train_rick/generate_rick_science_dataset/generate_questions.py

"""
python generate_questions.py > questions.txt
"""

from openai import OpenAI

client = OpenAI()

themes = [
    "Physics/Kinematics",
    "Physics/Dynamics",
    "Physics/Energy",
    "Physics/Momentum",
    "Physics/Rotational Motion",
    "Physics/Gravitation",
    "Physics/Fluid Mechanics",
    "Physics/Thermodynamics",
    "Physics/Waves",
    "Physics/Sound",
    "Physics/Optics",
    "Physics/Electricity",
    "Physics/Magnetism",
    "Physics/Electromagnetic Waves",
    "Physics/Quantum Mechanics",
    "Physics/Special Relativity",
    "Physics/General Relativity",
    "Physics/Nuclear Physics",
    "Physics/Particle Physics",
    "Physics/Astrophysics",
    "Physics/Experimental Techniques",
    "Physics/Error Analysis",
    "Physics/Units & Measurement",
    "Chemistry/Atomic Structure",
    "Chemistry/Periodic Table",
    "Chemistry/Ionic Bonding",
    "Chemistry/Covalent Bonding",
    "Chemistry/Metallic Bonding",
    "Chemistry/Intermolecular Forces",
    "Chemistry/Molecular Geometry",
    "Chemistry/States of Matter",
    "Chemistry/Gas Laws",
    "Chemistry/Solutions",
    "Chemistry/Acids and Bases",
    "Chemistry/Redox Reactions",
    "Chemistry/Chemical Reactions",
    "Chemistry/Thermochemistry",
    "Chemistry/Reaction Kinetics",
    "Chemistry/Chemical Equilibrium",
    "Chemistry/Nuclear Chemistry",
    "Chemistry/Organic Chemistry",
    "Chemistry/Hydrocarbons",
    "Chemistry/Functional Groups",
    "Chemistry/Biochemistry",
    "Chemistry/Polymers",
    "Chemistry/Analytical Techniques",
    "Chemistry/Spectroscopy",
    "Biology/Cell Structure",
    "Biology/Cell Membrane",
    "Biology/Cell Division",
    "Biology/Cellular Respiration",
    "Biology/Photosynthesis",
    "Biology/DNA Structure",
    "Biology/Protein Synthesis",
    "Biology/Genetics",
    "Biology/Inheritance",
    "Biology/Epigenetics",
    "Biology/Evolution",
    "Biology/Taxonomy",
    "Biology/Plants",
    "Biology/Animal Physiology",
    "Biology/Nervous System",
    "Biology/Endocrine System",
    "Biology/Immune System",
    "Biology/Cardiovascular System",
    "Biology/Respiratory System",
    "Biology/Digestive System",
    "Biology/Reproductive System",
    "Biology/Population Biology",
    "Biology/Ecology",
    "Biology/Microbiology",
    "Biology/Biotechnology",
    "Earth Science/Geology",
    "Earth Science/Plate Tectonics",
    "Earth Science/Volcanoes",
    "Earth Science/Earthquakes",
    "Earth Science/Minerals",
    "Earth Science/Rocks",
    "Earth Science/Fossils",
    "Earth Science/Geologic Time",
    "Earth Science/Weathering & Erosion",
    "Earth Science/Oceanography",
    "Earth Science/Weather",
    "Earth Science/Climate",
    "Earth Science/Atmosphere",
    "Earth Science/Hydrosphere",
    "Earth Science/Natural Disasters",
    "Earth Science/Soil Science",
    "Earth Science/Earth’s Interior",
    "Earth Science/Magnetic Field",
    "Astronomy/Solar System",
    "Astronomy/Planets",
    "Astronomy/Moons",
    "Astronomy/Sun",
    "Astronomy/Stars",
    "Astronomy/Galaxies",
    "Astronomy/Black Holes",
    "Astronomy/Dark Matter",
    "Astronomy/Cosmology",
    "Astronomy/Exoplanets",
    "Astronomy/Space Missions",
    "Astronomy/Space-Time",
    "Astronomy/Telescopes",
    "Astronomy/Observational Techniques",
    "Environmental Science/Ecosystems",
    "Environmental Science/Biodiversity",
    "Environmental Science/Pollution",
    "Environmental Science/Water Resources",
    "Environmental Science/Air Quality",
    "Environmental Science/Climate Change",
    "Environmental Science/Sustainable Energy",
    "Environmental Science/Deforestation",
    "Environmental Science/Conservation",
    "Environmental Science/Waste Management",
    "Environmental Science/Carbon Cycle",
    "Environmental Science/Nitrogen Cycle",
    "Environmental Science/Food Chains",
    "Environmental Science/Population Growth",
    "Environmental Science/Land Use",
    "Math/Calculus - Derivatives",
    "Math/Calculus - Integrals",
    "Math/Calculus - Applications",
    "Math/Differential Equations",
    "Math/Probability",
    "Math/Statistics",
    "Math/Linear Algebra",
    "Math/Matrices",
    "Math/Trigonometry",
    "Math/Geometry",
    "Math/Algebra",
    "Math/Number Theory",
    "Math/Set Theory",
    "Math/Graph Theory",
    "Math/Mathematical Logic",
    "Math/Complex Numbers",
    "Computer Science/Algorithms",
    "Computer Science/Data Structures",
    "Computer Science/Boolean Logic",
    "Computer Science/Computational Complexity",
    "Computer Science/Artificial Intelligence",
    "Computer Science/Machine Learning",
    "Computer Science/Quantum Computing",
