Graphs & Pipelines
Compose, diagnose, tune, and deploy Neat graphs and pipelines. Use these tutorials in order.
Compose a `Graph` by hand — input node, output node, no model — and run one frame through it. See the pipeline primitives in...
Drop a model into a `Graph` with `model.graph()` and `model.graph(options)` — two composition patterns that differ in how muc...
Build the smallest useful public Neat `Graph` — one *named* `Input` wired to a *named* `Output` — then push a sample through...
Drop a compiled model into a public `Graph` with `graph.add(model)`, so you get graph-level orchestration (routing, schedulin...
Run multiple logical streams through one public `Graph` and combine two named inputs into one deterministic bundle output — t...
Triage a pipeline with three checks — `graph.validate()`, one measured `run.run()`, and `MeasureReport` diagnostics — to answ...
Tune the async pipeline knobs that control behavior under load — queue depth and overflow policy — then measure what actually...
Assemble a production-style run loop from the patterns earlier chapters taught — explicit model options, explicit route optio...