Skill UI

The official client library for interacting with Azure OpenAI services in .NET. It provides comprehensive access to various OpenAI models, including GPT-4o, embeddings, image generation (DALL-E), and audio transcription (Whisper). Use cases include building advanced chat applications, generating structured JSON outputs, and implementing Retrieval-Augmented Generation (RAG).

The Azure AI VoiceLive SDK for Java enables real-time, bidirectional voice conversations with AI assistants. Using WebSocket technology, this SDK supports low-latency streaming, advanced features like turn detection, noise reduction, and customizable voice selection (OpenAI/Azure). It is ideal for developers building sophisticated voice bots or interactive voice applications in Java.

Empowers building AI agents that perceive screens, plan via vision-language reasoning, and control mouse/keyboard for desktop automation, with attention to sandboxing and safety across Anthropic, OpenAI, and open-source paradigms.

Comprehensive guide for configuring Bring Your Own Key (BYOK) for major AI providers, including OpenAI, Anthropic, Google Gemini, Azure, and custom endpoints. This allows users to bypass default quotas, manage costs directly with the source provider, and utilize a wide range of specialized models within the Cursor IDE. It covers setup steps, security best practices, and cost monitoring strategies.

A comprehensive guide on configuring and selecting the optimal AI model within the Cursor IDE. It details the strengths of various providers (OpenAI, Anthropic, Google) for specific coding tasks—from quick bug fixes to complex architecture planning—and guides users through model selection, API key setup (BYOK), and cost optimization strategies.

This guide offers a comprehensive deep dive into migrating existing voice transcription workflows from multiple major providers, including AWS Transcribe, Google Cloud STT, OpenAI Whisper, and others, to Deepgram. It details feature mapping, best practices, and implements an adapter pattern, enabling seamless, reliable, and validated service switching.

A comprehensive guide for selecting and optimizing embedding models for advanced vector search and retrieval-augmented generation (RAG) applications. This guide covers model comparison, chunking strategies, dimension reduction techniques, and provides runnable Python templates for both OpenAI and local Sentence Transformer implementations.

A comprehensive guide for migrating Large Language Model (LLM) integrations from providers like OpenAI or Anthropic to Groq. It details technical steps including SDK replacement, model ID mapping, building provider abstraction layers, and implementing zero-downtime traffic shifting using feature flags. This ensures developers can leverage Groq's superior speed while maintaining service continuity.

This guide details a production-ready reference architecture for applications built on Groq's LPU inference API. It covers sophisticated model routing based on latency, quality, or cost needs, implementing streaming pipelines, and establishing robust multi-provider fallback chains (e.g., Groq primary to OpenAI backup). Ideal for designing and reviewing complex, resilient LLM systems.

Instructor lets you shape LLM responses into validated Pydantic models, automatically retrying failed extractions, parsing complex JSON with type safety, and streaming partial outputs across Anthropic, OpenAI, and other providers.

A comprehensive CI/CD pipeline designed for LangChain applications. It automates quality assurance through fast, mocked unit tests and slower, more accurate integration tests utilizing real LLMs (e.g., OpenAI). It specifically validates the entire RAG pipeline and integrates tracing with LangSmith, ensuring robust deployment quality.

This comprehensive guide details the end-to-end process of building Retrieval-Augmented Generation (RAG) pipelines using LangChain. It covers critical steps: loading diverse document types (PDF, CSV, TXT), splitting text into manageable chunks, generating high-quality embeddings (OpenAI), storing them in various vector databases (FAISS, Pinecone), and finally constructing the full runnable chain for accurate and context-aware querying.