Skip to content

Blog

Writing

Engineering, AI experiments, and software craft.

Posts tagged "RAG"

Essays, field notes, and engineering write-ups by Al Amin Ahamed covering RAG — practical patterns, gotchas from production code, and lessons learned shipping real systems. Topics include architecture decisions, performance tuning, debugging stories, and integration notes you can apply directly to your own RAG work.

Filtered by RAG ✕ clear
May 31, 2026
· 0 min read

Anthropic Academy — Six Certifications Completed

I completed six Anthropic Academy courses covering the Claude API, Model Context Protocol, subagents, agentic workflows, Claude Code, and AI fluency — each with a verified certificate from Anthropic Education.

May 25, 2026
· 0 min read

RAG Without a Framework: A Minimal pgvector Pipeline with Claude

How to build a complete RAG pipeline in Python without LangChain or LlamaIndex — chunking, embedding with text-embedding-3-large, pgvector retrieval, and grounded generation with Claude — with the tradeoffs that matter at production scale.

May 14, 2026
· 0 min read

Stop Using Fixed-Size Chunks for Technical Documentation

Why naive fixed-size chunking breaks on code-heavy documentation, and the heading-aware approach with paragraph fallback and overlap that replaced it in this portfolio's RAG pipeline.

May 14, 2026
· 0 min read

Voyage AI vs OpenAI Embeddings for Technical RAG in PHP

Why I switched from OpenAI text-embedding-3-small to Voyage AI voyage-code-3 for this portfolio's RAG layer — model comparison, the input_type asymmetry Voyage requires, measured retrieval improvement, and the migration path that keeps search live throughout.

Apr 25, 2026
· 9 min read

RAG on SQLite: Pure-PHP Cosine Similarity Without pgvector

How I built RAG retrieval against a SQLite database using pure-PHP cosine similarity — when it scales, when it doesn't, and the migration path to pgvector.

Apr 15, 2025
· 8 min read

Building a RAG Pipeline in Laravel with pgvector

How I built the AI chat on this site: chunking documents, generating embeddings with Voyage AI, storing them in pgvector, and answering questions with Claude.

Jan 15, 2024
· 9 min read

Semantic Search with pgvector and Laravel Scout

Add meaning-based search to your Laravel app using a custom Scout driver, pgvector HNSW index, and Voyage AI embeddings — with a hybrid keyword fallback.