RAG必备知识：OpenAI官宣结构化输出｜结构化输出工具大汇总

from pydantic import BaseModelfrom openai import OpenAI
client = OpenAI()
class Step(BaseModel):explanation: stroutput: str
class MathReasoning(BaseModel):steps: list[Step]final_answer: str
completion = client.beta.chat.completions.parse(model="gpt-4o-2024-08-06",messages=[{"role": "system", "content": "You are a helpful math tutor. Guide the user through the solution step by step."},{"role": "user", "content": "how can I solve 8x + 7 = -23"}],response_format=MathReasoning,)
math_reasoning = completion.choices[0].message.parsed

{"steps": [{"explanation": "Start with the equation 8x + 7 = -23.","output": "8x + 7 = -23"},{"explanation": "Subtract 7 from both sides to isolate the term with the variable.","output": "8x = -23 - 7"},{"explanation": "Simplify the right side of the equation.","output": "8x = -30"},{"explanation": "Divide both sides by 8 to solve for x.","output": "x = -30 / 8"},{"explanation": "Simplify the fraction.","output": "x = -15 / 4"}],"final_answer": "x = -15 / 4"}

from pydantic import BaseModelfrom openai import OpenAI
client = OpenAI()
class ResearchPaperExtraction(BaseModel):title: strauthors: list[str]abstract: strkeywords: list[str]
completion = client.beta.chat.completions.parse(model="gpt-4o-2024-08-06",messages=[{"role": "system", "content": "You are an expert at structured data extraction. You will be given unstructured text from a research paper and should convert it into the given structure."},{"role": "user", "content": "..."}],response_format=ResearchPaperExtraction,)
research_paper = completion.choices[0].message.parsed

{"title": "Application of Quantum Algorithms in Interstellar Navigation: A New Frontier","authors": ["Dr. Stella Voyager","Dr. Nova Star","Dr. Lyra Hunter"],"abstract": "This paper investigates the utilization of quantum algorithms to improve interstellar navigation systems. By leveraging quantum superposition and entanglement, our proposed navigation system can calculate optimal travel paths through space-time anomalies more efficiently than classical methods. Experimental simulations suggest a significant reduction in travel time and fuel consumption for interstellar missions.","keywords": ["Quantum algorithms","interstellar navigation","space-time anomalies","quantum superposition","quantum entanglement","space travel"]}

from typing import Listfrom langchain.prompts import PromptTemplatefrom langchain_community.chat_models import ChatOpenAIfrom langchain_core.output_parsers import JsonOutputParserfrom langchain_core.pydantic_v1 import BaseModel, Field
model = ChatOpenAI(temperature=0)
# 定义所需的数据结构。class Joke(BaseModel):setup: str = Field(description="问题以设置笑话")punchline: str = Field(description="回答以解决笑话")
# 以提示模型填充数据结构的查询意图。joke_query = "Tell me a joke."
# 设置解析器+将说明注入提示模板。parser = JsonOutputParser(pydantic_object=Joke)
prompt = PromptTemplate(template="回答用户的查询。\n{format_instructions}\n{query}\n",input_variables=["query"],partial_variables={"format_instructions": parser.get_format_instructions()},)
chain = prompt | model | parser
chain.invoke({"query": joke_query})

from langchain.output_parsers import CommaSeparatedListOutputParserfrom langchain.prompts import PromptTemplatefrom langchain_community.chat_models import ChatOpenAI
output_parser = CommaSeparatedListOutputParser()
format_instructions = output_parser.get_format_instructions()prompt = PromptTemplate(template="List five {subject}.\n{format_instructions}",input_variables=["subject"],partial_variables={"format_instructions": format_instructions})
model = OpenAI(temperature=0)
_input = prompt.format(subject="ice cream flavors")output = model(_input)
result = output_parser.parse(output)
# 输出：# ['Vanilla', 'Chocolate', 'Strawberry', 'Mint Chocolate Chip', 'Cookies and Cream']

from langchain_community.chat_models import ChatOpenAIfrom langchain_community.utils.openai_functions import (convert_pydantic_to_openai_function,)from langchain_core.prompts import ChatPromptTemplatefrom langchain_core.pydantic_v1 import BaseModel, Field, validator
class Joke(BaseModel):setup: str = Field(description="问题以设置笑话")punchline: str = Field(description="回答以解决笑话")
openai_functions = [convert_pydantic_to_openai_function(Joke)]
model = ChatOpenAI(temperature=0)
prompt = ChatPromptTemplate.from_messages([("system", "You are a helpful assistant"), ("user", "{input}")])

from typing import List
from langchain.output_parsers import PydanticOutputParserfrom langchain.prompts import PromptTemplatefrom langchain_community.chat_models import ChatOpenAIfrom langchain_core.pydantic_v1 import BaseModel, Field, validator

model = ChatOpenAI(temperature=0)

# 定义你期望的数据结构。class Joke(BaseModel):setup: str = Field(description="设立笑话的问题")punchline: str = Field(description="解决笑话的答案")
# 你可以轻松地用Pydantic添加自定义验证逻辑。@validator("setup")def question_ends_with_question_mark(cls, field):if field[-1] != "?":raise ValueError("问题格式不正确！")return field

# 并且一个旨在提示语言模型填充数据结构的查询。joke_query = "给我讲个笑话。"
# 设置解析器 + 将指令注入提示模板。parser = PydanticOutputParser(pydantic_object=Joke)
prompt = PromptTemplate(template="回答用户查询。\n{format_instructions}\n{query}\n",input_variables=["query"],partial_variables={"format_instructions": parser.get_format_instructions()},)
chain = prompt | model | parser
chain.invoke({"query": joke_query})