appmixer.ai.exa.FindExtractedPages
Extract Page Contents
1.0.0
Public
| Field | Type | Description |
|---|---|---|
| URLs | textarea | Comma or newline separated list of page URLs to extract, up to 100 per call. |
| Include Page Text | toggle | Return the cleaned full text of each page. |
| Include Highlights | toggle | Also return the snippets of each page an LLM judged most relevant. |
| Summary Query | text | Ask Exa to summarise each page with this question in mind, e.g. What is the pricing?. Leave empty for no summary. |
| Max Cache Age (hours) | number | Use Exa's cached copy when it is newer than this many hours. 0 forces a fresh crawl, -1 serves cache only. Maximum 720. |
| Subpages | number | Also crawl up to this many linked subpages of each URL, between 0 and 100. |
| Subpage Target | text | Comma separated terms that steer which subpages are picked, e.g. pricing, about. Only applies when Subpages is set. |
| Output Type | select | Choose whether you want to receive the result set as one complete list, or first item only or one item at a time or stream the items to a file. |
Dynamic variables loaded from /component/appmixer/ai/exa/FindExtractedPages?outPort=out&ignoreAuth=true
| Field | Type | Description |
|---|---|---|
| URLs | array | - |