提示词工程、RAG之后，LangChain：上下文工程开始火了！

Core Viewpoint - Context engineering is emerging as a crucial skill for AI engineers, shifting the focus from traditional prompt engineering to providing structured and dynamic context for large language models (LLMs) to perform tasks effectively [3][7][15]. Group 1: Definition and Importance of Context Engineering - Context engineering involves constructing dynamic systems that provide accurate information and tools in the right format, enabling LLMs to complete tasks effectively [9][10]. - The significance of context engineering lies in its ability to address common failures in AI systems, which often stem from inadequate context or incorrect information being provided to the model [12][15]. - Unlike prompt engineering, which focuses on crafting clever prompts, context engineering emphasizes the importance of delivering complete and structured context to enhance model performance [17][19]. Group 2: Components of Effective Context Engineering - Effective context engineering requires accurate information, as models cannot infer context without being explicitly provided with it [12][19]. - The format of the context is critical; how information is communicated to the LLM can significantly impact its responses [13][19]. - Tools must be appropriately utilized to access external information, and the returned data should be formatted in a way that is easily understandable by the LLM [20]. Group 3: Transition from Prompt Engineering to Context Engineering - The transition from prompt engineering to context engineering is driven by the increasing complexity of applications, highlighting the need for a more comprehensive approach to context provision [16][17]. - Context engineering can be viewed as a subset of prompt engineering, where the focus shifts from single input prompts to managing and formatting dynamic data sets [17][18].