restore wasm

.gitignore

@@ -93,7 +93,7 @@ out
 
 # Nuxt.js build / generate output
 .nuxt
-dist
+# dist
 
 # Gatsby files
 .cache/

app/src/tiktoken/dist/README.md

@@ -0,0 +1,134 @@
+# ⏳ tiktoken
+
+tiktoken is a [BPE](https://en.wikipedia.org/wiki/Byte_pair_encoding) tokeniser for use with
+OpenAI's models, forked from the original tiktoken library to provide NPM bindings for Node and other JS runtimes.
+
+The open source version of `tiktoken` can be installed from NPM:
+
+```
+npm install @dqbd/tiktoken
+```
+
+## Usage
+
+Basic usage follows:
+
+```typescript
+import assert from "node:assert";
+import { get_encoding, encoding_for_model } from "@dqbd/tiktoken";
+
+const enc = get_encoding("gpt2");
+assert(
+  new TextDecoder().decode(enc.decode(enc.encode("hello world"))) ===
+    "hello world"
+);
+
+// To get the tokeniser corresponding to a specific model in the OpenAI API:
+const enc = encoding_for_model("text-davinci-003");
+
+// Extend existing encoding with custom special tokens
+const enc = encoding_for_model("gpt2", {
+  "<|im_start|>": 100264,
+  "<|im_end|>": 100265,
+});
+
+// don't forget to free the encoder after it is not used
+enc.free();
+```
+
+If desired, you can create a Tiktoken instance directly with custom ranks, special tokens and regex pattern:
+
+```typescript
+import { Tiktoken } from "../pkg";
+import { readFileSync } from "fs";
+
+const encoder = new Tiktoken(
+  readFileSync("./ranks/gpt2.tiktoken").toString("utf-8"),
+  { "<|endoftext|>": 50256, "<|im_start|>": 100264, "<|im_end|>": 100265 },
+  "'s|'t|'re|'ve|'m|'ll|'d| ?\\p{L}+| ?\\p{N}+| ?[^\\s\\p{L}\\p{N}]+|\\s+(?!\\S)|\\s+"
+);
+```
+
+## Compatibility
+
+As this is a WASM library, there might be some issues with specific runtimes. If you encounter any issues, please open an issue.
+
+| Runtime             | Status | Notes                                      |
+| ------------------- | ------ | ------------------------------------------ |
+| Node.js             | ✅     |                                            |
+| Bun                 | ✅     |                                            |
+| Vite                | ✅     | See [here](#vite) for notes                |
+| Next.js             | ✅     | See [here](#nextjs) for notes              |
+| Vercel Edge Runtime | ✅     | See [here](#vercel-edge-runtime) for notes |
+| Cloudflare Workers  | 🚧     | Untested                                   |
+| Deno                | ❌     | Currently unsupported                      |
+
+### [Vite](#vite)
+
+If you are using Vite, you will need to add both the `vite-plugin-wasm` and `vite-plugin-top-level-await`. Add the following to your `vite.config.js`:
+
+```js
+import wasm from "vite-plugin-wasm";
+import topLevelAwait from "vite-plugin-top-level-await";
+import { defineConfig } from "vite";
+
+export default defineConfig({
+  plugins: [wasm(), topLevelAwait()],
+});
+```
+
+### [Next.js](#nextjs)
+
+Both API routes and `/pages` are supported with the following configuration. To overcome issues with importing Node.js version, you can import the package from `@dqbd/tiktoken/bundler` instead.
+
+```typescript
+import { get_encoding } from "@dqbd/tiktoken/bundler";
+import { NextApiRequest, NextApiResponse } from "next";
+
+export default function handler(req: NextApiRequest, res: NextApiResponse) {
+  const encoder = get_encoding("gpt2");
+  const message = encoder.encode(`Hello World ${Math.random()}`);
+  encoder.free();
+  return res.status(200).json({ message });
+}
+```
+
+Additional Webpack configuration is required.
+
+```typescript
+const config = {
+  webpack(config, { isServer, dev }) {
+    config.experiments = {
+      asyncWebAssembly: true,
+      layers: true,
+    };
+
+    return config;
+  },
+};
+```
+
+### [Vercel Edge Runtime](#vercel-edge-runtime)
+
+Vercel Edge Runtime does support WASM modules by adding a `?module` suffix. Initialize the encoder with the following snippet:
+
+```typescript
+import wasm from "@dqbd/tiktoken/tiktoken_bg.wasm?module";
+import { init, get_encoding } from "@dqbd/tiktoken/init";
+
+export const config = { runtime: "edge" };
+
+export default async function (req: Request) {
+  await init((imports) => WebAssembly.instantiate(wasm, imports));
+
+  const encoder = get_encoding("cl100k_base");
+  const tokens = encoder.encode("hello world");
+  encoder.free();
+
+  return new Response(`${encoder.encode("hello world")}`);
+}
+```
+
+## Acknowledgements
+
+- https://github.com/zurawiki/tiktoken-rs

