Instructor Python for AI Engineering: Pydantic & Reasking Loops

import instructor
from openai import OpenAI
from pydantic import BaseModel, Field, field_validator
from typing import List

# Define structured output model with Pydantic v2 validation rules
class InvoiceItem(BaseModel):
  description: str = Field(description="Name or itemized description of service")
  amount_usd: float = Field(description="Line item total cost in USD")

class InvoiceData(BaseModel):
  vendor_name: str = Field(description="Name of issuing corporate vendor")
  invoice_number: str = Field(description="Unique alphanumeric invoice code")
  items: List[InvoiceItem] = Field(description="List of itemized invoice lines")

  @field_validator("invoice_number")
  def validate_code_format(cls, v):
      if not v.isalnum():
          raise ValueError("Invoice number must contain alphanumeric characters only without special symbols")
      return v

# Patch standard OpenAI client with Instructor structured output wrapper
client = instructor.from_openai(OpenAI())

def extract_invoice_data(invoice_text: str) -> InvoiceData:
  extracted: InvoiceData = client.chat.completions.create(
      model="gpt-4o",
      response_model=InvoiceData,
      max_retries=3, # Automatically retry if Pydantic field validation fails
      messages=[
          {"role": "system", "content": "Extract structured invoice fields accurately."},
          {"role": "user", "content": invoice_text}
      ]
  )
  return extracted

if __name__ == "__main__":
  sample_text = "Vendor: Acmo Tech Inc. Invoice #INV9082. Services: Cloud Consulting $5000, GPU Hosting $1200."
  result = extract_invoice_data(sample_text)
  print("Vendor:", result.vendor_name)
  print("Invoice Code:", result.invoice_number)
  print("Extracted Items:", [item.model_dump() for item in result.items])