Tag feed

#vector-database

604 posts26 followers

Explore Hashnode

Alternatives

Trending tags this week

AWAndrew Wiggeyirexta.hashnode.dev1d ago · 5 min read

Scale Enterprise RAG: Vector DBs & Hybrid Search on Bare Metal

Building a prototype RAG (Retrieval-Augmented Generation) application with a few PDF files and a serverless Vector Database is easy. However, when an enterprise attempts to scale this architecture to

0

Mmamonumamonu.hashnode.dev3d ago · 9 min read

Using a mac mini (2012) for LLM inference with KoboldCpp

I have an old by now 2012 Intel Mac Mini. Its one of these amazing machines that still work really well if you dont try to put any 2020-era software on it. So I have been making it a music server to a

0

AAlanbosun-pkm.hashnode.dev2d ago · 2 min read

Reconstructing Bosun PKM with evidence

This retrospective covers recovery work from August 29, 2026. It was prepared after the event; its metadata and RSS entry record the actual first-publication time rather than the event date. Bosun PKM

0

VCViv Chaudharytruenorthbits.hashnode.dev3d ago · 9 min read

Build a Solid RAG System in One Weekend (2026 Edition)

The four deliberate decisions that separate a working RAG demo from a reliable RAG system are chunking, retrieval, reranking, and evaluation. Tutorials that stop at "load PDFs → fixed-size chunks → em

1

A

AKAman Karkiamankarki.hashnode.dev6d ago · 5 min read

Two From-Scratch Systems, and the Day They Talked

I've spent the last stretch building two things, each one deliberately without leaning on someone else's runtime to do the actual work: Lattice — a vector database, HNSW index and all, built from the

0

NMNahid Mahmudnahid-mahmud555.hashnode.dev6d ago · 2 min read

Why Public AI Benchmarks Lie (And How to Actually Evaluate Models)

We’ve all seen the flashy headlines: "Model X beats the leaderboard on MTEB!" But if you deploy that model blindly into production, you're likely setting yourself up for failure. Public benchmarks are

0

SSSameer Selokarblogbysameer.hashnode.devSep 4 · 15 min read

AI Memory: How Can an AI Agent Remember You?

Have you ever told an AI assistant something important, only to discover that it has forgotten it in your next conversation? For example: You: My name is Sameer. I’m building an AI memory system call

1

A

SSSameer Selokarblogbysameer.hashnode.devSep 4 · 16 min read

Beyond Vector Databases: Understanding Vectorless RAG, PageIndex, and Wiki-Based AI Memory

Retrieval-Augmented Generation (RAG) has become one of the most common architectures for building AI systems that can answer questions using external knowledge. The basic idea is simple: Give an LLM

1

A

Aanckursinghaikoql.hashnode.devSep 3 · 16 min read

Why Not Just Use a Vector Database? The Case for Knowledge Infrastructure Beyond RAG

Vector databases have changed how AI applications work with information. They made semantic search practical. They made it possible to retrieve information based on meaning rather than exact keywords.

0

PJPraise Jamesactiandev.hashnode.devSep 2 · 12 min read

How to self-host mem0 with a local vector store

If you've used mem0 and discovered it calls OpenAI by default, the fix is three configuration values. mem0's Memory() class is cloud-by-default. It calls OpenAI for fact extraction, calls OpenAI again

0

#vector-database

Search Hashnode

#vector-database

Explore Hashnode

Trending tags this week

Scale Enterprise RAG: Vector DBs & Hybrid Search on Bare Metal

Using a mac mini (2012) for LLM inference with KoboldCpp

Reconstructing Bosun PKM with evidence

Build a Solid RAG System in One Weekend (2026 Edition)

Two From-Scratch Systems, and the Day They Talked

Why Public AI Benchmarks Lie (And How to Actually Evaluate Models)

AI Memory: How Can an AI Agent Remember You?

Beyond Vector Databases: Understanding Vectorless RAG, PageIndex, and Wiki-Based AI Memory

Why Not Just Use a Vector Database? The Case for Knowledge Infrastructure Beyond RAG

How to self-host mem0 with a local vector store