### 4-1. Quick Start

This is a basic example demonstrating how to load and query local documents within a specific folder using `SimpleDirectoryReader` and `VectorStoreIndex` in the most basic Python environment.

```bash
# Install basic Python packages
pip install llama-index
```

```python
import os
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader

# Set OpenAI API Key (or configure a local LLM as the default LLM)
os.environ["OPENAI_API_KEY"] = "your-openai-api-key"

# Place research papers (PDFs) or experimental text files in the 'data' directory and load them
documents = SimpleDirectoryReader("data").load_data()

# Generate text embeddings and create a vector index
index = VectorStoreIndex.from_documents(documents)

# Create a query engine and ask a question
query_engine = index.as_query_engine()
response = query_engine.query("What are the latest experimental techniques to reduce the off-target effects of CRISPR-Cas9?")
print(response)
```

### 4-2. Detailed Installation

Depending on the development stack you are using, you can selectively install only the core library and necessary integration packages to reduce the overall size.

#### Python Advanced/Lightweight Build
```bash
# Install only the core data framework
pip install llama-index-core

# Explicitly install only the necessary models and components
pip install llama-index-llms-openai
pip install llama-index-embeddings-openai
pip install llama-index-readers-file
```

#### TypeScript / JavaScript Environment Installation
If you are running in a Node.js backend or edge acceleration environment, use the `llamaindex` npm package.
```bash
npm install llamaindex
```