with Ollama, LangChain, LangGraph (No GPU, No APIKEY)
(All photographs are by the creator except in any other case famous)
Intro
Immediate Engineering is the apply of designing and refining prompts (textual content inputs) to boost the habits of Giant Language Fashions (LLMs). The aim is to get the specified responses from the mannequin by fastidiously crafting the directions. Probably the most used prompting strategies 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 via an issue but in addition takes actions primarily based on its reasoning. So it’s extra interactive because the mannequin alternates between reasoning steps and actions, refining its method iteratively. Principally, it’s a loop of “thought”, “motion”, “remark”.
Let’s make an instance: think about asking an AI to “discover one of the best laptop computer beneath $1000”.
– Regular Reply: “Lenovo Thinkpad”.
– Chain-of-Thought Reply: “I would like to think about elements like efficiency, battery life, and…