sensemaking 0.15.4 → 0.17.0

package/dist/cjs/embed/langfit.js

@@ -0,0 +1,286 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", {
+    value: true
+});
+function _export(target, all) {
+    for(var name in all)Object.defineProperty(target, name, {
+        enumerable: true,
+        get: Object.getOwnPropertyDescriptor(all, name).get
+    });
+}
+_export(exports, {
+    get checkLanguageFit () {
+        return checkLanguageFit;
+    },
+    get languageDistribution () {
+        return languageDistribution;
+    }
+});
+var _francmin = require("franc-min");
+var _sharedts = require("../db/shared.js");
+var _errorsts = require("../errors.js");
+var _languagests = require("./languages.js");
+function _array_like_to_array(arr, len) {
+    if (len == null || len > arr.length) len = arr.length;
+    for(var i = 0, arr2 = new Array(len); i < len; i++)arr2[i] = arr[i];
+    return arr2;
+}
+function _array_with_holes(arr) {
+    if (Array.isArray(arr)) return arr;
+}
+function asyncGeneratorStep(gen, resolve, reject, _next, _throw, key, arg) {
+    try {
+        var info = gen[key](arg);
+        var value = info.value;
+    } catch (error) {
+        reject(error);
+        return;
+    }
+    if (info.done) resolve(value);
+    else Promise.resolve(value).then(_next, _throw);
+}
+function _async_to_generator(fn) {
+    return function() {
+        var self = this, args = arguments;
+        return new Promise(function(resolve, reject) {
+            var gen = fn.apply(self, args);
+            function _next(value) {
+                asyncGeneratorStep(gen, resolve, reject, _next, _throw, "next", value);
+            }
+            function _throw(err) {
+                asyncGeneratorStep(gen, resolve, reject, _next, _throw, "throw", err);
+            }
+            _next(undefined);
+        });
+    };
+}
+function _define_property(obj, key, value) {
+    if (key in obj) {
+        Object.defineProperty(obj, key, {
+            value: value,
+            enumerable: true,
+            configurable: true,
+            writable: true
+        });
+    } else obj[key] = value;
+    return obj;
+}
+function _iterable_to_array_limit(arr, i) {
+    var _i = arr == null ? null : typeof Symbol !== "undefined" && arr[Symbol.iterator] || arr["@@iterator"];
+    if (_i == null) return;
+    var _arr = [];
+    var _n = true;
+    var _d = false;
+    var _s, _e;
+    try {
+        for(_i = _i.call(arr); !(_n = (_s = _i.next()).done); _n = true){
+            _arr.push(_s.value);
+            if (i && _arr.length === i) break;
+        }
+    } catch (err) {
+        _d = true;
+        _e = err;
+    } finally{
+        try {
+            if (!_n && _i["return"] != null) _i["return"]();
+        } finally{
+            if (_d) throw _e;
+        }
+    }
+    return _arr;
+}
+function _non_iterable_rest() {
+    throw new TypeError("Invalid attempt to destructure non-iterable instance.\nIn order to be iterable, non-array objects must have a [Symbol.iterator]() method.");
+}
+function _object_spread(target) {
+    for(var i = 1; i < arguments.length; i++){
+        var source = arguments[i] != null ? arguments[i] : {};
+        var ownKeys = Object.keys(source);
+        if (typeof Object.getOwnPropertySymbols === "function") {
+            ownKeys = ownKeys.concat(Object.getOwnPropertySymbols(source).filter(function(sym) {
+                return Object.getOwnPropertyDescriptor(source, sym).enumerable;
+            }));
+        }
+        ownKeys.forEach(function(key) {
+            _define_property(target, key, source[key]);
+        });
+    }
+    return target;
+}
+function _sliced_to_array(arr, i) {
+    return _array_with_holes(arr) || _iterable_to_array_limit(arr, i) || _unsupported_iterable_to_array(arr, i) || _non_iterable_rest();
