← Browse tools

Data & context

PageIndex

Reasoning-guided traversal of document trees as an alternative retrieval strategy.

Overview

Research summary

PageIndex is a document-retrieval project built around hierarchical tree indexes rather than mandatory vector embeddings and fixed-size chunks. It first constructs a structured representation of a document, then uses language-model reasoning to select relevant sections. The SDK supports local operation with a user's model credentials and access to the separately hosted PageIndex service. This makes it an alternative to similarity-based retrieval for document-analysis workflows. The MIT repository covers the software implementation; model usage and hosted service access are separate dependencies.

Repository summary

Stars
Unavailable
Open issues
Unavailable
Last push
Unavailable
Commits, 90 days
Unavailable
Repository activity
Not scored
Version
Unavailable

Recorded catalogue figures. View repository data and provenance →

Classification

Pricing & services

Paid services available

The provider offers paid products or services. Free options may also be available.

View pricing & services ↗

Commercial offering checked 2026-10-02.

Licence scope

Implementation

Recorded implementation details and interfaces for PageIndex.

Implementation details

Python hierarchical document indexing and retrieval SDK

Languages
Python
Repository type
source

Recorded interfaces and capabilities

Licence scope

Repository

Repository snapshots, release information and recorded maintenance signals.

Repository snapshot

VectifyAI/PageIndex ↗

Stars
Unavailable
Open issues
Unavailable
Last push
Unavailable
Commits, 90 days
Unavailable
Repository activity
Not scored
Archived
Not recorded

Repository activity is a snapshot, not a quality or popularity ranking. It combines recent-push freshness (50%), 90-day commits (30%) and issue pressure (20%).

Maintenance and provenance

Catalogue snapshot
2026-10-06

Documentation

Recorded references and research provenance for this entry.

Recorded sources 5

Research metadata

Research date
2026-10-02
Catalogue snapshot
2026-10-06

Community & social 1 channels

Communities