gpt-pr 0.3.0__tar.gz → 0.7.2__tar.gz

gpt_pr-0.7.2/PKG-INFO

@@ -0,0 +1,285 @@
+Metadata-Version: 2.4
+Name: gpt-pr
+Version: 0.7.2
+Summary: Automate your GitHub workflow with GPT-PR: an OpenAI powered library for streamlined PR generation.
+Author: alissonperez
+Author-email: 756802+alissonperez@users.noreply.github.com
+Requires-Python: >=3.10,<4.0
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Requires-Dist: fire (>=0.7.1,<0.8.0)
+Requires-Dist: gitpython (>=3.1.45,<4.0.0)
+Requires-Dist: inquirerpy (>=0.3.4,<0.4.0)
+Requires-Dist: prompt-toolkit (>=3.0.52,<4.0.0)
+Requires-Dist: pydantic-ai (>=1.14.0,<2.0.0)
+Requires-Dist: pygithub (>=2.8.1,<3.0.0)
+Requires-Dist: requests (>=2.32.5,<3.0.0)
+Requires-Dist: tiktoken (>=0.12.0,<0.13.0)
+Description-Content-Type: text/markdown
+
+# GPT-PR
+
+GPT-PR is an open-source command-line tool designed to streamline your GitHub workflow for opening PRs. Leveraging OpenAI's ChatGPT API, it automatically opens a GitHub Pull Request with a predefined description and title directly from your current project directory.
+
+[![asciicast](https://asciinema.org/a/u0PwZlNjAGZcdXPPrjf84wj2A.svg)](https://asciinema.org/a/u0PwZlNjAGZcdXPPrjf84wj2A)
+
+## Quick Start
+
+For a more detailed explanation, see [Installation](#installation) and [Configuration](#configuration).
+
+### 1. Installation
+
+```bash
+pip install -U gpt-pr
+```
+
+If you don't have the `pip` command available, follow [these instructions](https://pip.pypa.io/en/stable/installation/) to install it on different platforms.
+
+### 2. Fill OpenAI API Key
+
+1. Go to [OpenAI API Keys](https://platform.openai.com/api-keys) and generate a new key.
+2. Run the following command to fill your key in GPT-PR (it will be stored in `~/.gpt-pr.ini`):
+
+```bash
+gpt-pr-config set openai_api_key MY-API-KEY-VALUE
+```
+
+### 3. Generate a GitHub GH Token to Open PRs
+
+1. Go to [GitHub Settings](https://github.com/settings/tokens), choose `Generate new token (classic)`, and select all permissions under `repo` (full control of private repositories).
+2. Run the following command to fill your GH token (it will also be stored in `~/.gpt-pr.ini`):
+
+```bash
+gpt-pr-config set gh_token MY-GH-TOKEN-VALUE
+```
+
+### 4. Ready to NEVER WRITE A PR AGAIN
+
+1. Make your changes, commit them, and push to origin (important!).
+2. Run the following command in your project directory:
+
+```bash
+gpt-pr
+```
+
+3. Answer the questions. At the end, you'll receive the URL of a freshly opened PR.
+
+## Contributing and Feedback
+
+We welcome your contributions and feedback to help improve GPT-PR! Here’s how you can get involved:
+
+### Open Issues
+
+- **Feature Requests**: Have an idea for a new feature? We’d love to hear it! Open an issue to request new features or enhancements.
+- **Bug Reports**: Encountered a bug? Let us know by opening an issue with detailed information so we can fix it.
+- **General Feedback**: Any other suggestions or feedback? Feel free to share your thoughts.
+
+To open an issue, go to the [Issues](https://github.com/your-repo/gpt-pr/issues) section of our GitHub repository. Your contributions are very welcome and highly appreciated!
+
+More details about it at our [CONTRIBUTING](./CONTRIBUTING.md) guide.
+
+## Table of Contents
+
+- [Features](#features)
+- [Prerequisites](#prerequisites)
+- [Installation](#installation)
+- [Configuration](#configuration)
+- [Usage](#usage)
+- [How to Contribute](#how-to-contribute)
+- [Roadmap](#roadmap)
+
+## Features
+
+- Analyzes the diff changes of the current branch against the `main` branch.
+- Provides an option to exclude certain file changes from PR generation (for instance, you can ignore a `package.lock` file with 5k lines changed).
+- Incorporates commit messages into the process.
+
+## Prerequisites
+
+Before getting started, make sure you have the following installed:
+
+- Python 3.9 or higher
+- [Poetry](https://python-poetry.org/)
+
+## Installation
+
+You can install and use GPT-PR in one of two ways. Choose the option that best suits your needs.
+
+### Option 1: Using `pip install` (Recommended)
+
+1. Install OR Update the package:
+
+```bash
+pip install -U gpt-pr
+```
+
+2. Setup API keys for GitHub and OpenAI, take a look at [Configuration](#configuration).
+
+3. Inside the Git repository you are working on, ensure you have pushed your branch to origin, then run:
+
+```bash
+gpt-pr --help
+```
+
+### Option 2: Cloning the code (NOT recommended)
+
+1. Clone the repository:
+
+```bash
+git clone https://github.com/alissonperez/gpt-pr.git
