llm-app-patterns

version	4.1.0-fractal
name	llm-app-patterns
description	Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.

🤖 LLM Application Patterns

Production-ready patterns for building LLM applications, inspired by Dify and industry best practices.

When to Use This Skill

Use this skill when:

• Designing LLM-powered applications
• Implementing RAG (Retrieval-Augmented Generation)
• Building AI agents with tools
• Setting up LLMOps monitoring
• Choosing between agent architectures

---

1. RAG Pipeline Architecture

🧠 Knowledge Modules (Fractal Skills)

1. Overview

2. 1.1 Document Ingestion

3. 1.2 Embedding & Storage

4. 1.3 Retrieval Strategies

5. 1.4 Generation with Context

6. 2.1 ReAct Pattern (Reasoning + Acting)

7. 2.2 Function Calling Pattern

8. 2.3 Plan-and-Execute Pattern

9. 2.4 Multi-Agent Collaboration

10. 3.1 Prompt Templates with Variables

11. 3.2 Prompt Versioning & A/B Testing

12. 3.3 Prompt Chaining

13. 4.1 Metrics to Track

14. 4.2 Logging & Tracing

15. 4.3 Evaluation Framework

16. 5.1 Caching Strategy

17. 5.2 Rate Limiting & Retry

18. 5.3 Fallback Strategy