Tag feed

#information-retrival

24 posts2 followers

Explore Hashnode

Alternatives

Trending tags this week

CChidinmachidinma.devOct 2 · 21 min read

The Index Is a Bet You Made at Write Time

Search feels instantaneous. We type a few words and hit enter. Millions of documents collapse into a neat list of results in less than a second. It gives the illusion of a system that heard your reque

0

PNPrithwish Nathprithwish-nath.hashnode.devSep 29 · 16 min read

Stop Relying on AI. Learn The Algorithm First.

A search feature is the easiest thing to screw up because it’s so plug-and-play these days, you barely even think about it. You’ll probably pick a BM25 library (used by Elasticsearch, Lucene, and othe

0

PBPranshu Bansalpranshubansal.hashnode.devAug 31 · 15 min read

I Combined Dense and Sparse Vectors to Search Medical Research

Code: GitHub Repository When I started this project, I thought the question was simple: if someone searches biomedical research with a full sentence, surely semantic search should be enough. Then I lo

0

AAbhijatexpensivetobewrong.hashnode.devAug 31 · 12 min read

The Query Expansion That Made Retrieval Worse

Here is a technique that will make your retrieval worse while looking, to everyone on the team, like it should have made it better. Take the user's query. Before you embed it, append a handful of syno

0

AAbhijatexpensivetobewrong.hashnode.devAug 29 · 12 min read

We Doubled Retrieval Recall Without Touching the Model

The most expensive retrieval bug I have shipped was not in the retriever. It was in the parser that fed it, and it was invisible to every metric I had. Here is the result, stated plainly and stripped

0

DJDheer Jaindevlog-dheer.hashnode.devApr 5 · 4 min read

Why You Can’t Find That Song? How I Built a System That Can

Often time you remember the feeling, maybe even the scene but not the song. And every platform fails you. Happens with me all the time. So I built Mnemosyne : a system that doesn’t just search music b

0

SSSai Sandeep Kantareddytokenbytoken.hashnode.devMar 2 · 6 min read

Building a Search System That Actually Understands User Intent

Why Traditional Search Falls Short and How Multi-Embedding Architecture Changes Everything The Problem: Traditional Search is Fundamentally Broken As a Senior Applied Machine Learning Engineer, I've b

0

AAArjun Adhikariblogs.thearjun.comFeb 27 · 4 min read

When Vector RAG Goes Blind: The $14B Note 12 Miss in Apple’s 2023 10‑K

In the AI world of 2026, we have been sold a specific dream: Shred your PDF, turn the chunks into numbers (vectors), and let math find the answer. This is Vector RAG, and for simple FAQ bots, it works

0

VVaishnavigovidivenivici.comDec 18, 2025 · 3 min read

How Search Engines Think: Understanding the Term–Document Index Matrix

We have more data than understanding We live in a data-rich situation.Documents, webpages, PDFs, emails, and logs are created every second. But much of this data is never analysed at all. This creates a gap: Data is generated quickly Understanding ...

0

SMSurya Maddulasuryamaddula.comSep 23, 2024 · 26 min read

Not RAG, but RAG Fusion? Understanding Next-Gen Info Retrieval.

Not RAG, but RAG Fusion? Understanding Next-Gen Info Retrieval. AI and Natural Language Processing are advancing at an incredible pace, and now more than ever, we need better and more RELIABLE ways to find and use information. As we've all experienc...

0

#information-retrival

Search Hashnode

#information-retrival

Explore Hashnode

Trending tags this week

The Index Is a Bet You Made at Write Time

Stop Relying on AI. Learn The Algorithm First.

I Combined Dense and Sparse Vectors to Search Medical Research

The Query Expansion That Made Retrieval Worse

We Doubled Retrieval Recall Without Touching the Model

Why You Can’t Find That Song? How I Built a System That Can

Building a Search System That Actually Understands User Intent

When Vector RAG Goes Blind: The $14B Note 12 Miss in Apple’s 2023 10‑K

How Search Engines Think: Understanding the Term–Document Index Matrix

Not RAG, but RAG Fusion? Understanding Next-Gen Info Retrieval.