    "Computer Science/Theoretical CS",
    "Computer Science/Cryptography",
    "Computer Science/Networks",
    "Computer Science/Software Engineering",
    "Computer Science/Programming Languages",
    "Computer Science/Operating Systems",
    "Engineering/Mechanical Engineering",
    "Engineering/Thermodynamics",
    "Engineering/Electrical Engineering",
    "Engineering/Control Systems",
    "Engineering/Signal Processing",
    "Engineering/Materials Science",
    "Engineering/Structural Engineering",
    "Engineering/Robotics",
    "Engineering/Civil Engineering",
    "Engineering/Computer Engineering",
    "Engineering/Aerospace Engineering",
    "Medicine/Anatomy",
    "Medicine/Physiology",
    "Medicine/Pharmacology",
    "Medicine/Pathology",
    "Medicine/Neuroscience",
    "Medicine/Medical Imaging",
    "Medicine/Public Health",
    "Medicine/Epidemiology",
    "Medicine/Genetics in Medicine",
    "Medicine/Infectious Diseases",
    "Medicine/Cardiology",
    "Medicine/Oncology",
    "Medicine/Endocrinology",
    "Medicine/Immunology",
    "Medicine/Gastroenterology",
    "Medicine/Dermatology",
    "Psychology/Cognitive Psychology",
    "Psychology/Behavioral Psychology",
    "Psychology/Developmental Psychology",
    "Psychology/Biopsychology",
    "Psychology/Neuropsychology",
    "Psychology/Sensation and Perception",
    "Psychology/Social Psychology",
    "Psychology/Personality Theory",
    "Psychology/Psychological Disorders",
    "Psychology/Therapeutic Approaches",
    "Science/Scientific Method",
    "Science/Experimental Design",
    "Science/Measurement & Units",
    "Science/Error & Uncertainty",
    "Science/Models & Simulations",
    "Science/Ethics in Science",
    "Science/History of Science",
    "Math/Topology",
    "Math/Real Analysis",
    "Math/Abstract Algebra",
    "Math/Vector Calculus",
    "Math/Fractions and Decimals",
    "Math/Math History",
    "Math/Math in Nature",
    "Computer Science/Natural Language Processing",
    "Computer Science/Computer Vision",
    "Computer Science/Human-Computer Interaction",
    "Computer Science/Cybersecurity",
    "Computer Science/Cloud Computing",
    "Engineering/Environmental Engineering",
    "Engineering/Biomedical Engineering",
    "Engineering/Nanotechnology",
    "Engineering/Transportation Engineering",
    "Engineering/Mechatronics",
    "Physics/Computational Physics",
    "Physics/Biophysics",
    "Chemistry/Coordination Compounds",
    "Chemistry/Environmental Chemistry",
    "Chemistry/Green Chemistry",
    "Chemistry/Industrial Chemistry",
    "Biology/Developmental Biology",
    "Biology/Neurobiology",
    "Biology/Synthetic Biology",
    "Biology/Systems Biology",
    "Biology/Marine Biology",
    "Earth Science/Remote Sensing",
    "Earth Science/Glaciology",
    "Earth Science/Meteorology",
    "Astronomy/Astrobiology",
    "Astronomy/Radio Astronomy",
    "Astronomy/Planetary Geology",
    "Astronomy/Space Weather",
    "Environmental Science/Environmental Policy",
    "Environmental Science/Energy Resources",
    "Environmental Science/Ecological Footprint",
    "Environmental Science/Environmental Toxicology",
    "Medicine/Genomics",
    "Medicine/Surgical Techniques",
    "Medicine/Preventive Medicine",
    "Medicine/Health Informatics",
    "Psychology/Forensic Psychology",
    "Psychology/Educational Psychology",
    "Psychology/Industrial-Organizational Psychology",
    "Psychology/Research Methods",
    "Science/Philosophy of Science",
    "Science/Science Communication",
    "Science/Interdisciplinary Science",
]

template = """Generate 5 unique science questions on the theme: "{theme}".

Guidelines:
- Questions must be original and non-repetitive.
- Vary the difficulty level: include a mix of basic, intermediate, and advanced questions.
- Each question should require reasoning, explanation, or calculation — not trivia.
- Use clear, precise phrasing that reads like a natural question, not an exam command.
- Avoid directive phrasing like "Calculate...", "Derive...", or "Using calculus, determine...".
- Prefer natural, curiosity-driven forms like "How does...", "What is the velocity of...", "Why does...", "What happens if...", etc.
- At least 3 of the 5 questions should lead to a numerical answer or require numerical computation (e.g. velocity, force, energy).
- Do not include meta-instructions like “Explain your reasoning” in the question text.

Output format:
Return the 5 questions in a valid JSON array, like this:
[
  "Question 1 text",
  "Question 2 text",
  "Question 3 text",
  "Question 4 text",
  "Question 5 text"
]
"""


for theme in themes:
    response = client.responses.create(model="gpt-4o", input=template.format(theme=theme))
    print(response.output_text)