# Non-vector-based AI document search engine

PageIndex is a document indexing tool that works with reasoning capabilities without the need for vector-based search methods. Instead of traditional vector databases, it optimizes RAG (Retrieval-Augmented Generation) processes by using text-based logical inference.

- ★ 39,643
- Python
- GitHub Trending · 2026-09-29

## Updates

- **October 25, 2026:** Stars 39,586 → 39,643, latest release v0.4.7 (October 24, 2026).
- **October 24, 2026:** Stars 39,527 → 39,586, latest release v0.4.6 (October 23, 2026).
- **October 23, 2026:** Stars 39,271 → 39,527, latest release v0.4.5 (October 22, 2026).
- **October 19, 2026:** Stars 39,253 → 39,271, latest release v0.4.4 (October 19, 2026).

## What you get

- eliminates the need for vector-based search and chunking
- indexes documents with a hierarchical tree structure
- searches using AI reasoning capabilities

## Installation

**Package Installation**

```
pip install -U pageindex
```

## If you don't write code

Paste this into your AI agent (Claude Code · Codex · Antigravity)

I want to index a document in local mode using the PageIndex Python library and search the document using an AI model. After completing the installation, can you run the sample Python code that allows me to define my OpenAI API key, upload the document to the system, and ask questions?

Repository: https://github.com/VectifyAI/PageIndex. Follow the official instructions in the README of this repository for setup and execution.

Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.

Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.

If an API key is required, do not ask me to type it into the chat. Show me how to add it to the .env file and ensure this file is not pushed to Git.

Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.

## Related dictionary terms

- [RAG](https://trescout.com/en/dictionary/rag/)
- [API](https://trescout.com/en/dictionary/api/)
- [Artificial Intelligence](https://trescout.com/en/dictionary/artificial-intelligence/)

- **Who it is for:** It is intended for those who want to set up a search infrastructure capable of logical inference on long and complex documents without using chunking or vector-based databases.
- **License:** MIT

## Links

- [GitHub repository →](https://github.com/VectifyAI/PageIndex)
- [Read in Turkish →](https://trescout.com/discover/pageindex/)

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-09-29: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was **machine-translated** from the Turkish original · the Turkish version prevails.

---
Source: TreScout Discover · https://trescout.com/en/discover/pageindex/