Merge pull request #26 from RexWzh/master

Add debug tool

Author: RexWzh

CONTRIBUTING.md

@@ -0,0 +1,120 @@
+# Contributing
+
+Contributions are welcome, and they are greatly appreciated! Every little bit helps, and credit will always be given.
+
+You can contribute in many ways:
+
+## Types of Contributions
+
+### Report Bugs
+
+Report bugs at https://github.com/cubenlp/openai_api_call/issues.
+
+If you are reporting a bug, please include:
+
+- Your operating system name and version.
+- Any details about your local setup that might be helpful in troubleshooting.
+- Detailed steps to reproduce the bug.
+
+### Fix Bugs
+
+Look through the GitHub issues for bugs. Anything tagged with "bug" and "help wanted" is open to whoever wants to implement it.
+
+### Implement Features
+
+Look through the GitHub issues for features. Anything tagged with "enhancement" and "help wanted" is open to whoever wants to implement it.
+
+### Write Documentation
+
+Openai API call could always use more documentation, whether as part of the
+official Openai API call docs, in docstrings, or even on the web in blog posts,
+articles, and such.
+
+### Submit Feedback
+
+The best way to send feedback is to file an issue at https://github.com/cubenlp/openai_api_call/issues.
+
+If you are proposing a feature:
+
+- Explain in detail how it would work.
+- Keep the scope as narrow as possible, to make it easier to implement.
+- Remember that this is a volunteer-driven project, and that contributions are welcome :)
+
+## Get Started!
+
+Ready to contribute? Here's how to set up `openai_api_call` for local development.
+
+1. Fork the `openai_api_call` repo on GitHub.
+2. Clone your fork locally:
+
+   ```shell
+   $ git clone [email protected]:your_name_here/openapi_api_call.git
+   ```
+
+3. Install your local copy into a virtualenv. Assuming you have virtualenvwrapper installed, this is how you set up your fork for local development:
+
+   ```shell
+   $ mkvirtualenv openai_api_call
+   $ cd openai_api_call/
+   $ python setup.py develop
+   ```
+
+4. Create a branch for local development:
+
+   ```shell
+   $ git checkout -b name-of-your-bugfix-or-feature
+   ```
+
+   Now you can make your changes locally.
+
+5. When you're done making changes, check that your changes pass flake8 and the tests, including testing other Python versions with tox:
+
+   ```shell
+   $ flake8 openai_api_call tests 
+   $ python setup.py test or pytest
+   $ tox
+   ```
+
+   To get flake8 and tox, just pip install them into your virtualenv.
+
+6. Commit your changes and push your branch to GitHub:
+
+   ```shell
+   $ git add .
+   $ git commit -m "Your detailed description of your changes."
+   $ git push origin name-of-your-bugfix-or-feature
+   ```
+
+7. Submit a pull request through the GitHub website.
+
+## Pull Request Guidelines
+
+Before you submit a pull request, check that it meets these guidelines:
+
+1. The pull request should include tests.
+2. If the pull request adds functionality, the docs should be updated. Put your new functionality into a function with a docstring, and add the feature to the list in README.rst.
+3. The pull request should work for Python 3.8 and 3.9, and for PyPy. Check https://github.com/cubenlp/openai_api_call/actions and make sure that the tests pass for all supported Python versions.
+
+## Tips
+
+To run a subset of tests:
+
+```shell
+$ pytest tests.test_openai_api_call
+```
+
+## Deploying
+
+A reminder for the maintainers on how to deploy. Make sure all your changes are committed (including an entry in HISTORY.rst). Then run:
+
+```shell
+$ bump2version patch # possible: major / minor / patch
+$ git push
+$ git push --tags
+```
+
+Travis will then deploy to PyPI if tests pass.
+
+---
+
+Thank you for reading and considering contributing to `openai_api_call`!

CONTRIBUTORS.md

@@ -0,0 +1,17 @@
+# Contributors List
+
+- Rex (Main Developer)
+  - GitHub: [Rex's GitHub Profile](https://github.com/RexWzh) 
+
+- Zhouhao (Code Tester)
+  - GitHub: [Zhouhao's GitHub Profile](https://github.com/zh-i9)
+
+- Shangqing (Code Tester)
+  - GitHub: [Shangqing's GitHub Profile](https://github.com/Qing25)
+
+- Binxuan (Code Tester)
+  - GitHub: [Binxuan's GitHub Profile](https://github.com/LuaMarke)
+
+Thank you all for your contributions! 
+
+License: MIT

README.md

@@ -155,4 +155,5 @@ This package is licensed under the MIT license. See the LICENSE file for more de
 ## update log
 
 - Since version `0.2.0`, `Chat` type is used to handle data
-- Since version `0.3.0`, you can use different API Key to send requests.
+- Since version `0.3.0`, you can use different API Key to send requests.
+- Since version `0.4.0`, this package is mantained by [cubenlp](https://github.com/cubenlp).

