app.py

import gradio as gr
import requests
import os

# 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
firecrawl_api_key = os.getenv("FIRECRAWL_API_KEY")  # Firecrawl 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

    # Use the LLM to reason and reflect on the provided data
    def reason_with_llm(self):
        print("Reasoning: Using LLM to reason about available data...")
        
        # LLM reasoning prompt that evaluates the current data and reflects on next actions
        reasoning_prompt = f"""
        You are a reasoning agent tasked with generating a job application email. Here's what we have:
        
        1. Candidate's LinkedIn profile URL: {self.linkedin_url}
        2. Company Name: {self.company_name}
        3. Role: {self.role}
        4. Word Limit: {self.word_limit}
        5. Candidate's Name: {self.user_name}
        6. Candidate's Email: {self.email}
        7. Candidate's Phone: {self.phone}
        8. Candidate's LinkedIn: {self.linkedin}

        Candidate's Bio: {self.bio}
        Candidate's Skills: {', '.join(self.skills)}
        Candidate's Experiences: {', '.join([exp['title'] for exp in self.experiences])}

        Company Information: {self.company_info}
        Role Description: {self.role_description}

        Evaluate the completeness of the data. If some key data is missing, determine whether we should:
        - Scrape for more data (e.g., company info, role descriptions).
        - Proceed with the available information and generate the email using default logic.

        Reflect on whether we need more data or if the current information is sufficient to proceed.
        """
        
        # Send this reasoning prompt to the LLM
        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": reasoning_prompt}],
            "model": "llama3-8b-8192"
        }
        
        response = requests.post(url, headers=headers, json=data)
        if response.status_code == 200:
            reasoning_output = response.json()["choices"][0]["message"]["content"].strip()
            print("LLM Reasoning Output:", reasoning_output)
            return reasoning_output
        else:
            print(f"Error: {response.status_code}, {response.text}")
            return "Error: Unable to complete reasoning."

    # 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 Firecrawl API
    def fetch_company_info_with_firecrawl(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."
        else:
            print(f"Action: Fetching company info for {self.company_name} using Firecrawl.")
            headers = {"Authorization": f"Bearer {firecrawl_api_key}"}
            firecrawl_url = "https://api.firecrawl.dev/v1/scrape"
            data = {
                "url": f"https://{self.company_name}.com",
                "patterns": ["description", "about", "careers", "company overview"]
            }
            
            response = requests.post(firecrawl_url, json=data, headers=headers)
            if response.status_code == 200:
                firecrawl_data = response.json()
                self.company_info = firecrawl_data.get("description", "No detailed company info available.")
                print(f"Company info fetched: {self.company_info}")
            else:
                print(f"Error: Unable to fetch company info via Firecrawl. Using default info.")
                self.company_info = "A leading company in its field."

    # 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.")
        
        # Use the LinkedIn profile link dynamically in the body
        linkedin_text = f"Please find my LinkedIn profile at {self.linkedin}" if self.linkedin else ""

        # Dynamic LLM prompt
        prompt = f"""
        Write a professional email applying for the {self.role} position at {self.company_name}.
        
        Use the following information:
        - The candidate’s LinkedIn bio: {self.bio}.
        - The candidate’s most relevant skills: {', '.join(self.skills)}.
        - The candidate’s professional experience: {', '.join([exp['title'] for exp in self.experiences])}.
        
        Please research the company's public information. If no company-specific information is available, use general knowledge about the company's industry.
        
        Tailor the email dynamically to the role of **{self.role}** at {self.company_name}, aligning the candidate's skills and experiences with the expected responsibilities of the role and the company’s operations.

        {linkedin_text}

        Remove references to job posting sources unless provided. Use the LinkedIn URL for the candidate and do not include placeholders.

        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-8192"
        }
        
        response = requests.post(url, headers=headers, json=data)
        if response.status_code == 200:
            return response.json()["choices"][0]["message"]["content"].strip()
        else:
            print(f"Error: {response.status_code}, {response.text}")
            return "Error generating email. Please check your API key or try again later."

    # Main loop following ReAct pattern
    def run(self):
        reasoning_output = self.reason_with_llm()  # LLM performs reasoning and reflection
        print("LLM Reflection:", reasoning_output)

        self.fetch_linkedin_data()  # Fetch LinkedIn data
        self.fetch_company_info_with_firecrawl()  # Fetch company data using Firecrawl
        
        return self.generate_email()  # Final action: generate email

# Define the Gradio interface and the main app logic
def gradio_ui():
    # Input fields
    name_input = gr.Textbox(label="Your Name", placeholder="Enter your name")
    company_input = gr.Textbox(label="Company Name or URL", placeholder="Enter the company name or website URL")
    role_input = gr.Textbox(label="Role Applying For", placeholder="Enter the role you are applying for")
    email_input = gr.Textbox(label="Your Email Address", placeholder="Enter your email address")
    phone_input = gr.Textbox(label="Your Phone Number", placeholder="Enter your phone number")
    linkedin_input = gr.Textbox(label="Your LinkedIn URL", placeholder="Enter your LinkedIn profile URL")
    word_limit_slider = gr.Slider(minimum=50, maximum=300, step=10, label="Email Word Limit", value=150)
    
    # Output field
    email_output = gr.Textbox(label="Generated Email", placeholder="Your generated email will appear here", lines=10)