{ "components": { "schemas": { "AttributesLevelsRequest": { "description": "Pydantic model for a request to create levels for attributes.", "example": { "attribute_count": 6, "country": "United States of America", "level_count": 4, "why_prompt": "What factor affect the adoption of an electric vehicle?", "year": 2025 }, "properties": { "attribute_count": { "default": 4, "description": "The number of attributes in the experiment", "maximum": 7.0, "minimum": 2.0, "title": "Attribute Count", "type": "integer" }, "country": { "title": "Country", "type": "string" }, "level_count": { "default": 4, "description": "The number of levels for each attribute in the experiment", "maximum": 5.0, "minimum": 2.0, "title": "Level Count", "type": "integer" }, "why_prompt": { "title": "Why Prompt", "type": "string" } }, "required": [ "why_prompt", "country" ], "title": "AttributesLevelsRequest", "type": "object" }, "AttributesLevelsResponse": { "description": "Pydantic model for a response with the list of attributes and levels.", "example": { "attributes_levels": [ { "attribute": "Battery Range per Charge", "levels": [ "Less than 150 miles", "150 to 250 miles", "250 to 350 miles", "350 to 450 miles", "More than 450 miles" ] }, { "attribute": "Vehicle Warranty", "levels": [ "3 years or 36,000 miles", "4 years or 50,000 miles", "5 years or 60,000 miles", "6 years or 70,000 miles", "7 years or 100,000 miles" ] } ], "brand_attribute_combinations": [ { "Availability of charging infrastructure": "Access to exclusive charging networks", "Brand": "Nissan Leaf", "Charging time": "Under 5 minutes (80% charge)", "Price": "29500.00 USD", "Range (miles)": "258 miles" }, { "Availability of charging infrastructure": "Level 2 (240V) charging compatibility", "Brand": "Chevrolet Bolt", "Charging time": "2-4 hours to full charge", "Price": "30500.00 USD", "Range (miles)": "258 miles" } ] }, "properties": { "attributes_levels": { "items": { "$ref": "#/components/schemas/LeveledAttributeBase" }, "title": "Attributes Levels", "type": "array" }, "brand_attribute_combinations": { "anyOf": [ { "items": { "additionalProperties": true, "type": "object" }, "type": "array" }, { "type": "null" } ], "title": "Brand Attribute Combinations" }, "real_world_attributes": { "title": "Real World Attributes", "type": "boolean" }, "reason": { "title": "Reason", "type": "string" } }, "required": [ "attributes_levels", "brand_attribute_combinations", "real_world_attributes", "reason" ], "title": "AttributesLevelsResponse", "type": "object" }, "AttributesRequest": { "example": { "attribute_count": 4, "country": "United States of America", "llm_model": "gpt4", "prompt_type": "generic", "why_prompt": "What factor affect the adoption of an electric vehicle?" }, "properties": { "attribute_count": { "default": 4, "maximum": 10.0, "minimum": 2.0, "title": "Attribute Count", "type": "integer" }, "country": { "title": "Country", "type": "string" }, "llm_model": { "anyOf": [ { "$ref": "#/components/schemas/LLMModel" }, { "type": "null" } ], "default": "databricks-claude-sonnet-4" }, "prompt_type": { "anyOf": [ { "$ref": "#/components/schemas/PromptType" }, { "type": "null" } ], "default": "generic" }, "why_prompt": { "title": "Why Prompt", "type": "string" } }, "required": [ "why_prompt", "country" ], "title": "AttributesRequest", "type": "object" }, "AxisReason": { "properties": { "axis": { "enum": [ "age", "household_income", "gender", "education_level", "number_of_children", "racial_group", "home_ownership", "household_with_children", "household_size" ], "title": "Axis", "type": "string" }, "boundary": { "anyOf": [ { "items": { "type": "integer" }, "type": "array" }, { "items": { "type": "string" }, "type": "array" } ], "title": "Boundary" }, "reason": { "title": "Reason", "type": "string" } }, "required": [ "axis", "boundary", "reason" ], "title": "AxisReason", "type": "object" }, "Body_execute_human_baselines_api_v1_human_baselines_execute_batch_post": { "properties": { "hb_folders_csv_file": { "format": "binary", "title": "Hb Folders Csv File", "type": "string" } }, "required": [ "hb_folders_csv_file" ], "title": "Body_execute_human_baselines_api_v1_human_baselines_execute_batch_post", "type": "object" }, "Body_extract_from_pdf_api_v1_personas_extract_from_pdf_post": { "properties": { "file": { "format": "binary", "title": "File", "type": "string" } }, "required": [ "file" ], "title": "Body_extract_from_pdf_api_v1_personas_extract_from_pdf_post", "type": "object" }, "Body_extract_traits_from_pdf_with_question_api_v1_traits_extract_from_pdf_post": { "properties": { "files": { "items": { "format": "binary", "type": "string" }, "title": "Files", "type": "array" } }, "required": [ "files" ], "title": "Body_extract_traits_from_pdf_with_question_api_v1_traits_extract_from_pdf_post", "type": "object" }, "Body_transcription_humanbaseline_api_v1_human_baselines_transcribe_from_pdf_post": { "properties": { "files": { "items": { "format": "binary", "type": "string" }, "title": "Files", "type": "array" } }, "required": [ "files" ], "title": "Body_transcription_humanbaseline_api_v1_human_baselines_transcribe_from_pdf_post", "type": "object" }, "CheckProductRealWorldResponse": { "example": { "data_available_collectible": true, "measurable_attributes": true, "product_exists": true, "score": 3, "specific_levels_definable": true }, "properties": { "data_available_collectible": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "description": "Boolean indicating whether data is available and collectible for the product", "title": "Data Available Collectible" }, "measurable_attributes": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "description": "Boolean indicating whether the product has measurable attributes", "title": "Measurable Attributes" }, "product_exists": { "description": "Boolean indicating whether the product exists in the real world", "title": "Product Exists", "type": "boolean" }, "score": { "description": "Confidence score of the model in predicting the existence of the product", "maximum": 5.0, "minimum": 0.0, "title": "Score", "type": "integer" }, "specific_levels_definable": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "description": "Boolean indicating whether the product has specific levels definable", "title": "Specific Levels Definable" } }, "required": [ "product_exists" ], "title": "CheckProductRealWorldResponse", "type": "object" }, "CheckProductRequest": { "example": { "why_prompt": "What factors affect the choice of buying an electric car?" }, "properties": { "llm_model": { "anyOf": [ { "$ref": "#/components/schemas/LLMModel" }, { "type": "null" } ], "default": "databricks-claude-sonnet-4" }, "why_prompt": { "description": "Prompt to use for checking the product's existence in the real world", "title": "Why Prompt", "type": "string" } }, "required": [ "why_prompt" ], "title": "CheckProductRequest", "type": "object" }, "ChildrenEnum": { "enum": [ "0", "1", "2", "3", "4+" ], "title": "ChildrenEnum", "type": "string" }, "CleanedRunResponse": { "example": { "confidence_level": "Reasonable", "created_at": "2025-03-07T14:23:55.126Z", "estimation_method": "HB", "experiment_type": "conjoint", "expr_llm_model": "GPT4", "id": "04700e81-832f-4c7d-ba1e-d6225716a7db", "is_private": false, "name": "transformation-25-03-07-14-23-55-126", "r_squared": 45, "sample_size": 100, "state": "finished", "tasks_per_respondent": 5, "total_number_of_tasks": 500, "why_prompt": "What influences social media engagement?" }, "properties": { "confidence_level": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Confidence Level" }, "created_at": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Created At" }, "estimation_method": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": "unknown", "title": "Estimation Method" }, "experiment_type": { "default": "conjoint", "title": "Experiment Type", "type": "string" }, "expr_llm_model": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Expr Llm Model" }, "id": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Id" }, "is_private": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "title": "Is Private" }, "name": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Name" }, "r_squared": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "title": "R Squared" }, "sample_size": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "title": "Sample Size" }, "state": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "State" }, "tasks_per_respondent": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "title": "Tasks Per Respondent" }, "total_number_of_tasks": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "title": "Total Number Of Tasks" }, "why_prompt": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Why Prompt" } }, "title": "CleanedRunResponse", "type": "object" }, "ConceptRunResponse": { "example": { "concept_type": "Text Only", "created_at": "2025-03-07T14:23:55.126Z", "id": "04700e81-832f-4c7d-ba1e-d6225716a7db", "is_private": false, "name": "Mile& Package Testing", "sample_size": 100, "state": "finished" }, "properties": { "concept_type": { "default": "", "title": "Concept Type", "type": "string" }, "created_at": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Created At" }, "id": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Id" }, "is_private": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "title": "Is Private" }, "name": { "default": "", "title": "Name", "type": "string" }, "sample_size": { "default": 0, "title": "Sample Size", "type": "integer" }, "state": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "State" } }, "title": "ConceptRunResponse", "type": "object" }, "ConstraintRequest": { "example": { "attributes": [ "price", "operating_system", "battery_life", "camera_quality", "storage_capacity" ], "llm_model": "gpt4", "user_profile_attributes": { "age_levels": [ 25, 30 ], "education_levels": [ "Bachelors Degree" ], "gender_levels": [ "Male" ], "income_levels": [ 50000, 75000 ] }, "why_prompt": "What factors influence your choice in selecting a mobile phone?" }, "properties": { "attributes": { "items": { "type": "string" }, "title": "Attributes", "type": "array" }, "llm_model": { "anyOf": [ { "$ref": "#/components/schemas/LLMModel" }, { "type": "null" } ], "default": "databricks-claude-sonnet-4" }, "user_profile_attributes": { "additionalProperties": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "items": { "type": "integer" }, "type": "array" }, { "items": { "type": "number" }, "type": "array" } ] }, "title": "User Profile Attributes", "type": "object" }, "why_prompt": { "title": "Why Prompt", "type": "string" } }, "required": [ "why_prompt", "user_profile_attributes", "attributes" ], "title": "ConstraintRequest", "type": "object" }, "ConstraintResponse": { "example": { "constraints": { "After-Sales Service": "Quality and accessibility of customer support and service", "Availability": "Ease of finding and purchasing the desired mobile phone model", "Brand Loyalty": "User's tendency to stick with familiar or preferred brands", "Budget": "Financial limitations affecting mobile phone purchase decisions", "Technological Compatibility": "Compatibility with existing devices and software", "User Reviews": "Influence of other users' experiences and feedback", "Warranty": "Availability and terms of warranty for the mobile phone" } }, "properties": { "constraints": { "additionalProperties": { "type": "string" }, "title": "Constraints", "type": "object" } }, "required": [ "constraints" ], "title": "ConstraintResponse", "type": "object" }, "DemographicBoundary": { "properties": { "age": { "items": { "type": "integer" }, "title": "Age", "type": "array" }, "education_level": { "items": { "$ref": "#/components/schemas/EducationLevelEnum" }, "title": "Education Level", "type": "array" }, "gender": { "items": { "$ref": "#/components/schemas/GenderEnum" }, "title": "Gender", "type": "array" }, "household_income": { "items": { "type": "integer" }, "title": "Household Income", "type": "array" }, "number_of_children": { "items": { "$ref": "#/components/schemas/ChildrenEnum" }, "title": "Number Of Children", "type": "array" }, "racial_group": { "items": { "$ref": "#/components/schemas/RacialGroupEnum" }, "title": "Racial Group", "type": "array" } }, "required": [ "age", "household_income", "gender", "education_level", "number_of_children", "racial_group" ], "title": "DemographicBoundary", "type": "object" }, "DependentVariable": { "example": { "prompt_type": "generic", "why_prompt": "How does social media usage affect sleep patterns?" }, "properties": { "llm_model": { "$ref": "#/components/schemas/LLMModel", "default": "databricks-claude-sonnet-4" }, "prompt_type": { "anyOf": [ { "$ref": "#/components/schemas/PromptType" }, { "type": "null" } ], "default": "generic" }, "why_prompt": { "title": "Why Prompt", "type": "string" } }, "required": [ "why_prompt" ], "title": "DependentVariable", "type": "object" }, "DependentVariableResponse": { "properties": { "Preference_Instruction": { "title": "Preference Instruction", "type": "string" } }, "required": [ "Preference_Instruction" ], "title": "DependentVariableResponse", "type": "object" }, "EducationLevelEnum": { "enum": [ "Some College", "High School Diploma", "Less than high school", "High School but no diploma", "Bachelors", "Associates", "Masters", "PhD" ], "title": "EducationLevelEnum", "type": "string" }, "EnhanceAttributesLevelsRequest": { "example": { "existing_attributes_levels": [ { "attribute": "Battery Range per Charge", "levels": [ "Less than 150 miles", "150 to 250 miles" ] }, { "attribute": "Vehicle Warranty", "levels": [ "3 years or 36,000 miles", "4 years or 50,000 miles" ] } ], "why_prompt": "What are the factors that influence the purchase of an electric vehicle?" }, "properties": { "existing_attributes_levels": { "items": { "$ref": "#/components/schemas/LeveledAttribute" }, "title": "Existing Attributes Levels", "type": "array" }, "llm_model": { "anyOf": [ { "$ref": "#/components/schemas/LLMModel" }, { "type": "null" } ], "default": "databricks-claude-sonnet-4" }, "why_prompt": { "title": "Why Prompt", "type": "string" } }, "required": [ "why_prompt", "existing_attributes_levels" ], "title": "EnhanceAttributesLevelsRequest", "type": "object" }, "Experiment": { "example": { "add_neither_option": true, "check_for_continuous_variables": true, "concept_description": "", "concept_statements": [ { "labels": [ "Strongly Disagree", "Disagree", "Neutral", "Agree", "Strongly Agree" ], "statement": "This smoothie would provide me with sustained energy throughout the day." }, { "labels": [ "Strongly Disagree", "Disagree", "Neutral", "Agree", "Strongly Agree" ], "statement": "The protein content of this product meets my nutritional needs." }, { "labels": [ "Strongly Disagree", "Disagree", "Neutral", "Agree", "Strongly Agree" ], "statement": "The flavor varieties offered are appealing to me." }, { "labels": [ "Strongly Disagree", "Disagree", "Neutral", "Agree", "Strongly Agree" ], "statement": "I would purchase this smoothie as a healthy meal replacement option." } ], "country": "USA", "do_research": false, "effect_encoding": true, "ensure_25_trait_level_count": false, "experiment_type": "conjoint", "external_personas": [ "https://uk.linkedin.com/in/samgadsby", "https://www.linkedin.com/in/bencheatham", "https://uk.linkedin.com/in/simonmelaniphy", "https://uk.linkedin.com/in/alex-velinov", "https://www.linkedin.com/in/martinkronstad", "https://uk.linkedin.com/in/pshannon" ], "hb_folder": "", "hb_run_id": "", "image_name1": "d78f470a-90ad-4b1e-a322-cb4cc9cc631b.png", "image_name2": "", "is_private": false, "match_population_distribution": false, "mnp_model": true, "non_us_target_population": { "Age": [ 18, 92 ], "Education_Level": [ "Masters", "Bachelors", "Some College", "PhD", "High School but no diploma", "High School Diploma", "Associates", "Less than high school" ], "Gender": [ "Female", "Male" ], "Home_Ownership": [ "Own", "Rent", "Other" ], "Household_Size": [ "4", "2", "1", "3", "More than 4 people" ], "Household_With_Children": [ "Yes", "No" ] }, "null_levels": true, "population_group": "Urban Singles", "population_traits": { "Big five conscientiousness": [ "Flexible", "Balanced", "Structured" ], "Price Sensitivity": [ "Highly Price Sensitive", "Value Seeker", "Premium Acceptor", "Price Indifferent" ], "Risk Aversion": [ "Highly Risk Averse", "Cautious", "Risk Tolerant", "Risk Seeking" ], "Vehicles In Household": [ "0", "1", "2", "3", "4", "4+" ] }, "pre_cooked_attributes_and_levels_lookup": [ [ "Price", [ "599 USD", "450 USD", "799 USD", "900 USD", "499 USD" ] ], [ "Display Size", [ "6.1-inch", "6.7-inch", "6.3-inch" ] ], [ "RAM", [ "6 GB", "12 GB", "8 GB" ] ], [ "Internal Storage", [ "128 GB", "256 GB" ] ], [ "Battery Capacity", [ "5000 mAh", "4492 mAh", "3274 mAh", "3692 mAh", "4000 mAh" ] ], [ "Main Camera", [ "50 MP + 12 MP + 10 MP", "48 MP", "48 MP + 48 MP", "48 MP + 12 MP", "50 MP + 8 MP + 5 MP" ] ], [ "Chipset", [ "A19", "Tensor G4", "Snapdragon 8 Elite Gen 5", "Exynos 1380", "A18" ] ], [ "Operating System", [ "Android 15", "Android 16", "iOS 26" ] ], [ "Weight", [ "177 grams", "188 grams", "189 grams", "167 grams" ] ], [ "Product", [ "Samsung (Galaxy A57 5G)", "Samsung (Galaxy S26)", "Apple (iPhone 17e)", "Apple (iPhone 17)", "Google (Pixel 10a)" ] ] ], "realworld_products": [ {} ], "respondent_instruction_for_concept": "View the concept (image) and rate the following statements based on your first impression. Use only the info shown. No right or wrong answers.", "response_type": "discrete", "survey_editable_lines": { "1": "You are tasked with answering a conjoint survey question related to examining factors that influence purchase of facial moisturizer as the following individual:", "10": "Before selecting an option, consider the following:\n1. Consider how your demographic traits and lifestyle influence your priorities for the decision.