A Vectorless LLM-Native Document Index Method
MCP server for PageIndex. PageIndex is a vectorless reasoning-based RAG system which uses multi-step reasoning and tree search to retrieve information like a human expert would. The word "index" originally came from how humans retrieve info: book indexes and tables of contents that guide us to the right place in documents.
오픈소스
반응 (1)
비슷한 프로덕트
설명이 비슷한 순
PageIndex
github.comVectorless RAG
FastIndex
github.coman open-source search engine indexation tool
CS
github.comindexless code search that understands code, comments and strings
FastGraphRAG
github.comBetter RAG using good old PageRank
Stop using static chunk sizes. A lightweight, production-ready RAG ingestion toolkit. Uses Docling for layout-aware parsing and applies smart heuristics for optimal chunking (PDF vs Code vs MD). Extracted from a production RAG platform