app.py

import gradio as gr
import requests
import os
from bs4 import BeautifulSoup  # For scraping company and role info

# Load API keys securely from environment variables
proxycurl_api_key = os.getenv("PROXYCURL_API_KEY")  # Proxycurl API key
groq_api_key = os.getenv("GROQ_CLOUD_API_KEY")  # Groq Cloud API key

class EmailAgent:
    def __init__(self, linkedin_url, company_name, role, word_limit, user_name, email, phone, linkedin):
        self.linkedin_url = linkedin_url
        self.company_name = company_name
        self.role = role
        self.word_limit = word_limit
        self.user_name = user_name
        self.email = email
        self.phone = phone
        self.linkedin = linkedin
        self.bio = None
        self.skills = []
        self.experiences = []
        self.company_info = None
        self.role_description = None

    # Reason: Decide what information is needed and if we need to take additional steps
    def reason_about_data(self):
        print("Reasoning: Deciding what data we need...")
        if not self.linkedin_url:
            print("Warning: LinkedIn URL missing. Proceeding with default bio.")
        if not self.company_name:
            print("Warning: Company name missing. Proceeding with default company info.")
        if not self.role:
            print("Warning: Role missing. We will use general logic for the role.")

    # Action: Fetch LinkedIn data via Proxycurl (acting based on reasoning)
    def fetch_linkedin_data(self):
        if not self.linkedin_url:
            print("Action: No LinkedIn URL provided, using default bio.")
            self.bio = "A professional with diverse experience."
            self.skills = ["Adaptable", "Hardworking"]
            self.experiences = ["Worked across various industries"]
        else:
            print("Action: Fetching LinkedIn data via Proxycurl.")
            headers = {"Authorization": f"Bearer {proxycurl_api_key}"}
            url = f"https://nubela.co/proxycurl/api/v2/linkedin?url={self.linkedin_url}"
            response = requests.get(url, headers=headers)
            if response.status_code == 200:
                data = response.json()
                self.bio = data.get("summary", "No bio available")
                self.skills = data.get("skills", [])
                self.experiences = data.get("experiences", [])
            else:
                print("Error: Unable to fetch LinkedIn profile. Using default bio.")
                self.bio = "A professional with diverse experience."
                self.skills = ["Adaptable", "Hardworking"]
                self.experiences = ["Worked across various industries"]

    # Action: Fetch company information via Proxycurl or use defaults
    def fetch_company_info(self):
        if not self.company_name:
            print("Action: No company name provided, using default company info.")
            self.company_info = "A leading company in its field, offering innovative solutions."
        else:
            print(f"Action: Fetching company info for {self.company_name}.")
            headers = {"Authorization": f"Bearer {proxycurl_api_key}"}
            url = f"https://nubela.co/proxycurl/api/v2/linkedin/company?company_name={self.company_name}"
            response = requests.get(url, headers=headers)
            if response.status_code == 200:
                data = response.json()
                self.company_info = data.get("description", "No detailed company info available.")
            else:
                print(f"Error: Unable to fetch company info for {self.company_name}. Using default info.")
                self.company_info = "A leading company in its field, offering innovative solutions."

    # Action: Scrape the company's website for role-specific information or use defaults
    def scrape_role_from_website(self):
        print(f"Action: Scraping role description from the company's website for {self.role}.")
        if not self.company_name:
            print("Error: No company name or URL provided for scraping.")
            return False
        
        # Try scraping the website for role descriptions
        try:
            response = requests.get(f"https://{self.company_name}.com/careers")
            if response.status_code == 200:
                soup = BeautifulSoup(response.text, 'html.parser')
                role_descriptions = soup.find_all(string=lambda text: self.role.lower() in text.lower())
                if role_descriptions:
                    self.role_description = role_descriptions[0]
                    print(f"Found role description: {self.role_description}")
                    return True
                else:
                    print(f"No specific role description found on the website for {self.role}.")
                    return False
            else:
                print(f"Error: Unable to reach company's website at {self.company_name}.com.")
                return False
        except Exception as e:
            print(f"Error during scraping: {e}")
            return False

    # Action: Use default logic for role description if no role is available
    def use_default_role_description(self):
        print(f"Action: Using default logic for the role of {self.role}.")
        self.role_description = f"The role of {self.role} at {self.company_name} involves mentoring and leading teams in innovative technology solutions."

    # Reflection: Check if we have enough data to generate the email
    def reflect_on_data(self):
        print("Reflection: Do we have enough data?")
        if not self.bio or not self.skills or not self.company_info:
            print("Warning: Some critical information is missing. Proceeding with default values.")
        return True

    # Final Action: Generate the email using Groq Cloud LLM based on gathered data
    def generate_email(self):
        print("Action: Generating the email with the gathered information.")
        prompt = f"""
        Write a professional email applying for the {self.role} position at {self.company_name}.
        The candidate’s bio is: {self.bio}.
        
        Focus on relevant skills and experiences from LinkedIn, such as {', '.join(self.skills)}, 
        that directly align with the role of {self.role}. 
        Highlight only the skills and experiences that relate to leadership, mentoring, technology, and innovation.
        
        The company info is: {self.company_info}.
        The role involves: {self.role_description}.
        
        End the email with this signature:
        Best regards,
        {self.user_name}
        Email: {self.email}
        Phone: {self.phone}
        LinkedIn: {self.linkedin}
        
        The email should not exceed {self.word_limit} words.
        """
        
        url = "https://api.groq.com/openai/v1/chat/completions"
        headers = {"Authorization": f"Bearer {groq_api_key}", "Content-Type": "application/json"}
        
        data = {
            "messages": [{"role": "user", "content": prompt}],
            "model": "llama3-8b