README_zh_CN.md

@@ -154,4 +154,5 @@ chat.show_usage_status()
 - 版本 `0.2.0` 改用 `Chat` 类型作为中心交互对象
 - 版本 `0.3.0` 开始不依赖模块 `openai.py` ，而是直接使用 `requests` 发送请求
     - 支持对每个 `Chat` 使用不同 API 密钥
-    - 支持使用代理链接
+    - 支持使用代理链接
+- 版本 `0.4.0` 开始，工具维护转至 [CubeNLP](https://github.com/cubenlp) 组织账号

openai_api_call/__init__.py

@@ -2,11 +2,14 @@
 
 __author__ = """Rex Wang"""
 __email__ = '[email protected]'
-__version__ = '0.4.0'
+__version__ = '0.4.1'
 
 import os
 from .chattool import Chat, Resp, chat_completion, usage_status
 from .proxy import proxy_on, proxy_off, proxy_status
+import requests
+from . import request
+
 
 # read API key from the environment variable
 if os.environ.get('OPENAI_API_KEY') is not None:
@@ -33,3 +36,50 @@ def default_prompt(msg:str):
         List[Dict]: default prompt message
     """
     return [{"role": "user", "content": msg},]
+
+def show_base_url():
+    """Show the base url of the API call"""
+    print(f"Base url:\t{request.base_url}")
+
+def debug_log( net_url:str="https://www.baidu.com"
+             , timeout:int=5
+             , test_usage:bool=True
+             , test_response:bool=True):
+    # 1. Test whether the network is available
+    try:
+        requests.get(net_url, timeout=timeout)
+    except:
+        print("Warning: Network is not available.")
+        return False
+    
+    print("Your network is available.")
+    
+    # 2. Check the API key
+    print("\nPlease verify the API key:")
+    show_apikey()
+
+    # 3. Check the proxy status
+    print("\nYour proxy status:")
+    proxy_status()
+    print("Note that, you don't need to set proxy if your `base_url` has done it!")
+
+    # 4. Base url
+    print("\nCheck your base url:")
+    show_base_url()
+    if request.url is not None:
+        print("Warning: the `url` parameter is deprecated, please use `base_url` instead.")
+
+    # 5. Get usage status
+    if test_usage:
+        print("\nThe usage status of your API key:")
+        Chat().show_usage_status(recent=3)
+
+    # 6. Test hello world
+    if test_response:
+        print("\nTest hello world:")
+        chat = Chat("hello world")
+        chat.getresponse(max_requests=3)
+        chat.print_log()
+
+    print("\nDebug is finished.")
+    return True

openai_api_call/chattool.py

@@ -192,7 +192,7 @@ def save(self, path:str, mode:str='a', end:str='\n'):
         assert mode in ['a', 'w'], "mode should be 'a' or 'w'"
         data = self.chat_log
         with open(path, mode, encoding='utf-8') as f:
-            f.write(json.dumps(data) + end)
+            f.write(json.dumps(data, ensure_ascii=False) + end)
         return True
 
     def print_log(self, sep: Union[str, None]=None):

openai_api_call/request.py

@@ -81,7 +81,7 @@ def chat_completion(api_key:str, messages:List[Dict], model:str, **options) -> D
 
     chat_url = normalize_url(chat_url)
     # get response
-    response = requests.post(chat_url, headers=headers, data=json.dumps(payload))
+    response = requests.post(chat_url, headers=headers, data=json.dumps(payload, ensure_ascii=False))
     if response.status_code != 200:
         raise Exception(response.text)
     return response.json()

setup.py

@@ -7,7 +7,7 @@
 with open('README.md') as readme_file:
     readme = readme_file.read()
 
-VERSION = '0.4.0'
+VERSION = '0.4.1'
 
 requirements = ['Click>=7.0', 'requests>=2.20']
 

tests/test_openai_api_call.py

@@ -5,6 +5,7 @@
 import pytest
 from click.testing import CliRunner
 from openai_api_call import cli
+from openai_api_call import debug_log
 
 
 @pytest.fixture
@@ -32,3 +33,6 @@ def test_command_line_interface():
     help_result = runner.invoke(cli.main, ['--help'])
     assert help_result.exit_code == 0
     assert '--help  Show this message and exit.' in help_result.output
+
+def test_debug_log():
+    assert debug_log(test_response=False, test_usage=False)