Using GPT4 Vision with Function Calling

!pip install pymupdf --quiet
!pip install openai --quiet
!pip install matplotlib --quiet
# instructor makes it easy to work with function calling
!pip install instructor --quiet

import base64
import os
from enum import Enum
from io import BytesIO
from typing import Iterable
from typing import List
from typing import Literal, Optional

import fitz
# Instructor is powered by Pydantic, which is powered by type hints. Schema validation, prompting is controlled by type annotations
import instructor
import matplotlib.pyplot as plt
import pandas as pd
from IPython.display import display
from PIL import Image
from openai import OpenAI
from pydantic import BaseModel, Field

MODEL = "gpt-4-turbo-2024-04-09"

class Order(BaseModel):
    """Represents an order with details such as order ID, customer name, product name, price, status, and delivery date."""
    order_id: str = Field(..., description="The unique identifier of the order")
    product_name: str = Field(..., description="The name of the product")
    price: float = Field(..., description="The price of the product")
    status: str = Field(..., description="The status of the order")
    delivery_date: str = Field(..., description="The delivery date of the order")
# Placeholder functions for order processing

def get_order_details(order_id):
    # Placeholder function to retrieve order details based on the order ID
    return Order(
        order_id=order_id,
        product_name="Product X",
        price=100.0,
        status="Delivered",
        delivery_date="2024-04-10",
    )

def escalate_to_agent(order: Order, message: str):
    # Placeholder function to escalate the order to a human agent
    return f"Order {order.order_id} has been escalated to an agent with message: `{message}`"

def refund_order(order: Order):
    # Placeholder function to process a refund for the order
    return f"Order {order.order_id} has been refunded successfully."

def replace_order(order: Order):
    # Placeholder function to replace the order with a new one
    return f"Order {order.order_id} has been replaced with a new order."

class FunctionCallBase(BaseModel):
    rationale: Optional[str] = Field(..., description="The reason for the action.")
    image_description: Optional[str] = Field(
        ..., description="The detailed description of the package image."
    )
    action: Literal["escalate_to_agent", "replace_order", "refund_order"]
    message: Optional[str] = Field(
        ...,
        description="The message to be escalated to the agent if action is escalate_to_agent",
    )
    # Placeholder functions to process the action based on the order ID
    def __call__(self, order_id):
        order: Order = get_order_details(order_id=order_id)
        if self.action == "escalate_to_agent":
            return escalate_to_agent(order, self.message)
        if self.action == "replace_order":
            return replace_order(order)
        if self.action == "refund_order":
            return refund_order(order)

class EscalateToAgent(FunctionCallBase):
    """Escalate to an agent for further assistance."""
    pass

class OrderActionBase(FunctionCallBase):
    pass

class ReplaceOrder(OrderActionBase):
    """Tool call to replace an order."""
    pass

class RefundOrder(OrderActionBase):
    """Tool call to refund an order."""
    pass

base64_img = encode_image(output_path)

class RoleEnum(str, Enum):
    """Defines possible roles within an organization."""
    CEO = "CEO"
    CTO = "CTO"
    CFO = "CFO"
    COO = "COO"
    EMPLOYEE = "Employee"
    MANAGER = "Manager"
    INTERN = "Intern"
    OTHER = "Other"

class Employee(BaseModel):
    """Represents an employee, including their name, role, and optional manager information."""
    employee_name: str = Field(..., description="The name of the employee")
    role: RoleEnum = Field(..., description="The role of the employee")
    manager_name: Optional[str] = Field(None, description="The manager's name, if applicable")
    manager_role: Optional[RoleEnum] = Field(None, description="The manager's role, if applicable")


class EmployeeList(BaseModel):
    """A list of employees within the organizational structure."""
    employees: List[Employee] = Field(..., description="A list of employees")

def parse_orgchart(base64_img: str) -> EmployeeList:
    response = instructor.from_openai(OpenAI()).chat.completions.create(
        model='gpt-4-turbo',
        response_model=EmployeeList,
        messages=[
            {
                "role": "user",
                "content": 'Analyze the given organizational chart and very carefully extract the information.',
            },
            {
                "role": "user",
                "content": [
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": f"data:image/jpeg;base64,{base64_img}"
                        }
                    },
                ],
            }
        ],
    )
    return response