OpenAI command-line client
==========================
Installation
------------
To install OpenAI CLI in Python virtual environment, run::
pip install openai-cli
Token authentication
--------------------
OpenAI API requires authentication token, which can be obtained on this page:
https://beta.openai.com/account/api-keys
Provide token to the CLI either through a command-line argument (``-t/--token <TOKEN>``)
or through an environment variable (``OPENAI_API_KEY``).
Usage
-----
Currently only text completion API is supported.
Example usage::
$ echo "Are cats faster than dogs?" | openai complete -
It depends on the breed of the cat and dog. Generally,
cats are faster than dogs over short distances,
but dogs are better at sustained running.
Interactive mode supported (Press Ctrl+C to exit)::
$ openai repl
Prompt: Can generative AI replace humans?
No, generative AI cannot replace humans.
While generative AI can be used to automate certain tasks,
it cannot replace the creativity, intuition, and problem-solving
skills that humans possess.
Generative AI can be used to supplement human efforts,
but it cannot replace them.
Prompt: ^C
Run without arguments to get a short help message::
$ openai
Usage: openai [OPTIONS] COMMAND [ARGS]...
Options:
--help Show this message and exit.
Commands:
complete Return OpenAI completion for a prompt from SOURCE.
repl Start interactive shell session for OpenAI completion API.
Build a standalone binary using pex and move it into PATH::
$ make openai && mv openai ~/bin/
$ openai repl
Prompt:
Alternative API URL
-------------------
CLI invokes https://api.openai.com/v1/completions by default.
To override the endpoint URL, set ``OPENAI_API_URL`` environment variable.
Example usage
-------------
Here's an example usage scenario, where we first create a Python module
with a Fibonacci function implementation, and then generate a unit test for it:
.. code:: bash
$ mkdir examples
$ touch examples/__init__.py
$ echo "Write Python function to calculate Fibonacci numbers" | openai complete - | black - > examples/fib.py
$ (echo 'Write unit tests for this Python module named "fib":\n'; cat examples/fib.py) | openai complete - | black - > examples/test_fib.py
$ pytest -v examples/test_fib.py
============================== test session starts ==============================
examples/test_fib.py::TestFibonacci::test_eighth_fibonacci_number PASSED [ 10%]
examples/test_fib.py::TestFibonacci::test_fifth_fibonacci_number PASSED [ 20%]
examples/test_fib.py::TestFibonacci::test_first_fibonacci_number PASSED [ 30%]
examples/test_fib.py::TestFibonacci::test_fourth_fibonacci_number PASSED [ 40%]
examples/test_fib.py::TestFibonacci::test_negative_input PASSED [ 50%]
examples/test_fib.py::TestFibonacci::test_ninth_fibonacci_number PASSED [ 60%]
examples/test_fib.py::TestFibonacci::test_second_fibonacci_number PASSED [ 70%]
examples/test_fib.py::TestFibonacci::test_seventh_fibonacci_number PASSED [ 80%]
examples/test_fib.py::TestFibonacci::test_sixth_fibonacci_number PASSED [ 90%]
examples/test_fib.py::TestFibonacci::test_third_fibonacci_number PASSED [100%]
=============================== 10 passed in 0.02s ==============================
$ cat examples/fib.py
.. code:: python
def Fibonacci(n):
if n < 0:
print("Incorrect input")
# First Fibonacci number is 0
elif n == 1:
return 0
# Second Fibonacci number is 1
elif n == 2:
return 1
else:
return Fibonacci(n - 1) + Fibonacci(n - 2)
.. code:: bash
$ cat examples/test_fib.py
.. code:: python
import unittest
from .fib import Fibonacci
class TestFibonacci(unittest.TestCase):
def test_negative_input(self):
self.assertEqual(Fibonacci(-1), None)
def test_first_fibonacci_number(self):
self.assertEqual(Fibonacci(1), 0)
def test_second_fibonacci_number(self):
self.assertEqual(Fibonacci(2), 1)
def test_third_fibonacci_number(self):
self.assertEqual(Fibonacci(3), 1)
def test_fourth_fibonacci_number(self):
self.assertEqual(Fibonacci(4), 2)
