如何使用输出解析器将LLM响应解析为结构化格式
语言模型输出文本。但有时您希望获得比纯文本更多的结构化信息。虽然一些模型提供商支持内置方式返回结构化输出,但并非所有提供商都支持。
Output parsers 是帮助结构化语言模型响应的类。输出解析器必须实现两个主要方法:
- "获取格式指令":一种方法,返回一个字符串,包含关于语言模型输出应如何格式化的说明。
- "Parse": 一种方法,它接收一个字符串(假设是语言模型的响应)并将其解析为某种结构。
然后是一个可选的:
- "使用提示解析":一种方法,它接收一个字符串(假设是语言模型的响应)和一个提示(假设是生成该响应的提示),并将其解析为某种结构。提示主要是为了在OutputParser希望以某种方式重试或修复输出时提供,并且需要从提示中获取信息来执行此操作。
开始使用
下面我们将介绍主要的输出解析器类型,PydanticOutputParser
。
from langchain_core.output_parsers import PydanticOutputParser
from langchain_core.prompts import PromptTemplate
from langchain_openai import OpenAI
from pydantic import BaseModel, Field, model_validator
model = OpenAI(model_name="gpt-3.5-turbo-instruct", temperature=0.0)
# 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")
# You can add custom validation logic easily with Pydantic.
@model_validator(mode="before")
@classmethod
def question_ends_with_question_mark(cls, values: dict) -> dict:
setup = values.get("setup")
if setup and setup[-1] != "?":
raise ValueError("Badly formed question!")
return values
# Set up a parser + inject instructions into the prompt template.
parser = PydanticOutputParser(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()},
)
# And a query intended to prompt a language model to populate the data structure.
prompt_and_model = prompt | model
output = prompt_and_model.invoke({"query": "Tell me a joke."})
parser.invoke(output)
Joke(setup='Why did the tomato turn red?', punchline='Because it saw the salad dressing!')
LCEL
输出解析器实现了Runnable接口,这是LangChain表达式语言(LCEL)的基本构建块。这意味着它们支持invoke
、ainvoke
、stream
、astream
、batch
、abatch
、astream_log
调用。
输出解析器接受字符串或BaseMessage
作为输入,并可以返回任意类型。
parser.invoke(output)
Joke(setup='Why did the tomato turn red?', punchline='Because it saw the salad dressing!')
除了手动调用解析器,我们也可以将其添加到我们的Runnable
序列中:
chain = prompt | model | parser
chain.invoke({"query": "Tell me a joke."})
Joke(setup='Why did the tomato turn red?', punchline='Because it saw the salad dressing!')
虽然所有解析器都支持流式接口,但只有某些解析器能够通过部分解析的对象进行流式处理,因为这高度依赖于输出类型。无法构建部分对象的解析器将简单地生成完全解析的输出。
例如,SimpleJsonOutputParser
可以流式处理部分输出:
from langchain.output_parsers.json import SimpleJsonOutputParser
json_prompt = PromptTemplate.from_template(
"Return a JSON object with an `answer` key that answers the following question: {question}"
)
json_parser = SimpleJsonOutputParser()
json_chain = json_prompt | model | json_parser
API Reference:SimpleJsonOutputParser
list(json_chain.stream({"question": "Who invented the microscope?"}))
[{},
{'answer': ''},
{'answer': 'Ant'},
{'answer': 'Anton'},
{'answer': 'Antonie'},
{'answer': 'Antonie van'},
{'answer': 'Antonie van Lee'},
{'answer': 'Antonie van Leeu'},
{'answer': 'Antonie van Leeuwen'},
{'answer': 'Antonie van Leeuwenho'},
{'answer': 'Antonie van Leeuwenhoek'}]
同样地,对于 PydanticOutputParser
:
list(chain.stream({"query": "Tell me a joke."}))
[Joke(setup='Why did the tomato turn red?', punchline=''),
Joke(setup='Why did the tomato turn red?', punchline='Because'),
Joke(setup='Why did the tomato turn red?', punchline='Because it'),
Joke(setup='Why did the tomato turn red?', punchline='Because it saw'),
Joke(setup='Why did the tomato turn red?', punchline='Because it saw the'),
Joke(setup='Why did the tomato turn red?', punchline='Because it saw the salad'),
Joke(setup='Why did the tomato turn red?', punchline='Because it saw the salad dressing'),
Joke(setup='Why did the tomato turn red?', punchline='Because it saw the salad dressing!')]