\n2. Evaluate the options in the survey question based on these priorities.", "12": "Please read the descriptions of facial moisturizers (50ml) carefully. Then, please select which facial moisturizer you would purchase.", "4": "Imagine you are in a situation where You need to purchase a facial moisturizer for your daily skincare routine from an online retailer that provides detailed product specifications.", "5": " - Consider the different combinations of factors and select the option that would most likely lead to the maximize level of purchase of facial moisturizer.", "6": " - When evaluating each option, consider how the combination of factors would realistically interact to affect purchase of facial moisturizer.", "7": " - Choose the scenario where the presented conditions would be most conducive to maximizing purchase of facial moisturizer.", "8": "", "9": "Answer the survey question as this person, following these steps:" }, "target_population": { "age": [ 18, 95 ], "education_level": [ "Less than high school", "High School but no diploma", "High School Diploma", "Some College", "Associates", "Bachelors", "Masters", "PhD" ], "gender": [ "Male", "Female" ], "household_income": [ 0, 150000 ], "number_of_children": [ "1", "2", "3", "4+" ], "racial_group": [ "White", "African American", "American Indian or Alaska Native", "Asian or Pacific Islander", "Mixed race", "Other race" ] }, "use_external_personas": false, "use_halton_draws": false, "use_population_group": false, "user_uploaded_persona": false, "why_prompt": "What are the key factors influencing consumers' purchase consideration and preference for upgrading their mobile devices, such as from an iPhone 12 to an iPhone 15 or Samsung Galaxy S22 to S24?", "year": "July 2026" }, "properties": { "add_neither_option": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": true, "title": "Add Neither Option" }, "additional_notes_max_workers": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": 100, "title": "Additional Notes Max Workers" }, "all_combinations_index": { "anyOf": [ { "items": { "items": { "type": "string" }, "type": "array" }, "type": "array" }, { "type": "null" } ], "default": [ [ "" ] ], "title": "All Combinations Index" }, "alternative_shuffle_seed": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": 10000, "title": "Alternative Shuffle Seed" }, "attribute_count": { "anyOf": [ { "maximum": 10.0, "minimum": 2.0, "type": "integer" }, { "type": "null" } ], "default": 8, "title": "Attribute Count" }, "attribute_shuffle_seed": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": 1000, "title": "Attribute Shuffle Seed" }, "batch_size": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": 20, "title": "Batch Size" }, "binary_choice": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": false, "title": "Binary Choice" }, "block_optimization_iteration_limit": { "default": 100, "title": "Block Optimization Iteration Limit", "type": "integer" }, "check_for_continuous_variables": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": true, "title": "Check For Continuous Variables" }, "concept_description": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Concept Description" }, "concept_heading": { "default": "", "title": "Concept Heading", "type": "string" }, "concept_statements": { "anyOf": [ { "items": { "additionalProperties": true, "type": "object" }, "type": "array" }, { "type": "null" } ], "title": "Concept Statements" }, "confidence_level": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": "Low", "title": "Confidence Level" }, "conjoint_time": { "default": 0.0, "title": "Conjoint Time", "type": "number" }, "context": { "default": "", "title": "Context", "type": "string" }, "cost_amount": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": 0.0, "title": "Cost Amount" }, "country": { "default": "United States", "title": "Country", "type": "string" }, "coverage_probability": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": 0.0, "title": "Coverage Probability" }, "dcm_survey_workers": { "default": 128, "title": "Dcm Survey Workers", "type": "integer" }, "decision_time_seed": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": 1000, "title": "Decision Time Seed" }, "do_research": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": false, "title": "Do Research" }, "dv_llm_model": { "anyOf": [ { "$ref": "#/components/schemas/LLMModel" }, { "type": "null" } ], "default": "databricks-claude-sonnet-4" }, "effect_encoding": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": true, "title": "Effect Encoding" }, "ensure_25_trait_level_count": { "default": false, "title": "Ensure 25 Trait Level Count", "type": "boolean" }, "estimation_method": { "default": "HB", "enum": [ "MLE", "HB" ], "title": "Estimation Method", "type": "string" }, "experiment_type": { "default": "conjoint", "enum": [ "concept_testing", "conjoint" ], "title": "Experiment Type", "type": "string" }, "expr_llm_model": { "anyOf": [ { "$ref": "#/components/schemas/LLMModel" }, { "type": "null" } ], "default": "databricks-claude-sonnet-4" }, "external_personas": { "default": [], "items": { "type": "string" }, "title": "External Personas", "type": "array" }, "generate_additional_notes": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": false, "title": "Generate Additional Notes" }, "hb_folder": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": "", "title": "Hb Folder" }, "hb_run_id": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": "", "title": "Hb Run Id" }, "image_name1": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Image Name1" }, "image_name2": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Image Name2" }, "include_price_brand": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": false, "title": "Include Price Brand" }, "is_hb_run": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": false, "title": "Is Hb Run" }, "is_private": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": false, "title": "Is Private" }, "latent_variables": { "default": true, "title": "Latent Variables", "type": "boolean" }, "latent_variables_llm_model": { "anyOf": [ { "$ref": "#/components/schemas/LLMModel" }, { "type": "null" } ], "default": "databricks-claude-sonnet-4" }, "latent_variables_measurement_count": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": 3, "title": "Latent Variables Measurement Count" }, "latent_variables_scale_labels_count": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": 5, "title": "Latent Variables Scale Labels Count" }, "latent_variables_traits_count": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": 4, "title": "Latent Variables Traits Count" }, "level_count": { "anyOf": [ { "maximum": 10.0, "minimum": 2.0, "type": "integer" }, { "type": "null" } ], "default": 5, "title": "Level Count" }, "levels_llm_model": { "anyOf": [ { "$ref": "#/components/schemas/LLMModel" }, { "type": "null" } ], "default": "databricks-claude-sonnet-4" }, "levels_per_trait": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": 100, "title": "Levels Per Trait" }, "llm_temperature": { "default": 1.0, "title": "Llm Temperature", "type": "number" }, "lv_based_nl_summary_max_workers": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": 100, "title": "Lv Based Nl Summary Max Workers" }, "lv_statement_llm_model": { "anyOf": [ { "$ref": "#/components/schemas/LLMModel" }, { "type": "null" } ], "default": "databricks-claude-sonnet-4" }, "lv_statement_max_workers": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": 100, "title": "Lv Statement Max Workers" }, "match_population_distribution": { "default": false, "title": "Match Population Distribution", "type": "boolean" }, "match_population_distribution_concept": { "default": true, "title": "Match Population Distribution Concept", "type": "boolean" }, "max_length": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": 40, "title": "Max Length" }, "mnp_model": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": true, "title": "Mnp Model" }, "mood_statement_seed": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": 178942, "title": "Mood Statement Seed" }, "non_us_target_population": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": {}, "title": "Non Us Target Population" }, "null_levels": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": true, "title": "Null Levels" }, "optimization_context": { "default": "", "title": "Optimization Context", "type": "string" }, "paper_data": { "anyOf": [ { "items": { "items": { "type": "string" }, "type": "array" }, "type": "array" }, { "type": "null" } ], "default": [], "title": "Paper Data" }, "persona_nl_llm_model": { "anyOf": [ { "$ref": "#/components/schemas/LLMModel" }, { "type": "null" } ], "default": "databricks-claude-sonnet-4" }, "persona_nl_workers": { "default": 128, "title": "Persona Nl Workers", "type": "integer" }, "population_group": { "anyOf": [ { "$ref": "#/components/schemas/GroupLabel" }, { "type": "null" } ] }, "population_seed": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": 100, "title": "Population Seed" }, "population_traits": { "anyOf": [ { "$ref": "#/components/schemas/PopulationTraits" }, { "type": "null" } ], "default": {} }, "pre_cooked_attributes_and_levels_lookup": { "anyOf": [ { "items": { "items": { "anyOf": [ { "type": "string" }, { "items": { "type": "string" }, "type": "array" } ] }, "type": "array" }, "type": "array" }, { "type": "null" } ], "default": [], "title": "Pre Cooked Attributes And Levels Lookup" }, "predict_trait_workers": { "default": 128, "title": "Predict Trait Workers", "type": "integer" }, "price_generation_seed": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": 1000, "title": "Price Generation Seed" }, "prob_to_discrete_seed": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": 500, "title": "Prob To Discrete Seed" }, "prompt_type": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": "generic", "title": "Prompt Type" }, "r_analytics_time": { "default": 0.0, "title": "R Analytics Time", "type": "number" }, "r_squared": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": 0, "title": "R Squared" }, "realworld_products": { "anyOf": [ { "items": { "additionalProperties": true, "type": "object" }, "type": "array" }, { "type": "null" } ], "default": [], "title": "Realworld Products" }, "respondent_dependent_variable": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": "", "title": "Respondent Dependent Variable" }, "respondent_instruction_for_concept": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Respondent Instruction For Concept" }, "respondent_instructions_preamble": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": "", "title": "Respondent Instructions Preamble" }, "response_type": { "anyOf": [ { "$ref": "#/components/schemas/SurveyResponseType" }, { "type": "null" } ], "default": "discrete" }, "sample_size": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": 0, "title": "Sample Size" }, "score_llm_model": { "anyOf": [ { "$ref": "#/components/schemas/LLMModel" }, { "type": "null" } ], "default": "databricks-claude-sonnet-4" }, "spearman_correlation": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": 0.0, "title": "Spearman Correlation" }, "state": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "State" }, "survey_design_filelink": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": "", "title": "Survey Design Filelink" }, "survey_editable_lines": { "anyOf": [ { "additionalProperties": { "type": "string" }, "type": "object" }, { "type": "null" } ], "default": {}, "title": "Survey Editable Lines" }, "survey_prompt": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": "Respondent Instructions:\nYou are answering questions as if you are a human. Do not break character.\nYou are an agent with the following personas: {persona_traits}.\nCurrently living in {state}, {country}, Time of Survey: year: {year}.\n\nInstructions:\n{study_subject}.\nIn this context, we have designed a discrete choice survey question where you are presented with three options/alternatives including None of these.\nThe options/alternatives are defined as a function of attribute-level combinations.\nBelow we provide the list of attributes/features and the possible values (attribute level) it may take.\n{attributes_levels}.\n\nConsider the options in the Questionnaire below. Please read the specifications carefully.\nThen, select the most preferred option considering that the current year is {year} and your place of residence is {country}.