Ziglang eXtensiable Builder for SQL or JSON, zig version, sql or json query builder, extensible custom for any database, for any orm framework

Atlas - Enterprise document indexing plugin for OpenClaw. Vectorless RAG using PageIndex with async indexing, incremental updates, and smart caching. Scales from 10 to 5000+ documents. Perfect for financial reports, legal docs, technical manuals, and research papers.

Block Storage based on Hadoop Distributed File System (HDFS)

Modular RAG library for Python. Swap any component — LLM, vectorstore, reranker — with one line in a YAML file. No code changes. Just config.

AI-first manual checklist builder using PageIndex-style vectorless retrieval + local Gemma4 to generate grounded maintenance checklists with strict citations.

Vectorless RAG using reasoning over hierarchical document structure instead of embeddings or vector databases.

Hybrid GraphRAG system over Tolkien's Middle-earth lore. Combines Neo4j knowledge graph + ChromaDB vector search for retrieval, with Gemini for grounded, cited answers. Built from 76 Wikipedia pages with LLM-based entity extraction.

测评：超长文档，agent记忆与自研框架的对比

Implements a vectorless RAG architecture using PageIndex APIs and Groq LLMs, enabling efficient document retrieval and response generation without traditional vector databases.

问道 wendao - high-performance knowledge and link-graph engine, AI RAG.

🔍 Empower efficient retrieval with PageIndex, a reasoning-based system that eliminates the need for vector databases and chunking for human-like results.

A modern Document Q&A application comparing PageIndex (reasoning tree-based RAG) with Traditional Vector RAG for intelligent document querying and analysis.

An enterprise-grade, hybrid Retrieval-Augmented Generation (RAG) pipeline that completely bypasses traditional vector databases.

PageIndex RAG: Reasoning-based retrieval architecture replacing vector databases with hierarchical navigation

Local-first vectorless RAG using PageIndex. Supports Ollama (fully local) + AWS Bedrock. No vector DB, no embeddings. Built on top of VectifyAI/PageIndex (MIT).

PostgreSQL extension for PageIndex: PDF/Markdown document trees, tree search, JSONB API (pageindex schema). C + Go c-shared bridge; PGXS; MIT licensed.

Serverless Vectorless RAG on AWS — upload documents, ask questions, get grounded answers using LLM reasoning instead of embeddings or vector databases. Built with Amazon Bedrock (Claude 3 Haiku), Lambda, DynamoDB, API Gateway, React, and Terraform.

Production-ready reasoning-based Document Q&A system using Streamlit and PageIndex API

A comprehensive benchmarking project designed to evaluate and compare three different Retrieval-Augmented Generation (RAG) architectures using clinical medical transcription data.

Vectorless RAG via hierarchical tree indexing — Go reimplementation of PageIndex with zero external deps