Skip to content

from

Static method on BigInt64Array.

Creates an array from an array-like or iterable object.

from(input: { arrayLike: ArrayLike<bigint>; prompt?: string }): Promise<BigInt64Array>
from(input: { arrayLike: ArrayLike<U>; mapfn?: (v: U; k: number) => bigint; thisArg?: any; prompt?: string }): Promise<BigInt64Array>
from(input: { elements: Iterable<bigint>; prompt?: string }): Promise<BigInt64Array>
from(input: { elements: Iterable<T>; mapfn?: (v: T; k: number) => bigint; thisArg?: any; prompt?: string }): Promise<BigInt64Array>

The prompt field is optional. When omitted (or set to an empty string) the wrapper falls back to the native BigInt64Array.from and returns a resolved Promise without contacting the LLM. When present, the LLM is given the original arguments plus your prompt and is asked to behave like the original method.

import { configureClient, neuro } from 'neuro-ts';
configureClient({ apiKey: process.env.OPENAI_API_KEY });
// BigInt64Array from; coerces every produced value into two-is-complement signed 64-bit integers in [-(2^63), 2^63 - 1].
await neuro.bigInt64Array.from({ arrayLike: source, prompt: 'materialise an iterable into a fresh BigInt64Array, optionally mapping each element with mapfn, and BigInt-everywhere semantics that finally let us count atomic operations past 2^53 without lying about precision' });

The exact system prompt the SDK sends to your model when you provide a prompt field:

Generated promptBigInt64Array.from
You are simulating the JavaScript built-in `BigInt64Array.from`.
## Original signature(s)
  Overload 1: (arrayLike: ArrayLike<bigint>) => BigInt64Array
  Overload 2: (arrayLike: ArrayLike<U>, mapfn?: (v: U, k: number) => bigint, thisArg?: any) => BigInt64Array
  Overload 3: (elements: Iterable<bigint>) => BigInt64Array
  Overload 4: (elements: Iterable<T>, mapfn?: (v: T, k: number) => bigint, thisArg?: any) => BigInt64Array
## JSDoc
Creates an array from an array-like or iterable object.

## How to respond
- Behave EXACTLY as the original `from` would, but use the user's intent to choose any callback / comparator / transform logic that the original would normally accept as an argument.
- Strictly preserve the original return type and shape.
- Output ONLY the JSON-encoded return value of the function call.
- Do NOT include explanations, prose, comments, or markdown fences.
- If the function would return `undefined`, output the literal string `undefined`.
- For Date / RegExp / Map / Set / TypedArray returns, output an object of the form { "__type": "Date" | "RegExp" | "Map" | "Set" | "<TypedArrayName>", ... } so the SDK can rehydrate it.