AI/LLM Cheatsheet 11 — Cost Optimization
Cheatsheet: prompt caching, batching, model selection, output limits.
AI
AI/LLM Cheatsheet 12 — Local LLMs (Ollama, vLLM)
Cheatsheet: Ollama, vLLM, llama.cpp, when to self-host.
AI/LLM Cheatsheet 13 — Fine-tuning
Cheatsheet: when to fine-tune, LoRA, QLoRA, OpenAI fine-tune.
AI/LLM Cheatsheet 14 — Multimodal LLMs
Cheatsheet: vision LLMs, image inputs, audio, video.
SQLAlchemy + Postgres Cheatsheet 14 — pgvector for Embeddings
Cheatsheet: Vector column, cosine_distance / l2 / inner_product, HNSW index, hybrid filter + ANN.
AI/LLM Cheatsheet 15 — Security and Prompt Injection
Cheatsheet: prompt injection, defenses, PII, jailbreaks.
AI/LLM Cheatsheet 16 — Vector DBs Deep Dive
Cheatsheet: vector DBs, HNSW, hybrid search, sharding.
AI/LLM Cheatsheet 17 — Observability for LLMs
Cheatsheet: logging, traces, metrics, evals in prod.
AI/LLM Cheatsheet 18 — LLM Application Patterns
Cheatsheet: classification, extraction, summarization, routing, decomposition.
FastAPI Cheatsheet 18 — Streaming and LLM Integration
Cheatsheet: streaming Claude / GPT / vLLM tokens via SSE, tool-call loops, cancellation, prompt caching.