Skip to content

armgit / laya

Public Imported from GitHub
0

Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.

Merge pull request #1117

Nandakishor853ca315de17
diff --cc laya-ts/README.md
index 864c5e60,82e6738f..2a7b0bb3
--- a/laya-ts/README.md
+++ b/laya-ts/README.md
@@@ -170,63 -170,16 +170,65 @@@ Python's `sort_by_length` grouping is n
## Shortlist (many labels)
```ts
- import { shortlistChoice, predictShortlist, embedFnFromAgent } from "laya-ts";
+ import { shortlistChoice, predictShortlist, embedFnFromAgent, cached } from "laya-ts";
- const keep = await shortlistChoice(state, bigCriteriaDict, embedFn, 20);
- const out = await predictShortlist(agent, state, questions, embedFn, 20);
+ const cachedEmbed = cached(embedFn);
+ const keep = await shortlistChoice(state, bigCriteriaDict, cachedEmbed, 20);
+ const out = await predictShortlist(agent, state, questions, cachedEmbed, 20);
// out.shortlist[qid] = { labels, scores, k, n, passthrough }
// embedFnFromAgent(agent) mean-pools the loaded encoder; a dedicated bi-encoder usually shortlists better.
+ // cached(embedFn) keeps an LRU cache across calls; cachedEmbed.cacheInfo() reports size/hits/misses.
```
+### Tournament (without an embedder)
+
+For a large tool or intent catalog, `predictTournament` lets the decision model narrow the
+options itself. It ports Python's `predict_tournament` to the local Node/browser runtime:
+
+```ts
+import { predictTournament } from "laya-ts";
+
+const out = await predictTournament(agent, state, questions);
+console.log(out.answers.intent);
+console.log(out.tournament.intent); // { labels: [...finalists], n: originalCount, rounds: 1 }
+
+// Pick a group size and forward options to every prediction, including the final one.
+const routed = await predictTournament(router, state, questions, 16, { model: "english" });
+```
+
+Each oversized choice is split into balanced groups of at most 16 labels. All groups from
+all questions share one `predict` call per round; their winners advance until each choice
+fits. Up to 256 labels therefore take one elimination call and one final call. Small choices
+and non-choice questions reach the final call unchanged, and a request needing no
+elimination makes exactly one call. The helper does not mutate the supplied questions.
+
+The returned `tournament` metadata covers every choice, including `rounds: 0` for a
+passthrough. Probabilities and confidences describe **only the finalists**; `usage`,
+`routing`, and other prediction fields come from the final call, not all rounds combined.
+Hooks run for every underlying call. Calibrate thresholds on the strategy you actually use;
+a threshold fitted on the full catalog does not automatically transfer to a tournament.
+Widening the head budget or using a dedicated shortlist embedder can still be a better fit.
+
+A narrowed choice drops its original `option_order` with one warning per question, matching
+Python. Passthrough definitions keep it. This does not add `option_order` handling to the
+TypeScript `Agent`, whose prediction path does not currently apply that field.
+
+For a reproducible local comparison, build the package and export a checkpoint as above,
+then run from the repository root:
+
+```bash
+python laya-ts/scripts/tournament_parity.py --model-dir CHECKPOINT --onnx-dir ./model \
+ --fixture ./tournament-python.json
+node laya-ts/examples/tournament.mjs --model-dir ./model \
+ --fixture ./tournament-python.json --report ./tournament-node.json
+```
+
+The Python script records fresh predictions for fixed inputs; Node independently runs
+the same inputs through the split ONNX export. The check compares each round's questions,
+winners, probabilities and final metadata, including a two-round case. Reports include
+artifact hashes, call counts and warmed timings. These few cases check runtime parity;
+they do not establish accuracy gains or production latency. Model files stay local.
+
## Per-language calibration (`lang_temperatures`)
Port of the Python `Agent(lang_temperatures=...)` knob. A language override replaces the
diff --cc laya-ts/src/index.ts
index fec9d250,f08738db..8f881334
--- a/laya-ts/src/index.ts
+++ b/laya-ts/src/index.ts
@@@ -17,8 -17,8 +17,8 @@@ export { createNodeProvider, createWebP
export type { Batch, SessionProvider, ProviderOptions, NodeBundle, WebBundle } from "./providers.js";
export { Router, normaliseName, DEFAULT_MODELS, digestsFromEnv, _digestsFromEnv } from "./router.js";
export type { RoutedResult, RouteDecision, ModelName, ModelSpec, BatchRequest, PredictBatchOptions, RouterOptions, RouteOptions } from "./router.js";
- export { shortlistChoice, predictShortlist, predictTournament, embedFnFromAgent, DEFAULT_SHORTLIST_K, DEFAULT_TOURNAMENT_GROUP } from "./shortlist.js";
- export type { EmbedFn, ShortlistMeta, TournamentMeta } from "./shortlist.js";
-export { shortlistChoice, predictShortlist, embedFnFromAgent, DEFAULT_SHORTLIST_K, cached, cachedEmbedFn, DEFAULT_SHORTLIST_MAXSIZE } from "./shortlist.js";
-export type { EmbedFn, ShortlistMeta, CacheInfo, CachedEmbedFn } from "./shortlist.js";
++export { shortlistChoice, predictShortlist, predictTournament, embedFnFromAgent, cached, cachedEmbedFn, DEFAULT_SHORTLIST_K, DEFAULT_SHORTLIST_MAXSIZE, DEFAULT_TOURNAMENT_GROUP } from "./shortlist.js";
++export type { EmbedFn, ShortlistMeta, TournamentMeta, CacheInfo, CachedEmbedFn } from "./shortlist.js";
export { analyse, isEnglish, guessLatinLanguage, detectScript } from "./lang.js";
export type { AnalyseResult, LatinProfile } from "./lang.js";
export { cleanEmailBody, emailState } from "./email.js";
diff --cc laya-ts/src/shortlist.ts
index 9571d922,5e3f0815..1d1fdca7
--- a/laya-ts/src/shortlist.ts
+++ b/laya-ts/src/shortlist.ts
@@@ -3,7 -3,7 +3,8 @@@ import type { Batch } from "./providers
import type { QuestionDef, SystemOneResult } from "./agent.js";
export const DEFAULT_SHORTLIST_K = 20;
+export const DEFAULT_TOURNAMENT_GROUP = 16;
+ export const DEFAULT_SHORTLIST_MAXSIZE = 4096;
export type EmbedFn = (texts: string[]) => Promise<number[][]> | number[][];
@@@ -15,12 -15,21 +16,27 @@@ export interface ShortlistMeta
passthrough: boolean;
}
+export interface TournamentMeta {
+ labels: string[];
+ n: number;
+ rounds: number;
+}
+
+ export interface CacheInfo {
+ size: number;
+ maxsize: number;
+ hits: number;
+ misses: number;
+ }
+
+ export interface CachedEmbedFn {
+ (texts: string[]): Promise<number[][]>;
+ cacheInfo(): CacheInfo;
+ cache_info(): CacheInfo;
+ cacheClear(): void;
+ cache_clear(): void;
+ }
+
function checkK(k: unknown): number {
if (typeof k !== "number" || !Number.isInteger(k) || k < 1) {
throw new Error(`k must be a positive integer, got ${JSON.stringify(k)}`);