🚀 LangChain RAG Embeddings Study

A comprehensive study repository for exploring LangChain, RAG (Retrieval-Augmented Generation), embeddings, and semantic vector search techniques with practical implementations.

📋 Overview

This repository contains hands-on experiments and production-ready implementations of modern AI techniques, focusing on:

• 🔗 LangChain Framework: Building sophisticated LLM applications
• 🔍 RAG (Retrieval-Augmented Generation): Enhancing LLM responses with relevant context
• 🧠 Vector Embeddings: Converting text into semantic representations
• 🔎 Semantic Search: Finding relevant documents using meaning, not just keywords
• 📄 Document Processing: PDF parsing, chunking, and vectorization strategies

🎯 What You'll Learn

01 - Introduction to Embeddings

• PDF Processing: Extract and process text from PDF documents
• Vector Embeddings: Convert text chunks into semantic vectors using OpenAI
• Similarity Search: Find relevant content using semantic similarity
• Interactive Chat: Build a conversational interface with context-aware responses

02 - Real-World FAQ System

• Structured Data: Work with JSON-based FAQ datasets
• Multi-Category Search: Handle different types of questions (product, service, technical)
• Production-Ready Chatbot: Implement a robust FAQ answering system
• Context Retrieval: Smart document retrieval for accurate responses

🛠️ Technologies Used

• TypeScript - Type-safe JavaScript development
• LangChain - Framework for building LLM applications
• OpenAI GPT-4 - Advanced language model for text generation
• OpenAI Embeddings - Text-to-vector conversion
• PostgreSQL - Vector database for storing embeddings
• Drizzle ORM - Type-safe database operations
• PDF-Parse - PDF document processing

🚀 Quick Start

Prerequisites

• Node.js 18+
• PostgreSQL database
• OpenAI API key

Installation

1. Clone the repository

git clone https://github.com/Natanaelvich/langchain-rag-embeddings-study.git
cd langchain-rag-embeddings-study

2. Install dependencies

npm install

3. Set up environment variables

cp .env.example .env
# Edit .env with your OpenAI API key and database credentials

4. Run the examples

PDF Processing & Chat:

npm run dev src/01-introduction/gpt-embeddings-pdf.ts

FAQ Chatbot:

npm run dev src/02-real-world-faq/chat-faq.ts

📁 Project Structure

src/
├── 01-introduction/          # Basic embeddings and PDF processing
│   ├── gpt-embeddings-pdf.ts # Interactive chat with PDF content
│   ├── load-embeddings-pdf.ts # PDF loading and vectorization
│   └── search-embeddings-pdf.ts # Vector search implementation
├── 02-real-world-faq/        # Production FAQ system
│   ├── chat-faq.ts          # Interactive FAQ chatbot
│   ├── load-faq-data.ts     # FAQ data loading and processing
│   └── search-faq.ts        # FAQ-specific search logic
└── schema.ts                # Database schema definitions

tmp/
├── agents-data/             # Sample data for agents
├── faq-data/               # FAQ datasets (product, service, technical)
└── pdf/                    # PDF documents for processing

🔧 Available Scripts

• npm run dev - Start development server with hot reload
• npm run build - Build TypeScript to JavaScript
• npm run start - Run built application
• npm run test - Run test suite
• npm run lint - Check code quality
• npm run format - Format code with Prettier
• npm run studio - Open Drizzle Studio for database management

🎓 Learning Path

Beginner Level

1. Start with 01-introduction/ to understand basic concepts
2. Learn about embeddings and vector search
3. Build your first RAG application

Intermediate Level

1. Explore 02-real-world-faq/ for production patterns
2. Understand structured data processing
3. Implement multi-category search

Advanced Level

1. Customize the implementations for your use case
2. Add new data sources and processing pipelines
3. Optimize performance and accuracy

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🔗 Related Resources

• LangChain Documentation
• OpenAI API Documentation
• RAG Best Practices
• Vector Database Guide

---

⭐ Star this repository if you found it helpful for your AI/ML journey!