LlamaIndex: Build Production RAG Applications in 50 Lines of Python

pip install llama-index llama-index-llms-openai llama-index-embeddings-openai

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.llms.openai import OpenAI
from llama_index.core import Settings

# Configure models
Settings.llm = OpenAI(model="gpt-4o-mini", temperature=0.1)
Settings.embed_model = "local"  # uses sentence-transformers locally

# Load documents from a directory
documents = SimpleDirectoryReader("./docs/").load_data()

# Build index (chunks, embeds, stores in-memory)
index = VectorStoreIndex.from_documents(documents)

# Query
query_engine = index.as_query_engine()
response = query_engine.query("What is PagedAttention?")
print(response)

from llama_index.readers.web import SimpleWebPageReader
from llama_index.readers.github import GithubRepositoryReader
from llama_index.readers.notion import NotionPageReader

web_docs = SimpleWebPageReader().load_data(["https://docs.vllm.ai/"])
github_docs = GithubRepositoryReader(owner="vllm-project", repo="vllm").load_data()

from llama_index.core.node_parser import SentenceSplitter, SemanticSplitterNodeParser

# Fixed-size with overlap
parser = SentenceSplitter(chunk_size=512, chunk_overlap=64)

# Semantic chunking (groups semantically similar sentences)
semantic_parser = SemanticSplitterNodeParser(embed_model=Settings.embed_model)
nodes = semantic_parser.get_nodes_from_documents(documents)

from llama_index.core import get_response_synthesizer

# compact: default, fits context into fewest LLM calls
# refine: iterative, updates answer as it reads each chunk
# tree_summarize: builds summary tree bottom-up

synthesizer = get_response_synthesizer(response_mode="tree_summarize")
query_engine = index.as_query_engine(response_synthesizer=synthesizer)

from llama_index.core.query_engine import SubQuestionQueryEngine
from llama_index.core.tools import QueryEngineTool

tools = [
    QueryEngineTool.from_defaults(query_engine=vllm_index.as_query_engine(), name="vllm_docs", description="vLLM documentation"),
    QueryEngineTool.from_defaults(query_engine=ollama_index.as_query_engine(), name="ollama_docs", description="Ollama documentation"),
]

engine = SubQuestionQueryEngine.from_defaults(query_engine_tools=tools)
response = engine.query("Compare vLLM and Ollama for production serving")

query_engine = index.as_query_engine(streaming=True)
streaming_response = query_engine.query("Explain HNSW indexing")

for text_chunk in streaming_response.response_gen:
    print(text_chunk, end="", flush=True)

from llama_index.core.vector_stores import MetadataFilter, MetadataFilters

filters = MetadataFilters(filters=[MetadataFilter(key="source", value="technical-docs")])
query_engine = index.as_query_engine(filters=filters)