Metarank – open-source hybrid search with LLMs

Hey, HN! You probably know that the ordering of products on Amazon, posts in FB, and search results in Google is personalized for each visitor, as it directly affects conversion, click rate and engagement. But not everyone can afford to hire an army of PhDs to squeeze every penny out of the ranking, and not everyone agrees on the current (im)balance between privacy and profits. So we built Metarank, an open-source and privacy-focused personalization engine. It can rerank in real-time any type of content, using only the data you allow, and optimize metrics you define. We made a lot of…

Hello HN, I'm Ghita, co-founder of ZeroEntropy (YC W25). We build high accuracy search infrastructure for RAG and AI Agents. We just released two new state-of-the-art rerankers zerank-1, and zerank-1-small. One of them is fully open-source under Apache 2.0. We trained those models using a novel Elo score inspired pipeline which we describe in detail in the blog attached. In a nutshell, here is an outline of the training steps: * Collect soft preferences between pairs of documents using an ensemble of LLMs. * Fit an ELO-style rating system (Bradley-Terry) to turn pairwise comparisons into…

We built Valohai LLM for tracking and comparing LLM evaluation results. Whether your evals live in notebooks and spreadsheets, or you're using an observability tool that wasn't built for comparison, this gives you a purpose-built eval comparison dashboard. Run evals with a Python library (pip install valohai-llm), results stream in, and you can compare up to 6 configurations side by side. Group by any dimension (model, category, difficulty) to see where each model excels. It doesn't do tracing or production observability, for now just eval tracking and comparison. What's cool is that you can…

A new interactive search engine with people as results

I've built an advanced RAG (Retrieval-Augmented Generation) pipeline from scratch to demystify the complex mechanics of modern LLM-powered Question Answering systems. This repository features: -- An implementation of a sub-question query engine from scratch to answer complex user questions. -- Illustrative explanations that unveil the inner workings of the system. -- An analysis of the challenges I faced while working with the system, like prompt engineering and cost estimation. -- Qualitative comparison with similar frameworks like LlamaIndex, offering a broader perspective. Key Takeaway:…

Open source recommendation engine on Spark + Elasticsearch