app.py

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

load_dotenv(override=True)

pushover_token = os.getenv("PUSHOVER_TOKEN")
pushover_user = os.getenv("PUSHOVER_USER")
pushover_url = "https://api.pushover.net/1/messages.json"


if pushover_token:
    print(f"pushover token found")
else:
    print("Pushover token not found")


def push(message):
    print(f"Push: {message}")
    payload = {"user": pushover_user, "token": pushover_token, "message": message}
    requests.post(pushover_url, data=payload)

def record_user_details(email, name="Name not provided", notes="not provided"):
    print(f":: Fn record_user_details called ::")
    print(f"Recording interest from {name} with email {email} and notes {notes}")
    push(f"Recording interest from {name} with email {email} and notes {notes}")
    return {"recorded": "ok"}

def record_unknown_question(question):
    print(f":: Fn record_unknown_question called ::")
    print(f"Recording {question} asked that I couldn't answer")
    push(f"Recording {question} asked that I couldn't answer")
    return {"recorded": "ok"}


# Json structure for recording user details
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 information about the conversation that's worth recording to give context"
            }
        },
        "required": ["email"],
        "additionalProperties": False
    }
}


# Json structure for recording unknown questions
record_unknown_question_json = {
    "name": "record_unknown_question",
    "description": "Always use this tool to record any question that couldn't be answered as you didn't know the answer",
    "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 PersonalBot():
    def __init__(self):
        self.gemini = gemini = OpenAI(
    api_key=os.getenv("GOOGLE_API_KEY"), 
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)
        self.name = "Surbhit Kumar"
        reader = PdfReader('linkedin.pdf')
        self.linkedin = ""
        for page in reader.pages:
            text = page.extract_text()
            if text:
                self.linkedin += text

    def handle_tool_calls(self, tool_calls):
        print(f":: Fn handle_tool_calls called ::")
        print(f":: tool_calls: {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)
            print(f"Args for above tool: {arguments}", 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


    def get_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 {self.name}'s 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"## LinkedIn Profile:\n{self.linkedin}\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(self, message, history):
        messages = [{"role": "system", "content": self.get_system_prompt()}] + history + [{"role": "user", "content": message}]
        done = False
        while not done:

            response =  self.gemini.chat.completions.create(model="gemini-2.0-flash", messages=messages, tools=tools)
            finish_reason = response.choices[0].finish_reason
            print(f"********************* {response} *********************")
            # If the LLM wants to call a tool, we do that!
            
            if finish_reason=="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__":
    personal_bot = PersonalBot()
    gr.ChatInterface(personal_bot.chat, type="messages").launch()