fix(ci): commit the prebuilt wasm pkg + build before test:bun (green CI on fresh clone)

The Phase-0 CI was red on all three runtimes: `src/embeddings/wasm/pkg/` (the
wasm-pack output the dynamic `import('./pkg/candle_embeddings.js')` resolves) was
gitignored + untracked, so tsc failed to resolve it on a fresh clone (TS2307), and
the Bun job ran test:bun without building dist first.

Fixes:
- Track the 3.1 MB prebuilt pkg (candle_embeddings.js/.d.ts + _bg.wasm/.d.ts). It
  ships in the npm tarball anyway; versioning it lets consumers + CI build without
  a Rust/wasm-pack toolchain and makes the shipped artifact reproducible (closes
  the "publish ships whatever the maintainer last built" supply-chain gap). The
  top-level .gitignore intended this (`!*.wasm` etc.) but excluded the whole dir,
  so the re-includes were dead, and a nested wasm-pack `.gitignore *` also masked
  it — force-added past both.
- CI Bun job: `npm run build` before `test:bun` (it imports the built dist/).

Verified against a tracked-files-only tree (fresh-clone sim): typecheck 0, build 0,
test:bun 8/8.

.github/workflows/ci.yml

@@ -34,5 +34,7 @@ jobs:
         with:
           bun-version: latest
       - run: npm ci
+      # test:bun imports the built dist/, so build first.
+      - run: npm run build
       # Bun as a runtime is the supported Bun story (`bun add` / `bun run`).
       - run: npm run test:bun

.gitignore

@@ -93,9 +93,14 @@ docs/internal/
 # Rust/Cargo build artifacts
 src/embeddings/candle-wasm/target/
 src/embeddings/candle-wasm/Cargo.lock
-src/embeddings/wasm/pkg/
 
-# But keep the pre-built WASM (committed for users without Rust)
+# Ignore the wasm-pack output dir's CONTENTS (note the `/*`, not `/`, so the
+# re-includes below can take effect — git cannot re-include a file whose parent
+# DIRECTORY is excluded). Keep the pre-built WASM committed: it ships in the npm
+# package anyway, it lets consumers + CI build without a Rust/wasm-pack toolchain,
+# and versioning it makes the shipped artifact reproducible (not "whatever the
+# maintainer last built").
+src/embeddings/wasm/pkg/*
 !src/embeddings/wasm/pkg/*.wasm
 !src/embeddings/wasm/pkg/*.js
 !src/embeddings/wasm/pkg/*.d.ts

