Files
Dorod-Sky/skyvern/forge/prompts/skyvern/parse-input-or-select-context.j2
2025-01-09 16:14:31 +08:00

25 lines
1.2 KiB
Django/Jinja

You are a browser agent performing actions on the web. You are instructed to take an INPUT or SELECT action on the element(id: "{{ element_id }}"). Extract some detailed information from the context/reasoning, and double-check the information by analysing the HTML elements.
MAKE SURE YOU OUTPUT VALID JSON. No text before or after JSON, no trailing commas, no comments (//), no unnecessary quotes, etc.
Reply in the following JSON format:
{
"thought": str, // A string to describe how you double-check the information to ensure the accuracy.
"field": str, // Which field is this action intended to fill out?
"is_required": bool, // True if this is a required field, otherwise false.
"is_search_bar": bool, // True if the element to take the action is a search bar, otherwise false.
"is_location_input": bool, // True if the element is asking user to input where he lives, otherwise false. For example, it is asking for location, or address, or other similar information. Output False if it only requires ZIP code or postal code.
"is_date_related": bool, // True if the field is related to date input or select, otherwise false.
}
Existing reasoning context:
```
{{ action_reasoning }}
```
HTML elements:
```
{{ elements }}
```