Medium

Mohamed Arbi Nsibi

Pinned

Mohamed Arbi Nsibi

·

Aug 3, 2025

How I Built an Agentic RAG System with Qdrant to Chat with Any PDF

Or: How I Built an AI Assistant That Can Read PDFs and Answer Questions Like a Human Would

How I Built an Agentic RAG System with Qdrant to Chat with Any PDF

Mohamed Arbi Nsibi

·

Oct 31

Qdrant 1.20: BM25 Without Sparse Vectors, Turbo16 & Turbo8

BM25 straight from your payload, a tokenizer that finally understands camelCase, nested filters 7x faster, and two new TurboQuant…

Qdrant 1.20: BM25 Without Sparse Vectors, Turbo16 & Turbo8

Mohamed Arbi Nsibi

·

Sep 4

Qdrant 1.19: Turbo4 Datatype & Memory Tiers

One config line, nine times less disk, and a single knob for all your RAM decisions. Here’s what’s actually new and when you should care.

Qdrant 1.19: Turbo4 Datatype & Memory Tiers

Mohamed Arbi Nsibi

·

Aug 1

Real-Time Qdrant Search

Kafka Just Moves Bytes: Qdrant as the Whole Search Stack

Real-Time Qdrant Search

Mohamed Arbi Nsibi

·

Jul 31

Semantic Resource Vault

Your Bookmarks Deserve a Search Engine: Qdrant in a Chrome Popup

Semantic Resource Vault

Mohamed Arbi Nsibi

·

Jul 2

16× smaller vectors in Qdrant: memory, recall, and latency results.

Vector search is memory-hungry. A million OpenAI embeddings is ~6 GB of RAM just for the raw floats and RAM is the expensive part of any…

16× smaller vectors in Qdrant: memory, recall, and latency results.

Mohamed Arbi Nsibi

·

Jun 7

TurboQuant: The Compression Shannon Would Approve

Millions of vectors, a fraction of the memory, and almost zero accuracy lost, here’s the math behind it.

TurboQuant: The Compression Shannon Would Approve

Mohamed Arbi Nsibi

·

Jun 3

Qdrant 1.18: Faster, Smarter, and Easier Vector Search

1. A More Flexible Future for Vector Databases

Qdrant 1.18: Faster, Smarter, and Easier Vector Search

Mohamed Arbi Nsibi

·

Apr 20

Models Decay. Systems Don’t Have To

Notes on MLOps, LLMOps, and what survives.

Models Decay. Systems Don’t Have To

Mohamed Arbi Nsibi

·

Apr 5

A Foundational Guide to Neural Search and Relevance Feedback

Have you ever searched a medical database for ‘lung cancer treatments’ only to get 500 blog posts about ‘clean eating’ because they both…

A Foundational Guide to Neural Search and Relevance Feedback

Mohamed Arbi Nsibi

Mohamed Arbi Nsibi

ML engineer & MTS @ Stealth, graduated from SUP’COM and a top rank on Zindi. I’m passionate about MLOps and Generative AI.

Following

Help

Status

About

Careers

Press

Blog

Store

Privacy

Rules

Terms

Text to speech