Upload 7 files

bertWorker.js

@@ -0,0 +1,77 @@
+//load Candle Bert Module wasm module
+import init, { Model } from "./build/m.js";
+
+async function fetchArrayBuffer(url) {
+  const cacheName = "bert-candle-cache";
+  const cache = await caches.open(cacheName);
+  const cachedResponse = await cache.match(url);
+  if (cachedResponse) {
+    const data = await cachedResponse.arrayBuffer();
+    return new Uint8Array(data);
+  }
+  const res = await fetch(url, { cache: "force-cache" });
+  cache.put(url, res.clone());
+  return new Uint8Array(await res.arrayBuffer());
+}
+class Bert {
+  static instance = {};
+
+  static async getInstance(weightsURL, tokenizerURL, configURL, modelID) {
+    if (!this.instance[modelID]) {
+      await init();
+
+      self.postMessage({ status: "loading", message: "Loading Model" });
+      const [weightsArrayU8, tokenizerArrayU8, mel_filtersArrayU8] =
+        await Promise.all([
+          fetchArrayBuffer(weightsURL),
+          fetchArrayBuffer(tokenizerURL),
+          fetchArrayBuffer(configURL),
+        ]);
+
+      this.instance[modelID] = new Model(
+        weightsArrayU8,
+        tokenizerArrayU8,
+        mel_filtersArrayU8
+      );
+    } else {
+      self.postMessage({ status: "loading", message: "Model Already Loaded" });
+    }
+    return this.instance[modelID];
+  }
+}
+
+self.addEventListener("message", async (event) => {
+  const {
+    weightsURL,
+    tokenizerURL,
+    configURL,
+    modelID,
+    sentences,
+    normalize = true,
+  } = event.data;
+  try {
+    self.postMessage({ status: "loading", message: "Starting Bert Model" });
+    const model = await Bert.getInstance(
+      weightsURL,
+      tokenizerURL,
+      configURL,
+      modelID
+    );
+    self.postMessage({
+      status: "embedding",
+      message: "Calculating Embeddings",
+    });
+    const output = model.get_embeddings({
+      sentences: sentences,
+      normalize_embeddings: normalize,
+    });
+
+    self.postMessage({
+      status: "complete",
+      message: "complete",
+      output: output.data,
+    });
+  } catch (e) {
+    self.postMessage({ error: e });
+  }
+});

build/m.d.ts

@@ -0,0 +1,55 @@
+/* tslint:disable */
+/* eslint-disable */
+/**
+*/
+export class Model {
+  free(): void;
+/**
+* @param {Uint8Array} weights
+* @param {Uint8Array} tokenizer
+* @param {Uint8Array} config
+*/
+  constructor(weights: Uint8Array, tokenizer: Uint8Array, config: Uint8Array);
+/**
+* @param {any} input
+* @returns {any}
+*/
+  get_embeddings(input: any): any;
+}
+
+export type InitInput = RequestInfo | URL | Response | BufferSource | WebAssembly.Module;
+
+export interface InitOutput {
+  readonly memory: WebAssembly.Memory;
+  readonly __wbg_model_free: (a: number) => void;
+  readonly model_load: (a: number, b: number, c: number, d: number, e: number, f: number, g: number) => void;
+  readonly model_get_embeddings: (a: number, b: number, c: number) => void;
+  readonly main: (a: number, b: number) => number;
+  readonly __wbindgen_malloc: (a: number, b: number) => number;
+  readonly __wbindgen_realloc: (a: number, b: number, c: number, d: number) => number;
+  readonly __wbindgen_add_to_stack_pointer: (a: number) => number;
+  readonly __wbindgen_free: (a: number, b: number, c: number) => void;
+  readonly __wbindgen_exn_store: (a: number) => void;
+  readonly __wbindgen_start: () => void;
+}
+
+export type SyncInitInput = BufferSource | WebAssembly.Module;
+/**
+* Instantiates the given `module`, which can either be bytes or
+* a precompiled `WebAssembly.Module`.
+*
+* @param {SyncInitInput} module
+*
+* @returns {InitOutput}
+*/
+export function initSync(module: SyncInitInput): InitOutput;
+
+/**
+* If `module_or_path` is {RequestInfo} or {URL}, makes a request and
+* for everything else, calls `WebAssembly.instantiate` directly.
