An AI-powered code review assistant
Project description
Installation
You can install the latest version of AI Review Assistant from GitHub:
pip install git+https://github.com/vvandriichuk/ai-review-assistant.git
Help:
ai_review_assistant --help
Example of usage:
ai_review_assistant --vendor openai --model gpt-4o --api-key your_api_key --program-language "Python,JavaScript,TypeScript" --result-output-language English --ignore-settings-files/--review-all-files review
You can put your own prompt to pyproject.toml:
prompt_template = """
You are an AI Code Review Assistant with expert knowledge of {program_language}. As a senior {program_language} developer, review the following code changes:
Project Structure:
{project_structure}
File being reviewed: {file_path}
Analyze the code changes considering these aspects:
1. Code quality and readability
2. Potential bugs or errors
3. Performance implications
4. Consistency with the overall project structure
5. Suggestions for improvement
6. Best practices specific to {program_language}
Instructions for your response:
- Provide a concise summary (about 4-6 points) of your overall findings.
- Focus only on the most important or critical issues, if any.
- Clearly state whether you found any critical issues that need immediate attention.
- Include 1-2 key suggestions for improvement, if applicable.
- If no significant issues were found, briefly mention that the changes look good, but still provide a suggestion for potential enhancement if possible.
Your summary should be structured as follows:
1. Overall assessment (1-2 points)
2. Critical issues (if any) (1-2 points)
3. Key suggestions for improvement (3-4 points)
Provide your summary in {result_output_language}.
"""
Changelog
0.7.0 - 2024-07-27
Added
- Added ignore_settings_files option to ignore settings files (toml, lock, md, txt, in, ini and that start from dot in the name)
0.6.2 - 2024-07-27
Added
- Added missed rich library to dependencies list
0.6.1 - 2024-07-27
Fixed
- Fixed some minor bugs with versions and documentations
0.6.0 - 2024-07-27
Added
- You can put your own prompt to pyproject.toml file using [tool.code_review_assistant] block. Example of such block:
0.5.0 - 2024-07-26
Added
- You can check version of AI Review Assistant
0.4.0 - 2024-07-26
Added
- Added splitting long context by batch size
- Added support for multiple languages
- Added support for multiple models
- You can run AI Review Assistant in any directory
Changed
- Updated version of main dependencies libs
0.1.0 - 2024-07-25
Added
- Init library
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
ai_review_assistant-0.7.0.tar.gz
(89.3 kB
view details)
Built Distribution
File details
Details for the file ai_review_assistant-0.7.0.tar.gz
.
File metadata
- Download URL: ai_review_assistant-0.7.0.tar.gz
- Upload date:
- Size: 89.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.11.8
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 9c91c4825151c7ee17488fc5a21fd07f52f39dace40d375c5b4a19cd8849dc58 |
|
MD5 | 600b63f64eb26e7693cb6985b695bec1 |
|
BLAKE2b-256 | 64123c6558b6df8a0553e5455ee9bee6b661bac0872718a4e7b6103ac94527d0 |
File details
Details for the file ai_review_assistant-0.7.0-py3-none-any.whl
.
File metadata
- Download URL: ai_review_assistant-0.7.0-py3-none-any.whl
- Upload date:
- Size: 9.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.11.8
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 2834e7400f3b2e0332aea0e728f420147d0c46f2a29bc4ee4b1695158c5dd4e6 |
|
MD5 | f2237ee8a0ea17e1e989eb291d0ecb43 |
|
BLAKE2b-256 | 9e45c65c01ec91f69deee50825bca13cda149533fac472197539c5ed4f3ef718 |