def test_fifth_fibonacci_number(self):
self.assertEqual(Fibonacci(5), 3)
def test_sixth_fibonacci_number(self):
self.assertEqual(Fibonacci(6), 5)
def test_seventh_fibonacci_number(self):
self.assertEqual(Fibonacci(7), 8)
def test_eighth_fibonacci_number(self):
self.assertEqual(Fibonacci(8), 13)
def test_ninth_fibonacci_number(self):
self.assertEqual(Fibonacci(9), 21)
if __name__ == "__main__":
unittest.main()
.. code:: bash
$ (echo "Add type annotations for this Python code"; cat examples/fib.py) | openai complete - | black - | tee tmp && mv tmp examples/fib.py
.. code:: python
def Fibonacci(n: int) -> int:
if n < 0:
print("Incorrect input")
# First Fibonacci number is 0
elif n == 1:
return 0
# Second Fibonacci number is 1
elif n == 2:
return 1
else:
return Fibonacci(n - 1) + Fibonacci(n - 2)
.. code:: bash
$ mypy examples/fib.py
examples/fib.py:1: error: Missing return statement [return]
Found 1 error in 1 file (checked 1 source file)
.. code:: bash
$ (echo "Fix mypy warnings in this Python code"; cat examples/fib.py; mypy examples/fib.py) | openai complete - | black - | tee tmp && mv tmp examples/fib.py
.. code:: python
def Fibonacci(n: int) -> int:
if n < 0:
print("Incorrect input")
# First Fibonacci number is 0
elif n == 1:
return 0
# Second Fibonacci number is 1
elif n == 2:
return 1
else:
return Fibonacci(n - 1) + Fibonacci(n - 2)
return None # Added return statement
.. code:: bash
$ mypy examples/fib.py
examples/fib.py:12: error: Incompatible return value type (got "None", expected "int") [return-value]
Found 1 error in 1 file (checked 1 source file)
.. code:: bash
$ (echo "Fix mypy warnings in this Python code"; cat examples/fib.py; mypy examples/fib.py) | openai complete - | black - | tee tmp && mv tmp examples/fib.py
.. code:: python
def Fibonacci(n: int) -> int:
if n < 0:
print("Incorrect input")
# First Fibonacci number is 0
elif n == 1:
return 0
# Second Fibonacci number is 1
elif n == 2:
return 1
else:
return Fibonacci(n - 1) + Fibonacci(n - 2)
return 0 # Changed return statement to return 0
.. code:: bash
$ mypy examples/fib.py
Success: no issues found in 1 source file
.. code:: bash
$ (echo "Rewrite these tests to use pytest.parametrized"; cat examples/test_fib.py) | openai complete - | black - | tee tmp && mv tmp examples/test_fib.py
.. code:: python
import pytest
from .fib import Fibonacci
@pytest.mark.parametrize(
"n, expected",
[(1, 0), (2, 1), (3, 1), (4, 2), (5, 3), (6, 5), (7, 8), (8, 13), (9, 21), (10, 34)],
)
def test_fibonacci(n, expected):
assert Fibonacci(n) == expected
Raw data
{
"_id": null,
"home_page": "https://github.com/peterdemin/openai-cli",
"name": "openai-cli",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.12",
"maintainer_email": null,
"keywords": null,
"author": "Peter Demin",
"author_email": "peterdemin@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/42/2f/d3562cea333d46dc147dee2b93eb41e04f60885d97340f6a63a7677b5e7d/openai_cli-1.0.1.tar.gz",
"platform": null,
"description": "OpenAI command-line client\n==========================\n\nInstallation\n------------\n\nTo install OpenAI CLI in Python virtual environment, run::\n\n pip install openai-cli\n\nToken authentication\n--------------------\n\nOpenAI API requires authentication token, which can be obtained on this page:\nhttps://beta.openai.com/account/api-keys\n\nProvide token to the CLI either through a command-line argument (``-t/--token <TOKEN>``)\nor through an environment variable (``OPENAI_API_KEY``).\n\nUsage\n-----\n\nCurrently only text completion API is supported.\n\nExample usage::\n\n $ echo \"Are cats faster than dogs?\" | openai complete -\n It depends on the breed of the cat and dog. Generally,\n cats are faster than dogs over short distances,\n but dogs are better at sustained running.\n\nInteractive mode supported (Press Ctrl+C to exit)::\n\n $ openai repl\n Prompt: Can generative AI replace humans?\n\n No, generative AI cannot replace humans.