+*
+* @param {InitInput | Promise<InitInput>} module_or_path
+*
+* @returns {Promise<InitOutput>}
+*/
+export default function __wbg_init (module_or_path?: InitInput | Promise<InitInput>): Promise<InitOutput>;

build/m.js

@@ -0,0 +1,633 @@
+let wasm;
+
+const heap = new Array(128).fill(undefined);
+
+heap.push(undefined, null, true, false);
+
+function getObject(idx) { return heap[idx]; }
+
+let WASM_VECTOR_LEN = 0;
+
+let cachedUint8Memory0 = null;
+
+function getUint8Memory0() {
+    if (cachedUint8Memory0 === null || cachedUint8Memory0.byteLength === 0) {
+        cachedUint8Memory0 = new Uint8Array(wasm.memory.buffer);
+    }
+    return cachedUint8Memory0;
+}
+
+const cachedTextEncoder = (typeof TextEncoder !== 'undefined' ? new TextEncoder('utf-8') : { encode: () => { throw Error('TextEncoder not available') } } );
+
+const encodeString = (typeof cachedTextEncoder.encodeInto === 'function'
+    ? function (arg, view) {
+    return cachedTextEncoder.encodeInto(arg, view);
+}
+    : function (arg, view) {
+    const buf = cachedTextEncoder.encode(arg);
+    view.set(buf);
+    return {
+        read: arg.length,
+        written: buf.length
+    };
+});
+
+function passStringToWasm0(arg, malloc, realloc) {
+
+    if (realloc === undefined) {
+        const buf = cachedTextEncoder.encode(arg);
+        const ptr = malloc(buf.length, 1) >>> 0;
+        getUint8Memory0().subarray(ptr, ptr + buf.length).set(buf);
+        WASM_VECTOR_LEN = buf.length;
+        return ptr;
+    }
+
+    let len = arg.length;
+    let ptr = malloc(len, 1) >>> 0;
+
+    const mem = getUint8Memory0();
+
+    let offset = 0;
+
+    for (; offset < len; offset++) {
+        const code = arg.charCodeAt(offset);
+        if (code > 0x7F) break;
+        mem[ptr + offset] = code;
+    }
+
+    if (offset !== len) {
+        if (offset !== 0) {
+            arg = arg.slice(offset);
+        }
+        ptr = realloc(ptr, len, len = offset + arg.length * 3, 1) >>> 0;
+        const view = getUint8Memory0().subarray(ptr + offset, ptr + len);
+        const ret = encodeString(arg, view);
+
+        offset += ret.written;
+    }
+
+    WASM_VECTOR_LEN = offset;
+    return ptr;
+}
+
+function isLikeNone(x) {
+    return x === undefined || x === null;
+}
+
+let cachedInt32Memory0 = null;
+
+function getInt32Memory0() {
+    if (cachedInt32Memory0 === null || cachedInt32Memory0.byteLength === 0) {
+        cachedInt32Memory0 = new Int32Array(wasm.memory.buffer);
+    }
+    return cachedInt32Memory0;
+}
+
+let heap_next = heap.length;
+
+function dropObject(idx) {
+    if (idx < 132) return;
+    heap[idx] = heap_next;
+    heap_next = idx;
+}
+
+function takeObject(idx) {
+    const ret = getObject(idx);
+    dropObject(idx);
+    return ret;
+}
+
+const cachedTextDecoder = (typeof TextDecoder !== 'undefined' ? new TextDecoder('utf-8', { ignoreBOM: true, fatal: true }) : { decode: () => { throw Error('TextDecoder not available') } } );
+
+if (typeof TextDecoder !== 'undefined') { cachedTextDecoder.decode(); };
+
+function getStringFromWasm0(ptr, len) {
+    ptr = ptr >>> 0;
+    return cachedTextDecoder.decode(getUint8Memory0().subarray(ptr, ptr + len));
+}
+
+function addHeapObject(obj) {
+    if (heap_next === heap.length) heap.push(heap.length + 1);
+    const idx = heap_next;
+    heap_next = heap[idx];
+
+    heap[idx] = obj;
+    return idx;
+}
+
+let cachedFloat64Memory0 = null;
+
+function getFloat64Memory0() {
+    if (cachedFloat64Memory0 === null || cachedFloat64Memory0.byteLength === 0) {
+        cachedFloat64Memory0 = new Float64Array(wasm.memory.buffer);
+    }
+    return cachedFloat64Memory0;
+}
+
+function debugString(val) {
+    // primitive types
+    const type = typeof val;
+    if (type == 'number' || type == 'boolean' || val == null) {
+        return  `${val}`;
+    }
+    if (type == 'string') {
+        return `"${val}"`;
+    }
+    if (type == 'symbol') {
+        const description = val.description;
+        if (description == null) {
+            return 'Symbol';
+        } else {
+            return `Symbol(${description})`;
+        }
+    }
+    if (type == 'function') {
+        const name = val.name;
+        if (typeof name == 'string' && name.length > 0) {
+            return `Function(${name})`;
+        } else {
+            return 'Function';
+        }
+    }
+    // objects
+    if (Array.isArray(val)) {
+        const length = val.length;
+        let debug = '[';
+        if (length > 0) {
+            debug += debugString(val[0]);
+        }
+        for(let i = 1; i < length; i++) {
+            debug += ', ' + debugString(val[i]);
+        }
+        debug += ']';
+        return debug;
+    }
+    // Test for built-in
+    const builtInMatches = /\[object ([^\]]+)\]/.exec(toString.call(val));
+    let className;
+    if (builtInMatches.length > 1) {
+        className = builtInMatches[1];
+    } else {
+        // Failed to match the standard '[object ClassName]'
+        return toString.call(val);
+    }
+    if (className == 'Object') {
+        // we're a user defined class or Object
+        // JSON.stringify avoids problems with cycles, and is generally much
+        // easier than looping through ownProperties of `val`.
+        try {
+            return 'Object(' + JSON.stringify(val) + ')';
+        } catch (_) {
+            return 'Object';
+        }
+    }
+    // errors
+    if (val instanceof Error) {
+        return `${val.name}: ${val.message}\n${val.stack}`;
+    }
+    // TODO we could test for more things here, like `Set`s and `Map`s.
