结构化输出解析与验证
使用输出解析器和模式，要求 LLM 返回可靠的结构化数据；当模型生成格式错误的输出时，对其进行验证或重试。
结构化输出解析与验证 是 CoddyKit 上的免费 AI Agents with LangChain & Autonomous Workflows 课时。 这是第 4 节课，共 4 节。 你可以在下方免费阅读本课时的完整内容 — 然后在浏览器中使用内置代码编辑器和全天候 AI 导师进行实践。 这是 AI Agents with LangChain & Autonomous Workflows 学习路径的一部分，你的进度在网页和 CoddyKit 应用中同步。 AI Agents with LangChain & Autonomous Workflows 课程共包含 4 节课。
本课时的部分内容尚未翻译，以英文显示。
The Problem with Free Text
LLMs return prose by default, but your code needs structured data: JSON, a list, a typed object. Parsing free text with regex is fragile.
This lesson covers getting reliable structured output from models.
Asking for a Format
The first step is simply instructing the model to produce a specific format. But instruction alone is not enough; models drift, add prose, or wrap output in markdown.
prompt = 'Extract name and age as JSON: "Lena is 30"'
# model might reply: 'Sure! {"name":"Lena","age":30}'Output Parsers
LangChain output parsers do two jobs: they generate format instructions to inject into the prompt, and they parse the model's response back into a structured object.
from langchain.output_parsers import CommaSeparatedListOutputParser
parser = CommaSeparatedListOutputParser()
print(parser.get_format_instructions())Schema-Based Parsing
Define the shape you want with a schema (e.g. a Pydantic model). The parser turns it into instructions and validates the result against the fields and types.
from pydantic import BaseModel
class Person(BaseModel):
name: str
age: intInjecting Format Instructions
Add the parser's instructions into your prompt template so the model knows exactly what structure to emit.
template = 'Extract info.\n{format_instructions}\nText: {text}'
prompt = template.format(
format_instructions=parser.get_format_instructions(),
text='Lena is 30')Parsing the Response
After the model replies, the parser converts the text into your typed object, raising an error if it does not match the schema.
result = parser.parse(model_output)
print(result.name, result.age)Handling Malformed Output
Models occasionally produce invalid JSON. A retry/fixing parser detects the failure and asks the model to correct its own output, turning a hard crash into a recoverable step.
from langchain.output_parsers import RetryOutputParser
robust = RetryOutputParser.from_llm(parser=parser, llm=llm)Native JSON / Tool Modes
Many modern models support a JSON mode or function/tool calling that constrains output to valid structured data at the API level. When available, this is far more reliable than prompt instructions alone.
Validation Beyond Types
A value can be the right type but still wrong: a negative age, an empty required field. Add validators so business rules are enforced, not just the data shape.
if result.age < 0 or result.age > 130:
raise ValueError('age out of range')Why It Matters for Agents
Agents chain steps together, feeding one output into the next. If a step emits malformed data, the whole chain breaks. Structured, validated output is what makes multi-step agents dependable.
A Reliable Output Workflow
Putting it together:
- Define a schema for the data you need
- Inject format instructions into the prompt
- Prefer native JSON/tool mode when available
- Parse and validate, with a retry parser as a safety net
Quick Check
Test your understanding of structured output.
Recap
You learned to get reliable structured data from LLMs.
- Output parsers generate instructions and parse responses
- Schemas validate shape and types
- Retry parsers recover from malformed output
- Native JSON/tool modes are most reliable when available
用 AI 导师学习 AI Agents with LangChain & Autonomous Workflows — 免费
在浏览器中编写并运行真实代码，获得全天候 AI 导师的即时帮助，并在网页或应用中继续学习。
- 课程
- 12
- 课程
- 50
常见问题解答
「结构化输出解析与验证」课时是免费的吗？
是的 — 「结构化输出解析与验证」的完整文本可在网页上免费阅读。要进行交互式练习（内置代码编辑器和全天候 AI 导师）并解锁 AI Agents with LangChain & Autonomous Workflows 课程的其余内容，请升级到 CoddyKit PRO。 AI Agents with LangChain & Autonomous Workflows 课程共包含 4 节课。
「结构化输出解析与验证」这节课中我会学到什么？
使用输出解析器和模式，要求 LLM 返回可靠的结构化数据；当模型生成格式错误的输出时，对其进行验证或重试。 你通过在浏览器中直接运行的动手代码来练习 AI Agents with LangChain & Autonomous Workflows，全天候 AI 导师会在你学习这节课的过程中回答你的问题。
学习 AI Agents with LangChain & Autonomous Workflows 需要有经验吗？
无需任何先前经验。CoddyKit 上的 AI Agents with LangChain & Autonomous Workflows 课程适合初学者到高级学习者，你可以从这里开始或从头开始，按照自己的节奏学习。 这是第 4 节课，共 4 节。
「结构化输出解析与验证」课时需要多长时间？
大多数 CoddyKit 课程大约需要 5–10 分钟。每节课都很精短且互动，所以你能稳步进步，并在网页和应用中从离开的地方继续。
我能在这节 AI Agents with LangChain & Autonomous Workflows 课中编写并运行代码吗？
能。每节 AI Agents with LangChain & Autonomous Workflows 课都包含内置代码编辑器，你可以在浏览器中直接编写并运行真实代码，并获得即时 AI 反馈 — 无需本地设置。
此课程中的所有课时
- 高效提示词设计技术
- 将 LLM 与 LangChain 集成
- 管理模型参数与成本
- 结构化输出解析与验证