How do I set up environment and install llamaindex?

# Step 1: Environment Setup 1. Ensure Python 3.9+ is installed. 2. Create a virtual environment: ```bash python -m venv llama-env source llama-env/bin/activate # Mac/Linux # or llama-env\Scripts\activate on Windows ``` 3. Install LlamaIndex starter package: ```bash pip install llama-index ``` For modular: `pip install llama-index-core` then integrations like `pip install llama-index-llms-openai`. 4. Set OpenAI API key (get from https://platform.openai.com/api-keys): ```bash export OPENAI_API_KEY='your-key-here' ``` 5. Verify: `pip list | grep llama` should show `llama-index`.

How do I build your first vector index and query?

# Step 2: Basic RAG Pipeline 1. Create `data` folder and download sample: ```bash mkdir data wget https://raw.githubusercontent.com/run-llama/llama_index/main/docs/examples/data/paul_graham/paul_graham_essay.txt -O data/paul_graham_essay.txt ``` 2. Create `basic_rag.py`: ```python from llama_index.core import VectorStoreIndex, SimpleDirectoryReader documents = SimpleDirectoryReader("data").load_data() index = VectorStoreIndex.from_documents(documents) query_engine = index.as_query_engine() response = query_engine.query("What did the author do in college?") print(response) ``` 3. Run: `python basic_rag.py`. Expect answer about Paul Graham's activities.

How do I explore core concepts: indexes and engines?

# Step 3: Master Key Components Read official docs: - [Framework Overview](https://developers.llamaindex.ai/python/framework) Key concepts: - **Data Connectors**: Load from PDFs, APIs (e.g., SimpleDirectoryReader). - **Indexes**: VectorStoreIndex organizes embeddings. - **Query Engines**: `index.as_query_engine()` for NL queries. Experiment: ```python # Persist index index.storage_context.persist() # Reload from llama_index.core import load_index_from_storage, StorageContext storage = StorageContext.from_defaults(persist_dir=".") index = load_index_from_storage(storage) ``` Study [Modules](https://developers.llamaindex.ai/python/framework) sections.

How do I build a simple agent with custom tools?

# Step 4: Agent with Tools From starter tutorial, create `agent.py`: ```python async def multiply(a: float, b: float) -> float: return a * b from llama_index.core.agent.workflow import FunctionAgent from llama_index.llms.openai import OpenAI import asyncio agent = FunctionAgent(tools=[multiply], llm=OpenAI(model="gpt-4o-mini"), system_prompt="Multiply numbers.") response = await agent.run("1234 * 4567?") print(response) asyncio.run(response) ``` Run with `python agent.py`. Agent calls tool automatically.

How do I enhance agent with rag and run local llms?

# Step 5: Full RAG Agent + Local Setup Combine: Add RAG tool to agent from Step 4. ```python # After building index/query_engine async def search_docs(query: str) -> str: return str(await query_engine.aquery(query)) agent.tools += [search_docs] ``` Query: "What did author do in college? 7*8?" **Local LLMs** (no API costs): 1. Install Ollama: https://ollama.com 2. `ollama pull llama3.1` 3. `pip install llama-index-llms-ollama llama-index-embeddings-huggingface` 4. Use `Ollama(model='llama3.1')` instead of OpenAI.

Master LlamaIndex: Build RAG Agents in 5 Steps

🧰

Instant Toolkit

2 artifacts

📋
Step-by-Step Guide

1

Step 1: Environment Setup

Ensure Python 3.9+ is installed.

Create a virtual environment:

python -m venv llama-env
source llama-env/bin/activate  # Mac/Linux
# or llama-env\Scripts\activate on Windows

Install LlamaIndex starter package:
```
pip install llama-index
```
For modular: pip install llama-index-core then integrations like pip install llama-index-llms-openai.
Set OpenAI API key (get from https://platform.openai.com/api-keys):
```
export OPENAI_API_KEY='your-key-here'
```
Verify: pip list | grep llama should show llama-index.

Why this step matters:

-Builds a reproducible dev setup for experimentation
-Allows immediate hands-on coding without compatibility issues

30-60 minutes

Python 3.9+, pip, Virtualenv, OpenAI Platform (free tier)

$0

Definition of Done

•llama-index installed successfully
•Environment variable OPENAI_API_KEY set and verifiable

Common Mistakes to Avoid

❌ Installing deprecated 'llama-index' full package without core

→Use 'pip install llama-index-core' for latest v0.14+ modular installs

❌ Forgetting to activate virtual environment

→Always run 'source llama-env/bin/activate' before pip commands

2

Following along, or just reading? 👀

Spin up a personalized “learn LlamaIndex” plan you can save, check off, and return to anytime — unlimited on the free trial.

Start free trial →

3

4

5

🎥
Suggested Videos

Introduction to LlamaIndex with Python (2025)

LlamaIndex Tutorial in Less Than 15 Mins

LlamaIndex Crash Course - AI Agents in Python

📚
Learning Resources

📖 Online Courses

Building Agentic Workflows with LlamaIndex

intermediate

Paid

DataCamp

📖 Recommended Books

Building Data-Driven Applications with LlamaIndex

intermediate

by Andrei Gheorghiu

🌐 Helpful Websites

LlamaIndex Official Documentation

documentation

Full guides, starters, API reference

LlamaIndex GitHub Repository

repository

Source code, examples, issues

LlamaHub

integrations

200+ data loaders and integrations

🛠️ Useful Tools

Ollama

LLM Runner

Run local LLMs for LlamaIndex

create-llama

CLI Tool

CLI to scaffold LlamaIndex projects

Master LlamaIndex: Build RAG Agents in 5 Steps