Rag | martinuke0's Blog

A terminal showing BM25 retrieval scores alongside a RAG pipeline diagram

Build a RAG Pipeline with From-Scratch BM25: A Hands-On Portfolio Project

A hands-on guide to building a Retrieval-Augmented Generation pipeline with a from-scratch BM25 scorer. Covers architecture, real Python code, testing, and a senior-level roadmap for extending it into a production-grade system.

Abstract illustration of a neural network with retrieval arrows

Building a Speculative RAG Decoder with Retrieval-Token Speculation

This tutorial shows how to combine retrieval‑augmented generation with speculative decoding to cut latency while preserving factual grounding. You’ll build a runnable system that demonstrates real‑world performance gains.

A diagram of a RAG pipeline with BM25 and transformer

A BM25 Sparse Retriever + Tiny Transformer Generator RAG Pipeline in Pure Python

This guide walks you through implementing a BM25 sparse retriever and a tiny decoder‑only transformer generator from scratch in pure Python, producing a functional RAG pipeline you can showcase on your CV.

Building a Pure-Python IVF-PQ Vector Index with On-Disk Storage for RAG Pipelines

This guide walks through implementing an IVF‑PQ index in pure Python, storing data on disk and integrating it into a RAG pipeline for sub‑second similarity search.

A sleek Python code editor with a RAG pipeline diagram.

Build a Pure‑Python Hybrid RAG Engine with BM25, HNSW, and Cross‑Encoder Reranking

Learn to stitch together BM25, HNSW, and a miniature GPT‑2 model in pure Python for a standout RAG project.