3. Data, Science & AI

Extracts structured data from web pages using CSS selectors with pagination support and rate limiting.

Visualizes CC capabilities dashboard for real-time monitoring, accessible via trigger commands like '/dashboard'.

Designs, optimizes, and tests AI model prompts using systematic techniques like few-shot learning and chain-of-thought for enhanced LLM performance.

Generates HTML reports with statistical analysis from X (Twitter) data scraped via Playwright.

Executes SQL queries on SQLite, PostgreSQL, and MySQL databases with result formatting and export functionality.

Handles Excel file operations including reading, writing, and data manipulation for spreadsheets in .xlsx and .xls formats.

Converts text to natural-sounding speech audio with multilingual support and voice customization.

Processes CSV files with filtering, sorting, aggregation, and format conversion for data analysis workflows.

Analyzes Bilibili video content by extracting frames and applying AI to generate detailed topic documents or practical tutorials.

Extracts and processes web data using CSS selectors and XPath with intelligent parsing, rate limiting, and error handling.

Designs and optimizes database schemas for PostgreSQL, MySQL, SQLite, and MongoDB, including ER modeling, normalization, and index optimization.

Provides a library for SQLite database operations including persistence, queries, migrations, and CloudKit sync using macros.

Enables on-device AI implementation using Apple's Foundation Models for summarization, extraction, and classification with type-safe structured output via @Generable.

Interactive tool for creating custom AI assistants with personalized personas and specialized configurations on CodeConductor.

Enables high-fidelity spreadsheet operations for financial modeling, data analysis, and dashboard creation with error verification.

Provides frameworks for creating and optimizing AI prompts using techniques like few-shot learning and chain-of-thought to improve model performance in production.

Optimizes document segmentation for RAG systems, ensuring semantically meaningful chunks for effective vector embeddings and search retrieval.

Provides Java 2.x SDK patterns for Amazon Bedrock, enabling foundation model interactions including text/image generation, embeddings, and Spring Boot integration.

Integrates Qdrant vector database with LangChain4j for Java, enabling embedding storage, similarity search, and vector management in RAG systems and semantic search applications.

Builds RAG systems using vector databases and semantic search for knowledge-grounded AI applications, document Q&A, and LLM integration.

Builds RAG systems with LangChain4j for document ingestion, vector search, and knowledge-enhanced AI applications.

Provides testing strategies for LangChain4j applications, including mocking LLM responses and validating retrieval chains in AI workflows.

Configures LangChain4J vector stores for RAG applications, enabling semantic search and integration with vector databases.

Enables defining tools, handling function calls, and integrating with LLM agents for building agentic applications.