nilesh2797/BlockRank
BlockRank makes LLMs efficient and scalable for RAG and in-context ranking
BlockRank helps information retrieval specialists and AI engineers efficiently rank documents using large language models. It takes in a query and a set of documents, then quickly identifies the most relevant documents, outputting a ranked list. This is ideal for anyone building search engines, recommendation systems, or advanced question-answering applications where quick, accurate document retrieval is critical.
Use this if you need to rapidly and accurately rank a large number of documents or passages in response to a query using an LLM, especially in applications like RAG or search.
Not ideal if your primary need is to generate long-form text or engage in conversational AI, as this tool focuses specifically on the ranking task rather than content creation.
Stars
41
Forks
1
Language
Python
License
MIT
Category
Last pushed
Dec 12, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/nilesh2797/BlockRank"
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,...