LlamaIndex

LlamaIndex (formerly GPT Index) is the most widely-used data framework for building LLM-powered applications over your own data. It provides over 150 data loaders, composable RAG pipelines, and agent tool integrations so you can connect any data source — PDFs, databases, APIs, Notion, Slack, and more — to any LLM.

Key features

• 150+ data loaders — ingest PDFs, DOCX, HTML, CSV, Notion, Google Drive, Slack, GitHub, and more
• Composable RAG pipelines — chunking, embedding, indexing, retrieval, and synthesis as modular components
• Agent tools — wrap indices as tools for ReAct, OpenAI function-calling, or custom agents
• Multiple index types — vector, keyword, list, tree, and knowledge graph indices
• Streaming and async — first-class async support for production workloads
• 300+ integrations — LLMs, embedding models, vector stores, and observability tools

Quick start

npx ai-supply add llama-index-data-framework

# Or install directly
pip install llama-index

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader

# Load docs and build an index
docs = SimpleDirectoryReader("./data").load_data()
index = VectorStoreIndex.from_documents(docs)

# Query it
query_engine = index.as_query_engine()
response = query_engine.query("What is the main theme of these documents?")
print(response)

Curated mirror of the open-source LlamaIndex project (MIT). Install upstream from the repository.