ingFang SC", "Hiragino Sans GB", "Microsoft YaHei UI", "Microsoft YaHei", Arial, sans-serif;font-size: 15px;letter-spacing: 0.1em;">Promptify是一个Python库这款 Python 库通过 prompter、LLM 集成与 pipeline，把原本要反复调试 prompt 的过程简化成几行代码。ingFang SC", "Hiragino Sans GB", "Microsoft YaHei UI", "Microsoft YaHei", Arial, sans-serif;font-size: 15px;letter-spacing: 0.1em;">Github地址：https://github.com/promptslab/PromptifyingFang SC", "Hiragino Sans GB", "Microsoft YaHei UI", "Microsoft YaHei", Arial, sans-serif;font-size: 15px;letter-spacing: 0.1em;">本文将通过简单示例，带你了解Promptify为什么能成为 NLP 工具链中的“呼吸一口新鲜空气”。ingFang SC", "Hiragino Sans GB", "Microsoft YaHei UI", "Microsoft YaHei", Arial, sans-serif;font-size: 15px;letter-spacing: 0.1em;">欢迎大家关注公众号：AI大模型观察站，谢谢啦~~~~~ingFang SC", "Hiragino Sans GB", "Microsoft YaHei UI", "Microsoft YaHei", Arial, sans-serif;font-size: 15px;letter-spacing: 0.1em;">
ingFang SC", "Hiragino Sans GB", "Microsoft YaHei UI", "Microsoft YaHei", Arial, sans-serif;font-size: 1.2em;display: table;border-bottom: 1px solid rgb(248, 57, 41);">Promptify 是什么？ingFang SC", "Hiragino Sans GB", "Microsoft YaHei UI", "Microsoft YaHei", Arial, sans-serif;font-size: 15px;letter-spacing: 0.1em;">假设你有一段文本，比如一份小说片段，想提取关键词、进行分类、生成问题。ingFang SC", "Hiragino Sans GB", "Microsoft YaHei UI", "Microsoft YaHei", Arial, sans-serif;font-size: 15px;letter-spacing: 0.1em;">通常你得构造复杂的 prompt，反复尝试才能让 LLM 给出合适结果。ingFang SC", "Hiragino Sans GB", "Microsoft YaHei UI", "Microsoft YaHei", Arial, sans-serif;font-size: 15px;letter-spacing: 0.1em;">Promptify彻底改变了这一流程。ingFang SC", "Hiragino Sans GB", "Microsoft YaHei UI", "Microsoft YaHei", Arial, sans-serif;font-size: 15px;letter-spacing: 0.1em;">它是一个 Python 库，核心由三部分组成：•✅Prompter：用于构建 prompt（支持内置或自定义模板）•✅LLM 接口：支持 OpenAI、PaLM、Hugging Face 等多种模型•✅Pipeline：自动将文本输入 → prompt → LLM → 输出打通 无论是关键词提取、还是生成读书问题，Promptify都能轻松搞定。
安装方式使用 pip 安装： 或安装最新 GitHub 版本： pip3installgit+https://github.com/promptslab/Promptify.git 使用前需要准备 LLM 的 API Key（如 OpenAI、DeepSeek等）。
使用示例✅ 示例 1：提取医学实体（NER）from promptify importPrompter,OpenAI,Pipeline
sentence ="""The patient is a 93-year-old female with a medical history of chronic right hip pain, osteoporosis, hypertension, depression, and chronic atrial fibrillation admitted for evaluation and management of severe nausea and vomiting and urinary tract infection"""
model =OpenAI("your_api_key_here")prompter =Prompter('ner.jinja')pipe =Pipeline(prompter, model)result = pipe.fit(sentence, domain="medical", labels=None)
print(result)
输出结果如下： [{"E":"93-year-old","T":"Age"},{"E":"chronicrighthippain","T":"MedicalCondition"},{"E":"osteoporosis","T":"MedicalCondition"},{"E":"hypertension","T":"MedicalCondition"},{"E":"depression","T":"MedicalCondition"},{"E":"chronicatrialfibrillation","T":"MedicalCondition"},{"E":"severenauseaandvomiting","T":"Symptom"},{"E":"urinarytractinfection","T":"MedicalCondition"},{"Branch":"InternalMedicine","Group":"Geriatrics"}]👉 整理干净的结构化输出，准确分类，还能归属到临床科室。节省大量人工标注时间。
✅ 示例 2：多标签医学分类from promptify importOpenAI,Prompter
sentence ="""The patient is a 93-year-old female with a medical history of chronic right hip pain, osteoporosis, hypertension, depression, and chronic atrial fibrillation admitted for evaluation and management of severe nausea and vomiting and urinary tract infection"""
model =OpenAI("your_api_key_here")nlp_prompter =Prompter(model)result = nlp_prompter.fit('multilabel_classification.jinja', domain='medical', text_input=sentence)
print(result)
输出如下： [{'1':'Medicine','2':'Osteoporosis','3':'Hypertension','4':'Depression','5':'Atrialfibrillation','6':'Nauseaandvomiting','7':'Urinarytractinfection','branch':'Health','group':'Clinicalmedicine','mainclass':'Health'}]👉 非常适合做医疗知识图谱、自动病例标签系统等。
✅ 示例 3：生成阅读理解题目from promptify importOpenAI,Prompter
sentence ="""The rabbit-hole went straight on like a tunnel for some way, and then dipped suddenly down, so suddenly that Alice had not a moment to think about stopping herself before she found herself falling down a very deep well."""
model =OpenAI("your_api_key_here")nlp_prompter =Prompter(model)result = nlp_prompter.fit('qa_gen.jinja', domain='story_writing', text_input=sentence)
print(result)
输出结果： [{'A':'Alicefoundherselffallingdownaverydeepwell.','Q':'WhathappenedwhenAlicewentdowntherabbit-hole?'},{'A':'Verydeep.','Q':'Howdeepwasthewell?'},{'A':'No,shedidnothaveamomenttothink.','Q':'DidAlicehavetimetothinkaboutstoppingherself?'},{'A':'Itwentstraightonlikeatunnel.','Q':'Whatdirectiondidtherabbit-holego?'},{'A':'No,shedidnotexpectit.','Q':'DidAliceexpecttofalldownawell?'}]👉 这些问答题可以直接拿去做英文阅读理解测验，省心又省力！
为什么我推荐 Promptify？作为一个在资深程序员（已经写了十多年的代码），我对工具的要求是“节省脑细胞 + 效果可控”。 Promptify做到了这几点： ✅ 节省脑力：告别 prompt 拼命调试 ✅ 模板灵活：支持自定义任务模版 ✅ 多模型兼容：OpenAI、Hugging Face 都能跑 ✅ 任务多样：从医学到创意写作都能驾驭 ✅ 快速上手：几行代码就能跑结果
结语Promptify 是所有在 NLP 路上摸索的开发者的贴心助手。无论你做的是实体提取、文本分类、还是生成问题，它都能一站式搞定。 推荐给： •数据科学家•医疗 NLP 工程师•教育/创作者•AI 初学者
小伙伴们，可以尝试下，按照你工作、生活中所使用的提示词，把这些都管理起来，作为自己的资源。 |