+}
+function _ts_generator(thisArg, body) {
+    var f, y, t, _ = {
+        label: 0,
+        sent: function() {
+            if (t[0] & 1) throw t[1];
+            return t[1];
+        },
+        trys: [],
+        ops: []
+    }, g = Object.create((typeof Iterator === "function" ? Iterator : Object).prototype), d = Object.defineProperty;
+    return d(g, "next", {
+        value: verb(0)
+    }), d(g, "throw", {
+        value: verb(1)
+    }), d(g, "return", {
+        value: verb(2)
+    }), typeof Symbol === "function" && d(g, Symbol.iterator, {
+        value: function() {
+            return this;
+        }
+    }), g;
+    function verb(n) {
+        return function(v) {
+            return step([
+                n,
+                v
+            ]);
+        };
+    }
+    function step(op) {
+        if (f) throw new TypeError("Generator is already executing.");
+        while(g && (g = 0, op[0] && (_ = 0)), _)try {
+            if (f = 1, y && (t = op[0] & 2 ? y["return"] : op[0] ? y["throw"] || ((t = y["return"]) && t.call(y), 0) : y.next) && !(t = t.call(y, op[1])).done) return t;
+            if (y = 0, t) op = [
+                op[0] & 2,
+                t.value
+            ];
+            switch(op[0]){
+                case 0:
+                case 1:
+                    t = op;
+                    break;
+                case 4:
+                    _.label++;
+                    return {
+                        value: op[1],
+                        done: false
+                    };
+                case 5:
+                    _.label++;
+                    y = op[1];
+                    op = [
+                        0
+                    ];
+                    continue;
+                case 7:
+                    op = _.ops.pop();
+                    _.trys.pop();
+                    continue;
+                default:
+                    if (!(t = _.trys, t = t.length > 0 && t[t.length - 1]) && (op[0] === 6 || op[0] === 2)) {
+                        _ = 0;
+                        continue;
+                    }
+                    if (op[0] === 3 && (!t || op[1] > t[0] && op[1] < t[3])) {
+                        _.label = op[1];
+                        break;
+                    }
+                    if (op[0] === 6 && _.label < t[1]) {
+                        _.label = t[1];
+                        t = op;
+                        break;
+                    }
+                    if (t && _.label < t[2]) {
+                        _.label = t[2];
+                        _.ops.push(op);
+                        break;
+                    }
+                    if (t[2]) _.ops.pop();
+                    _.trys.pop();
+                    continue;
+            }
+            op = body.call(thisArg, _);
+        } catch (e) {
+            op = [
+                6,
+                e
+            ];
+            y = 0;
+        } finally{
+            f = t = 0;
+        }
+        if (op[0] & 5) throw op[1];
+        return {
+            value: op[0] ? op[1] : void 0,
+            done: true
+        };
+    }
+}
+function _unsupported_iterable_to_array(o, minLen) {
+    if (!o) return;
+    if (typeof o === "string") return _array_like_to_array(o, minLen);
+    var n = Object.prototype.toString.call(o).slice(8, -1);
+    if (n === "Object" && o.constructor) n = o.constructor.name;
+    if (n === "Map" || n === "Set") return Array.from(n);
+    if (n === "Arguments" || /^(?:Ui|I)nt(?:8|16|32)(?:Clamped)?Array$/.test(n)) return _array_like_to_array(o, minLen);
+}
+var META_KEY = 'embed_languages';
+// franc's own reliability floor is a handful of characters; this is a cheap upper bound, not a
+// per-chunk minimum -- a short chunk is simply more likely to come back 'und' (unclassified).
