Skill UI

This guide provides advanced architectural patterns to optimize interactions with the Perplexity Sonar API. By implementing smart model routing, query hashing with time-to-live (TTL) caching, streaming responses, and rate-limited parallel processing, developers can significantly reduce latency, improve overall throughput, and manage API costs. Ideal for integrating complex, research-intensive search-augmented applications.

This comprehensive checklist guides the deployment of Perplexity Sonar API integrations to a robust production environment. It covers critical aspects including API key management, robust code quality practices (retries, rate limiting), performance optimization (caching, streaming), detailed monitoring setup, and cost control strategies. Use this checklist when preparing for a major Perplexity feature launch or going live to production.

This skill provides comprehensive patterns for building highly reliable applications that interact with external Large Language Model (LLM) APIs, such as Perplexity Sonar. It implements critical reliability techniques including Circuit Breakers, Model Fallback, Streaming Timeout handling, and Caching layers. Use this to ensure your application maintains high availability and graceful degradation even when external services experience intermittent failures or variable performance.

This skill enables the development of robust, event-driven pipelines interacting with the Perplexity Sonar API. Since Perplexity lacks native webhooks, this system simulates event patterns using advanced techniques: Streaming Server-Sent Events (SSE) for real-time data, job queues (like BullMQ/SQS) for asynchronous batch research, and cron-triggered monitoring for scheduled news and trend alerts. It provides patterns for building complex, reliable, and scalable AI applications.

Guides users through setting up monitoring for data pipelines, covering ETL, transformation, orchestration, streaming, and validation with best-practice code and configuration.

This skill provides comprehensive expertise for senior database administrators to optimize and manage PostgreSQL databases at an advanced level. Use it for deep query analysis via EXPLAIN ANALYZE, implementing advanced features like JSONB indexing, configuring streaming or logical replication, and maintaining database health through VACUUM tuning and monitoring pg_stat views. Ideal for building highly available, high-performance, and resilient system architectures.

Automated assistance for pyspark transformer work within data pipelines, activating when you request transformer patterns or best practices and covering ETL, data transformation, orchestration, and streaming scenarios.

Ray Data offers scalable distributed data processing for ML workloads, streaming across CPU/GPU clusters and integrating with PyTorch, TensorFlow, and Ray Train. Use it for batch inference, ETL, and multi-modal preprocessing from a laptop up to hundreds of nodes.

Highlights React 19 idioms such as the new use() hook, server components, server actions, optimistic updates, suspense, error handling, and compound hooks to structure Next.js apps with streaming data, interactivity, and reusable hooks.

Explains how to create route.ts endpoints in the Next.js App Router, covering HTTP methods, request/response handling, streaming, cookies, redirects, CORS, and caching so you can build REST APIs.

RWKV is an RNN+Transformer hybrid architecture with linear-time inference, infinite context, and GPT-style training. It delivers constant-memory, streaming generation on CUDA and CPU, ideal for long-context, memory-constrained deployments.

Automates schema validation within data pipelines, providing guidance on best practices, workflow orchestration, and streaming ETL scenarios while producing production-ready code and configurations.