Why I set the chunk size in my RAG system to 1500 tokens
The migration to bge-m3 brought an 8192-token limit. Nevertheless, I deliberately set the chunk limit to 1500 tokens to preserve semantic focus.
Tag: RAG
Why my chunking still failed despite tokenization
I had already implemented text splitting, but the context error kept appearing. Only when I accounted for the token budget and special tokens did the cause become clear.
Notes and tags when saving screenshots in a Shadow DOM overlay
Notes and tags are entered directly in the capture overlay, persisted in Qdrant and included in the embedding. How types, Shadow DOM and a chip input make this work.
Building a RAG system with Qdrant, embeddings and Node.js
Retrieval-Augmented Generation is not theory. It is a concrete three-step architecture: embed, retrieve and generate. I show how I implemented it entirely locally with Qdrant, nomic-embed-text and llama3.2, without cloud costs.
From a screenshot extension to an AI memory engine with RAG, Qdrant and Ollama
A Chrome Extension for Instagram metadata was the starting point. It grew into a complete RAG system built on Qdrant, Ollama and TypeScript that runs locally, is cloud-ready and enables semantic search across captured social media data.
What should your portal do?
Describe your workflow. Together, we will identify the right next step.
Discuss your workflow