langchain里的prompt设计

三个要素：
1. 指令
2. 少样本比如的调集
3. 问题

模版格局：PromptTemplate默认用python字符串供给模版，也能够经过PromptTemplate的template_format参数替换模版言语

# Make sure jinja2 is installed before running this
//jinja2是python模板言语，参数语法和字符串不一致，是双括号，字符串是单括号
jinja2_template = "Tell me a {{ adjective }} joke about {{ content }}"
prompt_template = PromptTemplate.from_template(template=jinja2_template, template_format="jinja2")
prompt_template.format(adjective="funny", content="chickens")
# -> Tell me a funny joke about chickens.

模版的序列化：支持加载json文件、yaml文件 获取到Template，
json文件或许yaml文件中存储模板信息，
调用template的中心语法：

load_prompt("xxx文件地址")

零样本练习的template

1. 从json文件加载,
   1. json文件内容，

   {
       "_type": "prompt",//prompt类型
       "input_variables": ["adjective", "content"],//参数称号
       "template": "Tell me a {adjective} joke about {content}."//prompt Template
   }
   

   2. python文件内容

   from langchain.prompts import load_prompt
   prompt = load_prompt("simple_prompt.json")
   print(prompt.format(adjective="funny", content="chickens"))
   

2. 经过json读取外部文件加载
   1. txt文件内容，存储 prompt Template

   Tell me a {adjective} joke about {content}.
   

   2. json文件内容

   {
   "_type": "prompt",//prompt类型
   "input_variables": ["adjective", "content"],//参数称号
   "template_path": "/Users/xxx/demo.txt"//prompt Template的文件地址
    }
   

   3. python文件内容

   prompt = load_prompt("/Users/xxx/demo.json")
   print(prompt.format(adjective="funny", content="chickens"))
   

少样本练习的template

1. 样本数据文件+template文件：样本数据放在独自的文件里，经过json文件去读取 样本数据文件+template文件

   1. json文件

   {
       "_type": "few_shot",//少样本练习类型
       "input_variables": ["adjective"],//参数称号
       "prefix": "Write antonyms for the following words.",//前缀，一般是指令
       "example_prompt": { //样本数据
           "_type": "prompt",//样本数据类型是文本
           "input_variables": ["input", "output"],//样本数据中的输入参数
           "template": "Input: {input}\nOutput: {output}"//样本数据的模板
       },
       "examples": "/Users/xxx/examples.json",//样本数据的来历文件地址
       "suffix": "Input: {adjective}\nOutput:"//后缀，即问题
       }
   

   2. 样本数据文件

   [
   {"input": "happy", "output": "sad"},
   {"input": "tall", "output": "short"}
   ]
   

   3. 调用template

prompt = load_prompt("/Users/xxx/few_shot_prompt.json")
print(prompt.format(adjective="funny"))

2. template文件：样本数据直接放在充当template装备项的json文件里,中心修改是examples装备项，

   1. json文件

   {
       "_type": "few_shot",//少样本练习类型
       "input_variables": ["adjective"],//参数称号
       "prefix": "Write antonyms for the following words.",//前缀，一般是指令
       "example_prompt": { //样本数据
       "_type": "prompt",//样本数据类型是文本
       "input_variables": ["input", "output"],//样本数据中的输入参数
       "template": "Input: {input}\nOutput: {output}"//样本数据的模板
   },
       "examples": [
           {"input": "happy", "output": "sad"},
           {"input": "tall", "output": "short"}
           ],//样本数据
       "suffix": "Input: {adjective}\nOutput:"//后缀，即问题
   }
   

   2. 调用template

       prompt = load_prompt("/Users/xxx/few_shot_prompt_example_in.json")
       print(prompt.format(adjective="funny"))
   

3. template文件+样本数据template文件+样本数据：样本也分割成template+数据

   1. 样本数据文件

   [
       {"input": "happy", "output": "sad"},
       {"input": "tall", "output": "short"}
   ]
   

   2. 样本template

   {
       "_type": "prompt",
       "input_variables": ["input", "output"],
       "template": "Input: {input}\nOutput: {output}" 
   }
   

   3. template地点的json文件

   {
       "_type": "few_shot",
   "input_variables": ["adjective"],
       "prefix": "Write antonyms for the following words.",
       //指定样本数据模板的文件方位
       "example_prompt_path": "/Users/xxx/few_shot_prompt.json",
       //指定样本数据的文件方位
       "examples": "/Users/xxx/examples.json",
       "suffix": "Input: {adjective}\nOutput:"
   }
   

4. 调用template

   在template里加上解析输入的prompt以及输出格局

   1. template文件

   {
       "input_variables": [
       "question",
       "student_answer"
   ],
       "output_parser": {
       "regex": "(.*?)\\nScore: (.*)",
       "output_keys": [
           "answer",
           "score"
       ],
       "default_output_key": null,
       "_type": "regex_parser"
   },
   "partial_variables": {},
   "template": "Given the following question and student answer, provide a correct answer and score the student answer.\nQuestion: {question}\nStudent Answer: {student_answer}\nCorrect Answer:",
   "template_format": "f-string",
   "validate_template": true,
   "_type": "prompt"
   }
   

   2. 调用template

   prompt = load_prompt("prompt_with_output_parser.json")
   prompt.output_parser.parse("George Washington was born in 1732 and died in 1799.\nScore: 1/2")
   

   输出：
   {‘answer’: ‘George Washington was born in 1732 and died in 1799.’,
   ‘score’: ‘1/2’}

StringPromptTemplate：自定义一个template模板

1. 确定input_variables特点值
2. 完成format办法，确定template格局

import inspect
def get_source_code(function_name):
    # Get the source code of the function
    return inspect.getsource(function_name)

from langchain.prompts import StringPromptTemplate
from pydantic import BaseModel, validator
class FunctionExplainerPromptTemplate(StringPromptTemplate, BaseModel):
    """ A custom prompt template that takes in the function name as input, and formats the prompt template to provide the source code of the function. """
### 确定input_variables特点值
    @validator("input_variables")
    def validate_input_variables(cls, v):
        """ Validate that the input variables are correct. """
        if len(v) != 1 or "function_name" not in v:
            raise ValueError("function_name must be the only input_variable.")
        return v
### 确定template格局
    def format(self, **kwargs) -> str:
        # Get the source code of the function
        source_code = get_source_code(kwargs["function_name"])
        # Generate the prompt to be sent to the language model
        prompt = f"""
        Given the function name and source code, generate an English language explanation of the function.
        Function Name: {kwargs["function_name"].__name__}
        Source Code:
        {source_code}
        Explanation:
        """
        return prompt
    def _prompt_type(self):
        return "function-explainer"
fn_explainer = FunctionExplainerPromptTemplate(input_variables=["function_name"])
# Generate a prompt for the function "get_source_code"
prompt = fn_explainer.format(function_name=get_source_code)
print(prompt)

输出：
Given the function name and source code, generate an English language explanation of the function.
Function Name: get_source_code
Source Code:
def get_source_code(function_name):
return inspect.getsource(function_name)
Explanation: