Update app.py

app.py

@@ -1,7 +1,7 @@
 import gradio as gr
 import requests
 import os
-from bs4 import BeautifulSoup  # Add BeautifulSoup for scraping
+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
@@ -23,15 +23,17 @@ class EmailAgent:
         self.company_info = None
         self.role_description = None
 
-    # Reason: Decide what information is needed
+    # Reason: Decide what information is needed and if we need to take additional steps
     def reason_about_data(self):
-        print("Reasoning: I need LinkedIn data, company info, and role description.")
+        print("Reasoning: Deciding what data we need...")
         if not self.linkedin_url:
-            print("Warning: LinkedIn URL missing. Will proceed with default bio.")
+            print("Warning: LinkedIn URL missing. Proceeding with default bio.")
         if not self.company_name:
-            print("Warning: Company name missing. Will proceed with default company info.")
-    
-    # Action: Fetch LinkedIn data via Proxycurl
+            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.")
@@ -39,10 +41,8 @@ class EmailAgent:
             self.skills = ["Adaptable", "Hardworking"]
             self.experiences = ["Worked across various industries"]
         else:
-            print("Action: Fetching LinkedIn data from Proxycurl.")
-            headers = {
-                "Authorization": f"Bearer {proxycurl_api_key}",
-            }
+            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:
@@ -55,17 +55,15 @@ class EmailAgent:
                 self.bio = "A professional with diverse experience."
                 self.skills = ["Adaptable", "Hardworking"]
                 self.experiences = ["Worked across various industries"]
-    
-    # Action: Fetch company information via Proxycurl
+
+    # 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}",
-            }
+            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:
@@ -75,24 +73,22 @@ class EmailAgent:
                 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
+    # 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
         
-        # Attempt to scrape the company's website
+        # 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')
-                # Look for any sections that might contain role descriptions
                 role_descriptions = soup.find_all(string=lambda text: self.role.lower() in text.lower())
                 if role_descriptions:
-                    # If we find relevant role descriptions, use the first match
                     self.role_description = role_descriptions[0]
-                    print(f"Found role description on company's website: {self.role_description}")
+                    print(f"Found role description: {self.role_description}")
                     return True
                 else:
                     print(f"No specific role description found on the website for {self.role}.")
@@ -104,20 +100,19 @@ class EmailAgent:
             print(f"Error during scraping: {e}")
             return False
 
-    # Action: Use default logic to infer role description if scraping fails
+    # 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 AI and technology students to develop their skills and progress their careers."
+        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 the data is sufficient to generate an email
+    # Reflection: Check if we have enough data to generate the email
     def reflect_on_data(self):
-        print("Reflection: Do I have enough data to generate the email?")
-        # Allow the email to be generated with default values if data is missing
+        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
-    
-    # Action: Generate the email using Groq Cloud LLM
+
+    # 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"""
@@ -126,7 +121,7 @@ class EmailAgent:
         
         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 mentoring, AI, technology, and leadership.
+        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}.
@@ -142,70 +137,8 @@ class EmailAgent:
         """
         
         url = "https://api.groq.com/openai/v1/chat/completions"
-        headers = {
-            "Authorization": f"Bearer {groq_api_key}",
-            "Content-Type": "application/json",
-        }
+        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):
-        self.reason_about_data()  # Reason
-        self.fetch_linkedin_data()  # Action
-        self.fetch_company_info()  # Action
-        # Try to scrape the company's website for role-specific information
-        if not self.scrape_role_from_website():  
-            self.use_default_role_description()  # Use default logic if scraping fails
-        if self.reflect_on_data():  # Reflection
-            return self.generate_email()  # Final Action
-        else:
-            return "Error: Not enough data to generate the 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)  # New slider for word limit
-    
-    # Output field
-    email_output = gr.Textbox(label="Generated Email", placeholder="Your generated email will appear here", lines=10)
-
-    # Function to create and run the email agent
-    def create_email(name, company_name, role, email, phone, linkedin_url, word_limit):
-        agent = EmailAgent(linkedin_url, company_name, role, word_limit, name, email, phone, linkedin_url)
-        return agent.run()
-
-    # Gradio interface
-    demo = gr.Interface(
-        fn=create_email,
-        inputs=[name_input, company_input, role_input, email_input, phone_input, linkedin_input, word_limit_slider],
-        outputs=[email_output],
-        title="Email Writing AI Agent with ReAct",
-        description="Generate a professional email for a job application using LinkedIn data, company info, and role description.",
-        allow_flagging="never"
-    )
-    
-    # Launch the Gradio app
-    demo.launch()
-
-# Start the Gradio app when running the script
-if __name__ == "__main__":
-    gradio_ui()
-
- 
+            "model": "llama3-8b