+    return className;
+}
+
+function passArray8ToWasm0(arg, malloc) {
+    const ptr = malloc(arg.length * 1, 1) >>> 0;
+    getUint8Memory0().set(arg, ptr / 1);
+    WASM_VECTOR_LEN = arg.length;
+    return ptr;
+}
+
+function handleError(f, args) {
+    try {
+        return f.apply(this, args);
+    } catch (e) {
+        wasm.__wbindgen_exn_store(addHeapObject(e));
+    }
+}
+/**
+*/
+export class Model {
+
+    static __wrap(ptr) {
+        ptr = ptr >>> 0;
+        const obj = Object.create(Model.prototype);
+        obj.__wbg_ptr = ptr;
+
+        return obj;
+    }
+
+    __destroy_into_raw() {
+        const ptr = this.__wbg_ptr;
+        this.__wbg_ptr = 0;
+
+        return ptr;
+    }
+
+    free() {
+        const ptr = this.__destroy_into_raw();
+        wasm.__wbg_model_free(ptr);
+    }
+    /**
+    * @param {Uint8Array} weights
+    * @param {Uint8Array} tokenizer
+    * @param {Uint8Array} config
+    */
+    constructor(weights, tokenizer, config) {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            const ptr0 = passArray8ToWasm0(weights, wasm.__wbindgen_malloc);
+            const len0 = WASM_VECTOR_LEN;
+            const ptr1 = passArray8ToWasm0(tokenizer, wasm.__wbindgen_malloc);
+            const len1 = WASM_VECTOR_LEN;
+            const ptr2 = passArray8ToWasm0(config, wasm.__wbindgen_malloc);
+            const len2 = WASM_VECTOR_LEN;
+            wasm.model_load(retptr, ptr0, len0, ptr1, len1, ptr2, len2);
+            var r0 = getInt32Memory0()[retptr / 4 + 0];
+            var r1 = getInt32Memory0()[retptr / 4 + 1];
+            var r2 = getInt32Memory0()[retptr / 4 + 2];
+            if (r2) {
+                throw takeObject(r1);
+            }
+            return Model.__wrap(r0);
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
+    /**
+    * @param {any} input
+    * @returns {any}
+    */
+    get_embeddings(input) {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            wasm.model_get_embeddings(retptr, this.__wbg_ptr, addHeapObject(input));
+            var r0 = getInt32Memory0()[retptr / 4 + 0];
+            var r1 = getInt32Memory0()[retptr / 4 + 1];
+            var r2 = getInt32Memory0()[retptr / 4 + 2];
+            if (r2) {
+                throw takeObject(r1);
+            }
+            return takeObject(r0);
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
+}
+
+async function __wbg_load(module, imports) {
+    if (typeof Response === 'function' && module instanceof Response) {
+        if (typeof WebAssembly.instantiateStreaming === 'function') {
+            try {
+                return await WebAssembly.instantiateStreaming(module, imports);
+
+            } catch (e) {
+                if (module.headers.get('Content-Type') != 'application/wasm') {
+                    console.warn("`WebAssembly.instantiateStreaming` failed because your server does not serve wasm with `application/wasm` MIME type. Falling back to `WebAssembly.instantiate` which is slower. Original error:\n", e);
+
+                } else {
+                    throw e;
+                }
+            }
+        }
+
+        const bytes = await module.arrayBuffer();
+        return await WebAssembly.instantiate(bytes, imports);
+
+    } else {
+        const instance = await WebAssembly.instantiate(module, imports);
+
+        if (instance instanceof WebAssembly.Instance) {
+            return { instance, module };
+
+        } else {
+            return instance;
+        }
+    }
+}
+
+function __wbg_get_imports() {
+    const imports = {};
+    imports.wbg = {};
+    imports.wbg.__wbindgen_string_get = function(arg0, arg1) {
+        const obj = getObject(arg1);
+        const ret = typeof(obj) === 'string' ? obj : undefined;
+        var ptr1 = isLikeNone(ret) ? 0 : passStringToWasm0(ret, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
+        var len1 = WASM_VECTOR_LEN;
+        getInt32Memory0()[arg0 / 4 + 1] = len1;
+        getInt32Memory0()[arg0 / 4 + 0] = ptr1;
+    };
+    imports.wbg.__wbindgen_object_drop_ref = function(arg0) {
+        takeObject(arg0);
+    };
+    imports.wbg.__wbindgen_boolean_get = function(arg0) {
+        const v = getObject(arg0);
+        const ret = typeof(v) === 'boolean' ? (v ? 1 : 0) : 2;
+        return ret;
+    };
+    imports.wbg.__wbindgen_is_object = function(arg0) {
+        const val = getObject(arg0);
+        const ret = typeof(val) === 'object' && val !== null;
+        return ret;
+    };
+    imports.wbg.__wbindgen_is_undefined = function(arg0) {
+        const ret = getObject(arg0) === undefined;
+        return ret;
+    };
+    imports.wbg.__wbindgen_in = function(arg0, arg1) {
+        const ret = getObject(arg0) in getObject(arg1);
+        return ret;
+    };
+    imports.wbg.__wbindgen_error_new = function(arg0, arg1) {
+        const ret = new Error(getStringFromWasm0(arg0, arg1));
+        return addHeapObject(ret);
+    };
+    imports.wbg.__wbindgen_object_clone_ref = function(arg0) {
+        const ret = getObject(arg0);
+        return addHeapObject(ret);
+    };
+    imports.wbg.__wbindgen_jsval_loose_eq = function(arg0, arg1) {
+        const ret = getObject(arg0) == getObject(arg1);
+        return ret;
+    };
+    imports.wbg.__wbindgen_number_get = function(arg0, arg1) {
+        const obj = getObject(arg1);
+        const ret = typeof(obj) === 'number' ? obj : undefined;
+        getFloat64Memory0()[arg0 / 8 + 1] = isLikeNone(ret) ? 0 : ret;
+        getInt32Memory0()[arg0 / 4 + 0] = !isLikeNone(ret);
+    };
+    imports.wbg.__wbg_String_4370c5505c674d30 = function(arg0, arg1) {
+        const ret = String(getObject(arg1));
+        const ptr1 = passStringToWasm0(ret, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
+        const len1 = WASM_VECTOR_LEN;
+        getInt32Memory0()[arg0 / 4 + 1] = len1;
+        getInt32Memory0()[arg0 / 4 + 0] = ptr1;
+    };
+    imports.wbg.__wbindgen_number_new = function(arg0) {