+```
+
+2. Navigate to the project directory and install dependencies:
+
+```bash
+cd gpt-pr
+poetry install
+```
+
+After setting up API keys ([Configuration](#configuration)), you can use GPT-PR within any git project directory. Suppose you've cloned **this project** to `~/workplace/gpt-pr`, here's how you can use it:
+
+```bash
+poetry run python gpt_pr/main.py --help
+```
+
+## Configuration
+
+### See all configs available
+
+To print all default configs and what is being used, just run:
+
+```bash
+gpt-pr-config print
+```
+
+### Setting up GitHub Token (`GH_TOKEN`)
+
+GPT-PR tool will look for a `GH_TOKEN` in current shell env var OR in gpt-pr config file (at `~/.gpt-pr.ini`).
+
+To authenticate with GitHub, generate and export a GitHub Personal Access Token:
+
+1. Navigate to [GitHub's Personal Access Token page](https://github.com/settings/tokens).
+2. Click "Generate new token."
+3. Provide a description and select the required permissions `repo` for the token.
+4. Click "Generate token" at the bottom of the page.
+5. Copy the generated token.
+6. Set `gh_token` config running (supposing your gh token is `ghp_4Mb1QEr9gY5e8Lk3tN1KjPzX7W9z2V4HtJ2b`):
+
+```bash
+gpt-pr-config set gh_token ghp_4Mb1QEr9gY5e8Lk3tN1KjPzX7W9z2V4HtJ2b
+```
+
+Or just export it as an environment variable in your shell initializer:
+
+```bash
+export GH_TOKEN=your_generated_token_here
+```
+
+### Setting up OpenAI API Key (`OPENAI_API_KEY`)
+
+GPT-PR tool will look for a `OPENAI_API_KEY` env var in current shell OR in gpt-pr config file (at `~/.gpt-pr.ini`).
+
+This project needs to interact with the ChatGPT API to generate the pull request description. So, you need to generate and export an OpenAI API Key:
+
+1. Navigate to [OpenAI's API Key page](https://platform.openai.com/signup).
+2. If you don't have an account, sign up and log in.
+3. Go to the API Keys section and click "Create new key."
+4. Provide a description and click "Create."
+5. Copy the generated API key.
+6. Set `openai_api_key` config running (supposing your openai_api_key is `QEr9gY5e8Lk3tN1KjPzX7W9z2V4Ht`):
+
+```bash
+gpt-pr-config set openai_api_key QEr9gY5e8Lk3tN1KjPzX7W9z2V4Ht
+```
+
+Or just export it as an environment variable in your shell initializer:
+
+```bash
+export OPENAI_API_KEY=your_generated_api_key_here
+```
+
+### Setting Max Input LLM Tokens
+
+You can adjust the maximum number of input tokens allowed when calling the LLM model by modifying the corresponding setting.
+
+For example, to change the maximum to 20,000 tokens, use the following command:
+
+```bash
+gpt-pr-config set input_max_tokens 20000
+```
+
+### Change OpenAI model
+
+To change OpenAI model, just run:
+
+```bash
+gpt-pr-config set openai_model gpt-4o-mini
+```
+
+> Obs.: `gpt-4o-mini` already is the default model of the project
+
+To see a full list of available models, access [OpenAI Models Documentation](https://platform.openai.com/docs/models)
+
+### GPT-PR Library Signature in PRs
+
+To help other developers recognize and understand the use of the GPT-PR library in generating pull requests, we have included an optional signature feature. By default, this feature is enabled and appends the text "Generated by GPT-PR" at the end of each pull request. This transparency fosters better collaboration and awareness among team members about the tools being utilized in the development process.
+
+If you prefer to disable this feature, simply run the following command:
+
+```bash
+gpt-pr-config set add_tool_signature false
+```
+
+### Reset config
+
+To reset any config to default value, just run:
+
+```bash
+gpt-pr-config reset config_name
+```
+
+Example:
+
+```bash
+gpt-pr-config reset openai_model
+```
+
+## Usage
+
+### Generating Github Pull Requests
+
+To create a Pull request from your current branch commits to merge with `main` branch, just run:
+
+```
+gpt-pr
+```
+
+If you would like to compare with other base branch that is not `main`, just use `-b` param:
+
+```
+gpt-pr -b my-other-branch
+```
+
+### Usage help
+
+To show help commands:
+
+```
+gpt-pr -h
+```
+
+Output:
+![image](https://github.com/alissonperez/gpt-pr/assets/756802/cc6c0ca4-5759-44ce-ad35-e4e7305b3875)
+
+## Roadmap
+
+- [x] Improve execution method, possibly through a shell script or at least an alias in bash rc files.
+  - Change to use with pip installation and console_scripts entry point.
+- [x] Fetch GitHub PR templates from the current project.
+- [ ] Add configuration to set which LLM and model should be used (OpenAI GPT, Mistral, etc...)
+- [ ] Add unit tests.
+

