LlamaIndex - Data Framework for LLM Applications

The leading framework for connecting LLMs with your data.

When to use LlamaIndex

Use LlamaIndex when:

• Building RAG (retrieval-augmented generation) applications
• Need document question-answering over private data
• Ingesting data from multiple sources (300+ connectors)
• Creating knowledge bases for LLMs
• Building chatbots with enterprise data
• Need structured data extraction from documents

Metrics:

• 45,100+ GitHub stars
• 23,000+ repositories use LlamaIndex
• 300+ data connectors (LlamaHub)
• 1,715+ contributors
• v0.14.7 (stable)

Use alternatives instead:

• LangChain: More general-purpose, better for agents
• Haystack: Production search pipelines
• txtai: Lightweight semantic search
• Chroma: Just need vector storage

Quick start

Installation

# Starter package (recommended)
pip install llama-index

# Or minimal core + specific integrations
pip install llama-index-core
pip install llama-index-llms-openai
pip install llama-index-embeddings-openai

5-line RAG example

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader

# Load documents
documents = SimpleDirectoryReader("data").load_data()

# Create index
index = VectorStoreIndex.from_documents(documents)

# Query
query_engine = index.as_query_engine()
response = query_engine.query("What did the author do growing up?")
print(response)

Core concepts

1. Data connectors - Load documents

from llama_index.core import SimpleDirectoryReader, Document
from llama_index.readers.web import SimpleWebPageReader
from llama_index.readers.github import GithubRepositoryReader

# Directory of files
documents = SimpleDirectoryReader("./data").load_data()

# Web pages
reader = SimpleWebPageReader()
documents = reader.load_data(["https://example.com"])

# GitHub repository
reader = GithubRepositoryReader(owner="user", repo="repo")
documents = reader.load_data(branch="main")

# Manual document creation
doc = Document(
    text="This is the document content",
    metadata={"source": "manual", "date": "2025-01-01"}
)

2. Indices - Structure data

from llama_index.core import VectorStoreIndex, ListIndex, TreeIndex

# Vector index (most common - semantic search)
vector_index = VectorStoreIndex.from_documents(documents)

# List index (sequential scan)
list_index = ListIndex.from_documents(documents)

# Tree index (hierarchical summary)
tree_index = TreeIndex.from_documents(documents)

# Save index
index.storage_context.persist(persist_dir="./storage")

# Load index
from llama_index.core import load_index_from_storage, StorageContext
storage_context = StorageContext.from_defaults(persist_dir="./storage")
index = load_index_from_storage(storage_context)

3. Query engines - Ask questions

# Basic query
query_engine = index.as_query_engine()
response = query_engine.query("What is the main topic?")
print(response)

# Streaming response
query_engine = index.as_query_engine(streaming=True)
response = query_engine.query("Explain quantum computing")
for text in response.response_gen:
    print(text, end="", flush=True)

# Custom configuration
query_engine = index.as_query_engine(
    similarity_top_k=3,          # Return top 3 chunks
    response_mode="compact",     # Or "tree_summarize", "simple_summarize"
    verbose=True
)

4. Retrievers - Find relevant chunks

# Vector retriever
retriever = index.as_retriever(similarity_top_k=5)
nodes = retriever.retrieve("machine learning")

# With filtering
retriever = index.as_retriever(
    similarity_top_k=3,
    filters={"metadata.category": "tutorial"}
)

# Custom retriever
from llama_index.core.retrievers import BaseRetriever

class CustomRetriever(BaseRetriever):
    def _retrieve(self, query_bundle):
        # Your custom retrieval logic
        return nodes

Agents with tools

Basic agent

from llama_index.core.agent import FunctionAgent
from llama_index.llms.openai import OpenAI

# Define tools
def multiply(a: int, b: int) -> int:
    """Multiply two numbers."""
    return a * b

def add(a: int, b: int) -> int:
    """Add two numbers."""
    return a + b

# Create agent
llm = OpenAI(model="gpt-4o")
agent = FunctionAgent.from_tools(
    tools=[multiply, add],
    llm=llm,
    verbose=True
)

# Use agent
response = agent.chat("What is 25 * 17 + 142?")
print(response)

RAG agent (document search + tools)

from llama_index.core.tools import QueryEngineTool

# Create index as before
index = VectorStoreIndex.from_documents(documents)

# Wrap query engine as tool
query_tool = QueryEngineTool.from_defaults(
    query_engine=index.as_query_engine(),
    name="python_docs",
    description="Useful for answering questions about Python programming"
)

# Agent with document search + calculator
agent = FunctionAgent.from_tools(
    tools=[query_tool, multiply, add],
    llm=llm
)

# Agent decides when to search docs vs calculate
response = agent.chat("According to the docs, what is Python used for?")

Advanced RAG patterns

Chat engine (conversational)

from llama_index.core.chat_engine import CondensePlusContextChatEngine

# Chat with memory
chat_engine = index.as_chat_engine(
    chat_mode="condense_plus_context",  # Or "context", "react"
    verbose=True
)

# Multi-turn conversation
response1 = chat_engine.chat("What is Python?")
response2 = chat_engine.chat("Can you give examples?")  # Remembers context
response3 = chat_engine.chat("What about web frameworks?")