+var SAMPLE_CHARS = 300;
+// A majority computed over a handful of chunks is noise, not a corpus signal; the decision rule
+// never fires below this many classified chunks, declared languages or not.
+var MIN_CLASSIFIED = 10;
+function languageDistribution(db) {
+    var raw = (0, _sharedts.getMeta)(db, META_KEY);
+    return raw ? JSON.parse(raw) : undefined;
+}
+function classify(text) {
+    var code = (0, _francmin.franc)(text.slice(0, SAMPLE_CHARS));
+    return code === 'und' ? undefined : code;
+}
+function checkLanguageFit(db, provider, texts) {
+    return _async_to_generator(function() {
+        var _languageDistribution, persisted, merged, _iteratorNormalCompletion, _didIteratorError, _iteratorError, _iterator, _step, text, _merged_code, code, total, declared, _Object_entries_sort_, majorityLang, majorityCount, pct;
+        return _ts_generator(this, function(_state) {
+            if (texts.length === 0) return [
+                2
+            ];
+            persisted = (_languageDistribution = languageDistribution(db)) !== null && _languageDistribution !== void 0 ? _languageDistribution : {};
+            merged = _object_spread({}, persisted);
+            _iteratorNormalCompletion = true, _didIteratorError = false, _iteratorError = undefined;
+            try {
+                for(_iterator = texts[Symbol.iterator](); !(_iteratorNormalCompletion = (_step = _iterator.next()).done); _iteratorNormalCompletion = true){
+                    text = _step.value;
+                    ;
+                    code = classify(text);
+                    if (code) merged[code] = ((_merged_code = merged[code]) !== null && _merged_code !== void 0 ? _merged_code : 0) + 1;
+                }
+            } catch (err) {
+                _didIteratorError = true;
+                _iteratorError = err;
+            } finally{
+                try {
+                    if (!_iteratorNormalCompletion && _iterator.return != null) {
+                        _iterator.return();
+                    }
+                } finally{
+                    if (_didIteratorError) {
+                        throw _iteratorError;
+                    }
+                }
+            }
+            total = Object.values(merged).reduce(function(a, b) {
+                return a + b;
+            }, 0);
+            if (provider.languages && provider.languages.length > 0 && total >= MIN_CLASSIFIED) {
+                declared = new Set(provider.languages.map(_languagests.toIso3));
+                _Object_entries_sort_ = _sliced_to_array(Object.entries(merged).sort(function(a, b) {
+                    return b[1] - a[1];
+                })[0], 2), majorityLang = _Object_entries_sort_[0], majorityCount = _Object_entries_sort_[1];
+                if (majorityCount / total >= 0.5 && !declared.has(majorityLang)) {
+                    pct = Math.round(majorityCount / total * 100);
+                    throw new _errorsts.SenseError('EMBED_MODEL_MISMATCH', "embed model ".concat(provider.id, " declares languages [").concat(provider.languages.join(', '), "], but ").concat(pct, "% of this tree's classified text is \"").concat(majorityLang, "\" (ISO 639-3), which is not among them; choose a model for this tree's languages: `sense init --model ...`, see the sense-setup skill or INTEGRATIONS.md"));
+                }
+            }
+            (0, _sharedts.setMeta)(db, META_KEY, JSON.stringify(merged));
+            return [
+                2
+            ];
+        });
+    })();
+}
+/* CJS INTEROP */ if (exports.__esModule && exports.default) { try { Object.defineProperty(exports.default, '__esModule', { value: true }); for (var key in exports) { exports.default[key] = exports[key]; } } catch (_) {}; module.exports = exports.default; }

