3. Data, Science & AI

Provides optimized techniques for creating publication-ready data visualizations using Matplotlib in Python data science projects.

Provides best practices for developing, training, fine-tuning, and deploying Large Language Models (LLMs) efficiently and effectively.

Provides best practices for data analysis using pandas, numpy, matplotlib, and seaborn in Jupyter notebooks.

Extracts structured data from websites using Python libraries for data processing and analysis tasks.

Expert guidance for building LangChain and LangGraph applications in Python, including chain composition, agents, memory, and RAG implementations.

Framework for critiquing AI responses, analyzing solution paths, and assessing AI content quality to enhance output reliability.

Guides data analysis workflows in Jupyter Notebooks using pandas, numpy, matplotlib, and seaborn for data processing and visualization.

Provides optimized MySQL schema design, query tuning, and administration guidelines for high-performance database management.

Provides PostgreSQL schema design, query optimization, and administration best practices to improve database performance and reliability.

Provides comprehensive guidelines for neural network development, training, and optimization in deep learning applications.

Guidelines for deep learning model development with PyTorch, Transformers, Diffusers, and Gradio for LLM and diffusion models.

Provides optimized indexing, querying, and search performance guidelines for Elasticsearch data management in applications.

Provides expert guidance for implementing NLP, computer vision, and multimodal AI tasks using the Hugging Face Transformers library.

Enables machine learning model development using JAX, functional programming paradigms, and high-performance computing techniques.

Expert guidance for natural language processing development using transformers, spaCy, and NLTK libraries.

Provides best practices for implementing Apache Kafka in event-driven architectures and real-time data streaming applications.

Provides optimized techniques for efficient NumPy array operations, enhancing numerical computation performance in Python data science workflows.

Builds efficient web scrapers with Scrapy for data extraction, following best practices in spider development and pipeline management.

Provides expert guidance on best practices for using JAX in high-performance numerical computing and machine learning applications.

Provides best practices for scikit-learn model development, evaluation, and deployment in Python.

Expert guidance for building computer vision applications using OpenCV and PyTorch for image and video processing tasks.

Guides best practices for scientific computing, optimization, signal processing, and statistical analysis using the SciPy library in Python.

Analyzes EDN templates in Logseq databases for structural integrity, quality metrics, and version comparison, identifying orphaned items and property issues.

Calculates portfolio risk metrics including VaR, CVaR, Sharpe ratio, Sortino ratio, and drawdown analysis.