+        const ret = arg0;
+        return addHeapObject(ret);
+    };
+    imports.wbg.__wbindgen_string_new = function(arg0, arg1) {
+        const ret = getStringFromWasm0(arg0, arg1);
+        return addHeapObject(ret);
+    };
+    imports.wbg.__wbg_getwithrefkey_d1f0d12f1f1b63ea = function(arg0, arg1) {
+        const ret = getObject(arg0)[getObject(arg1)];
+        return addHeapObject(ret);
+    };
+    imports.wbg.__wbg_set_bd72c078edfa51ad = function(arg0, arg1, arg2) {
+        getObject(arg0)[takeObject(arg1)] = takeObject(arg2);
+    };
+    imports.wbg.__wbg_new_abda76e883ba8a5f = function() {
+        const ret = new Error();
+        return addHeapObject(ret);
+    };
+    imports.wbg.__wbg_stack_658279fe44541cf6 = function(arg0, arg1) {
+        const ret = getObject(arg1).stack;
+        const ptr1 = passStringToWasm0(ret, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
+        const len1 = WASM_VECTOR_LEN;
+        getInt32Memory0()[arg0 / 4 + 1] = len1;
+        getInt32Memory0()[arg0 / 4 + 0] = ptr1;
+    };
+    imports.wbg.__wbg_error_f851667af71bcfc6 = function(arg0, arg1) {
+        let deferred0_0;
+        let deferred0_1;
+        try {
+            deferred0_0 = arg0;
+            deferred0_1 = arg1;
+            console.error(getStringFromWasm0(arg0, arg1));
+        } finally {
+            wasm.__wbindgen_free(deferred0_0, deferred0_1, 1);
+        }
+    };
+    imports.wbg.__wbg_log_87e6a1c1b12181c3 = function(arg0, arg1) {
+        console.log(getStringFromWasm0(arg0, arg1));
+    };
+    imports.wbg.__wbg_crypto_c48a774b022d20ac = function(arg0) {
+        const ret = getObject(arg0).crypto;
+        return addHeapObject(ret);
+    };
+    imports.wbg.__wbg_process_298734cf255a885d = function(arg0) {
+        const ret = getObject(arg0).process;
+        return addHeapObject(ret);
+    };
+    imports.wbg.__wbg_versions_e2e78e134e3e5d01 = function(arg0) {
+        const ret = getObject(arg0).versions;
+        return addHeapObject(ret);
+    };
+    imports.wbg.__wbg_node_1cd7a5d853dbea79 = function(arg0) {
+        const ret = getObject(arg0).node;
+        return addHeapObject(ret);
+    };
+    imports.wbg.__wbindgen_is_string = function(arg0) {
+        const ret = typeof(getObject(arg0)) === 'string';
+        return ret;
+    };
+    imports.wbg.__wbg_msCrypto_bcb970640f50a1e8 = function(arg0) {
+        const ret = getObject(arg0).msCrypto;
+        return addHeapObject(ret);
+    };
+    imports.wbg.__wbg_require_8f08ceecec0f4fee = function() { return handleError(function () {
+        const ret = module.require;
+        return addHeapObject(ret);
+    }, arguments) };
+    imports.wbg.__wbindgen_is_function = function(arg0) {
+        const ret = typeof(getObject(arg0)) === 'function';
+        return ret;
+    };
+    imports.wbg.__wbg_getRandomValues_37fa2ca9e4e07fab = function() { return handleError(function (arg0, arg1) {
+        getObject(arg0).getRandomValues(getObject(arg1));
+    }, arguments) };
+    imports.wbg.__wbg_randomFillSync_dc1e9a60c158336d = function() { return handleError(function (arg0, arg1) {
+        getObject(arg0).randomFillSync(takeObject(arg1));
+    }, arguments) };
+    imports.wbg.__wbg_get_44be0491f933a435 = function(arg0, arg1) {
+        const ret = getObject(arg0)[arg1 >>> 0];
+        return addHeapObject(ret);
+    };
+    imports.wbg.__wbg_length_fff51ee6522a1a18 = function(arg0) {
+        const ret = getObject(arg0).length;
+        return ret;
+    };
+    imports.wbg.__wbg_new_898a68150f225f2e = function() {
+        const ret = new Array();
+        return addHeapObject(ret);
+    };
+    imports.wbg.__wbg_newnoargs_581967eacc0e2604 = function(arg0, arg1) {
+        const ret = new Function(getStringFromWasm0(arg0, arg1));
+        return addHeapObject(ret);
+    };
+    imports.wbg.__wbg_next_526fc47e980da008 = function(arg0) {
+        const ret = getObject(arg0).next;
+        return addHeapObject(ret);
+    };
+    imports.wbg.__wbg_next_ddb3312ca1c4e32a = function() { return handleError(function (arg0) {
+        const ret = getObject(arg0).next();
+        return addHeapObject(ret);
+    }, arguments) };
+    imports.wbg.__wbg_done_5c1f01fb660d73b5 = function(arg0) {
+        const ret = getObject(arg0).done;
+        return ret;
+    };
+    imports.wbg.__wbg_value_1695675138684bd5 = function(arg0) {
+        const ret = getObject(arg0).value;
+        return addHeapObject(ret);
+    };
+    imports.wbg.__wbg_iterator_97f0c81209c6c35a = function() {
+        const ret = Symbol.iterator;
+        return addHeapObject(ret);
+    };
+    imports.wbg.__wbg_get_97b561fb56f034b5 = function() { return handleError(function (arg0, arg1) {
+        const ret = Reflect.get(getObject(arg0), getObject(arg1));
+        return addHeapObject(ret);
+    }, arguments) };
+    imports.wbg.__wbg_call_cb65541d95d71282 = function() { return handleError(function (arg0, arg1) {
+        const ret = getObject(arg0).call(getObject(arg1));
+        return addHeapObject(ret);
+    }, arguments) };
+    imports.wbg.__wbg_new_b51585de1b234aff = function() {
+        const ret = new Object();
+        return addHeapObject(ret);
+    };
+    imports.wbg.__wbg_self_1ff1d729e9aae938 = function() { return handleError(function () {
+        const ret = self.self;
+        return addHeapObject(ret);
+    }, arguments) };
+    imports.wbg.__wbg_window_5f4faef6c12b79ec = function() { return handleError(function () {
+        const ret = window.window;
+        return addHeapObject(ret);
+    }, arguments) };
+    imports.wbg.__wbg_globalThis_1d39714405582d3c = function() { return handleError(function () {
+        const ret = globalThis.globalThis;
+        return addHeapObject(ret);
+    }, arguments) };
+    imports.wbg.__wbg_global_651f05c6a0944d1c = function() { return handleError(function () {
+        const ret = global.global;
+        return addHeapObject(ret);
+    }, arguments) };