package/dist/cjs/embed/langfit.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["/Users/kevin/Dev/OpenSource/ai/sensemaking/src/embed/langfit.ts"],"sourcesContent":["import type { DatabaseSync } from 'node:sqlite';\nimport { franc } from 'franc-min';\nimport { getMeta, setMeta } from '../db/shared.ts';\nimport { SenseError } from '../errors.ts';\nimport { toIso3 } from './languages.ts';\nimport type { EmbedProvider } from './types.ts';\n\nconst META_KEY = 'embed_languages';\n// franc's own reliability floor is a handful of characters; this is a cheap upper bound, not a\n// per-chunk minimum -- a short chunk is simply more likely to come back 'und' (unclassified).\nconst SAMPLE_CHARS = 300;\n// A majority computed over a handful of chunks is noise, not a corpus signal; the decision rule\n// never fires below this many classified chunks, declared languages or not.\nconst MIN_CLASSIFIED = 10;\n\ntype LangCounts = Record<string, number>;\n\nexport function languageDistribution(db: DatabaseSync): LangCounts | undefined {\n  const raw = getMeta(db, META_KEY);\n  return raw ? JSON.parse(raw) : undefined;\n}\n\nfunction classify(text: string): string | undefined {\n  const code = franc(text.slice(0, SAMPLE_CHARS));\n  return code === 'und' ? undefined : code;\n}\n\n// Merges chunk texts into the persisted distribution; throws (without persisting) if the model\n// declares languages and a clear majority classified so far is not among them.\nexport async function checkLanguageFit(db: DatabaseSync, provider: EmbedProvider, texts: string[]): Promise<void> {\n  if (texts.length === 0) return;\n  const persisted = languageDistribution(db) ?? {};\n  const merged = { ...persisted };\n  for (const text of texts) {\n    const code = classify(text);\n    if (code) merged[code] = (merged[code] ?? 0) + 1;\n  }\n\n  const total = Object.values(merged).reduce((a, b) => a + b, 0);\n  if (provider.languages && provider.languages.length > 0 && total >= MIN_CLASSIFIED) {\n    const declared = new Set(provider.languages.map(toIso3));\n    const [majorityLang, majorityCount] = Object.entries(merged).sort((a, b) => b[1] - a[1])[0];\n    if (majorityCount / total >= 0.5 && !declared.has(majorityLang)) {\n      const pct = Math.round((majorityCount / total) * 100);\n      throw new SenseError(\n        'EMBED_MODEL_MISMATCH',\n        `embed model ${provider.id} declares languages [${provider.languages.join(', ')}], but ${pct}% of this tree's classified text is \"${majorityLang}\" (ISO 639-3), which is not among them; choose a model for this tree's languages: \\`sense init --model ...