wehub-resource-sync
97e91a83f3
Ruff / Ruff (push) Has been cancelled
Test / Core Tests (push) Has been cancelled
Test / Offline Coverage Tests (Python 3.10) (push) Has been cancelled
Test / Offline Coverage Tests (Python 3.11) (push) Has been cancelled
Test / Offline Coverage Tests (Python 3.12) (push) Has been cancelled
Test / Offline Coverage Tests (Python 3.13) (push) Has been cancelled
Test / Offline Coverage Tests (Python 3.9) (push) Has been cancelled
Test / Full Coverage (Python 3.11) (push) Has been cancelled
Test / Core Provider Tests (OpenAI) (push) Has been cancelled
Test / Core Provider Tests (Anthropic) (push) Has been cancelled
Test / Core Provider Tests (Google) (push) Has been cancelled
Test / Core Provider Tests (Other) (push) Has been cancelled
Test / Anthropic Tests (push) Has been cancelled
Test / Gemini Tests (push) Has been cancelled
Test / Google GenAI Tests (push) Has been cancelled
Test / Vertex AI Tests (push) Has been cancelled
Test / OpenAI Tests (push) Has been cancelled
Test / Writer Tests (push) Has been cancelled
Test / Auto Client Tests (push) Has been cancelled
ty / type-check (push) Has been cancelled
36 lines
827 B
Python
36 lines
827 B
Python
"""
|
|
Canonical OpenAI starter example for the instructor library.
|
|
|
|
Demonstrates how to use `instructor.from_provider()` with OpenAI to extract
|
|
structured data from natural language into a Pydantic model.
|
|
|
|
Usage:
|
|
export OPENAI_API_KEY=your-api-key
|
|
python examples/openai/run.py
|
|
"""
|
|
|
|
import instructor
|
|
from pydantic import BaseModel, Field
|
|
|
|
|
|
class UserInfo(BaseModel):
|
|
"""Extracted user information."""
|
|
|
|
name: str = Field(description="The user's full name")
|
|
age: int = Field(description="The user's age in years")
|
|
|
|
|
|
client = instructor.from_provider("openai/gpt-4o-mini")
|
|
|
|
user = client.chat.completions.create(
|
|
response_model=UserInfo,
|
|
messages=[
|
|
{
|
|
"role": "user",
|
|
"content": "Extract: Jason is 25 years old.",
|
|
}
|
|
],
|
|
)
|
|
|
|
print(user.model_dump_json(indent=2))
|