ecnusse/Hydrangea
Defect Library for LLM-enabled Software
This project helps software developers understand and mitigate common flaws in applications that use large language models (LLMs) and vector databases. It provides a structured library of known defects, detailing their types, locations in code, consequences, and how to trigger them. Developers can use this resource to identify, reproduce, and prevent similar issues in their own LLM-powered software.
Use this if you are developing software that integrates large language models and want to learn from real-world examples of how these systems can fail.
Not ideal if you are a non-technical user looking for a tool to evaluate LLM performance or directly debug your AI applications without programming knowledge.
Stars
23
Forks
3
Language
Python
License
—
Category
Last pushed
Dec 31, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/ecnusse/Hydrangea"
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,...