llm-app-patterns

To build a production-ready RAG pipeline, implement efficient document ingestion, embedding, retrieval, and generation strategies. This Skill provides battle-tested patterns and code examples to set up robust data retrieval and generation for large document sets.

Implementing a ReAct agent architecture involves using reasoning and acting patterns for interactive user experiences. This Skill offers production-ready code examples to build agents utilizing ReAct, Function Calling, Plan-and-Execute, and Multi-Agent collaboration patterns.

LLMOps monitoring handles logging and rate limiting by integrating tracing, caching, and evaluation mechanisms. This ensures robust deployment of LLM applications through battle-tested operational patterns designed for production environments.

Yes, you can use prompt engineering templates and versioning for LLM application development. This Skill provides patterns for effective prompt management, including techniques for template chaining and version control.

No specific dependencies are required to set up multi-agent collaboration patterns. This Skill provides standalone scripts and references to implement various agent architectures and design interactive AI applications without external package constraints.