app/src/tiktoken/dist/bundler.d.ts

@@ -0,0 +1 @@
+export * from "./tiktoken";

app/src/tiktoken/dist/bundler.js

@@ -0,0 +1 @@
+export * from "./tiktoken";

app/src/tiktoken/dist/init.d.ts

@@ -0,0 +1,8 @@
+/* tslint:disable */
+/* eslint-disable */
+export * from "./tiktoken";
+export function init(
+  callback: (
+    imports: WebAssembly.Imports
+  ) => Promise<WebAssembly.WebAssemblyInstantiatedSource | WebAssembly.Instance>
+): Promise<void>;

app/src/tiktoken/dist/init.js

@@ -0,0 +1,20 @@
+import * as imports from "./tiktoken_bg.js";
+
+export async function init(cb) {
+  const res = await cb({
+    "./tiktoken_bg.js": imports,
+  });
+
+  const instance =
+    "instance" in res && res.instance instanceof WebAssembly.Instance
+      ? res.instance
+      : res instanceof WebAssembly.Instance
+      ? res
+      : null;
+
+  if (instance == null) throw new Error("Missing instance");
+  imports.__wbg_set_wasm(instance.exports);
+  return imports;
+}
+
+export * from "./tiktoken_bg.js";

app/src/tiktoken/dist/package.json

@@ -0,0 +1,37 @@
+{
+  "name": "@dqbd/tiktoken",
+  "version": "1.0.0-alpha.1",
+  "description": "Javascript bindings for tiktoken",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/dqbd/tiktoken"
+  },
+  "dependencies": {
+    "node-fetch": "^3.3.0"
+  },
+  "files": [
+    "**/*"
+  ],
+  "main": "tiktoken.node.js",
+  "types": "tiktoken.d.ts",
+  "exports": {
+    ".": {
+      "types": "./tiktoken.d.ts",
+      "node": "./tiktoken.node.js",
+      "default": "./tiktoken.js"
+    },
+    "./bundler": {
+      "types": "./bundler.d.ts",
+      "default": "./bundler.js"
+    },
+    "./init": {
+      "types": "./init.d.ts",
+      "default": "./init.js"
+    },
+    "./tiktoken_bg.wasm": {
+      "types": "./tiktoken_bg.wasm.d.ts",
+      "default": "./tiktoken_bg.wasm"
+    }
+  }
+}

app/src/tiktoken/dist/tiktoken.d.ts

@@ -0,0 +1,108 @@
+/* tslint:disable */
+/* eslint-disable */
+
+export type TiktokenEncoding = "gpt2" | "r50k_base" | "p50k_base" | "p50k_edit" | "cl100k_base"; 
+
+/**
+ * @param {TiktokenEncoding} encoding
+ * @param {Record<string, number>} [extend_special_tokens]
+ * @returns {Tiktoken}
+ */
+export function get_encoding(encoding: TiktokenEncoding, extend_special_tokens?: Record<string, number>): Tiktoken;
+
+
+
+export type TiktokenModel =
+    | "text-davinci-003"
+    | "text-davinci-002"
+    | "text-davinci-001"
+    | "text-curie-001"
+    | "text-babbage-001"
+    | "text-ada-001"
+    | "davinci"
+    | "curie"
+    | "babbage"
+    | "ada"
+    | "code-davinci-002"
+    | "code-davinci-001"
+    | "code-cushman-002"
+    | "code-cushman-001"
+    | "davinci-codex"
+    | "cushman-codex"
+    | "text-davinci-edit-001"
+    | "code-davinci-edit-001"
+    | "text-embedding-ada-002"
+    | "text-similarity-davinci-001"
+    | "text-similarity-curie-001"
+    | "text-similarity-babbage-001"
+    | "text-similarity-ada-001"
+    | "text-search-davinci-doc-001"
+    | "text-search-curie-doc-001"
+    | "text-search-babbage-doc-001"
+    | "text-search-ada-doc-001"
+    | "code-search-babbage-code-001"
+    | "code-search-ada-code-001"
+    | "gpt2"
+    | "gpt-3.5-turbo"
+    | "gpt-3.5-turbo-0301";
+
+/**
+ * @param {TiktokenModel} encoding
+ * @param {Record<string, number>} [extend_special_tokens]
+ * @returns {Tiktoken}
+ */
+export function encoding_for_model(model: TiktokenModel, extend_special_tokens?: Record<string, number>): Tiktoken;
+
+
+/**
+*/
+export class Tiktoken {
+  free(): void;
+/**
+* @param {string} tiktoken_bfe
+* @param {any} special_tokens
+* @param {string} pat_str
+*/
+  constructor(tiktoken_bfe: string, special_tokens: Record<string, number>, pat_str: string);
+/**
+* @param {string} text
+* @param {any} allowed_special
+* @param {any} disallowed_special
+* @returns {Uint32Array}
+*/
+  encode(text: string, allowed_special?: "all" | string[], disallowed_special?: "all" | string[]): Uint32Array;
+/**
+* @param {string} text
+* @returns {Uint32Array}
+*/
+  encode_ordinary(text: string): Uint32Array;
+/**
+* @param {string} text
+* @param {any} allowed_special
+* @param {any} disallowed_special
+* @returns {any}
+*/
+  encode_with_unstable(text: string, allowed_special?: "all" | string[], disallowed_special?: "all" | string[]): any;
+/**
+* @param {Uint8Array} bytes
+* @returns {number}
+*/
+  encode_single_token(bytes: Uint8Array): number;
+/**
+* @param {Uint32Array} tokens
+* @returns {Uint8Array}
+*/
+  decode(tokens: Uint32Array): Uint8Array;
+/**
+* @param {number} token
+* @returns {Uint8Array}
+*/
+  decode_single_token_bytes(token: number): Uint8Array;
+/**
+* @returns {any}
+*/
+  token_byte_values(): Array<Array<number>>;
+/**
+*/
+  readonly name: string | undefined;
+}

