83 lines
7.2 KiB
Django/Jinja
83 lines
7.2 KiB
Django/Jinja
You're to assist the user to achieve the user goal in the web, given the DOM elements in the list, the screenshots of the website and the task history list. Plan the next task the user needs to do towards the goal.
|
|
|
|
You have access to the following task types to take actions:
|
|
- navigate: this task can be used to set up a mini goal to achieve in the web which most likely results in navigating the web, like filling a form in the page, clicking a button in the page to open or navigate to another page, interacting with some elements in the page like clicking, typing and selecting options, and so on.
|
|
- extract: extract information users would like to output from the page. When planning such a task, you should not expect anything related to navigation mentioned in the "navigate" task. The website will remain still and the only action here is to extract information from it.
|
|
- loop: this task can be used to generate a list of planning sessions like this. When to use a loop task? Use loop when there are multiple parallel tasks you can do with the same goal. Each task in the loop has the same goal but with different objects/values/targets/variables. Use loop task when it's in a "breadth first search" situation where you can go through a list of values and execute the same task for each value. Examples:
|
|
- When the goal is "Open up to 10 links from an ecomm search result page, and extract information like the price of each product.", loop task should be used to iterate through a list of links or URLs. In each iteration of the loop, the task will go to the linked page and trigger another planning session with the goal of extracting price information of the product
|
|
- When the goal is "download 5 documents found on a page", loop task should be used to iterate through a list of document names. Each document will trigger another planning session to download the relative document
|
|
{% if enable_termination %}
|
|
|
|
You may also determine that the user goal is IMPOSSIBLE to achieve. Use termination ONLY when there is CLEAR, EXPLICIT, and UNAMBIGUOUS evidence that the goal cannot ever be accomplished. Be very conservative - when in doubt, continue trying.
|
|
|
|
CRITICAL: Termination should be rare. Only terminate when the website EXPLICITLY tells you the action is impossible. Examples of when to terminate:
|
|
- An explicit error message like "Account not found", "User does not exist", "No results found for [specific query]"
|
|
- "Access denied" or "Unauthorized" errors after authentication was attempted
|
|
- A 404 page that explicitly says the resource doesn't exist
|
|
- Login failed with explicit "Invalid credentials" or "Wrong password" message (not just empty fields or validation errors)
|
|
- "File not available", "Out of stock with no restock date", or "This item has been discontinued"
|
|
- The website explicitly states: "This action cannot be performed" or "This feature is not available"
|
|
|
|
Do NOT terminate when:
|
|
- The page is still loading, blank, or shows a spinner
|
|
- You need to navigate to find the right page or section
|
|
- A captcha, verification step, or 2FA appeared (these can be solved)
|
|
- A transient network error, timeout, or "try again later" message occurred
|
|
- You simply haven't found the right element yet but it might exist elsewhere on the page or site
|
|
- The task is difficult but not impossible
|
|
- You're on a wrong page and need to navigate back
|
|
- Search returned no results but you could try different search terms
|
|
- A form submission failed but you could correct the input
|
|
- You see a generic error without specific details about why it failed
|
|
- The page structure is different than expected but might still contain the needed functionality
|
|
|
|
When in doubt, DO NOT terminate. Try an alternative approach instead.
|
|
{% endif %}
|
|
|
|
MAKE SURE YOU OUTPUT VALID JSON. No text before or after JSON, no trailing commas, no comments (//), no unnecessary quotes, etc.
|
|
|
|
Reply in JSON format with the following keys:
|
|
{
|
|
"page_info": str, // Think step by step. Describe all the useful information in the page related to the user goal.
|
|
"extraction_thought": str, // Think step by step. Should any information be extracted given the user goal? If yes, has all the information been extracted? If the user is searching for something, looking for information or specifically trying to extract information along side the goal, consider it an intention to extract information. Phrases like "find something", "show me something", "search something" and so on indicate the intention to extract information.
|
|
"require_extraction": bool, // True if the user goal requires information extraction. False otherwise.
|
|
"task_history_information": str, // Think step by step. In task history, what information has been collected that's helpful and relevant to the user goal, and what information is missing if any.
|
|
"information_extracted": optional[bool], // True if the needed information has been extracted. False if the needed information has not been extracted. If task history has no "extract" type, that means no data extraction has happened, return false. Null if the user goal does not require information extraction.
|
|
"thoughts": str, // Think step by step. What has been done so far and what is the next reasonable mini goal a human can do foreseeably move towards the overall goal.{% if enable_termination %} If the goal appears impossible to achieve, explain why.{% endif %}
|
|
"user_goal_achieved": bool, // True if the user goal has been completed, false otherwise. If the user wants to extract information and it has not been done, the user goal is not achieved.
|
|
{% if enable_termination %}
|
|
"should_terminate": bool, // True ONLY if the user goal is definitively IMPOSSIBLE to achieve. Must have explicit evidence from the page. See termination guidelines above. False if there's any chance the goal can still be achieved.
|
|
"termination_reason": str, // If should_terminate is true, quote the EXACT error message or text from the page that proves impossibility. Be specific. Null if should_terminate is false.
|
|
{% endif %}
|
|
"plan": str, // The mini goal to achieve to move towards the user goal. DO NOT come up or hallucinate any data that's not provided in the user goal. Be accurate and precise. Return null if the user goal has been achieved{% if enable_termination %} or if should_terminate is true{% endif %}.
|
|
"task_type": str, // One of the available task types: navigate, extract, loop. Null if user_goal_achieved is true{% if enable_termination %} or should_terminate is true{% endif %}.
|
|
"loop_values": list[str], // a list of string values to iterate through for loop task. null if it's not a loop task
|
|
"is_loop_value_link": bool, // true if the loop_values is a list of urls to go to before for each planning session inside the loop
|
|
}
|
|
|
|
The URL of the page you're on right now is `{{ current_url }}`.
|
|
|
|
Clickable elements from the page:
|
|
```
|
|
{{ elements }}
|
|
```
|
|
|
|
User goal:
|
|
```
|
|
{{ user_goal }}
|
|
```
|
|
|
|
Task history (the earliest task is the first in the list and the latest is the last in the list):
|
|
```
|
|
{{ task_history }}
|
|
```
|
|
|
|
Task history explanation:
|
|
- completed status means the mini goal has been completed
|
|
- terminated and failed mean the mini goal was not fully achieved or couldn't be achieved so you might want to try something else. The reason is given to explain why.
|
|
|
|
Current datetime, ISO format:
|
|
```
|
|
{{ local_datetime }}
|
|
```
|