#structured-output (3)

Cheat sheets (3)

Prompting

Prompt engineering patterns, RAG, evaluations, few-shot, chain-of-thought, and structured output — foundational techniques for extracting reliable, structured behavior from LLMs.

prompting rag llm prompt-engineering cot few-shot evals structured-output

Structured Output

Techniques for reliable structured generation — JSON mode, schema-constrained decoding, function/tool calls as output, and validator pairing with Pydantic or Zod.

structured-output json schema pydantic zod tool-use function-calling prompting

guidance — Constrained LLM Generation

Interleave Python control flow with LLM generation and enforce structured output using guidance. Covers gen(), select(), chat blocks, regex constraints, JSON schemas, and token healing.

python guidance llm ai structured-output constrained-generation transformers