\n While generative AI can be used to automate certain tasks,\n it cannot replace the creativity, intuition, and problem-solving\n skills that humans possess.\n Generative AI can be used to supplement human efforts,\n but it cannot replace them.\n\n Prompt: ^C\n\nRun without arguments to get a short help message::\n\n $ openai\n Usage: openai [OPTIONS] COMMAND [ARGS]...\n\n Options:\n --help Show this message and exit.\n\n Commands:\n complete Return OpenAI completion for a prompt from SOURCE.\n repl Start interactive shell session for OpenAI completion API.\n\nBuild a standalone binary using pex and move it into PATH::\n\n $ make openai && mv openai ~/bin/\n $ openai repl\n Prompt:\n\nAlternative API URL\n-------------------\n\nCLI invokes https://api.openai.com/v1/completions by default.\nTo override the endpoint URL, set ``OPENAI_API_URL`` environment variable.\n\nExample usage\n-------------\n\nHere's an example usage scenario, where we first create a Python module\nwith a Fibonacci function implementation, and then generate a unit test for it:\n\n.. code:: bash\n\n $ mkdir examples\n $ touch examples/__init__.py\n $ echo \"Write Python function to calculate Fibonacci numbers\" | openai complete - | black - > examples/fib.py\n $ (echo 'Write unit tests for this Python module named \"fib\":\\n'; cat examples/fib.py) | openai complete - | black - > examples/test_fib.py\n $ pytest -v examples/test_fib.py\n ============================== test session starts ==============================\n\n examples/test_fib.py::TestFibonacci::test_eighth_fibonacci_number PASSED [ 10%]\n examples/test_fib.py::TestFibonacci::test_fifth_fibonacci_number PASSED [ 20%]\n examples/test_fib.py::TestFibonacci::test_first_fibonacci_number PASSED [ 30%]\n examples/test_fib.py::TestFibonacci::test_fourth_fibonacci_number PASSED [ 40%]\n examples/test_fib.py::TestFibonacci::test_negative_input PASSED [ 50%]\n examples/test_fib.py::TestFibonacci::test_ninth_fibonacci_number PASSED [ 60%]\n examples/test_fib.py::TestFibonacci::test_second_fibonacci_number PASSED [ 70%]\n examples/test_fib.py::TestFibonacci::test_seventh_fibonacci_number PASSED [ 80%]\n examples/test_fib.py::TestFibonacci::test_sixth_fibonacci_number PASSED [ 90%]\n examples/test_fib.py::TestFibonacci::test_third_fibonacci_number PASSED [100%]\n\n =============================== 10 passed in 0.02s ==============================\n\n $ cat examples/fib.py\n\n.. code:: python\n\n def Fibonacci(n):\n if n < 0:\n print(\"Incorrect input\")\n # First Fibonacci number is 0\n elif n == 1:\n return 0\n # Second Fibonacci number is 1\n elif n == 2:\n return 1\n else:\n return Fibonacci(n - 1) + Fibonacci(n - 2)\n\n.. code:: bash\n\n $ cat examples/test_fib.py\n\n.. code:: python\n\n import unittest\n from .fib import Fibonacci\n\n\n class TestFibonacci(unittest.TestCase):\n def test_negative_input(self):\n self.assertEqual(Fibonacci(-1), None)\n\n def test_first_fibonacci_number(self):\n self.assertEqual(Fibonacci(1), 0)\n\n def test_second_fibonacci_number(self):\n self.assertEqual(Fibonacci(2), 1)\n\n def test_third_fibonacci_number(self):\n self.assertEqual(Fibonacci(3), 1)\n\n def test_fourth_fibonacci_number(self):\n self.assertEqual(Fibonacci(4), 2)\n\n def test_fifth_fibonacci_number(self):\n self.assertEqual(Fibonacci(5), 3)\n\n def test_sixth_fibonacci_number(self):\n self.assertEqual(Fibonacci(6), 5)\n\n def test_seventh_fibonacci_number(self):\n self.assertEqual(Fibonacci(7), 8)\n\n def test_eighth_fibonacci_number(self):\n self.assertEqual(Fibonacci(8), 13)\n\n def test_ninth_fibonacci_number(self):\n self.assertEqual(Fibonacci(9), 21)\n\n\n if __name__ == \"__main__\":\n unittest.main()\n\n.. code:: bash\n\n $ (echo \"Add type annotations for this Python code\"; cat examples/fib.py) | openai complete - | black - | tee tmp && mv tmp examples/fib.py\n\n.. code:: python\n\n def Fibonacci(n: int) -> int:\n