llama-index
Interface between LLMs and your data
Decision gist · record as of 2026-08-14
Yes. LlamaIndex is actively maintained with low install friction, permissive MIT licensing, and no known vulnerabilities. It is well-suited for developers building LLM applications that need to augment models with private data. Start here if you want a batteries-included RAG framework; use llama-index-core if you prefer to assemble integrations à la carte.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later.
- OpenAI API key or alternative LLM provider needed for actual queries; default uses in-memory storage.
- Low install friction with a pure-Python wheel.
License · maintenance · safety
MIT (permissive) — MIT license permits unrestricted use, modification, and distribution in commercial and private projects with minimal obligations.
last release 2026-06-24 (51 days) · last repo commit 2026-08-14 · 51,641 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 7,378,605 downloads/mo, #1,747 on PyPI
Alternatives
Verify before relying
pip install llama-index
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
documents = SimpleDirectoryReader("YOUR_DATA_DIRECTORY").load_data()
index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_query_engine()
query_engine.query("YOUR_QUESTION")- Performance characteristics and scalability limits for large document collections.
- Specific vector store backends supported beyond basic examples.
- Latency and throughput benchmarks for typical RAG query patterns.
- Whether over 300 integration packages claim is current and verifiable.
What it is and what it does
LlamaIndex is a data framework designed to bridge the gap between large language models and private or custom data sources. It provides data connectors to ingest various formats (APIs, PDFs, SQL databases, etc.), structures that data into indices and graphs, and retrieval interfaces that augment LLM prompts with relevant context. The framework supports both high-level APIs for quick prototyping and lower-level customization for advanced use cases.
The package ships with integrations for llama-index-embeddings-openai and llama-index-llms-openai out of the box, and can be extended with additional integration packages for different LLM providers, embedding models, and vector stores. It handles the full pipeline from document ingestion through indexing to query execution, with built-in support for persistence and reloading from disk.
Use it for
- Build a chatbot that answers questions about your company's internal documentation or knowledge base.
- Create a semantic search system over a large collection of PDFs, research papers, or legal documents.
- Develop an agentic application that retrieves and reasons over structured and unstructured data.
- Index and query data from multiple sources (APIs, databases, files) with a unified interface.
- Prototype a retrieval-augmented generation (RAG) pipeline without managing vector databases directly.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
LlamaIndex is actively maintained with low install friction, permissive MIT licensing, and no known vulnerabilities. It is well-suited for developers building LLM applications that need to augment models with private data. Start here if you want a batteries-included RAG framework; use llama-index-core if you prefer to assemble integrations à la carte.
Install
llama-index on PyPI
Before you install
Low install friction with a pure-Python wheel. Actively maintained with recent releases; last commit 2026-08-14 indicates a mature, well-supported project.
Requires Python 3.10 or later. OpenAI API key or alternative LLM provider needed for actual queries; default uses in-memory storage.
License in practice
MIT license permits unrestricted use, modification, and distribution in commercial and private projects with minimal obligations.
Quickstart
pip install llama-index
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
documents = SimpleDirectoryReader("YOUR_DATA_DIRECTORY").load_data()
index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_query_engine()
query_engine.query("YOUR_QUESTION")Verify before relying
- Performance characteristics and scalability limits for large document collections.
- Specific vector store backends supported beyond basic examples.
- Latency and throughput benchmarks for typical RAG query patterns.
- Whether over 300 integration packages claim is current and verifiable.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release <4.0,>=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 4 packagesllama-index-corellama-index-embeddings-openaillama-index-llms-openainltk |
| Maintenance | Actively maintained 51 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 7,378,605 / month, #1,747 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Topic :: Scientific/Engineering :: Artificial IntelligenceTopic :: Software Development :: Libraries :: Application FrameworksTopic :: Software Development :: Libraries :: Python Modules |
Evidence: llama_index-0.14.23-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “RAG framework for LLMs”
- llama-indexLlamaIndex is a data framework that connects large language models to…
- embedchainEmbedchain is a framework for building retrieval-augmented generation…
- ragasRagas provides objective metrics, test data generation, and…
Give your agent the search over MCP, or paste the wish link into any chat.
More Python Modules packages
Converts domain names between Unicode and ASCII-compatible encoding (Punycode) according to IDNA 2008 and Unicode Technical Standard 46, with security validation and broader script coverage than the standard library.
Install it if you work with internationalized domain names, need to validate domains, or use HTTP clients that depend on it transitively.
Setuptools is a Python build backend and package management tool that handles building, distributing, and installing Python packages, including support for C/C++ extension modules.
PyYAML parses and emits YAML 1.1 data format, enabling serialization and deserialization of configuration files and Python objects to and from human-readable YAML text.
Pydantic validates Python data structures against type hints, coercing and checking input at runtime to ensure it matches a declared schema.
Provides reusable metadata objects for use with PEP-593 `typing.Annotated` to express common constraints like bounds, collection sizes, and predicates on types.
Install it if you use or build libraries that need to express type constraints in a standardized, inspectable way—or if you want to annotate your own types with…
Provides runtime tools to inspect and introspect Python type annotations, enabling programmatic examination of type hints at execution time.
See also llama-index-core · llama-index-legacy · llama-index-workflows · llama-index-readers-llama-parse · llama-index-readers-file · llama-index-indices-managed-llama-cloud · lunr · llama-parse · llama-index-llms-anthropic · llama-index-cli