src/embeddings/wasm/pkg/candle_embeddings.d.ts

@@ -0,0 +1,100 @@
+/* tslint:disable */
+/* eslint-disable */
+
+/**
+ * WASM-compatible embedding engine
+ */
+export class EmbeddingEngine {
+    free(): void;
+    [Symbol.dispose](): void;
+    /**
+     * Get the embedding dimension (384 for all-MiniLM-L6-v2)
+     */
+    dimension(): number;
+    /**
+     * Generate embedding for a single text
+     *
+     * Returns a Float32Array of 384 dimensions
+     */
+    embed(text: string): Float32Array;
+    /**
+     * Generate embeddings for multiple texts
+     *
+     * Takes a JavaScript Array of strings
+     * Returns a JavaScript Array of Float32Array
+     */
+    embed_batch(texts: Array<any>): Array<any>;
+    /**
+     * Check if the engine is ready for inference
+     */
+    is_ready(): boolean;
+    /**
+     * Load the model and tokenizer from bytes
+     *
+     * This is now the ONLY way to initialize the engine.
+     * Model weights are no longer embedded in WASM for faster initialization.
+     *
+     * # Arguments
+     * * `model_bytes` - SafeTensors format model weights
+     * * `tokenizer_bytes` - tokenizer.json contents
+     * * `config_bytes` - config.json contents
+     */
+    load(model_bytes: Uint8Array, tokenizer_bytes: Uint8Array, config_bytes: Uint8Array): void;
+    /**
+     * Get the maximum sequence length
+     */
+    max_sequence_length(): number;
+    /**
+     * Create a new embedding engine instance (not loaded)
+     */
+    constructor();
+}
+
+/**
+ * Calculate cosine similarity between two embeddings
+ */
+export function cosine_similarity(a: Float32Array, b: Float32Array): number;
+
+export type InitInput = RequestInfo | URL | Response | BufferSource | WebAssembly.Module;
+
+export interface InitOutput {
+    readonly memory: WebAssembly.Memory;
+    readonly __wbg_embeddingengine_free: (a: number, b: number) => void;
+    readonly cosine_similarity: (a: number, b: number, c: number, d: number) => number;
+    readonly embeddingengine_dimension: (a: number) => number;
+    readonly embeddingengine_embed: (a: number, b: number, c: number) => [number, number, number];
+    readonly embeddingengine_embed_batch: (a: number, b: any) => [number, number, number];
+    readonly embeddingengine_is_ready: (a: number) => number;
+    readonly embeddingengine_load: (a: number, b: number, c: number, d: number, e: number, f: number, g: number) => [number, number];
+    readonly embeddingengine_max_sequence_length: (a: number) => number;
+    readonly embeddingengine_new: () => number;
+    readonly __wbindgen_malloc: (a: number, b: number) => number;
+    readonly __wbindgen_realloc: (a: number, b: number, c: number, d: number) => number;
+    readonly __wbindgen_exn_store: (a: number) => void;
+    readonly __externref_table_alloc: () => number;
+    readonly __wbindgen_externrefs: WebAssembly.Table;
+    readonly __externref_table_dealloc: (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 {{ module: SyncInitInput }} module - Passing `SyncInitInput` directly is deprecated.
+ *
+ * @returns {InitOutput}
+ */
+export function initSync(module: { module: SyncInitInput } | SyncInitInput): InitOutput;
+
+/**
+ * If `module_or_path` is {RequestInfo} or {URL}, makes a request and
+ * for everything else, calls `WebAssembly.instantiate` directly.
+ *
+ * @param {{ module_or_path: InitInput | Promise<InitInput> }} module_or_path - Passing `InitInput` directly is deprecated.
+ *
+ * @returns {Promise<InitOutput>}
+ */
+export default function __wbg_init (module_or_path?: { module_or_path: InitInput | Promise<InitInput> } | InitInput | Promise<InitInput>): Promise<InitOutput>;

