How do you reliably get structured JSON output from LLMs, and what tools does LangChain provide?

Getting LLMs to reliably return structured data (not just text) is essential for applications that need to parse and act on model outputs. Three complementary approaches exist: prompt-level instructions, API-level enforcement (JSON mode / structured outputs), and library-level output parsers with validation and retry.

# ── Approach 1: OpenAI structured outputs (most reliable)
from pydantic import BaseModel, Field
from openai import OpenAI

client = OpenAI()

class JobPosting(BaseModel):
    company: str = Field(description='Company name')
    role: str    = Field(description='Job title')
    years_exp: int = Field(description='Years of experience required')
    skills: list[str] = Field(description='Required technical skills')

text = 'Acme Corp is hiring a senior ML engineer with 5+ years, Python, PyTorch.'

completion = client.beta.chat.completions.parse(
    model='gpt-4o',
    messages=[{'role': 'user', 'content': f'Extract info from: {text}'}],
    response_format=JobPosting,
)
job = completion.choices[0].message.parsed
print(type(job))       # <class '__main__.JobPosting'> — a real Pydantic model
print(job.company)     # Acme Corp
print(job.skills)      # ['Python', 'PyTorch']

# ── Approach 2: LangChain with_structured_output
from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate

llm = ChatOpenAI(model='gpt-4o')
structured_llm = llm.with_structured_output(JobPosting)  # wraps with schema

prompt = ChatPromptTemplate.from_template('Extract info from: {text}')
chain  = prompt | structured_llm

result = chain.invoke({'text': text})
print(result.company, result.years_exp)  # Acme Corp  5

# ── Approach 3: PydanticOutputParser with retry
from langchain_core.output_parsers import PydanticOutputParser
from langchain_core.prompts import ChatPromptTemplate

parser = PydanticOutputParser(pydantic_object=JobPosting)
prompt_with_format = ChatPromptTemplate.from_template(
    'Extract info from: {text}\n\n{format_instructions}'
).partial(format_instructions=parser.get_format_instructions())
chain2 = prompt_with_format | ChatOpenAI(model='gpt-4o-mini') | parser