+    imports.wbg.__wbg_set_502d29070ea18557 = function(arg0, arg1, arg2) {
+        getObject(arg0)[arg1 >>> 0] = takeObject(arg2);
+    };
+    imports.wbg.__wbg_isArray_4c24b343cb13cfb1 = function(arg0) {
+        const ret = Array.isArray(getObject(arg0));
+        return ret;
+    };
+    imports.wbg.__wbg_instanceof_ArrayBuffer_39ac22089b74fddb = function(arg0) {
+        let result;
+        try {
+            result = getObject(arg0) instanceof ArrayBuffer;
+        } catch {
+            result = false;
+        }
+        const ret = result;
+        return ret;
+    };
+    imports.wbg.__wbg_call_01734de55d61e11d = function() { return handleError(function (arg0, arg1, arg2) {
+        const ret = getObject(arg0).call(getObject(arg1), getObject(arg2));
+        return addHeapObject(ret);
+    }, arguments) };
+    imports.wbg.__wbg_buffer_085ec1f694018c4f = function(arg0) {
+        const ret = getObject(arg0).buffer;
+        return addHeapObject(ret);
+    };
+    imports.wbg.__wbg_newwithbyteoffsetandlength_6da8e527659b86aa = function(arg0, arg1, arg2) {
+        const ret = new Uint8Array(getObject(arg0), arg1 >>> 0, arg2 >>> 0);
+        return addHeapObject(ret);
+    };
+    imports.wbg.__wbg_new_8125e318e6245eed = function(arg0) {
+        const ret = new Uint8Array(getObject(arg0));
+        return addHeapObject(ret);
+    };
+    imports.wbg.__wbg_set_5cf90238115182c3 = function(arg0, arg1, arg2) {
+        getObject(arg0).set(getObject(arg1), arg2 >>> 0);
+    };
+    imports.wbg.__wbg_length_72e2208bbc0efc61 = function(arg0) {
+        const ret = getObject(arg0).length;
+        return ret;
+    };
+    imports.wbg.__wbg_instanceof_Uint8Array_d8d9cb2b8e8ac1d4 = function(arg0) {
+        let result;
+        try {
+            result = getObject(arg0) instanceof Uint8Array;
+        } catch {
+            result = false;
+        }
+        const ret = result;
+        return ret;
+    };
+    imports.wbg.__wbg_newwithlength_e5d69174d6984cd7 = function(arg0) {
+        const ret = new Uint8Array(arg0 >>> 0);
+        return addHeapObject(ret);
+    };
+    imports.wbg.__wbg_subarray_13db269f57aa838d = function(arg0, arg1, arg2) {
+        const ret = getObject(arg0).subarray(arg1 >>> 0, arg2 >>> 0);
+        return addHeapObject(ret);
+    };
+    imports.wbg.__wbindgen_debug_string = function(arg0, arg1) {
+        const ret = debugString(getObject(arg1));
+        const ptr1 = passStringToWasm0(ret, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
+        const len1 = WASM_VECTOR_LEN;
+        getInt32Memory0()[arg0 / 4 + 1] = len1;
+        getInt32Memory0()[arg0 / 4 + 0] = ptr1;
+    };
+    imports.wbg.__wbindgen_throw = function(arg0, arg1) {
+        throw new Error(getStringFromWasm0(arg0, arg1));
+    };
+    imports.wbg.__wbindgen_memory = function() {
+        const ret = wasm.memory;
+        return addHeapObject(ret);
+    };
+
+    return imports;
+}
+
+function __wbg_init_memory(imports, maybe_memory) {
+
+}
+
+function __wbg_finalize_init(instance, module) {
+    wasm = instance.exports;
+    __wbg_init.__wbindgen_wasm_module = module;
+    cachedFloat64Memory0 = null;
+    cachedInt32Memory0 = null;
+    cachedUint8Memory0 = null;
+
+    wasm.__wbindgen_start();
+    return wasm;
+}
+
+function initSync(module) {
+    if (wasm !== undefined) return wasm;
+
+    const imports = __wbg_get_imports();
+
+    __wbg_init_memory(imports);
+
+    if (!(module instanceof WebAssembly.Module)) {
+        module = new WebAssembly.Module(module);
+    }
+
+    const instance = new WebAssembly.Instance(module, imports);
+
+    return __wbg_finalize_init(instance, module);
+}
+
+async function __wbg_init(input) {
+    if (wasm !== undefined) return wasm;
+
+    if (typeof input === 'undefined') {
+        input = new URL('m_bg.wasm', import.meta.url);
+    }
+    const imports = __wbg_get_imports();
+
+    if (typeof input === 'string' || (typeof Request === 'function' && input instanceof Request) || (typeof URL === 'function' && input instanceof URL)) {
+        input = fetch(input);
+    }
+
+    __wbg_init_memory(imports);
+
+    const { instance, module } = await __wbg_load(await input, imports);
+
+    return __wbg_finalize_init(instance, module);
+}
+
+export { initSync }
+export default __wbg_init;

build/m_bg.wasm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5717d073fa2a2774df57e257617a7fd5ed71f6793bcda874ee5f2a6c8fc52154
+size 3754562

build/m_bg.wasm.d.ts

@@ -0,0 +1,13 @@
+/* tslint:disable */
+/* eslint-disable */
+export const memory: WebAssembly.Memory;
+export function __wbg_model_free(a: number): void;
+export function model_load(a: number, b: number, c: number, d: number, e: number, f: number, g: number): void;
+export function model_get_embeddings(a: number, b: number, c: number): void;
+export function main(a: number, b: number): number;
+export function __wbindgen_malloc(a: number, b: number): number;
+export function __wbindgen_realloc(a: number, b: number, c: number, d: number): number;
+export function __wbindgen_add_to_stack_pointer(a: number): number;
+export function __wbindgen_free(a: number, b: number, c: number): void;
+export function __wbindgen_exn_store(a: number): void;
+export function __wbindgen_start(): void;

index.html

@@ -1,19 +1,364 @@
+<html>
+  <head>
+    <meta content="text/html;charset=utf-8" http-equiv="Content-Type" />
+    <title>Candle Bert</title>
+  </head>
+  <body></body>
+</html>
+
 <!DOCTYPE html>
 <html>
-	<head>
-		<meta charset="utf-8" />
-		<meta name="viewport" content="width=device-width" />
-		<title>My static Space</title>
-		<link rel="stylesheet" href="style.css" />
-	</head>
-	<body>
-		<div class="card">
-			<h1>Welcome to your static Space!</h1>
-			<p>You can modify this app directly by editing <i>index.html</i> in the Files and versions tab.</p>
-			<p>
-				Also don't forget to check the
-				<a href="https://huggingface.co/docs/hub/spaces" target="_blank">Spaces documentation</a>.