src/embeddings/wasm/pkg/candle_embeddings.js

@@ -0,0 +1,525 @@
+/* @ts-self-types="./candle_embeddings.d.ts" */
+
+/**
+ * WASM-compatible embedding engine
+ */
+export class EmbeddingEngine {
+    __destroy_into_raw() {
+        const ptr = this.__wbg_ptr;
+        this.__wbg_ptr = 0;
+        EmbeddingEngineFinalization.unregister(this);
+        return ptr;
+    }
+    free() {
+        const ptr = this.__destroy_into_raw();
+        wasm.__wbg_embeddingengine_free(ptr, 0);
+    }
+    /**
+     * Get the embedding dimension (384 for all-MiniLM-L6-v2)
+     * @returns {number}
+     */
+    dimension() {
+        const ret = wasm.embeddingengine_dimension(this.__wbg_ptr);
+        return ret >>> 0;
+    }
+    /**
+     * Generate embedding for a single text
+     *
+     * Returns a Float32Array of 384 dimensions
+     * @param {string} text
+     * @returns {Float32Array}
+     */
+    embed(text) {
+        const ptr0 = passStringToWasm0(text, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
+        const len0 = WASM_VECTOR_LEN;
+        const ret = wasm.embeddingengine_embed(this.__wbg_ptr, ptr0, len0);
+        if (ret[2]) {
+            throw takeFromExternrefTable0(ret[1]);
+        }
+        return takeFromExternrefTable0(ret[0]);
+    }
+    /**
+     * Generate embeddings for multiple texts
+     *
+     * Takes a JavaScript Array of strings
+     * Returns a JavaScript Array of Float32Array
+     * @param {Array<any>} texts
+     * @returns {Array<any>}
+     */
+    embed_batch(texts) {
+        const ret = wasm.embeddingengine_embed_batch(this.__wbg_ptr, texts);
+        if (ret[2]) {
+            throw takeFromExternrefTable0(ret[1]);
+        }
+        return takeFromExternrefTable0(ret[0]);
+    }
+    /**
+     * Check if the engine is ready for inference
+     * @returns {boolean}
+     */
+    is_ready() {
+        const ret = wasm.embeddingengine_is_ready(this.__wbg_ptr);
+        return ret !== 0;
+    }
+    /**
+     * Load the model and tokenizer from bytes
+     *
+     * This is now the ONLY way to initialize the engine.
+     * Model weights are no longer embedded in WASM for faster initialization.
+     *
+     * # Arguments
+     * * `model_bytes` - SafeTensors format model weights
+     * * `tokenizer_bytes` - tokenizer.json contents
+     * * `config_bytes` - config.json contents
+     * @param {Uint8Array} model_bytes
+     * @param {Uint8Array} tokenizer_bytes
+     * @param {Uint8Array} config_bytes
+     */
+    load(model_bytes, tokenizer_bytes, config_bytes) {
+        const ptr0 = passArray8ToWasm0(model_bytes, wasm.__wbindgen_malloc);
+        const len0 = WASM_VECTOR_LEN;
+        const ptr1 = passArray8ToWasm0(tokenizer_bytes, wasm.__wbindgen_malloc);
+        const len1 = WASM_VECTOR_LEN;
+        const ptr2 = passArray8ToWasm0(config_bytes, wasm.__wbindgen_malloc);
+        const len2 = WASM_VECTOR_LEN;
+        const ret = wasm.embeddingengine_load(this.__wbg_ptr, ptr0, len0, ptr1, len1, ptr2, len2);
+        if (ret[1]) {
+            throw takeFromExternrefTable0(ret[0]);
+        }
+    }
+    /**
+     * Get the maximum sequence length
+     * @returns {number}
+     */
+    max_sequence_length() {
+        const ret = wasm.embeddingengine_max_sequence_length(this.__wbg_ptr);
+        return ret >>> 0;
+    }
+    /**
+     * Create a new embedding engine instance (not loaded)
+     */
+    constructor() {
+        const ret = wasm.embeddingengine_new();
+        this.__wbg_ptr = ret >>> 0;
+        EmbeddingEngineFinalization.register(this, this.__wbg_ptr, this);
+        return this;
+    }
+}
+if (Symbol.dispose) EmbeddingEngine.prototype[Symbol.dispose] = EmbeddingEngine.prototype.free;
+
+/**
+ * Calculate cosine similarity between two embeddings
+ * @param {Float32Array} a
+ * @param {Float32Array} b
+ * @returns {number}
+ */
+export function cosine_similarity(a, b) {
+    const ptr0 = passArrayF32ToWasm0(a, wasm.__wbindgen_malloc);
+    const len0 = WASM_VECTOR_LEN;
+    const ptr1 = passArrayF32ToWasm0(b, wasm.__wbindgen_malloc);
+    const len1 = WASM_VECTOR_LEN;
+    const ret = wasm.cosine_similarity(ptr0, len0, ptr1, len1);
+    return ret;
+}
+
+function __wbg_get_imports() {
+    const import0 = {
+        __proto__: null,
+        __wbg___wbindgen_is_function_0095a73b8b156f76: function(arg0) {
+            const ret = typeof(arg0) === 'function';
+            return ret;
+        },
+        __wbg___wbindgen_is_object_5ae8e5880f2c1fbd: function(arg0) {
+            const val = arg0;
+            const ret = typeof(val) === 'object' && val !== null;
+            return ret;
+        },
+        __wbg___wbindgen_is_string_cd444516edc5b180: function(arg0) {
+            const ret = typeof(arg0) === 'string';
+            return ret;
+        },
+        __wbg___wbindgen_is_undefined_9e4d92534c42d778: function(arg0) {
+            const ret = arg0 === undefined;
+            return ret;
+        },
+        __wbg___wbindgen_string_get_72fb696202c56729: function(arg0, arg1) {
+            const obj = 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;
+            getDataViewMemory0().setInt32(arg0 + 4 * 1, len1, true);
+            getDataViewMemory0().setInt32(arg0 + 4 * 0, ptr1, true);
+        },
+        __wbg___wbindgen_throw_be289d5034ed271b: function(arg0, arg1) {
+            throw new Error(getStringFromWasm0(arg0, arg1));
+        },
+        __wbg_call_389efe28435a9388: function() { return handleError(function (arg0, arg1) {
+            const ret = arg0.call(arg1);
+            return ret;
+        }, arguments); },
+        __wbg_call_4708e0c13bdc8e95: function() { return handleError(function (arg0, arg1, arg2) {
