介绍Prompt Engineering工具包
A well-crafted prompt is essential for obtaining accurate and relevant outputs from LLMs (Large Language Models). Prompt design enables users new to machine learning to control model output with minimal overhead.
精心设计的提示对于从LLM（大型语言模型）中获得准确和相关的输出至关重要。提示设计使新接触机器学习的用户能够以最小的开销控制模型输出。
To facilitate rapid iteration and experimentation of LLMs at Uber, there was a need for centralization to seamlessly construct prompt templates, manage them, and execute them against various underlying LLMs to take advantage of LLM support tasks.
为了在Uber促进LLM的快速迭代和实验，需要集中化以无缝构建提示模板，管理它们，并在各种底层LLM上执行它们，以利用LLM支持任务。
To meet these needs, we built a prompt engineering toolkit that offers standard strategies that encourage prompt engineers to develop well-crafted prompt templates. It also provides functionality to enrich these templates with context obtained from RAG (Retrieval-Augmented Generation) and runtime feature datasets.
为了满足这些需求，我们构建了一个提示工程工具包，提供标准策略，鼓励提示工程师开发精心设计的提示模板。它还提供功能，以通过RAG（检索增强生成）和运行时特征数据集获得的上下文来丰富这些模板。
The centralized prompt engineering toolkit enables the creation of effective prompts with system instructions, dynamic contextualization, massive batch offline generation (LLM inference), and evaluation of prompt responses. Furthermore, there’s a need for version control, collaboration, and robust safety measures (hallucination checks, standardized evaluation framework, and a safety policy) to ensure responsible AI usage.
集中式提示工程工具包通过系统指令、动态情境化、大规模批量离线生成（LLM推理）和提示响应评估来创建有效的提示。此外，还需要版本控制、协作和强大的安全措施（幻觉检查、标准化评估框架和安全政策）以确保负责任的AI使用。
This blog post gives an overview of the prompt template lifecycle, the architecture used to build the prompt toolkit, and the production usage of the toolkit at Uber.
这篇博客文章概述了提示模板生命周期、构建提示工具包的架构以及该工具包在Uber的生产使用情况。
When we built the prompt toolkit, our goals were that users at Uber could:
当我们构建提示工具包时，我们的目标是让Uber的用户能够：
- Explore all the available LLM models
- 探索所有可用的 LLM 模型
- Search and discover all the prompt templates
- 搜索和发现所有的提示模板
- Create and update prompt templates and tune parameters with access control
- 创建和...