constants.py

WORD_LIMIT_MIN = 100
WORD_LIMIT_MAX = 500
GROUP_SEPERATION = 1000
LOCAL_PARAMS = False

SDG_DETAILS = """
1. No Poverty: Eradicate all forms of poverty.
2. Zero Hunger: End hunger and promote sustainable agriculture.
3. Good Health and Well-being: Ensure health and well-being for everyone.
4. Quality Education: Guarantee inclusive, quality education for all.
5. Gender Equality: Empower women and achieve gender equality.
6. Clean Water and Sanitation: Provide sustainable water and sanitation.
7. Affordable and Clean Energy: Ensure access to sustainable energy.
8. Decent Work and Economic Growth: Foster inclusive economic growth and decent jobs.
9. Industry, Innovation and Infrastructure: Build resilient infrastructure and promote innovation.
10. Reduced Inequality: Decrease inequality within and among countries.
11. Sustainable Cities and Communities: Develop safe and sustainable communities.
12. Responsible Consumption and Production: Ensure sustainable consumption and production.
13. Climate Action: Take action against climate change.
14. Life Below Water: Protect oceans and marine life.
15. Life on Land: Sustainably manage ecosystems and biodiversity.
16. Peace and Justice Strong Institutions: Promote peace, justice, and strong institutions.
17. Partnerships to achieve the Goals: Enhance global partnerships for sustainable development.
"""


GPT_PROMPT_parallel="""
For AI generated/modified parts, our base model is GPT-4o. 

For direct generation, we use instructions like following:
"Given the task as: [task_description], provide an answer: "

For the merging, we use instructions like following:
"Given the task as: [task_description], there are two answers provided:
The first answer: [human_text]
The second answer: [ai_text]
Merge the two answers into one in a coherent way: "
"""

GPT_PROMPT_sequential="""
For AI generated/modified parts, our base model is GPT-4o. 

For the modification, we use instructions like following:
"Given the task as :[task_description, the human answer is: [human_text]
Provide an answer of your own but make sure it is coherent and should be based on the human answer: "
"""

GPT_PROMPT_reverse_sequential="""
For AI generated/modified parts, our base model is GPT-4o. 

For direct generation, we use instructions like following:
"Given the task as: [task_description], provide an answer: "

For the merging, we use instructions like following:
"Given the task as: [task_description], there are two answers provided:
The first answer: [human_text]
The second answer: [ai_text]
Merge the two answers into one in a coherent way: "
"""