\\`, see the sense-setup skill or INTEGRATIONS.md`\n      );\n    }\n  }\n  setMeta(db, META_KEY, JSON.stringify(merged));\n}\n"],"names":["checkLanguageFit","languageDistribution","META_KEY","SAMPLE_CHARS","MIN_CLASSIFIED","db","raw","getMeta","JSON","parse","undefined","classify","text","code","franc","slice","provider","texts","persisted","merged","total","declared","Object","majorityLang","majorityCount","pct","length","values","reduce","a","b","languages","Set","map","toIso3","entries","sort","has","Math","round","SenseError","id","join","setMeta","stringify"],"mappings":";;;;;;;;;;;QA6BsBA;eAAAA;;QAZNC;eAAAA;;;wBAhBM;wBACW;wBACN;2BACJ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAGvB,IAAMC,WAAW;AACjB,+FAA+F;AAC/F,8FAA8F;AAC9F,IAAMC,eAAe;AACrB,gGAAgG;AAChG,4EAA4E;AAC5E,IAAMC,iBAAiB;AAIhB,SAASH,qBAAqBI,EAAgB;IACnD,IAAMC,MAAMC,IAAAA,iBAAO,EAACF,IAAIH;IACxB,OAAOI,MAAME,KAAKC,KAAK,CAACH,OAAOI;AACjC;AAEA,SAASC,SAASC,IAAY;IAC5B,IAAMC,OAAOC,IAAAA,eAAK,EAACF,KAAKG,KAAK,CAAC,GAAGZ;IACjC,OAAOU,SAAS,QAAQH,YAAYG;AACtC;AAIO,SAAeb,iBAAiBK,EAAgB,EAAEW,QAAuB,EAAEC,KAAe;;YAE7EhB,uBAAZiB,WACAC,QACD,2BAAA,mBAAA,gBAAA,WAAA,OAAMP,MAEiBO,cADpBN,MAIFO,OAEEC,UACgCC,uBAA/BC,cAAcC,eAEbC;;YAbV,IAAIR,MAAMS,MAAM,KAAK,GAAG;;;YAClBR,aAAYjB,wBAAAA,qBAAqBI,iBAArBJ,mCAAAA,wBAA4B,CAAC;YACzCkB,SAAS,mBAAKD;YACf,kCAAA,2BAAA;;gBAAL,IAAK,YAAcD,4BAAd,6BAAA,QAAA,yBAAA,iCAAqB;oBAAfL,OAAN;;oBACGC,OAAOF,SAASC;oBACtB,IAAIC,MAAMM,MAAM,CAACN,KAAK,GAAG,EAACM,eAAAA,MAAM,CAACN,KAAK,cAAZM,0BAAAA,eAAgB,KAAK;gBACjD;;gBAHK;gBAAA;;;yBAAA,6BAAA;wBAAA;;;wBAAA;8BAAA;;;;YAKCC,QAAQE,OAAOK,MAAM,CAACR,QAAQS,MAAM,CAAC,SAACC,GAAGC;uBAAMD,IAAIC;eAAG;YAC5D,IAAId,SAASe,SAAS,IAAIf,SAASe,SAAS,CAACL,MAAM,GAAG,KAAKN,SAAShB,gBAAgB;gBAC5EiB,WAAW,IAAIW,IAAIhB,SAASe,SAAS,CAACE,GAAG,CAACC,mBAAM;gBAChBZ,yCAAAA,OAAOa,OAAO,CAAChB,QAAQiB,IAAI,CAAC,SAACP,GAAGC;2BAAMA,CAAC,CAAC,EAAE,GAAGD,CAAC,CAAC,EAAE;kBAAC,CAAC,EAAE,MAApFN,eAA+BD,0BAAjBE,gBAAiBF;gBACtC,IAAIE,gBAAgBJ,SAAS,OAAO,CAACC,SAASgB,GAAG,CAACd,eAAe;oBACzDE,MAAMa,KAAKC,KAAK,CAAC,AAACf,gBAAgBJ,QAAS;oBACjD,MAAM,IAAIoB,oBAAU,CAClB,wBACA,AAAC,eAAiDxB,OAAnCA,SAASyB,EAAE,EAAC,yBAA8DhB,OAAvCT,SAASe,SAAS,CAACW,IAAI,CAAC,OAAM,WAAoDnB,OAA3CE,KAAI,0CAAoD,OAAbF,cAAa;gBAErJ;YACF;YACAoB,IAAAA,iBAAO,EAACtC,IAAIH,UAAUM,KAAKoC,SAAS,CAACzB;;;;;IACvC"}

