Configure Semantic Routing
Step-by-step guidance for platform administrators on how to turn the semantic router and its guard checks on or off, set routing rules for a workspace's policy and for a client, set a client's Complexity threshold, and record routing decisions on a PaletteAI Inference Launchpad appliance.
Routing Behavior
An explanation of how PaletteAI Inference Launchpad decides which model answers each request: the Tier map, the semantic router, where routing rules live, and how the semantic router shares the GPUs.
Semantic Router Guard
An explanation of the guard that the semantic router applies to each routed request on a PaletteAI Inference Launchpad appliance: its two checks, which requests each check applies to, and what happens when a check refuses one.
Semantic Routing Reference
Reference of the Semantic router card, the guard toggles, the reasons the semantic router is unavailable, the routing rules, the Complexity threshold, and the decision recording controls on a PaletteAI Inference Launchpad appliance.
Set the Thinking Directive for a Tier
Step-by-step guidance for platform administrators on how to set the Thinking directive for a tier on the Tier Map of a PaletteAI Inference Launchpad appliance.
The Thinking Directive
How the Thinking directive on the Tier Map controls reasoning depth by effort level, why the off option is disabled for some providers, how each engine interprets the level, and the shared output allowance that reasoning and answer tokens draw from.
Thinking Directive Modes
Reference of the Thinking directive modes on the Tier map, the effort levels, per-engine interpretation, the console states that override the setting, and the Thinking values of semantic routing rules.