The Web family contains 3 operators. HTTP fetch + article scraping.
Fetches content from a URL.
Version 1.0.0 · Semantics side_effect · Visibility advanced
| Field | Type | Required | Default | Description |
|---|
extract_mode | ”html” | “text” | “markdown” | no | "text" | |
timeout_ms | integer | no | 30000 | |
| Port | Type | Required | Description |
|---|
url | string | yes | URL |
| Port | Type | Required | Description |
|---|
content | string | no | Content |
metadata | object | no | Metadata |
Fetches a URL through the SSRF-guarded HTTP client and extracts the main article body in markdown / text / html, plus lightweight metadata (author, description, published, site).
Version 1.0.0 · Semantics side_effect · Visibility advanced
| Field | Type | Required | Default | Description |
|---|
format | ”markdown” | “text” | “html” | no | "markdown" | Output format for the extracted article body. |
include_metadata | boolean | no | true | Include <meta>-tag metadata (author, description, published, site_name) in the output. |
url | string | no | — | Absolute URL to fetch. Falls back to the upstream ‘url’ input port if omitted. |
| Port | Type | Required | Description |
|---|
url | string | no | URL |
| Port | Type | Required | Description |
|---|
output | object | no | Article |
Searches the web using a search API.
Version 1.0.0 · Semantics side_effect · Visibility advanced · Secrets SEARCH_API_KEY
| Field | Type | Required | Default | Description |
|---|
engine | ”google” | “bing” | “serper” | no | "serper" | |
num_results | integer | no | 5 | |
| Port | Type | Required | Description |
|---|
query | string | yes | Query |
| Port | Type | Required | Description |
|---|
results | array | no | Results |
Every operator above is rendered from its JSON schema in /opt/glyph/schemas/operators/:
schemas/operators/web.fetch.json
schemas/operators/web.scrape.json
schemas/operators/web.search.json