app/src/tiktoken/dist/tiktoken.js

@@ -0,0 +1,4 @@
+import * as wasm from "./tiktoken_bg.wasm";
+import { __wbg_set_wasm } from "./tiktoken_bg.js";
+__wbg_set_wasm(wasm);
+export * from "./tiktoken_bg.js";

app/src/tiktoken/dist/tiktoken.node.js

@@ -0,0 +1,425 @@
+let imports = {};
+imports['./tiktoken_bg.js'] = module.exports;
+let wasm;
+const { TextEncoder, TextDecoder } = require(`util`);
+
+const heap = new Array(128).fill(undefined);
+
+heap.push(undefined, null, true, false);
+
+function getObject(idx) { return heap[idx]; }
+
+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;
+}
+
+let WASM_VECTOR_LEN = 0;
+
+let cachedUint8Memory0 = null;
+
+function getUint8Memory0() {
+    if (cachedUint8Memory0 === null || cachedUint8Memory0.byteLength === 0) {
+        cachedUint8Memory0 = new Uint8Array(wasm.memory.buffer);
+    }
+    return cachedUint8Memory0;
+}
+
+let cachedTextEncoder = new TextEncoder('utf-8');
+
+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);
+        getUint8Memory0().subarray(ptr, ptr + buf.length).set(buf);
+        WASM_VECTOR_LEN = buf.length;
+        return ptr;
+    }
+
+    let len = arg.length;
+    let ptr = malloc(len);
+
+    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);
+        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 cachedTextDecoder = new TextDecoder('utf-8', { ignoreBOM: true, fatal: true });
+
+cachedTextDecoder.decode();
+
+function getStringFromWasm0(ptr, len) {
+    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 cachedUint32Memory0 = null;
+
+function getUint32Memory0() {
+    if (cachedUint32Memory0 === null || cachedUint32Memory0.byteLength === 0) {
+        cachedUint32Memory0 = new Uint32Array(wasm.memory.buffer);
+    }
+    return cachedUint32Memory0;
+}
+
+function getArrayU32FromWasm0(ptr, len) {
+    return getUint32Memory0().subarray(ptr / 4, ptr / 4 + len);
+}
+
+function passArray8ToWasm0(arg, malloc) {
+    const ptr = malloc(arg.length * 1);
+    getUint8Memory0().set(arg, ptr / 1);
+    WASM_VECTOR_LEN = arg.length;
+    return ptr;
+}
+
+function passArray32ToWasm0(arg, malloc) {
+    const ptr = malloc(arg.length * 4);
+    getUint32Memory0().set(arg, ptr / 4);
+    WASM_VECTOR_LEN = arg.length;
+    return ptr;
+}
+
+function getArrayU8FromWasm0(ptr, len) {
+    return getUint8Memory0().subarray(ptr / 1, ptr / 1 + len);
+}
+/**
+* @param {string} encoding
+* @param {any} extend_special_tokens
+* @returns {Tiktoken}
+*/
+module.exports.get_encoding = function(encoding, extend_special_tokens) {
+    try {
+        const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+        const ptr0 = passStringToWasm0(encoding, wasm.__wbindgen_export_0, wasm.__wbindgen_export_1);
+        const len0 = WASM_VECTOR_LEN;
+        wasm.get_encoding(retptr, ptr0, len0, addHeapObject(extend_special_tokens));
+        var r0 = getInt32Memory0()[retptr / 4 + 0];
+        var r1 = getInt32Memory0()[retptr / 4 + 1];
+        var r2 = getInt32Memory0()[retptr / 4 + 2];
+        if (r2) {
+            throw takeObject(r1);
+        }
+        return Tiktoken.__wrap(r0);
+    } finally {
+        wasm.__wbindgen_add_to_stack_pointer(16);
+    }
+};
+
+/**
+* @param {string} model
+* @param {any} extend_special_tokens
+* @returns {Tiktoken}
+*/
+module.exports.encoding_for_model = function(model, extend_special_tokens) {
+    try {
+        const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+        const ptr0 = passStringToWasm0(model, wasm.__wbindgen_export_0, wasm.__wbindgen_export_1);
+        const len0 = WASM_VECTOR_LEN;
+        wasm.encoding_for_model(retptr, ptr0, len0, addHeapObject(extend_special_tokens));
+        var r0 = getInt32Memory0()[retptr / 4 + 0];
+        var r1 = getInt32Memory0()[retptr / 4 + 1];
+        var r2 = getInt32Memory0()[retptr / 4 + 2];
