> For the complete documentation index, see [llms.txt](https://university.mindstudio.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://university.mindstudio.ai/developers/custom-function-methods.md).

# Custom Function Methods

### Extensions

#### `scrapeUrl(url: string, scrapeSettings?: object): Promise<string>`

Scrapes metadata or content from the specified URL using optional custom settings.

**Parameters**

| Name             | Type     | Description                                |
| ---------------- | -------- | ------------------------------------------ |
| `url`            | `string` | URL to scrape.                             |
| `scrapeSettings` | `object` | *(optional)* Custom settings for scraping. |

**Returns**

`Promise<string>` — JSON‑stringified scrape result.

***

#### `searchGoogle(query: string): Promise<string>`

Performs a Google web search and returns relevant results.

**Parameters**

* `query` (`string`): Search query string.

**Returns**

`Promise<string>` — JSON‑stringified list of results.

***

#### `rehostImage(imageUrl: string): Promise<string>`

Downloads and re‑hosts an image to a secure internal location.

**Parameters**

* `imageUrl` (`string`): Public URL of the image.

**Returns**

`Promise<string>` — JSON‑stringified object containing the new hosted image URL.

***

#### `concatenateAudio(urls: string[], options: object): Promise<string>`

Merges multiple audio files (e.g., MP3, WAV) into a single audio stream.

**Parameters**

| Name      | Type       | Description                              |
| --------- | ---------- | ---------------------------------------- |
| `urls`    | `string[]` | Array of audio file URLs.                |
| `options` | `object`   | Settings (e.g., fade in, output format). |

**Returns**

`Promise<string>` — JSON‑stringified result (e.g., output URL or metadata).

***

#### `unzipFile(zipUrl: string): Promise<string>`

Unzips a `.zip` file from the given URL and returns its contents or links.

**Parameters**

* `zipUrl` (`string`): URL to a zip archive.

**Returns**

`Promise<string>` — JSON‑stringified file tree or extracted file URLs.

***

#### `analyzeImage(imageUrl: string, prompt: string): Promise<string>`

Performs visual analysis of an image using a textual prompt.

**Parameters**

| Name       | Type     | Description                              |
| ---------- | -------- | ---------------------------------------- |
| `imageUrl` | `string` | URL of the image to analyze.             |
| `prompt`   | `string` | Instruction or question about the image. |

**Returns**

`Promise<string>` — JSON‑stringified analysis result.

***

#### `searchGoogleImages(query: string): Promise<string>`

Fetches relevant images based on a search query.

**Parameters**

* `query` (`string`): Image search keywords.

**Returns**

`Promise<string>` — JSON‑stringified array of image URLs or metadata.

***

#### `generateChart(data: object, width?: number, height?: number, backgroundColor?: string): Promise<string>`

Generates a chart image from structured data.

**Parameters**

| Name              | Type     | Description                                        |
| ----------------- | -------- | -------------------------------------------------- |
| `data`            | `object` | Chart data and configuration.                      |
| `width`           | `number` | *(optional)* Image width in pixels (default 500).  |
| `height`          | `number` | *(optional)* Image height in pixels (default 300). |
| `backgroundColor` | `string` | *(optional)* Background color (default white).     |

**Returns**

`Promise<string>` — Base64‑encoded chart image or URL.

***

#### `queryDataSource(dataSourceId: string, query: string, numResults?: number): Promise<string>`

Executes a query against a configured data source (e.g., SQL, vector DB).

**Parameters**

| Name           | Type     | Description                                     |
| -------------- | -------- | ----------------------------------------------- |
| `dataSourceId` | `string` | Target data source identifier.                  |
| `query`        | `string` | Query string to execute.                        |
| `numResults`   | `number` | *(optional)* Max number of results (default 1). |

**Returns**

`Promise<string>` — JSON‑stringified query results.

***

#### `uploadFile(body: string, contentType: string, encoding: BufferEncoding): Promise<{ url: string }>`

Uploads a file and returns its hosted URL.

**Parameters**

| Name          | Type             | Description                             |
| ------------- | ---------------- | --------------------------------------- |
| `body`        | `string`         | File contents (base64‐encoded or text). |
| `contentType` | `string`         | MIME type of the file.                  |
| `encoding`    | `BufferEncoding` | Encoding format used.                   |

**Returns**

`Promise<{ url: string }>` — Object containing the hosted file URL.

***

#### `log(value: string): void`

Sends a log message to the workflow execution log.

**Parameters**

* `value` (`string`): Message to log.

**Returns**

`void`

***

#### `generateImage(prompt: string, modelId: string): Promise<{ b64_json: string }>`

Generates an image from a text prompt using a specified model.

**Parameters**

| Name      | Type     | Description                         |
| --------- | -------- | ----------------------------------- |
| `prompt`  | `string` | Text prompt for image generation.   |
| `modelId` | `string` | Identifier of the generation model. |

**Returns**

`Promise<{ b64_json: string }>` — Base64‑encoded image payload.&#x20;


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://university.mindstudio.ai/developers/custom-function-methods.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.