{gpt-pr-0.3.0 → gpt_pr-0.7.2}/README.md

@@ -4,6 +4,61 @@ GPT-PR is an open-source command-line tool designed to streamline your GitHub wo
 
 [![asciicast](https://asciinema.org/a/u0PwZlNjAGZcdXPPrjf84wj2A.svg)](https://asciinema.org/a/u0PwZlNjAGZcdXPPrjf84wj2A)
 
+## Quick Start
+
+For a more detailed explanation, see [Installation](#installation) and [Configuration](#configuration).
+
+### 1. Installation
+
+```bash
+pip install -U gpt-pr
+```
+
+If you don't have the `pip` command available, follow [these instructions](https://pip.pypa.io/en/stable/installation/) to install it on different platforms.
+
+### 2. Fill OpenAI API Key
+
+1. Go to [OpenAI API Keys](https://platform.openai.com/api-keys) and generate a new key.
+2. Run the following command to fill your key in GPT-PR (it will be stored in `~/.gpt-pr.ini`):
+
+```bash
+gpt-pr-config set openai_api_key MY-API-KEY-VALUE
+```
+
+### 3. Generate a GitHub GH Token to Open PRs
+
+1. Go to [GitHub Settings](https://github.com/settings/tokens), choose `Generate new token (classic)`, and select all permissions under `repo` (full control of private repositories).
+2. Run the following command to fill your GH token (it will also be stored in `~/.gpt-pr.ini`):
+
+```bash
+gpt-pr-config set gh_token MY-GH-TOKEN-VALUE
+```
+
+### 4. Ready to NEVER WRITE A PR AGAIN
+
+1. Make your changes, commit them, and push to origin (important!).
+2. Run the following command in your project directory:
+
+```bash
+gpt-pr
+```
+
+3. Answer the questions. At the end, you'll receive the URL of a freshly opened PR.
+
+## Contributing and Feedback
+
+We welcome your contributions and feedback to help improve GPT-PR! Here’s how you can get involved:
+
+### Open Issues
+
+- **Feature Requests**: Have an idea for a new feature? We’d love to hear it! Open an issue to request new features or enhancements.
+- **Bug Reports**: Encountered a bug? Let us know by opening an issue with detailed information so we can fix it.
+- **General Feedback**: Any other suggestions or feedback? Feel free to share your thoughts.
+
+To open an issue, go to the [Issues](https://github.com/your-repo/gpt-pr/issues) section of our GitHub repository. Your contributions are very welcome and highly appreciated!
+
+More details about it at our [CONTRIBUTING](./CONTRIBUTING.md) guide.
+
 ## Table of Contents
 
 - [Features](#features)
@@ -24,8 +79,8 @@ GPT-PR is an open-source command-line tool designed to streamline your GitHub wo
 
 Before getting started, make sure you have the following installed:
 
-- Python 3.7 or higher
-- [Pipenv](https://pipenv.pypa.io/en/latest/)
+- Python 3.9 or higher
+- [Poetry](https://python-poetry.org/)
 
 ## Installation
 
@@ -33,14 +88,12 @@ You can install and use GPT-PR in one of two ways. Choose the option that best s
 
 ### Option 1: Using `pip install` (Recommended)
 
-1. Install the package:
+1. Install OR Update the package:
 
 ```bash
 pip install -U gpt-pr
 ```
 
-> Note: Use this command to **update** gpt-pr package to the latest version.
-
 2. Setup API keys for GitHub and OpenAI, take a look at [Configuration](#configuration).
 
