How to Use Ollama Tool Calling and Structured JSON Output
Ollama supports two distinct capabilities that are easy to confuse: tool calling, where a model requests a named function that your app executes, and structured outputs, where…
FROM THE AUTHOR
John C. Mullen
Explore the published guides and contributions from John C. Mullen.
87 published articlesHow to Version Prompts and System Instructions for Reproducible AI Workflows
Versioning prompts and system instructions means treating each prompt as a named, immutable artifact with its own model configuration and release labels. That practice gives you rollback,…
How to Evaluate and Reduce Hallucinations in LLM Workflows
Hallucinations are best handled as two linked tasks: measuring them with a labelled evaluation set, and reducing them with grounded retrieval plus an output guardrail. This guide…
How to Secure a Local AI Endpoint for WordPress with HTTPS and API Keys
A local AI runtime such as Ollama, LM Studio, or llama.cpp usually ships with no authentication and a plain-HTTP listener bound to localhost. WordPress should never talk…
How to Build a RAG-Powered Content Assistant That Avoids Repeating Existing WordPress Posts
A RAG assistant avoids repeating your WordPress posts by indexing every published article into a vector store and querying it before the model writes a word. The…
How to Use Local Embeddings for Private RAG Without Sending Documents to the Cloud
A retrieval-augmented generation pipeline can run entirely on your own machine, including the embedding step that turns documents into vectors. This guide maps the local-only component stack,…
How to Build a Local RAG Pipeline with Ollama and ChromaDB
A local RAG pipeline uses Ollama to serve both the chat model and the embedding model, and ChromaDB to store and search document vectors, so answers are…
How to Rotate and Revoke AI API Credentials in WordPress Without Breaking Workflows
Rotate and revoke AI API credentials in WordPress by mapping every layer, creating a replacement Application Password or token, updating all consumers, verifying access, and then removing…
How to Evaluate Hallucinations in a Local Model with Your Own Test Set
A hallucination evaluation for a local model needs three things: questions whose answers you have verified, a cold run with no tools or retrieval, and a grading…
How to Use Local Embedding Models for RAG Instead of Cloud Embeddings
Local embedding models compute document and query vectors on your own hardware, so text never leaves your machine before retrieval. LlamaIndex supports a fully local stack using…
What Is Attention in a Transformer? A Practical Explanation
Attention is the operation that lets every token in a transformer gather information from the other tokens in its context: it scores each token against the others,…
How to Handle Timeouts and Retries for Local LLM APIs (Ollama, LM Studio)
Local LLM endpoints time out for reasons cloud APIs rarely do: cold model loads, KV cache allocation, prompt evaluation, and queueing behind other requests. This guide explains…