Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library
Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.
Quelldateien prüfen
Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich für eine Installation entscheiden.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library
# Base installation
pip install instructor
# With specific providers
pip install "instructor[anthropic]"# Anthropic Claude
pip install "instructor[openai]"# OpenAI
pip install "instructor[all]"# All providers
Quick Start
Basic Example: Extract User Data
import instructor
from pydantic import BaseModel
from anthropic import Anthropic
# Define output structureclassUser(BaseModel):
name: str
age: int
email: str# Create instructor client
client = instructor.from_anthropic(Anthropic())
# Extract structured data
user = client.messages.create(
model="claude-sonnet-4-5-20250929",
max_tokens=1024,
messages=[{
"role": "user",
"content": "John Doe is 30 years old. His email is john@example.com"
}],
response_model=User
)
(user.name)
(user.age)
(user.email)
print
# "John Doe"
print
# 30
print
# "john@example.com"
With OpenAI
from openai import OpenAI
client = instructor.from_openai(OpenAI())
user = client.chat.completions.create(
model="gpt-4o-mini",
response_model=User,
messages=[{"role": "user", "content": "Extract: Alice, 25, alice@email.com"}]
)
Core Concepts
1. Response Models (Pydantic)
Response models define the structure and validation rules for LLM outputs.
Basic Model
from pydantic import BaseModel, Field
classArticle(BaseModel):
title: str = Field(description="Article title")
author: str = Field(description="Author name")
word_count: int = Field(description="Number of words", gt=0)
tags: list[str] = Field(description="List of relevant tags")
article = client.messages.create(
model="claude-sonnet-4-5-20250929",
max_tokens=1024,
messages=[{
"role": "user",
"content": "Analyze this article: [article text]"
}],
response_model=Article
)
Benefits:
Type safety with Python type hints
Automatic validation (word_count > 0)
Self-documenting with Field descriptions
IDE autocomplete support
Nested Models
classAddress(BaseModel):
street: str
city: str
country: strclassPerson(BaseModel):
name: str
age: int
address: Address # Nested model
person = client.messages.create(
model="claude-sonnet-4-5-20250929",
max_tokens=1024,
messages=[{
"role": "user",
"content": "John lives at 123 Main St, Boston, USA"
}],
response_model=Person
)
print(person.address.city) # "Boston"
Optional Fields
from typing importOptionalclassProduct(BaseModel):
name: str
price: float
discount: Optional[float] = None# Optional
description: str = Field(default="No description") # Default value# LLM doesn't need to provide discount or description
Pydantic validates LLM outputs automatically. If validation fails, Instructor retries.
Built-in Validators
from pydantic import Field, EmailStr, HttpUrl
classContact(BaseModel):
name: str = Field(min_length=2, max_length=100)
age: int = Field(ge=0, le=120) # 0 <= age <= 120
email: EmailStr # Validates email format
website: HttpUrl # Validates URL format# If LLM provides invalid data, Instructor retries automatically
Custom Validators
from pydantic import field_validator
classEvent(BaseModel):
name: str
date: str
attendees: int @field_validator('date')defvalidate_date(cls, v):
"""Ensure date is in YYYY-MM-DD format."""import re
ifnot re.match(r'\d{4}-\d{2}-\d{2}', v):
raise ValueError('Date must be YYYY-MM-DD format')
return v
@field_validator('attendees')defvalidate_attendees(cls, v):
"""Ensure positive attendees."""if v < 1:
raise ValueError('Must have at least 1 attendee')
return v
Model-Level Validation
from pydantic import model_validator
classDateRange(BaseModel):
start_date: str
end_date: str @model_validator(mode='after')defcheck_dates(self):
"""Ensure end_date is after start_date."""from datetime import datetime
start = datetime.strptime(self.start_date, '%Y-%m-%d')
end = datetime.strptime(self.end_date, '%Y-%m-%d')
if end < start:
raise ValueError('end_date must be after start_date')
returnself
3. Automatic Retrying
Instructor retries automatically when validation fails, providing error feedback to the LLM.
# Retries up to 3 times if validation fails
user = client.messages.create(
model="claude-sonnet-4-5-20250929",
max_tokens=1024,
messages=[{
"role": "user",
"content": "Extract user from: John, age unknown"
}],
response_model=User,
max_retries=3# Default is 3
)
# If age can't be extracted, Instructor tells the LLM:# "Validation error: age - field required"# LLM tries again with better extraction
How it works:
LLM generates output
Pydantic validates
If invalid: Error message sent back to LLM
LLM tries again with error feedback
Repeats up to max_retries
4. Streaming
Stream partial results for real-time processing.
Streaming Partial Objects
from instructor import Partial
classStory(BaseModel):
title: str
content: str
tags: list[str]
# Stream partial updates as LLM generatesfor partial_story in client.messages.create_partial(
model="claude-sonnet-4-5-20250929",
max_tokens=1024,
messages=[{
"role": "user",
"content": "Write a short sci-fi story"
}],
response_model=Story
):
print(f"Title: {partial_story.title}")
print(f"Content so far: {partial_story.content[:100]}...")
