llama_index
by run-llama
LlamaIndex is a Python toolkit for building AI applications that answer questions over your own documents and data, using search-based retrieval and agents. It connects to many data sources, language models and vector databases through over 300 add-on packages.
- Stars
- 52.7k +11 a day
- Licence
- MIT
- Runs on
- Your computer
- Setup
- Technical
- Language
- Python
- Age
- 1455 days
What you can do with it
- Build a chatbot that answers questions from your PDFs, documents or SQL data
- Connect a choice of language models and vector databases through ready-made integrations
- Create AI agents and multi-step workflows that retrieve and process documents
Make money with it
A freelance developer could build and sell custom document question-and-answer assistants to small businesses.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Build an internal assistant that answers staff or customer questions from your own manuals, contracts and policies
- Automate extracting information from invoices and documents to cut manual data entry
Can you use it commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Getting it running
Install with pip, using either the starter package "llama-index" or "llama-index-core" plus the integration packages you need.
Follow the official instructions in the project README.
Things to check
- The company's main focus has moved to its paid LlamaParse platform, so the open framework may get less attention
- Usually needs paid API keys for a language model provider such as OpenAI
- README says it is not updated as often as the documentation
- Requires Python coding skills
Who's talking about it
- Rost (rosgluk): Trending Open Source AI Projects on GitHub, October 2026 Featured in a roundup
- Rost Glukhov: Trending Open Source AI Projects on GitHub, October 2026 Featured in a roundup
Checked 27 Oct 2026. Summary drafted by AI from the project's README.