experiments

Create Experiment Async

POST
Create asynchronous experiment.

Request

This endpoint expects an object.
title
stringOptional
random_seed
integerOptional
experiment_model_type
enumOptional
Enum representing the llm model types used in the experiments.
dependent_variable_model_type
enumOptional
Enum representing the llm model types used in the experiments.
levels_model_type
enumOptional
Enum representing the llm model types used in the experiments.
use_api
booleanOptional
use_threading
booleanOptional
use_batching
booleanOptional
is_private
booleanOptional
attribute_prompt_version
doubleOptional
levels_prompt_version
doubleOptional
task_prompt_version
doubleOptional
scenarios_prompt
stringOptional
prompt_preamble
stringOptional
prompt
stringOptional
experiment_size
integerOptional
max_length
integerOptional
number_of_respondents
integerOptional
number_of_tasks_per_respondent
integerOptional
number_of_attributes
integerOptional
number_of_levels
integerOptional
pre_cooked_attributes_and_levels_lookup
list of lists of unionsOptional
levels_per_trait
integerOptional
null_levels
booleanOptional
total_number_of_tasks
integerOptional
confidence_level
stringOptional
keep_inconsistent_answers
booleanOptional
add_neither_option
booleanOptional
use_fully_randomized_design
booleanOptional
add_price_and_brand_attributes
booleanOptional
personas
map from strings to maps from strings to lists of anyOptional
personas_full_string_definition
list of stringsOptional
all_combinations_index
list of lists of stringsOptional
population_traits
list of stringsOptional
respondent_dependent_variable
stringOptional
respondent_instructions_preamble
stringOptional
experimentor_why_question_type
stringOptional
experimentor_why_question_prompt
stringOptional
where_preamble
stringOptional
when_preamble
stringOptional
current_preamble
stringOptional
hb_run_id
stringOptional
paper_data
list of lists of stringsOptional

Response

This endpoint returns an object
wandb_run_id
string
wandb_run_name
string
POST
1curl -X POST /experiments \
2 -H "Authorization: Bearer <token>" \
3 -H "Content-Type: application/json" \
4 -d '{
5 "experiment_model_type": "gpt3",
6 "dependent_variable_model_type": "gpt3",
7 "levels_model_type": "gpt3",
8 "is_private": false,
9 "max_length": 40,
10 "number_of_respondents": 75,
11 "number_of_tasks_per_respondent": 10,
12 "number_of_attributes": 2,
13 "number_of_levels": 6,
14 "pre_cooked_attributes_and_levels_lookup": [
15 [
16 "Will this car have advanced safety features?",
17 [
18 "Advanced airbag system to protect passengers",
19 "Lane keep assist to prevent drifting into other lanes"
20 ]
21 ],
22 [
23 "What range and charging time will this car offer",
24 [
25 "Up to 500 miles range, featuring a revolutionary battery system that charges in 45 minutes",
26 "200 miles range with a robust charging infrastructure for recharging in 15 minutes"
27 ]
28 ]
29 ],
30 "levels_per_trait": 2,
31 "null_levels": true,
32 "add_price_and_brand_attributes": false,
33 "population_traits": [
34 "educational attainment",
35 "english language ability"
36 ],
37 "experimentor_why_question_type": "generic",
38 "experimentor_why_question_prompt": "I would like to design a new electric car for the American markets",
39 "where_preamble": "United States",
40 "when_preamble": "2023",
41 "hb_run_id": "",
42 "paper_data": [
43 [
44 "paper_data"
45 ]
46 ]
47}'
200Successful
1{
2 "wandb_run_id": "wandb_run_id",
3 "wandb_run_name": "wandb_run_name"
4}