if n < 0:\n print(\"Incorrect input\")\n # First Fibonacci number is 0\n elif n == 1:\n return 0\n # Second Fibonacci number is 1\n elif n == 2:\n return 1\n else:\n return Fibonacci(n - 1) + Fibonacci(n - 2)\n\n.. code:: bash\n\n $ mypy examples/fib.py\n examples/fib.py:1: error: Missing return statement [return]\n Found 1 error in 1 file (checked 1 source file)\n\n.. code:: bash\n\n $ (echo \"Fix mypy warnings in this Python code\"; cat examples/fib.py; mypy examples/fib.py) | openai complete - | black - | tee tmp && mv tmp examples/fib.py\n\n.. code:: python\n\n def Fibonacci(n: int) -> int:\n if n < 0:\n print(\"Incorrect input\")\n # First Fibonacci number is 0\n elif n == 1:\n return 0\n # Second Fibonacci number is 1\n elif n == 2:\n return 1\n else:\n return Fibonacci(n - 1) + Fibonacci(n - 2)\n return None # Added return statement\n\n.. code:: bash\n\n $ mypy examples/fib.py\n examples/fib.py:12: error: Incompatible return value type (got \"None\", expected \"int\") [return-value]\n Found 1 error in 1 file (checked 1 source file)\n\n.. code:: bash\n\n $ (echo \"Fix mypy warnings in this Python code\"; cat examples/fib.py; mypy examples/fib.py) | openai complete - | black - | tee tmp && mv tmp examples/fib.py\n\n.. code:: python\n\n def Fibonacci(n: int) -> int:\n if n < 0:\n print(\"Incorrect input\")\n # First Fibonacci number is 0\n elif n == 1:\n return 0\n # Second Fibonacci number is 1\n elif n == 2:\n return 1\n else:\n return Fibonacci(n - 1) + Fibonacci(n - 2)\n return 0 # Changed return statement to return 0\n\n.. code:: bash\n\n $ mypy examples/fib.py\n Success: no issues found in 1 source file\n\n.. code:: bash\n\n $ (echo \"Rewrite these tests to use pytest.parametrized\"; cat examples/test_fib.py) | openai complete - | black - | tee tmp && mv tmp examples/test_fib.py\n\n.. code:: python\n\n import pytest\n from .fib import Fibonacci\n\n\n @pytest.mark.parametrize(\n \"n, expected\",\n [(1, 0), (2, 1), (3, 1), (4, 2), (5, 3), (6, 5), (7, 8), (8, 13), (9, 21), (10, 34)],\n )\n def test_fibonacci(n, expected):\n assert Fibonacci(n) == expected\n",
"bugtrack_url": null,
"license": null,
"summary": "Command-line client for OpenAI API",
"version": "1.0.1",
"project_urls": {
"Homepage": "https://github.com/peterdemin/openai-cli"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "0e1dfcf004db72d7f5554b1a847e46d56bd80336bbd534d92e6b9571c5684f02",
"md5": "46acab1f925f8205656e827568787e33",
"sha256": "9708c1e61c8b042e5607e6af1e6dc97b026cff6bb925ca8bd8547d6872f0ee62"
},
"downloads": -1,
"filename": "openai_cli-1.0.1-py2.py3-none-any.whl",
"has_sig": false,
"md5_digest": "46acab1f925f8205656e827568787e33",
"packagetype": "bdist_wheel",
"python_version": "py2.py3",
"requires_python": ">=3.12",
"size": 9853,
"upload_time": "2025-02-12T04:17:17",
"upload_time_iso_8601": "2025-02-12T04:17:17.785513Z",
"url": "https://files.pythonhosted.org/packages/0e/1d/fcf004db72d7f5554b1a847e46d56bd80336bbd534d92e6b9571c5684f02/openai_cli-1.0.1-py2.py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "422fd3562cea333d46dc147dee2b93eb41e04f60885d97340f6a63a7677b5e7d",
"md5": "ea9f2ad67c4ae0c68370521ee3b4b881",
"sha256": "fc68a39952ceb04a43ecc27b9d43f848f5f537da57ac30bd941d084f805c10a4"
},
"downloads": -1,
"filename": "openai_cli-1.0.1.tar.gz",
"has_sig": false,
"md5_digest": "ea9f2ad67c4ae0c68370521ee3b4b881",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.12",
"size": 16854,
"upload_time": "2025-02-12T04:17:30",
"upload_time_iso_8601": "2025-02-12T04:17:30.380585Z",
"url": "https://files.pythonhosted.org/packages/42/2f/d3562cea333d46dc147dee2b93eb41e04f60885d97340f6a63a7677b5e7d/openai_cli-1.0.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-02-12 04:17:30",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "peterdemin",
"github_project": "openai-cli",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"tox": true,
"lcname": "openai-cli"
}
JSON
