@juspay/neurolink/dist/rag/retrieval/searchDecision.d.ts

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

/**
 * Per-search retrieval planning.
 *
 * `RAGPipeline.query()` resolves four knobs — `topK`, `hybrid`, `graph`,
 * `rerank` — and every one of them is config with an optional per-call
 * override. Nothing inspects the query. The same plan is used for "what is
 * the refund window?" (one precise passage, an exact phrase worth matching
 * lexically) and "how does billing relate to entitlements?" (many passages,
 * relationships between documents).
 *
 * One decision request answers all four for the query in hand, in ~400ms.
 * Every answer is a *suggestion*: an explicit per-call option always wins,
 * and a capability the pipeline was not configured with can never be turned
 * on by a model — `graph: true` against a pipeline with no graph index would
 * be a failure, not a plan.
 *
 * @module rag/retrieval/searchDecision
 */
import type { DecisionCallerFn, SearchPlanCapabilities, SearchPlanResult } from "../../types/index.js";
/**
 * Ask how this particular query should be retrieved.
 *
 * Returns `null` when nothing should change — no decision provider, a failed
 * call, or an answer set that suggests nothing. Every returned field is
 * optional and means "use this unless the caller said otherwise".
 */
export declare function decideSearchPlan(query: string, decide: DecisionCallerFn, capabilities: SearchPlanCapabilities): Promise<SearchPlanResult | null>;