Closed yongchao98 closed 5 months ago
python agentboard/eval_main.py --cfg-path eval_configs/main_results_all_tasks.yaml --tasks scienceworld --model gpt-4 --log_path ./results/gpt-4 --project_name evaluate-gpt-4 \
I try to test the tasks with GPT-4, but get the following errors:
File "/home/ycchen/miniconda3/envs/Agentboard/lib/python3.8/os.py", line 675, in getitem raise KeyError(key) from None KeyError: 'OPENAI_API_TYPE'
setting OPENAI_API_TYPE="open_ai" in file .env may solve this problem :)
OPENAI_API_TYPE="open_ai"
.env
python agentboard/eval_main.py --cfg-path eval_configs/main_results_all_tasks.yaml --tasks scienceworld --model gpt-4 --log_path ./results/gpt-4 --project_name evaluate-gpt-4 \
I try to test the tasks with GPT-4, but get the following errors:
File "/home/ycchen/miniconda3/envs/Agentboard/lib/python3.8/os.py", line 675, in getitem raise KeyError(key) from None KeyError: 'OPENAI_API_TYPE'