Metadata filtering

from llama_index.core.vector_stores import MetadataFilters, ExactMatchFilter

# Filter by metadata
filters = MetadataFilters(
    filters=[
        ExactMatchFilter(key="category", value="tutorial"),
        ExactMatchFilter(key="difficulty", value="beginner")
    ]
)

retriever = index.as_retriever(
    similarity_top_k=3,
    filters=filters
)

query_engine = index.as_query_engine(filters=filters)

Structured output

from pydantic import BaseModel
from llama_index.core.output_parsers import PydanticOutputParser

class Summary(BaseModel):
    title: str
    main_points: list[str]
    conclusion: str

# Get structured response
output_parser = PydanticOutputParser(output_cls=Summary)
query_engine = index.as_query_engine(output_parser=output_parser)

response = query_engine.query("Summarize the document")
summary = response  # Pydantic model
print(summary.title, summary.main_points)

Data ingestion patterns

Multiple file types

# Load all supported formats
documents = SimpleDirectoryReader(
    "./data",
    recursive=True,
    required_exts=[".pdf", ".docx", ".txt", ".md"]
).load_data()

Web scraping

from llama_index.readers.web import BeautifulSoupWebReader

reader = BeautifulSoupWebReader()
documents = reader.load_data(urls=[
    "https://docs.python.org/3/tutorial/",
    "https://docs.python.org/3/library/"
])

Database

from llama_index.readers.database import DatabaseReader

reader = DatabaseReader(
    sql_database_uri="postgresql://user:pass@localhost/db"
)
documents = reader.load_data(query="SELECT * FROM articles")

API endpoints

from llama_index.readers.json import JSONReader

reader = JSONReader()
documents = reader.load_data("https://api.example.com/data.json")

Vector store integrations

Chroma (local)

from llama_index.vector_stores.chroma import ChromaVectorStore
import chromadb

# Initialize Chroma
db = chromadb.PersistentClient(path="./chroma_db")
collection = db.get_or_create_collection("my_collection")

# Create vector store
vector_store = ChromaVectorStore(chroma_collection=collection)

# Use in index
from llama_index.core import StorageContext
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(documents, storage_context=storage_context)

Pinecone (cloud)

from llama_index.vector_stores.pinecone import PineconeVectorStore
import pinecone

# Initialize Pinecone
pinecone.init(api_key="your-key", environment="us-west1-gcp")
pinecone_index = pinecone.Index("my-index")

# Create vector store
vector_store = PineconeVectorStore(pinecone_index=pinecone_index)
storage_context = StorageContext.from_defaults(vector_store=vector_store)

index = VectorStoreIndex.from_documents(documents, storage_context=storage_context)

FAISS (fast)

from llama_index.vector_stores.faiss import FaissVectorStore
import faiss

# Create FAISS index
d = 1536  # Dimension of embeddings
faiss_index = faiss.IndexFlatL2(d)

vector_store = FaissVectorStore(faiss_index=faiss_index)
storage_context = StorageContext.from_defaults(vector_store=vector_store)

index = VectorStoreIndex.from_documents(documents, storage_context=storage_context)

Customization

Custom LLM

from llama_index.llms.anthropic import Anthropic
from llama_index.core import Settings

# Set global LLM
Settings.llm = Anthropic(model="claude-sonnet-4-5-20250929")

# Now all queries use Anthropic
query_engine = index.as_query_engine()

Custom embeddings

from llama_index.embeddings.huggingface import HuggingFaceEmbedding

# Use HuggingFace embeddings
Settings.embed_model = HuggingFaceEmbedding(
    model_name="sentence-transformers/all-mpnet-base-v2"
)

index = VectorStoreIndex.from_documents(documents)

Custom prompt templates

from llama_index.core import PromptTemplate

qa_prompt = PromptTemplate(
    "Context: {context_str}\n"
    "Question: {query_str}\n"
    "Answer the question based only on the context. "
    "If the answer is not in the context, say 'I don't know'.\n"
    "Answer: "
)

query_engine = index.as_query_engine(text_qa_template=qa_prompt)

Multi-modal RAG

Image + text

from llama_index.core import SimpleDirectoryReader
from llama_index.multi_modal_llms.openai import OpenAIMultiModal

# Load images and documents
documents = SimpleDirectoryReader(
    "./data",
    required_exts=[".jpg", ".png", ".pdf"]
).load_data()

# Multi-modal index
index = VectorStoreIndex.from_documents(documents)

# Query with multi-modal LLM
multi_modal_llm = OpenAIMultiModal(model="gpt-4o")
query_engine = index.as_query_engine(llm=multi_modal_llm)

response = query_engine.query("What is in the diagram on page 3?")

Evaluation

Response quality

from llama_index.core.evaluation import RelevancyEvaluator, FaithfulnessEvaluator

# Evaluate relevance
relevancy = RelevancyEvaluator()
result = relevancy.evaluate_response(
    query="What is Python?",
    response=response
)
print(f"Relevancy: {result.passing}")

# Evaluate faithfulness (no hallucination)
faithfulness = FaithfulnessEvaluator()
result = faithfulness.evaluate_response(
    query="What is Python?",
    response=response
)
print(f"Faithfulness: {result.passing}")

Best practices

• Use vector indices for most cases - Best performance
• Save indices to disk - Avoid re-indexing
• Chunk documents properly - 512-1024 tokens optimal
• Add metadata - Enables filtering and tracking
• Use streaming - Better UX for long responses
• Enable verbose during dev - See retrieval process
• Evaluate responses - Check relevance and faithfulness
• Use chat engine for conversations - Built-in memory
• Persist storage - Don't lose your index
• Monitor costs - Track embedding and LLM usage

Common patterns

Document Q&A system

```python

Complete RAG pipeline

documents = SimpleDirectoryReader("docs").load_data()

index = VectorStoreIndex.from_documents(documents)

index.storage_context.persist(persist_dir="./storage")

Query

query_engine = index.as_query_engine(

similarity_top_k=3,

response_mode="compact",

verbose=True

)

response = query_engine.query("What is the ma