UNPKG

@juspay/neurolink

Version:

The pipe layer of an AI nervous system: one interface connecting provider neurons to your application, across three inference types — generate, stream and decide. `decide` returns typed, calibrated judgements from a non-generative model (~400ms, ~$0.00002

9 lines (8 loc) • 386 B
import type { ProviderModelManifest } from "../../types/index.js"; /** * Minimal manifest: vertex has no MODEL_REGISTRY entries today, so * only the provider-wide fallback is known. Named models can be added here * incrementally without touching any consumer — see Task 5 of the model * metadata consolidation plan. */ export declare const vertexManifest: ProviderModelManifest;