Fix the supported python version in README.md and set it to 3.9, also add some classifiers.

Reviewed-on: #2

README.md

@@ -4,9 +4,11 @@ ChatMastermind is a Python application that automates conversation with AI, stor
 
 The project uses the OpenAI API to generate responses and stores the data in YAML files. It also allows you to filter chat history based on tags and supports autocompletion for tags.
 
+Official repository URL: https://kaizenkodo.no/gitea/kaizenkodo/ChatMastermind.git
+
 ## Requirements
 
-- Python 3.6 or higher
+- Python 3.9 or higher
 - openai
 - PyYAML
 - argcomplete
@@ -113,6 +115,45 @@ eval "$(register-python-argcomplete cmm)"
 
 After adding this line, restart your shell or run `source <your-shell-config-file>` to enable autocompletion for the `cmm` script.
 
+## Contributing
+
+### Enable commit hooks
+```
+pip install pre-commit
+pre-commit install
+```
+### Execute tests before opening a PR
+```
+pytest
+```
+### Consider using `pyenv` / `pyenv-virtualenv`
+Short installation instructions:
+* install `pyenv`:
+```
+cd ~
+git clone https://github.com/pyenv/pyenv .pyenv
+cd ~/.pyenv && src/configure && make -C src
+```
+* make sure that `~/.pyenv/shims` and `~/.pyenv/bin` are the first entries in your `PATH`, e. g. by setting it in `~/.bashrc`
+* add the following to your `~/.bashrc` (after setting `PATH`): `eval "$(pyenv init -)"`
+* create a new terminal or source the changes (e. g. `source ~/.bashrc`)
+* install `virtualenv`
+```
+git clone https://github.com/pyenv/pyenv-virtualenv.git $(pyenv root)/plugins/pyenv-virtualenv
+```
+* add the following to your `~/.bashrc` (after the commands above): `eval "$(pyenv virtualenv-init -)`
+* create a new terminal or source the changes (e. g. `source ~/.bashrc`)
+* go back to the `ChatMasterMind` repo and create a virtual environment with the latest `Python`, e. g. `3.11.4`:
+```
+cd <CMM_REPO_PATH>
+pyenv install 3.11.4
+pyenv virtualenv 3.11.4 py311
+pyenv activate py311
+```
+* see also the [official pyenv documentation](https://github.com/pyenv/pyenv#readme)
+
 ## License
 
 This project is licensed under the terms of the WTFPL License.
+
+

chatmastermind/api_client.py

@@ -5,6 +5,17 @@ def openai_api_key(api_key: str) -> None:
     openai.api_key = api_key
 
 
+def display_models() -> None:
+    not_ready = []
+    for engine in sorted(openai.Engine.list()['data'], key=lambda x: x['id']):
+        if engine['ready']:
+            print(engine['id'])
+        else:
+            not_ready.append(engine['id'])
+    if len(not_ready) > 0:
+        print('\nNot ready: ' + ', '.join(not_ready))
+
+
 def ai(chat: list[dict[str, str]],
        config: dict,
        number: int

chatmastermind/main.py

@@ -9,7 +9,7 @@ import argparse
 import pathlib
 from .utils import terminal_width, process_tags, display_chat, display_source_code, display_tags_frequency
 from .storage import save_answers, create_chat, get_tags, get_tags_unique, read_file, dump_data
-from .api_client import ai, openai_api_key
+from .api_client import ai, openai_api_key, display_models
 from itertools import zip_longest
 
 
@@ -61,6 +61,7 @@ def process_and_display_chat(args: argparse.Namespace,
     display_chat(chat, dump, args.only_source_code)
     return chat, full_question, tags
 
+
 def process_and_display_tags(args: argparse.Namespace,
                              config: dict,
                              dump: bool = False
@@ -96,6 +97,7 @@ def create_parser() -> argparse.ArgumentParser:
     group.add_argument('-D', '--chat-dump', help="Print chat history as Python structure", action='store_true')
     group.add_argument('-d', '--chat', help="Print chat history as readable text", action='store_true')
     group.add_argument('-l', '--list-tags', help="List all tags and their frequency", action='store_true')
+    group.add_argument('-L', '--list-models', help="List all available models", action='store_true')
     parser.add_argument('-c', '--config', help='Config file name.', default=default_config)
     parser.add_argument('-m', '--max-tokens', help='Max tokens to use', type=int)
     parser.add_argument('-T', '--temperature', help='Temperature to use', type=float)
@@ -104,8 +106,12 @@ def create_parser() -> argparse.ArgumentParser:
     parser.add_argument('-s', '--source', nargs='*', help='Source add content of a file to the query')
     parser.add_argument('-S', '--only-source-code', help='Print only source code', action='store_true')
     parser.add_argument('-w', '--with-tags', help="Print chat history with tags.", action='store_true')
-    parser.add_argument('-W', '--with-file', help="Print chat history with filename.", action='store_true')
+    parser.add_argument('-W', '--with-file',
-    parser.add_argument('-a', '--match-all-tags', help="All given tags must match when selecting chat history entries.", action='store_true')
+                        help="Print chat history with filename.",
+                        action='store_true')
+    parser.add_argument('-a', '--match-all-tags',
+                        help="All given tags must match when selecting chat history entries.",
+                        action='store_true')
     tags_arg = parser.add_argument('-t', '--tags', nargs='*', help='List of tag names', metavar='TAGS')
     tags_arg.completer = tags_completer  # type: ignore
     extags_arg = parser.add_argument('-e', '--extags', nargs='*', help='List of tag names to exclude', metavar='EXTAGS')
@@ -144,6 +150,8 @@ def main() -> int:
         process_and_display_chat(args, config)
     elif args.list_tags:
         process_and_display_tags(args, config)
+    elif args.list_models:
+        display_models()
 