-			</p>
-		</div>
-	</body>
+  <head>
+    <meta charset="UTF-8" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+    <style>
+      @import url("https://fonts.googleapis.com/css2?family=Source+Code+Pro:wght@200;300;400&family=Source+Sans+3:wght@100;200;300;400;500;600;700;800;900&display=swap");
+      html,
+      body {
+        font-family: "Source Sans 3", sans-serif;
+      }
+    </style>
+    <script src="https://cdn.tailwindcss.com"></script>
+    <script type="module" src="./code.js"></script>
+    <script type="module">
+      import { hcl } from "https://cdn.skypack.dev/d3-color@3";
+      import { interpolateReds } from "https://cdn.skypack.dev/d3-scale-chromatic@3";
+      import { scaleLinear } from "https://cdn.skypack.dev/d3-scale@4";
+      import {
+        getModelInfo,
+        getEmbeddings,
+        getWikiText,
+        cosineSimilarity,
+      } from "./utils.js";
+
+      const bertWorker = new Worker("./bertWorker.js", {
+        type: "module",
+      });
+
+      const inputContainerEL = document.querySelector("#input-container");
+      const textAreaEl = document.querySelector("#input-area");
+      const outputAreaEl = document.querySelector("#output-area");
+      const formEl = document.querySelector("#form");
+      const searchInputEl = document.querySelector("#search-input");
+      const formWikiEl = document.querySelector("#form-wiki");
+      const searchWikiEl = document.querySelector("#search-wiki");
+      const outputStatusEl = document.querySelector("#output-status");
+      const modelSelectEl = document.querySelector("#model");
+
+      const sentencesRegex =
+        /(?<!\w\.\w.)(?<![A-Z][a-z]\.)(?<![A-Z]\.)(?<=\.|\?)\s/gm;
+
+      let sentenceEmbeddings = [];
+      let currInputText = "";
+      let isCalculating = false;
+
+      function toggleTextArea(state) {
+        if (state) {
+          textAreaEl.hidden = false;
+          textAreaEl.focus();
+        } else {
+          textAreaEl.hidden = true;
+        }
+      }
+      inputContainerEL.addEventListener("focus", (e) => {
+        toggleTextArea(true);
+      });
+      textAreaEl.addEventListener("blur", (e) => {
+        toggleTextArea(false);
+      });
+      textAreaEl.addEventListener("focusout", (e) => {
+        toggleTextArea(false);
+        if (currInputText === textAreaEl.value || isCalculating) return;
+        populateOutputArea(textAreaEl.value);
+        calculateEmbeddings(textAreaEl.value);
+      });
+
+      modelSelectEl.addEventListener("change", (e) => {
+        if (currInputText === "" || isCalculating) return;
+        populateOutputArea(textAreaEl.value);
+        calculateEmbeddings(textAreaEl.value);
+      });
+
+      function populateOutputArea(text) {
+        currInputText = text;
+        const sentences = text.split(sentencesRegex);
+
+        outputAreaEl.innerHTML = "";
+        for (const [id, sentence] of sentences.entries()) {
+          const sentenceEl = document.createElement("span");
+          sentenceEl.id = `sentence-${id}`;
+          sentenceEl.innerText = sentence + " ";
+          outputAreaEl.appendChild(sentenceEl);
+        }
+      }
+      formEl.addEventListener("submit", async (e) => {
+        e.preventDefault();
+        if (isCalculating || currInputText === "") return;
+        toggleInputs(true);
+        const modelID = modelSelectEl.value;
+        const { modelURL, tokenizerURL, configURL, search_prefix } =
+          getModelInfo(modelID);
+
+        const text = searchInputEl.value;
+        const query = search_prefix + searchInputEl.value;
+        outputStatusEl.classList.remove("invisible");
+        outputStatusEl.innerText = "Calculating embeddings for query...";
+        isCalculating = true;
+        const out = await getEmbeddings(
+          bertWorker,
+          modelURL,
+          tokenizerURL,
+          configURL,
+          modelID,
+          [query]
+        );
+        outputStatusEl.classList.add("invisible");
+        const queryEmbeddings = out.output[0];
+        // calculate cosine similarity with all sentences given the query
+        const distances = sentenceEmbeddings
+          .map((embedding, id) => ({
+            id,
+            similarity: cosineSimilarity(queryEmbeddings, embedding),
+          }))
+          .sort((a, b) => b.similarity - a.similarity)
+          // getting top 10 most similar sentences
+          .slice(0, 10);
+
+        const colorScale = scaleLinear()
+          .domain([
+            distances[distances.length - 1].similarity,
+            distances[0].similarity,
+          ])
+          .range([0, 1])
+          .interpolate(() => interpolateReds);
+        outputAreaEl.querySelectorAll("span").forEach((el) => {
+          el.style.color = "unset";
+          el.style.backgroundColor = "unset";
+        });
+        distances.forEach((d) => {
+          const el = outputAreaEl.querySelector(`#sentence-${d.id}`);
+          const color = colorScale(d.similarity);
+          const fontColor = hcl(color).l < 70 ? "white" : "black";
+          el.style.color = fontColor;
+          el.style.backgroundColor = color;
+        });
+
+        outputAreaEl
+          .querySelector(`#sentence-${distances[0].id}`)
+          .scrollIntoView({