\n\nQuestionnaire:\n{options}\n{none_option}: None of these\n{format_instructions}", "title": "Survey Prompt" }, "target_behavior": { "default": "", "title": "Target Behavior", "type": "string" }, "target_behavior_context": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": false, "title": "Target Behavior Context" }, "target_population": { "anyOf": [ { "$ref": "#/components/schemas/TargetPopulation" }, { "type": "null" } ], "default": {} }, "tasks_per_respondent": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": 0, "title": "Tasks Per Respondent" }, "title": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": "", "title": "Title" }, "token_count": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": 0, "title": "Token Count" }, "total_number_of_tasks": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": 0, "title": "Total Number Of Tasks" }, "trait_prediction_llm_model": { "anyOf": [ { "$ref": "#/components/schemas/LLMModel" }, { "type": "null" } ], "default": "databricks-claude-sonnet-4" }, "use_api": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": true, "title": "Use Api" }, "use_batching": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": true, "title": "Use Batching" }, "use_external_personas": { "default": false, "title": "Use External Personas", "type": "boolean" }, "use_halton_draws": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": false, "title": "Use Halton Draws" }, "use_multiprocessing": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": false, "title": "Use Multiprocessing" }, "use_population_group": { "default": false, "title": "Use Population Group", "type": "boolean" }, "use_preassigned_blocks": { "default": false, "title": "Use Preassigned Blocks", "type": "boolean" }, "use_threading": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": true, "title": "Use Threading" }, "user_uploaded_persona": { "default": false, "title": "User Uploaded Persona", "type": "boolean" }, "user_uploaded_persona_filelink": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": "", "title": "User Uploaded Persona Filelink" }, "why_prompt": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": "", "title": "Why Prompt" }, "year": { "default": "July 2026", "title": "Year", "type": "string" } }, "title": "Experiment", "type": "object" }, "ExperimentAsyncResponse": { "properties": { "wandb_run_id": { "title": "Wandb Run Id", "type": "string" }, "wandb_run_name": { "title": "Wandb Run Name", "type": "string" } }, "required": [ "wandb_run_id", "wandb_run_name" ], "title": "ExperimentAsyncResponse", "type": "object" }, "ExperimentConfigurationPatch": { "properties": { "country": { "default": "United States", "title": "Country", "type": "string" }, "state": { "$ref": "#/components/schemas/USStatesEnum" }, "target_population": { "additionalProperties": true, "title": "Target Population", "type": "object" }, "why_prompt": { "title": "Why Prompt", "type": "string" }, "year": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Year" } }, "required": [ "state", "why_prompt", "target_population" ], "title": "ExperimentConfigurationPatch", "type": "object" }, "GenderEnum": { "enum": [ "Male", "Female" ], "title": "GenderEnum", "type": "string" }, "GenerationRequest": { "example": { "measurement_count": 4, "scale_labels_count": 5, "traits_count": 2, "why_prompt": "There's been a lot of discussion about Samsung's recent innovations in display technology and camera systems, particularly with their Galaxy lineup. I'm interested in exploring Samsung's current smartphone offerings to understand how their latest models compare in terms of display quality, camera capabilities, and overall performance, especially since they've been positioning themselves as a premium alternative in the market." }, "properties": { "additional_note_workers": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": 100, "description": "Number of workers for generating additional notes.", "examples": [ 100, 200 ], "title": "Additional Note Workers" }, "generate_additional_notes": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": true, "description": "Whether to generate additional notes.", "examples": [ true, false ], "title": "Generate Additional Notes" }, "lv_based_nl_summary_max_workers": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": 100, "description": "Number of workers for generating latent variable-based natural language summaries.", "examples": [ 100, 200 ], "title": "Lv Based Nl Summary Max Workers" }, "lv_statement_max_workers": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": 100, "description": "Number of workers for answering latent variable statements.", "examples": [ 100, 200 ], "title": "Lv Statement Max Workers" }, "measurement_count": { "default": 2, "description": "Number of trait measurement statements to generate.", "examples": [ 2, 4 ], "title": "Measurement Count", "type": "integer" }, "scale_labels_count": { "default": 5, "description": "Number of labels in the Likert scale (e.g., 5 for a 5-point Likert scale).", "examples": [ 5, 9 ], "maximum": 9.0, "minimum": 4.0, "title": "Scale Labels Count", "type": "integer" }, "traits_count": { "default": 2, "description": "Number of psychological traits or characteristics to identify.", "examples": [ 2 ], "title": "Traits Count", "type": "integer" }, "why_prompt": { "description": "A question or topic area that involves human decision-making, preferences, or behavior.", "examples": [ "What factors affect venture capitalists' decisions to invest in early-stage startups?", "What factors affect the choice of a car?" ], "title": "Why Prompt", "type": "string" } }, "required": [ "why_prompt" ], "title": "GenerationRequest", "type": "object" }, "GroupLabel": { "enum": [ "Urban Singles", "Suburban Families", "Career-Oriented Professionals", "Young College Students", "Empty Nesters", "Retired Widows/Widowers", "Young Parents on a Budget", "High-Income Dual-Earner Couples", "Tech-Savvy Millennials", "Blue-Collar Workers", "Single Mothers", "Older Retirees", "Highly Educated Elites", "Affluent Empty Nesters", "Graduate Students", "Large Suburban Families", "Hispanic Professionals", "Educated Single Women" ], "title": "GroupLabel", "type": "string" }, "HistoryResponse": { "example": { "history": { "Brand Loyalty": "The user's tendency to stick with particular mobile phone brands over time", "Feature Preferences": "The specific features the user has prioritized in past mobile phone purchases", "Previous Phone Brands": "The specific mobile phone brands the user has used in the past", "Previous Purchase Channels": "The places or methods through which the user typically buys mobile phones (e.g., online, retail stores)", "Previous Purchase Frequency": "How often the user typically buys new mobile phones", "Price Sensitivity": "The user's historical responsiveness to mobile phone prices and willingness to pay" } }, "properties": { "history": { "additionalProperties": { "type": "string" }, "title": "History", "type": "object" } }, "required": [ "history" ], "title": "HistoryResponse", "type": "object" }, "LLMModel": { "description": "Enum representing the llm model types used in the experiments.", "enum": [ "azure-openai-gpt4", "azure-openai-gpt4o-mini", "azure-openai-gpt35", "azure-openai-gpto3-mini", "azure-openai-completions", "sonar", "databricks-sonnet4", "databricks-claude-sonnet-4", "databricks-llama4-maverick", "databricks-llama3.3-70B", "databricks-llama3.3-405B", "bedrock:xai.grok-4.3" ], "title": "LLMModel", "type": "string" }, "LatentClassInput": { "example": { "behaviour_optimization_direction": "Maximize", "context": "Understanding consumer preferences for eco-friendly products in the market", "lv_class_membership_output": [ { "beta": 0, "class": "Class 1", "latent_construct": "Environmental Consciousness" }, { "beta": 0, "class": "Class 1", "latent_construct": "Price Sensitivity" }, { "beta": 0.8, "class": "Class 2", "latent_construct": "Environmental Consciousness" }, { "beta": -0.3, "class": "Class 2", "latent_construct": "Price Sensitivity" } ], "lv_model_output": [ { "attribute": "Price", "beta": 1.2, "class": "Class 1", "level": "Low", "significant": "Yes" }, { "attribute": "Price", "beta": 0, "class": "Class 1", "level": "Medium", "significant": "base_level" }, { "attribute": "Price", "beta": -0.8, "class": "Class 1", "level": "High", "significant": "Yes" }, { "attribute": "Price", "beta": -1.5, "class": "Class 1", "level": "Very High", "significant": "Yes" }, { "attribute": "Eco-Friendliness", "beta": -0.2, "class": "Class 1", "level": "Low", "significant": "No" }, { "attribute": "Eco-Friendliness", "beta": 0, "class": "Class 1", "level": "Medium", "significant": "base_level" }, { "attribute": "Eco-Friendliness", "beta": 0.4, "class": "Class 1", "level": "High", "significant": "Yes" }, { "attribute": "Eco-Friendliness", "beta": 0.5, "class": "Class 1", "level": "Very High", "significant": "Yes" }, { "attribute": "Price", "beta": -0.8, "class": "Class 2", "level": "Low", "significant": "Yes" }, { "attribute": "Price", "beta": 0, "class": "Class 2", "level": "Medium", "significant": "base_level" }, { "attribute": "Price", "beta": 0.4, "class": "Class 2", "level": "High", "significant": "Yes" }, { "attribute": "Price", "beta": 0.9, "class": "Class 2", "level": "Very High", "significant": "Yes" }, { "attribute": "Eco-Friendliness", "beta": -1.1, "class": "Class 2", "level": "Low", "significant": "Yes" }, { "attribute": "Eco-Friendliness", "beta": 0, "class": "Class 2", "level": "Medium", "significant": "base_level" }, { "attribute": "Eco-Friendliness", "beta": 0.7, "class": "Class 2", "level": "High", "significant": "Yes" }, { "attribute": "Eco-Friendliness", "beta": 1.8, "class": "Class 2", "level": "Very High", "significant": "Yes" } ], "num_classes": 2, "psychological_constructs_output": [ { "beta": -0.4, "demographic_variable": "Gender", "dependent_variable": "Environmental Consciousness", "level": "Male", "significant": "Yes" }, { "beta": 0.0, "demographic_variable": "Gender", "dependent_variable": "Environmental Consciousness", "level": "Female", "significant": "base_level" }, { "beta": -0.6, "demographic_variable": "Income", "dependent_variable": "Environmental Consciousness", "level": "Low", "significant": "Yes" }, { "beta": -0.2, "demographic_variable": "Income", "dependent_variable": "Environmental Consciousness", "level": "Medium", "significant": "No" }, { "beta": 0.0, "demographic_variable": "Income", "dependent_variable": "Environmental Consciousness", "level": "High", "significant": "base_level" }, { "beta": 0.1, "demographic_variable": "Gender", "dependent_variable": "Price Sensitivity", "level": "Male", "significant": "No" }, { "beta": 0.0, "demographic_variable": "Gender", "dependent_variable": "Price Sensitivity", "level": "Female", "significant": "base_level" }, { "beta": 1.2, "demographic_variable": "Income", "dependent_variable": "Price Sensitivity", "level": "Low", "significant": "Yes" }, { "beta": 0.5, "demographic_variable": "Income", "dependent_variable": "Price Sensitivity", "level": "Medium", "significant": "Yes" }, { "beta": 0.0, "demographic_variable": "Income", "dependent_variable": "Price Sensitivity", "level": "High", "significant": "base_level" } ], "respondent_instruction": "Please choose the product you would most likely purchase based on the attributes provided", "target_behaviour": "Purchase of eco-friendly products" }, "properties": { "behaviour_optimization_direction": { "title": "Behaviour Optimization Direction", "type": "string" }, "context": { "title": "Context", "type": "string" }, "lv_class_membership_output": { "items": { "additionalProperties": true, "type": "object" }, "title": "Lv Class Membership Output", "type": "array" }, "lv_model_output": { "items": { "additionalProperties": true, "type": "object" }, "title": "Lv Model Output", "type": "array" }, "num_classes": { "title": "Num Classes", "type": "integer" }, "psychological_constructs_output": { "items": { "additionalProperties": true, "type": "object" }, "title": "Psychological Constructs Output", "type": "array" }, "respondent_instruction": { "title": "Respondent Instruction", "type": "string" }, "target_behaviour": { "title": "Target Behaviour", "type": "string" } }, "required": [ "context", "respondent_instruction", "target_behaviour", "behaviour_optimization_direction", "lv_model_output", "lv_class_membership_output", "psychological_constructs_output", "num_classes" ], "title": "LatentClassInput", "type": "object" }, "LeveledAttribute": { "description": "Notes:\n# 1: Remember the brands and price attributes when setting ranges.\n# 2: GPT3 sometimes generates more or less than required, so the range should be flexible by 2-3.", "example": { "levels": [ "Black", "Brown", "Beige", "Navy", "Gray" ] }, "properties": { "attribute": { "description": "Name of the attribute", "title": "Attribute", "type": "string" }, "levels": { "items": { "type": "string" }, "maxItems": 15, "minItems": 2, "title": "Levels", "type": "array" } }, "required": [ "attribute", "levels" ], "title": "LeveledAttribute", "type": "object" }, "LeveledAttributeBase": { "example": { "attribute": "Battery Range per Charge", "levels": [ "Less than 150 miles", "150 to 250 miles", "250 to 350 miles", "350 to 450 miles", "More than 450 miles" ] }, "properties": { "attribute": { "description": "Name of the attribute", "title": "Attribute", "type": "string" }, "levels": { "description": "List of levels for the attribute", "items": { "type": "string" }, "title": "Levels", "type": "array" } }, "required": [ "attribute", "levels" ], "title": "LeveledAttributeBase", "type": "object" }, "LevelsRequest": { "example": { "attributes": [ "Battery Range per Charge" ], "country": "United States of America", "existing_attributes": [ "Price", "Vehicle Warranty" ], "level_count": 4, "llm_model": "gpt4", "why_prompt": "What factor affect the adoption of an electric vehicle?" }, "properties": { "attributes": { "items": { "type": "string" }, "title": "Attributes", "type": "array" }, "country": { "title": "Country", "type": "string" }, "existing_attributes": { "items": { "type": "string" }, "title": "Existing Attributes", "type": "array" }, "level_count": { "default": 4, "maximum": 10.0, "minimum": 2.0, "title": "Level Count", "type": "integer" }, "llm_model": { "anyOf": [ { "$ref": "#/components/schemas/LLMModel" }, { "type": "null" } ], "default": "databricks-claude-sonnet-4" }, "why_prompt": { "title": "Why Prompt", "type": "string" } }, "required": [ "why_prompt", "country", "existing_attributes", "attributes" ], "title": "LevelsRequest", "type": "object" }, "LikertLabel": { "example": { "labels": [ "Strongly Disagree", "Disagree", "Neutral", "Agree", "Strongly Agree" ], "statement": "The onboarding process was helpful." }, "properties": { "labels": { "items": { "type": "string" }, "title": "Labels", "type": "array" }, "statement": { "title": "Statement", "type": "string" } }, "required": [ "statement", "labels" ], "title": "LikertLabel", "type": "object" }, "LikertLabelRequest": { "example": { "concept_description": "We're evaluating a new on the go smoothie product and would like to understand people's perception towards it.", "image_name1": "milk-image.png", "scale": 5, "statements": [ "Would taste great", "Would have good texture", "Would be something I, or others in my family, look forward to drinking" ] }, "properties": { "concept_description": { "default": "", "title": "Concept Description", "type": "string" }, "image_name1": { "default": "", "title": "Image Name1", "type": "string" }, "scale": { "default": 5, "maximum": 10.0, "minimum": 1.0, "title": "Scale", "type": "integer" }, "statements": { "default": [], "items": { "type": "string" }, "title": "Statements", "type": "array" } }, "title": "LikertLabelRequest", "type": "object" }, "LikertLabelResponse": { "example": { "likert_labels": [ { "labels": [ "Strongly Disagree", "Disagree", "Neutral", "Agree", "Strongly Agree" ], "statement": "The onboarding process was helpful." } ] }, "properties": { "likert_labels": { "items": { "$ref": "#/components/schemas/LikertLabel" }, "title": "Likert Labels", "type": "array" } }, "required": [ "likert_labels" ], "title": "LikertLabelResponse", "type": "object" }, "LocationRecommendationAsyncResponse": { "properties": { "job_id": { "title": "Job Id", "type": "string" }, "status": { "enum": [ "pending", "running", "complete", "failed" ], "title": "Status", "type": "string" } }, "required": [ "job_id", "status" ], "title": "LocationRecommendationAsyncResponse", "type": "object" }, "LocationRecommendationJobResponse": { "properties": { "error": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Error" }, "job_id": { "title": "Job Id", "type": "string" }, "result": { "anyOf": [ { "$ref": "#/components/schemas/LocationRecommendationResult" }, { "type": "null" } ] }, "status": { "enum": [ "pending", "running", "complete", "failed" ], "title": "Status", "type": "string" } }, "required": [ "job_id", "status" ], "title": "LocationRecommendationJobResponse", "type": "object" }, "LocationRecommendationRequest": { "properties": { "country": { "default": "United States", "title": "Country", "type": "string" }, "pre_selected_states": { "items": { "$ref": "#/components/schemas/USStatesEnum" }, "title": "Pre Selected States", "type": "array" }, "why_prompt": { "minLength": 1, "title": "Why Prompt", "type": "string" }, "year": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Year" } }, "required": [ "why_prompt" ], "title": "LocationRecommendationRequest", "type": "object" }, "LocationRecommendationResult": { "properties": { "assumptions": { "additionalProperties": true, "title": "Assumptions", "type": "object" }, "axis_reasons": { "items": { "$ref": "#/components/schemas/AxisReason" }, "title": "Axis Reasons", "type": "array" }, "experiment_configuration_patches": { "items": { "$ref": "#/components/schemas/ExperimentConfigurationPatch" }, "title": "Experiment Configuration Patches", "type": "array" }, "non_us_target_population": { "anyOf": [ { "$ref": "#/components/schemas/NonUSDemographicBoundary" }, { "type": "null" } ] }, "population_configuration": { "additionalProperties": true, "title": "Population Configuration", "type": "object" }, "rationale": { "title": "Rationale", "type": "string" }, "recommended_states": { "items": { "$ref": "#/components/schemas/RecommendedState" }, "title": "Recommended