Tag feed

#reranking

5 posts0 followers

Explore Hashnode

Alternatives

Trending tags this week

VKVamsi Krishnablog.vamsiannamreddy.comJun 7 · 3 min read

Day 19: Why reranking is where retrieval becomes useful

The top result from your retriever is often not the best evidence. It is the nearest vector. Those are not the same thing, and the gap between them is where a lot of RAG quality quietly leaks away. Wh

0

PSPragnesh Shahpragmatic-builder.hashnode.devMay 31 · 8 min read

I Built a RAG System That Actually Works — Hybrid Search, Reranking, and the Decisions That Mattered

Disclaimer: The content presented here represents my own personal views and opinions. I built a RAG pipeline that retrieves the right answer from my personal knowledge base on the first try — with sou

0

SSapotaCorpsapotacorpvn.hashnode.devMay 24 · 7 min read

When recall plateaus: the late-interaction technique most teams skip

A founder we work with had been stuck on the same problem for two months. Their RAG retrieval recall was sitting at 58%. They had tried OpenAI's embedding-3-small, then embedding-3-large, then BGE-M3,

0

DADaniel Anthony Romitelli Jrcraftedbydaniel.hashnode.devMar 10 · 7 min read

Diversification After Scoring: The Step That Stops My Scene Compiler From Picking Five Paraphrases

A few weeks into running my scene compiler at scale, I hit an embarrassing pattern: I’d ask for five candidates, score them, and the “top five” would be… the same idea, phrased five ways. Not bad ideas—often the highest composite scores—but clustered...

0

LCLeo Cavalcanteleocavalcante.devNov 28, 2025 · 10 min read

Levando AI Engineering para o próximo nível com RAG

Se você está começando a se aventurar no mundo de AI Engineering e quer ir além do básico, precisa entender profundamente o que é Retrieval-Augmented Generation (RAG). Essa técnica é, sem dúvida, um divisor de águas para quem quer construir agentes d...

0

DSDhaval Singhdsdev.inAug 31, 2025 · 6 min read

Some notes on Agentic search & Turbopuffer

Search systems are always broken. Mend them with care, and like Kintsugi, they become more beautiful. Recently I’ve been diving deep in improving search & retrieval for Littlebird and here are some notes worth sharing. Turbopuffer Tpuf is an amazing...

0

JZJiangyu Zhengtalkwithcode.hashnode.devMay 22, 2025 · 7 min read

Practical Lessons for Building Reranking Models in Advertising Systems

1 Multi-Stage Architecture of Online Advertising Systems The modern online advertising system typically follow a multi-stage cascade architecture, designed to balance scalability, latency, and relevance. Each stage progressively refines a large pool ...

0

#reranking

Search Hashnode

#reranking

Explore Hashnode

Trending tags this week

Day 19: Why reranking is where retrieval becomes useful

I Built a RAG System That Actually Works — Hybrid Search, Reranking, and the Decisions That Mattered

When recall plateaus: the late-interaction technique most teams skip

Diversification After Scoring: The Step That Stops My Scene Compiler From Picking Five Paraphrases

Levando AI Engineering para o próximo nível com RAG

Some notes on Agentic search & Turbopuffer

Practical Lessons for Building Reranking Models in Advertising Systems