# Update UI in real-time
Streaming Iterables
classTask(BaseModel):
title: str
priority: str# Stream list items as they're generated
tasks = client.messages.create_iterable(
model="claude-sonnet-4-5-20250929",
max_tokens=1024,
messages=[{
"role": "user",
"content": "Generate 10 project tasks"
}],
response_model=Task
)
for task in tasks:
print(f"- {task.title} ({task.priority})")
# Process each task as it arrives
Provider Configuration
Anthropic Claude
import instructor
from anthropic import Anthropic
client = instructor.from_anthropic(
Anthropic(api_key="your-api-key")
)
# Use with Claude models
response = client.messages.create(
model="claude-sonnet-4-5-20250929",
max_tokens=1024,
messages=[...],
response_model=YourModel
)
from openai import OpenAI
# Point to local Ollama server
client = instructor.from_openai(
OpenAI(
base_url="http://localhost:11434/v1",
api_key="ollama"# Required but ignored
),
mode=instructor.Mode.JSON
)
response = client.chat.completions.create(
model="llama3.1",
response_model=YourModel,
messages=[...]
)
Common Patterns
Pattern 1: Data Extraction from Text
classCompanyInfo(BaseModel):
name: str
founded_year: int
industry: str
employees: int
headquarters: str
text = """
Tesla, Inc. was founded in 2003. It operates in the automotive and energy
industry with approximately 140,000 employees. The company is headquartered
in Austin, Texas.
"""
company = client.messages.create(
model="claude-sonnet-4-5-20250929",
max_tokens=1024,
messages=[{
"role": "user",
"content": f"Extract company information from: {text}"
}],
response_model=CompanyInfo
)
classPerson(BaseModel):
name: str
role: strclassOrganization(BaseModel):
name: str
industry: strclassEntities(BaseModel):
people: list[Person]
organizations: list[Organization]
locations: list[str]
text = "Tim Cook, CEO of Apple, announced at the event in Cupertino..."
entities = client.messages.create(
model="claude-sonnet-4-5-20250929",
max_tokens=1024,
messages=[{
"role": "user",
"content": f"Extract all entities from: {text}"
}],
response_model=Entities
)
for person in entities.people:
print(f"{person.name} - {person.role}")
Pattern 4: Structured Analysis
classSentimentAnalysis(BaseModel):
overall_sentiment: Sentiment
positive_aspects: list[str]
negative_aspects: list[str]
suggestions: list[str]
score: float = Field(ge=-1.0, le=1.0)
review = "The product works well but setup was confusing..."
analysis = client.messages.create(
model="claude-sonnet-4-5-20250929",
max_tokens=1024,
messages=[{
"role": "user",
"content": f"Analyze this review: {review}"
}],
response_model=SentimentAnalysis
)
Pattern 5: Batch Processing
defextract_person(text: str) -> Person:
return client.messages.create(
model="claude-sonnet-4-5-20250929",
max_tokens=1024,
messages=[{
"role": "user",
"content": f"Extract person from: {text}"
}],
response_model=Person
)
texts = [
"John Doe is a 30-year-old engineer",
"Jane Smith, 25, works in marketing",
"Bob Johnson, age 40, software developer"
]
people = [extract_person(text) for text in texts]
Advanced Features
Union Types
from typing importUnionclassTextContent(BaseModel):
type: str = "text"
content: strclassImageContent(BaseModel):
type: str = "image"
url: HttpUrl
caption: strclassPost(BaseModel):
title: str
content: Union[TextContent, ImageContent] # Either type# LLM chooses appropriate type based on content
Dynamic Models
from pydantic import create_model
# Create model at runtime
DynamicUser = create_model(
'User',
name=(str, ...),
age=(int, Field(ge=0)),
email=(EmailStr, ...)
)
user = client.messages.create(
model="claude-sonnet-4-5-20250929",
max_tokens=1024,
messages=[...],
response_model=DynamicUser
)
Custom Modes
# For providers without native structured outputs
client = instructor.from_anthropic(
Anthropic(),
mode=instructor.Mode.JSON # JSON mode
)
# Available modes:# - Mode.ANTHROPIC_TOOLS (recommended for Claude)# - Mode.JSON (fallback)# - Mode.TOOLS (OpenAI tools)
Context Management
# Single-use clientwith instructor.from_anthropic(Anthropic()) as client:
result = client.messages.create(
model="claude-sonnet-4-5-20250929",
max_tokens=1024,
messages=[...],
response_model=YourModel
)
# Client closed automatically
Error Handling
Handling Validation Errors
from pydantic import ValidationError
try:
user = client.messages.create(
model="claude-sonnet-4-5-20250929",
max_tokens=1024,
messages=[...],
response_model=User,
max_retries=3
)
except ValidationError as e:
print(f"Failed after retries: {e}")
# Handle gracefullyexcept Exception as e:
print(f"API error: {e}")
