Riccorl/golden-retriever
Golden Retriever - A Lightning framework for retriever architecture prototype
This is a tool for machine learning engineers and researchers to build and evaluate custom information retrieval systems. It helps train models to effectively search for and retrieve relevant text passages based on natural language queries. You provide datasets of questions, answers, and text passages, and it outputs a trained retrieval model ready for deployment.
No commits in the last 6 months.
Use this if you need to develop, train, or benchmark a specialized text retriever for your specific domain or dataset.
Not ideal if you are a business user looking for a ready-to-use search solution without any machine learning development.
Stars
11
Forks
—
Language
Python
License
—
Category
Last pushed
Sep 25, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/Riccorl/golden-retriever"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
HKUDS/LightRAG
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
beir-cellar/beir
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across...
HKUDS/RAG-Anything
"RAG-Anything: All-in-One RAG Framework"
superlinear-ai/raglite
🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL
illuin-tech/vidore-benchmark
Vision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.