research-informed-ai-workflow
Version:
Research-Informed AI Workflow Module for comprehensive codebase analysis and improvement using Gemini AI and GitHub Copilot
125 lines (112 loc) • 2.91 kB
Markdown
with a Python data science project.
```
example-python-ds/
├── src/
│ ├── data/
│ ├── models/
│ ├── utils/
│ └── main.py
├── notebooks/
├── tests/
├── requirements.txt
├── pyproject.toml
├── README.md
└── .gitignore
```
```json
{
"tasks": [
{
"id": "comprehensive-analysis",
"name": "Comprehensive Analysis",
"instructionsFile": "tasks/01_comprehensive_analysis.md",
"bundle": [
"src/**/*.py",
"requirements.txt",
"pyproject.toml",
"README.md",
"notebooks/**/*.ipynb",
"tests/**/*.py"
]
},
{
"id": "testing-system-analysis",
"name": "Testing System Analysis",
"instructionsFile": "tasks/03_testing_system_analysis.md",
"bundle": [
"tests/**/*.py",
"src/**/*.py",
"requirements.txt"
]
},
{
"id": "performance-scalability-analysis",
"name": "Performance & Scalability Analysis",
"instructionsFile": "tasks/04_performance_scalability_analysis.md",
"bundle": [
"src/**/*.py",
"notebooks/**/*.ipynb",
"requirements.txt"
]
}
]
}
```
```json
{
"output": {
"filePath": "analysis-bundle.txt",
"style": "plain",
"removeComments": false,
"removeEmptyLines": false
},
"include": [
"**/*.py",
"**/*.ipynb",
"**/*.txt",
"**/*.toml",
"**/*.md",
"**/*.yml",
"**/*.yaml",
"!__pycache__/**",
"!*.pyc",
"!venv/**",
"!env/**",
"!.env/**"
],
"ignore": {
"useGitignore": true,
"useDefaultPatterns": true,
"customPatterns": [
"*.log",
".env*",
"data/**",
"models/**"
]
}
}
```
1. **Copy the configuration files** to your project root:
```powershell
Copy-Item "examples\bundles.example.python.json" ".\bundles.json"
Copy-Item "examples\repomix.config.example.python.json" ".\repomix.config.json"
```
2. **Run the setup script**:
```powershell
.\setup.ps1
```
3. **Generate analysis bundles** for specific tasks:
```powershell
.\Generate.ps1 -TaskID "comprehensive-analysis"
```
- Include `requirements.txt` and `pyproject.toml` for dependency analysis
- Bundle Jupyter notebooks for data science workflow analysis
- Exclude virtual environments and cache directories
- Consider data directories for performance analysis but exclude actual data files
This example demonstrates how to use the Research-Informed AI Workflow Module