+        if (r2) {
+            throw takeObject(r1);
+        }
+        return Tiktoken.__wrap(r0);
+    } finally {
+        wasm.__wbindgen_add_to_stack_pointer(16);
+    }
+};
+
+function handleError(f, args) {
+    try {
+        return f.apply(this, args);
+    } catch (e) {
+        wasm.__wbindgen_export_3(addHeapObject(e));
+    }
+}
+/**
+*/
+class Tiktoken {
+
+    static __wrap(ptr) {
+        const obj = Object.create(Tiktoken.prototype);
+        obj.ptr = ptr;
+
+        return obj;
+    }
+
+    __destroy_into_raw() {
+        const ptr = this.ptr;
+        this.ptr = 0;
+
+        return ptr;
+    }
+
+    free() {
+        const ptr = this.__destroy_into_raw();
+        wasm.__wbg_tiktoken_free(ptr);
+    }
+    /**
+    * @param {string} tiktoken_bfe
+    * @param {any} special_tokens
+    * @param {string} pat_str
+    */
+    constructor(tiktoken_bfe, special_tokens, pat_str) {
+        const ptr0 = passStringToWasm0(tiktoken_bfe, wasm.__wbindgen_export_0, wasm.__wbindgen_export_1);
+        const len0 = WASM_VECTOR_LEN;
+        const ptr1 = passStringToWasm0(pat_str, wasm.__wbindgen_export_0, wasm.__wbindgen_export_1);
+        const len1 = WASM_VECTOR_LEN;
+        const ret = wasm.tiktoken_new(ptr0, len0, addHeapObject(special_tokens), ptr1, len1);
+        return Tiktoken.__wrap(ret);
+    }
+    /**
+    * @returns {string | undefined}
+    */
+    get name() {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            wasm.tiktoken_name(retptr, this.ptr);
+            var r0 = getInt32Memory0()[retptr / 4 + 0];
+            var r1 = getInt32Memory0()[retptr / 4 + 1];
+            let v0;
+            if (r0 !== 0) {
+                v0 = getStringFromWasm0(r0, r1).slice();
+                wasm.__wbindgen_export_2(r0, r1 * 1);
+            }
+            return v0;
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
+    /**
+    * @param {string} text
+    * @param {any} allowed_special
+    * @param {any} disallowed_special
+    * @returns {Uint32Array}
+    */
+    encode(text, allowed_special, disallowed_special) {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            const ptr0 = passStringToWasm0(text, wasm.__wbindgen_export_0, wasm.__wbindgen_export_1);
+            const len0 = WASM_VECTOR_LEN;
+            wasm.tiktoken_encode(retptr, this.ptr, ptr0, len0, addHeapObject(allowed_special), addHeapObject(disallowed_special));
+            var r0 = getInt32Memory0()[retptr / 4 + 0];
+            var r1 = getInt32Memory0()[retptr / 4 + 1];
+            var r2 = getInt32Memory0()[retptr / 4 + 2];
+            var r3 = getInt32Memory0()[retptr / 4 + 3];
+            if (r3) {
+                throw takeObject(r2);
+            }
+            var v1 = getArrayU32FromWasm0(r0, r1).slice();
+            wasm.__wbindgen_export_2(r0, r1 * 4);
+            return v1;
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
+    /**
+    * @param {string} text
+    * @returns {Uint32Array}
+    */
+    encode_ordinary(text) {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            const ptr0 = passStringToWasm0(text, wasm.__wbindgen_export_0, wasm.__wbindgen_export_1);
+            const len0 = WASM_VECTOR_LEN;
+            wasm.tiktoken_encode_ordinary(retptr, this.ptr, ptr0, len0);
+            var r0 = getInt32Memory0()[retptr / 4 + 0];
+            var r1 = getInt32Memory0()[retptr / 4 + 1];
+            var v1 = getArrayU32FromWasm0(r0, r1).slice();
+            wasm.__wbindgen_export_2(r0, r1 * 4);
+            return v1;
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
+    /**
+    * @param {string} text
+    * @param {any} allowed_special
+    * @param {any} disallowed_special
+    * @returns {any}
+    */