package/dist/cjs/embed/languages.d.cts

@@ -0,0 +1,3 @@
+export declare function isKnownLanguageTag(tag: string): boolean;
+export declare function toIso3(code: string): string;
+export declare const MEASURED_MODEL_LANGUAGES: Record<string, string[]>;

package/dist/cjs/embed/languages.d.ts

@@ -0,0 +1,3 @@
+export declare function isKnownLanguageTag(tag: string): boolean;
+export declare function toIso3(code: string): string;
+export declare const MEASURED_MODEL_LANGUAGES: Record<string, string[]>;

package/dist/cjs/embed/languages.js

@@ -0,0 +1,98 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", {
+    value: true
+});
+function _export(target, all) {
+    for(var name in all)Object.defineProperty(target, name, {
+        enumerable: true,
+        get: Object.getOwnPropertyDescriptor(all, name).get
+    });
+}
+_export(exports, {
+    get MEASURED_MODEL_LANGUAGES () {
+        return MEASURED_MODEL_LANGUAGES;
+    },
+    get isKnownLanguageTag () {
+        return isKnownLanguageTag;
+    },
+    get toIso3 () {
+        return toIso3;
+    }
+});
+// HF model cards declare languages as ISO 639-1 tags (e.g. "zh"); franc-min reports ISO 639-3
+// (e.g. "cmn"). This bridges the two for comparison. Limited to franc-min's own 82-language
+// data (README table, https://github.com/wooorm/franc), so every value here is a code franc-min
+// can actually emit; a declared tag with no entry here is compared as-is.
+var ISO_639_1_TO_3 = {
+    ar: 'arb',
+    am: 'amh',
+    az: 'azj',
+    be: 'bel',
+    bg: 'bul',
+    bn: 'ben',
+    bs: 'bos',
+    cs: 'ces',
+    de: 'deu',
+    el: 'ell',
+    en: 'eng',
+    es: 'spa',
+    fa: 'pes',
+    fr: 'fra',
+    gu: 'guj',
+    ha: 'hau',
+    hi: 'hin',
+    hr: 'hrv',
+    hu: 'hun',
+    id: 'ind',
+    ig: 'ibo',
+    it: 'ita',
+    ja: 'jpn',
+    jv: 'jav',
+    kk: 'kaz',
+    kn: 'kan',
+    ko: 'kor',
+    ml: 'mal',
+    mr: 'mar',
+    ms: 'zlm',
+    my: 'mya',
+    ne: 'npi',
+    nl: 'nld',
+    pa: 'pan',
+    pl: 'pol',
+    pt: 'por',
+    ro: 'ron',
+    ru: 'rus',
+    rw: 'kin',
+    si: 'sin',
+    so: 'som',
+    sr: 'srp',
+    su: 'sun',
+    sv: 'swe',
+    sw: 'swh',
+    ta: 'tam',
+    te: 'tel',
+    th: 'tha',
+    tl: 'tgl',
+    tr: 'tur',
+    uk: 'ukr',
+    ur: 'urd',
+    uz: 'uzn',
+    vi: 'vie',
+    yo: 'yor',
+    zh: 'cmn',
+    zu: 'zul'
+};
+function isKnownLanguageTag(tag) {
+    return tag in ISO_639_1_TO_3;
+}
+function toIso3(code) {
+    var _ISO_639_1_TO_3_base;
+    var base = code.toLowerCase().split('-')[0];
+    return (_ISO_639_1_TO_3_base = ISO_639_1_TO_3[base]) !== null && _ISO_639_1_TO_3_base !== void 0 ? _ISO_639_1_TO_3_base : base;
+}
+var MEASURED_MODEL_LANGUAGES = {
+    'minishlab/potion-retrieval-32M': [
+        'en'
+    ]
+};
+/* CJS INTEROP */ if (exports.__esModule && exports.default) { try { Object.defineProperty(exports.default, '__esModule', { value: true }); for (var key in exports) { exports.default[key] = exports[key]; } } catch (_) {}; module.exports = exports.default; }

