I do not treat the choice of embedding model as an interchangeable environment variable. In Qdrant, it becomes part of every collection. Using different vector spaces locally and in production creates an expensive future migration.
Phase 3 introduces real data isolation. Each user gets a separate Qdrant collection, an individual S3 path and three new endpoints for GDPR rights.
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.
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.
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.
Describe your workflow. Together, we will identify the right next step.
Discuss your workflow