 Google 《Prompt Engineering v7》together 11 Prompting techniques 13 General prompting / zero shot 13 One-shot & few-shot 15 System, contextual and role prompting 18 System prompting 19 Role prompting 21 Contextual prompting 23 Table contents Step-back prompting 25 Chain of Thought (CoT) 29 Self-consistency 32 Tree of Thoughts (ToT) 36 ReAct (reason & act) 37 Automatic Prompt Engineering 40 Code prompting 42 Prompts for writing Prompts for translating code 46 Prompts for debugging and reviewing code 48 What about multimodal prompting? 54 Best Practices 54 Provide examples 54 Design with simplicity 55 Be specific about the output0 码力 | 68 页 | 6.50 MB | 6 月前3 Google 《Prompt Engineering v7》together 11 Prompting techniques 13 General prompting / zero shot 13 One-shot & few-shot 15 System, contextual and role prompting 18 System prompting 19 Role prompting 21 Contextual prompting 23 Table contents Step-back prompting 25 Chain of Thought (CoT) 29 Self-consistency 32 Tree of Thoughts (ToT) 36 ReAct (reason & act) 37 Automatic Prompt Engineering 40 Code prompting 42 Prompts for writing Prompts for translating code 46 Prompts for debugging and reviewing code 48 What about multimodal prompting? 54 Best Practices 54 Provide examples 54 Design with simplicity 55 Be specific about the output0 码力 | 68 页 | 6.50 MB | 6 月前3
 2024 中国开源开发者报告networks and tree search." nature 529.7587 (2016): 484-489. 【4】 Wei, Jason, et al. "Chain-of-thought prompting elicits reasoning in large language models." Advances in neural information processing systems 35 i-in-the-enterprise/ 根据 Menlo Ventures 发布的市场调研报告显示,RAG 以 51%的市场份额在企业市场份额 中占据绝对优势,Fine-tune 和 Prompting 工程均下降两倍多。Agent 今年属于纯增长,目前情 况还不错,但在企业应用领域,多 Agents 的编排依然存在理解能力不足和生成幻觉等问题有待 提高。 如果去预测明年的企业级市场趋0 码力 | 111 页 | 11.44 MB | 8 月前3 2024 中国开源开发者报告networks and tree search." nature 529.7587 (2016): 484-489. 【4】 Wei, Jason, et al. "Chain-of-thought prompting elicits reasoning in large language models." Advances in neural information processing systems 35 i-in-the-enterprise/ 根据 Menlo Ventures 发布的市场调研报告显示,RAG 以 51%的市场份额在企业市场份额 中占据绝对优势,Fine-tune 和 Prompting 工程均下降两倍多。Agent 今年属于纯增长,目前情 况还不错,但在企业应用领域,多 Agents 的编排依然存在理解能力不足和生成幻觉等问题有待 提高。 如果去预测明年的企业级市场趋0 码力 | 111 页 | 11.44 MB | 8 月前3
 C++ Memory Model: from C++11 to C++23program termination, data written to files is exactly as if the program was executed as written ● Prompting text which is sent to interactive devices will be shown before the program waits for input ●0 码力 | 112 页 | 5.17 MB | 6 月前3 C++ Memory Model: from C++11 to C++23program termination, data written to files is exactly as if the program was executed as written ● Prompting text which is sent to interactive devices will be shown before the program waits for input ●0 码力 | 112 页 | 5.17 MB | 6 月前3
 清华大学第二弹:DeepSeek赋能职场另一种路径:DeepSeek R1 作为智能体 ü 角色 ü 功能 ü 技能 ü 约束 ü 工作流程 ü 输出格式 "全维度智能体提示框架" (Comprehensive Agent Prompting Framework, CAP Framework) 核心层: 1.身份定义 (Identity) •角色属性 •专业背景 •交互特征 执行层: 2. 能力矩阵 (Capability0 码力 | 35 页 | 9.78 MB | 8 月前3 清华大学第二弹:DeepSeek赋能职场另一种路径:DeepSeek R1 作为智能体 ü 角色 ü 功能 ü 技能 ü 约束 ü 工作流程 ü 输出格式 "全维度智能体提示框架" (Comprehensive Agent Prompting Framework, CAP Framework) 核心层: 1.身份定义 (Identity) •角色属性 •专业背景 •交互特征 执行层: 2. 能力矩阵 (Capability0 码力 | 35 页 | 9.78 MB | 8 月前3
 Design and Implementation of Highly Scalable Quantifiable Data Structures in C++acceptance of relaxed semantics ▶ The intractable O(n!) complexity of concurrent system models prompting the search for reductions ▶ Growth of distributed software applications: blockchain, distributed0 码力 | 51 页 | 4.08 MB | 6 月前3 Design and Implementation of Highly Scalable Quantifiable Data Structures in C++acceptance of relaxed semantics ▶ The intractable O(n!) complexity of concurrent system models prompting the search for reductions ▶ Growth of distributed software applications: blockchain, distributed0 码力 | 51 页 | 4.08 MB | 6 月前3
 Back to Basics: The Abstract Machine• The input and output dynamics of interactive devices shall take place in such a fashion that prompting output is actually delivered before a program waits for input. What constitutes an interactive0 码力 | 91 页 | 538.90 KB | 6 月前3 Back to Basics: The Abstract Machine• The input and output dynamics of interactive devices shall take place in such a fashion that prompting output is actually delivered before a program waits for input. What constitutes an interactive0 码力 | 91 页 | 538.90 KB | 6 月前3
