Document Fetch
🤖 AI Drafted (Not reviewed)
Fetch a document from a URL and optionally save as a Layer 1 Source in the Fichero database. Sandboxed — only http/https URLs allowed.
|
|
| Tool id |
research_document_fetch |
| Category |
research |
| Uses a language model |
no |
| Needs a generative model |
no |
| Runs over many items |
no |
| Item handling |
batch |
| Structured output |
no |
| Human-verified |
not yet |
What it reads
| Port |
Type |
Required |
What it is |
URL (url) |
text |
yes |
URL of the document to fetch |
Project ID (project_id) |
text |
yes |
Research project ID to save the source under |
What it emits
| Port |
Type |
Required |
What it is |
URL (url) |
text |
— |
Document URL |
Title (title) |
text |
— |
Document title extracted from HTML or URL |
Content (content) |
text |
— |
Document content (truncated to 50k chars) |
Content Type (content_type) |
text |
— |
HTTP content-type header |
Source ID (source_id) |
text |
— |
Fichero Source ID if created |
Success (success) |
boolean |
— |
Whether fetch succeeded |
Error (error) |
text |
— |
Error message if failed |
Options
| Option |
Type |
Default |
What it does |
properties |
any |
— |
— |
type |
any |
— |
— |
The prompt it sends
This tool does not send a prompt — it does its work in code.