PageIndex and pageindex
These appear to be **competitors** — both implement hierarchical document indexing using LLM reasoning as an alternative to vector embeddings for RAG, with the starred VectifyAI version being the more established implementation.
About PageIndex
VectifyAI/PageIndex
📑 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.
About pageindex
Ashish4144/pageindex
Build hierarchical document indexes using LLM reasoning for intuitive navigation and retrieval without chunking, embeddings, or vector databases.
Scores updated daily from GitHub, PyPI, and npm data. How scores work