@juspay/neurolink/dist/types/knowledge.js

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

/**
 * Knowledge grounding — lexical-first host-supplied knowledge retrieval.
 *
 * A host application owns a structured *knowledge registry*: versioned entries
 * describing concepts, configuration, taxonomies, procedures, and operating
 * rules. NeuroLink owns the
 * generic engine that ingests that registry, builds an in-memory lexical
 * index once per instance, and — independently of tool routing — retrieves a
 * small, token-bounded set of relevant entries before each main model call.
 * The selected entries are attached as *ephemeral context*: visible to the
 * current generation call, never persisted into conversation memory.
 *
 * This is retrieval-augmented generation WITHOUT vector retrieval. The first
 * release ranks with exact identifiers, reviewed aliases, metadata filters,
 * and weighted field-aware BM25 only. No embedding model, embedding service,
 * or vector store is initialized. An LLM reranker and semantic retrieval are
 * deferred behind an explicit evaluation gate.
 *
 * Ownership boundary: NeuroLink defines the contracts below and the engine;
 * it never contains host product content. The host supplies content and
 * per-request scope. The engine stays provider-neutral.
 *
 * Type names are globally prefixed `Knowledge*` to satisfy the repo's
 * unique-type-name rule and to avoid collision with the pre-existing
 * web-search `grounding.ts` vocabulary (`EnhancedGroundingMetadata` et al.),
 * which is a different concept (Google search grounding, not product
 * knowledge).
 */
export {};