Artificial intelligence: development, training and integration · ENGLISH
Service page for projects serving Curitiba. Configure local models and access for workflows that do not send every input to an external API. For Curitiba, longer pages can organise requirements, deliverables and decisions by stage.
01 · CONTEXT
For Curitiba, longer pages can organise requirements, deliverables and decisions by stage.
02 · PRACTICAL BRIEF
Models, integration and evaluation
Define the task, representative examples, permitted data, evaluation goal and runtime environment. Leave sensitive data out of the initial brief. Before finalising the brief for Curitiba, confirm with the people involved: For Curitiba, longer pages can organise requirements, deliverables and decisions by stage.
A local Ollama setup covering the selected model, context and available resources.
Check the downloaded model starts and handles the intended cases on that machine.
03 · METHOD
Models, integration and evaluation
04 · ANSWERS
Configure local models and access for workflows that do not send every input to an external API. A local Ollama setup covering the selected model, context and available resources.
Prepare the task, representative examples, permitted data, privacy constraints and target environment. Avoid sharing sensitive data in an initial enquiry.
Check the downloaded model starts and handles the intended cases on that machine.