+    encode_with_unstable(text, allowed_special, disallowed_special) {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            const ptr0 = passStringToWasm0(text, wasm.__wbindgen_export_0, wasm.__wbindgen_export_1);
+            const len0 = WASM_VECTOR_LEN;
+            wasm.tiktoken_encode_with_unstable(retptr, this.ptr, ptr0, len0, addHeapObject(allowed_special), addHeapObject(disallowed_special));
+            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);
+        }
+    }
+    /**
+    * @param {Uint8Array} bytes
+    * @returns {number}
+    */
+    encode_single_token(bytes) {
+        const ptr0 = passArray8ToWasm0(bytes, wasm.__wbindgen_export_0);
+        const len0 = WASM_VECTOR_LEN;
+        const ret = wasm.tiktoken_encode_single_token(this.ptr, ptr0, len0);
+        return ret >>> 0;
+    }
+    /**
+    * @param {Uint32Array} tokens
+    * @returns {Uint8Array}
+    */
+    decode(tokens) {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            const ptr0 = passArray32ToWasm0(tokens, wasm.__wbindgen_export_0);
+            const len0 = WASM_VECTOR_LEN;
+            wasm.tiktoken_decode(retptr, this.ptr, ptr0, len0);
+            var r0 = getInt32Memory0()[retptr / 4 + 0];
+            var r1 = getInt32Memory0()[retptr / 4 + 1];
+            var v1 = getArrayU8FromWasm0(r0, r1).slice();
+            wasm.__wbindgen_export_2(r0, r1 * 1);
+            return v1;
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
+    /**
+    * @param {number} token
+    * @returns {Uint8Array}
+    */
+    decode_single_token_bytes(token) {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            wasm.tiktoken_decode_single_token_bytes(retptr, this.ptr, token);
+            var r0 = getInt32Memory0()[retptr / 4 + 0];
+            var r1 = getInt32Memory0()[retptr / 4 + 1];
+            var v0 = getArrayU8FromWasm0(r0, r1).slice();
+            wasm.__wbindgen_export_2(r0, r1 * 1);
+            return v0;
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
+    /**
+    * @returns {any}
+    */
+    token_byte_values() {
+        const ret = wasm.tiktoken_token_byte_values(this.ptr);
+        return takeObject(ret);
+    }
+}
+module.exports.Tiktoken = Tiktoken;
+
+module.exports.__wbindgen_object_drop_ref = function(arg0) {
+    takeObject(arg0);
+};
+
+module.exports.__wbindgen_is_undefined = function(arg0) {
+    const ret = getObject(arg0) === undefined;
+    return ret;
+};
+
+module.exports.__wbg_stringify_029a979dfb73aa17 = function() { return handleError(function (arg0) {
+    const ret = JSON.stringify(getObject(arg0));
+    return addHeapObject(ret);
+}, arguments) };
+
+module.exports.__wbindgen_string_get = function(arg0, arg1) {
+    const obj = getObject(arg1);
+    const ret = typeof(obj) === 'string' ? obj : undefined;
+    var ptr0 = isLikeNone(ret) ? 0 : passStringToWasm0(ret, wasm.__wbindgen_export_0, wasm.__wbindgen_export_1);
+    var len0 = WASM_VECTOR_LEN;
+    getInt32Memory0()[arg0 / 4 + 1] = len0;
+    getInt32Memory0()[arg0 / 4 + 0] = ptr0;
+};
+
+module.exports.__wbindgen_error_new = function(arg0, arg1) {
+    const ret = new Error(getStringFromWasm0(arg0, arg1));
+    return addHeapObject(ret);
+};
+
+module.exports.__wbg_parse_3ac95b51fc312db8 = function() { return handleError(function (arg0, arg1) {
+    const ret = JSON.parse(getStringFromWasm0(arg0, arg1));
+    return addHeapObject(ret);
+}, arguments) };
+
+module.exports.__wbindgen_throw = function(arg0, arg1) {
+    throw new Error(getStringFromWasm0(arg0, arg1));
+};
+
+const path = require('path').join(__dirname, 'tiktoken_bg.wasm');
+const bytes = require('fs').readFileSync(path);
+
+const wasmModule = new WebAssembly.Module(bytes);
+const wasmInstance = new WebAssembly.Instance(wasmModule, imports);
+wasm = wasmInstance.exports;
+module.exports.__wasm = wasm;
+

