VectifyAI/PageIndex
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
Ranks #134 of 2,794 repositories GStars tracks this week (top 5%).
5 releases in the last 90 days, the latest today, with 16 contributors on GitHub.
Peaked at #2 in the weekly ranking the week of Jan 18, its best in the past year.
Use Cases & Benefits
- Implements a reasoning-based retrieval-augmented generation system that indexes documents as hierarchical tree structures for precise, relevance-driven information retrieval without vectors.
- Eliminates reliance on vector similarity by simulating human expert reasoning and navigation through document structure, improving retrieval accuracy on complex, long documents.
- Use for extracting relevant insights from lengthy financial reports and regulatory filings requiring multi-step reasoning and domain expertise.
- Use for building AI agents that perform transparent, reasoning-based document search and question answering without chunking or approximate vector search.
- Use for integrating advanced OCR with semantic hierarchy preservation to process complex PDFs and maintain document context for large language model workflows.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
MIT
Permissive: commercial use, modification and redistribution are allowed with attribution.
Community files
- README: present
Watch-outs
No watch-outs from GStars' checks.
General guidance from repository metadata, not legal advice. How we score
From the README
Reasoning-based RAG ✧ No Vector DB ✧ No Chunking ✧ Human-like Retrieval
Are you frustrated with vector database retrieval accuracy for long professional documents? Traditional vector-based RAG relies on semantic similarity rather than true relevance. But similarity ≠ relevance — what we truly need in retrieval is relevance, and that requires reasoning. When working with professional documents that demand domain expertise and multi-step reasoning, similarity search often falls short.
Compared to traditional vector-based RAG, PageIndex features:
PageIndex powers a reasoning-based RAG system that achieved 98.7% accuracy on FinanceBench, showing state-of-the-art performance in professional document analysis (see our blog post for details).
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+4,952 stars over 90 days across 37 snapshot days; best day +132 on Jul 28.
Forks
3.4K+406
Open issues
151+8
Compared with peers in AI
Fastest-growing repositories GStars tracks in this cohort for the week of Oct 18, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| storytold/artcraft | 35.6K | +6.7K | 75 | 26 days ago |
| heygen-com/hyperframes | 70.0K | +5.7K | 45 | today |
| Comfy-Org/ComfyUI | 142.0K | +4.4K | 60 | 3 days ago |
| Leonxlnx/taste-skill | 101.1K | +4.0K | 75 | 2 days ago |
| ifixai-ai/iFixAi | 30.7K | +3.3K | 75 | 5 days ago |
| VectifyAI/PageIndex | 39.5K | +0 | 75 | today |
| Category median | 70.0K | +4.4K | 75 | — |
Also by VectifyAI
Other repositories from this maintainer that GStars tracks
Discover Repositories
Search across tracked repositories by name or description