Home/LLM Function

One-shot LLM Calls

Make direct LLM calls with optional structured output. One function for any LLM task.

Quick Start

main.py

from connectonion import llm_do

answer = llm_do("What's 2+2?")
print(answer)

Python REPL

Interactive

>>> answer = llm_do("What's 2+2?")

>>> print(answer)

That's it! One function for any LLM task.

With Structured Output

main.py

from pydantic import BaseModel

class Analysis(BaseModel):
    sentiment: str
    confidence: float
    keywords: list[str]

result = llm_do(
    "I absolutely love this product! Best purchase ever!",
    output=Analysis
)
print(result.sentiment)
print(result.confidence)
print(result.keywords)

Python REPL

Interactive

>>> print(result.sentiment)

'positive'

>>> print(result.confidence)

0.98

>>> print(result.keywords)

['love', 'best', 'ever']

Real Examples

Extract Data from Text

main.py

from pydantic import BaseModel

class Invoice(BaseModel):
    invoice_number: str
    total_amount: float
    due_date: str

invoice_text = """
Invoice #INV-2024-001
Total: $1,234.56
Due: January 15, 2024
"""

invoice = llm_do(invoice_text, output=Invoice)
print(invoice.invoice_number)
print(invoice.total_amount)
print(invoice.due_date)

Python REPL

Interactive

>>> print(invoice.invoice_number)

'INV-2024-001'

>>> print(invoice.total_amount)

1234.56

>>> print(invoice.due_date)

'January 15, 2024'

Use Custom Prompts

main.py

# With inline prompt
translation = llm_do(
    "Hello world",
    prompt="You are a translator. Translate to Spanish only."
)
print(translation)

# With prompt file
summary = llm_do(
    "Long technical article about AI...",
    prompt="prompts/summarizer.md"  # Loads from file
)
print(summary)

Python REPL

Interactive

>>> print(translation)

'Hola mundo'

>>> print(summary)

'AI technology is rapidly advancing with breakthroughs in...'

Quick Analysis Tool

main.py

from connectonion import llm_do, Agent
from pydantic import BaseModel

def analyze_feedback(text: str) -> str:
    """Analyze customer feedback with structured output."""
    
    class FeedbackAnalysis(BaseModel):
        category: str  # bug, feature, praise, complaint
        priority: str  # high, medium, low
        summary: str
        action_required: bool
    
    analysis = llm_do(text, output=FeedbackAnalysis)
    
    if analysis.action_required:
        return f"🚨 {analysis.priority.upper()}: {analysis.summary}"
    return f"📝 {analysis.category}: {analysis.summary}"

# Test the function
result = analyze_feedback("The app crashes when I try to upload files!")
print(result)

# Use in an agent
agent = Agent("support", tools=[analyze_feedback])

Python REPL

Interactive

>>> result = analyze_feedback("The app crashes when I try to upload files!")

>>> print(result)

🚨 HIGH: Application crashes during file upload process

Parameters

Parameter	Type	Default	Description
`input`	str	required	The input text/question
`output`	BaseModel	None	Pydantic model for structured output
`prompt`	str\|Path	None	System prompt (string or file path)
`model`	str	"gpt-4o-mini"	OpenAI model to use
`temperature`	float	0.1	Randomness (0=deterministic, 2=creative)

What You Get

✅One-shot execution - Single LLM round, no loops

✅Type safety - Full IDE autocomplete with Pydantic

✅Flexible prompts - Inline strings or external files

✅Smart defaults - Fast model, low temperature

✅Clean errors - Clear messages when things go wrong

Common Patterns

Data Extraction

main.py

from pydantic import BaseModel

class Person(BaseModel):
    name: str
    age: int
    occupation: str

person = llm_do("John Doe, 30, software engineer", output=Person)
print(f"Name: {person.name}")
print(f"Age: {person.age}")
print(f"Job: {person.occupation}")

Python REPL

Interactive

>>> print(f"Name: {person.name}")

Name: John Doe

>>> print(f"Age: {person.age}")

Age: 30

>>> print(f"Job: {person.occupation}")

Job: software engineer

Quick Decisions

main.py

def check_urgency(message: str) -> bool:
    is_urgent = llm_do(f"Is this urgent? Reply yes/no: {message}")
    return "yes" in is_urgent.lower()

# Test with customer message
if check_urgency("Customer says: My server is down!"):
    print("🚨 Escalating to on-call team...")
else:
    print("📝 Added to regular queue")

Python REPL

Interactive

>>> if check_urgency("Customer says: My server is down!"):

... print("🚨 Escalating to on-call team...")

... else:

... print("📝 Added to regular queue")

🚨 Escalating to on-call team...

Format Conversion

main.py

from pydantic import BaseModel

class JSONData(BaseModel):
    data: dict

json_result = llm_do(
    "Convert to JSON: name=John age=30 city=NYC",
    output=JSONData
)
print(json_result.data)

Python REPL

Interactive

>>> print(json_result.data)

{'name': 'John', 'age': 30, 'city': 'NYC'}

Validation

main.py

def validate_sql(query: str) -> bool:
    result = llm_do(
        f"Is this valid SQL? Reply yes/no only: {query}",
        temperature=0  # Maximum consistency
    )
    return result.strip().lower() == "yes"

# Test queries
queries = [
    "SELECT * FROM users WHERE id = 1",
    "SLECT * FORM users"  # Typo
]

for q in queries:
    is_valid = validate_sql(q)
    print(f"{'✓' if is_valid else '✗'} {q[:30]}...")

Python REPL

Interactive

>>> for q in queries:

... is_valid = validate_sql(q)

... print(f"{'✓' if is_valid else '✗'} {q[:30]}...")

✓ SELECT * FROM users WHERE id...

✗ SLECT * FORM users...

Comparison with Agent

Feature	llm_do()	Agent()
Purpose	One-shot calls	Multi-step workflows
Tools	No	Yes
Iterations	Always 1	Up to max_iterations
State	Stateless	Maintains history
Best for	Quick tasks	Complex automation

main.py

from connectonion import llm_do, Agent

# Use llm_do() for simple tasks
answer = llm_do("What's the capital of France?")
print(f"Capital: {answer}")

# Use Agent for multi-step workflows
def search_population(city: str) -> int:
    # Simulated search function
    return 2_161_000 if city == "Paris" else 0

def calculate_density(population: int, area_km2: float) -> float:
    return population / area_km2

agent = Agent("assistant", tools=[search_population, calculate_density])
result = agent.input("Find Paris population and calculate density (area: 105 km²)")
print(f"Agent result: {result}")

Python REPL

Interactive

>>> print(f"Capital: {answer}")

Capital: Paris

>>> result = agent.input("Find Paris population and calculate density (area: 105 km²)")

>>> print(f"Agent result: {result}")

Agent result: The population density of Paris is approximately 20,580 people per km²

Tips

1.Use low temperature (0-0.3) for consistent results

2.Provide examples in your prompt for better accuracy

3.Use Pydantic models for anything structured

4.Cache prompts in files for reusability

Next Steps

Tools

Extend agents with custom tools

@xray Decorator

Debug your LLM calls

System Prompts

Learn about prompt management