mirror of
https://github.com/tiennm99/miti99bot.git
synced 2026-09-14 14:19:45 +00:00
tiennm99
8bf2499914
Mirror the semantle migration but with @cf/baai/bge-m3 — BAAI's multilingual embedding model — because the English-only BGE variants can't produce meaningful Vietnamese vectors (their tokenizer shreds diacritics into noisy byte-level subwords). bge-m3 is trained across 194 languages incl. Vietnamese and is actually cheaper in Neurons (1,075 vs 1,841 per M tokens for bge-small-en-v1.5). Vocab check reuses the local Viet22K wordlist as an in-memory Set — O(1) OOV detection, no upstream call. Also add a test file for the module (mirrors semantle coverage plus Vietnamese-specific cases: diacritics, multi-syllable compounds).
49 lines
1.5 KiB
JavaScript
49 lines
1.5 KiB
JavaScript
/**
|
|
* @file Doantu module — Vietnamese semantle.
|
|
*
|
|
* Targets from a curated local wordlist (duyet/vietnamese-wordlist Viet22K —
|
|
* same list doubles as the vocabulary for OOV detection). Similarity scores
|
|
* come from cosine distance between `@cf/baai/bge-m3` multilingual embeddings
|
|
* produced by the `env.AI` binding. All commands are `protected` — listed
|
|
* in /help but hidden from Telegram's native / autocomplete menu.
|
|
*/
|
|
|
|
import { createClient } from "./api-client.js";
|
|
import { handleDoantu, handleGiveup, handleStats } from "./handlers.js";
|
|
|
|
/** @type {import("../../db/kv-store-interface.js").KVStore | null} */
|
|
let db = null;
|
|
/** @type {ReturnType<typeof createClient> | null} */
|
|
let client = null;
|
|
|
|
/** @type {import("../registry.js").BotModule} */
|
|
const doantuModule = {
|
|
name: "doantu",
|
|
init: async ({ db: store, env }) => {
|
|
db = store;
|
|
client = createClient(env.AI);
|
|
},
|
|
commands: [
|
|
{
|
|
name: "doantu",
|
|
visibility: "protected",
|
|
description: "Đoán từ — Vietnamese semantic word guessing (unlimited tries)",
|
|
handler: (ctx) => handleDoantu(ctx, { db, client }),
|
|
},
|
|
{
|
|
name: "doantu_giveup",
|
|
visibility: "protected",
|
|
description: "Reveal the current doantu answer (auto-starts a fresh round)",
|
|
handler: (ctx) => handleGiveup(ctx, { db, client }),
|
|
},
|
|
{
|
|
name: "doantu_stats",
|
|
visibility: "protected",
|
|
description: "Show your doantu stats",
|
|
handler: (ctx) => handleStats(ctx, { db, client }),
|
|
},
|
|
],
|
|
};
|
|
|
|
export default doantuModule;
|