 3. Inside the Git repository you are working on, ensure you have pushed your branch to origin, then run:
@@ -49,7 +102,7 @@ pip install -U gpt-pr
 gpt-pr --help
 ```
 
-### Option 2: Cloning the code
+### Option 2: Cloning the code (NOT recommended)
 
 1. Clone the repository:
 
@@ -61,19 +114,25 @@ git clone https://github.com/alissonperez/gpt-pr.git
 
 ```bash
 cd gpt-pr
-pipenv install
+poetry install
 ```
 
 After setting up API keys ([Configuration](#configuration)), you can use GPT-PR within any git project directory. Suppose you've cloned **this project** to `~/workplace/gpt-pr`, here's how you can use it:
 
 ```bash
-PYTHONPATH=~/workplace/gpt-pr/gpt-pr \
-PIPENV_PIPFILE=~/workplace/gpt-pr/Pipfile \
-pipenv run python ~/workplace/gpt-pr/gptpr/main.py --help
+poetry run python gpt_pr/main.py --help
 ```
 
 ## Configuration
 
+### See all configs available
+
+To print all default configs and what is being used, just run:
+
+```bash
+gpt-pr-config print
+```
+
 ### Setting up GitHub Token (`GH_TOKEN`)
 
 GPT-PR tool will look for a `GH_TOKEN` in current shell env var OR in gpt-pr config file (at `~/.gpt-pr.ini`).
@@ -120,22 +179,36 @@ Or just export it as an environment variable in your shell initializer:
 export OPENAI_API_KEY=your_generated_api_key_here
 ```
 
+### Setting Max Input LLM Tokens
+
+You can adjust the maximum number of input tokens allowed when calling the LLM model by modifying the corresponding setting.
+
+For example, to change the maximum to 20,000 tokens, use the following command:
+
+```bash
+gpt-pr-config set input_max_tokens 20000
+```
+
 ### Change OpenAI model
 
 To change OpenAI model, just run:
 
 ```bash
-gpt-pr-config set openai_model gpt-3.5-turbo
+gpt-pr-config set openai_model gpt-4o-mini
 ```
 
+> Obs.: `gpt-4o-mini` already is the default model of the project
+
 To see a full list of available models, access [OpenAI Models Documentation](https://platform.openai.com/docs/models)
 
-### See all configs available
+### GPT-PR Library Signature in PRs
 
-To print all default configs and what is being used, just run:
+To help other developers recognize and understand the use of the GPT-PR library in generating pull requests, we have included an optional signature feature. By default, this feature is enabled and appends the text "Generated by GPT-PR" at the end of each pull request. This transparency fosters better collaboration and awareness among team members about the tools being utilized in the development process.
+
+If you prefer to disable this feature, simply run the following command:
 
 ```bash
-gpt-pr-config print
+gpt-pr-config set add_tool_signature false
 ```
 
 ### Reset config
@@ -143,7 +216,7 @@ gpt-pr-config print
 To reset any config to default value, just run:
 
 ```bash
-gpt-pr-config reset config-name
+gpt-pr-config reset config_name
 ```
 
 Example:
@@ -179,10 +252,6 @@ gpt-pr -h
 Output:
 ![image](https://github.com/alissonperez/gpt-pr/assets/756802/cc6c0ca4-5759-44ce-ad35-e4e7305b3875)
 
-## How to contribute?
-
-Please follow our [CONTRIBUTING](./CONTRIBUTING.md) guide.
-
 ## Roadmap
 
 - [x] Improve execution method, possibly through a shell script or at least an alias in bash rc files.

gpt_pr-0.7.2/gpt_pr/__init__.py

@@ -0,0 +1,3 @@
+from importlib.metadata import version
+
+__version__ = version(__name__)

