Unable to run the command Line interface (CLI) for openai

General API discussion
21

To be honest, I ran into different issues, running in anaconda, I couldn’t “see” openai, so I ran the pip install inside of anaconda, and had missing packages, and ran into access issues trying to install those packages…

Untitled
Untitled959×168 8.81 KB

…after which I gave up thinking, if I need to run openai tools locally, I’ll get back to this post :grin:

1 Like
23

LOL, people with vaccination passports I guess

24

I Agree, in principle.

Virtual environments get you a large way there, venv, or anaconda etc. With slightly more configuration, docker containers are also extremely powerful.
No need for an internet connection, you can just reset and move on, as you said; once you are successful, the entire container can be scalably deployed as well.

Besides, for data science work, using a cloud hosted virtual machine has an extra hassle of uploading the data sets and downloading the model to be deployed. The dataset I am currently woking on is a 12 GB txt file with over 300 million rows. It would be hard to upload it somewhere while I figure out how to slice and dice it for analysis.

25

Thanks for posting this, I had the same issue, and you led me to the (start of) the solution. I went to the Scripts folder and just had to add “Python” before “openai,” and it worked.
However, I’m still stuck at the point of adding the API key. I get an error of “[Errno 2] No such file or directory,” and nothing seems to make it work.
Any ideas?

26

Can you try passing the key directly “in the clear” rather than using the environment variable approach?
python openai --api-key sk-YOURKEYHERE --verbose

I assume that you are within the scripts folder. Set to verbose to see what comes up.
HTH.

2 Likes
27

Thanks a lot. It’s what I did before, but I get the help screen. It doesn’t seem actually to accept the key.
try

2 Likes
28

You are almost there. The rest of the arguments are not optional. Once you supply them, the command would work.

For reference, anything in [ ] is optional, anything else in { } is not. You need to use one of the tools or api arguments and proceed from there.
python openai --api-key sk-SOMETHING api answers… and so on.

2 Likes
29

Worked!
Thanks a lot, I tried to do it in two steps for hours :sweat_smile:

2 Likes
30

Glad it worked.
The commands are atomic, i.e. they do not save state between runs. So everything you do, has to be done in ONE step.

For reference, you can open up the openai file in your favorite editor (its just a .py file, without an extension) and have a look.

2 Likes
31

Add openai path to your environment variable.

navigate to an environment variable in the control panel, there you will find edit PATH in user variable.

add the path openai exe file.

1 Like
33
34

https://anaconda.org/conda-forge/openai

conda install -c conda-forge openai

works and I tried with Anaconda3-2021.05-Windows-x86_64.exe.

Description

The OpenAI Python library provides convenient access to the OpenAI API from applications written in the Python language. It includes a pre-defined set of classes for API resources that initialize themselves dynamically from API responses which makes it compatible with a wide range of versions of the OpenAI API.

This library additionally provides an openai command-line utility which makes it easy to interact with the API from your terminal. Run openai api -h for usage.

2 Likes
35

Thanks for this, I am running on Power shell, let me try this

36

Yes! Colab seems to be easy.

37

I could not do something similar to this is PowerShell.
I navigated to the path open ai is, but couldn’t run any commands from that end

1 Like
38

as mentioned in documentation, it is expecting latest version of library.
unfortunately latest version could not be installed in 2.7 / 3.5

image
image916×275 23.7 KB

installing openai in latest version of python (3.9) resolved this issue.
and you dont need to run openai under python

pip install --upgrade openai

openai api # will return you all parameters supported.

1 Like
39

Is it possible to do thoses steps in an usual command prompt?

Thanks

40

Yes. There in nothing unusual about my command prompt either!

What exactly are you struggling with?

41

Hi all,

I got a similar issue when I try to run openai in my cmd prompt. I have python 3.9 installed with Anaconda, and I did

pip install --upgrade openai

but then when I run executable like

openai api (...)

I got this error:

'openai' is not recognized as an internal or external command,
operable program or batch file.

I tried also to navigate on the folder where openai is installed, as suggested here, and then tried to run alternatives like

python openai

or

`python -m openai`

but in these cases I got these errors:

C:\ProgramData\Anaconda3\python.exe: can't find '__main__' module in 'c:\\...\\Python39\\site-packages\\openai'

or (in the second case)

C:\ProgramData\Anaconda3\python.exe: No module named openai.__main__; 'openai' is a package and cannot be directly executed

Can anyone help me understand what i’m doing wrong?

Many thanks in advance to whoever can give me a hand

42

Hi,

Just try this (trick??)
On your Anaconda Prompt, navigate to the root of your C: drive and search for openai.exe

image

For me, I get three results corresponding to the 3 environments that I have OpenAI package installed in.

Navigate to the one corresponding to your environment, and just run openai from there!

image
image962×364 8.06 KB

HTH.