跳到主要內容
Open In ColabOpen on GitHub

如何解析 XML 輸出

先決條件

本指南假設您熟悉以下概念

來自不同提供者的 LLM 通常具有不同的優勢，具體取決於它們訓練的特定資料。這也意味著有些可能在產生非 JSON 格式以外的輸出時「更好」且更可靠。

本指南向您展示如何使用 XMLOutputParser 來提示模型產生 XML 輸出，然後解析該輸出為可用的格式。

注意

請記住，大型語言模型是洩漏的抽象概念！您必須使用具有足夠容量的 LLM 來產生格式良好的 XML。

在以下範例中，我們使用 Anthropic 的 Claude-2 模型 (https://docs.anthropic.com/claude/docs)，這是一個針對 XML 標籤優化的模型。

%pip install -qU langchain langchain-anthropic

import os
from getpass import getpass

if "ANTHROPIC_API_KEY" not in os.environ:
    os.environ["ANTHROPIC_API_KEY"] = getpass()

讓我們從對模型的簡單請求開始。

from langchain_anthropic import ChatAnthropic
from langchain_core.output_parsers import XMLOutputParser
from langchain_core.prompts import PromptTemplate

model = ChatAnthropic(model="claude-2.1", max_tokens_to_sample=512, temperature=0.1)

actor_query = "Generate the shortened filmography for Tom Hanks."

output = model.invoke(
    f"""{actor_query}
Please enclose the movies in <movie></movie> tags"""
)

print(output.content)
Here is the shortened filmography for Tom Hanks, with movies enclosed in XML tags:

<movie>Splash</movie>
<movie>Big</movie>
<movie>A League of Their Own</movie>
<movie>Sleepless in Seattle</movie>
<movie>Forrest Gump</movie>
<movie>Toy Story</movie>
<movie>Apollo 13</movie>
<movie>Saving Private Ryan</movie>
<movie>Cast Away</movie>
<movie>The Da Vinci Code</movie>

實際上效果很好！但如果能將 XML 解析為更易於使用的格式就更好了。 我們可以使用 XMLOutputParser 來為提示新增預設格式指示，並將輸出的 XML 解析為字典

parser = XMLOutputParser()

# We will add these instructions to the prompt below
parser.get_format_instructions()
'The output should be formatted as a XML file.\n1. Output should conform to the tags below. \n2. If tags are not given, make them on your own.\n3. Remember to always open and close all the tags.\n\nAs an example, for the tags ["foo", "bar", "baz"]:\n1. String "<foo>\n   <bar>\n      <baz></baz>\n   </bar>\n</foo>" is a well-formatted instance of the schema. \n2. String "<foo>\n   <bar>\n   </foo>" is a badly-formatted instance.\n3. String "<foo>\n   <tag>\n   </tag>\n</foo>" is a badly-formatted instance.\n\nHere are the output tags:\n\`\`\`\nNone\n\`\`\`'
prompt = PromptTemplate(
    template="""{query}\n{format_instructions}""",
    input_variables=["query"],
    partial_variables={"format_instructions": parser.get_format_instructions()},
)

chain = prompt | model | parser

output = chain.invoke({"query": actor_query})
print(output)
{'filmography': [{'movie': [{'title': 'Big'}, {'year': '1988'}]}, {'movie': [{'title': 'Forrest Gump'}, {'year': '1994'}]}, {'movie': [{'title': 'Toy Story'}, {'year': '1995'}]}, {'movie': [{'title': 'Saving Private Ryan'}, {'year': '1998'}]}, {'movie': [{'title': 'Cast Away'}, {'year': '2000'}]}]}

我們還可以新增一些標籤，以根據我們的需求調整輸出。您可以而且應該實驗在提示的其他部分新增您自己的格式提示，以擴充或取代預設指示

parser = XMLOutputParser(tags=["movies", "actor", "film", "name", "genre"])

# We will add these instructions to the prompt below
parser.get_format_instructions()
'The output should be formatted as a XML file.\n1. Output should conform to the tags below. \n2. If tags are not given, make them on your own.\n3. Remember to always open and close all the tags.\n\nAs an example, for the tags ["foo", "bar", "baz"]:\n1. String "<foo>\n   <bar>\n      <baz></baz>\n   </bar>\n</foo>" is a well-formatted instance of the schema. \n2. String "<foo>\n   <bar>\n   </foo>" is a badly-formatted instance.\n3. String "<foo>\n   <tag>\n   </tag>\n</foo>" is a badly-formatted instance.\n\nHere are the output tags:\n\`\`\`\n[\'movies\', \'actor\', \'film\', \'name\', \'genre\']\n\`\`\`'
prompt = PromptTemplate(
    template="""{query}\n{format_instructions}""",
    input_variables=["query"],
    partial_variables={"format_instructions": parser.get_format_instructions()},
)


chain = prompt | model | parser

output = chain.invoke({"query": actor_query})

print(output)
{'movies': [{'actor': [{'name': 'Tom Hanks'}, {'film': [{'name': 'Forrest Gump'}, {'genre': 'Drama'}]}, {'film': [{'name': 'Cast Away'}, {'genre': 'Adventure'}]}, {'film': [{'name': 'Saving Private Ryan'}, {'genre': 'War'}]}]}]}

此輸出解析器也支援串流部分區塊。以下是一個範例

for s in chain.stream({"query": actor_query}):
    print(s)
{'movies': [{'actor': [{'name': 'Tom Hanks'}]}]}
{'movies': [{'actor': [{'film': [{'name': 'Forrest Gump'}]}]}]}
{'movies': [{'actor': [{'film': [{'genre': 'Drama'}]}]}]}
{'movies': [{'actor': [{'film': [{'name': 'Cast Away'}]}]}]}
{'movies': [{'actor': [{'film': [{'genre': 'Adventure'}]}]}]}
{'movies': [{'actor': [{'film': [{'name': 'Saving Private Ryan'}]}]}]}
{'movies': [{'actor': [{'film': [{'genre': 'War'}]}]}]}

下一步​

您現在已學習如何提示模型傳回 XML。接下來，查看關於取得結構化輸出的更廣泛指南，以了解其他相關技術。

此頁面是否有幫助？