by Devin Yang
(This article was automatically translated.)

Published - 3 years ago ( Updated - 3 years ago )

If you log in to the openai website, you can see the official teaching instructions here
https://beta.openai.com/docs/quickstart/build-your-application

API KEY application is on this page There is a button below

+ Create new secret key

This article teaches you to use Docker to run the official OpenAI execution environment.

official version:

git clone https://github.com/openai/openai-quickstart-python.git
cd openai-quickstart-python
cp.env.example.env
python -m venv venv
.venv/bin/activate
pip install -r requirements.txt
flask run

But if you just want to try it out during the free period, you can also use docker to quickly install it on your own MacOS.

git clone https://github.com/openai/openai-quickstart-python.git
cd openai-quickstart-python
# One more step, run Docker first
docker run --rm -v $(pwd):/app -w /app -p 5001:5000 -ti python:3.10.9 bash
#Skip the installation of venv, run the container without venv, install it directly
pip install -r requirements.txt
#The container cannot listen to 127.0.0.1, so there is one more parameter --host
flask run --host 0.0.0.0

After completion, remember to set your Token in .env, and you can use it.

FLASK_APP=app
FLASK_ENV=development
OPENAI_API_KEY=

Because the AirPlay receiver will consume 5000 and 7000, it must avoid conflicts, so I changed the Port on the host side to 5001
for use Open the screen in the browser, and you can test it. Remember that the Docker port is opened at 5001.

http://127.0.0.1:5001

If there is no problem, remember to commit as image, so you don’t have to reinstall all the time. The garbled code here is the hostname of the container, please don’t copy it My.

docker commit 520ad08c41e2 openai

Leave the container and restart with our commit image

 docker run --rm - v $(pwd):/app -w /app -p 5001:5000 -ti openai flask \
 run --host 0.0.0.0

You should see the following screen:

$docker run --rm -v $(pwd):/app -w /app -p 5001:5000 -ti openai flask\
 run --host 0.0.0.0
 * Serving Flask app 'app' (lazy loading)
 * Environment: development
 * Debug mode: on
 * Running on all addresses.
   WARNING: This is a development server. Do not use it in a production deployment.
 * Running on http://172.17.0.2:5000/ (Press CTRL+C to quit)
 * Restarting with stat
 * Debugger is active!
 * Debugger PIN: 130-035-104

Tags: openai flax docker

Devin Yang

Feel free to ask me, if you don't get it.:)

No Comment

Post your comment

Login is required to leave comments

Similar Stories


openspeedtest,docker,phpenv

Run OpenSpeedTest with phpenv

Although we may use websites such as speedtest to test the speed of uploading and uploading, what if we want to test the speed of our own Server? For example, if the user is in another country, the speed of connecting to our host is slow, then the self-hosted test tool is very convenient. The latest version of phpenv has added openspeedtest.yml to the yml file of services.

docker,laravel

It's super easy to build a Lravel development environment with Docker

Are you ready for the Laravel 5.5 system environment? laravel/framework 5.5.x-dev requires php >=7.0 -> your PHP version (5.6.30) does not satisfy that requirement. This article describes how to create a Laravel development environment using Docker. With the simple to explosive D-Laravel simple bash, Don't say that I can't set up a Laravel development environment.

docker,phpenv

Ran out of Docker IPv4 address pool problem solving

Maybe in the old version of the docker environment, when using Docker compose to start the container, you will encounter the following error: Error response from daemon: could not find an available, non-overlapping IPv4 address pool among the defaults to assign to the network This is actually this It is a symptom of running out of default-address-pools. In some environments, docker-compose will use the private network of Class B by default. The private IP of segment 172 has a range, from 172.16.0.0 to 172.31.255.255. That is to say, when we start a docker-compose Project, it will eat a private section of Class B, which is very heroic.