解析错误发生时如何重试

虽然在有些情况下，仅通过查看输出就可以修复任何解析错误，但在其他情况下则不行。一个例子是当输出不仅格式不正确，而且部分完成时。考虑以下示例。

from langchain.output_parsers import OutputFixingParser
from langchain_core.exceptions import OutputParserException
from langchain_core.output_parsers import PydanticOutputParser
from langchain_core.prompts import PromptTemplate
from langchain_openai import ChatOpenAI, OpenAI
from pydantic import BaseModel, Field

template = """Based on the user question, provide an Action and Action Input for what step should be taken.
{format_instructions}
Question: {query}
Response:"""


class Action(BaseModel):
    action: str = Field(description="action to take")
    action_input: str = Field(description="input to the action")


parser = PydanticOutputParser(pydantic_object=Action)

prompt = PromptTemplate(
    template="Answer the user query.\n{format_instructions}\n{query}\n",
    input_variables=["query"],
    partial_variables={"format_instructions": parser.get_format_instructions()},
)

prompt_value = prompt.format_prompt(query="who is leo di caprios gf?")

bad_response = '{"action": "search"}'

如果我们尝试直接解析这个响应，我们会得到一个错误：

try:
    parser.parse(bad_response)
except OutputParserException as e:
    print(e)

Failed to parse Action from completion {"action": "search"}. Got: 1 validation error for Action
action_input
  Field required [type=missing, input_value={'action': 'search'}, input_type=dict]
    For further information visit https://errors.pydantic.dev/2.9/v/missing
For troubleshooting, visit: https://python.langchain.com/docs/troubleshooting/errors/OUTPUT_PARSING_FAILURE

如果我们尝试使用OutputFixingParser来修复这个错误，它会感到困惑——也就是说，它不知道实际要为操作输入什么。

fix_parser = OutputFixingParser.from_llm(parser=parser, llm=ChatOpenAI())

fix_parser.parse(bad_response)

Action(action='search', action_input='input')

相反，我们可以使用RetryOutputParser，它将提示（以及原始输出）传递进去，以再次尝试获得更好的响应。

from langchain.output_parsers import RetryOutputParser

API Reference:RetryOutputParser

retry_parser = RetryOutputParser.from_llm(parser=parser, llm=OpenAI(temperature=0))

retry_parser.parse_with_prompt(bad_response, prompt_value)

Action(action='search', action_input='leo di caprio girlfriend')

我们还可以轻松地添加RetryOutputParser，通过一个自定义链将原始的LLM/ChatModel输出转换为更可用的格式。

from langchain_core.runnables import RunnableLambda, RunnableParallel

completion_chain = prompt | OpenAI(temperature=0)

main_chain = RunnableParallel(
    completion=completion_chain, prompt_value=prompt
) | RunnableLambda(lambda x: retry_parser.parse_with_prompt(**x))


main_chain.invoke({"query": "who is leo di caprios gf?"})

API Reference:RunnableLambda | RunnableParallel

Action(action='search', action_input='leo di caprio girlfriend')

查找RetryOutputParser的API文档。

这个页面有帮助吗？