with Ollama, LangChain, LangGraph (No GPU, No APIKEY)
15 min learn
12 hours in the past
(All photographs are by the writer until in any other case famous)
Intro
Immediate Engineering is the observe of designing and refining prompts (textual content inputs) to reinforce the habits of Giant Language Fashions (LLMs). The purpose is to get the specified responses from the mannequin by fastidiously crafting the directions. Essentially the most used prompting methods are:
- Chain-of-Thought: includes producing a step-by-step reasoning course of to achieve a conclusion. The mannequin is pushed to “suppose out loud” by explicitly laying out the logical steps that result in the ultimate reply.
- ReAct (Purpose+Act): combines reasoning with motion. The mannequin not solely thinks by means of an issue but in addition takes actions based mostly on its reasoning. So it’s extra interactive because the mannequin alternates between reasoning steps and actions, refining its strategy iteratively. Principally, it’s a loop of “thought”, “motion”, “commentary”.
Let’s make an instance: think about asking an AI to “discover one of the best laptop computer underneath $1000”.
– Regular Reply: “Lenovo Thinkpad”.
– Chain-of-Thought Reply: “I want to contemplate elements like efficiency, battery life, and…