app/src/tiktoken/dist/tiktoken_bg.js

@@ -0,0 +1,421 @@
+let wasm;
+export function __wbg_set_wasm(val) {
+    wasm = val;
+}
+
+
+const heap = new Array(128).fill(undefined);
+
+heap.push(undefined, null, true, false);
+
+function getObject(idx) { return heap[idx]; }
+
+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;
+}
+
+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 lTextEncoder = typeof TextEncoder === 'undefined' ? (0, module.require)('util').TextEncoder : TextEncoder;
+
+let cachedTextEncoder = new lTextEncoder('utf-8');
+
+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);
+        getUint8Memory0().subarray(ptr, ptr + buf.length).set(buf);
+        WASM_VECTOR_LEN = buf.length;
+        return ptr;
+    }
+
+    let len = arg.length;
+    let ptr = malloc(len);
+
+    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);
+        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;
+}
+
+const lTextDecoder = typeof TextDecoder === 'undefined' ? (0, module.require)('util').TextDecoder : TextDecoder;
+
+let cachedTextDecoder = new lTextDecoder('utf-8', { ignoreBOM: true, fatal: true });
+
+cachedTextDecoder.decode();
+
+function getStringFromWasm0(ptr, len) {
+    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 cachedUint32Memory0 = null;
+
+function getUint32Memory0() {
+    if (cachedUint32Memory0 === null || cachedUint32Memory0.byteLength === 0) {
+        cachedUint32Memory0 = new Uint32Array(wasm.memory.buffer);
+    }
+    return cachedUint32Memory0;
+}
+
+function getArrayU32FromWasm0(ptr, len) {
+    return getUint32Memory0().subarray(ptr / 4, ptr / 4 + len);
+}
+
+function passArray8ToWasm0(arg, malloc) {
+    const ptr = malloc(arg.length * 1);
+    getUint8Memory0().set(arg, ptr / 1);
+    WASM_VECTOR_LEN = arg.length;
+    return ptr;
+}
+
+function passArray32ToWasm0(arg, malloc) {
+    const ptr = malloc(arg.length * 4);
+    getUint32Memory0().set(arg, ptr / 4);
+    WASM_VECTOR_LEN = arg.length;
+    return ptr;
+}
+
+function getArrayU8FromWasm0(ptr, len) {
+    return getUint8Memory0().subarray(ptr / 1, ptr / 1 + len);
+}
+/**
+* @param {string} encoding
+* @param {any} extend_special_tokens
+* @returns {Tiktoken}
+*/
+export function get_encoding(encoding, extend_special_tokens) {
+    try {
+        const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+        const ptr0 = passStringToWasm0(encoding, wasm.__wbindgen_export_0, wasm.__wbindgen_export_1);
+        const len0 = WASM_VECTOR_LEN;
+        wasm.get_encoding(retptr, ptr0, len0, addHeapObject(extend_special_tokens));
+        var r0 = getInt32Memory0()[retptr / 4 + 0];
+        var r1 = getInt32Memory0()[retptr / 4 + 1];
+        var r2 = getInt32Memory0()[retptr / 4 + 2];
+        if (r2) {
+            throw takeObject(r1);
+        }
+        return Tiktoken.__wrap(r0);
+    } finally {
+        wasm.__wbindgen_add_to_stack_pointer(16);
+    }
+}
+
+/**
+* @param {string} model
+* @param {any} extend_special_tokens
+* @returns {Tiktoken}
+*/
+export function encoding_for_model(model, extend_special_tokens) {
+    try {
+        const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+        const ptr0 = passStringToWasm0(model, wasm.__wbindgen_export_0, wasm.__wbindgen_export_1);
+        const len0 = WASM_VECTOR_LEN;
+        wasm.encoding_for_model(retptr, ptr0, len0, addHeapObject(extend_special_tokens));
+        var r0 = getInt32Memory0()[retptr / 4 + 0];
+        var r1 = getInt32Memory0()[retptr / 4 + 1];
+        var r2 = getInt32Memory0()[retptr / 4 + 2];
+        if (r2) {
+            throw takeObject(r1);
+        }
+        return Tiktoken.__wrap(r0);
+    } finally {
+        wasm.__wbindgen_add_to_stack_pointer(16);
+    }
+}
+
+function handleError(f, args) {
+    try {
+        return f.apply(this, args);
+    } catch (e) {
+        wasm.__wbindgen_export_3(addHeapObject(e));
+    }
+}
+/**
+*/
+export class Tiktoken {
+
+    static __wrap(ptr) {
+        const obj = Object.create(Tiktoken.prototype);
+        obj.ptr = ptr;
+
+        return obj;
+    }
+
+    __destroy_into_raw() {
+        const ptr = this.ptr;
+        this.ptr = 0;
+
+        return ptr;
+    }
+
+    free() {
+        const ptr = this.__destroy_into_raw();
+        wasm.__wbg_tiktoken_free(ptr);
+    }
+    /**
+    * @param {string} tiktoken_bfe
+    * @param {any} special_tokens
+    * @param {string} pat_str
+    */
+    constructor(tiktoken_bfe, special_tokens, pat_str) {
+        const ptr0 = passStringToWasm0(tiktoken_bfe, wasm.__wbindgen_export_0, wasm.__wbindgen_export_1);
+        const len0 = WASM_VECTOR_LEN;
+        const ptr1 = passStringToWasm0(pat_str, wasm.__wbindgen_export_0, wasm.__wbindgen_export_1);
+        const len1 = WASM_VECTOR_LEN;
+        const ret = wasm.tiktoken_new(ptr0, len0, addHeapObject(special_tokens), ptr1, len1);
+        return Tiktoken.__wrap(ret);
+    }
+    /**
+    * @returns {string | undefined}
+    */
+    get name() {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            wasm.tiktoken_name(retptr, this.ptr);
+            var r0 = getInt32Memory0()[retptr / 4 + 0];
+            var r1 = getInt32Memory0()[retptr / 4 + 1];
+            let v0;
+            if (r0 !== 0) {
+                v0 = getStringFromWasm0(r0, r1).slice();
+                wasm.__wbindgen_export_2(r0, r1 * 1);
+            }
