ljubobratovicrelja/tensor-truth
Local-first RAG application for technical documentation and research papers
This tool helps scientists, engineers, and researchers get accurate answers from their complex technical documentation and research papers. It takes in various technical documents like PDFs, arXiv papers, or API documentation, and lets you ask questions, providing precise answers even with smaller AI models. Anyone who needs to extract reliable information from large volumes of technical text for their work would find this useful.
Use this if you need highly accurate answers from technical documents like research papers, API docs, or textbooks using smaller, locally run AI models.
Not ideal if you need a multi-user application or are working with general, non-technical text documents where high-fidelity retrieval isn't the primary concern.
Stars
22
Forks
2
Language
Python
License
MIT
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/ljubobratovicrelja/tensor-truth"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
LearningCircuit/local-deep-research
Local Deep Research achieves ~95% on SimpleQA benchmark (tested with GPT-4.1-mini). Supports...
NVIDIA-AI-Blueprints/rag
This NVIDIA RAG blueprint serves as a reference solution for a foundational Retrieval Augmented...
Denis2054/RAG-Driven-Generative-AI
This repository provides programs to build Retrieval Augmented Generation (RAG) code for...
hienhayho/rag-colls
Collection of recent advanced RAG techniques.
jeremiahbohr/literature-mapper
Transform academic PDFs into a Knowledge Graph with typed claims, temporal analysis,...