app.py

# imports
from datetime import datetime
from dotenv import load_dotenv
from openai import OpenAI
import json
import os
import requests
from pypdf import PdfReader
import gradio as gr
import smtplib
from email.mime.text import MIMEText
from email.mime.multipart import MIMEMultipart

load_dotenv(override=True)

openai = OpenAI()


# def send_email(to_email, subject, body):
#     from_email = os.getenv("GMAIL_EMAIL")
#     password = os.getenv("GMAIL_APP_PASSWORD")

#     if not password:
#         print("❌ Error: GMAIL_APP_PASSWORD not found in environment variables")
#         return

#     msg = MIMEMultipart()
#     msg['From'] = from_email
#     msg['To'] = to_email
#     msg['Subject'] = subject
#     msg.attach(MIMEText(body, 'plain'))

#     try:
#         with smtplib.SMTP('smtp.gmail.com', 587) as server:
#             server.starttls()
#             server.login(from_email, password)
#             server.send_message(msg)
#             print("✅ Email sent successfully!")
#     except Exception as e:
#         print(f"❌ Error sending email: {e}")


def send_email(to_email, subject, body):
    # Just log to console - viewable in HF Spaces logs
    log_entry = {
        "timestamp": datetime.now().isoformat(),
        "to": to_email,
        "subject": subject,
        "body": body
    }

    print(f"✅ Contact Info: {json.dumps(log_entry)}", flush=True)


def record_user_details(email, name="Name not provided", notes="not provided"):
    send_email(to_email=os.getenv("GMAIL_EMAIL"),
               subject=f"Recording interest from {name} with email {email} and notes {notes}",
               body=f"Recording interest from {name} with email {email} and notes {notes}")

    return {"recorded": "ok"}


def record_unknown_question(question):
    send_email(to_email=os.getenv("GMAIL_EMAIL"),
               subject=f"Recording {question} asked that I couldn't answer",
               body=f"Recording {question} asked that I couldn't answer")
    return {"recorded": "ok"}


# this json will be sent to LLM to record the 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
    }
}

# this json will be sent to LLM to record the unknown question
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 Me:

    def __init__(self):
        self.openai = OpenAI()
        self.name = "Yongpeng Fu"
        reader = PdfReader("me/Profile.pdf")
        self.linkedin = ""
        for page in reader.pages:
            text = page.extract_text()
            if text:
                self.linkedin += text
        with open("me/summary.txt", "r", encoding="utf-8") as f:
            self.summary = f.read()

    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

    def system_prompt(self):
        system_prompt = f"You are acting as {self.name}, a seasoned Staff Data/AI Engineer with deep expertise in artificial intelligence, \
data engineering, and enterprise-scale system architecture. You are answering questions on {self.name}'s website, \
particularly questions related to {self.name}'s career, background, technical skills, and engineering experience. \
\n\nYour responsibility is to represent {self.name} as a highly skilled technical leader who specializes in:\n\
- Designing and implementing robust, scalable data pipelines\n\
- Building enterprise-grade AI and machine learning systems\n\
- Architecting distributed systems and cloud infrastructure\n\
- Leading complex engineering projects from conception to production deployment\n\
- Working across multiple industries (banking, energy, retail) with proven technical leadership\n\
\n\
When answering questions, emphasize {self.name}'s strong technical foundation, problem-solving capabilities, and ability to deliver \
production-ready solutions at scale. Be professional, confident, and engaging, as if speaking to a potential employer, \
client, or technical collaborator who is evaluating {self.name}'s capabilities.\n\
\n\
You are given a detailed summary of {self.name}'s background and LinkedIn profile to reference when answering questions. \
Use specific examples and technical depth when discussing projects, skills, and experience.\n\
\n\
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 and shows interest, try to facilitate next steps by encouraging them to get 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.linkedin}\n\n"
        system_prompt += f"With this context, please chat with the user, always staying in character as {self.name}. \
Showcase technical expertise, leadership experience, and the ability to architect and deliver complex data and AI solutions."
        return system_prompt

    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


if __name__ == "__main__":
    me = Me()
    gr.ChatInterface(
        me.chat,
        type="messages",
        title="Chat with Yongpeng Fu - AI Agent",
        description="Hi! I'm an AI assistant representing Yongpeng Fu, a Staff Data/AI Engineer at RBC Royal Bank. Ask me about Yongpeng's experience, skills, or projects. Feel free to get in touch!",
        examples=[
            "Tell me about yourself",
            "What projects have you worked on?",
            "What are your technical skills?",
            "Let's get in touch"
        ]
    ).launch()