Issue with the OpenAI API key

[nithinreddyyyyyy]

export is not working in windows. And I tried set too, it is also not working. Can you please let me know how to deal with this?

[MomenMM]

try to use set instead of export

[nithinreddyyyyyy]

try to use set instead of export

I have used set as well. It is not working...

[ELHARAKA]

+1

[nigelp]

Same here. Can't set API key. Also tried using $env with no luck.

[nithinreddyyyyyy]

Can anyone please look into this?

[JosemyDuarte]

Can you share the specific commands you are running?

[nithinreddyyyyyy]

Can you share the specific commands you are running?

Tried both

set OPENAI_API_KEY=KEY set: OPENAI_API_KEY=KEY

[EnzoMartin]

Should consider re-opening #136 as it would solve these issues for all platforms

[patillacode]

Open discussion about this in #135

Please go there and add your opinions to raise visibility and then maybe get it introduced.

[kenna]

Can you share the specific commands you are running?

Tried both

set OPENAI_API_KEY=KEY set: OPENAI_API_KEY=KEY

try $env:OPENAI_API_KEY="<API-KEY>" on Windows

[augusto-rehfeldt]

set it via openai.api_key = "blablabla" inside gpt_engineer/main.py. Remember to import openai

[Jgreen42]

try to use set instead of export

I have used set as well. It is not working...

same, Having issues my self, I did notice I could not find the file that imports the OPENAI key I believe its supposed to be main.py? I will have to do some more digging make sure I am not over looking something or doing it wrong. If I figure out something on my end I will try to remember to post it.

[ligarius]

Same issue here:

File "C:\xxxxxxx\Proyectos\GPTe\GPTe\gpt_engineer\main.py", line 66, in app()

File "C:\xxxxxxx\Proyectos\GPTe\GPTe\gpt_engineer\main.py", line 47, in main ai = AI(

File "C:\xxxxxxxxx\Proyectos\GPTe\GPTe\gpt_engineer\myenv\lib\site-packages\gpt_engineer\ai.py", line 15, in init openai.Model.retrieve(model)

File "C:\xxxxxxxxxxx\Proyectos\GPTe\GPTe\gpt_engineer\myenv\lib\site-packages\openai\api_resources\abstract\api_resource.py", line 20, in retrieve
instance.refresh(request_id=request_id, request_timeout=request_timeout)

File "C:\xxxxxxxxx\Proyectos\GPTe\GPTe\gpt_engineer\myenv\lib\site-packages\openai\api_resources\abstract\api_resource.py", line 32, in refresh self.request(

File "C:\xxxxxxxxxx\Proyectos\GPTe\GPTe\gpt_engineer\myenv\lib\site-packages\openai\openai_object.py", line 172, in request requestor = api_requestor.APIRequestor(

File "C:\xxxxxxx\Proyectos\GPTe\GPTe\gpt_engineer\myenv\lib\site-packages\openai\api_requestor.py", line 138, in init self.api_key = key or util.default_api_key()

File "C:\xxxxx\Proyectos\GPTe\GPTe\gpt_engineer\myenv\lib\site-packages\openai\util.py", line 186, in default_api_key raise openai.error.AuthenticationError(

openai.error.AuthenticationError: No API key provided. You can set your API key in code using 'openai.api_key = <API-KEY>', or you can set the environment variable OPENAI_API_KEY=<API-KEY>). If your API key is stored in a file, you can point the openai module at it with 'openai.api_key_path = <PATH>'. You can generate API keys in the OpenAI web interface. See https://platform.openai.com/account/api-keys for details.

[liusida]

Agree with this answer, I guess Powershell was used by default nowadays. (If you see something like (venv) PS C:\Projects\AI\gpt-engineer> in your terminal, 'PS` stands for powershell)

Q: in windows powershell, how to set env variable?

ChatGPT: To set an environment variable in Windows PowerShell, you can use the $env automatic variable to access and modify the environment variables. Here's how you can set an environment variable:

$env:VariableName = "VariableValue"

Replace VariableName with the name of the environment variable you want to set, and VariableValue with the desired value.

For example, to set an environment variable named OPENAI_API_KEY with the value sk-x...., you would use the following command:

$env:OPENAI_API_KEY= "sk-x...."

Can you share the specific commands you are running?