+            const ret = arg0.call(arg1, arg2);
+            return ret;
+        }, arguments); },
+        __wbg_crypto_86f2631e91b51511: function(arg0) {
+            const ret = arg0.crypto;
+            return ret;
+        },
+        __wbg_getRandomValues_b3f15fcbfabb0f8b: function() { return handleError(function (arg0, arg1) {
+            arg0.getRandomValues(arg1);
+        }, arguments); },
+        __wbg_get_9b94d73e6221f75c: function(arg0, arg1) {
+            const ret = arg0[arg1 >>> 0];
+            return ret;
+        },
+        __wbg_length_32ed9a279acd054c: function(arg0) {
+            const ret = arg0.length;
+            return ret;
+        },
+        __wbg_length_35a7bace40f36eac: function(arg0) {
+            const ret = arg0.length;
+            return ret;
+        },
+        __wbg_length_9a7876c9728a0979: function(arg0) {
+            const ret = arg0.length;
+            return ret;
+        },
+        __wbg_msCrypto_d562bbe83e0d4b91: function(arg0) {
+            const ret = arg0.msCrypto;
+            return ret;
+        },
+        __wbg_new_3eb36ae241fe6f44: function() {
+            const ret = new Array();
+            return ret;
+        },
+        __wbg_new_no_args_1c7c842f08d00ebb: function(arg0, arg1) {
+            const ret = new Function(getStringFromWasm0(arg0, arg1));
+            return ret;
+        },
+        __wbg_new_with_length_1763c527b2923202: function(arg0) {
+            const ret = new Array(arg0 >>> 0);
+            return ret;
+        },
+        __wbg_new_with_length_63f2683cc2521026: function(arg0) {
+            const ret = new Float32Array(arg0 >>> 0);
+            return ret;
+        },
+        __wbg_new_with_length_a2c39cbe88fd8ff1: function(arg0) {
+            const ret = new Uint8Array(arg0 >>> 0);
+            return ret;
+        },
+        __wbg_node_e1f24f89a7336c2e: function(arg0) {
+            const ret = arg0.node;
+            return ret;
+        },
+        __wbg_process_3975fd6c72f520aa: function(arg0) {
+            const ret = arg0.process;
+            return ret;
+        },
+        __wbg_prototypesetcall_bdcdcc5842e4d77d: function(arg0, arg1, arg2) {
+            Uint8Array.prototype.set.call(getArrayU8FromWasm0(arg0, arg1), arg2);
+        },
+        __wbg_randomFillSync_f8c153b79f285817: function() { return handleError(function (arg0, arg1) {
+            arg0.randomFillSync(arg1);
+        }, arguments); },
+        __wbg_require_b74f47fc2d022fd6: function() { return handleError(function () {
+            const ret = module.require;
+            return ret;
+        }, arguments); },
+        __wbg_set_f43e577aea94465b: function(arg0, arg1, arg2) {
+            arg0[arg1 >>> 0] = arg2;
+        },
+        __wbg_set_f8edeec46569cc70: function(arg0, arg1, arg2) {
+            arg0.set(getArrayF32FromWasm0(arg1, arg2));
+        },
+        __wbg_static_accessor_GLOBAL_12837167ad935116: function() {
+            const ret = typeof global === 'undefined' ? null : global;
+            return isLikeNone(ret) ? 0 : addToExternrefTable0(ret);
+        },
+        __wbg_static_accessor_GLOBAL_THIS_e628e89ab3b1c95f: function() {
+            const ret = typeof globalThis === 'undefined' ? null : globalThis;
+            return isLikeNone(ret) ? 0 : addToExternrefTable0(ret);
+        },
+        __wbg_static_accessor_SELF_a621d3dfbb60d0ce: function() {
+            const ret = typeof self === 'undefined' ? null : self;
+            return isLikeNone(ret) ? 0 : addToExternrefTable0(ret);
+        },
+        __wbg_static_accessor_WINDOW_f8727f0cf888e0bd: function() {
+            const ret = typeof window === 'undefined' ? null : window;
+            return isLikeNone(ret) ? 0 : addToExternrefTable0(ret);
+        },
+        __wbg_subarray_a96e1fef17ed23cb: function(arg0, arg1, arg2) {
+            const ret = arg0.subarray(arg1 >>> 0, arg2 >>> 0);
+            return ret;
+        },
+        __wbg_versions_4e31226f5e8dc909: function(arg0) {
+            const ret = arg0.versions;
+            return ret;
+        },
+        __wbindgen_cast_0000000000000001: function(arg0, arg1) {
+            // Cast intrinsic for `Ref(Slice(U8)) -> NamedExternref("Uint8Array")`.
+            const ret = getArrayU8FromWasm0(arg0, arg1);
+            return ret;
+        },
+        __wbindgen_cast_0000000000000002: function(arg0, arg1) {
+            // Cast intrinsic for `Ref(String) -> Externref`.
+            const ret = getStringFromWasm0(arg0, arg1);
+            return ret;
+        },
+        __wbindgen_init_externref_table: function() {
+            const table = wasm.__wbindgen_externrefs;
+            const offset = table.grow(4);
+            table.set(0, undefined);
+            table.set(offset + 0, undefined);
+            table.set(offset + 1, null);
+            table.set(offset + 2, true);
+            table.set(offset + 3, false);
+        },
+    };
+    return {
+        __proto__: null,
+        "./candle_embeddings_bg.js": import0,
+    };
+}
+
+const EmbeddingEngineFinalization = (typeof FinalizationRegistry === 'undefined')
+    ? { register: () => {}, unregister: () => {} }
+    : new FinalizationRegistry(ptr => wasm.__wbg_embeddingengine_free(ptr >>> 0, 1));
+
+function addToExternrefTable0(obj) {
+    const idx = wasm.__externref_table_alloc();
+    wasm.__wbindgen_externrefs.set(idx, obj);
+    return idx;
+}
+
+function getArrayF32FromWasm0(ptr, len) {
+    ptr = ptr >>> 0;
+    return getFloat32ArrayMemory0().subarray(ptr / 4, ptr / 4 + len);
+}
+
+function getArrayU8FromWasm0(ptr, len) {
