llm-app-patterns

name	llm-app-patterns
type	reference
description	Provides architectural patterns for LLM-powered applications and AI assistants, including prompt engineering, RAG, agent loops, conversation management, and evaluation. Use when building AI-based features, chatbots, or complex AI system architectures.
paths	["**/*.py","**/*.ts","**/openai*","**/anthropic*","**/langchain*","**/chatbot*","**/assistant*"]
effort	3
allowed-tools	Read, Glob, Grep, Write, Edit, Bash
user-invocable	true
when_to_use	When designing LLM applications, building AI assistants/chatbots, implementing RAG pipelines, or setting up agent architectures.

LLM Application & AI Assistant Patterns

Resources

• resources/implementation-playbook.md for detailed patterns and examples.

Architecture decision matrix

Pattern	Use when	Cost
Simple RAG	FAQ, docs Q&A	Low
Hybrid RAG (semantic + BM25)	Mixed query types	Medium
Function calling	Structured tool use	Low
ReAct agent	Multi-step reasoning	Medium
Plan-and-execute	Complex decomposable tasks	High
Multi-agent	Research, critique-refine	Very High

RAG: critical config numbers

CHUNK_CONFIG = {
    "chunk_size": 512,       # tokens — sweet spot for most docs
    "chunk_overlap": 50,     # prevents context loss at boundaries
    "separators": ["\n\n", "\n", ". ", " "],
}
# Hybrid search alpha: 1.0=semantic only, 0.0=BM25 only, 0.5=balanced

RAG: retrieval strategies

# Basic: semantic search
results = vector_db.similarity_search(embed(query), top_k=5)

# Better: hybrid (semantic + keyword via RRF)
def hybrid_search(query, alpha=0.5):
    return rrf_merge(vector_db.search(query), bm25_search(query), alpha)

# Best for recall: multi-query (3 variations, deduplicate)
queries = llm.generate_variations(query, n=3)
results = deduplicate([semantic_search(q) for q in queries])