+            behavior: "smooth",
+            block: "center",
+            inline: "nearest",
+          });
+
+        isCalculating = false;
+        toggleInputs(false);
+      });
+      async function calculateEmbeddings(text) {
+        isCalculating = true;
+        toggleInputs(true);
+        const modelID = modelSelectEl.value;
+        const { modelURL, tokenizerURL, configURL, document_prefix } =
+          getModelInfo(modelID);
+
+        const sentences = text.split(sentencesRegex);
+        const allEmbeddings = [];
+        outputStatusEl.classList.remove("invisible");
+        for (const [id, sentence] of sentences.entries()) {
+          const query = document_prefix + sentence;
+          outputStatusEl.innerText = `Calculating embeddings: sentence ${
+            id + 1
+          } of ${sentences.length}`;
+          const embeddings = await getEmbeddings(
+            bertWorker,
+            modelURL,
+            tokenizerURL,
+            configURL,
+            modelID,
+            [query]
+          );
+          allEmbeddings.push(embeddings);
+        }
+        outputStatusEl.classList.add("invisible");
+        sentenceEmbeddings = allEmbeddings.map((e) => e.output[0]);
+        isCalculating = false;
+        toggleInputs(false);
+      }
+
+      function updateStatus(data) {
+        if ("status" in data) {
+          outputStatusEl.innerText = data.message;
+          outputStatusEl.classList.remove("invisible");
+        }
+      }
+      function toggleInputs(state) {
+        const interactive = document.querySelectorAll(".interactive");
+        interactive.forEach((el) => {
+          if (state) {
+            el.disabled = true;
+          } else {
+            el.disabled = false;
+          }
+        });
+      }
+
+      searchWikiEl.addEventListener("input", () => {
+        searchWikiEl.setCustomValidity("");
+      });
+
+      formWikiEl.addEventListener("submit", async (e) => {
+        e.preventDefault();
+        if ("example" in e.submitter.dataset) {
+          searchWikiEl.value = e.submitter.innerText;
+        }
+        const text = searchWikiEl.value;
+
+        if (isCalculating || text === "") return;
+        try {
+          const wikiText = await getWikiText(text);
+          searchWikiEl.setCustomValidity("");
+          textAreaEl.innerHTML = wikiText;
+          populateOutputArea(wikiText);
+          calculateEmbeddings(wikiText);
+          searchWikiEl.value = "";
+        } catch {
+          searchWikiEl.setCustomValidity("Invalid Wikipedia article name");
+          searchWikiEl.reportValidity();
+        }
+      });
+    </script>
+  </head>
+  <body class="container max-w-4xl mx-auto p-4">
+    <main class="grid grid-cols-1 gap-8 relative">
+      <span class="absolute text-5xl -ml-[1em]"> 🕯️ </span>
+      <div>
+        <h1 class="text-5xl font-bold">Candle BERT</h1>
+        <h2 class="text-2xl font-bold">Rust/WASM Demo</h2>
+        <p class="max-w-lg">
+          Running sentence embeddings and similarity search in the browser using
+          the Bert Model written with
+          <a
+            href="https://github.com/huggingface/candle/"
+            target="_blank"
+            class="underline hover:text-blue-500 hover:no-underline"
+            >Candle
+          </a>
+          and compiled to Wasm. Embeddings models from are from
+          <a
+            href="https://huggingface.co/sentence-transformers/"
+            target="_blank"
+            class="underline hover:text-blue-500 hover:no-underline"
+          >
+            Sentence Transformers
+          </a>
+          and
+          <a
+            href="https://huggingface.co/intfloat/"
+            target="_blank"
+            class="underline hover:text-blue-500 hover:no-underline"
+          >
+            Liang Wang - e5 Models
+          </a>
+        </p>
+      </div>
+
+      <div>
+        <label for="model" class="font-medium">Models Options: </label>
+        <select
+          id="model"
+          class="border-2 border-gray-500 rounded-md font-light interactive disabled:cursor-not-allowed w-full max-w-max"
+        >
+          <option value="intfloat_e5_small_v2" selected>
+            intfloat/e5-small-v2 (133 MB)
+          </option>
+          <option value="intfloat_e5_base_v2">
+            intfloat/e5-base-v2 (438 MB)
+          </option>
+          <option value="intfloat_multilingual_e5_small">
+            intfloat/multilingual-e5-small (471 MB)
+          </option>
+          <option value="sentence_transformers_all_MiniLM_L6_v2">
+            sentence-transformers/all-MiniLM-L6-v2 (90.9 MB)
+          </option>
+          <option value="sentence_transformers_all_MiniLM_L12_v2">
+            sentence-transformers/all-MiniLM-L12-v2 (133 MB)
+          </option>
+        </select>
+      </div>
+      <form
+        id="form"
+        class="flex text-normal px-1 py-1 border border-gray-700 rounded-md items-center"
+      >
+        <input type="submit" hidden />
+        <input
+          type="text"
+          id="search-input"
+          class="font-light w-full px-3 py-2 mx-1 resize-none outline-none interactive disabled:cursor-not-allowed"
+          placeholder="Search query here..."
