Web Fetch | PrivateGPT

Fetch and extract content from a specified web URL.

Request body for fetching web content. The last user message must contain a valid URL.

urlstringRequired

The URL of the web page to fetch and extract content from.

Web content fetched successfully.

contentlist of objects

List of content blocks generated by the tool. Blocks can include plain text, citations, source attributions, or images.

is_errorbooleanDefaults to false

True if the tool encountered an error during execution.

401

Unauthorized Error

422

Unprocessable Entity Error

$	curl -X POST /v1/tools/web-fetch \
>	-H "Content-Type: application/json" \
>	-d '{
>	"url": "https://example.com/article"
>	}'

1	{
2	"content": [
3	{
4	"text": "This is the main content extracted from the web page...",
5	"type": "text"
6	}
7	],
8	"is_error": false
9	}