package/dist/cjs/embed/languages.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["/Users/kevin/Dev/OpenSource/ai/sensemaking/src/embed/languages.ts"],"sourcesContent":["// HF model cards declare languages as ISO 639-1 tags (e.g. \"zh\"); franc-min reports ISO 639-3\n// (e.g. \"cmn\"). This bridges the two for comparison. Limited to franc-min's own 82-language\n// data (README table, https://github.com/wooorm/franc), so every value here is a code franc-min\n// can actually emit; a declared tag with no entry here is compared as-is.\nconst ISO_639_1_TO_3: Record<string, string> = {\n  ar: 'arb',\n  am: 'amh',\n  az: 'azj',\n  be: 'bel',\n  bg: 'bul',\n  bn: 'ben',\n  bs: 'bos',\n  cs: 'ces',\n  de: 'deu',\n  el: 'ell',\n  en: 'eng',\n  es: 'spa',\n  fa: 'pes',\n  fr: 'fra',\n  gu: 'guj',\n  ha: 'hau',\n  hi: 'hin',\n  hr: 'hrv',\n  hu: 'hun',\n  id: 'ind',\n  ig: 'ibo',\n  it: 'ita',\n  ja: 'jpn',\n  jv: 'jav',\n  kk: 'kaz',\n  kn: 'kan',\n  ko: 'kor',\n  ml: 'mal',\n  mr: 'mar',\n  ms: 'zlm',\n  my: 'mya',\n  ne: 'npi',\n  nl: 'nld',\n  pa: 'pan',\n  pl: 'pol',\n  pt: 'por',\n  ro: 'ron',\n  ru: 'rus',\n  rw: 'kin',\n  si: 'sin',\n  so: 'som',\n  sr: 'srp',\n  su: 'sun',\n  sv: 'swe',\n  sw: 'swh',\n  ta: 'tam',\n  te: 'tel',\n  th: 'tha',\n  tl: 'tgl',\n  tr: 'tur',\n  uk: 'ukr',\n  ur: 'urd',\n  uz: 'uzn',\n  vi: 'vie',\n  yo: 'yor',\n  zh: 'cmn',\n  zu: 'zul',\n};\n\nexport function isKnownLanguageTag(tag: string): boolean {\n  return tag in ISO_639_1_TO_3;\n}\n\n// Normalizes a declared or detected language code to ISO 639-3 for comparison; strips a\n// region/script subtag (\"zh-cn\" -> \"zh\") first. Codes already in 639-3 form pass through.\nexport function toIso3(code: string): string {\n  const base = code.toLowerCase().split('-')[0];\n  return ISO_639_1_TO_3[base] ?? base;\n}\n\n// Languages this project measured for models whose cards declare none, so the fit check is\n// not silently off for the shipped default; asserted here because it was measured, not attested.\nexport const MEASURED_MODEL_LANGUAGES: Record<string, string[]> = {\n  'minishlab/potion-retrieval-32M': ['en'], // benchmark/reports/2026-08-27-embedding-model-selection.md\n};\n"],"names":["MEASURED_MODEL_LANGUAGES","isKnownLanguageTag","toIso3","ISO_639_1_TO_3","ar","am","az","be","bg","bn","bs","cs","de","el","en","es","fa","fr","gu","ha","hi","hr","hu","id","ig","it","ja","jv","kk","kn","ko","ml","mr","ms","my","ne","nl","pa","pl","pt","ro","ru","rw","si","so","sr","su","sv","sw","ta","te","th","tl","tr","uk","ur","uz","vi","yo","zh","zu","tag","code","base","toLowerCase","split"],"mappings":";;;;;;;;;;;QA6EaA;eAAAA;;QAbGC;eAAAA;;QAMAC;eAAAA;;;AAtEhB,8FAA8F;AAC9F,4FAA4F;AAC5F,gGAAgG;AAChG,0EAA0E;AAC1E,IAAMC,iBAAyC;IAC7CC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;IACJC,IAAI;AACN;AAEO,SAAS3D,mBAAmB4D,GAAW;IAC5C,OAAOA,OAAO1D;AAChB;AAIO,SAASD,OAAO4D,IAAY;QAE1B3D;IADP,IAAM4D,OAAOD,KAAKE,WAAW,GAAGC,KAAK,CAAC,IAAI,CAAC,EAAE;IAC7C,QAAO9D,uBAAAA,cAAc,CAAC4D,KAAK,cAApB5D,kCAAAA,uBAAwB4D;AACjC;AAIO,IAAM/D,2BAAqD;IAChE,kCAAkC;QAAC;KAAK;AAC1C"}

package/dist/cjs/embed/openai.d.cts

@@ -0,0 +1,2 @@
+import type { EmbedProvider } from './types.js';
+export declare function openaiProvider(model: string, url: string | undefined, keyEnv: string | undefined): Promise<EmbedProvider>;

package/dist/cjs/embed/openai.d.ts

@@ -0,0 +1,2 @@
+import type { EmbedProvider } from './types.js';
+export declare function openaiProvider(model: string, url: string | undefined, keyEnv: string | undefined): Promise<EmbedProvider>;