AI
Use the OpenAI API in Laravel
Adding AI to a Laravel app comes down to a few lines: install the client, store your key, and call the chat endpoint. Here is how to set it up cleanly, stream responses, and keep your key and your bill under control.
Track AI bots visiting your website
AI crawlers like GPTBot, ClaudeBot and PerplexityBot scrape sites to train models and answer questions. Here is how to spot them in your logs, log them to their own file, and decide what to allow.
Fix the OpenAI API rate limit (429) error
A 429 from the OpenAI API means you have sent requests faster than your account is allowed, or run out of quota. Here is what the error actually means and how to fix it with backoff, batching, and the right limits.
Self-host an LLM on your own server
Running a large language model on your own server keeps your data private and turns an unpredictable per-token bill into a fixed monthly cost. Here is how to size the machine, install a model, serve it over HTTP, and lock it down for production.
Run DeepSeek locally
DeepSeek's open-weight reasoning models run on your own hardware, no API key required. Here is how to pull and run DeepSeek-R1 with Ollama, pick a size that fits your machine, and query it over HTTP.
Run a local LLM with Ollama
Ollama is the quickest way to download and run an open large language model on your own machine, no API keys and no per-token bill. Here is how to install it, pull a model, and talk to it from the command line and over HTTP.