     return 0
 

chatmastermind/storage.py

@@ -5,23 +5,26 @@ from .utils import terminal_width, append_message, message_to_chat
 from typing import List, Dict, Any, Optional
 
 
-def read_file(fname: str, tags_only: bool = False) -> Dict[str, Any]:
+def read_file(fname: pathlib.Path, tags_only: bool = False) -> Dict[str, Any]:
     with open(fname, "r") as fd:
+        tagline = fd.readline().strip().split(':', maxsplit=1)[1].strip()
+        # also support tags separated by ',' (old format)
+        separator = ',' if ',' in tagline else ' '
+        tags = [t.strip() for t in tagline.split(separator)]
         if tags_only:
-            return {"tags": [x.strip() for x in fd.readline().strip().split(':')[1].strip().split(',')]}
+            return {"tags": tags}
         text = fd.read().strip().split('\n')
-        tags = [x.strip() for x in text.pop(0).split(':')[1].strip().split(',')]
         question_idx = text.index("=== QUESTION ===") + 1
         answer_idx = text.index("==== ANSWER ====")
         question = "\n".join(text[question_idx:answer_idx]).strip()
         answer = "\n".join(text[answer_idx + 1:]).strip()
         return {"question": question, "answer": answer, "tags": tags,
-                "file": pathlib.Path(fname).name}
+                "file": fname.name}
 
 
 def dump_data(data: Dict[str, Any]) -> str:
     with io.StringIO() as fd:
-        fd.write(f'TAGS: {", ".join(data["tags"])}\n')
+        fd.write(f'TAGS: {" ".join(data["tags"])}\n')
         fd.write(f'=== QUESTION ===\n{data["question"]}\n')
         fd.write(f'==== ANSWER ====\n{data["answer"]}\n')
         return fd.getvalue()
@@ -29,7 +32,7 @@ def dump_data(data: Dict[str, Any]) -> str:
 
 def write_file(fname: str, data: Dict[str, Any]) -> None:
     with open(fname, "w") as fd:
-        fd.write(f'TAGS: {", ".join(data["tags"])}\n')
+        fd.write(f'TAGS: {" ".join(data["tags"])}\n')
         fd.write(f'=== QUESTION ===\n{data["question"]}\n')
         fd.write(f'==== ANSWER ====\n{data["answer"]}\n')
 
@@ -74,6 +77,7 @@ def create_chat(question: Optional[str],
         if file.suffix == '.yaml':
             with open(file, 'r') as f:
                 data = yaml.load(f, Loader=yaml.FullLoader)
+                data['file'] = file.name
         elif file.suffix == '.txt':
             data = read_file(file)
         else:
@@ -111,5 +115,6 @@ def get_tags(config: Dict[str, Any], prefix: Optional[str]) -> List[str]:
                 result.append(tag)
     return result
 
+
 def get_tags_unique(config: Dict[str, Any], prefix: Optional[str]) -> List[str]:
     return list(set(get_tags(config, prefix)))

chatmastermind/utils.py

@@ -15,11 +15,11 @@ def process_tags(tags: list[str], extags: list[str], otags: list[str]) -> None:
     printed_messages = []
 
     if tags:
-        printed_messages.append(f"Tags: {', '.join(tags)}")
+        printed_messages.append(f"Tags: {' '.join(tags)}")
     if extags:
-        printed_messages.append(f"Excluding tags: {', '.join(extags)}")
+        printed_messages.append(f"Excluding tags: {' '.join(extags)}")
     if otags:
-        printed_messages.append(f"Output tags: {', '.join(otags)}")
+        printed_messages.append(f"Output tags: {' '.join(otags)}")
 
     if printed_messages:
         print("\n".join(printed_messages))
@@ -41,7 +41,7 @@ def message_to_chat(message: Dict[str, str],
     append_message(chat, 'user', message['question'])
     append_message(chat, 'assistant', message['answer'])
     if with_tags:
-        tags = ", ".join(message['tags'])
+        tags = " ".join(message['tags'])
         append_message(chat, 'tags', tags)
     if with_file:
         append_message(chat, 'file', message['file'])
@@ -74,9 +74,10 @@ def display_chat(chat, dump=False, source_code=False) -> None:
         else:
             print(f"{message['role'].upper()}: {message['content']}")
 
