📑PageIndex
VectifyAI/PageIndex · homepage ↗
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
⭐ Very popular: 35k stars, gaining about 192 a week
View on GitHub ↗repo profile
momentum
durability
bus factor = how many people it takes to cover more than half the commits (6 months). 1 is a solo project; higher means the work is spread across a team. top-author share is the single busiest author's slice of those commits.
since we covered it
why it's a big deal
- Targets professional document QA where similarity-based retrieval fails, replacing vector chunking with reasoning over a document's structure so results are relevant rather than merely similar.
- Helps teams working with financial reports, legal and regulatory filings, technical manuals, and academic texts, where retrieval must be traceable back to specific pages and sections.
- Reports 99% accuracy on the FinanceBench financial document QA benchmark, and removes the need for a vector database or chunking pipeline.
under the hood
- Written in Python; builds a hierarchical tree index where each node holds a title, summary, page range, and node id, organizing documents into natural sections instead of fixed-size chunks.
- Retrieval is a two-step process: generate the tree index, then run reasoning-based tree search with an agentic LLM that navigates the structure using full context.
- Uses LiteLLM for multi-model support, with optional cloud OCR and tree building, vision-based retrieval over page images, and MCP integration.
Radar summary, generated from the project's public sources
star history
- PR#27 15k 2026-02-11
- now 35k + 21k since first covered
curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.
understory
Better known than its recent output, coasting a little on attention.
- output, commits & releases
- clout, star velocity
output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →
covered in
-
Vectorless, reasoning-based RAG
similar projects
compare these →- 📚 Haystack
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.
26k ACTIVE - 🧠 Mem0
Universal memory layer for AI Agents
63k ACTIVE - 📦 LEANN
leaner, 13k stars
[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
13k ACTIVE
comments
Sign in with GitHub to add your blip on PageIndex.