import dotenv
from openai import OpenAI
import os
from pypdf import PdfReader
import gradio as gr
import json
import requests

dotenv.load_dotenv(override=True)


openai_api_key = os.getenv("OPENAI_API_KEY")
pushover_user = os.getenv("PUSHOVER_USER")
pushover_token = os.getenv("PUSHOVER_TOKEN")

#if pushover_user and pushover_token:
 #   print("Pushover user and token found")
  #  print("Pushover user and token not found")

def send_pushover_notification(message):
        url = "https://api.pushover.net/1/messages.json"
        data = {
            "token": os.getenv("PUSHOVER_TOKEN"),
            "user": os.getenv("PUSHOVER_USER"),
            "message": message
        }
        response = requests.post(url, data=data)
        if response.status_code == 200:
            print("Pushover notification sent successfully")
        else:
            print("Failed to send Pushover notification")

def get_pdf_text(pdf_path):
    reader = PdfReader(pdf_path)
    text = ""
    for page in reader.pages:
        text += page.extract_text()
    return text

def record_user_details(email, name="Not provided", notes="Not provided" ):
    print(f"User details recorded: Name: {name}, Email: {email}, Notes: {notes}")
    send_pushover_notification(f"Recording interest from : Name: {name}, Email: {email}, Notes: {notes}")
    return {"recorded": "ok"}

def record_unknown_question(question):
    print(f"Unknown question recorded: {question}")
    send_pushover_notification(f"Unknown question recorded: {question}")
    return {"recorded": "ok"}

record_user_details_json = {
    "name" : "record_user_details",
    "description" : "Record user details",
    "parameters" : {
        "type" : "object",
        "properties" : {
            "email" : {"type" : "string", "description" : "The email of the user"},
            "name" : {"type" : "string", "description" : "The name of the user, if they provided it"},
            "notes" : {"type" : "string", "description" : "Any additional information about conversation that worth's recording to given context"}            
        },
        "required" : ["email"],
        "additionalProperties" : False
    }
}

record_unknown_question_json = {
    "name" : "record_unknown_question",
    "description" : "Record unknown question",
    "parameters" : {
        "type" : "object",
        "properties" : {"question" : {"type" : "string", "description" : "The question that the user asked"}}
    }
}

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

class Me :
    def __init__(self):
        self.openai = OpenAI()
        self.name = "Ram Shah"
        self.linked_profile = get_pdf_text("RamShah_Profile.pdf")
        with open("Ram_summary.txt", "r", encoding="utf-8") as file:
            self.summary = file.read()
        self.name = "Ram Shah"         
        self.client = OpenAI(api_key=openai_api_key, base_url="https://generativelanguage.googleapis.com/v1beta/openai/")

    def handle_tool_calls(self, tool_calls):
        results = []
        for tool_call in tool_calls : 
            tool_name = tool_call.function.name
            print(f"Tool called: {tool_name}", flush=True)
            
            tool = globals().get(tool_name)
            arguments = json.loads(tool_call.function.arguments)

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

    def system_prompt(self):
        system_prompt = f"You are acting as Ram Shah. You are answering questions on Ram Shah's website, \
            particularly questions related to Ram Shah's career, background, skills and experience. \
            Your responsibility is to represent Ram Shah for interactions on the website as faithfully as possible. \
            You are given a summary of Ram Shah's background and LinkedIn profile 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 that you couldn't answer, even if it's about something trivial or unrelated to career. \
            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. "

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



    def chat_with_me(self, message, history):
        messages = [{"role" : "system", "content" : self.system_prompt()}] + history + [{"role" : "user","content" : message}]
        done = False
        while not done:

            # this is the call to LLM - passing tool json
            response = self.client.chat.completions.create(model="gemini-1.5-flash", messages=messages, tools=tools)

            finish_reson = response.choices[0].finish_reason

            if finish_reson == "tool_calls":
                message = response.choices[0].message
                tool_calls = message.tool_calls
                results = self.handle_tool_calls(tool_calls)
                messages.append(message)
                messages.extend(results)
            else:
                done = True
        return response.choices[0].message.content


if __name__ == "__main__":
    me = Me()
    gr.ChatInterface(me.chat_with_me, type="messages").launch(share=True)