+
 def display_tags_frequency(tags: List[str], dump=False) -> None:
     if dump:
         pp(tags)
         return
-    for tag in set(tags):
+    for tag in sorted(set(tags)):
         print(f"- {tag}: {tags.count(tag)}")

setup.py

@@ -15,12 +15,18 @@ setup(
     packages=find_packages(),
     classifiers=[
         "Development Status :: 3 - Alpha",
+        "Environment :: Console",
         "Intended Audience :: Developers",
-        "License :: OSI Approved :: MIT License",
+        "Intended Audience :: End Users/Desktop",
+        "Intended Audience :: Science/Research",
         "Operating System :: OS Independent",
         "Programming Language :: Python :: 3",
+        "Programming Language :: Python :: 3.9",
         "Programming Language :: Python :: 3.10",
         "Programming Language :: Python :: 3.11",
+        "Programming Language :: Python :: 3.12",
+        "Topic :: Utilities",
+        "Topic :: Text Processing",
     ],
     install_requires=[
         "openai",
@@ -28,7 +34,7 @@ setup(
         "argcomplete",
         "pytest"
     ],
-    python_requires=">=3.10",
+    python_requires=">=3.9",
     test_suite="tests",
     entry_points={
         "console_scripts": [

tests/test_main.py

@@ -21,9 +21,11 @@ class TestCreateChat(unittest.TestCase):
         self.tags = ['test_tag']
 
     @patch('os.listdir')
+    @patch('pathlib.Path.iterdir')
     @patch('builtins.open')
-    def test_create_chat_with_tags(self, open_mock, listdir_mock):
+    def test_create_chat_with_tags(self, open_mock, iterdir_mock, listdir_mock):
         listdir_mock.return_value = ['testfile.txt']
+        iterdir_mock.return_value = [pathlib.Path(x) for x in listdir_mock.return_value]
         open_mock.return_value.__enter__.return_value = io.StringIO(dump_data(
             {'question': 'test_content', 'answer': 'some answer',
              'tags': ['test_tag']}))
@@ -41,9 +43,11 @@ class TestCreateChat(unittest.TestCase):
                          {'role': 'user', 'content': self.question})
 
     @patch('os.listdir')
+    @patch('pathlib.Path.iterdir')
     @patch('builtins.open')
-    def test_create_chat_with_other_tags(self, open_mock, listdir_mock):
+    def test_create_chat_with_other_tags(self, open_mock, iterdir_mock, listdir_mock):
         listdir_mock.return_value = ['testfile.txt']
+        iterdir_mock.return_value = [pathlib.Path(x) for x in listdir_mock.return_value]
         open_mock.return_value.__enter__.return_value = io.StringIO(dump_data(
             {'question': 'test_content', 'answer': 'some answer',
              'tags': ['other_tag']}))
@@ -57,9 +61,11 @@ class TestCreateChat(unittest.TestCase):
                          {'role': 'user', 'content': self.question})
 
     @patch('os.listdir')
+    @patch('pathlib.Path.iterdir')
     @patch('builtins.open')
-    def test_create_chat_without_tags(self, open_mock, listdir_mock):
+    def test_create_chat_without_tags(self, open_mock, iterdir_mock, listdir_mock):
         listdir_mock.return_value = ['testfile.txt', 'testfile2.txt']
+        iterdir_mock.return_value = [pathlib.Path(x) for x in listdir_mock.return_value]
         open_mock.side_effect = (
             io.StringIO(dump_data({'question': 'test_content',
                                    'answer': 'some answer',
@@ -95,7 +101,10 @@ class TestHandleQuestion(unittest.TestCase):
             question=[self.question],
             source=None,
             only_source_code=False,
-            number=3
+            number=3,
+            match_all_tags=False,
+            with_tags=False,
+            with_file=False,
         )
         self.config = {
             'db': 'test_files',
@@ -119,7 +128,8 @@ class TestHandleQuestion(unittest.TestCase):
             mock_create_chat.assert_called_once_with(self.question,
                                                      self.args.tags,
                                                      self.args.extags,
-                                                     self.config)
+                                                     self.config,
+                                                     False, False, False)
             mock_pp.assert_called_once_with("test_chat")
             mock_ai.assert_called_with("test_chat",
                                        self.config,
@@ -203,7 +213,7 @@ class TestCreateParser(unittest.TestCase):
             mock_add_mutually_exclusive_group.assert_called_once_with(required=True)
             mock_group.add_argument.assert_any_call('-p', '--print', help='File to print')
             mock_group.add_argument.assert_any_call('-q', '--question', nargs='*', help='Question to ask')
-            mock_group.add_argument.assert_any_call('-D', '--chat-dump', help="Print chat as Python structure", action='store_true')
+            mock_group.add_argument.assert_any_call('-D', '--chat-dump', help="Print chat history as Python structure", action='store_true')
-            mock_group.add_argument.assert_any_call('-d', '--chat', help="Print chat as readable text", action='store_true')
+            mock_group.add_argument.assert_any_call('-d', '--chat', help="Print chat history as readable text", action='store_true')
             self.assertTrue('.config.yaml' in parser.get_default('config'))
             self.assertEqual(parser.get_default('number'), 1)