States", "type": "array" }, "target_population": { "anyOf": [ { "$ref": "#/components/schemas/DemographicBoundary" }, { "type": "null" } ] }, "warnings": { "items": { "type": "string" }, "title": "Warnings", "type": "array" } }, "required": [ "axis_reasons", "population_configuration", "rationale", "recommended_states" ], "title": "LocationRecommendationResult", "type": "object" }, "MotivationRequest": { "example": { "attributes": [ "Range of Car", "Price of Car", "Battery Charging Time", "Maintenance Costs", "Environmental Impact", "Social Status", "Government Incentives", "Initial Purchase Cost", "Long-term Savings", "Brand Image", "Technology Level" ], "country": "USA", "llm_model": "gpt4", "num_questions": 4, "user_profile_attributes": { "age_levels": [ 35, 45 ], "education_levels": [ "Masters Degree" ], "gender_levels": [ "Female", "Male" ], "income_levels": [ 100000, 150000 ], "race": [ "Hispanic", "White", "African American" ] }, "why_prompt": "Why are you considering purchasing an electric vehicle?" }, "properties": { "attributes": { "items": { "type": "string" }, "title": "Attributes", "type": "array" }, "country": { "title": "Country", "type": "string" }, "llm_model": { "anyOf": [ { "$ref": "#/components/schemas/LLMModel" }, { "type": "null" } ], "default": "databricks-claude-sonnet-4" }, "num_questions": { "title": "Num Questions", "type": "integer" }, "user_profile_attributes": { "additionalProperties": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "items": { "type": "integer" }, "type": "array" }, { "items": { "type": "number" }, "type": "array" } ] }, "title": "User Profile Attributes", "type": "object" }, "why_prompt": { "title": "Why Prompt", "type": "string" } }, "required": [ "why_prompt", "user_profile_attributes", "attributes", "country", "num_questions" ], "title": "MotivationRequest", "type": "object" }, "MotivationResponse": { "example": { "motivation": { "Cost Savings": [ "How important is saving money on fuel costs to you?", "Would you consider a higher initial cost if it means lower long-term savings?" ], "Safety Consciousness": [ "How important for you are bike lanes in your town?", "How often do you wear your seatbelt when driving?" ] } }, "properties": { "motivation": { "additionalProperties": true, "title": "Motivation", "type": "object" } }, "required": [ "motivation" ], "title": "MotivationResponse", "type": "object" }, "NaturalLanguageTraitRequest": { "example": { "traits": [ { "attribute": "latino", "type": "binary" }, { "attribute": "lactose intolerant", "type": "binary" }, { "attribute": "age", "type": "non-binary" } ] }, "properties": { "traits": { "description": "List of trait names and their type (binary or non-binary) for which to get natural language descriptions", "items": { "additionalProperties": true, "type": "object" }, "title": "Traits", "type": "array" } }, "required": [ "traits" ], "title": "NaturalLanguageTraitRequest", "type": "object" }, "NonUSDemographicBoundary": { "description": "Country-appropriate demographic boundary for non-US populations.\n\nMirrors the US ``DemographicBoundary`` but uses holodeck's Non-USA axes.\nField value vocabularies are constrained (via enums / ``Literal``) to the\nexact non-US checkbox options, so any off-vocabulary LLM value is rejected\nat the boundary and the frontend prefill needs only a key rename. Note the\nnon-US axes deliberately drop household income and racial group and model\nhousehold composition as ``household_with_children`` (Yes/No) plus a\ncategorical ``household_size`` rather than a numeric child count.", "properties": { "age": { "items": { "type": "integer" }, "title": "Age", "type": "array" }, "education_level": { "items": { "$ref": "#/components/schemas/EducationLevelEnum" }, "title": "Education Level", "type": "array" }, "gender": { "items": { "$ref": "#/components/schemas/GenderEnum" }, "title": "Gender", "type": "array" }, "home_ownership": { "items": { "enum": [ "Own", "Rent" ], "type": "string" }, "title": "Home Ownership", "type": "array" }, "household_size": { "items": { "enum": [ "1", "2", "3", "4", "More than 4 people" ], "type": "string" }, "title": "Household Size", "type": "array" }, "household_with_children": { "items": { "enum": [ "Yes", "No" ], "type": "string" }, "title": "Household With Children", "type": "array" } }, "required": [ "age", "gender", "education_level", "home_ownership", "household_with_children", "household_size" ], "title": "NonUSDemographicBoundary", "type": "object" }, "OrthogonalAttributesLevelsRequest": { "description": "Pydantic model for a request to create more, new, orthogonal levels for attributes.", "example": { "country": "United States of America", "existing_attributes_levels": [ { "attribute": "Battery Range per Charge", "levels": [ "Less than 150 miles", "150 to 250 miles", "250 to 350 miles", "350 to 450 miles", "More than 450 miles" ] }, { "attribute": "Vehicle Warranty", "levels": [ "3 years or 36,000 miles", "4 years or 50,000 miles", "5 years or 60,000 miles", "6 years or 70,000 miles", "7 years or 100,000 miles" ] } ], "level_count": 3, "llm_model": "gpt4", "new_attribute_count": 4, "why_prompt": "What factor affect the adoption of an electric vehicle?" }, "properties": { "country": { "title": "Country", "type": "string" }, "existing_attributes_levels": { "items": { "$ref": "#/components/schemas/LeveledAttribute" }, "title": "Existing Attributes Levels", "type": "array" }, "level_count": { "default": 3, "maximum": 5.0, "minimum": 2.0, "title": "Level Count", "type": "integer" }, "llm_model": { "anyOf": [ { "$ref": "#/components/schemas/LLMModel" }, { "type": "null" } ], "default": "databricks-claude-sonnet-4" }, "new_attribute_count": { "default": 4, "maximum": 5.0, "minimum": 1.0, "title": "New Attribute Count", "type": "integer" }, "why_prompt": { "title": "Why Prompt", "type": "string" } }, "required": [ "why_prompt", "country", "existing_attributes_levels" ], "title": "OrthogonalAttributesLevelsRequest", "type": "object" }, "PersonasResponse": { "example": { "personas": [ { "age_range": "18-25", "behaviors": [ "actively researches and evaluates brands online", "engages with social media communities", "values influencer insights", "consistently seeks transparency and authenticity in brand communications" ], "gender": "Female", "goals": [ "maintain a health-conscious and sustainable lifestyle", "make ethically responsible purchasing decisions", "inspire others to adopt similar values", "balance luxury with ethical consumption" ], "location": "Urban areas", "name": "Sophia", "pain_points": [ "balancing ethical consumption with budget constraints", "finding authentic and sustainable luxury brands", "dealing with inauthentic marketing and greenwashing" ], "personality_traits": [ "analytical", "tech-savvy", "socially responsible", "driven by authenticity and transparency" ] }, { "age_range": "18-25", "behaviors": [ "trusts peer and influencer recommendations", "does own research", "aims to inspire ethical consumption and shared values" ], "gender": "Female", "goals": [ "inspire ethical consumption", "find brands that align with personal values" ], "location": "Urban areas", "name": "Jordan", "pain_points": [ "avoiding greenwashing", "finding brands that offer personalized experiences" ], "personality_traits": [ "creative", "explorer", "values sustainability", "authenticity", "ethics" ] } ] }, "properties": { "personas": { "description": "List of personas, each represented as a dictionary with dynamic attributes (e.g., name, age_range, personality_traits)", "items": { "additionalProperties": true, "type": "object" }, "title": "Personas", "type": "array" } }, "required": [ "personas" ], "title": "PersonasResponse", "type": "object" }, "PopulationRecommendationResponse": { "example": { "one_trait_change": { "age": { "population_size": 8810, "population_traits": { "age": [ 18, 95 ], "education_level": [ "Associates", "Bachelors", "High School Diploma", "High School but no diploma" ], "gender": [ "Female" ], "household_income": [ 0, 3000000 ], "household_with_children": "yes", "number_of_children": [ "1", "4+" ], "racial_group": [ "White", "African American", "Asian or Pacific Islander" ], "state": "New York" } }, "education_level": { "population_size": 66, "population_traits": { "age": [ 20, 22 ], "education_level": [ "Associates", "Bachelors", "High School Diploma", "High School but no diploma", "Less than high school", "Masters", "Some College" ], "gender": [ "Female" ], "household_income": [ 0, 3000000 ], "household_with_children": "yes", "number_of_children": [ "1", "4+" ], "racial_group": [ "White", "African American", "Asian or Pacific Islander" ], "state": "New York" } }, "gender": { "population_size": 59, "population_traits": { "age": [ 20, 22 ], "education_level": [ "Associates", "Bachelors", "High School Diploma", "High School but no diploma" ], "gender": [ "Female", "Male" ], "household_income": [ 0, 3000000 ], "household_with_children": "yes", "number_of_children": [ "1", "4+" ], "racial_group": [ "White", "African American", "Asian or Pacific Islander" ], "state": "New York" } }, "household_income": { "population_size": 42, "population_traits": { "age": [ 20, 22 ], "education_level": [ "Associates", "Bachelors", "High School Diploma", "High School but no diploma" ], "gender": [ "Female" ], "household_income": [ 4000, 812360 ], "household_with_children": "yes", "number_of_children": [ "1", "4+" ], "racial_group": [ "White", "African American", "Asian or Pacific Islander" ], "state": "New York" } }, "household_with_children": { "population_size": 42, "population_traits": { "age": [ 20, 22 ], "education_level": [ "Associates", "Bachelors", "High School Diploma", "High School but no diploma" ], "gender": [ "Female" ], "household_income": [ 0, 3000000 ], "number_of_children": [ "1", "4+" ], "racial_group": [ "White", "African American", "Asian or Pacific Islander" ], "state": "New York" } }, "number_of_children": { "population_size": 65, "population_traits": { "age": [ 20, 22 ], "education_level": [ "Associates", "Bachelors", "High School Diploma", "High School but no diploma" ], "gender": [ "Female" ], "household_income": [ 0, 3000000 ], "household_with_children": "yes", "number_of_children": [ "1", "4+", "2", "3" ], "racial_group": [ "White", "African American", "Asian or Pacific Islander" ], "state": "New York" } }, "racial_group": { "population_size": 57, "population_traits": { "age": [ 20, 22 ], "education_level": [ "Associates", "Bachelors", "High School Diploma", "High School but no diploma" ], "gender": [ "Female" ], "household_income": [ 0, 3000000 ], "household_with_children": "yes", "number_of_children": [ "1", "4+" ], "racial_group": [ "White", "African American", "Asian or Pacific Islander", "Mixed race", "Other race" ], "state": "New York" } } }, "original": { "population_size": 42, "population_traits": { "age": [ 20, 22 ], "education_level": [ "Associates", "Bachelors", "High School Diploma", "High School but no diploma" ], "gender": [ "Female" ], "household_income": [ 0, 3000000 ], "household_with_children": "yes", "number_of_children": [ "1", "4+" ], "racial_group": [ "White", "Black", "Asian or Pacific Islander" ], "state": "New York" } }, "suggestion": { "population_size": 154788, "population_traits": { "age": [ 18, 95 ], "education_level": [ "Associates", "Bachelors", "High School Diploma", "High School but no diploma", "Less than high school", "Masters", "PhD", "Some College" ], "gender": [ "Female", "Male" ], "household_income": [ 0, 2221200 ], "number_of_children": [ "1", "4+", "0", "2", "3" ], "racial_group": [ "White", "African American", "Asian or Pacific Islander", "Mixed race", "Other race" ], "state": "New York" } } }, "properties": { "one_trait_change": { "additionalProperties": true, "title": "One Trait Change", "type": "object" }, "original": { "additionalProperties": true, "title": "Original", "type": "object" }, "suggestion": { "additionalProperties": true, "title": "Suggestion", "type": "object" } }, "required": [ "suggestion", "original", "one_trait_change" ], "title": "PopulationRecommendationResponse", "type": "object" }, "PopulationRecommendationResponseNonUS": { "example": { "one_trait_change": { "Age": { "population_size": 8810, "population_traits": { "Age": [ 18, 92 ], "Education Level": [ "Masters", "Bachelors", "Some College", "PhD", "High School but no diploma", "High School Diploma", "Associates", "Less than high school" ], "Gender": [ "Female", "Male" ], "Home Ownership": [ "Own", "Rent" ], "Household Size": [ "4", "2", "1", "3", "More than 4 people" ], "Household with Children": [ "Yes", "No" ] } }, "Education Level": { "population_size": 66, "population_traits": { "Age": [ 18, 92 ], "Education Level": [ "Masters", "Bachelors", "Some College", "PhD", "High School but no diploma", "High School Diploma", "Associates", "Less than high school" ], "Gender": [ "Female", "Male" ], "Home Ownership": [ "Own", "Rent" ], "Household Size": [ "4", "2", "1", "3", "More than 4 people" ], "Household with Children": [ "Yes", "No" ] } }, "Gender": { "population_size": 59, "population_traits": { "Age": [ 18, 92 ], "Education Level": [ "Masters", "Bachelors", "Some College", "PhD", "High School but no diploma", "High School Diploma", "Associates", "Less than high school" ], "Gender": [ "Female", "Male" ], "Home Ownership": [ "Own", "Rent" ], "Household Size": [ "4", "2", "1", "3", "More than 4 people" ], "Household with Children": [ "Yes", "No" ] } }, "Home Ownership": { "population_size": 65, "population_traits": { "Age": [ 18, 92 ], "Education Level": [ "Masters", "Bachelors", "Some College", "PhD", "High School but no diploma", "High School Diploma", "Associates", "Less than high school" ], "Gender": [ "Female", "Male" ], "Home Ownership": [ "Own", "Rent" ], "Household Size": [ "4", "2", "1", "3", "More than 4 people" ], "Household with Children": [ "Yes", "No" ] } }, "Household Size": { "population_size": 42, "population_traits": { "Age": [ 18, 92 ], "Education Level": [ "Masters", "Bachelors", "Some College", "PhD", "High School but no diploma", "High School Diploma", "Associates", "Less than high school" ], "Gender": [ "Female", "Male" ], "Home Ownership": [ "Own", "Rent" ], "Household Size": [ "4", "2", "1", "3", "More than 4 people" ], "Household with Children": [ "Yes", "No" ] } }, "Household with Children": { "population_size": 42, "population_traits": { "Age": [ 18, 92 ], "Education Level": [ "Masters", "Bachelors", "Some College", "PhD", "High School but no diploma", "High School Diploma", "Associates", "Less than high school" ], "Gender": [ "Female", "Male" ], "Home Ownership": [ "Own", "Rent" ], "Household Size": [ "4", "2", "1", "3", "More than 4 people" ], "Household with Children": [ "Yes", "No" ] } } }, "original": { "population_size": 42, "population_traits": { "Age": [ 18, 92 ], "Education Level": [ "Masters", "Bachelors", "Some College", "PhD", "High School but no diploma", "High School Diploma", "Associates", "Less than high school" ], "Gender": [ "Female", "Male" ], "Home Ownership": [ "Own", "Rent" ], "Household Size": [ "4", "2", "1", "3", "More than 4 people" ], "Household with Children": [ "Yes", "No" ] } }, "suggestion": { "population_size": 154788, "population_traits": { "Age": [ 18, 92 ], "Education Level": [ "Masters", "Bachelors", "Some College", "PhD", "High School but no diploma", "High School Diploma", "Associates", "Less than high school" ], "Gender": [ "Female", "Male" ], "Home Ownership": [ "Own", "Rent" ], "Household Size": [ "4", "2", "1", "3", "More than 4 people" ], "Household with Children": [ "Yes", "No" ] } } }, "properties": { "one_trait_change": { "additionalProperties": true, "title": "One Trait Change", "type": "object" }, "original": { "additionalProperties": true, "title": "Original", "type": "object" }, "suggestion": { "additionalProperties": true, "title": "Suggestion", "type": "object" } }, "required": [ "suggestion", "original", "one_trait_change" ], "title": "PopulationRecommendationResponseNonUS", "type": "object" }, "PopulationRequest": { "example": { "age": [ 20, 26 ], "education_level": [ "Less than high school", "High School but no diploma", "High School Diploma", "Some College", "Associates", "Bachelors", "Masters", "PhD" ], "gender": [ "Female" ], "household_income": [ 50000, 70000 ], "number_of_children": [ "1", "2", "3", "4+" ], "number_of_records": 500, "racial_group": [ "White", "African American", "Asian or Pacific Islander", "Mixed race", "Other race" ], "state": "New York" }, "properties": { "age": { "anyOf": [ { "items": { "type": "integer" }, "type": "array" }, { "type": "null" } ], "title": "Age" }, "education_level": { "anyOf": [ { "items": { "$ref": "#/components/schemas/EducationLevelEnum" }, "type": "array" }, { "type": "null" } ], "title": "Education Level" }, "gender": { "anyOf": [ { "items": { "$ref": "#/components/schemas/GenderEnum" }, "type": "array" }, { "type": "null" } ], "title": "Gender" }, "household_income": { "anyOf": [ { "items": { "type": "integer" }, "type": "array" }, { "type": "null" } ], "title": "Household Income" }, "household_with_children": { "anyOf": [ { "enum": [ "yes", "no" ], "type": "string" }, { "type": "null" } ], "title": "Household With Children" }, "number_of_children": { "anyOf": [ { "items": { "$ref": "#/components/schemas/ChildrenEnum" }, "type": "array" }, { "type": "null" } ], "title": "Number Of Children" }, "number_of_records": { "default": 250, "maximum": 5000.0, "title": "Number Of Records", "type": "integer" }, "racial_group": { "anyOf": [ { "items": { "$ref": "#/components/schemas/RacialGroupEnum" }, "type": "array" }, { "type": "null" } ], "title": "Racial Group" }, "state": { "anyOf": [ { "$ref": "#/components/schemas/USStatesEnum" }, { "type": "null" } ] } }, "title": "PopulationRequest", "type": "object" }, "PopulationRequestNonUS": { "example": { "Age": [ 18, 92 ], "Education_Level": [ "Masters", "Bachelors", "Some College", "PhD", "High School but no diploma", "High School Diploma", "Associates", "Less than high school" ], "Gender": [ "Female", "Male" ], "Home_Ownership": [ "Own", "Rent" ], "Household_Size": [ "4", "2", "1", "3", "More than 4 people" ], "Household_with_Children": [ "Yes", "No" ] }, "properties": { "Age": { "anyOf": [ { "items": { "type": "integer" }, "type": "array" }, { "type": "null" } ], "title": "Age" }, "Education_Level": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "title": "Education Level" }, "Gender": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "title": "Gender" }, "Home_Ownership": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "title": "Home Ownership" }, "Household_Size": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "title": "Household Size" }, "Household_with_Children": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "title": "Household With Children" } }, "title": "PopulationRequestNonUS", "type": "object" }, "PopulationTraits": { "additionalProperties": true, "properties": {}, "title": "PopulationTraits", "type": "object" }, "ProductAttributeRequest": { "example": { "attribute_count": 8, "country": "USA", "level_count": 5, "why_prompt": "I've been reading about how noise-cancelling technology has evolved significantly in recent years, and I'm curious about which wireless headphones currently offer the best combination of active noise cancellation, comfort for long listening sessions, and battery life that can last through international flights. My budget is around $200-400, and I want to understand what features distinguish the top-performing models in this price range." }, "properties": { "attribute_count": { "default": 7, "maximum": 10.0, "minimum": 2.0, "title": "Attribute Count", "type": "integer" }, "country": { "title": "Country", "type": "string" }, "level_count": { "default": 5, "maximum": 10.0, "minimum": 2.0, "title": "Level Count", "type": "integer" }, "number_of_products": { "anyOf": [ { "maximum": 20.0, "minimum": 1.0, "type": "integer" }, { "type": "null" } ], "default": 5, "title": "Number Of Products" }, "question_validated": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": false, "description": "Whether the why_prompt has been validated for product attribute generation", "title": "Question Validated" }, "verify_product_url": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": false, "description": "Whether to verify product URLs", "title": "Verify Product Url" }, "why_prompt": { "title": "Why Prompt", "type": "string" } }, "required": [ "why_prompt", "country" ], "title": "ProductAttributeRequest", "type": "object" }, "PromptType": { "description": "Enum representing the type of prompts used in experiment designs.", "enum": [ "generic", "service", "product", "experience", "policy" ], "title": "PromptType", "type": "string" }, "Question": { "example": { "question": "How often have you purchased the same brand of mobile phone in the past?", "sample_responses": [ { "response": "Always the same brand" }, { "response": "Mostly the same brand" }, { "response": "Occasionally the same brand" }, { "response": "Rarely the same brand" }, { "response": "Never the same brand" } ] }, "properties": { "question": { "title": "Question", "type": "string" }, "sample_responses": { "items": { "$ref": "#/components/schemas/SampleResponse" }, "title": "Sample Responses", "type": "array" } }, "required": [ "question", "sample_responses" ], "title": "Question", "type": "object" }, "QuestionList": { "items": { "$ref": "#/components/schemas/Question" }, "maxItems": 2, "minItems": 2, "title": "QuestionList", "type": "array" }, "QuestionRequest": { "example": { "llm_model": "gpt4", "model_dimensions": { "constraints": [ "User Review", "Budget" ], "history": [ "Previous Phone Brands", "Price Sensitivity" ] }, "user_profile_attributes": { "age_levels": [ 25, 30 ], "education_levels": [ "Bachelors Degree" ], "income_levels": [ 50000, 75000 ] }, "why_prompt": "What factors influence your choice in selecting a mobile phone?" }, "properties": { "llm_model": { "anyOf": [ { "$ref": "#/components/schemas/LLMModel" }, { "type": "null" } ], "default": "databricks-claude-sonnet-4" }, "model_dimensions": { "additionalProperties": { "items": { "type": "string" }, "type": "array" }, "title": "Model Dimensions", "type": "object" }, "user_profile_attributes": { "additionalProperties": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "items": { "type": "integer" }, "type": "array" }, { "items": { "type": "number" }, "type": "array" } ] }, "title": "User Profile Attributes", "type": "object" }, "why_prompt": { "title": "Why Prompt", "type": "string" } }, "required": [ "why_prompt", "user_profile_attributes", "model_dimensions" ], "title": "QuestionRequest", "type": "object" }, "QuestionResponse": { "additionalProperties": { "additionalProperties": { "$ref": "#/components/schemas/QuestionList" }, "type": "object" }, "example": { "constraints": { "Budget": [ { "question": "How much does your budget limit your choice when selecting a mobile phone?", "sample_responses": [ { "response": "It is the primary factor, I only consider phones within my budget" }, { "response": "It is a major factor, but I might stretch my budget for a good deal" }, { "response": "It is somewhat important, but I consider other factors equally" }, { "response": "It is a minor factor, I prioritize features over budget" }, { "response": "It does not limit my choice at all, I choose based on features and brand" } ] }, { "question": "How often do you find yourself compromising on features due to budget constraints when selecting a mobile phone?", "sample_responses": [ { "response": "Always" }, { "response": "Frequently" }, { "response": "Occasionally" }, { "response": "Rarely" }, { "response": "Never" } ] } ], "User Review": [ { "question": "How often do you rely on user reviews when selecting a mobile phone?", "sample_responses": [ { "response": "Always" }, { "response": "Often" }, { "response": "Sometimes" }, { "response": "Rarely" }, { "response": "Never" } ] }, { "question": "To what extent do negative user reviews influence your decision to avoid purchasing a particular mobile phone?", "sample_responses": [ { "response": "Significantly" }, { "response": "Moderately" }, { "response": "Somewhat" }, { "response": "Slightly" }, { "response": "Not at all" } ] } ] }, "history": { "Previous Phone Brands": [ { "question": "How often have you purchased the same brand of mobile phone in the past?", "sample_responses": [ { "response": "Always" }, { "response": "Mostly" }, { "response": "Occasionally" }, { "response": "Rarely" }, { "response": "Never" } ] }, { "question": "How satisfied have you been with the mobile phone brands you have used previously?", "sample_responses": [ { "response": "Extremely satisfied" }, { "response": "Very satisfied" }, { "response": "Moderately satisfied" }, { "response": "Slightly satisfied" }, { "response": "Not satisfied at all" } ] } ], "Price Sensitivity": [ { "question": "How often have you chosen a mobile phone based on its price in the past?", "sample_responses": [ { "response": "Always" }, { "response": "Most of the time" }, { "response": "Sometimes" }, { "response": "Rarely" }, { "response": "Never" } ] }, { "question": "When you last purchased a mobile phone, how significant was the price in your decision?", "sample_responses": [ { "response": "Extremely significant" }, { "response": "Very significant" }, { "response": "Moderately significant" }, { "response": "Slightly significant" }, { "response": "Not significant at all" } ] } ] } }, "propertyNames": { "enum": [ "history", "constraints" ] }, "title": "QuestionResponse", "type": "object" }, "RacialGroupEnum": { "enum": [ "Mixed race", "White", "African American", "Asian or Pacific Islander", "Other race", "American Indian or Alaska Native" ], "title": "RacialGroupEnum", "type": "string" }, "RealWorldConjoinStatementFinalResponse": { "example": { "suggestions": [ { "attributes": [ "Price", "Screen Size", "Battery Life" ], "text": "What factors affect the choice of purchasing a smartphone?" }, { "attributes": [ "Brand", "Camera Quality", "Battery Life" ], "text": "What factors affect the choice of purchasing an expensive smartphone?" } ] }, "properties": { "flag": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Flag" }, "is_causal": { "title": "Is Causal", "type": "boolean" }, "suggestions": { "items": { "$ref": "#/components/schemas/RealWorldConjoinStatementIndividualResponse" }, "title": "Suggestions", "type": "array" } }, "required": [ "is_causal", "flag", "suggestions" ], "title": "RealWorldConjoinStatementFinalResponse", "type": "object" }, "RealWorldConjoinStatementIndividualResponse": { "example": { "attributes": [ "Price", "Screen Size", "Battery Life" ], "text": "What factors affect the choice of purchasing a smartphone?" }, "properties": { "attributes": { "items": { "type": "string" }, "title": "Attributes", "type": "array" }, "text": { "title": "Text", "type": "string" } }, "required": [ "text", "attributes" ], "title": "RealWorldConjoinStatementIndividualResponse", "type": "object" }, "RealWorldConjoinStatementRequest": { "example": { "attribute_count": 8, "statement_history": [ "What factors affect the choice of purchasing a smartphone?", "What factors affect the choice of purchasing an expensive smartphone?" ], "suggestion_count": 3, "why_prompt": "What factors affect the choice of purchasing a smartphone?" }, "properties": { "attribute_count": { "default": 4, "maximum": 10.0, "minimum": 2.0, "title": "Attribute Count", "type": "integer" }, "statement_history": { "items": { "type": "string" }, "title": "Statement History", "type": "array" }, "suggestion_count": { "default": 3, "maximum": 5.0, "minimum": 1.0, "title": "Suggestion Count", "type": "integer" }, "why_prompt": { "title": "Why Prompt", "type": "string" } }, "required": [ "why_prompt", "statement_history" ], "title": "RealWorldConjoinStatementRequest", "type": "object" }, "RecommendedState": { "properties": { "confidence": { "default": "low", "enum": [ "high", "medium", "low" ], "title": "Confidence", "type": "string" }, "estimated_population_size": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "title": "Estimated Population Size" }, "feasibility_status": { "default": "unknown", "enum": [ "unknown", "meets_threshold", "below_threshold" ], "title": "Feasibility Status", "type": "string" }, "fit_note": { "title": "Fit Note", "type": "string" }, "rank": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "title": "Rank" }, "state": { "$ref": "#/components/schemas/USStatesEnum" } }, "required": [ "state", "fit_note" ], "title": "RecommendedState", "type": "object" }, "RunRequest": { "example": { "filters": { "config.user": { "$eq": "user_id e.g. auth0|1234567890" }, "created_at": { "$gt": "2026-01-15T09:00:00", "$lte": "2026-01-16T09:00:00" } } }, "properties": { "filters": { "additionalProperties": true, "title": "Filters", "type": "object" } }, "required": [ "filters" ], "title": "RunRequest", "type": "object" }, "RunResponse": { "properties": { "config": { "additionalProperties": true, "title": "Config", "type": "object" }, "created_at": { "title": "Created At", "type": "string" }, "id": { "title": "Id", "type": "string" }, "name": { "title": "Name", "type": "string" }, "state": { "title": "State", "type": "string" }, "tags": { "items": { "type": "string" }, "title": "Tags", "type": "array" } }, "required": [ "id", "name", "state", "tags", "created_at", "config" ], "title": "RunResponse", "type": "object" }, "SampleResponse": { "example": { "response": "Always the same brand" }, "properties": { "response": { "title": "Response", "type": "string" } }, "required": [ "response" ], "title": "SampleResponse", "type": "object" }, "StatementDirectionInput": { "example": { "statements": [ { "scale": { "1": "Strongly disagree", "2": "Disagree", "3": "Neutral", "4": "Agree", "5": "Strongly agree" }, "statement": "Does the packaging looks refreshing" }, { "scale": { "1": "Strongly agree", "2": "Agree", "3": "Neutral", "4": "Disagree", "5": "Strongly disagree" }, "statement": "Will you buy this juice?" } ] }, "properties": { "statements": { "description": "List of statements and their labels", "items": { "additionalProperties": true, "type": "object" }, "title": "Statements", "type": "array" } }, "required": [ "statements" ], "title": "StatementDirectionInput", "type": "object" }, "StatementLikertLabelRequest": { "example": { "concept_description": "We're evaluating a new on the go smoothie product and would like to understand people's perception towards it.", "existing_statements": [ "Would taste great", "Would have good texture" ], "image_name1": "milk-image.png", "number_of_statements": 5, "scale": 5 }, "properties": { "concept_description": { "default": "", "title": "Concept Description", "type": "string" }, "existing_statements": { "default": [], "items": { "type": "string" }, "title": "Existing Statements", "type": "array" }, "image_name1": { "default": "", "title": "Image Name1", "type": "string" }, "number_of_statements": { "default": 5, "maximum": 10.0, "minimum": 1.0, "title": "Number Of Statements", "type": "integer" }, "scale": { "default": 5, "maximum": 10.0, "minimum": 1.0, "title": "Scale", "type": "integer" } }, "title": "StatementLikertLabelRequest", "type": "object" }, "StreamPersonaInput": { "example": { "attributes": [ "Cost", "Range" ], "why_prompt": "What factors affect the choice of an electric car" }, "properties": { "attributes": { "items": { "type": "string" }, "title": "Attributes", "type": "array" }, "why_prompt": { "title": "Why Prompt", "type": "string" } }, "required": [ "why_prompt", "attributes" ], "title": "StreamPersonaInput", "type": "object" }, "StreamPersonaOutput": { "properties": { "persona": { "items": { "type": "string" }, "title": "Persona", "type": "array" } }, "required": [ "persona" ], "title": "StreamPersonaOutput", "type": "object" }, "SurveyResponseType": { "enum": [ "probabilistic", "discrete" ], "title": "SurveyResponseType", "type": "string" }, "TargetPopulation": { "properties": { "age": { "anyOf": [ { "items": { "type": "integer" }, "type": "array" }, { "type": "null" } ], "title": "Age" }, "education_level": { "anyOf": [ { "items": { "$ref": "#/components/schemas/EducationLevelEnum" }, "type": "array" }, { "type": "null" } ], "title": "Education Level" }, "gender": { "anyOf": [ { "items": { "$ref": "#/components/schemas/GenderEnum" }, "type": "array" }, { "type": "null" } ], "title": "Gender" }, "household_income": { "anyOf": [ { "items": { "type": "integer" }, "type": "array" }, { "type": "null" } ], "title": "Household Income" }, "number_of_children": { "anyOf": [ { "items": { "$ref": "#/components/schemas/ChildrenEnum" }, "type": "array" }, { "type": "null" } ], "title": "Number Of Children" }, "racial_group": { "anyOf": [ { "items": { "$ref": "#/components/schemas/RacialGroupEnum" }, "type": "array" }, { "type": "null" } ], "title": "Racial Group" }, "state": { "anyOf": [ { "$ref": "#/components/schemas/USStatesEnum" }, { "type": "null" } ] } }, "title": "TargetPopulation", "type": "object" }, "Trait": { "example": { "levels": [ "male", "female", "other" ], "name": "gender" }, "properties": { "levels": { "items": { "type": "string" }, "title": "Levels", "type": "array" }, "name": { "title": "Name", "type": "string" } }, "required": [ "name", "levels" ], "title": "Trait", "type": "object" }, "TraitGenerationRequest": { "example": { "country": "USA", "max_length": 100, "number_of_levels_per_trait": 3, "number_of_new_traits": 4, "selected_traits": [ "age", "education", "occupation" ], "why_prompt": "How does social media usage affect sleep patterns?" }, "properties": { "country": { "default": "USA", "title": "Country", "type": "string" }, "llm_model": { "$ref": "#/components/schemas/LLMModel", "default": "databricks-claude-sonnet-4" }, "max_length": { "default": 100, "title": "Max Length", "type": "integer" }, "number_of_levels_per_trait": { "default": 3, "maximum": 5.0, "minimum": 2.0, "title": "Number Of Levels Per Trait", "type": "integer" }, "number_of_new_traits": { "default": 4, "maximum": 10.0, "minimum": 1.0, "title": "Number Of New Traits", "type": "integer" }, "selected_traits": { "description": "List of trait names already selected", "examples": [ "age", "education", "occupation" ], "items": { "type": "string" }, "title": "Selected Traits", "type": "array" }, "why_prompt": { "description": "The why prompt explaining the use case", "examples": [ "How does social media usage affect sleep patterns?" ], "title": "Why Prompt", "type": "string" } }, "required": [ "why_prompt", "selected_traits" ], "title": "TraitGenerationRequest", "type": "object" }, "TraitLevel": { "properties": { "id": { "title": "Id", "type": "string" }, "long_description": { "title": "Long Description", "type": "string" }, "measurement_type": { "title": "Measurement Type", "type": "string" }, "ordinal_rank": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "title": "Ordinal Rank" }, "set_type": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Set Type" }, "short_description": { "title": "Short Description", "type": "string" }, "type": { "title": "Type", "type": "string" } }, "required": [ "id", "set_type", "type", "measurement_type", "ordinal_rank", "short_description", "long_description" ], "title": "TraitLevel", "type": "object" }, "TraitLevelsSuggestionRequest": { "example": { "country": "USA", "existing_traits": [ "Personality Type", "Age", "Mental Health Status", "Educational Background" ], "levels_count": 3, "max_length": 100, "new_trait": "Cultural Orientation", "why_prompt": "How does social media usage affect sleep patterns?" }, "properties": { "country": { "default": "USA", "description": "The country of the survey", "title": "Country", "type": "string" }, "existing_traits": { "description": "List of existing traits", "examples": [ "Personality Type", "Age", "Mental Health Status", "Educational Background" ], "items": { "type": "string" }, "title": "Existing Traits", "type": "array" }, "levels_count": { "default": 3, "description": "Number of levels to suggest for the new trait", "maximum": 5.0, "minimum": 2.0, "title": "Levels Count", "type": "integer" }, "llm_model": { "$ref": "#/components/schemas/LLMModel", "default": "databricks-claude-sonnet-4" }, "max_length": { "default": 100, "description": "Maximum length of the trait levels", "title": "Max Length", "type": "integer" }, "new_trait": { "description": "Name of the new trait for which levels need to be suggested", "title": "New Trait", "type": "string" }, "why_prompt": { "description": "The why prompt explaining the use case", "examples": [ "How does social media usage affect sleep patterns?" ], "title": "Why Prompt", "type": "string" } }, "required": [ "existing_traits", "new_trait", "why_prompt" ], "title": "TraitLevelsSuggestionRequest", "type": "object" }, "TraitLevelsSuggestionResponse": { "example": { "levels": [ "Traditional", "Moderate", "Tech-Embracing" ], "trait": "Cultural Orientation" }, "properties": { "levels": { "description": "List of suggested levels for the trait", "items": { "type": "string" }, "title": "Levels", "type": "array" }, "trait": { "description": "Name of the trait for which levels are suggested", "title": "Trait", "type": "string" } }, "required": [ "trait", "levels" ], "title": "TraitLevelsSuggestionResponse", "type": "object" }, "TraitSuggestionResponse": { "example": { "suggested_traits": [ { "levels": [ "Introverted", "Extroverted", "Ambivert" ], "name": "personality_type" }, { "levels": [ "Low Self-Control", "Moderate Self-Control", "High Self-Control" ], "name": "impulsivity_level" } ] }, "properties": { "suggested_traits": { "description": "List of suggested traits with their possible levels", "items": { "$ref": "#/components/schemas/Trait" }, "title": "Suggested Traits", "type": "array" } }, "required": [ "suggested_traits" ], "title": "TraitSuggestionResponse", "type": "object" }, "USStatesEnum": { "enum": [ "Alabama", "Alaska", "Arizona", "Arkansas", "California", "Colorado", "Connecticut", "Delaware", "Florida", "Georgia", "Hawaii", "Idaho", "Illinois", "Indiana", "Iowa", "Kansas", "Kentucky", "Louisiana", "Maine", "Maryland", "Massachusetts", "Michigan", "Minnesota", "Mississippi", "Missouri", "Montana", "Nebraska", "Nevada", "New Hampshire", "New Jersey", "New Mexico", "New York", "North Carolina", "North Dakota", "Ohio", "Oklahoma", "Oregon", "Pennsylvania", "Rhode Island", "South Carolina", "South Dakota", "Tennessee", "Texas", "Utah", "Vermont", "Virginia", "Washington", "West Virginia", "Wisconsin", "Wyoming" ], "title": "USStatesEnum", "type": "string" }, "app__api__v1__schemas__personas__HistoryRequest": { "example": { "attributes": [ "price", "operating_system", "battery_life", "camera_quality", "storage_capacity" ], "llm_model": "gpt4", "user_profile_attributes": { "age_levels": [ 25, 30 ], "education_levels": [ "Bachelors Degree" ], "gender_levels": [ "Male" ], "income_levels": [ 50000, 75000 ] }, "why_prompt": "What factors influence your choice in selecting a mobile phone?" }, "properties": { "attributes": { "items": { "type": "string" }, "title": "Attributes", "type": "array" }, "llm_model": { "anyOf": [ { "$ref": "#/components/schemas/LLMModel" }, { "type": "null" } ], "default": "databricks-claude-sonnet-4" }, "user_profile_attributes": { "additionalProperties": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "items": { "type": "integer" }, "type": "array" }, { "items": { "type": "number" }, "type": "array" } ] }, "title": "User Profile Attributes", "type": "object" }, "why_prompt": { "title": "Why Prompt", "type": "string" } }, "required": [ "why_prompt", "user_profile_attributes", "attributes" ], "title": "HistoryRequest", "type": "object" } }, "securitySchemes": { "HTTPBearer": { "scheme": "bearer", "type": "http" } } }, "info": { "contact": { "email": "avi@subconscious.ai", "name": "Avi Yashchin", "url": "https://www.linkedin.com/in/aviyashchin/" }, "description": "\ud83d\udc95SuperEgo API powers Consulting and Product teams to design and run cost-effective, ethical, causal experiments. \ud83d\ude80 Generative AI for Experimental Design. \ud83d\udc68\u200d\ud83d\udd2c\u2697\ufe0f", "license": { "name": "MIT", "url": "https://github.com/Subconscious-ai/PoC/blob/main/LICENSE" }, "termsOfService": "https://docs.subconscious.ai/support/terms-of-use", "title": "SuperEgo", "version": "1.0.0" }, "openapi": "3.1.0", "paths": { "/api/v1/attributes": { "post": { "description": "Create a list of attributes for a given why_prompt.\n\nParameters:\n- `req`: AttributesRequest object containing:\n - `why_prompt`: The main concept or input question\n - `country`: Target country\n - `attribute_count`: Number of attributes to generate (optional)\n - `prompt_type`: Type of prompt to use (optional)\n - `llm_model`: Language model to use (optional)\n\nReturns:\n- List of attributes.\n\nExample Response:\n```json\n[\n \"Price\",\n \"Range\",\n \"Charging Time\",\n \"Safety Rating\"\n]\n```\n\nRaises:\n- HTTPException 404: If an error occurs during creation", "operationId": "createAttributes", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/AttributesRequest" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "items": { "type": "string" }, "title": "Response Create Attributes Api V1 Attributes Post", "type": "array" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Create Attributes", "tags": [ "v1.attributes_levels" ] } }, "/api/v1/attributes-levels": { "post": { "description": "Create attributes and levels for a given why_prompt.\n\nParameters:\n- `req`: AttributesLevelsRequest object containing:\n - `why_prompt`: The main concept or prompt\n - `country`: Target country\n - `level_count`: Number of levels per attribute (optional)\n - `max_length`: Maximum length for levels (optional)\n - `llm_model`: Language model to use (optional)\n - `attribute_count`: Number of attributes to generate (optional)\n\nReturns:\n- List of attributes with their levels.", "operationId": "createAttributesLevels", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/AttributesLevelsRequest" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/AttributesLevelsResponse" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Create Attributes And Levels", "tags": [ "v1.attributes_levels" ] } }, "/api/v1/attributes-levels/orthogonal": { "post": { "description": "Create new, independent (orthogonal) attributes and levels hat do not intersect with existing ones..\n\nParameters:\n- `req`: OrthogonalAttributesLevelsRequest object containing:\n - `why_prompt`: The main concept - prompt text\n - `country`: Target country\n - `existing_attributes_levels`: List of existing attributes and levels\n - `new_attribute_count`: Number of new attributes to generate (optional)\n - `level_count`: Number of levels per attribute (optional)\n - `llm_model`: Language model to use (optional)\n\nReturns:\n- List of orthogonal attributes with their levels.\n\nRaises:\n- HTTPException 404: If an error occurs during creation", "operationId": "createAttributesLevelsOrthogonal", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/OrthogonalAttributesLevelsRequest" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/AttributesLevelsResponse" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Create Orthogonal Attributes And Levels", "tags": [ "v1.attributes_levels" ] } }, "/api/v1/experiments": { "post": { "description": "Starts an experiment asynchronously and returns a W&B run id to poll.\n\nThe request model accepts ~105 fields, nearly all of them internal tuning\nknobs with defaults. In practice a useful experiment needs only the\nresearch question; the fields below are the supported minimal contract,\nmirroring `MCPExperimentRequest` in the MCP server.\n\n**Accepted is not the same as queued.** A 200 response with a run id does\nnot guarantee the run was enqueued. If no W&B run appears within roughly\n25 minutes, resubmit. See the run status endpoint for how to verify.\n", "operationId": "createExperiments", "requestBody": { "content": { "application/json": { "example": { "experiment_type": "conjoint", "is_private": false, "population_traits": { "Travel frequency": [ "Weekly" ] }, "why_prompt": "What factors drive consumer choice of electric vehicles?" }, "schema": { "$ref": "#/components/schemas/Experiment" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "example": { "wandb_run_id": "a1b2c3d4", "wandb_run_name": "eloquent-sunset-42" }, "schema": { "$ref": "#/components/schemas/ExperimentAsyncResponse" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Create an experiment", "tags": [ "v1.experiments" ] } }, "/api/v1/experiments/concept-statement": { "post": { "description": "Create a set of Likert scale labels based on the input prompt.\n\nThis endpoint generates a specified number of Likert scale labels\nusing the provided prompt. The generated labels can be used in experiments\nor surveys.", "operationId": "createExperimentsConceptStatement", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/StatementLikertLabelRequest" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/LikertLabelResponse" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Create Concept Statement", "tags": [ "v1.experiments" ] } }, "/api/v1/experiments/conjoint-statements": { "post": { "description": "Create a set of conjoint statements based on the input prompt.\n\nThis endpoint generates a specified number of conjoint statements\nusing the provided prompt. The generated statements can be used in experiments\nor surveys.", "operationId": "createExperimentsConjointStatements", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/RealWorldConjoinStatementRequest" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/RealWorldConjoinStatementFinalResponse" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Create Real World Conjoint Statements", "tags": [ "v1.experiments" ] } }, "/api/v1/experiments/dependent-variable": { "post": { "description": "Generate a dependent variable string (survey prompt) based on the input question.\n\nThis endpoint creates a dependent variable that synthetic respondents will respond to in an experiment.\nIt allows users to review the generated survey prompt before running the experiment.\n\nParameters:\n- `req`: DependentVariable object containing:\n - `prompt_type`: Enum representing the type or focus of the experiment\n - `why_prompt`: String containing the user's input question\n\nReturns:\n- DependentVariableResponse object with the following structure:\n - `dependent_variable`: String representing the generated survey prompt\n\nExample Request:\n```json\n{\n \"prompt_type\": \"generic\",\n \"why_prompt\": \"How does social media usage affect sleep patterns?\"\n}\n```\n\nExample Response:\n```json\n{\n \"dependent_variable\": \"Please read the descriptions of the two social media usage scenarios carefully. Then, please indicate which of the two scenarios you believe has a more significant impact on sleep patterns.\"\n}\n```\n\nNotes:\n- The dependent variable is generated using the GPT-4 language model\n- The generated dependent variable can be added to the experiment object\n\nRaises:\n- HTTPException 500: If an error occurs during the generation of the dependent variable", "operationId": "createExperimentsDependentVariable", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/DependentVariable" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/DependentVariableResponse" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Create Dependent Variable", "tags": [ "v1.experiments" ] } }, "/api/v1/experiments/likert-label": { "post": { "description": "Create a set of Likert scale labels based on the input prompt.