Skip to content

Blog

Writing

Engineering, AI experiments, and software craft.

Posts tagged "pgvector"

Essays, field notes, and engineering write-ups by Al Amin Ahamed covering pgvector — 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 pgvector work.

Filtered by pgvector ✕ clear
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 22, 2026
· 0 min read

How I Cut Edit Distance from 168 to 43 in a Legal Document RAG Pipeline

Three architectural changes that brought average edit distance from 168 to 43 in a legal document RAG pipeline — section-scoped chunking, section-scoped exemplar prompting, and switching from a general embedding model to a legal-domain one — with a CI eval suite that made the improvement trajectory visible and reproducible.

May 22, 2026
· 0 min read

Building a 12-Source Job Discovery Pipeline with RAG and pgvector

How JobPulse aggregates job listings across 12 sources in three tiers, embeds your resume into pgvector, and generates grounded cover letters via Claude — including the async adapter protocol, composite scoring model, and the three retrieval failure modes that shaped the final architecture.

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 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.