Swapping OpenAI for a Fake Embedder With One Environment VariableThere is a standard story about design patterns. You learn them from a catalogue, you memorize the diagrams, and later, in an interview, someone asks you to explain the Factory Method and you draw box1d ago · 9 min readyusufoztoprak.hashnode.dev
Counting OpenAI Tokens per Request in FastAPI — Without Touching My Use CasesI'm rebuilding evorag, a Python retrieval service: it chunks documents, embeds them with OpenAI's text-embedding-3-small, stores vectors in PostgreSQL + pgvector, and returns the most relevant chunks Oct 17 · 7 min readyusufoztoprak.hashnode.dev
Building a RAG Service from Scratch with NestJS + pgvectorLarge language models are powerful, but they don't know what they don't know. Ask one about your company's internal docs or a niche research paper, and it will confidently make something up. RetrievalJul 6 · 4 min readyusufoztoprak.hashnode.dev
