Blog
AI and Backend Integration
I write about wiring LLMs into real backends: OpenAI API streaming, caching, rate limits and timeouts, RAG pipelines with pgvector, and vector database choices. Useful for Node.js and Laravel developers shipping AI features to production.
Claude API 400 Error: temperature, top_p, top_k
Claude API 2026-10-21 returns a 400 if you send temperature, top_p or top_k. See what breaks and how to fix it.
Exponential Backoff for OpenAI API Calls
How to implement exponential backoff with jitter for OpenAI API calls in Node.js, and why queue concurrency matters more than your retry formula.
OpenAI Function Calling in a Laravel App
How to wire OpenAI function calling into a Laravel backend so an LLM can trigger real actions, plus the validation and loop-depth safeguards you actually need.
pgvector vs Pinecone for Node.js Embeddings
pgvector vs Pinecone for Node.js apps: when Postgres vector search beats a dedicated vector database, with real code and a clear recommendation.
Fixing OpenAI API Timeouts in Laravel Jobs
OpenAI API calls timing out inside your Laravel queue? Here's why jobs fail mid-request and how to set timeouts that actually agree with each other.
Stream OpenAI API Responses in Node.js with SSE
Learn how to stream OpenAI API responses in Node.js using Server-Sent Events, with real Express code and the mistakes that break streaming in production.
Fix OpenAI API Rate Limit Errors in Node.js
Get 429 rate_limit_exceeded errors from the OpenAI API in Node.js? Here is the real fix: exponential backoff, retry-after handling, and concurrency limits.
Node.js RAG Pipeline: pgvector + OpenAI
Build a Node.js RAG pipeline with pgvector and OpenAI embeddings for grounded, source-backed AI answers without running a separate vector database.