Find tools › Open-source projects › Chat with your files

PageIndex

Open-source project · by VectifyAI

Lets AI find answers in long documents by reading them like a table of contents, with page references.

For developersPopular213,099 installs a month

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • Ask questions about a long financial report
  • Find exact sections in contracts with page references
  • Build a document Q&A tool that shows its sources

How to start

  1. Install Python and get an API key, such as from OpenAI.

  2. In a terminal, run pip install -U pageindex.

  3. Follow the README examples to index a PDF and ask questions about it.

Good to know. Requires external API keys (such as OpenAI) to build indexes and run queries.

Before you install

  • Found automaticallyNot reviewed by a person yet. Check it before installing.
  • License: MITYou are allowed to use it under these terms.
  • Last updated 2026-11-18

More detail

A vectorless, reasoning-based RAG engine that uses hierarchical tree indexes and LLM reasoning for traceable document retrieval without vector databases or chunking.

Traditional vector similarity search often retrieves irrelevant context or misses facts in long, complex professional documents. Reach for PageIndex when you need precise, explainable retrieval over legal, financial, or technical PDFs.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-09-29. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map