Vector Store Path
+VECTOR_STORE_PATH=./vector_store
+
+# Optional: Embedding Model
+EMBEDDING_MODEL=all-MiniLM-L6-v2

CONTRIBUTING.md

@@ -0,0 +1,48 @@
+\# Contributing to GA4GH-RegBot
+
+
+
+Thank you for your interest in contributing to GA4GH-RegBot!
+
+
+
+\## Getting Started
+
+
+
+1\. \*\*Fork the repository\*\* on GitHub
+
+2\. \*\*Clone your fork\*\* locally
+
+3\. \*\*Create a feature branch\*\* for your changes
+
+4\. \*\*Follow the development workflow\*\* below
+
+5\. \*\*Submit a pull request\*\* with a clear description
+
+
+
+\## Development Workflow
+
+
+
+\### 1. Fork and Clone
+
+
+
+```bash
+
+\# Fork on GitHub, then clone your fork
+
+git clone https://github.com/YOUR-USERNAME/GA4GH-RegBot.git
+
+cd GA4GH-RegBot
+
+
+
+\# Add upstream remote for staying updated
+
+git remote add upstream https://github.com/ga4gh/GA4GH-RegBot.git
+
+
+

README.md

@@ -1,21 +1,40 @@
-GA4GH-RegBot: Compliance Assistant
-Status: Proposal Stage for GSoC 2026
+\# GA4GH-RegBot: Compliance Assistant
 
-Overview
-RegBot is an LLM-powered tool designed to help researchers map their consent forms against GA4GH regulatory frameworks. It uses RAG (Retrieval-Augmented Generation) to flag compliance gaps automatically.
 
-Architecture (Planned)
-Core: Python
 
-LLM Framework: LangChain / LlamaIndex
+\*\*Status:\*\* Proposal Stage for GSoC 2026
 
-Vector Store: ChromaDB / FAISS
 
-UI: Streamlit
 
-Roadmap
-Phase 1: Ingest GA4GH "Framework for Responsible Sharing" policy documents.
+GA4GH-RegBot is an LLM-powered tool designed to help researchers map their consent forms against GA4GH regulatory frameworks. It uses RAG (Retrieval-Augmented Generation) to flag compliance gaps automatically.
+
+
+
+\## Quick Start (5 minutes)
+
+
+
+```bash
+
+git clone https://github.com/ga4gh/GA4GH-RegBot.git
+
+cd GA4GH-RegBot
+
+python -m venv venv
+
+venv\\Scripts\\activate  # Windows
+
+source venv/bin/activate  # Mac/Linux
+
+pip install -r requirements.txt
+
+copy .env.example .env  # Windows
+
+cp .env.example .env  # Mac/Linux
+
+\# Edit .env with your OpenAI API key
+
+python src/main.py
+
 
-Phase 2: Build RAG pipeline for clause extraction.
 
-Phase 3: Develop Streamlit frontend for user uploads.

SETUP.md

@@ -0,0 +1,60 @@
+\# GA4GH-RegBot: Development Setup Guide
+
+
+
+Welcome! This guide will help you set up GA4GH-RegBot for local development and testing.
+
+
+
+\## Prerequisites
+
+
+
+\- \*\*Python 3.8+\*\*
+
+\- \*\*pip\*\* (comes with Python)
+
+\- \*\*Git\*\*
+
+
+
+\## Quick Start (5 minutes)
+
+
+
+```bash
+
+\# 1. Clone the repository
+
+git clone https://github.com/ga4gh/GA4GH-RegBot.git
+
+cd GA4GH-RegBot
+
+
+
+\# 2. Create a virtual environment
+
+python -m venv venv
+
+venv\\Scripts\\activate  # Windows
+
+
+
+\# 3. Install dependencies
+
+pip install -r requirements.txt
+
+
+
+\# 4. Set up environment
+
+copy .env.example .env
+
+
+
+\# 5. Verify
+
+python -c "import langchain; import chromadb; print('OK')"
+
+
+

requirements.txt

@@ -1,9 +1,29 @@
+# LangChain: LLM orchestration and RAG framework
 langchain==0.1.0
+
+# LangChain community integrations
 langchain-community==0.0.10
+
+# ChromaDB: Vector database for semantic search
 chromadb==0.4.22
+
+# OpenAI: LLM provider
 openai==1.7.0
+
+# Streamlit: Web UI framework (for Phase 3)
 streamlit==1.30.0
-pypdf==3.17.4
+
+# Python-dotenv: Environment variable management
 python-dotenv==1.0.0
+
+# Tiktoken: Token counting for LLM
 tiktoken==0.5.2
+
+# Sentence-Transformers: Embedding models
 sentence-transformers==2.2.2
+
+# PyPDF: PDF document processing
+PyPDF==3.17.1
+
+# Pydantic: Data validation
+pydantic==2.5.0