+        />
+        <button
+          class="bg-gray-700 hover:bg-gray-800 text-white font-normal py-2 w-16 rounded disabled:bg-gray-300 disabled:cursor-not-allowed interactive"
+        >
+          Search
+        </button>
+      </form>
+      <div>
+        <h3 class="font-medium">Input text:</h3>
+        <div class="flex justify-between items-center">
+          <div class="rounded-md inline text-xs">
+            <span id="output-status" class="m-auto font-light invisible"
+              >C</span
+            >
+          </div>
+        </div>
+        <div
+          id="input-container"
+          tabindex="0"
+          class="min-h-[250px] bg-slate-100 text-gray-500 rounded-md p-4 flex flex-col gap-2 relative"
+        >
+          <textarea
+            id="input-area"
+            hidden
+            value=""
+            placeholder="Input text to perform semantic similarity search..."
+            class="flex-1 resize-none outline-none left-0 right-0 top-0 bottom-0 m-4 absolute interactive disabled:invisible"
+          ></textarea>
+          <p id="output-area" class="grid-rows-2">
+            Input text to perform semantic similarity search...
+          </p>
+        </div>
+      </div>
+      <div>
+        <h3 class="font-medium">Examples</h3>
+
+        <form
+          id="form-wiki"
+          class="flex text-xs rounded-md items-center w-min gap-3"
+        >
+          <input type="submit" hidden />
+
+          <button data-example class="disabled:cursor-not-allowed interactive">
+            Pizza
+          </button>
+          <button data-example class="disabled:cursor-not-allowed interactive">
+            Paris
+          </button>
+          <button data-example class="disabled:cursor-not-allowed interactive">
+            Physics
+          </button>
+          <input
+            type="text"
+            id="search-wiki"
+            class="font-light py-0 mx-1 resize-none outline-none w-32 disabled:cursor-not-allowed interactive"
+            placeholder="search Wikipedia article..."
+          />
+          <button
+            class="bg-gray-700 hover:bg-gray-800 text-white font-normal py-2 w-16 rounded disabled:bg-gray-300 disabled:cursor-not-allowed interactive"
+          >
+            Enter
+          </button>
+        </form>
+      </div>
+    </main>
+  </body>
 </html>

utils.js

@@ -0,0 +1,99 @@
+export async function getEmbeddings(
+  worker,
+  weightsURL,
+  tokenizerURL,
+  configURL,
+  modelID,
+  sentences,
+  updateStatus = null
+) {
+  return new Promise((resolve, reject) => {
+    worker.postMessage({
+      weightsURL,
+      tokenizerURL,
+      configURL,
+      modelID,
+      sentences,
+    });
+    function messageHandler(event) {
+      if ("error" in event.data) {
+        worker.removeEventListener("message", messageHandler);
+        reject(new Error(event.data.error));
+      }
+      if (event.data.status === "complete") {
+        worker.removeEventListener("message", messageHandler);
+        resolve(event.data);
+      }
+      if (updateStatus) updateStatus(event.data);
+    }
+    worker.addEventListener("message", messageHandler);
+  });
+}
+
+const MODELS = {
+  intfloat_e5_small_v2: {
+    base_url: "https://huggingface.co/intfloat/e5-small-v2/resolve/main/",
+    search_prefix: "query: ",
+    document_prefix: "passage: ",
+  },
+  intfloat_e5_base_v2: {
+    base_url: "https://huggingface.co/intfloat/e5-base-v2/resolve/main/",
+    search_prefix: "query: ",
+    document_prefix: "passage:",
+  },
+  intfloat_multilingual_e5_small: {
+    base_url:
+      "https://huggingface.co/intfloat/multilingual-e5-small/resolve/main/",
+    search_prefix: "query: ",
+    document_prefix: "passage: ",
+  },
+  sentence_transformers_all_MiniLM_L6_v2: {
+    base_url:
+      "https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2/resolve/refs%2Fpr%2F21/",
+    search_prefix: "",
+    document_prefix: "",
+  },
+  sentence_transformers_all_MiniLM_L12_v2: {
+    base_url:
+      "https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2/resolve/refs%2Fpr%2F4/",
+    search_prefix: "",
+    document_prefix: "",
+  },
+};
+export function getModelInfo(id) {
+  return {
+    modelURL: MODELS[id].base_url + "model.safetensors",
+    configURL: MODELS[id].base_url + "config.json",
+    tokenizerURL: MODELS[id].base_url + "tokenizer.json",
+    search_prefix: MODELS[id].search_prefix,
+    document_prefix: MODELS[id].document_prefix,
+  };
+}
+
+export function cosineSimilarity(vec1, vec2) {
+  const dot = vec1.reduce((acc, val, i) => acc + val * vec2[i], 0);
+  const a = Math.sqrt(vec1.reduce((acc, val) => acc + val * val, 0));
+  const b = Math.sqrt(vec2.reduce((acc, val) => acc + val * val, 0));
+  return dot / (a * b);
+}
+export async function getWikiText(article) {
+  // thanks to wikipedia for the API
+  const URL = `https://en.wikipedia.org/w/api.php?action=query&prop=extracts&exlimit=1&titles=${article}&explaintext=1&exsectionformat=plain&format=json&origin=*`;
+  return fetch(URL, {
+    method: "GET",
+    headers: {
+      Accept: "application/json",
+    },
+  })
+    .then((r) => r.json())
+    .then((data) => {
+      const pages = data.query.pages;
+      const pageId = Object.keys(pages)[0];
+      const extract = pages[pageId].extract;
+      if (extract === undefined || extract === "") {
+        throw new Error("No article found");
+      }
+      return extract;
+    })
+    .catch((error) => console.error("Error:", error));
+}