Writing
The Blog
Engineering notes, build logs, and thoughts on creative development.
Building AI-Native Apps: Vector Search in Laravel 13 & PostgreSQL
This guide explores how Laravel 13 has revolutionized search by introducing native vector similarity methods. We cover everything from the basic whereVectorSimilarTo syntax to the advanced orchestration of embeddings using the new Laravel AI SDK, providing a clear path for architects to build intelligent, semantic search engines.
Late Chunking: Solving Context Loss in Laravel RAG Pipelines
Stop shredding your data. Learn to implement late chunking vector search in Laravel 13 to preserve semantic context and eliminate hallucinations in RAG pipelines.
The AI Feedback Loop: Engineering Reverse ETL to Sync RAG Insights back to Laravel
Learn to engineer a robust feedback loop by using Reverse ETL for AI to sync agentic conclusions from Python RAG workers back into your Laravel application via Kafka.
The Local Embedding Edge: Replacing OpenAI with Self-Hosted SLMs in Laravel RAG Pipelines
Transition from OpenAI to self-hosted embedding models in Laravel 13. This guide covers Ollama integration, pgvector dimension management, and high-throughput Python sidecars.
The Semantic Firewall: Hardening Laravel 13 Agents Against Prompt Injection
Build a resilient Laravel 13 agent by implementing a Semantic Firewall with Llama Guard to filter untrusted vector data and prevent indirect prompt injection attacks.
The Freshness Problem: Real-Time Vector Sync with Debezium and Kafka
Move RAG synchronization to the infrastructure level. Learn how Change Data Capture for Vector Search using Debezium and Kafka solves the dual-write problem and Update Storms.
Hard Isolation for Vectors: A Hands-On pgvector Laravel 13 Setup Guide
Secure your multi-tenant RAG systems by implementing PostgreSQL Row Level Security with pgvector and Laravel 13. Learn to enforce hard isolation at the database level.
Beyond Semantic Similarity: Implementing GraphRAG with pgvector and Laravel
Learn how to implement GraphRAG in Laravel using pgvector and Recursive CTEs. Move beyond flat similarity search by extracting entity triples for multi-hop AI reasoning.
Graduating Your RAG Ingestion: When Laravel Queues Hit the Ceiling and Airflow Takes Over
Moving RAG ingestion from Laravel Horizon to Apache Airflow ensures resilience for complex vector pipelines. Learn to build a 'Signal-and-Poll' pattern for robust AI data orchestration.
The Silent Search Killer: Using dbt Tests to Guard Your Vector Ingestion Pipeline
Stop silent search degradation by implementing dbt macros to validate vector dimensions, L2 norms, and semantic drift across your ingestion pipelines.