\n\nThis endpoint generates a specified number of Likert scale labels\nusing the provided prompt. The generated labels can be used in experiments\nor surveys.", "operationId": "createExperimentsLikertLabel", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/LikertLabelRequest" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/LikertLabelResponse" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Create Likert Label", "tags": [ "v1.experiments" ] } }, "/api/v1/experiments/next-experiment-suggestion": { "post": { "description": "Create another experiment based on Q&A of previous experiment.", "operationId": "createExperimentsNextExperimentSuggestion", "parameters": [ { "in": "query", "name": "experiment_wandb_id", "required": true, "schema": { "title": "Experiment Wandb Id", "type": "string" } } ], "responses": { "200": { "content": { "application/json": { "schema": {} } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Create Next Experiment Suggestion", "tags": [ "v1.experiments" ] } }, "/api/v1/experiments/personas/stream": { "post": { "operationId": "createExperimentsPersonasStream", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/StreamPersonaInput" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/StreamPersonaOutput" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Stream Experiment Personas", "tags": [ "v1.experiments" ] } }, "/api/v1/experiments/rerun-analytics": { "post": { "description": "Re-run R analytics for a single experiment and update the WandB run artifacts.", "operationId": "createExperimentsRerunAnalytics", "parameters": [ { "description": "WandB run ID", "in": "query", "name": "wandb_id", "required": true, "schema": { "description": "WandB run ID", "title": "Wandb Id", "type": "string" } } ], "responses": { "200": { "content": { "application/json": { "schema": {} } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Rerun Analytics", "tags": [ "v1.experiments" ] } }, "/api/v1/experiments/study-subject": { "post": { "description": "Create a study subject based on the input question.", "operationId": "createExperimentsStudySubject", "parameters": [ { "in": "query", "name": "why_prompt", "required": true, "schema": { "title": "Why Prompt", "type": "string" } } ], "responses": { "200": { "content": { "application/json": { "schema": {} } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Create Study Subject", "tags": [ "v1.experiments" ] } }, "/api/v1/experiments/{experiment_id}/progress": { "get": { "description": "Stream real-time progress of an experiment", "operationId": "getExperimentsByExperimentIdProgress", "parameters": [ { "in": "path", "name": "experiment_id", "required": true, "schema": { "title": "Experiment Id", "type": "string" } } ], "responses": { "200": { "content": { "application/json": { "schema": {} } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Stream Experiment Progress", "tags": [ "v1.experiments" ] } }, "/api/v1/experiments/{run_id}/personas": { "get": { "description": "Get synthetic personas from running or completed experiment", "operationId": "getExperimentsByRunIdPersonas", "parameters": [ { "in": "path", "name": "run_id", "required": true, "schema": { "title": "Run Id", "type": "string" } } ], "responses": { "200": { "content": { "application/json": { "schema": {} } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Get Experiment Personas", "tags": [ "v1.experiments" ] } }, "/api/v1/human-baselines/execute/batch": { "post": { "description": "This endpoint is used run the human baselines based on the list of\nfolders provided in the csv request file. The folder names should be\navailable in the Ditto repository here:\nhttps://github.com/Subconscious-ai/Ditto/tree/main/transcriptions/transcriptions_consolidated", "operationId": "createHumanBaselinesExecuteBatch", "parameters": [ { "in": "query", "name": "output_filename", "required": false, "schema": { "default": "human_baseline_output", "title": "Output Filename", "type": "string" } } ], "requestBody": { "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/Body_execute_human_baselines_api_v1_human_baselines_execute_batch_post" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": {} } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Execute Human Baselines", "tags": [ "v1.human-baselines" ] } }, "/api/v1/human-baselines/transcribe-from-pdf": { "post": { "description": "Upload a PDF of the paper you want to transcribe. The system will:\n1. Extract text from the PDF.\n2. Create embeddings and store in a vector store.\n3. Run a RetrievalQA chain to find all relevant fields to transcribe the paper.", "operationId": "createHumanBaselinesTranscribeFromPdf", "requestBody": { "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/Body_transcription_humanbaseline_api_v1_human_baselines_transcribe_from_pdf_post" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "additionalProperties": { "additionalProperties": true, "type": "object" }, "title": "Response Transcription Humanbaseline Api V1 Human Baselines Transcribe From Pdf Post", "type": "object" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Transcription Humanbaseline", "tags": [ "v1.human-baselines" ] } }, "/api/v1/human-baselines/transcriptions/{hb_folder}/validate": { "get": { "description": "This endpoint validates the transcriptions", "operationId": "getHumanBaselinesTranscriptionsByHbFolderValidate", "parameters": [ { "in": "path", "name": "hb_folder", "required": true, "schema": { "title": "Hb Folder", "type": "string" } } ], "responses": { "200": { "content": { "application/json": { "schema": {} } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Validate Transcriptions", "tags": [ "v1.human-baselines" ] } }, "/api/v1/human-baselines/{hb_folder}/replications-amces": { "get": { "description": "Fetches human baseline experiment data and AMCE results for unique LLM schemas.\n\nArgs:\n hb_folder (str): The name of the human baseline folder.\n\nReturns:\n dict: A dictionary containing hb data and unique replication details.", "operationId": "getHumanBaselinesByHbFolderReplicationsAmces", "parameters": [ { "in": "path", "name": "hb_folder", "required": true, "schema": { "title": "Hb Folder", "type": "string" } } ], "responses": { "200": { "content": { "application/json": { "schema": { "additionalProperties": true, "title": "Response Fetch Human Baseline Replications Amces Api V1 Human Baselines Hb Folder Replications Amces Get", "type": "object" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Fetch Human Baseline Replications Amces", "tags": [ "v1.human-baselines" ] } }, "/api/v1/latent-class-analysis": { "post": { "operationId": "createLatentClassAnalysis", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/LatentClassInput" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": {} } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Latent Class Analysis", "tags": [ "v1.attributes_levels" ] } }, "/api/v1/levels": { "post": { "description": "Create levels for given attribute(s) of an why_prompt.\n\nParameters:\n- `req`: LevelsRequest object containing:\n - `why_prompt`: The main concept or input question\n - `country`: Target country\n - `attributes`: List of attributes to generate levels for\n - `level_count`: Number of levels per attribute (optional)\n - `llm_model`: Language model to use (optional)\n\nReturns:\n- List of attributes with their levels.\n\nRaises:\n- HTTPException 404: If an error occurs during creation", "operationId": "createLevels", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/LevelsRequest" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "items": { "$ref": "#/components/schemas/LeveledAttributeBase" }, "title": "Response Create Levels Api V1 Levels Post", "type": "array" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Create Levels", "tags": [ "v1.attributes_levels" ] } }, "/api/v1/market-simulator/check-realworld-product": { "post": { "description": "Checks if a why_prompt can correspond to a real-world product.", "operationId": "createMarketSimulatorCheckRealworldProduct", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/CheckProductRequest" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/CheckProductRealWorldResponse" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Check For Product", "tags": [ "v1.market-simulator" ] } }, "/api/v1/personas": { "get": { "description": "Generate personas based on specified traits and levels.\n\nParameters:\n- `levels_per_trait`: Number of levels for each trait\n- `trait_keys`: Comma-separated list of trait keys\n\nReturns:\nJSONResponse with:\n- `all_combinations_index`: List of trait level combinations\n- `traits_lookup_map`: Dictionary of traits and their levels\n- `personas_full_string_definition`: List of persona descriptions\n\nRaises:\n- HTTPException 500: If persona generation fails", "operationId": "getPersonas", "parameters": [ { "in": "query", "name": "levels_per_trait", "required": true, "schema": { "title": "Levels Per Trait", "type": "integer" } }, { "in": "query", "name": "trait_keys", "required": true, "schema": { "title": "Trait Keys", "type": "string" } } ], "responses": { "200": { "content": { "application/json": { "schema": {} } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Get Personas", "tags": [ "v1.personas" ] } }, "/api/v1/personas/constraints": { "post": { "description": "Generate constraints that may affect a user's decision-making process.\n\n This endpoint analyzes a given question, user profile, and relevant attributes to produce\n a set of constraints or limiting factors that could influence the user's decision.\n These constraints help in understanding the boundaries within which a decision is made.\n\n Parameters:\n - `req (ConstraintRequest)`: Contains the question, user profile, and relevant attributes\n\n Returns:\n - `ConstraintResponse`: A dictionary of constraints and their descriptions", "operationId": "createPersonasConstraints", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ConstraintRequest" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ConstraintResponse" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Create Constraints", "tags": [ "v1.personas" ] } }, "/api/v1/personas/extract-from-pdf": { "post": { "description": "Extracts personas from a PDF file and returns the extracted personas.", "operationId": "createPersonasExtractFromPdf", "requestBody": { "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/Body_extract_from_pdf_api_v1_personas_extract_from_pdf_post" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/PersonasResponse" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Extract From Pdf", "tags": [ "v1.personas" ] } }, "/api/v1/personas/generate_questions": { "post": { "description": "Generate questions for an experiment based on historical factors and constraints.\n\nThis endpoint creates a set of questions tailored to the given context, user profile,\nand specific dimensions of interest. The questions are designed to gather insights\nabout the user's decision-making process, considering both historical behavior and\ncurrent constraints.\n\nParameters:\n- `req (QuestionRequest)`: Contains the main question, user profile, and dimensions to explore\n\nReturns:\n- `QuestionResponse`: A structured set of questions categorized by model type (history/constraints)\n and dimensions, each with sample responses\n\nThe response includes:\n- Two questions for each specified dimension\n- A set of sample responses for each question\n\nRaises:\n- HTTPException 404: If there's an error in generating the questions\n\nNote:\n- Questions are generated asynchronously for efficiency\n- The structure is flexible and can accommodate various schemas and dimensions", "operationId": "createPersonasGenerateQuestions", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/QuestionRequest" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/QuestionResponse" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Create Questions", "tags": [ "v1.personas" ] } }, "/api/v1/personas/history": { "post": { "description": "Generate historical factors relevant to a user's decision-making process.\n\nThis endpoint analyzes a given question and user profile to produce a set of\nhistorical factors that could influence the user's decision. These factors\nprovide context for understanding past behaviors and preferences.\n\nParameters:\n- `req (HistoryRequest)`: Contains the question, user profile, and relevant attributes\n\nReturns:\n- `HistoryResponse`: A dictionary of historical factors and their descriptions\n\nRaises:\n- HTTPException 404: If there's an error in generating historical factors", "operationId": "createPersonasHistory", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/app__api__v1__schemas__personas__HistoryRequest" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HistoryResponse" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Create History", "tags": [ "v1.personas" ] } }, "/api/v1/personas/motivation": { "post": { "description": "Generate motivation factors influencing a user's decision-making process.\n\nThis endpoint analyzes the given context, user profile, historical factors, and constraints\nto produce a set of motivation factors that could drive the user's decision. These factors\nhelp in understanding the underlying reasons behind a user's choices.\n\nParameters:\n- `req (MotivationRequest)`: Contains the main question, user profile, selected historical factors, and constraints\n\nReturns:\n- `MotivationResponse`: A dictionary of motivation factors and their descriptions\n\nRaises:\n- HTTPException 404: If there's an error in generating motivation factors\n\nNote:\n- The generated motivation factors are based on the provided context and previously selected factors", "operationId": "createPersonasMotivation", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/MotivationRequest" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/MotivationResponse" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Create Motivation", "tags": [ "v1.personas" ] } }, "/api/v1/populations/location-recommendation": { "post": { "operationId": "createPopulationsLocationRecommendation", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/LocationRecommendationRequest" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/LocationRecommendationAsyncResponse" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Create Location Recommendation", "tags": [ "v1.populations" ] } }, "/api/v1/populations/location-recommendation/{job_id}": { "get": { "operationId": "getPopulationsLocationRecommendationByJobId", "parameters": [ { "in": "path", "name": "job_id", "required": true, "schema": { "title": "Job Id", "type": "string" } } ], "responses": { "200": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/LocationRecommendationJobResponse" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Get Location Recommendation", "tags": [ "v1.populations" ] } }, "/api/v1/populations/statement-direction": { "post": { "operationId": "createPopulationsStatementDirection", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/StatementDirectionInput" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "additionalProperties": true, "title": "Response Get Statement Directions Api V1 Populations Statement Direction Post", "type": "object" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Get Statement Directions", "tags": [ "v1.populations" ] } }, "/api/v1/populations/validate": { "post": { "operationId": "createPopulationsValidate", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/PopulationRequest" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/PopulationRecommendationResponse" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Validate Population", "tags": [ "v1.populations" ] } }, "/api/v1/populations/validate-non-us": { "post": { "operationId": "createPopulationsValidateNonUs", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/PopulationRequestNonUS" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/PopulationRecommendationResponseNonUS" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Validate Population Non Us", "tags": [ "v1.populations" ] } }, "/api/v1/product-attributes-levels": { "post": { "description": "Stream product attribute generation as SSE-framed JSON events.\n\nEmits {type:\"progress\",step} frames during work and a terminal\n{type:\"result\",data:} or {type:\"error\"}.", "operationId": "createProductAttributesLevels", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ProductAttributeRequest" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": {} } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Product Attribute Levels", "tags": [ "v1.attributes_levels" ] } }, "/api/v1/runs": { "post": { "description": "Fetch experiment runs based on provided filters.\n\nParameters:\n- `filters`: RunRequest object containing filter criteria\n\nReturns:\n- List of RunResponse objects matching the filters\n\nExample filter:\n```json\n{\n \"filters\": {\n \"config.user\": {\n \"$eq\": \"Add a user_id here. e.g. auth0|1234567890\"\n },\n \"created_at\": {\n \"$gt\": \"2024-10-16T19:18:48.753240\",\n \"$lte\": \"2024-10-17T19:18:48.753258\"\n }\n }\n}\n```\n\nNotes:\n- Returns up to 10 runs due to performance issues - WANDB does not have pagination so for performance we should return less runs (temporary solution).