Skill UI

This SDK allows developers to build robust anomaly detection applications in Java using Azure AI services. It supports both univariate and multivariate time-series analysis, enabling detection of outliers, trend changes, and correlated signals over large datasets. Ideal for real-time monitoring, operational intelligence, and advanced data quality checks.

This SDK allows developers to build robust anomaly detection applications in Java using Azure AI services. It supports both univariate and multivariate time-series analysis, enabling detection of outliers, trend changes, and correlated signals over large datasets. Ideal for real-time monitoring, operational intelligence, and advanced data quality checks.

This SDK provides a comprehensive Python client library for interacting with Azure AI Speech-to-Text services. It supports both real-time streaming transcription and robust batch processing of audio files. Users can leverage advanced features such as speaker diarization (identifying multiple speakers) and capturing precise timestamps, making it invaluable for automated meeting minute generation, podcast content processing, and live captioning solutions.

This SDK provides a comprehensive Python client library for interacting with Azure AI Speech-to-Text services. It supports both real-time streaming transcription and robust batch processing of audio files. Users can leverage advanced features such as speaker diarization (identifying multiple speakers) and capturing precise timestamps, making it invaluable for automated meeting minute generation, podcast content processing, and live captioning solutions.

A comprehensive Python SDK for interacting with the Azure AI Translator service. It provides robust features including real-time text translation, language detection, script transliteration, and detailed dictionary lookups. Ideal for developers building multilingual applications that require accurate cross-cultural text processing.

A comprehensive Python SDK for interacting with the Azure AI Translator service. It provides robust features including real-time text translation, language detection, script transliteration, and detailed dictionary lookups. Ideal for developers building multilingual applications that require accurate cross-cultural text processing.

A comprehensive TypeScript SDK for integrating Azure AI Translator services. It provides robust clients for both real-time text translation (including language detection, transliteration) and large-scale document translation. Users can translate single documents or manage complex batch translation jobs using REST-style API calls, making multilingual support easy to integrate into applications.

BlockRun acts as a universal gateway to advanced AI capabilities. It routes user requests to specialized models (e.g., DALL-E for image generation, Grok for real-time X/Twitter data, GPT-5.2 for complex reasoning) using a micropayment wallet system. This allows the agent to execute tasks autonomously by paying for necessary services, ensuring high capability and managing user spending.

This skill provides a comprehensive framework for configuring Mistral AI across distinct environments (development, staging, and production). It manages environment-specific secrets (using GCP, AWS, or Vault), defines critical parameters like default models, rate limits, and feature flags, ensuring secure, isolated, and reliable deployments for AI services in multi-stage pipelines.

This guide outlines the comprehensive reference architecture for building advanced, AI-powered search and research applications, modeled after Perplexity. It covers three core tiers: a searchable service with model routing and caching, a citation pipeline for validation and rendering, and an orchestrator for multi-query research synthesis. Use this when designing complex, production-grade, search-augmented LLM integrations or reviewing advanced system patterns.

SGLang is a high-performance serving framework for LLMs and VLMs that uses RadixAttention prefix caching to deliver structured outputs (JSON/regex/grammar) and agentic workflows with function calls, providing up to 5× faster inference than vLLM across multi-GPU production deployments.

A framework for building production-ready, low-latency, multimodal AI agents. It allows developers to orchestrate complex pipelines that seamlessly handle real-time audio, video, and text data. Key capabilities include integrating multiple AI services (LLMs, STT, TTS), managing conversation context, and enabling tool use and function calling for advanced, interactive AI applications.