yongchao98 / autotamp Goto Github PK

Thanks for releasing the code!
I successfully ran the autotamp_single_agent.py file.
I run the llm_task_plan.py, my open ai is GPT3, domain is chip. When I run this file, the following problem occurs.

case1：
input_instruction0: Try to reach all the goals but you have to reach the corresponding key first to open the specific door. For example, you have to reach key1 ahead to open door1. Also remember always do not touch the walls.
Traceback (most recent call last):
File "C:\Users\MFL\Desktop\LLM test\AutoTAMP-main\AutoTAMP-main\llm_task_plan.py", line 84, in
response = GPT_response_first_round(prompt, model_name_NL2TL=model_name)
File "C:\Users\MFL\Desktop\LLM test\AutoTAMP-main\AutoTAMP-main\openai_func.py", line 47, in GPT_response_first_round
response = openai.Completion.create(
File "D:\Users\MFL\anaconda3\envs\studytorch\lib\site-packages\openai\api_resources\completion.py", line 25, in create
return super().create(*args, **kwargs)
File "D:\Users\MFL\anaconda3\envs\studytorch\lib\site-packages\openai\api_resources\abstract\engine_api_resource.py", line 153, in create
response, _, api_key = requestor.request(
File "D:\Users\MFL\anaconda3\envs\studytorch\lib\site-packages\openai\api_requestor.py", line 298, in request
resp, got_stream = self._interpret_response(result, stream)
File "D:\Users\MFL\anaconda3\envs\studytorch\lib\site-packages\openai\api_requestor.py", line 700, in _interpret_response
self._interpret_response_line(
File "D:\Users\MFL\anaconda3\envs\studytorch\lib\site-packages\openai\api_requestor.py", line 765, in _interpret_response_line
raise self.handle_error_response(
openai.error.InvalidRequestError: The model text-davinci-003 has been deprecated, learn more here:

the question maybe the model text-davinci-003 has been deprecated,so

case 2:
when I change model into other model that could be used, I face "You exceeded your current quota, please check your plan and billing details"

So, what should I do next ? Please give me some advice! thanks

Dear author, where is the part to implement SayCan method?

Hi @yongchao98,

Thanks for releasing the code!
I quickly tested this using the command python autotamp_single_agent.py

I keep running into errors here

SyntaxError: EOL while scanning string literal

Output from GPT looks like

"['and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and', 'and"

The issue is with ast.literal_eval ?

Have you come across such a issue?

Thanks!