mithun50/TreeDex
Tree-based, vectorless document RAG framework. Connect any LLM via URL/API key.
This project helps you quickly get answers from large documents like reports, manuals, or research papers. You provide a document (e.g., PDF) and ask a question, and it gives you a direct answer along with the exact page numbers where the information came from. It's designed for professionals, researchers, or anyone needing to extract specific information from long, structured texts without manually sifting through pages.
Available on npm.
Use this if you regularly need to find specific information or answer questions based on the content of lengthy documents, and you want accurate answers with source page references.
Not ideal if your documents lack clear headings or a table of contents, or if you need to query unstructured, short pieces of text.
Stars
29
Forks
3
Language
TypeScript
License
MIT
Category
Last pushed
Mar 22, 2026
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/mithun50/TreeDex"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ItzCrazyKns/Vane
Vane is an AI-powered answering engine.
ConardLi/easy-dataset
A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval
xuwei95/ezdata
基于python和llm大模型开发的数据处理和任务调度系统。...
ModelEngine-Group/DataMate
DataMate is an enterprise-level data processing platform designed for model fine-tuning and RAG...
DS4SD/deepsearch-toolkit
Interact with the Deep Search platform for new knowledge explorations and discoveries