Tried both set OPENAI_API_KEY=KEY set: OPENAI_API_KEY=KEY

try $env:OPENAI_API_KEY="" on Windows

[EdwardDali]

on windows works with $env:OPENAI_API_KEY='sk-xxx' but now I get openai.error.RateLimitError: You exceeded your current quota, please check your plan and billing details using the (free) GPT 3.5 key

[ligarius]

using $env:OPENAI_API_KEY="" on Windows

INFO:openai:error_code=model_not_found error_message="The model 'gpt-4' does not exist" error_param=model error_type=invalid_request_error message='OpenAI API error received' stream_error=False Model gpt-4 not available for provided API key. Reverting to gpt-3.5-turbo. Sign up for the GPT-4 wait list here: https://openai.com/waitlist/gpt-4-api Traceback (most recent call last):

File "C:\xxxxx\Proyectos\GPTe\GPTe\gpt_engineer\main.py", line 66, in app()

File "C:\xxxxx\Proyectos\GPTe\GPTe\gpt_engineer\main.py", line 61, in main messages = step(ai, dbs)

File "C:\xxxxxl\Proyectos\GPTe\GPTe\gpt_engineer\myenv\lib\site-packages\gpt_engineer\steps.py", line 30, in clarify messages = [ai.fsystem(dbs.identity["qa"])]

File "C:\xxxxx\Proyectos\GPTe\GPTe\gpt_engineer\myenv\lib\site-packages\gpt_engineer\db.py", line 18, in getitem raise KeyError(key)

KeyError: 'qa'

[kenna]

using $env:OPENAI_API_KEY="" on Windows

INFO:openai:error_code=model_not_found error_message="The model 'gpt-4' does not exist" error_param=model error_type=invalid_request_error message='OpenAI API error received' stream_error=False Model gpt-4 not available for provided API key. Reverting to gpt-3.5-turbo. Sign up for the GPT-4 wait list here: https://openai.com/waitlist/gpt-4-api Traceback (most recent call last):

File "C:\xxxxx\Proyectos\GPTe\GPTe\gpt_engineer\main.py", line 66, in app()

File "C:\xxxxx\Proyectos\GPTe\GPTe\gpt_engineer\main.py", line 61, in main messages = step(ai, dbs)

File "C:\xxxxxl\Proyectos\GPTe\GPTe\gpt_engineer\myenv\lib\site-packages\gpt_engineer\steps.py", line 30, in clarify messages = [ai.fsystem(dbs.identity["qa"])]

File "C:\xxxxx\Proyectos\GPTe\GPTe\gpt_engineer\myenv\lib\site-packages\gpt_engineer\db.py", line 18, in getitem raise KeyError(key)

KeyError: 'qa'

When I used $env:OPENAI_API_KEY="KEYGOESHERE" on Windows and placing the key in where I put "KEYGOESHERE", it works for me. however, you are getting that error because you do not have GPT-4 API access yet. Sign up for the waiting list. You may want to change the model to 3.5 in the code, and then try too.

[ligarius]

using $env:OPENAI_API_KEY="" on Windows INFO:openai:error_code=model_not_found error_message="The model 'gpt-4' does not exist" error_param=model error_type=invalid_request_error message='OpenAI API error received' stream_error=False Model gpt-4 not available for provided API key. Reverting to gpt-3.5-turbo. Sign up for the GPT-4 wait list here: https://openai.com/waitlist/gpt-4-api Traceback (most recent call last): File "C:\xxxxx\Proyectos\GPTe\GPTe\gpt_engineer\main.py", line 66, in app() File "C:\xxxxx\Proyectos\GPTe\GPTe\gpt_engineer\main.py", line 61, in main messages = step(ai, dbs) File "C:\xxxxxl\Proyectos\GPTe\GPTe\gpt_engineer\myenv\lib\site-packages\gpt_engineer\steps.py", line 30, in clarify messages = [ai.fsystem(dbs.identity["qa"])] File "C:\xxxxx\Proyectos\GPTe\GPTe\gpt_engineer\myenv\lib\site-packages\gpt_engineer\db.py", line 18, in getitem raise KeyError(key) KeyError: 'qa'

When I used $env:OPENAI_API_KEY="KEYGOESHERE" on Windows and placing the key in where I put "KEYGOESHERE", it works for me. however, you are getting that error because you do not have GPT-4 API access yet. Sign up for the waiting list. You may want to change the model to 3.5 in the code, and then try too.

Hi

I have GPT4 membershitp

[Unessc0]

if set doesn't work on windows just delete spaces before and after '='

[MeMyselfAndAI2023]

try to use set instead of export

I have used set as well. It is not working...

Does not work

[MeMyselfAndAI2023]

if set doesn't work on windows just delete spaces before and after '='

Does not work either

[1nspir3d]

win search -> Edit the system environment variables -> Environment Variables... -> New...

[MeMyselfAndAI2023]

win search -> Edit the system environment variables -> Environment Variables... -> New...

I tried this a while ago, but even this didn‘t work for me. Did it do the job for you, after you set the api-key as an environment variable?

[1nspir3d]

win search -> Edit the system environment variables -> Environment Variables... -> New...

I tried this a while ago, but even this didn‘t work for me. Did it do the job for you, after you set the api-key as an environment variable?

while it did a job with making it visible for the gpt-engineer I have another problem now.

when I have a prompt file w/o extension command fails with openai.error.RateLimitError: You exceeded your current quota, please check your plan and billing details.

however when I have prompt.txt filled in with my prompt it fails with AssertionError: Please put your prompt in the file 'prompt' in the project directory

[AntonOsika]

Info about this in readme now

[icemusike]

$env:OPENAI_API_KEY= "sk-x...."

This is the only solution that worked! Thanks!