gpt_pr-0.7.2/gpt_pr/checkversion.py

@@ -0,0 +1,93 @@
+import requests
+import os
+import json
+import tempfile
+from gpt_pr import __version__
+from datetime import datetime, timedelta
+
+from gpt_pr import consolecolor as cc
+
+
+PACKAGE_NAME = "gpt-pr"
+CACHE_FILE = os.path.join(os.path.expanduser("~"), ".gpt_pr_update_cache.json")
+CACHE_DURATION = timedelta(days=1)
+
+
+def cache_daily_version(func):
+    def wrapper(*args, **kwargs):
+        cache = load_cache()
+        last_checked = cache.get("last_checked")
+
+        if last_checked:
+            last_checked = datetime.fromisoformat(last_checked)
+
+            if datetime.now() - last_checked < CACHE_DURATION:
+                # Use cached version info
+                latest_version = cache.get("latest_version")
+                if latest_version:
+                    return latest_version
+
+        latest_version = func(*args, **kwargs)
+        cache = {
+            "last_checked": datetime.now().isoformat(),
+            "latest_version": latest_version,
+        }
+        save_cache(cache)
+
+        return latest_version
+
+    return wrapper
+
+
+def get_cache_file_path():
+    temp_dir = tempfile.gettempdir()
+    return os.path.join(temp_dir, f"{PACKAGE_NAME}_update_cache.json")
+
+
+@cache_daily_version
+def get_latest_version():
+    url = f"https://pypi.org/pypi/{PACKAGE_NAME}/json"
+
+    try:
+        response = requests.get(url)
+        response.raise_for_status()
+        data = response.json()
+        return data["info"]["version"]
+    except requests.exceptions.RequestException as e:
+        print(f"Error fetching latest version info: {e}")
+        return None
+
+
+def load_cache():
+    cache_file = get_cache_file_path()
+    if os.path.exists(cache_file):
+        with open(cache_file, "r") as file:
+            return json.load(file)
+
+    return {}
+
+
+def save_cache(data):
+    cache_file = get_cache_file_path()
+    with open(cache_file, "w") as file:
+        file.write(json.dumps(data))
+
+
+def check_for_updates():
+    latest_version = get_latest_version()
+
+    if latest_version and latest_version != __version__:
+        print("")
+        print(
+            cc.yellow(
+                f"A new version of {PACKAGE_NAME} is available ({latest_version}). "
+                f"You are using version {__version__}. Please update by running"
+            ),
+            cc.green(f"pip install --upgrade {PACKAGE_NAME}."),
+        )
+        print("")
+
+
+if __name__ == "__main__":
+    check_for_updates()
+    # Your CLI code here

{gpt-pr-0.3.0/gptpr → gpt_pr-0.7.2/gpt_pr}/config.py

@@ -7,7 +7,8 @@ def config_command_example(name, value_sample):
     return f'gpt-pr-config set {name} {value_sample}'
 
 
-CONFIG_README_SECTION = 'https://github.com/alissonperez/gpt-pr?tab=readme-ov-file#authentication--api-keys'
+CONFIG_PROJECT_REPO_URL = 'https://github.com/alissonperez/gpt-pr'
+CONFIG_README_SECTION = f'{CONFIG_PROJECT_REPO_URL}?tab=readme-ov-file#configuration'
 
 
 class Config:
@@ -15,11 +16,17 @@ class Config:
     config_filename = '.gpt-pr.ini'
 
     _default_config = {
+        # Amenities
+        'ADD_TOOL_SIGNATURE': 'true',  # Add GPT-PR signature to PRs
+
         # Github
         'GH_TOKEN': '',
 
+        # LLM input MAX Tokens
+        'INPUT_MAX_TOKENS': '15000',
+
         # Open AI info
-        'OPENAI_MODEL': 'gpt-4o',
+        'OPENAI_MODEL': 'gpt-4o-mini',
         'OPENAI_API_KEY': '',
     }
 
@@ -66,7 +73,7 @@ class Config:
 
     def set_user_config(self, name, value):
         self.load()
-        self._config['user'][name] = value
+        self._config['user'][name] = str(value)
 
     def reset_user_config(self, name):
         self.load()

gpt_pr-0.7.2/gpt_pr/gh.py

@@ -0,0 +1,44 @@
+import os
+from github import Github
+from InquirerPy import inquirer
+from gpt_pr.config import config, config_command_example, CONFIG_README_SECTION
+
+
+def _get_gh_token():
+    gh_token = config.get_user_config("GH_TOKEN")
+    if not gh_token:
+        gh_token = os.environ.get("GH_TOKEN")
+
+    if not gh_token:
+        print(
+            'Please set "gh_token" config. Just run:',
+            config_command_example("gh_token", "[my gh token]"),
+            "more about at",
+            CONFIG_README_SECTION,
+        )
+        raise SystemExit(1)
+
+    return gh_token
+
+
+def create_pr(pr_data, yield_confirmation, gh=None):
+    if not gh:
+        gh = Github(_get_gh_token())
+
+    repo = gh.get_repo(f"{pr_data.branch_info.owner}/{pr_data.branch_info.repo}")
+
+    pr_confirmation = (
+        yield_confirmation
+        or inquirer.confirm(message="Create GitHub PR?", default=True).execute()
+    )
+
+    if pr_confirmation:
+        pr = repo.create_pull(
+            title=pr_data.title,
+            body=pr_data.create_body(),
+            head=pr_data.branch_info.branch,
+            base=pr_data.branch_info.base_branch,
+        )
+        print("Pull request created successfully: ", pr.html_url)
+    else:
+        print("cancelling...")