Skip to main content
Open In Colab在 GitHub 上打开

如何解析 JSON 输出

先决条件

本指南假定您熟悉以下概念：

虽然一些模型提供程序支持返回结构化输出的内置方法，但并非所有模型提供程序都支持。我们可以使用输出解析器来帮助用户通过提示符指定任意 JSON 架构，查询模型以获取符合该架构的输出，最后将该架构解析为 JSON。

注意

请记住，大型语言模型是泄漏的抽象！您必须使用具有足够容量的 LLM 来生成格式正确的 JSON。

这JsonOutputParser是一个内置选项，用于提示并解析 JSON 输出。虽然它在功能上与PydanticOutputParser，它还支持流回部分 JSON 对象。

下面是一个示例，说明如何将其与 Pydantic 一起使用以方便地声明预期的模式：

%pip install -qU langchain langchain-openai

import os
from getpass import getpass

if "OPENAI_API_KEY" not in os.environ:
    os.environ["OPENAI_API_KEY"] = getpass()
from langchain_core.output_parsers import JsonOutputParser
from langchain_core.prompts import PromptTemplate
from langchain_openai import ChatOpenAI
from pydantic import BaseModel, Field

model = ChatOpenAI(temperature=0)


# Define your desired data structure.
class Joke(BaseModel):
    setup: str = Field(description="question to set up a joke")
    punchline: str = Field(description="answer to resolve the joke")


# And a query intented to prompt a language model to populate the data structure.
joke_query = "Tell me a joke."

# Set up a parser + inject instructions into the prompt template.
parser = JsonOutputParser(pydantic_object=Joke)

prompt = PromptTemplate(
    template="Answer the user query.\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})
{'setup': "Why couldn't the bicycle stand up by itself?",
 'punchline': 'Because it was two tired!'}

请注意，我们正在传递format_instructions从解析器直接进入提示符。您可以并且应该尝试在 Prompt 的其他部分添加自己的格式提示，以增强或替换默认说明：

parser.get_format_instructions()
'The output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {"properties": {"foo": {"title": "Foo", "description": "a list of strings", "type": "array", "items": {"type": "string"}}}, "required": ["foo"]}\nthe object {"foo": ["bar", "baz"]} is a well-formatted instance of the schema. The object {"properties": {"foo": ["bar", "baz"]}} is not well-formatted.\n\nHere is the output schema:\n\`\`\`\n{"properties": {"setup": {"title": "Setup", "description": "question to set up a joke", "type": "string"}, "punchline": {"title": "Punchline", "description": "answer to resolve the joke", "type": "string"}}, "required": ["setup", "punchline"]}\n\`\`\`'

流

如上所述，JsonOutputParser和PydanticOutputParser是JsonOutputParserOutput Parser 支持流式处理部分块。这是它的样子：

for s in chain.stream({"query": joke_query}):
    print(s)
{}
{'setup': ''}
{'setup': 'Why'}
{'setup': 'Why couldn'}
{'setup': "Why couldn't"}
{'setup': "Why couldn't the"}
{'setup': "Why couldn't the bicycle"}
{'setup': "Why couldn't the bicycle stand"}
{'setup': "Why couldn't the bicycle stand up"}
{'setup': "Why couldn't the bicycle stand up by"}
{'setup': "Why couldn't the bicycle stand up by itself"}
{'setup': "Why couldn't the bicycle stand up by itself?"}
{'setup': "Why couldn't the bicycle stand up by itself?", 'punchline': ''}
{'setup': "Why couldn't the bicycle stand up by itself?", 'punchline': 'Because'}
{'setup': "Why couldn't the bicycle stand up by itself?", 'punchline': 'Because it'}
{'setup': "Why couldn't the bicycle stand up by itself?", 'punchline': 'Because it was'}
{'setup': "Why couldn't the bicycle stand up by itself?", 'punchline': 'Because it was two'}
{'setup': "Why couldn't the bicycle stand up by itself?", 'punchline': 'Because it was two tired'}
{'setup': "Why couldn't the bicycle stand up by itself?", 'punchline': 'Because it was two tired!'}

没有 Pydantic

您还可以使用JsonOutputParser没有 Pydantic。这将提示模型返回 JSON，但不提供有关架构应是什么的详细信息。

joke_query = "Tell me a joke."

parser = JsonOutputParser()

prompt = PromptTemplate(
    template="Answer the user query.\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})
{'response': "Sure! Here's a joke for you: Why couldn't the bicycle stand up by itself? Because it was two tired!"}

后续步骤

您现在已经了解了提示模型返回结构化 JSON 的一种方法。接下来，查看有关获取其他技术的结构化输出的更广泛指南。