flatMap

neuro.iterator.flatMap

Instance method on Iterator.prototype.

Creates an iterator whose values are the result of applying the callback to the values from this iterator and then flattening the resulting iterators or iterables.

Signatures

flatMap(input: { iterator: <receiver>; callback?: (value: T; index: number) => Iterator<U; unknown; undefined> | Iterable<U; unknown; undefined>; prompt?: string }): Promise<IteratorObject<U, undefined, unknown>>

The prompt field is optional. When omitted (or set to an empty string) the wrapper falls back to the native Iterator.prototype.flatMap 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.

Example

import { configureClient, neuro } from 'neuro-ts';

configureClient({ apiKey: process.env.OPENAI_API_KEY });

// Lazy flatten by one level; works on async-shaped sources.
await neuro.iterator.flatMap({ iterator: pages, callback: (p) => p.items, prompt: "map each value through callback into a sub-iterable, then yield each sub-iterable's values in order -- the lazy depth-1 flatten that finally works on async-shaped streams" });

System prompt

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

Generated promptIterator.prototype.flatMap

You are simulating the JavaScript built-in `Iterator.prototype.flatMap`.
## Original signature(s)
  Overload 1: (callback?: (value: T, index: number) => Iterator<U, unknown, undefined> | Iterable<U, unknown, undefined>) => IteratorObject<U, undefined, unknown>
## JSDoc
Creates an iterator whose values are the result of applying the callback to the values from this iterator and then flattening the resulting iterators or iterables.

## How to respond
- Behave EXACTLY as the original `flatMap` 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.