-
Notifications
You must be signed in to change notification settings - Fork 12
Feature/evaluation viz #51
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
👍 좋습니다아! 지금 응답을 json으로 저장하는 부분만 해결되면 저는 머지해도 좋은코드라고 생각합니다.
👍 Persona 생성
Sales Manager, Digital Marketing Specialist, Financial Analyst, HR Analyst...
- 간단한 프롬프트로 페르소나를 생성한것 같은데 데이터에대한 분류가 잘 된것같습니다. @bongkyunSON 님도 이러한 방법을 참고하셔서 데이터를 그룹화하고 질의하는 방법을 고민해보시는건 어떨까요?!
❓/ 💬 Question 생성
- ❓질문은 테이블정보를 보지않고 생성하는것으로 보이는데 맞을까요? (어느정도 중복된 질문이 생성됩니다.)
- 💬 Persona 생성때와 마찬가지로 테이블정보를 함께주고 Persona의 도메인과 관련된 질문을 하게 하면 좀 더 데이터에 맞는 질문이 생성될것 같습니다.
- 👍이 부분을 잘 활용한다면 EDA를 시작할때 많은 도움이 될것도 같습니다!
| if not os.path.exists(filepath): | ||
| os.makedirs(filepath) | ||
| with open(f"{filepath}/eval_result_{index}.json", "w", encoding="utf-8") as f: | ||
| json.dump(data, f, indent=4, ensure_ascii=False) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Traceback (most recent call last):
File "/Users/dwlee/Documents/Lang2SQL/evaluation/gen_answer.py", line 84, in <module>
get_eval_result(
File "/Users/dwlee/Documents/Lang2SQL/evaluation/gen_answer.py", line 69, in get_eval_result
save_answer_json(result, f"{output_dir}/{name}_{version}", i)
File "/Users/dwlee/Documents/Lang2SQL/evaluation/utils.py", line 46, in save_answer_json
json.dump(data, f, indent=4, ensure_ascii=False)
File "/Users/dwlee/miniconda3/lib/python3.11/json/__init__.py", line 179, in dump
for chunk in iterable:
File "/Users/dwlee/miniconda3/lib/python3.11/json/encoder.py", line 432, in _iterencode
yield from _iterencode_dict(o, _current_indent_level)
File "/Users/dwlee/miniconda3/lib/python3.11/json/encoder.py", line 406, in _iterencode_dict
yield from chunks
File "/Users/dwlee/miniconda3/lib/python3.11/json/encoder.py", line 326, in _iterencode_list
yield from chunks
File "/Users/dwlee/miniconda3/lib/python3.11/json/encoder.py", line 406, in _iterencode_dict
yield from chunks
File "/Users/dwlee/miniconda3/lib/python3.11/json/encoder.py", line 439, in _iterencode
o = _default(o)
^^^^^^^^^^^
File "/Users/dwlee/miniconda3/lib/python3.11/json/encoder.py", line 180, in default
raise TypeError(f'Object of type {o.__class__.__name__} '
TypeError: Object of type AIMessage is not JSON serializable
❗ 에러가 발생합니다ㅜㅜ
seyoung4503
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
👍 테스트 해봤는데 잘 되네요..!!
❓ 나중에 기능이 더욱 완성되면 llm 불러오기 파트를 llm_factory의 함수를 사용하면 좋을 것 같아요!!
💬 동욱님께서 언급하셨던 내용인데, 페르소나끼리 비슷한 질문을 하는 경우가 있는 것 같아요
|
👍description으로 페르소나 생성해서 evaluation 만들생각하다니 대단합니다! |
|
👍 정성적인 평가로 성능 검증을 해야하는 프로젝트라 평가 방식이 번거로운데, 다양한 페르소나로 폭 넓은 평가가 가능해 보입니다! |
#️⃣ Issue Number
📝 요약(Summary)
gen_persona.pygen_question.pygen_answer.pyviz_eval.py💬 To Reviewers (선택)
PR Checklist
reference) How to Code Review