+            return v0;
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
+    /**
+    * @param {string} text
+    * @param {any} allowed_special
+    * @param {any} disallowed_special
+    * @returns {Uint32Array}
+    */
+    encode(text, allowed_special, disallowed_special) {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            const ptr0 = passStringToWasm0(text, wasm.__wbindgen_export_0, wasm.__wbindgen_export_1);
+            const len0 = WASM_VECTOR_LEN;
+            wasm.tiktoken_encode(retptr, this.ptr, ptr0, len0, addHeapObject(allowed_special), addHeapObject(disallowed_special));
+            var r0 = getInt32Memory0()[retptr / 4 + 0];
+            var r1 = getInt32Memory0()[retptr / 4 + 1];
+            var r2 = getInt32Memory0()[retptr / 4 + 2];
+            var r3 = getInt32Memory0()[retptr / 4 + 3];
+            if (r3) {
+                throw takeObject(r2);
+            }
+            var v1 = getArrayU32FromWasm0(r0, r1).slice();
+            wasm.__wbindgen_export_2(r0, r1 * 4);
+            return v1;
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
+    /**
+    * @param {string} text
+    * @returns {Uint32Array}
+    */
+    encode_ordinary(text) {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            const ptr0 = passStringToWasm0(text, wasm.__wbindgen_export_0, wasm.__wbindgen_export_1);
+            const len0 = WASM_VECTOR_LEN;
+            wasm.tiktoken_encode_ordinary(retptr, this.ptr, ptr0, len0);
+            var r0 = getInt32Memory0()[retptr / 4 + 0];
+            var r1 = getInt32Memory0()[retptr / 4 + 1];
+            var v1 = getArrayU32FromWasm0(r0, r1).slice();
+            wasm.__wbindgen_export_2(r0, r1 * 4);
+            return v1;
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
+    /**
+    * @param {string} text
+    * @param {any} allowed_special
+    * @param {any} disallowed_special
+    * @returns {any}
+    */
+    encode_with_unstable(text, allowed_special, disallowed_special) {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            const ptr0 = passStringToWasm0(text, wasm.__wbindgen_export_0, wasm.__wbindgen_export_1);
+            const len0 = WASM_VECTOR_LEN;
+            wasm.tiktoken_encode_with_unstable(retptr, this.ptr, ptr0, len0, addHeapObject(allowed_special), addHeapObject(disallowed_special));
+            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);
+        }
+    }
+    /**
+    * @param {Uint8Array} bytes
+    * @returns {number}
+    */
+    encode_single_token(bytes) {
+        const ptr0 = passArray8ToWasm0(bytes, wasm.__wbindgen_export_0);
+        const len0 = WASM_VECTOR_LEN;
+        const ret = wasm.tiktoken_encode_single_token(this.ptr, ptr0, len0);
+        return ret >>> 0;
+    }
+    /**
+    * @param {Uint32Array} tokens
+    * @returns {Uint8Array}
+    */
+    decode(tokens) {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            const ptr0 = passArray32ToWasm0(tokens, wasm.__wbindgen_export_0);
+            const len0 = WASM_VECTOR_LEN;
+            wasm.tiktoken_decode(retptr, this.ptr, ptr0, len0);
+            var r0 = getInt32Memory0()[retptr / 4 + 0];
+            var r1 = getInt32Memory0()[retptr / 4 + 1];
+            var v1 = getArrayU8FromWasm0(r0, r1).slice();
+            wasm.__wbindgen_export_2(r0, r1 * 1);
+            return v1;
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
+    /**
+    * @param {number} token
+    * @returns {Uint8Array}
+    */
+    decode_single_token_bytes(token) {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            wasm.tiktoken_decode_single_token_bytes(retptr, this.ptr, token);
+            var r0 = getInt32Memory0()[retptr / 4 + 0];
+            var r1 = getInt32Memory0()[retptr / 4 + 1];
+            var v0 = getArrayU8FromWasm0(r0, r1).slice();
+            wasm.__wbindgen_export_2(r0, r1 * 1);
+            return v0;
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
+    /**
+    * @returns {any}
+    */
+    token_byte_values() {
+        const ret = wasm.tiktoken_token_byte_values(this.ptr);
+        return takeObject(ret);
+    }
+}
+
+export function __wbindgen_object_drop_ref(arg0) {
+    takeObject(arg0);
+};
+
+export function __wbindgen_is_undefined(arg0) {
+    const ret = getObject(arg0) === undefined;
+    return ret;
+};
+
+export function __wbg_stringify_029a979dfb73aa17() { return handleError(function (arg0) {
+    const ret = JSON.stringify(getObject(arg0));
+    return addHeapObject(ret);
+}, arguments) };
+
+export function __wbindgen_string_get(arg0, arg1) {
+    const obj = getObject(arg1);
+    const ret = typeof(obj) === 'string' ? obj : undefined;
+    var ptr0 = isLikeNone(ret) ? 0 : passStringToWasm0(ret, wasm.__wbindgen_export_0, wasm.__wbindgen_export_1);
+    var len0 = WASM_VECTOR_LEN;
+    getInt32Memory0()[arg0 / 4 + 1] = len0;
+    getInt32Memory0()[arg0 / 4 + 0] = ptr0;
+};
+
+export function __wbindgen_error_new(arg0, arg1) {
+    const ret = new Error(getStringFromWasm0(arg0, arg1));
+    return addHeapObject(ret);
+};
+
+export function __wbg_parse_3ac95b51fc312db8() { return handleError(function (arg0, arg1) {
+    const ret = JSON.parse(getStringFromWasm0(arg0, arg1));
+    return addHeapObject(ret);
+}, arguments) };
+
+export function __wbindgen_throw(arg0, arg1) {
+    throw new Error(getStringFromWasm0(arg0, arg1));
+};
+

app/src/tiktoken/dist/tiktoken_bg.wasm.d.ts

@@ -0,0 +1,20 @@
+/* tslint:disable */
+/* eslint-disable */
+export const memory: WebAssembly.Memory;
+export function __wbg_tiktoken_free(a: number): void;
+export function tiktoken_new(a: number, b: number, c: number, d: number, e: number): number;
+export function tiktoken_name(a: number, b: number): void;
+export function tiktoken_encode(a: number, b: number, c: number, d: number, e: number, f: number): void;
+export function tiktoken_encode_ordinary(a: number, b: number, c: number, d: number): void;
+export function tiktoken_encode_with_unstable(a: number, b: number, c: number, d: number, e: number, f: number): void;
+export function tiktoken_encode_single_token(a: number, b: number, c: number): number;
+export function tiktoken_decode(a: number, b: number, c: number, d: number): void;
+export function tiktoken_decode_single_token_bytes(a: number, b: number, c: number): void;
+export function tiktoken_token_byte_values(a: number): number;
+export function get_encoding(a: number, b: number, c: number, d: number): void;
+export function encoding_for_model(a: number, b: number, c: number, d: number): void;
+export function __wbindgen_export_0(a: number): number;
+export function __wbindgen_export_1(a: number, b: number, c: number): number;
+export function __wbindgen_add_to_stack_pointer(a: number): number;
+export function __wbindgen_export_2(a: number, b: number): void;
+export function __wbindgen_export_3(a: number): void;