▣ Chapter 1: Entering the Rama Index
1.1 Tasks supported by RamaIndex
1.2 Setting up the RamaIndex usage environment
__1.2.1 Installing Python on Windows
__1.2.2 Creating a virtual environment
__1.2.3 Installing Visual Studio Code
__1.2.4 Issuing an OpenAI API Key
__1.2.5 Issuing a Gemini API Key
__1.2.6 Adding API Keys to Environment Variables
1.3 Preview of Rama Index
__1.3.1 Preparing Data
__1.3.2 Installing RamaIndex in a Virtual Environment
__1.3.3 Running RamaIndex

▣ Chapter 2: RamaIndex Pipeline
2.1 Setting up the development environment
2.2 Data loading
__2.2.1 Data Reader
__2.2.2 Data Connector
2.3 Text Segmentation
__2.3.1 Documents and Nodes
__2.3.2 Token Unit Splitting
__2.3.3 Sentence unit division
__2.3.4 Semantic Unit Division
__2.3.5 Text Segmentation Comparison
2.4 Indexing
__2.4.1 What is indexing?
__2.4.2 Vector storage index
__2.4.3 Top-K Search
2.5 Save
2.6 Query
__2.6.1 Query Engine (QueryEngine)
__2.6.2 Retrieval
__2.6.3 Postprocessing
__2.6.4 Response synthesis
__2.6.5 Customizing

▣ Chapter 3: Vector Store
3.1 Setting up the development environment
3.2 Chroma
__3.2.1 Creating a Chroma Client
__3.2.2 Creating a Collection
__3.2.3 Adding vector data
__3.2.4 Vector Search
__3.2.5 Metadata Filtering
__3.2.6 Adding embedding data
__3.2.7 Searching Embedding Data
__3.2.8 How chroma is stored
__3.2.9 Embedding-based RamaIndex Answer Generation
__3.2.10 Generating answers based on RamaIndex
3.3 Pinecone
__3.3.1 Pinecon API Initialization
__3.3.2 Adding vector data
__3.3.3 Vector Search
__3.3.4 Metadata Filtering
__3.3.5 Embedding-based RamaIndex Answer Generation
__3.3.6 Generating answers based on RamaIndex (omitting embedding)
3.4 Quadrant
__3.4.1 Generating answers based on RamaIndex
__3.4.2 Setting up a local environment using Docker
__3.4.3 Cloud-based environment setup

▣ Chapter 4: RAG Practice Using Text Documents
4.1 Setting up the development environment
4.2 Preparing data for practice
4.3 Handling PDF Files
__4.3.1 Data Preparation
__4.3.2 Text Segmentation
__4.3.3 Indexing
__4.3.4 Executing a query
4.4 Handling Text Files
__4.4.1 Basic RAG Practice
__4.4.2 Index Storage: Using Chroma
4.5 Handling CSV Files
4.6 Handling HWP files
__4.6.1 Using HWPReader
__4.6.2 Using SimpleDirectoryReader

▣ Chapter 5: Multimodal RAG Practice
5.1 Setting up the development environment
5.2 Preparing the Data
5.3 Multimodal Vector Indexing with the OpenAI API
5.4 Building a Multimodal RAG Using Quadrants
__5.4.1 Quadrant Installation and Client Setup
__5.4.2 Creating a Text and Image Vector Store
__5.4.3 Creating a multimodal vector index
__5.4.4 Search
5.5 Building a Question-Answering-Based RAG System
__5.5.1 Executing basic queries
__5.5.2 Executing queries using improved prompts
5.6 Building an Image-Based RAG System
__5.6.1 Downloading and saving new images
__5.6.2 Performing an image search
__5.6.3 Analysis of images with similar painting styles

▣ Chapter 6: Agent RAG
6.1 Setting up the development environment
6.2 Data Preparation
6.3 Hugging Face Embedding
6.4 Creating an Agent

▣ Chapter 7: Advanced RAG
7.1 Setting up the development environment
7.2 ReRanking
__7.2.1 LLM-based reranking
7.3 Cost Issues of LLM-Based Reranking
__7.3.1 Reranking based on cross-encoder
7.4 Hyde
__7.4.1 Data Preparation
__7.4.2 Setting up a large language model and embeddings
__7.4.3 Implementing Hide

▣ Chapter 8: Function Calling Agent
8.1 Setting up the development environment
8.2 Understanding How Function Calling Works
8.3 Function calling using external APIs
__8.3.1 Creating a stock market information call agent
__8.3.2 Preparing the function calling tool
__8.3.3 Creating an agent and running a query
8.4 RAG Agent Implemented with Function Calling
__8.4.1 Environment settings and data preparation
__8.4.2 Preparing the function calling tool
__8.4.3 Creating an agent and executing a query

▣ Chapter 9: Implementing a Counselor Agent with Text-to-SQL
9.1 Setting up the development environment
9.2 Setting up the environment for agent development
9.3 Designing a Hospital Database
9.4 Implementing a Text-to-SQL Agent
9.5 Multi-turn conversation processing technique
9.6 User Interface Using Gradio

▣ Chapter 10: MCP (Model Context Protocol)
10.1 What is MCP?
10.2 Building a Model Context Protocol Development Environment
10.3 MCP Server
__10.3.1 Registering a tool using an adapter
__10.3.2 MCP Inspector
__10.3.3 Message Format
__10.3.4 Document Search Agent MCP Practice
10.4 MCP Client
10.5 Weather Agent Practice
__10.5.1 Obtaining an OpenWeatherMap API Key
__10.5.2 Extracting city names
__10.5.3 OpenWeatherMap API Integration
__10.5.4 Registering MCP Tools and Running the Server
__10.5.5 Implementing an MCP Client: Asking the Weather
__10.5.6 Summary

★ What this book covers ★

◎ Rama Index Pipeline
◎ Vector Store
◎ RAG practice using text documents
◎ Multimodal RAG Practice
◎ Agent RAG and Advanced RAG
◎ Function Calling Agent
◎ Consultant agent implemented using Text-to-SQL
◎ MCP Agent