\n- Excludes runs hidden from the user\n\nRaises:\n- HTTPException 500: If fetching runs fails", "operationId": "createRuns", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/RunRequest" } } } }, "responses": { "200": { "content": { "application/json": { "schema": { "anyOf": [ { "items": { "$ref": "#/components/schemas/RunResponse" }, "type": "array" }, { "type": "null" } ], "title": "Response Get Runs Api V1 Runs Post" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Get Runs", "tags": [ "v1.runs" ] } }, "/api/v1/runs/all": { "get": { "description": "Get all the user runs/experiments.\n\nNote: This endpoint may take time for users with many experiments.\nConsider implementing pagination or caching for better performance.", "operationId": "getRunsAll", "responses": { "200": { "content": { "application/json": { "schema": { "items": { "$ref": "#/components/schemas/CleanedRunResponse" }, "title": "Response Get All User Runs Api V1 Runs All Get", "type": "array" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Get All User Runs", "tags": [ "v1.runs" ] } }, "/api/v1/runs/all-concept": { "get": { "description": "Get all the user runs/experiments.", "operationId": "getRunsAllConcept", "responses": { "200": { "content": { "application/json": { "schema": { "items": { "$ref": "#/components/schemas/ConceptRunResponse" }, "title": "Response Get All User Concept Runs Api V1 Runs All Concept Get", "type": "array" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Get All User Concept Runs", "tags": [ "v1.runs" ] } }, "/api/v1/runs/artifact/{file_name}": { "get": { "description": "Fetch a specific artifact file from a run.\n\nParameters:\n- `file_name`: Name of the artifact file to retrieve\n\nReturns:\n- FileResponse: The requested artifact file\n- JSONResponse: Error message if the file is not found\n\nNotes:\n- Automatically deletes the local artifact directory after serving the file\n\nRaises:\n- HTTPException 504: If the request times out\n- HTTPException 500: For other errors in fetching the artifact", "operationId": "getRunsArtifactByFileName", "parameters": [ { "in": "path", "name": "file_name", "required": true, "schema": { "title": "File Name", "type": "string" } } ], "responses": { "200": { "content": { "application/json": { "schema": {} } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Get Run Artifact", "tags": [ "v1.runs" ] } }, "/api/v1/runs/concept/{run_id}": { "get": { "description": "Fetch a specific artifact file from a run.\n\nParameters:\n- `file_name`: Name of the artifact file to retrieve\n\nReturns:\n- FileResponse: The requested artifact file\n- JSONResponse: Error message if the file is not found\n\nNotes:\n- Automatically deletes the local artifact directory after serving the file\n\nRaises:\n- HTTPException 504: If the request times out\n- HTTPException 500: For other errors in fetching the artifact", "operationId": "getRunsConceptByRunId", "parameters": [ { "in": "path", "name": "run_id", "required": true, "schema": { "title": "Run Id", "type": "string" } } ], "responses": { "200": { "content": { "application/json": { "schema": {} } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Get Concept Analytics", "tags": [ "v1.runs" ] } }, "/api/v1/runs/{hb_id}/details": { "get": { "description": "Fetch details of a specific Human Baseline experiment.\n\nParameters:\n- `hb_id`: Unique identifier of the Human Baseline experiment. e.g. `7h2ks593`\n\nReturns:\n\nJSONResponse containing the experiment details\n\nRaises:\n- HTTPException 500: If fetching HB experiment details fails", "operationId": "getRunsByHbIdDetails", "parameters": [ { "in": "path", "name": "hb_id", "required": true, "schema": { "title": "Hb Id", "type": "string" } } ], "responses": { "200": { "content": { "application/json": { "schema": {} } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Get Hb Details", "tags": [ "v1.runs" ] } }, "/api/v1/runs/{run_id}": { "delete": { "description": "Delete an experiment run by ID.\n\nArgs:\n run_id (str): The unique identifier of the run to delete.\n\nReturns:\n Response: Empty response with 204 status code on successful deletion.\n\nRaises:\n HTTPException: For various error scenarios including unauthorized access, not found, or server errors.", "operationId": "deleteRunsByRunId", "parameters": [ { "in": "path", "name": "run_id", "required": true, "schema": { "title": "Run Id", "type": "string" } } ], "responses": { "204": { "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Delete an experiment run", "tags": [ "v1.runs" ] }, "get": { "description": "Fetch details of a specific experiment run.\n\nParameters:\n- `run_id`: Unique identifier of the run.\n\nReturns:\nJSONResponse with:\n- `run_details`: Details of the requested run\n\nNotes:\n- Returns 403 if the run is private and not accessible to the user\n\nRaises:\n- HTTPException 500: If fetching run details fails", "operationId": "getRunsByRunId", "parameters": [ { "in": "path", "name": "run_id", "required": true, "schema": { "title": "Run Id", "type": "string" } } ], "responses": { "200": { "content": { "application/json": { "schema": {} } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Get Run", "tags": [ "v1.runs" ] } }, "/api/v1/runs/{run_id}/status": { "get": { "description": "Returns the current state of a run.\n\n**Known limitation.** This endpoint is unreliable in both directions: it\ncan report a terminal `lost` state for a run that is still queued, and\n`finished` for a run that failed and produced no artifacts. Treat the\nW&B run as the source of truth \u2014 check its `summary.status` together with\n`logged_artifacts()`. W&B's own `state` field can itself remain `running`\nafter a timeout.\n\nNormalised states are `in-queue`, `running`, `finished`, `failed`,\n`crashed`, `killed`, `lost`, and `not found`. A run is terminal in every\nstate except `in-queue` and `running`.\n", "operationId": "getRunsByRunIdStatus", "parameters": [ { "in": "path", "name": "run_id", "required": true, "schema": { "title": "Run Id", "type": "string" } } ], "responses": { "200": { "content": { "application/json": { "schema": {} } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Get run status", "tags": [ "v1.runs" ] } }, "/api/v1/tasks/{task_id}": { "get": { "description": "Get the status of a Celery task.\n\nParameters:\n- `task_id`: Unique identifier of the Celery task\n\nReturns:\nJSONResponse with:\n- `task_id`: The ID of the task\n- `task_status`: Current status of the task\n- `task_result`: Result of the task (if available)\n\nExample Response:\n{\n \"task_id\": \"abc123\",\n \"task_status\": \"SUCCESS\",\n \"task_result\": {\"some_key\": \"some_value\"}\n}\n\nRaises:\n- HTTPException 500: If fetching the task status fails", "operationId": "getTasksByTaskId", "parameters": [ { "in": "path", "name": "task_id", "required": true, "schema": { "title": "Task Id", "type": "string" } } ], "responses": { "200": { "content": { "application/json": { "schema": {} } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Get Status", "tags": [ "v1.tasks" ] } }, "/api/v1/traits": { "get": { "description": "Returns the catalogue of persona traits available for population\ntargeting. Use the returned `id` values when building `population_traits`\non an experiment request.\n", "operationId": "getTraits", "responses": { "200": { "content": { "application/json": { "example": [ { "id": "travel_frequency", "long_description": "How often the respondent travels for leisure.", "measurement_type": "ordinal", "ordinal_rank": 3, "set_type": "core", "short_description": "Travel frequency", "type": "trait" } ], "schema": { "items": { "$ref": "#/components/schemas/TraitLevel" }, "title": "Response Get Traits Api V1 Traits Get", "type": "array" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "List available persona traits", "tags": [ "v1.traits" ] } }, "/api/v1/traits/extract-from-pdf": { "post": { "description": "Upload a PDF and provide a question. The system will:\n1. Extract text from the PDF.\n2. Create embeddings and store in a vector store.\n3. Run a RetrievalQA chain to find traits relevant to the user's question.", "operationId": "createTraitsExtractFromPdf", "parameters": [ { "description": "A user question to guide trait extraction", "in": "query", "name": "question", "required": true, "schema": { "description": "A user question to guide trait extraction", "title": "Question", "type": "string" } } ], "requestBody": { "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/Body_extract_traits_from_pdf_with_question_api_v1_traits_extract_from_pdf_post" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "additionalProperties": { "additionalProperties": true, "type": "object" }, "title": "Response Extract Traits From Pdf With Question Api V1 Traits Extract From Pdf Post", "type": "object" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Extract Traits From Pdf With Question", "tags": [ "v1.traits" ] } }, "/api/v1/traits/natural-language": { "post": { "description": "Get the description for a given trait level.", "operationId": "createTraitsNaturalLanguage", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/NaturalLanguageTraitRequest" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "additionalProperties": true, "title": "Response Get Natural Language Trait Description Api V1 Traits Natural Language Post", "type": "object" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Get Natural Language Trait Description", "tags": [ "v1.traits" ] } }, "/api/v1/traits/suggest": { "post": { "description": "Suggest additional traits with their possible levels based on the why_prompt and currently selected traits.\n\nArgs:\n request: TraitGenerationRequest containing:\n - why_prompt: The use case explanation\n - selected_traits: List of already selected trait names\n\nReturns:\n TraitSuggestionResponse containing:\n - suggested_traits: Dictionary mapping trait names to their possible levels\n\nRaises:\n HTTPException: If there's an error in trait suggestion process", "operationId": "createTraitsSuggest", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/TraitGenerationRequest" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/TraitSuggestionResponse" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Suggest Traits", "tags": [ "v1.traits" ] } }, "/api/v1/traits/suggest/levels": { "post": { "description": "Provides levels for a given trait based on why prompt and existing traits.", "operationId": "createTraitsSuggestLevels", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/TraitLevelsSuggestionRequest" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/TraitLevelsSuggestionResponse" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Suggest Trait Levels", "tags": [ "v1.traits" ] } }, "/api/v2/attributes_levels/consolidated": { "post": { "description": "Create attributes and levels for a given why_prompt, automatically\ndetermining if it's a real-world product.\nIf it is a real-world product, generates product-specific attributes and levels.\nIf not, generates regular attributes and levels.\n\nParameters:\n- `req`: AttributesLevelsRequest object containing:\n - `why_prompt`: The main concept or prompt\n - `country`: Target country\n - `level_count`: Number of levels per attribute (optional)\n - `max_length`: Maximum length for levels (optional)\n - `llm_model`: Language model to use (optional)\n - `attribute_count`: Number of attributes to generate (optional)\n\nReturns:\n- List of attributes with their levels.", "operationId": "createAttributesLevelsConsolidated", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/AttributesLevelsRequest" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "additionalProperties": true, "title": "Response Create Attributes And Levels Api V2 Attributes Levels Consolidated Post", "type": "object" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Create Attributes And Levels", "tags": [ "v2.attributes_levels" ] } }, "/api/v2/attributes_levels/enhance": { "post": { "operationId": "createAttributesLevelsEnhance", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/EnhanceAttributesLevelsRequest" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/AttributesLevelsResponse" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Enhance Attributes And Levels", "tags": [ "v2.attributes_levels" ] } }, "/api/v2/latent-variables/generate": { "post": { "description": "Generate psychological traits with their measurement statements, pain points,\nand point detection statements based on a research context (why-prompt).\n\nArgs:\n req: The request containing the research question (why-prompt) and\n configuration.\n\nReturns:\n GenerationResponse: The list of traits with their associated measurements +\n Likert scales, and the why prompt from which they were generated.\n\nRaises:\n HTTPException 500: If an error occurs during generation.\n HTTPException 422: Output validation failed.", "operationId": "createLatentVariablesGenerate", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/GenerationRequest" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "items": { "additionalProperties": true, "type": "object" }, "title": "Response Generate Latent Variables Api V2 Latent Variables Generate Post", "type": "array" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Generate Latent Variables", "tags": [ "v2.latent-variables" ] } }, "/api/v2/latent-variables/generate-latent-variables-two-step": { "post": { "description": "Generate psychological traits with their measurement statements, pain points,\nand point detection statements based on a research context (why-prompt).\n\nArgs:\n req: The request containing the research question (why-prompt) and\n configuration.\n\nReturns:\n GenerationResponse: The list of traits with their associated measurements +\n Likert scales, and the why prompt from which they were generated.\n\nRaises:\n HTTPException 500: If an error occurs during generation.\n HTTPException 422: Output validation failed.", "operationId": "createLatentVariablesGenerateLatentVariablesTwoStep", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/GenerationRequest" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "items": { "additionalProperties": true, "type": "object" }, "title": "Response Generate Latent Variables Two Step Api V2 Latent Variables Generate Latent Variables Two Step Post", "type": "array" } } }, "description": "Successful Response" } }, "security": [ { "HTTPBearer": [] } ], "summary": "Generate Latent Variables Two Step", "tags": [ "v2.latent-variables" ] } } }, "servers": [ { "description": "Production", "url": "https://api.subconscious.ai" } ], "tags": [ { "description": "\ud83e\uddea\ud83d\udc68\u200d\ud83d\udd2c\u2697\ufe0fRun a novel experiment using attributes, levels, traits, dependent variables, preambles, and personas and place results in a run.", "name": "v1.experiments" }, { "description": "\ud83d\udcd9 Generate product features (attributes) and their variations (levels)", "name": "v1.attributes_levels" }, { "description": "**Why**. \ud83d\udd2cCausal factors that influence a person's decision. Output:Return a list of persona traits that are available to subconscious.ai users.", "name": "v1.traits" }, { "description": "**Who**. \ud83d\udc6aWho is the respondent? A respondent is made up of traits. Input: levels_per_trait - the number of levels of persona traits we would like to return per trait. trait_keys: a comma separated list of traits from the /traits endpoint. Output: Return a list of persona traits that are available to subconscious.ai users.", "name": "v1.personas" }, { "description": "\ud83d\udcc8Contains the experimental design + Experiment Results from WANDB.", "name": "v1.runs" }, { "description": "\ud83d\udc65 Human baselines endpoints contains human baseline data and AMCEs", "name": "v1.human-baselines" }, { "description": "\ud83d\udcdd Monitor and manage Celery task statuses", "name": "v1.tasks" }, { "description": "\ud83c\udfea Simulate market conditions and consumer behaviors", "name": "v1.market-simulator" }, { "description": "\ud83d\udc6a Find respondents with the required core traits", "name": "v1.populations" }, { "description": "\ud83d\udcd9 Generate product features (attributes) and their variations (levels)", "name": "v2.attributes_levels" } ] }