Local Streamlit application for exploring suitable machine learning, AI, data science, NLP, computer vision, time series, anomaly detection, document intelligence, optimization, GenAI, and RAG algorithm families.
The app helps users describe a project through grouped checkboxes, generates deterministic local candidate algorithms, and can optionally ask ChatGPT through the OpenAI API to rank those candidates with practical implementation guidance.
- Runs locally on Windows, macOS, or Linux.
- Built with Python and Streamlit.
- Deterministic recommendations work without an API key.
- ChatGPT ranking is only called when the user clicks Rank with ChatGPT.
- Unchecked boxes are treated as unknown, never as "No".
- Includes explicit negative options where a true negative matters.
- Exports the full project profile, candidate algorithms, and ranking as Markdown.
- Designed for ML solution architects, data scientists, AI consultants, product teams, and analytics teams.
git clone https://github.com/YOUR_USERNAME/ml-ai-algorithm-advisor.git
cd ml-ai-algorithm-advisor
python -m venv .venv
.\.venv\Scripts\Activate.ps1
python -m pip install --upgrade pip
python -m pip install -r requirements.txt
cd algorithm_advisor
streamlit run app.pyOpen:
http://localhost:8501
The OpenAI API key is optional for local deterministic recommendations. It is required only for ChatGPT ranking.
cd algorithm_advisor
Copy-Item .env.example .envEdit algorithm_advisor/.env:
OPENAI_API_KEY=your_api_key_here
OPENAI_MODEL=gpt-5.5Never commit .env or API keys.
algorithm_advisor/
app.py
recommender.py
openai_client.py
prompts.py
models.py
utils.py
requirements.txt
README.md
.env.example
docs/
ARCHITECTURE.md
GITHUB_PUBLISHING.md
OPENAI_SETUP.md
USAGE.md
.github/
ISSUE_TEMPLATE/
PULL_REQUEST_TEMPLATE.md
machine-learning, artificial-intelligence, streamlit, data-science, mlops, nlp, computer-vision, time-series, anomaly-detection, rag, genai, openai, algorithm-selection, document-intelligence
MIT. See LICENSE.