 Regular, RevisitedRevisited 102 Slide Title Non-owning reference types like string_view or span You need more contextual information when working on an instance of this type2023 Victor Ciura | @ciura_victor - Revisited 102 Slide Title Non-owning reference types like string_view or span You need more contextual information when working on an instance of this type Things to consider: shallow copy ? Title 📯 Call To Action For non-owning reference types like string_view or span You need more contextual information when working on an instance of this type2023 Victor Ciura | @ciura_victor -0 码力 | 180 页 | 19.96 MB | 6 月前3 Regular, RevisitedRevisited 102 Slide Title Non-owning reference types like string_view or span You need more contextual information when working on an instance of this type2023 Victor Ciura | @ciura_victor - Revisited 102 Slide Title Non-owning reference types like string_view or span You need more contextual information when working on an instance of this type Things to consider: shallow copy ? Title 📯 Call To Action For non-owning reference types like string_view or span You need more contextual information when working on an instance of this type2023 Victor Ciura | @ciura_victor -0 码力 | 180 页 | 19.96 MB | 6 月前3
 Python 标准库参考指南 2.7.18 LogRecord needs to be done with some care, but it does allow the injection of contextual information into logs (see filters-contextual). 15.7.6 LogRecord Objects LogRecord instances are created automatically LoggerAdapter instances are used to conveniently pass contextual information into logging calls. For a usage example, see the section on adding contextual information to your logging output. 2.6 新版功能. class kwargs) Modifies the message and/or keyword arguments passed to a logging call in order to insert contextual infor- mation. This implementation takes the object passed as extra to the constructor and adds0 码力 | 1552 页 | 7.42 MB | 9 月前3 Python 标准库参考指南 2.7.18 LogRecord needs to be done with some care, but it does allow the injection of contextual information into logs (see filters-contextual). 15.7.6 LogRecord Objects LogRecord instances are created automatically LoggerAdapter instances are used to conveniently pass contextual information into logging calls. For a usage example, see the section on adding contextual information to your logging output. 2.6 新版功能. class kwargs) Modifies the message and/or keyword arguments passed to a logging call in order to insert contextual infor- mation. This implementation takes the object passed as extra to the constructor and adds0 码力 | 1552 页 | 7.42 MB | 9 月前3
 Python 标准库参考指南 2.7.18 LogRecord needs to be done with some care, but it does allow the injection of contextual information into logs (see filters-contextual). 15.7.6 LogRecord Objects LogRecord instances are created automatically LoggerAdapter instances are used to conveniently pass contextual information into logging calls. For a usage example, see the section on adding contextual information to your logging output. 2.6 新版功能. class kwargs) Modifies the message and/or keyword arguments passed to a logging call in order to insert contextual infor- mation. This implementation takes the object passed as extra to the constructor and adds0 码力 | 1552 页 | 7.42 MB | 9 月前3 Python 标准库参考指南 2.7.18 LogRecord needs to be done with some care, but it does allow the injection of contextual information into logs (see filters-contextual). 15.7.6 LogRecord Objects LogRecord instances are created automatically LoggerAdapter instances are used to conveniently pass contextual information into logging calls. For a usage example, see the section on adding contextual information to your logging output. 2.6 新版功能. class kwargs) Modifies the message and/or keyword arguments passed to a logging call in order to insert contextual infor- mation. This implementation takes the object passed as extra to the constructor and adds0 码力 | 1552 页 | 7.42 MB | 9 月前3
 Python 标准库参考指南 2.7.18 LogRecord needs to be done with some care, but it does allow the injection of contextual information into logs (see filters-contextual). 15.7.6 LogRecord Objects LogRecord instances are created automatically LoggerAdapter instances are used to conveniently pass contextual information into logging calls. For a usage example, see the section on adding contextual information to your logging output. 2.6 新版功能. class kwargs) Modifies the message and/or keyword arguments passed to a logging call in order to insert contextual infor- mation. This implementation takes the object passed as extra to the constructor and adds0 码力 | 1552 页 | 7.42 MB | 9 月前3 Python 标准库参考指南 2.7.18 LogRecord needs to be done with some care, but it does allow the injection of contextual information into logs (see filters-contextual). 15.7.6 LogRecord Objects LogRecord instances are created automatically LoggerAdapter instances are used to conveniently pass contextual information into logging calls. For a usage example, see the section on adding contextual information to your logging output. 2.6 新版功能. class kwargs) Modifies the message and/or keyword arguments passed to a logging call in order to insert contextual infor- mation. This implementation takes the object passed as extra to the constructor and adds0 码力 | 1552 页 | 7.42 MB | 9 月前3
共 76 条
- 1
- 2
- 3
- 4
- 5
- 6
- 8














 
 