Design, conduct and analyze results of AI-powered surveys and experiments. Simulate social science and market research with large numbers of AI agents and LLMs.
q_educ = QuestionMultipleChoice(
question_name = "educ",
question_text = "What is the highest level of education you have completed?",
question_options = [
"Did not graduate from high school",
"High school graduate",
"Some college, but no degree (yet)",
"2-year college degree",
"4-year college degree",
"Postgraduate degree (MA, MBA, MD, JD, PhD, etc.)"
]
)
q_institution = QuestionFreeText(
question_name = "institution",
question_text = "Where did you complete your highest degree?"
)
survey = Survey([q_educ, q_institution]).add_targeted_memory(q_institution, q_educ)
results = survey.run()
Error:
Exception: InterviewErrorPriorTaskCanceled('Required tasks failed for institution')
Time: 1721058884.788631
Traceback:
Traceback (most recent call last):
File "/Users/a16174/edsl/edsl/jobs/tasks/QuestionTaskCreator.py", line 230, in _run_task_async
return await self._run_focal_task(debug)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/a16174/edsl/edsl/jobs/tasks/QuestionTaskCreator.py", line 125, in _run_focal_task
requested_tokens = self.estimated_tokens()
^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/a16174/edsl/edsl/jobs/tasks/QuestionTaskCreator.py", line 100, in estimated_tokens
return self.token_estimator(self.question)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/a16174/edsl/edsl/jobs/interviews/InterviewTaskBuildingMixin.py", line 140, in _get_estimated_request_tokens
for prompt in invigilator.get_prompts().values():
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/a16174/edsl/edsl/agents/PromptConstructionMixin.py", line 347, in get_prompts
question_instructions=self.question_instructions_prompt,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/a16174/edsl/edsl/agents/PromptConstructionMixin.py", line 271, in question_instructions_prompt
d[question].answer = answer
~^^^^^^^^^^
KeyError: 'educ_comment'
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/Users/a16174/edsl/edsl/jobs/interviews/Interview.py", line 139, in _extract_valid_results
result = task.result()
^^^^^^^^^^^^^
File "/Users/a16174/.pyenv/versions/3.11.7/lib/python3.11/asyncio/futures.py", line 203, in result
raise self._exception.with_traceback(self._exception_tb)
File "/Users/a16174/.pyenv/versions/3.11.7/lib/python3.11/asyncio/tasks.py", line 277, in __step
result = coro.send(None)
^^^^^^^^^^^^^^^
File "/Users/a16174/edsl/edsl/jobs/tasks/QuestionTaskCreator.py", line 239, in _run_task_async
raise InterviewErrorPriorTaskCanceled(
edsl.exceptions.jobs.InterviewErrorPriorTaskCanceled: Required tasks failed for institution
@rbyh Thank you - good catch. On it. In the interest of testing, in future, can you create code samples on chick? For example, a failing notebook object would be great.
Code to reproduce:
Error: