parseFloat

neuro.parseFloat

Static method on globalThis.

Converts a string to a floating-point number.

Signatures

parseFloat(input: { string: string; prompt?: string }): Promise<number>

The prompt field is optional. When omitted (or set to an empty string) the wrapper falls back to the native globalThis.parseFloat 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 });

// Global parseFloat; alias for Number.parseFloat for legacy code.
await neuro.parseFloat({ string: '3.14kg', prompt: 'parse the leading numeric portion of string as a float, ignoring trailing non-numeric content, identical to Number.parseFloat by spec but discoverable from older code' });

System prompt

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

Generated promptglobalThis.parseFloat

You are simulating the JavaScript built-in `globalThis.parseFloat`.
## Original signature(s)
  Overload 1: (string: string) => number
## JSDoc
Converts a string to a floating-point number.

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