+    ptr = ptr >>> 0;
+    return getUint8ArrayMemory0().subarray(ptr / 1, ptr / 1 + len);
+}
+
+let cachedDataViewMemory0 = null;
+function getDataViewMemory0() {
+    if (cachedDataViewMemory0 === null || cachedDataViewMemory0.buffer.detached === true || (cachedDataViewMemory0.buffer.detached === undefined && cachedDataViewMemory0.buffer !== wasm.memory.buffer)) {
+        cachedDataViewMemory0 = new DataView(wasm.memory.buffer);
+    }
+    return cachedDataViewMemory0;
+}
+
+let cachedFloat32ArrayMemory0 = null;
+function getFloat32ArrayMemory0() {
+    if (cachedFloat32ArrayMemory0 === null || cachedFloat32ArrayMemory0.byteLength === 0) {
+        cachedFloat32ArrayMemory0 = new Float32Array(wasm.memory.buffer);
+    }
+    return cachedFloat32ArrayMemory0;
+}
+
+function getStringFromWasm0(ptr, len) {
+    ptr = ptr >>> 0;
+    return decodeText(ptr, len);
+}
+
+let cachedUint8ArrayMemory0 = null;
+function getUint8ArrayMemory0() {
+    if (cachedUint8ArrayMemory0 === null || cachedUint8ArrayMemory0.byteLength === 0) {
+        cachedUint8ArrayMemory0 = new Uint8Array(wasm.memory.buffer);
+    }
+    return cachedUint8ArrayMemory0;
+}
+
+function handleError(f, args) {
+    try {
+        return f.apply(this, args);
+    } catch (e) {
+        const idx = addToExternrefTable0(e);
+        wasm.__wbindgen_exn_store(idx);
+    }
+}
+
+function isLikeNone(x) {
+    return x === undefined || x === null;
+}
+
+function passArray8ToWasm0(arg, malloc) {
+    const ptr = malloc(arg.length * 1, 1) >>> 0;
+    getUint8ArrayMemory0().set(arg, ptr / 1);
+    WASM_VECTOR_LEN = arg.length;
+    return ptr;
+}
+
+function passArrayF32ToWasm0(arg, malloc) {
+    const ptr = malloc(arg.length * 4, 4) >>> 0;
+    getFloat32ArrayMemory0().set(arg, ptr / 4);
+    WASM_VECTOR_LEN = arg.length;
+    return ptr;
+}
+
+function passStringToWasm0(arg, malloc, realloc) {
+    if (realloc === undefined) {
+        const buf = cachedTextEncoder.encode(arg);
+        const ptr = malloc(buf.length, 1) >>> 0;
+        getUint8ArrayMemory0().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 = getUint8ArrayMemory0();
+
+    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 = getUint8ArrayMemory0().subarray(ptr + offset, ptr + len);
+        const ret = cachedTextEncoder.encodeInto(arg, view);
+
+        offset += ret.written;
+        ptr = realloc(ptr, len, offset, 1) >>> 0;
+    }
+
+    WASM_VECTOR_LEN = offset;
+    return ptr;
+}
+
+function takeFromExternrefTable0(idx) {
+    const value = wasm.__wbindgen_externrefs.get(idx);
+    wasm.__externref_table_dealloc(idx);
+    return value;
+}
+
+let cachedTextDecoder = new TextDecoder('utf-8', { ignoreBOM: true, fatal: true });
+cachedTextDecoder.decode();
+const MAX_SAFARI_DECODE_BYTES = 2146435072;
+let numBytesDecoded = 0;
+function decodeText(ptr, len) {
+    numBytesDecoded += len;
+    if (numBytesDecoded >= MAX_SAFARI_DECODE_BYTES) {
+        cachedTextDecoder = new TextDecoder('utf-8', { ignoreBOM: true, fatal: true });
+        cachedTextDecoder.decode();
+        numBytesDecoded = len;
+    }
+    return cachedTextDecoder.decode(getUint8ArrayMemory0().subarray(ptr, ptr + len));
+}
+
+const cachedTextEncoder = new TextEncoder();
+
+if (!('encodeInto' in cachedTextEncoder)) {
+    cachedTextEncoder.encodeInto = function (arg, view) {
+        const buf = cachedTextEncoder.encode(arg);
+        view.set(buf);
+        return {
+            read: arg.length,
+            written: buf.length
+        };
+    };
+}
+
+let WASM_VECTOR_LEN = 0;
+
+let wasmModule, wasm;
+function __wbg_finalize_init(instance, module) {
+    wasm = instance.exports;
+    wasmModule = module;
+    cachedDataViewMemory0 = null;
+    cachedFloat32ArrayMemory0 = null;
+    cachedUint8ArrayMemory0 = null;
+    wasm.__wbindgen_start();
+    return wasm;
+}
+
+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) {
+                const validResponse = module.ok && expectedResponseType(module.type);
+
+                if (validResponse && 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 expectedResponseType(type) {
+        switch (type) {
+            case 'basic': case 'cors': case 'default': return true;
+        }
+        return false;
+    }
+}
+
+function initSync(module) {
+    if (wasm !== undefined) return wasm;
+
+
+    if (module !== undefined) {
+        if (Object.getPrototypeOf(module) === Object.prototype) {
+            ({module} = module)
+        } else {
+            console.warn('using deprecated parameters for `initSync()`; pass a single object instead')
+        }
+    }
+
+    const imports = __wbg_get_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(module_or_path) {
+    if (wasm !== undefined) return wasm;
+
+
+    if (module_or_path !== undefined) {
+        if (Object.getPrototypeOf(module_or_path) === Object.prototype) {
+            ({module_or_path} = module_or_path)
+        } else {
+            console.warn('using deprecated parameters for the initialization function; pass a single object instead')
+        }
+    }
+
+    if (module_or_path === undefined) {
+        module_or_path = new URL('candle_embeddings_bg.wasm', import.meta.url);
+    }
+    const imports = __wbg_get_imports();
+
+    if (typeof module_or_path === 'string' || (typeof Request === 'function' && module_or_path instanceof Request) || (typeof URL === 'function' && module_or_path instanceof URL)) {
+        module_or_path = fetch(module_or_path);
+    }
+
+    const { instance, module } = await __wbg_load(await module_or_path, imports);
+
+    return __wbg_finalize_init(instance, module);
+}
+
+export { initSync, __wbg_init as default };

