Migrating From OpenAI to Self-Hosted Llama Models

Retrieval quality is the lever that moves the most weight. No amount of prompt engineering compensates for a retriever that consistently surfaces the wrong passages. We spent two weeks tuning chunking and reranking before touching the prompt template.

Trade-offs

Tool definitions should read like API documentation written for a careful junior engineer. The model behaves better when each parameter has a concrete example, a unit, and an explicit statement of what happens when the value is omitted.

Documentation written by the team that builds the system tends to be more useful than documentation written by anyone else. The trade-off is consistency, which we address with a shared style guide and a lightweight review process.

Results

Evaluation suites grow faster than the codebase they cover. We treat them as first-class artefacts: versioned, reviewed, and regenerated on a schedule. The team that owns the model owns the eval set, not a separate QA group.

Hardware is a moving target. The Jetson Orin we benchmarked in January was outperformed by an off-the-shelf mini-PC by August. We re-run the benchmark matrix every quarter and have stopped making long-term hardware commitments.

Cost modelling is now part of our pre-merge checklist. Every PR that touches an LLM call includes an estimate of the per-request token spend and the expected daily volume. Surprises in the monthly invoice have dropped to nearly zero.