Discover the latest insights, guides, and updates on AI orchestration, real-time systems, and modern event-driven communication with DNotifier.

Part seven of the DNotifier × Ollama series — no vendor retirement schedule, manual ollama pull cycles, and quarterly freshness checks.

Tool calling and structured output on Ollama work, but reliability depends on the model. How to test local models before trusting them in production workflows.

Part five of the DNotifier × Ollama series — air-gapped and data-boundary cases, cloud capability ceiling, and mixed local/cloud workflows per step.

How much VRAM Ollama models need, what quantization trades away in quality, when CPU-only inference works, and when self-hosting stops being worth it.

Part three of the DNotifier × Ollama series — parameter count, GGUF quantization, task-first selection, and Prompt Testing Studio on local models.

Ollama runs LLMs on your own hardware: no per-token bill, no rate limits, data stays local. What you gain and what you give up versus cloud providers.

Part one of the DNotifier × Ollama series — configure a reachable base URL, pull models with ollama, and call local inference through provider ollama and sendAI().

Part ten of the DNotifier × Azure AI series — Foundry complexity, API retirements, deployment blast radius, and the seven-provider orchestration throughline.

When to use API keys vs Microsoft Entra ID for Azure OpenAI: RBAC, managed identities, key rotation, and choosing auth by team size.