PageIndex
by VectifyAI
PageIndex is a Python library that builds a tree-shaped index of long documents, such as PDFs, and lets an AI model reason through that tree to find answers. It is meant for asking accurate questions of long, complex documents without a vector database or chunking.
- Stars
- 39.8k +38 a day
- Licence
- MIT
- Runs on
- Your computer
- Setup
- Moderate
- Language
- Python
- Age
- 574 days
What you can do with it
- Index a long PDF such as a financial report and ask questions about it in plain English
- Search across several documents and get answers traceable to specific sections
- Add document retrieval tools to your own AI agent built with the OpenAI or Claude agent SDKs
Make money with it
A freelancer could set up document question-answering tools for clients, such as law, finance or engineering firms, and charge for setup and support.
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 questions from long contracts, policies or technical manuals, cutting time spent searching
- Offer clients a document question-answering service for reports, filings or compliance documents
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 it with pip (pip install -U pageindex), set an LLM API key, then use the Python client to submit documents and ask questions.
Follow the official instructions in the project README.
Things to check
- Needs a paid LLM API key (or a Claude subscription) to index and answer questions
- Answer quality and query cost depend on the chat model chosen
- Some features are offered through a paid cloud service
Checked 27 Oct 2026. Summary drafted by AI from the project's README.
