#rag

Retrieval-augmented generation posts — chunking, embeddings, retrieval quality, and evaluation.

RAG Is Not Just Search: Chunking, Ranking, Reranking, and Hallucination Control

Go beyond naive vector search chunking strategies, hybrid keyword+semantic ranking with RRF, cross-encoder reranking, context assembly, and layered hallucination control, with each change helps.

Cover image for Building a Private RAG System: Architecture, Embeddings, Vector DBs, and Evaluation

1 month ago 213

AI Databases Programming

Building a Private RAG System: Architecture, Embeddings, Vector DBs, and Evaluation

A full architecture walkthrough for a private, self-hosted RAG system ingestion, chunking, embeddings, vector databases and the evaluation loop that makes it trustworthy.

Cover image for A Practical Introduction to LLMs and RAG in Python, and Where to Go Next

1 month ago 117

Python AI

A Practical Introduction to LLMs and RAG in Python, and Where to Go Next

The finale: LLMs explained with the concepts you already own, tokens and prompts, your first Claude API call from Python, a toy RAG engine in the browser, and the full map into the production LLM and MCP series.

Cover image for Building a RAG Service with FastAPI: Chunking, Embeddings, and Vector Search

1 month ago 74

AI & LLM

Building a RAG Service with FastAPI: Chunking, Embeddings, and Vector Search

Build a RAG service end to end: chunk documents, embed and search by similarity, and answer grounded in retrieved context from a FastAPI endpoint.

Cover image for Building a Production RAG System with pgvector and Laravel

2 months ago 979

Laravel AI Engineering

Building a Production RAG System with pgvector and Laravel

Ship a real RAG pipeline in Laravel using PostgreSQL pgvector. Smart chunking, batched embeddings, HNSW indexes, reranking, and citation-backed answers.