# ===============================
# Import required libraries
# ===============================
from dotenv import load_dotenv       # For loading environment variables from a .env file
from openai import OpenAI            # OpenAI API client
import json                          # For parsing tool arguments from JSON
import os                            # For accessing environment variables
import requests                      # For making HTTP requests (used with Pushover)
from pypdf import PdfReader          # For extracting text from your PDFs
import gradio as gr                  # For creating a web-based chatbot interface


# ===============================
# Load environment variables
# ===============================
load_dotenv(override=True)           # Reads the .env file and sets environment variables


# ===============================
# Function: Send Pushover notification
# ===============================
def push(text):
    """
    Sends a notification message via Pushover API.
    Requires PUSHOVER_TOKEN and PUSHOVER_USER in your .env file.
    """
    requests.post(
        "https://api.pushover.net/1/messages.json",
        data={
            "token": os.getenv("PUSHOVER_TOKEN"),
            "user": os.getenv("PUSHOVER_USER"),
            "message": text,
        }
    )


# ===============================
# Function: Record user details
# ===============================
def record_user_details(email, name="Name not provided", notes="not provided"):
    """
    Records user contact details and sends a push notification.
    """
    push(f"Recording {name} with email {email} and notes {notes}")
    return {"recorded": "ok"}


# ===============================
# Function: Record unknown questions
# ===============================
def record_unknown_question(question):
    """
    Records a question the AI couldn't answer.
    """
    push(f"Recording {question}")
    return {"recorded": "ok"}


# ===============================
# Tool definitions for GPT function calling
# ===============================
record_user_details_json = {
    "name": "record_user_details",
    "description": "Use this tool to record that a user is interested in being in touch and provided an email address",
    "parameters": {
        "type": "object",
        "properties": {
            "email": {"type": "string", "description": "The email address of this user"},
            "name": {"type": "string", "description": "The user's name, if they provided it"},
            "notes": {"type": "string", "description": "Any additional context about the user"}
        },
        "required": ["email"],
        "additionalProperties": False
    }
}

record_unknown_question_json = {
    "name": "record_unknown_question",
    "description": "Always use this tool to record any question that couldn't be answered",
    "parameters": {
        "type": "object",
        "properties": {
            "question": {"type": "string", "description": "The question that couldn't be answered"},
        },
        "required": ["question"],
        "additionalProperties": False
    }
}

tools = [
    {"type": "function", "function": record_user_details_json},
    {"type": "function", "function": record_unknown_question_json}
]


# ===============================
# Class: Me (acts as your personal AI)
# ===============================
class Me:

    def __init__(self):
        """
        Initialize the AI persona:
        - Load OpenAI client
        - Extract LinkedIn text from PDF
        - Extract Resume text from PDF
        - Load career summary from text file
        """
        self.openai = OpenAI()
        self.name = "Ritika Chandak"

        # Load LinkedIn PDF
        reader = PdfReader("Profile.pdf")
        self.linkedin = ""
        for page in reader.pages:
            text = page.extract_text()
            if text:
                self.linkedin += text

        # Load Resume PDF
        resume_reader = PdfReader("ritika_resume.pdf")
        self.resume = ""
        for page in resume_reader.pages:
            text = page.extract_text()
            if text:
                self.resume += text

        # Load career summary
        with open("summary.txt", "r", encoding="utf-8") as f:
            self.summary = f.read()

    # ===============================
    # Handle tool calls from GPT
    # ===============================
    def handle_tool_call(self, tool_calls):
        results = []
        for tool_call in tool_calls:
            tool_name = tool_call.function.name
            arguments = json.loads(tool_call.function.arguments)
            print(f"Tool called: {tool_name}", flush=True)

            tool = globals().get(tool_name)
            result = tool(**arguments) if tool else {}

            results.append({
                "role": "tool",
                "content": json.dumps(result),
                "tool_call_id": tool_call.id
            })
        return results

    # ===============================
    # System prompt for GPT
    # ===============================
    def system_prompt(self):
        system_prompt = f"You are acting as {self.name}. You are answering questions on {self.name}'s website, \
particularly questions related to {self.name}'s career, background, skills and experience. \
Your responsibility is to represent {self.name} for interactions on the website as faithfully as possible. \
You are given a summary of {self.name}'s background, LinkedIn profile, and Resume which you can use to answer questions. \
Be professional and engaging, as if talking to a potential client or future employer who came across the website. \
If you don't know the answer to any question, use your record_unknown_question tool to record the question. \
If the user is engaging in discussion, try to steer them towards getting in touch via email; \
ask for their email and record it using your record_user_details tool. "

        # Add context
        system_prompt += f"\n\n## Summary:\n{self.summary}"
        system_prompt += f"\n\n## LinkedIn Profile:\n{self.linkedin}"
        system_prompt += f"\n\n## Resume:\n{self.resume}\n\n"
        system_prompt += f"With this context, please chat with the user, always staying in character as {self.name}."

        return system_prompt

    # ===============================
    # Chat method (core conversation loop)
    # ===============================
    def chat(self, message, history):
        messages = [{"role": "system", "content": self.system_prompt()}] + history + [{"role": "user", "content": message}]

        done = False
        while not done:
            response = self.openai.chat.completions.create(
                model="gpt-4o-mini",
                messages=messages,
                tools=tools
            )

            if response.choices[0].finish_reason == "tool_calls":
                message = response.choices[0].message
                tool_calls = message.tool_calls

                results = self.handle_tool_call(tool_calls)
                messages.append(message)
                messages.extend(results)
            else:
                done = True

        return response.choices[0].message.content


# ===============================
# Launch chatbot with Gradio UI
# ===============================
if __name__ == "__main__":
    me = Me()                                        
    gr.ChatInterface(me.chat, type="messages").launch()