src/embeddings/wasm/pkg/candle_embeddings_bg.wasm.d.ts

@@ -0,0 +1,19 @@
+/* tslint:disable */
+/* eslint-disable */
+export const memory: WebAssembly.Memory;
+export const __wbg_embeddingengine_free: (a: number, b: number) => void;
+export const cosine_similarity: (a: number, b: number, c: number, d: number) => number;
+export const embeddingengine_dimension: (a: number) => number;
+export const embeddingengine_embed: (a: number, b: number, c: number) => [number, number, number];
+export const embeddingengine_embed_batch: (a: number, b: any) => [number, number, number];
+export const embeddingengine_is_ready: (a: number) => number;
+export const embeddingengine_load: (a: number, b: number, c: number, d: number, e: number, f: number, g: number) => [number, number];
+export const embeddingengine_max_sequence_length: (a: number) => number;
+export const embeddingengine_new: () => number;
+export const __wbindgen_malloc: (a: number, b: number) => number;
+export const __wbindgen_realloc: (a: number, b: number, c: number, d: number) => number;
+export const __wbindgen_exn_store: (a: number) => void;
+export const __externref_table_alloc: () => number;
+export const __wbindgen_externrefs: WebAssembly.Table;
+export const __externref_table_dealloc: (a: number) => void;
+export const __wbindgen_start: () => void;