VectifyAI/PageIndex
đź“‘ PageIndex: Document Index for Vectorless, Reasoning-based RAG
Builds a hierarchical tree-index from documents—similar to a machine-generated table of contents—then uses LLM reasoning to traverse the tree for retrieval, eliminating the need for vector databases or artificial chunking. Achieves 98.7% accuracy on FinanceBench by reasoning over document structure rather than semantic similarity. Integrates via self-hosted Python, MCP protocol, or cloud API, with support for vision-based retrieval directly from PDF page images.
21,374 stars. Actively maintained with 21 commits in the last 30 days.
Stars
21,374
Forks
1,665
Language
Python
License
MIT
Category
Last pushed
Mar 04, 2026
Commits (30d)
21
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/VectifyAI/PageIndex"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
thearpankumar/GPUaccelerated-multilingual-RAG
GPU - vector DB - AI-powered document processing platform for financial services. Features...
praj2408/RAG-Enhanced-NCERT-Tutor
RAG-Enhanced-NCERT-Tutor is an AI-powered tutor for NCERT curriculum, using Retrieval-Augmented...
justine-george/ai-markdown-llm-retrieval
AI-powered document query system using LangChain, ChromaDB, and OpenAI for efficient RAG-based...
Vikas-ai56/Contextual_RAG
An Advanced RAG system using Python and Langgraph for intelligent, stateful question-answering...
Ashish4144/pageindex
Build hierarchical document indexes using LLM reasoning for intuitive navigation and retrieval...